Activity
From 01/14/2016 to 02/12/2016
02/12/2016
- 11:29 PM Bug #14753: lokdep: uses lock name as the lock identity
- I don't think we want to change this by default. Locks that share the same name almost always have to follow the same...
- 11:19 PM Bug #14753 (Rejected): lokdep: uses lock name as the lock identity
- This is problematic if having multiple lock instances that share the same name.
- 10:51 PM Revision 5542c6e5 (ceph): Merge pull request #7634 from ceph/rgw-nfs-5
- nfs for rgw (Matt Benjamin, Orit Wasserman)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 10:35 PM Revision 892c1448 (ceph): Objecter: detect laggy ops with objecter_timeout, not osd_timeout
- Fixes: 14750
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 10:16 PM Bug #14660: selinux denials during rbd test run
- Boris,
you can ignore the unlabeled in the above logs for now, I will run this on non vm' system to check what pat... - 10:04 PM Revision a7d4e424 (ceph): rgw: Drop unused usage_exit from rgw_admin.cc
- Signed-off-by: Pete Zaitcev <zaitcev@redhat.com>
- 10:03 PM Revision 00d396e3 (ceph): rgw: don't use s->bucket for metadata api path entry
- Fixes #14549
s->bucket is only initialized at the object store handler (post auth
callback). We don't want to initia... - 09:03 PM Revision 447c8061 (ceph): rgw: adjust interfaces following rebase
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:03 PM Revision 865c76c3 (ceph): rgw: add drain_all() after collect() in sync crs
- this fixes a segfault caused by parent stacks completing while there are
child stacks outstanding
Signed-off-by: Cas... - 09:03 PM Revision 2d52ab31 (ceph): rgw: data sync env cleanup
- pass RGWDataSyncEnv container object instead of passing around multiple
params. (incomplete)
Signed-off-by: Yehuda S... - 09:03 PM Revision 7bbbec02 (ceph): rgw: add error_logger to sync env
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:03 PM Revision 0a0d437b (ceph): rgw: fail when trying to commit period if no master zone configured
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:03 PM Revision 9abb8e62 (ceph): rgw: more error handling
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:50 PM Revision caa73ba3 (ceph): os/filestore/FileJournal: simplify alignment asserts
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:45 PM Revision a8807641 (ceph): Merge pull request #7350 from ddiss/tracker14499_enotconn_rados_monitor...
- librados: check connection state in rados_monitor_log
Reviewed-by: Sage Weil <sage@redhat.com> - 08:40 PM Bug #14511 (Resolved): cache-flush-evict-all causes OSD stuck ops on unevictable objects
- 01:04 AM Bug #14511: cache-flush-evict-all causes OSD stuck ops on unevictable objects
- 08:40 PM Revision 56d3e94b (ceph): Merge pull request #7584 from ifed01/wip-14511
- osd: fix lack of object unblock when flush fails
Reviewed-by: Sage Weil <sage@redhat.com> - 08:39 PM Revision 50b45ccf (ceph): Merge pull request #7593 from ifed01/wip-no-blockedpromote-return-fix
- osd: fix return value from maybe_handle_cache_detail()
Reviewed-by: Sage Weil <sage@redhat.com> - 08:39 PM Revision bd17b5f4 (ceph): Merge pull request #7587 from cbodley/wip-pageset-align
- osd: memstore: fix alignment of Page for test_pageset
Reviewed-by: Dan Mick <dmick@redhat.com> - 08:38 PM Revision a00e8358 (ceph): Merge pull request #7595 from liewegas/wip-hobject-stringify
- osd: ghobject_t: use ! instead of @ as a separator
- 08:37 PM Revision 9be30dbe (ceph): Merge pull request #7596 from dachary/wip-erasure-code-corpus
- tests: sync ceph-erasure-code-corpus for mktemp -d
Reviewed-by: Sage Weil <sage@redhat.com> - 08:36 PM Revision eec65d03 (ceph): Merge pull request #7608 from liewegas/wip-warnings
- tests: fix a few build warnings
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:23 PM Revision 613457f9 (ceph): osd: consider high/low mode when putting agent to sleep
- If we are in low flush mode, we may only get up to max_low_ops in flight,
in which case we may never go to sleep here... - 08:22 PM Bug #14752 (Resolved): osd: agent can spin if in low flush mode and no evict work
- if there isn't evict work, we will only start the low flush max ops, but won't go to sleep if we're below the high li...
- 07:53 PM Revision c8048ce4 (ceph): os/filestore/FileJournal: set block size via config option
- We were setting the block_size as the MIN of the min size (4096) and the
block size reported for the journal file/dev... - 07:28 PM CephFS Bug #14684: test_scrub_checks fails
- http://pulpito.ceph.com/teuthology-2016-02-10_14:03:02-fs-jewel---basic-smithi/4160/...
- 07:05 PM Bug #14750: Objecter: do not mark OSD ops as laggy based on osd_timeout value
- https://github.com/ceph/ceph/pull/7629
- 06:58 PM Bug #14750 (Resolved): Objecter: do not mark OSD ops as laggy based on osd_timeout value
- We are currently looking at Objecter::osd_timeout when determining if OSD ops are laggy in Objecter::tick(). This hap...
- 07:00 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- John Spray wrote:
> The output is
> [...]
>
> (it's hard to see because it comes out at the point the command ac... - 01:35 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- aaaand here's why:...
- 01:30 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- The weirdness here is that the error is coming from os.write() rather than os.fsync().
The test expects that the c... - 01:24 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- The output is...
- 06:43 AM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- I'm confused — the log doesn't seem to include any of the output from the remote python script. Which makes me think ...
- 06:07 PM Revision cb9cfb72 (ceph): librgw: fix rpm packaging
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 06:07 PM Revision 85e4febb (ceph): librgw: fix new Debian control entries
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 06:07 PM Revision e18c6890 (ceph): librgw: remove junk files
- Files accidentally added.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 06:07 PM Revision 5f0fcdba (ceph): librgw: don't compare a string_ref with "" (use empty())
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 06:07 PM Revision 244ad79f (ceph): librgw: fix boost::basic_string_ref template instantiation
- The commit adding Seastar sstring.h replaced a part of the interface
which used an internal string-view type, with an... - 06:07 PM Revision de0f8669 (ceph): librgw: add debian and rpm packaging
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 06:07 PM Revision 2f706ef0 (ceph): librgw: consolidate S3 bucket name validation
- There is more cleanup potential here, but it is intrusive, as the
validators for bucket and object names have been fa... - 05:33 PM Revision 7496dd9f (ceph): Merge pull request #7626 from tchaikov/wip-fix-automake
- Makefile: workaround an automake bug for "make check"
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:08 PM Revision cfb8c81e (ceph): librgw: fix copyright in src/include/rados/rgw_file.h
- This file originated at Red Hat.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision 195185d4 (ceph): librgw: initialize RGWLib pointer members
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision a293c529 (ceph): librgw: remove slo, dlo, and supplied-md5 logic in RGWWriteRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision 3d7fa4f7 (ceph): librgw: remove RGWLibRequest "magic" numbers added for debugging
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision 303f5420 (ceph): librgw: comment rgw_nfs config_ops.h tunables
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision 48c0f5b4 (ceph): cohort_lru: remove #if 0 section
- The declaration being skipped was meant as a placeholder for future
optimization work, moved to a comment.
Signed-of... - 05:08 PM Revision 165079de (ceph): {rgw,common}/Makefile.am: add a few more missing .h files
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision acadd09b (ceph): common: add xxhash.h to Makefile.am
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision 47a5c0cf (ceph): rgw: fix null dereference
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision 1f6799df (ceph): librgw/rgw: fix librgw.la linkage
- Ensure that key symbols from global are satisfied in the library.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision c38e3cbb (ceph): librgw/rgw: reorganize autotools linkage
- Adds the RGW-NFS library to the radosgw build, with unit tests.
Adds -fPIC to compile flags to satisfy the linker, bu... - 05:08 PM Revision 269d90a4 (ceph): librgw: call obj_rec::sync() on dirs1_b
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision 77a40397 (ceph): librgw_file_nfsns: create readf_out_name, if needed
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision fa9cd660 (ceph): librgw: remove deprecated/unused librgw personality
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision 4b42c57b (ceph): librgw: properly detect RGWRados init failure
- Unit tests correctly see fail result from librgw_create.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision aa969585 (ceph): librgw: remove deprecated librgw methods
- Remove unused routines:
* librgw_acl_bin2xml
* librgw_free_xml
* librgw_acl_xml2bin
* librgw_free_bin(librgw_t r... - 05:08 PM Revision e43eb4d6 (ceph): librgw: temporary fix RGWWrite
- The current behavior of put_data_and_throttle leads to data
curruption, because the supplied buffer is apparently sti... - 05:08 PM Revision 8aa43781 (ceph): librgw: cleanup rgw_write
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:08 PM Revision 6b9b3d8f (ceph): librgw: add new rgw_write unit test
- WRITEF1 writes back data wread in READF1.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision 0eda995c (ceph): librgw: fix RGWReadRequest send_response_data
- In hindsight, it seems clear how to consume the available bytes and
account for the bytes written into the caller's b... - 05:08 PM Revision 06aff873 (ceph): librgw: add cross-bucket rgw_rename test
- It passes.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:08 PM Revision b35de479 (ceph): librgw: fix intra-bucket rename
- Avoid hopeless fail due to binding const::std::string& to a
temporary.
Signed-off-by: Matt Benjamin <mbenjamin@redha... - 05:08 PM Revision ca6e93bb (ceph): librgw: add support for rgw_rename tests
- Implements intra-bucket rgw_rename test, which unfortunately fails
currently.
Signed-off-by: Matt Benjamin <mbenjami... - 05:08 PM Revision 2e109ec3 (ceph): librgw: fix rgw_unlink and delete atomicity
- Move internal unlink logic into new RGWLibFS::unlink method, fix
logic for files and directories.
Use RGWFileHandle:... - 05:08 PM Revision ad3a22da (ceph): librgw: implement object rename
- The implementation uses currently does a copy, followed by a
delete operation (if successful).
Signed-off-by: Matt B... - 05:08 PM Revision 2a860f42 (ceph): librgw: fix timestamp on create (another case)
- In the rgw_create regular file case, the timestamp and size update
logic (though present) was being bypassed because ... - 05:08 PM Revision e68600be (ceph): librgw: cleanup, move 3 prints to log channel
- Save a pointer to CephContext in RGWProcess for use by logger--
using the existing pointer in ThreadPool would be an ... - 05:08 PM Revision 7ef64851 (ceph): librgw: add missing RGWFileHandle::stat in rgw_mkdir
- The lack of stat here induced a serious memory corruption, due to
the organization of Ganesha file attributes (and th... - 05:07 PM Revision 35445cf7 (ceph): librgw: fix leading-slash special case, again
- Fix boilerplate to sanitize relative_object_name() in rgw_create
as well as the RGWStatObjRequest case of RGWLibFS::s... - 05:07 PM Revision 4f8e7652 (ceph): librgw: disable name-cache lookups w/CREATE
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision b57f51bf (ceph): librgw: fix a prefix bug and bucket timestamp bug
- The fix for missing bucket.creation_time in RGWStatBucket is not
complete--we're not carrying all the info over.
Sig... - 05:07 PM Revision 998ed65d (ceph): librgw: ignore "/" as a common_prefix
- This happens commonly, apparently when a parent object name ends
with '/' (as all explicit directories do).
Signed-o... - 05:07 PM Revision 441bff73 (ceph): librgw: rgw_getattr refactor, RGWLibFS::stat_leaf (object)
- Rewrite rgw_getattr to just dispatch into RGWLibFS::getattr, where
we can better use RGWFileHandle and RGWLibFS inter... - 05:07 PM Revision ce62d805 (ceph): librgw: fix rgw_read, add unit test
- rgw_read had been trivially broken by the relative path change,
fixed.
Signed-off-by: Matt Benjamin <mbenjamin@redha... - 05:07 PM Revision 1b797a72 (ceph): librgw: add rgw_getattr tests
- Re-implement rgw_getattr to just dispatch into RGWFileHandle::stat,
we expect all objects to stat correctly for their... - 05:07 PM Revision 117208c7 (ceph): librgw: re-implement rgw_create
- rgw_create hadn't been re-implemented for NFS namespace behavior,
where we expect it to create empty file objects.
I... - 05:07 PM Revision ec924b66 (ceph): librgw: update rgw_* api calls so that all take a flags arg
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 4f2dd467 (ceph): librgw: normalize obj_rec::sync calls, fix signedness of refcnt asserts
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision a50416bc (ceph): librgw: partial getattrs/gc checks
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 402a76f2 (ceph): librgw: fix handle type in rgw_mkdir, finish dirs1 create tests
- Fixes handle type after rgw_mkdir.
Add handle type checks to nfsns unit tests. Adds tests to create
files and direc... - 05:07 PM Revision d18fe86b (ceph): librgw: set directory ctime and mtime
- Adds method to RGWStatBucketRequest to access the creation_time of
the returned bucket.
(For now, that's the only ti... - 05:07 PM Revision d8175918 (ceph): librgw: refactor nfsns dirs1 and fix a "bad unlink" case
- Fix the error returns from rgw_unlink. This is sufficient to
catch the errors that arise from operation failure.
We... - 05:07 PM Revision 558c2115 (ceph): librgw: incremental bucket-object 2-level tests
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 12fd3faa (ceph): librgw: enforce S3 object name restrictions
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 66b6b1fd (ceph): librgw: enforce S3 bucket name restrictions
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 54149b06 (ceph): librgw: FLAG_CREATE cleanup
- Split the transiently-creating concept (CREATING) from the request
to create objects used in lookup_fh.
Signed-off-b... - 05:07 PM Revision c1d1e15d (ceph): librgw: nfsns dirs1 delete, make hier1 conditional
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 41b2357a (ceph): librgw: incr. fix various nfs ops (REBASEME)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision b008fe52 (ceph): librgw: reorg SETUP_ENUMERATE test
- Stat nfsroot bucket, create it only if !exist && do_create.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:07 PM Revision b7730c0a (ceph): librgw: conditionally send '.' and '..' (rgw_readdir)
- Ganesha traditionally does not expect them, but they may be needed
when bypassing the MDCACHE (2.4).
Signed-off-by: ... - 05:07 PM Revision 5e75c183 (ceph): librgw: stop abusing parents
- Also make sure that root file handle has directory as its variant
type.
Signed-off-by: Matt Benjamin <mbenjamin@redh... - 05:07 PM Revision 7cc6a6db (ceph): librgw: likely correct marker handling
- New logic propagates is_truncated traveral-finished indicator up
from bucket and object list operations in all cases,... - 05:07 PM Revision 446d92c4 (ceph): librgw: is_truncated experiments
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision bd07c2ad (ceph): librgw nfsns: create/delete updates
- Add ability to delete marker objs, and create (but not yet delete)
nfs_hier objects.
Signed-off-by: Matt Benjamin <m... - 05:07 PM Revision adfb96a5 (ceph): librgw: don't early terminate readdirs (in progress)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 9a6944c7 (ceph): librgw: remove unused st
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 603f245e (ceph): librgw: split nfsns bucket and object create blocks
- Helps to see the respective timings.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:07 PM Revision 82aababc (ceph): librgw_file_nfsns: bugfix MARKER1_SETUP
- Successfully creates 5*1024 objects at /nfsroot/nfs_marker/, verifies
externally.
Follow-up rgw_readdir shows 999 re... - 05:07 PM Revision e6b3be3c (ceph): librgw: consolidate dup'd librgw, rgwlib
- There can be only one. Fixes crash on shutdown.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:07 PM Revision 103b9dde (ceph): librgw: remove search_prefix()
- Since it turns out this is a synonym for relative_object_name().
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:07 PM Revision 5b6af8a1 (ceph): incremental marker
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 80d5201a (ceph): librgw: omit always-false depth test.
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision bd4b9844 (ceph): librgw: rework full_object_name() and friends
- Flex RGWFileHandle::full_object_name() to build either a search
prefix (omits leading "/" and bucket name) or else th... - 05:07 PM Revision 41587210 (ceph): librgw: add continued readdir test
- Verify that files created in a single, large directory are correctly
enumerated through a sequence of rgw_readdir() c... - 05:07 PM Revision 1097ed4c (ceph): marker
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision a557c898 (ceph): Fix copyright statements on new test driver files (Red Hat, Inc.)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 597f69d9 (ceph): librgw: dir traversal state GC added
- To minimize overhead, traversal events are modeled as a linear
sequence of fh_key, timestamp tuples. GC operates out... - 05:07 PM Revision b970fd00 (ceph): librgw: restore readdir prints (move to dout)
- They are useful for checking the exact strings being produced,
and in which sequence (object or common prefix).
Sign... - 05:07 PM Revision 7acb20d8 (ceph): librgw: move readdir operations into RGWFileHandle::readdir
- The motivation here is to localize state updates to the class,
e.g., to hide consistency logic.
Signed-off-by: Matt ... - 05:07 PM Revision 453219cb (ceph): librgw: implement small-directory name cache
- Augment the existing marker cache with cache of name->type
mappings for up to 128 dirents (appx. 4x the common upper-... - 05:07 PM Revision e8fc2b75 (ceph): librgw: remote redundnat prints in RGWReaddirRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 49a034af (ceph): librgw: don't increment offset at rcb (it is no longer a counter)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision bd068089 (ceph): librgw: fill in dirent cache
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 33856c19 (ceph): librgw: implement framework for fs periodic work
- This can be used for, e.g., gc of stale handles and directory
traversals.
Signed-off-by: Matt Benjamin <mbenjamin@re... - 05:07 PM Revision 3237f0b9 (ceph): librgw: add intrusive refcnt to RGWLibFS
- Ensures that file system instances cannot be disposed while (e.g.)
background processing is ongoing.
Signed-off-by: ... - 05:07 PM Revision baffb146 (ceph): librgw: header and namespace reorganization
- Move RGWLibProcess and RGWLibFrontend into new rgw_lib_frontend.h
header, which can include rgw_lib.h and rgw_file.h.... - 05:07 PM Revision e448c4eb (ceph): librgw: use string_ref remove_prefix
- Save a few cycles over re-assigning a string_ref suffix substring
to itself.
Signed-off-by: Matt Benjamin <mbenjamin... - 05:07 PM Revision 8db2c6a9 (ceph): librgw: fix initialization of string_ref from temporary
- Found by valgrind. The good news: amounts to proof that the
sref notation works.
Signed-off-by: Matt Benjamin <mbe... - 05:07 PM Revision b19912c9 (ceph): cohort_lru: use correct new/delete operator pair
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision eaf15639 (ceph): librgw: move ObjUnref trace print ahead of...unref
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision 1f2ec092 (ceph): librgw: cleanup add_marker and handlers
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:07 PM Revision e6eee9fa (ceph): librgw: rename RGWGetObjRequest, RGWListBucketRequest
- The behavior of these requests is basically specific to the
needs of NFS READDIR and READ. (RGWWriteRequest already ... - 05:07 PM Revision ef6367fc (ceph): common: add (tweaked) sstring.h
- Add sstring.h from Seastar, slightly adapted for c++2011 and
boost::string_ref.
An sstring resembles std::string, bu... - 05:07 PM Revision 6147c3e5 (ceph): librgw: fix RGWLibFS::stat_leaf ex-ref
- Found verifying refcounts at RGWLibFS::close.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:06 PM Revision 9cf66708 (ceph): lirgw: call RGWLibFS::close in rgw_umount
- Also remove an unused warning in currently-disabled rgw_readv.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:06 PM Revision 562ebcbe (ceph): librgw: implement LRU lifecycle for handles
- This re-uses intrusive lane LRU and co-resident intrusive b-tree
for lookups (formerly, we were using just the dictio... - 05:06 PM Revision 066c2e8d (ceph): librgw: remove dead code (rgw_readdir)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 00571a51 (ceph): librgw: use correct finish path for RGWWriteRequest (logging and stats)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision e4b0c2be (ceph): librgw: update posix-style read path
- Update RGWGetObj to take ulp buffer rather than transferring the
elements of a buffer::list and re-traversing it.
Th... - 05:06 PM Revision 49a47d1d (ceph): librgw: set iov->iov_len to nread (get)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision ea51474a (ceph): librgw: sequential rgw_write works
- This commit finishes hooking up RGWWriteRequest, and its supporting
RGWLibContinuedRequest.
The rgw_read call now fa... - 05:06 PM Revision 5d9e395c (ceph): librgw: update mtime on write finish
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision e08b8d67 (ceph): librgw: -EISDIR
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 0090da6d (ceph): librgw: check variant type, fix reversed check for write trans
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 3b795c1c (ceph): librgw: finish write transactions in rgw_close path
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision a8f8c1a6 (ceph): librgw: block in RGWWriteRequest::exec_continue
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 6e630d69 (ceph): librgw: block in RGWWriteRequest::exec_start
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 1c722bbc (ceph): librgw: wire up more of continuation
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 80bac657 (ceph): librgw: dont forget to call exec_start
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 6b798deb (ceph): librgw: partial implementation of continued request framework
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision e3be0743 (ceph): librgw_file_aw: re-enable write sequence
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision a27a4070 (ceph): librgw: fix some incorrect uses of string temporary
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 5fe01703 (ceph): librgw: add initial atomic write unit test
- Tests are focused on open-write-close, open-read-close sequences.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:06 PM Revision 4e5aef61 (ceph): librgw: don't allow open on directories (externally)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision eb99b448 (ceph): librgw: restrict objects to single-open
- this is the simplest consistent model for an open-write-close
transaction (and it reads stable)
Signed-off-by: Matt ... - 05:06 PM Revision 57938d8c (ceph): librgw: fix last enumeration bug, move tracing to debug
- The last issue with enumeration was caused by inserting objects
into handle cache with their key-ified full_object_na... - 05:06 PM Revision a4207842 (ceph): librgw: fix and unify full-name assembly and hashing
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 46f82d7a (ceph): librgw: incremental listing fixes
- * remove path in RGWStatLeafRequest--use bool is_dir instead
* remove unused uri in RGWListBucketRequest
* more dbg p... - 05:06 PM Revision b83ac0d9 (ceph): librgw: incremental enumeration progress
- As of this change, enumeration is -almost- correct, but the
rules for name, object_name(), and full_object_name() nee... - 05:06 PM Revision 6dba6924 (ceph): librgw: remove unused string uri
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 589af39b (ceph): librgw: namespace bugfixes
- 1. stat_leaf() and stat_bucket() require RGWFileHandle::FLAG_CREATE
2. refactor RGWStatLeafRequest on the model of RG... - 05:06 PM Revision 821c562f (ceph): librgw_file_nfsns: stage namespace traversal (fails)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 27c9a360 (ceph): librgw: initial librgw_file_nfsns.cc test
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision ba82ff80 (ceph): librgw: add missing include deps (rgw_file.h)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 54dcf30c (ceph): librgw: fix parent chasing in make_fhk
- Avoid an...infinite loop.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:06 PM Revision f9173e89 (ceph): librgw: fix last-of marker detection
- Add the count of common_prefixes to the existing listing size, rather
than overwriting it, else size cannot be compar... - 05:06 PM Revision 4e9116ae (ceph): librgw: unify result cases in rgw_mkdir
- In both paths, instantiate a file handle iff the remote op
succeeded.
If this operation lost a race to create an obj... - 05:06 PM Revision 33539db7 (ceph): librgw: RGWListBucketRequest and related bugfixes
- 1. instantiate handles as required in RGWLibFS::stat_bucket
2. fix bucket_name() when bucket
3. fix full_object_name(... - 05:06 PM Revision e53eb38c (ceph): librgw: implement stat_bucket, call from rgw_lookup
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 21bf2776 (ceph): librgw: annotate unlink's rgw_lookup
- An rgw_lookup w/RGW_LOOKUP_FLAG_NONE will return an existing (hence
validated, modulo CREATE races) handle, but fail ... - 05:06 PM Revision b9f30657 (ceph): librgw: add lookup step in rgw_unlink
- Implement the required check for underlying leaf object, since with
the current signature it is not known.
(Is that ... - 05:06 PM Revision 1d17dcd9 (ceph): librgw: hide uri in RGWListBucketRequest, use full_objectname()
- Really would like to remove the requirement to format a URI for these
requests, since it is merely taken apart in par... - 05:06 PM Revision 06e2dad5 (ceph): librgw: add marker processing to RGWListBucket(s)Request
- Ignores object instances, for now. Not verified.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:06 PM Revision 6e70b6de (ceph): librgw: reimplement RGWLibFS::stat_leaf
- Now the code attempts to read an object header (which may be cached),
and if this fails, uses RGWStatLeafRequest to f... - 05:06 PM Revision 3ac44f91 (ceph): librgw: variant handle subtype and marker cache
- RGWFileHandle gets a type-specific variant part. For the directory
variant, define a flat_map of cookie to marker. ... - 05:06 PM Revision fcd43203 (ceph): librgw: create dir file handles w/correct type
- RGW objects which happen to represent directories will always end
in '/', but the trailing slash will not be present ... - 05:06 PM Revision 103eda1c (ceph): librgw: implement RGWLibFS::stat_leaf
- Stats one of <object>, <object/>. Additional control over handle
creation has been added to RGWLibFS::lookup_fh.
S... - 05:06 PM Revision 5725721f (ceph): librgw: incr rework stat
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 37810275 (ceph): librgw: fix uninitialized rgw_fh
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 196ef769 (ceph): cohort_lru: fix a maybe uninitialized warning (that seems invalid)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 4a23f4c0 (ceph): librgw: create explicit directory leaf objects in rgw_mkdir
- There is some asymmetry here, since directories are also inferred
from object names containing embedded "/."
The obv... - 05:06 PM Revision b94b51f9 (ceph): librgw: consolidate RGWLib RGWOps into RGWRequest
- The intermediate derivation mirrored that in RGWRest, but we
don't seem to need it.
Signed-off-by: Matt Benjamin <mb... - 05:06 PM Revision 42fc51a4 (ceph): librgw: don't discard lookup result, fix signedness of min_size
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 13bc25a1 (ceph): librgw: make_fhk put base name, object_name in wrong order
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 3e6e4ed2 (ceph): librgw: add pseudo() accessor
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision fc505f4a (ceph): librgw: add pseudofs awareness to lookup_fh
- And then allow rgw_mkdir() to create pseudofs vnodes, when parent
is not the root.
Signed-off-by: Matt Benjamin <mbe... - 05:06 PM Revision 33ee6d27 (ceph): librgw: make_fhk, compute object hashes path-wise
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:06 PM Revision 6691da04 (ceph): librgw: add depth and make_path to RGWFileHandle
- This just (mostly) efficiently builds a full path from its segments
on demand.
Signed-off-by: Matt Benjamin <mbenjam... - 05:06 PM Revision 443e9c9c (ceph): librgw: compress RGWFileHandle stat data
- Just save the state we actually mutate, and fill stat structures
on demand.
Signed-off-by: Matt Benjamin <mbenjamin@... - 05:06 PM Revision cfc7a4f5 (ceph): librgw: fix abuse of std::string& in RGWDeleteObjRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 80c85738 (ceph): librgw: fix rgw_unlink
- Fix handling of bucket namespace, remove bogus RGWLibFS::is_root()
logic. Also remove a stray debug check.
Signed-o... - 05:05 PM Revision fbfafb3e (ceph): librgw: ok, make RGW vnodes cache Unix attrs
- Ganesa ULP needs to see a sane progression of attrs in the CREATE
path.
With this change shell actions like
$ echo ... - 05:05 PM Revision 5f4ef7ed (ceph): librgw: forge Unix attrs in rgw_create
- Possibly RGW vnodes should cache Unix attrs, it would reduce the
latency of (frequent) getattr calls, and eventually ... - 05:05 PM Revision c480472f (ceph): librgw: fix Unix file modes
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 4fd6511c (ceph): librgw: implement rgw_create + bugfixes
- Incremental work to support CREATE,OPEN,WRITE*,CLOSE transactions.
Adds a new tuple-based signature for RGWFileHandle... - 05:05 PM Revision 6db1f9dd (ceph): librgw: fix size computation in RGWStatObjRequest
- Overrides RGWGetObj::execute(), calls the parent method and then
saves obj_size from the manifest.
Signed-off-by: Ma... - 05:05 PM Revision bf6bee61 (ceph): librgw: fix many rgw_file return codes
- This should all be -(POSIX), or at any rate negative.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:05 PM Revision 66823a06 (ceph): librgw: don't abuse fs_private
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 857aa1e3 (ceph): librgw: introduce RGW_LOOKUP_FLAG_CREATE
- The current API relies on rgw_lookup and rgw_lookup_filehandle to
return file handle instances, and like POSIX, needs... - 05:05 PM Revision 7f482c05 (ceph): librgw: add getattr unit tests, restructure
- The fids1, fids2 vectors were confusing, as fids2 mapped the
objects in the union of all buckets.
Now there's a matr... - 05:05 PM Revision 3c94a95b (ceph): librgw: handle a 3 cases in rgw_getattr
- Only the object case is mostly correct.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:05 PM Revision 885a603a (ceph): librgw: handle rgw_lookup in the root (minimally)
- In addition, check real return code from RGWStatRequest.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:05 PM Revision fd8f20e8 (ceph): librgw: change validity check for rgw_lookup
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 71590b8b (ceph): librgw: add RGWStatObjRequest and use it
- * implement a stat operation over RGWGetObj (returning early)
* use stat to validate rgw_lookup
* use stat to impleme... - 05:05 PM Revision 0e5f5e2b (ceph): librgw: add diagnostic dump_buckets() call.
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision a5e6d559 (ceph): librgw: fail RGWLibFS::authorize() on user-by-id lookup failure
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 0175a3d3 (ceph): librgw: implement rgw_vfsstat
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 74e4c5ab (ceph): librgw: rgw_mkdir and rgw_create return addresses
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 507ecab9 (ceph): librgw: pass struct rgw_fh_hk by reference
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 056c0cb8 (ceph): librgw: always add struct before rgw_file_handle in rgw_file.h
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 8417a788 (ceph): librgw: bring back lookup_handle()
- Now as a member of RGWLibFS, and exposed via rgw_lookup_handle()
for use by library clients.
Signed-off-by: Matt Ben... - 05:05 PM Revision 455d9d5c (ceph): librgw_file_gp: check test state before closing null fh handle
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 9821d6fb (ceph): librgw: implement intrusive filehandle cache
- The cache is keyed on a hash of bucket name, plus a hash of the
object name.
Signed-off-by: Matt Benjamin <mbenjamin... - 05:05 PM Revision d6e171a7 (ceph): librgw: add common/cohort_lru.h
- This a cache-line-friendly set of primitives for
a) shareded, intrusive maps based on boost::intrusive
b) an LRU sys... - 05:05 PM Revision e1b4fc7e (ceph): librgw_file: release file handles
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 73b19a91 (ceph): librgw_file_gp: don't leak a buffer::list
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision ab377b18 (ceph): librgw: checksum verify writev/readv read-after-write
- The changes to GET_OBJECT and PUT_OBJECT test options are needed,
since they are (re) writing the same object.
Sadly... - 05:05 PM Revision b9137e47 (ceph): librgw: really make hexdump optional, set resid in readv unit test
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 5e0b6e4d (ceph): librgw: fix 2 dout problems
- * rgw_file.cc needed to include include/assert.h AFTER all rgw
includes, for some reason
* use *_dout syntax as ta... - 05:05 PM Revision 5139c312 (ceph): librgw: try-implement rgw_readv/rgw_writev
- The model in the rgw_readv call is the caller owns the struct rgw_uio,
and uses it to pass uio_offset.
The caller re... - 05:05 PM Revision 540ce769 (ceph): librgw: improve rgw_write and add WRITE_READ_VERIFY
- Update rgw_write to return bytes written as an OUT argument,
use and verify in PUT test.
A new WRITE_READ_VERIFY tes... - 05:05 PM Revision 421f5ecc (ceph): librgw: remove junk prints
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 50abb8cb (ceph): librgw: set RGWGetObj::get_data = true, for great justice
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 290b06a9 (ceph): librgw: rework library CephContext* and init
- Remove duplicated init step. Just reference the global
Ceph context for the library instance(s).
The immediate effe... - 05:05 PM Revision 72fb1ad6 (ceph): librgw: dispatch RGWDeleteRequest in object branch in rgw_unlink().
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 88c2d028 (ceph): librgw: implement RGWGetObjRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision b6521266 (ceph): librgw: declare RGWDeleteObjRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 0ec522bc (ceph): librgw: declare RGWGetObjRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 21e6ff37 (ceph): librgw: fix RGWPutObj s->content_length
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 24da131d (ceph): RGWPutObjRequest: fix get_data()
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision b3150b0f (ceph): rgw log: disambiguate 'Read AccessControlPolicy' (logs)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision c352d4b2 (ceph): librgw: add --prelist to gp to prime cache
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 7f981b10 (ceph): librgw: fix rgw_open param names and invocation
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 9429cb13 (ceph): librgw: avoid illegal rele()
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision ec89aafd (ceph): librgw: don't create/delete in librgw_file.cc (unit test)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision adcba208 (ceph): librgw: fs->root_fh is a pointer (and assign it)
- Assign and expose the expanded root_fh indirectly from the mounted
root filesystem structure.
Signed-off-by: Matt Be... - 05:05 PM Revision 522c9588 (ceph): librgw: bucket names can be const
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision e562357b (ceph): librgw: reify root handles
- Reify root handle, remove traces of legacy (counter) handles.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:05 PM Revision 1e7539be (ceph): librgw: incremental RGWPutObj work and almost-complete RGWFH refactor.
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision a50bc13d (ceph): xxHash: build internally
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 1254f34f (ceph): librgw: add ZPage/ZPageSet abstraction (gp unit tests)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision 020aee93 (ceph): xxHash: add as submodule
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision fc0a895a (ceph): librgw: rgw_file_handle refactor, plus get/put
- Implement encapsulation of RGWFileHandle in rgw_file_handle,
so return these from rgw_lookup(), add new rgw_fh_rele()... - 05:05 PM Revision 03b66159 (ceph): librgw: add options for bucket name, multi create, delete
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:05 PM Revision abcec540 (ceph): librgw: fix acl assignment in RGWCreateBucket_OS_Lib
- The logic to create a default S3 policy in
RGWCreateBucket_OS_Lib::get_params() was essentially correct, but
failed t... - 05:04 PM Revision 29942221 (ceph): librgw: don't fake hostname (real hostname isn't used yet)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:04 PM Revision cca325e1 (ceph): librgw: don't allow running rgwfile tests as anon
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:04 PM Revision 3fcdd946 (ceph): librgw: partial delete/unlink support
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:04 PM Revision 9fb454ac (ceph): librgw: return result code from execute_request
- Update rgw_mkdir and rgw_readdir to use it.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:04 PM Revision c43384c0 (ceph): librgw: fix uri, read_permissions virtual for create-bucket
- * set uri in rgw_mkdir (duh)
* RGWCreateBucketRequest should override RGWHandler::read_permissions
to return 0
Sig... - 05:04 PM Revision 460794ef (ceph): librgw: block in create bucket, rgw_mkdir
- Unit test runs, doesn't...seem to create a bucket.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:04 PM Revision ceb2b0e9 (ceph): librgw: re-derive rgw_os_lib family
- * shorten names to match files
* remove derivation through rgw_rest intermediates
Signed-off-by: Matt Benjamin <mben... - 05:04 PM Revision 83bed47f (ceph): librgw: s/rgw_rest_lib.{h,cc}/rgw_os_lib.{h,cc}
- There is no longer an explicit (e.g., inherited) dependency on REST
implementations.
The remaining coupling (via RGW... - 05:04 PM Revision cbcb641e (ceph): lirgw: call RGWHanlder_Lib::init_from_header
- Call this from the general RGWLibRequest init() method, after
descendant header_init() has run.
Signed-off-by: Matt ... - 05:04 PM Revision 6dae209c (ceph): librgw: cleanups, incremental ListBuckets fixes
- 1. remove unused RGWLibRequestEnv code marked to delete
2. restore call to RGWHandler::authorize
3. provide RGWLibReq... - 05:04 PM Revision e2956295 (ceph): librgw: forward cmdline args to librgw_create
- Verified w/-d.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:04 PM Revision 55bb8d34 (ceph): librgw: remove disabled RGWLib RGWREST::get_handler()
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:04 PM Revision ed7dc88e (ceph): librgw: cleanups in process_request
- * remove disabled S3 authorize step (user authorized on mount)
* re-enable op->verify_permission()
Skipping the latt... - 05:04 PM Revision ec96809c (ceph): librgw: pull RGWUserinfo user into RGWLibRequest
- Also, return result from process_request(req, io) to caller.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:04 PM Revision 7e21e238 (ceph): librgw: cache RGWUserInfo in rgw_fs private handle
- The private RGWLibFS type holds a RGWUserInfo, and
calls rgw_get_user_info_by_access_key and verifies the returned
se... - 05:04 PM Revision 6688bc1c (ceph): librgw: split RGWUserInfo from struct req_state
- The immediate purpose is to permit auth caching in RGWLib, but
it seems likely that this will be useful for general r... - 05:04 PM Revision 290e7881 (ceph): librgw: RGWFileHandle and RGWLibFS
- Experimentally reframe the C interface objects as subobjects in
private internal types.
Signed-off-by: Matt Benjamin... - 05:04 PM Revision f9382815 (ceph): librgw: fixes for RGWListBucketRequest callback
- The cached req_state is still not correct at RGWOp::execute().
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 05:04 PM Revision 9c4de578 (ceph): librgw: untested RGWLibListBucketsRequest and caller.
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:04 PM Revision 80a56f20 (ceph): librgw: fix 2 bugs in RGWListBuckets, remove scaffolding
- 1. the prior commit had authorize cognate with S3
1.1 which may be right
1.2 but maybe not for each request
1.3 and l... - 05:04 PM Revision c44f19c4 (ceph): librgw: process_request prologue fixups
- * initialize RGWEnv with required HTTP_HOST (incorrectly!)
* assign req_state::cio (not really correctly)
* remove in... - 05:04 PM Revision 0b614a1b (ceph): librgw: reprocess process_request
- Refactor RGWLib variant of process_request(...) as a (actually 2,
one which puts an RGWLibIO on the stack) member fun... - 05:04 PM Revision 143bd14f (ceph): librgw: wire up RGWLibFrontend enqueue and exec operations
- Adds the missing bits of RGWLibProcess and RGWLibFrontend, and
calls them from rgw_readdir().
Clients can call enque... - 05:04 PM Revision 84fd9aa8 (ceph): librgw: remove RGWLibRequestEnv
- The REST cognates of this class largely deal with HTTP, and is 1-1
w/request, client-io, op, etc. At worst, its func... - 05:04 PM Revision 48671485 (ceph): librgw: wire up request initializers
- There's some tricky overloading induced by multiple inheritance,
also this design makes repeatedly shared handles in ... - 05:04 PM Revision 259be80c (ceph): librgw: re-derive RGWLibRequest
- Derive RGWLibRequest from RGWRequest, RGWHandler.
This strategy defines the dialect of ops following the derivation
... - 05:04 PM Revision d1d4535d (ceph): librgw: rename RGWHandler_REST_Lib (sic), inherit from RGWHandler
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:04 PM Revision ac379419 (ceph): librgw: remove dead code, add comments in RGWLib
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 05:02 PM Revision 4af5aeac (ceph): librgw: refactor RGWHandler HTTP/REST methods into _REST
- This change renames RGWHandler_ObjStore to RGWHandler_REST, and
moves the following protected, virtual, RESTful metho... - 04:58 PM Revision bf104629 (ceph): librgw: call rcb in RGWListBucketsRequest operator()
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:58 PM Revision 748a6e56 (ceph): librgw: add user_id to RGWListBucketsRequest
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:58 PM Revision adade479 (ceph): librgw: header inclusion fix, actually call callbacks
- Fix public header inclusion from rgw_file.h internal header, which
of course needs to see the public interface.
Fini... - 04:58 PM Revision 85087300 (ceph): librgw: incremental
- * move RGWLibRequest decls into rgw_file.h
* revise include guard token in rados/rgw_file.h (avoid conflict)
* save C... - 04:58 PM Revision 987821c7 (ceph): librgw: s/gen_request/enqueue_req/;
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:58 PM Revision 9d6c78ff (ceph): librgw: replace RGWHandler::put_op() in RGWLib path
- The method just called delete on the RGWOp pointer.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 04:58 PM Revision ab2349c4 (ceph): librgw: move authorize() and read_permissions()
- all RGW_Auth_S3::authorize() from process_request(). Add a
read_permissions() primitive replacing RGWHandler's versi... - 04:58 PM Revision 7e8ecc58 (ceph): librgw: pre-assign req->op (as self), avoid dynamic_cast
- It would be nice to have some compile-type assistance w/the
dual RGWOp & RGWLibRequest boilerplate.
Signed-off-by: M... - 04:58 PM Revision f4994c84 (ceph): librgw: breakthrough cleanups (I think)
- * RGWLib bucket ops prototyped
* progress made on RGWOp+RGWRequest unification (RGWLib only)
* mostly-harmlessness of... - 04:58 PM Revision f1720d88 (ceph): librgw: incremental rgw_rest_lib internals
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:58 PM Revision 35a5e501 (ceph): librgw: include rgw_lib.h from rgw_rest.cc
- RGWLibIO is forward declared in rgw_rest.h.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 04:58 PM Revision 5cc096d0 (ceph): librgw: tweaks to RGWREST::preprocess and fix a typo in RGWHandler_ObjS...
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:58 PM Revision df8f3920 (ceph): refactor RGWClientIO
- In order to support direct/library clients, we want to
more fully decouple RGWOp processing from client HTTP
processi... - 04:57 PM Revision 79d3879c (ceph): librgw: comments
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision 2903d754 (ceph): librgw: widen rgw_mount, open-code list buckets
- Widen rgw_mount(...) to take the library context, which from
there on follows struct rgw_fs.
Implement an open-coded... - 04:57 PM Revision a719a0bd (ceph): librgw: add LOOKUP_BUCKETS and LIST_OBJECTS
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision f6a95fc1 (ceph): librgw: add list bucket test
- The operation on store is missing, but interface works.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 04:57 PM Revision 5521c7ab (ceph): librgw: test rgw_(u)mount(...)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision 84e21660 (ceph): librgw: take keys in test
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision 9eeba4fb (ceph): librgw: fe::init must create RGWLibProcess
- All evidence suggests RGWLibFrontend::init needs to create
an RGWLibProcess, and assign to pprocess.
Signed-off-by: ... - 04:57 PM Revision d1bbfe94 (ceph): librgw: introduce struct rgw_fs
- Pretending for a moment that we can definitely use the "mount"
based model, rgw_file like libcephfs requires a contex... - 04:57 PM Revision fae842d2 (ceph): librgw: remove classes from extern, argv
- Remove class definitions from extern "C" block, which was
illogical.
Block in support for passing a C-style argument... - 04:57 PM Revision eb2ac51c (ceph): librgw: fix type of rgw_readdir eof argument (C-11 bool)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision 2035fcc1 (ceph): librgw: revise rgw_* method signatures
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision e7d0300c (ceph): librgw: update rgw_rename signature
- Currently unimplemented.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 04:57 PM Revision 8fb8f002 (ceph): librgw: define an rgw_setattr
- Currently, this operation has no effect. It may be unsafe to
assume that NFS clients can tolerate errors or inconsis... - 04:57 PM Revision 763f434b (ceph): librgw: make rgw_readdir take a bool* for eof
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision 5dd73b91 (ceph): librgw: update rgw_readdir interface (stub impl)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision c4262b29 (ceph): librgw: add hypothetical rgw_statfs call
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision c81b85d2 (ceph): librgw: stub implement rgw_getattr
- This method returns Unix attributes for an object, represented
by an rgw_file_handle.
Signed-off-by: Matt Benjamin <... - 04:57 PM Revision 27e066de (ceph): librgw: add a library version (1.0.0)
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:57 PM Revision c52a9fad (ceph): librgw: rgw shared library
- Refactor rgw_a and radosgw_srcs, and add librgw_srcs, permitting
librgw to contain a smaller subset of objects, and i... - 04:56 PM Revision ce5ba5d6 (ceph): librgw: compile and implement more of rgw_file
- The rgw_file body wasn't being built, so had some impossible
constructs. More had been added by the commit which ren... - 04:56 PM Revision e7696554 (ceph): librgw: the external type of librgw_t must be void*
- The C interface cannot contain a C++ forward declaration of
class CephContext.
Signed-off-by: Matt Benjamin <mbenjam... - 04:55 PM Revision f23cd03b (ceph): librgw: install librgw.h
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 04:55 PM Revision 3f603007 (ceph): librgw: s/nfs_file_handle/rgw_file_handle/;
- The interface is in rgw_file.h, so make it match.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 04:55 PM Revision 98309417 (ceph): rgw_file.h: preserve cosnt correctness
- /s
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 04:55 PM Revision 2aa79deb (ceph): librgw: fix some return warnings (and cosmetic)
- Fix return codes for several exported functions in the rgw_file
interface.
Fix spacing and pointer, reference type n... - 04:55 PM Revision 08b89a5f (ceph): rgw: introduce libradosgw
- This change exposes the radosgw service as a dynamic
library, and also introduces a file-oriented view of the
RGW cor... - 04:54 PM Revision 76f1dcaf (ceph): rgw: refactor rgw_main
- This change is an extended version of work by Orit Wasserman
moving some request-processing class headers and definit... - 04:10 PM Revision b709f7ce (ceph): Merge pull request #7351 from fmeppo/master
- Add --setuser and --setgroup options for ceph-disk
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:58 PM Bug #14723 (Fix Under Review): make check bot broken: execvp: /bin/sh: Argument list too long
- https://github.com/ceph/ceph/pull/7626
- 03:47 PM Bug #14723 (In Progress): make check bot broken: execvp: /bin/sh: Argument list too long
- 03:21 PM Bug #14723: make check bot broken: execvp: /bin/sh: Argument list too long
- turns out, @MAKEFILE_LIST@ is too long to be passed as a parameter for sh...
- 01:11 PM Bug #14723: make check bot broken: execvp: /bin/sh: Argument list too long
- https://jenkins.ceph.com/job/ceph-pull-requests/1378/consoleFull
- 03:56 PM Revision 19391b71 (ceph): Makefile: workaround an automake bug for "make check"
- override the automake variable of am__is_gnu_make. it is a workaround
for http://debbugs.gnu.org/cgi/bugreport.cgi?bu... - 02:11 PM CephFS Bug #14735 (Pending Backport): ceph-fuse does not mount at boot on Debian Jessie
- 01:40 PM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
- Nathan Cutler wrote:
> Should this be backported to Infernalis?
Yes, please. - 01:31 PM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
- Should this be backported to Infernalis?
- 01:47 PM Bug #14748 (Pending Backport): OSD coredumps with leveldb compact on mount = true
- 01:01 PM Bug #14748: OSD coredumps with leveldb compact on mount = true
- Seems this was fixed in master by https://github.com/ceph/ceph/pull/4372, still waiting for a backport to hammer, tho...
- 12:56 PM Bug #14748 (Resolved): OSD coredumps with leveldb compact on mount = true
- ...
- 01:42 PM Backport #14746 (In Progress): infernalis: systemd escaping of block devices in ceph-disk incorrect
- 05:46 AM Backport #14746 (Rejected): infernalis: systemd escaping of block devices in ceph-disk incorrect
- https://github.com/ceph/ceph/pull/7624
- 01:37 PM rbd Bug #14373 (Resolved): Cannot reliably create snapshot after freezing QEMU IO
- 01:37 PM rbd Bug #14030 (Resolved): rbd merge-diff doesn't properly handle >2GB diffs
- 01:35 PM rbd Bug #13491 (Resolved): misdirected op in rbd balance-reads test
- 01:25 PM Revision 153f7190 (ceph): msg/async: set MSG_MORE intelligently
- In write_message, set "more" flag according to ack queue, if there are
messages to acknowledge, set it. Unset it othe... - 01:25 PM Revision a07aea6d (ceph): msg/async: delay bufferlist construction
- We're using this bl only when removing *some* of data in front of
outcoming_bl, so there's no need to construct it ea... - 12:17 PM Revision 7d804cfa (ceph): osd/ReplicatedPG: fix whitespace
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:17 PM Revision bab48c2c (ceph): ceph_test_rados_api_tier: verify class op forces promotion
- A class op should force a promotion to the base tier. If it
doesn't, well get EOPNOSUPP from the base EC tier, which... - 12:17 PM Revision a0858a58 (ceph): osd/ReplicatedPG: respect must_promote in READFORWARD and READPROXY
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:17 PM Revision 7dbce5ba (ceph): osd/ReplicatedPG: respect must_promote in WRITEBACK cache mode
- Force a promotion of the op requires it. This bug was easily masked
because the defaultish cache parameters would of... - 11:59 AM Revision fb727143 (ceph): Merge pull request #7605 from dachary/wip-python-wheelhouse
- python: use pip instead of python setup.py
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:10 AM Revision c1d8faad (ceph): python: use pip instead of python setup.py
- python setup.py develop may try to pull dependencies from the net and
has no way to collect them from the wheelhouse ... - 10:10 AM Revision cd87bd48 (ceph): ceph-disk,ceph-detect-init: clean the build directory
- b030d8fc113736b479e84246b6b36d5f698a2da3 should have kept the build
directory in .gitignore and the clean target. Re-... - 10:00 AM Bug #14095: FreeBSD testsuite generates traps on os/FileJournal.cc:1043
- This error was gone until very recently when I again rebased.
Now it is back again.
Probably due to changes for the... - 06:58 AM CephFS Bug #14714 (Won't Fix): three jobs in samba suite failing for hammer v0.94.6 QE validation
- I'm not sure exactly what's going on here, but I'm pretty convinced it's a configuration issue not worth our time to ...
- 06:14 AM Revision 18e64820 (ceph): Merge pull request #7528 from objoo/YD-jewel-mailmap-updates-take2
- mailmap updates
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:54 AM Bug #14747 (Resolved): test_bit_vector.cc uses magic numbers against #defines that vary
- test_bit_vector's partial_decode_encode test allocates a 9161-element bit vector, and then tests with ranges based on...
- 05:42 AM rbd Backport #14610 (Resolved): infernalis: Flattening an rbd image with a running Qemu instances cau...
- 05:38 AM rbd Backport #14610 (In Progress): infernalis: Flattening an rbd image with a running Qemu instances ...
- 05:40 AM rbd Backport #14062 (Resolved): infernalis: rbd merge-diff doesn't properly handle >2GB diffs
- 05:38 AM rbd Backport #14062 (In Progress): infernalis: rbd merge-diff doesn't properly handle >2GB diffs
- 05:40 AM rbd Backport #14542 (Resolved): infernalis: Cannot reliably create snapshot after freezing QEMU IO
- 05:38 AM rbd Backport #14542 (In Progress): infernalis: Cannot reliably create snapshot after freezing QEMU IO
- 05:36 AM rbd Backport #13733 (Resolved): misdirected op in rbd balance-reads test
- 05:10 AM Revision a2888e0a (ceph): Merge pull request #7609 from dillaman/wip-librbd-flatten-test
- test: new librbd flatten test case
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:09 AM Revision bc22c0f3 (ceph): Merge pull request #7583 from dillaman/wip-librbd-journal-fsx
- librbd: integrate journal replay with fsx testing
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:07 AM Bug #14745: osd: call doesn't force promotion from ec base tier
- https://github.com/ceph/ceph/pull/7617
- 01:05 AM Bug #14745 (Resolved): osd: call doesn't force promotion from ec base tier
- reproduce with:...
- 01:01 AM Revision f88c8522 (ceph): rgw: Fix subuser harder with tenants
- We have several ways to set the tenant and user in the operation
state now:
radosgw-admin --uid=user <command> # de... - 12:17 AM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
- Nope, that's not it directly, we only propagate one at a time thanks to Journaler::handle_write_error().
This is a... - 12:13 AM Revision b2f7438d (ceph): rgw: fix create_default to handle EEXIST
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 5c2b519d (ceph): rgw: fix do_curl_wait() if curl_multi_wait() not defined
- needed for older systems
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 7a78b0ef (ceph): rgw: replace #warning with a comment
- not going to fix it now
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 744f3844 (ceph): rgw: add a timelog add operation cr
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 22faa002 (ceph): rgw: link_pending_requests() fixes
- set aside the list of reqs we need to finish, and only then iterate
through that list and finish. Otherwise we corrup... - 12:13 AM Revision fd46b2d9 (ceph): rgw: hold reference to req_completion while calling aio_operate()
- This is a workaround to fix issue with aio_operate() racing with the
request completion. This way we make sure comple... - 12:13 AM Revision 33489473 (ceph): rgw: use exclusive flag for store_name in RGWSystemMetaObj::create
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 67fccabc (ceph): radosgw-admin: realm pull should not fail if the realm exists
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 4342bd6b (ceph): rgw: add error messages to realm::create
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2360e165 (ceph): rgw: fix RGWSystemMetaObj::init to handle perdefined name correctly
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 79d6952f (ceph): rgw: metadata and data sync share RGWAsyncRadosProcessor
- each RGWAsyncRadosProcessor creates 32 worker threads by default, so we
should only create one instance and share it ... - 12:13 AM Revision defb4d3f (ceph): rgw: shorten name of RGWAsyncRadosProcessor thread pool
- threads now call pthread_setname_np(), and have to enforce a
16-character limit on the names. this fixes the assertio... - 12:13 AM Revision 45c53277 (ceph): rgw: safe disposal of async processors
- the async processor might out its container cr, need to refcount.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision b243075a (ceph): rgw: fix a few more leaks
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 847ec960 (ceph): radosgw-admin: add missing break in key rm command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 51eb2fad (ceph): rgw: in create_default read zone_params in case we raced with another
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 0ce5bc5a (ceph): rgw: fix a typo
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision ee9f2065 (ceph): rgw: more of dropping async ops reference
- instead of deleting. This was missing from a previous commit.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision d52bf638 (ceph): rgw: forward meta changes to master
- (initial work)
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 9ffa3e20 (ceph): rgw: fix a few leaks
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 46f1ee54 (ceph): rgw: more leak fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 9e2569e2 (ceph): rgw: clear stack ops when unwinding last op
- So that we don't drop the last one's reference twice
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 5363017e (ceph): rgw: reorder RGWRados shutdown
- dependency order fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 47db646f (ceph): rgw: minor cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision efc2dfcc (ceph): rgw: more leak fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8bcdb77d (ceph): rgw: stop meta sync handler when going down
- it needed to check internally whether it was going down
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision e53fbe31 (ceph): rgw: split RGWPeriod::reflect out of set_latest_epoch
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 60c9798b (ceph): rgw: add exclusive param to RGWPeriod::set_latest_epoch
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision d89d2247 (ceph): rgw: add RGWPeriodPuller for RGWPeriodHistory
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision f420bd2a (ceph): rgw: add period history and puller to RGWRados
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 71dd4085 (ceph): rgw: 'period push' handler uses RGWPeriodHistory
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision b0630d50 (ceph): rocksdb: set to master
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 813c021f (ceph): rgw: update datalog also when unlinking object instance
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 426e3fc4 (ceph): rgw: period commit updates sync status before writing the object
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision b72530bc (ceph): rgw: start pushing current period on startup
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 423719ba (ceph): rgw: RGWRealm::set_current_period takes RGWPeriod
- set_current_period() doesn't need to set the predecessor;
RGWPeriod::commit() takes care of that
Signed-off-by: Case... - 12:13 AM Revision b37739a2 (ceph): rgw: add realm epoch to RGWRealm and RGWPeriod
- RGWRealm::epoch is incremented on each new period, and
RGWPeriod::realm_epoch tracks the realm epoch when it was crea... - 12:13 AM Revision 1ee26eda (ceph): rgw: use realm epoch to choose most recent period to push
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 7469fc28 (ceph): rgw: fix documentation of RGWRealmWatcher
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 470595b0 (ceph): rgw: RGWPeriodHistory to track period history
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 69c1d9f2 (ceph): rgw: data sync, handle delete marker removal
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8821d065 (ceph): rgw: init_zg_from_period() fixes
- Reported-by: fangchen sun <sunspot0105@gmail.com>
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 5e708a96 (ceph): rgw: fix RGWZoneGroup ctor and check period update return code
- Add more debug messages
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 12:13 AM Revision 0ef1fae4 (ceph): radosgw-admin: zonegroup set and zone set should set the realm id
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e911e14c (ceph): rgw: use refrence in read_clear_modified
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2d90f858 (ceph): rgw: 'realm pull' uses realm's current_period for do_period_pull
- instead of using period_id/period_epoch, which are radosgw-admin
arguments that are unused by 'realm pull', use the p... - 12:13 AM Revision 71797cdb (ceph): radosgw-admin: add mdlog and datalog status to help.t
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 18f6853d (ceph): rgw: set_date_header should use header_name
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d26ebb0a (ceph): rgw: update datalog when creating delete marker
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision c78cb250 (ceph): mrgw.sh: modify log file name
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision a104062d (ceph): cls/rgw: log owner, display name when creating delete marker
- In the case of delete marker, we need to log the owner and the owner
display name so that we can create it correctly ... - 12:13 AM Revision 850dd42c (ceph): rgw: handle delete marker when doing incremental data sync
- Still need to handle the full sync, and to make sure we apply it
only if-newer (as with the other data sync operation... - 12:13 AM Revision 5e93a686 (ceph): rgw: guard versioned object removal from circular sync
- check if marker instance already exists, only apply (and update bi log)
if does not exist. Propagate the versioning f... - 12:13 AM Revision c5990873 (ceph): rgw: some debug info
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 6476c4e7 (ceph): rgw: data sync, update high marker when skipping duplicate sync entries
- Need to update the high marker when skipping an entry, so that when the processing
entry finishes we set the markers ... - 12:13 AM Revision 6052d4b0 (ceph): test-rgw-call.sh: add missing file
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision d2e41e8f (ceph): rgw: store obj pg version in the object's head
- this is done atomically when object is written, will allow us
to determine whether object is newer or not.
Signed-of... - 12:13 AM Revision b50b3bb9 (ceph): rgw: keep pg ver on obj state, and send it in HEAD request
- send it in HEAD request if it was done by the system user
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision de129aaa (ceph): rgw: create a short (32bit) zone id, keep it on the period map
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b37503ab (ceph): rgw: keep source zone attr on head object
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b9da8db7 (ceph): rgw: fetch remote obj depends on zone id and pg ver
- This provides a consistent objects view on zones when changes happen on
the same objects at the same time. The zone i... - 12:13 AM Revision a38a3ae8 (ceph): rgw-admin: add datalog status command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 673abbe7 (ceph): test_multi: test object sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 7a25c639 (ceph): test_multi: buckets and objects comparison
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision fb3dd942 (ceph): rgw: clear 'null' object instance when fetching remote obj
- otherwise the objclass code will handle it as a versioned object
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision f9b94071 (ceph): rgw/test_multy.py: improve test_object_sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 21e108bb (ceph): rgw/test_multi.py: meta checkpoint uses zones, not clusters
- The unit we need to care about is the zone, not the cluster
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 0cc621c9 (ceph): rgw/test_multi.py: add log level for saner output
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 76807064 (ceph): test_multi.py: generate boto connection per zone
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 38cefb41 (ceph): test_multi.py: can run through python nose
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8b8f91a5 (ceph): tests_multi.py: test bucket creation, fix meta checkpoint
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision aa5de3b2 (ceph): rgw: test_multi: start radosgw with debug logs, asok
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision a2583c50 (ceph): rgw: meta sync, handle ENOENT, ECANCELED
- retry when canceled, continue when entry does not exist.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 671f3196 (ceph): test_multi: add more bucket related tests
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 61de0364 (ceph): rgw: clone mdlog updates marker in any case
- Need to set the new_marker even if no new entries fetched.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 0e9f2e44 (ceph): rgw: meta sync can remove entries
- and also skip non complete entries
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 22129ec0 (ceph): radosgw-admin: fix help.t
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 44d0d3f4 (ceph): test/rgw: more test work
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 99da3393 (ceph): test_multi.py: finer control for bringing up system
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 7fd15284 (ceph): test_multi.py: wait for meta sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 6f544074 (ceph): test_multi.py: generate random key
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 82b5f3ae (ceph): test_multi.py: move meta checkpoint inside, add configurables
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b170343a (ceph): test_python.py: call radosgw-admin with cache disabled where applicable
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision aee4e85e (ceph): test_multi.py: create a test user
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8d4fbc09 (ceph): test/rgw: wait for metadata sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b4193211 (ceph): radosgw-admin: use realm current period master_zonegroup as remote for ...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e206c022 (ceph): rgw: cleanup remove realm unused master_zonegroup and zonegroups
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 845bf22e (ceph): rgw: create_default cannot set as default
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 1827781a (ceph): rgw: default zonegroup per realm
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2ec85ef6 (ceph): rgw: default zone per realm
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision afc900bd (ceph): radosgw-admin: zone list should print default zone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 69a395f6 (ceph): rgw: remove error message from read_default
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 74fdef41 (ceph): rgw: bucket sync, don't drain_all() before shutting down lease cr
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b991ff70 (ceph): rgw: more log info on realm reloading
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 346343ed (ceph): rgw: http client lock related fix
- need to call _finish_request() under the lock.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 94bd292d (ceph): rgw: fix period pull of first epoch
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8f34600b (ceph): rgw: option to set realm, zonegroup, zone as default
- when modifying / creating the entity. This is in addition to the explicit
command.
Signed-off-by: Yehuda Sadeh <yehu... - 12:13 AM Revision 4571f729 (ceph): test/rgw: initial work on multi site test framework
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 673b28c3 (ceph): test/rgw: basic meta sync status test util
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 1105cff6 (ceph): rgw-admin: add mdlog status command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b91e4511 (ceph): rgw: reflect period when setting as current period
- reflect period into local objects when setting it as current.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 684d8130 (ceph): rgw: report error
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision d1d93860 (ceph): rgw: rearrange zonegroup and zone initialization
- move into helpers, don't keep distinct structures for zonegroup local and period
zonegroup, we end up using the one w... - 12:13 AM Revision e8f148ee (ceph): rgw: adding more reflection where needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 1975310d (ceph): rgw: make realm pull a raw storage operation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision f81eb8e5 (ceph): rgw: switch to local zonegroup config if zone is not found
- We might be just creating a zone that is not in the period config yet,
if we can't find it in period config switch to... - 12:13 AM Revision 36861353 (ceph): rgw: fix data sync notification
- should send zone id, not zone name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 4720662d (ceph): rgw: update bucket index marker before skipping entries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision dd490b67 (ceph): rgw: merge related fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 0b5cdc31 (ceph): rgw: take a lease before syncing bucket shard
- This is needed for having multiple rgws running on the same zone
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 5c96534a (ceph): rgw: data shard sync locking
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 6494347d (ceph): rgw: realm pull also pulls period
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b8dcb667 (ceph): rgw: avoid unneeded yield
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision b9fbe050 (ceph): rgw: keep track of how busy a cr stack is
- this can give indication about crs that aren't structured correctly.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 52486a96 (ceph): rgw: data sync, don't yield when spawning
- this enables us to filter out duplicate keys without worrying about races, since
spawned crs will only be executed on... - 12:13 AM Revision 8b9cd668 (ceph): rgw: forward bucket creation removal if it's not meta master
- We can be in the master zonegroup, but not the meta master -- in which case
we still need to forward the request to t... - 12:13 AM Revision f00585f0 (ceph): rgw: incremental sync, skip non-complete entries early
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 2108b2d1 (ceph): rgw: remove incorrect conn assignment
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 36e5ded2 (ceph): rgw: fix call to index_key_to_marker()
- was passing variables in the wrong order
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision e08eb9c1 (ceph): rgw: don't spawn multiple concurrent object sync for same object
- Either mark the current running operation to retry, or wait for it to finish
(if it's not doing the same operation).
... - 12:13 AM Revision 3b41d87f (ceph): rgw: create a unique zone pool names
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision efe8d9d4 (ceph): radosgw-admin: zone set add a check for zone name in json
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision eca0bb84 (ceph): rgw: use zonegroup id for location constrain
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9dccf6e4 (ceph): radosgw-admin: clean backward support for region in the cli
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 6a31379f (ceph): rgw: fix setting of rgw_zonegroup from rgw_region
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 706a194d (ceph): rgw: remove run context when finished running
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 44194c01 (ceph): rgw: keep status and history in coroutine
- will replace the report container stuff
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 637bd560 (ceph): rgw: remove sync reporting
- will use the cr reporting framework instead
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision fa5b36c9 (ceph): rgw: start annotating coroutines status and description
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 0efd1ff3 (ceph): rgw: more coroutines annotation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 67fa54fd (ceph): rgw: data sync, only use complete log entries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 94ad24ae (ceph): rgw: rework set_description(), set_status()
- make it easier to construct description, status info
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision d6597be6 (ceph): rgw: cancel index operation if delete got ENOENT
- Should mark the operation as canceled, so that sync followers don't try to
apply it.
Signed-off-by: Yehuda Sadeh <ye... - 12:13 AM Revision 968cc6b4 (ceph): rgw: start moving report into coroutines
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision d920dab8 (ceph): rgw: add locking to coroutines reporting
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 1e0ac526 (ceph): rgw: hook cr managers to admin socket
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 21eaefac (ceph): rgw: admin socket related fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 28308458 (ceph): radosgw-admin: allow region use for backward compatability
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 24e1a4e9 (ceph): rgw: handle the case of non exisiting zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision b8eb5bd0 (ceph): rgw: more on fix for g_ceph_context shutdown
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 085ee732 (ceph): rgw: track all stacks, not just scheduled
- And don't expand spawned stacks out of existing cr. This flattens the
admin socket output.
Signed-off-by: Yehuda Sad... - 12:13 AM Revision 124cf065 (ceph): rgw: remove epoch and duplicates from list_periods
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision edc24bf1 (ceph): rgw: fix assert on shutdown by keeping g_ceph_context around longer
- RGWRealmWatcher and friends are on the stack in main(), so we can't drop
the last ref on g_ceph_context until their d... - 12:13 AM Revision 7f439b1b (ceph): radosgw-admin: replace region with zonegroup in the help file
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 5aa81b97 (ceph): ceph_json: add deque encode/decode
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 1c6ac7bb (ceph): rgw: framework for per-rgw sync status reporting
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 961e602d (ceph): rgw: start hooking sync report
- also multiple fixes around the report tool
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision f5f05ba7 (ceph): rgw: more metadata sync reporting
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 9ecd08fd (ceph): rgw: RGWRealmWatcher supports multiple watch types
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 22fca7eb (ceph): rgw: RGWPeriodPusher shares periods between zones/groups
- RGWPeriodPusher implements the RGWRealmWatcher interface to get
notifications for new periods. when it discovers tha... - 12:13 AM Revision 87ef103e (ceph): rgw: register RGWPeriodPusher with RGWRealmWatcher
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision cd1b46da (ceph): rgw: allocate a larger buffer for full sync omap oid
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision aa8a1ebd (ceph): rgw: call drain_all() before returning from some crs
- spawned crs are still using marker_tracker, need to drain_all() as
we destroy it in the destructor.
Signed-off-by: Y... - 12:13 AM Revision c54a99ff (ceph): rgw: fix compilation error on i386
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision f20c0ac8 (ceph): rgw: fix compilation error in RGWPeriodPusher::handle_notify
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9122fab4 (ceph): rgw: fix for decode of ZoneGroup id
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision abec368e (ceph): rgw: fix typo in RGWPeriod::update
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 5adae5b8 (ceph): rgw: add RGWRealm::notify_new_period()
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision ac18d0ce (ceph): rgw: keep Context for reconfig timer cancellation
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 76f811b7 (ceph): rgw: refactor reconfigure out of RGWRealmWatcher
- add a RGWRealmReloader class to handle reconfiguration, and use a
Watcher interface to get notifications from RGWReal... - 12:13 AM Revision cf8b1b2f (ceph): rgw: period push succeeds even if it isn't a new period
- when pushing periods between zones, we need a successful result to
signal that we can stop sending the period
Signed... - 12:13 AM Revision e836b368 (ceph): rgw: rename RGWRealmReloader::FrontendPauser to Pauser
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 1297b373 (ceph): radosgw-admin: add --zone-new-name to usage
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d065ef49 (ceph): rgw: fix RGWSystemMetaObj::rename
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 396bbb47 (ceph): rgw: we need to rename the zone inside the zonegroup too
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 521fb06a (ceph): rgw: data sync marker tracker, don't assert
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 155ab741 (ceph): rgw: cr call() doesn't return a value
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision f75388a9 (ceph): rgw: data sync fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 10171dcf (ceph): rgw: fetch bucket instance info if doesn't exist
- when doing data sync. This handles a race in which we try to sync data
of bucket instance before fetched its metadata... - 12:13 AM Revision 29496f0f (ceph): rgw: clarify log message
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8c11019b (ceph): rgw: start marker tracker sync entry can fail
- We might hit duplicate entry, just skip it, don't assert.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 4f17bbb5 (ceph): rgw: translate source_zone param into source zone id
- operations are done using the zone id, not the zone name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 9fc032f4 (ceph): rgw: use correct connection for certain data sync operations
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 1aabaafe (ceph): rgw: init num shards if sync status did not exist
- in data sync process
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 0cf3c913 (ceph): rgw: special handling of 'null' object version
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision fdbb9681 (ceph): rgw: full data sync, pass correct op
- Need to specify appropriate op (depending on whether object is
versioned or not versioned).
Signed-off-by: Yehuda Sa... - 12:13 AM Revision dcac9ba4 (ceph): rgw: initialize data sync if needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision dac0ed9e (ceph): rgw: data sync CR retry after specific errors
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision f5a07532 (ceph): rgw: backoff mechanism for data sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 77072341 (ceph): rgw: move code around
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 35ffcff1 (ceph): rgw: more backoff related changes and fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 8166ac43 (ceph): rgw: don't force pool names to start with periods
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 2bfd66ea (ceph): rgw: remove include to <boost/asio/coroutine.h>
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 209608a9 (ceph): rgw: remove include to <boost/asio/coroutine.h>
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 7942c937 (ceph): rgw: fix compilation with older boost versions that don't have asio cor...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision a958be00 (ceph): rgw: coroutine manager returns ECANCELED when going down
- RGWRemoteMetaLog::run_sync() was getting stuck in an infinite loop after
a call to RGWCoroutinesManager::stop(). ins... - 12:13 AM Revision d79fe697 (ceph): rgw: init REST connection by zone name
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 21347a5c (ceph): rgw: keep timestamp stats in incremental sync position data
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision fcc6b8e9 (ceph): rgw: initialize data member
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 62681589 (ceph): rgw: add make_param_list() helper
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision e81c1ac9 (ceph): rgw: RGWRESTPostResource takes param_list_t for RGWPostRESTResourceCR
- RGWPostRESTResourceCR needs to make a copy of the parameters given to
its constructor, because it doesn't use them un... - 12:13 AM Revision 03282533 (ceph): rgw: apply RGWRESTReadResource::wait_bl() fix to PostResource as well
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 1a0e74bb (ceph): rgw: use boost::intrusive_ptr for http_op ref counting
- this fixes a segfault in the RGWPostRESTResourceCR::request_complete()
error path, which accessed http_op after calli... - 12:13 AM Revision 86148c47 (ceph): rgw: shutdown lease CR on mdlog inc sync failure
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 28ba9af0 (ceph): rgw: update the correct shards when doing full sync
- The shard we use for each entry (either meta, or data) needs to be selected
correctly to match the different logs we ... - 12:13 AM Revision 7c435548 (ceph): rgw: keep sync progress info for full sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 49bf8ba1 (ceph): rgw: show data full sync stats
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 0c0c9960 (ceph): rgw: fix bucket creation and deletion when there is no realm or period ...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2a22b2b7 (ceph): rgw: realm watcher locks mutex for SafeTimer::shutdown()
- this fixes an assert() on shutdown
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 12:13 AM Revision 1f485dd7 (ceph): rgw: bucket ops, obj create and obj delete should check to see if bucke...
- rgw_build_policies set the bucket_exists flag
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 12:13 AM Revision 91de9b51 (ceph): rgw: workaround to clear location constrain when using default zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 384df8d1 (ceph): rgw: RGWRestConn uses vector instead of map
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision d585436d (ceph): rgw: move RGWPostRESTResourceCR to rgw_cr_rest.h
- for use by RGWRealmPusher
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 12:13 AM Revision a1816d97 (ceph): rgw: use insert to copy containers in rgw_rest_conn
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 6c1f3761 (ceph): rgw: add typedef for rest parameter lists
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 953086a2 (ceph): rgw: handle transient error in md full sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision d047763f (ceph): rgw: move children collection to other method
- and call it again instead of just draining at the end
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 105f8a07 (ceph): rgw: rework incremental md sync error handling
- similar to what we do with the full md sync. Identify transient
errors, and if so return -EAGAIN so that caller would... - 12:13 AM Revision 3fa1cc7b (ceph): rgw: move data sync init into the processing thread
- that way we don't depend on remote peer to be available
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 111cb41c (ceph): rgw: fix data sync initialization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 9acb6296 (ceph): rgw: allow creating a bucket without current period
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d12da625 (ceph): rgw: use default zonegroup and zone in init_complete
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 41bbe95a (ceph): rgw: cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 50fd0bd0 (ceph): rgw: return -EAGAIN on a connection related http failure
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision c8cd83c2 (ceph): rgw: multiple sync initialization and error handling fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision fbdd3ad2 (ceph): rgw: get some errors from req_data
- When reading request status, we need to check with req_data first,
since it might have failed before we even got the ... - 12:13 AM Revision 4bbfe637 (ceph): rgw: rework error handling when syncing a single md entry
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 91761d1d (ceph): rgw: a coroutine util function to collect a single stack
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 1a92c4b2 (ceph): rgw: RGWCoroutine::spawn() returns stack
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision a4cec387 (ceph): rgw: coroutine drain fixes
- Init drain_cr() before draining, otherwise we wouldn't be able to
call it a second time
Signed-off-by: Yehuda Sadeh ... - 12:13 AM Revision 31913902 (ceph): rgw: RGWPeriod stores sync_status as vector of strings
- rgw_meta_sync_status keeps the shards in a std::map, but a std::vector
is more appropriate when all keys are present.... - 12:13 AM Revision ca5e00b1 (ceph): rgw: create RGWMetaSyncEnv, use it as container to sync env
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision d8dcf9b3 (ceph): rgw: move sync_oid() and shard_object_name() to sync env
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 96e38506 (ceph): rgw: mdlog full sync, yield for each entry
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 7be92686 (ceph): rgw: init sync env
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 97029664 (ceph): rgw: error out if failed to build md sync index
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 09112f25 (ceph): rgw: fix the mdlog sync lock control flow
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision e99da775 (ceph): rgw: add backoff and restart to meta sync
- also fix lease cr lifecycle
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 580e017d (ceph): rgw: account total number of metadata entries for sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 55a5addb (ceph): rgw: add missing rgw_meta_sync_status.h to the Makefile
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 790eeb5d (ceph): rgw: add rgw_rest_realm.h to the Makefile
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision de748e53 (ceph): make: fix link of ceph_test_cls_rgw_meta
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 99ef6fc5 (ceph): rgw: store metadata sync status on period commit
- store the new master zone's sync status with each new period
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 12:13 AM Revision f2424a16 (ceph): rgw: update realm_id when converting a region to zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision ac6dcc78 (ceph): rgw: add RGWRegionMap for backward compatability
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2650b3b0 (ceph): rgw: update current_period after adding converted zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 6d65dac2 (ceph): rgw: add support for region format in RGWOp_ZoneGroupMap_Get
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e92c9155 (ceph): rgw: create a realm in case of pervious regions configuration
- The realm name is concatanation of master region and master zone and its
id is the mds sume of the name
Signed-off-b... - 12:13 AM Revision 261e6436 (ceph): rgw: md full sync backoff
- Still need to work this out correctly
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 2991ffb1 (ceph): rgw: use set_cr_error() and set_cr_done() instead of set_state()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision afc3194b (ceph): radosgw-admin: remove period activate in favor of commit
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision f81e72fe (ceph): rgw: RGWHTTPManager dtor stops background thread
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision c010a3c0 (ceph): rwlock: add prioritize_write flag to prevent write starvation
- RWLock's constructor takes an additional 'prioritize_write' flag, which
defaults to false. when enabled, this adds t... - 12:13 AM Revision 30f74854 (ceph): rgw: add pause/unpause to RGWFrontend interface
- RGWProcessFrontend implements pause/unpause through the ThreadPool
interface. RGWMongooseFrontend implements them wit... - 12:13 AM Revision 4d72adce (ceph): rgw: add realm control object for watch/notify
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 40608a5f (ceph): rgw: period commit calls notify_zone
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision ab6c9213 (ceph): rgw: RGWRealmWatcher to reload RGWRados on changes
- adds RGWRealmWatcher, which watches the RGWRealm control object for
changes. in a separate thread, all frontends are... - 12:13 AM Revision ae729aa7 (ceph): rgw: add converted regions into the current period
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 29779964 (ceph): radosgw-admin: add realm pull command
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 51133f1f (ceph): rgw: RGWPeriod accessors are const
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 25c14c8c (ceph): rgw: period push handler updates current period/epoch
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision d9a19c75 (ceph): rgw: add RGWPeriod::commit()
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision c38a7812 (ceph): rgw: period push handler supports commit
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 132c2a18 (ceph): radosgw-admin: add 'period commit' command
- on the master zone, store the new period locally and notify the zone for
restart. on other zones, send a 'period pus... - 12:13 AM Revision 6b1cb5dc (ceph): radosgw-admin: add --commit flag for period update
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 3b019faf (ceph): radosgw-admin: add 'period update' to usage
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 55dfc851 (ceph): rgw: omit epoch in oid for staging period
- there should only be one staging period object, so the epoch is
an unnecessary part of its oid. and for period commit... - 12:13 AM Revision fc483c82 (ceph): rgw: period allows setting id, epoch, latest_epoch
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision a69e69aa (ceph): rgw: move period Ops to rgw_rest_realm.cc
- this removes the handling of /admin/config?type=period
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 12:13 AM Revision 7623e437 (ceph): rgw: add realm params to period pull
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 5704bcd1 (ceph): rgw: add op for GET /admin/realm
- this is for the radosgw-admin 'realm pull' command, which gets the realm
object by name or id
Signed-off-by: Casey B... - 12:13 AM Revision ee6d76f4 (ceph): radosgw-admin: add send_to_remote_or_url() helper
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 70a2b935 (ceph): rgw: multiple init metadata sync locking fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 76bfd7b0 (ceph): rgw: initialize rest connection if no period
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 092303ab (ceph): rgw: a bit better coroutine related logging
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision f055fae8 (ceph): rgw: guard metadata sync initialization step
- Guard the fetch-meta stage
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 899ff3dd (ceph): rgw: guard metadata full/incremental sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision c7f77c66 (ceph): rgw: RGWHandler_Config should assume empty type is zonegroupmap
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d3b3ddae (ceph): rgw: fix comparison typo in RGWRados::init_complete
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 0174086d (ceph): rgw: RGWRemoteMetaLog ctor sets async_rados=nullptr
- RGWRemoteMetaLog::init() is not called in all error paths, so we need to
start with nullptr
Signed-off-by: Casey Bod... - 12:13 AM Revision ea60f7e2 (ceph): rgw: RGWRados internal zone should be protected and not accessed directly
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e9044fc0 (ceph): rgw: RGWRados zonegroup and zone_public_config should not be accessed d...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision ae807420 (ceph): rgw: use default zone in case there is no period or zone name
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision db6647d0 (ceph): radosgw-admin: fix zone get command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c16caa01 (ceph): rgw: update new name after converting region to zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 697753a0 (ceph): rgw: backward compatability update_name for existing zones
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 3263c2e6 (ceph): cmake: move link dependencies to rgw_a
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:13 AM Revision 8e77fa6f (ceph): rgw: remove zonegroup_map from RGWRados
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision f5857c72 (ceph): rgw: no need to store or update zonegroupmap
- Structure and command will be kept for backward compatability
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 12:13 AM Revision 4c6a01af (ceph): radosgw-admin: zonegroupmap get should no error if no realm or period
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2441b7cd (ceph): rgw: add support to zonegroupmap set
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c11a5a50 (ceph): rgw: convert regionmap
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 3468dd6d (ceph): rgw: fix RGWSystemMetaObj::init by passing old_format flag
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision bba68536 (ceph): rgw: use current_period zonegroup and zone when exists
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 4195f8b0 (ceph): rgw: read local zonegroup and zone only when needed
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision fb2b8f2f (ceph): rgw: update rest connections from the current period
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 8d323925 (ceph): rgw: can set zone read-only, can set zonegroup id
- and other fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 680e58e6 (ceph): rgw: fix log message
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 6a403507 (ceph): rgw: don't read/init sync status if meta master
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision d97718d4 (ceph): CMake - add check for libcurl
- Signed-off-by: Daniel Gryniewicz <dang@fprintf.net>
- 12:13 AM Revision 78294dd1 (ceph): radosgw-admin: zone add command should be zonegroup add
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d2109c73 (ceph): rgw_admin: update zone set
- zone set was broken, now it can update the zone params correctly. Also
inheriting the id from the current zone if exi... - 12:13 AM Revision d1e32a87 (ceph): rgw: can override master zone config
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 4a5d77aa (ceph): rgw: get_predefined_name should get the ceph context
- so it can be called before object init
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 12:13 AM Revision 4733ccba (ceph): rgw: zonegroup and zone should not be accessed directly
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision fa2dc6a1 (ceph): rgw: read current period during init
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 93bddf9f (ceph): rgw: create default zonegroup for first time run of the gateway
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 46b268cd (ceph): rgw: auto create placement target params
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 4d484019 (ceph): rgw_admin: period update command
- A command that creates staging period data out of current local data
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 78f53f3f (ceph): rgw: stuff more info into the period
- and don't update the current period when adding zone, this
will be done through the staging period.
Signed-off-by: Y... - 12:13 AM Revision a2e7cd58 (ceph): rgw: update master zone
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 526421ac (ceph): rgw: run sync thread only when number of zones > 2 and master is config...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 8e8f13d1 (ceph): rgw: set first created realm as default
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 448674b6 (ceph): rgw: prefix default pools with zone name
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision c497facd (ceph): rgw: set first created zone as default
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 12239dd5 (ceph): rgw_admin: can update zonegroup endpoints, is_master
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 56bbadf2 (ceph): rgw_admin: can set zonegroup api name
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 2ae0f41e (ceph): rgw_admin: can config access/secret key for zone
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 66041ae8 (ceph): rgw: --rgw-zone and --rgw-zonegroup use names not id
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision eeaf75da (ceph): rgw_admin: don't require zonegroup id on some commands
- should be able to get the default one
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 212d8f48 (ceph): rgw_admin: zone name need to be provided on zone create
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision ee29f62b (ceph): rgw_admin: zone delete doesn't require zonegroup
- iterates through all the zonegroups and remove it
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 5f774a1d (ceph): rgw_admin: realm set-default -> realm default
- to be in line with the other default commands
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision a325dd5e (ceph): rgw: use --rgw-realm instead of --realm
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 702d5b05 (ceph): rgw: period get does not require specifying period id
- Can return the current period
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision 369e484e (ceph): rgw: period oid doesn't include realm id
- So that realm id is not a dependency for reading period.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision fa12a072 (ceph): radosgw-admin: zone get and rename commands should work without zonegro...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision ba629cdb (ceph): rgw: update rest_conn_master when adding a new master zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision fc3df345 (ceph): rgw: update zone endpoints when creating a new zone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision fd315d9b (ceph): rgw: update zonegroup endpoints when creating it
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 65775645 (ceph): rgw_admin: don't use --zone, use --rgw-zone
- --rgw-zone is tied to ceph.conf, and what we've always been using
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:13 AM Revision a12ec59f (ceph): rgw_admin: a zone default command, and other changes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 962eb3cd (ceph): rgw: don't use --zonegroup, use --rgw-zonegroup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision f267df2f (ceph): radosgw-admin: check legal input for zone modify command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e79171cf (ceph): radosgw-admin: check for legal input for zonegroup default command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 01e342fe (ceph): radosgw-admin: check for valid input for zonegroup modify command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 2a947bfe (ceph): radosgw-admin: check for valid input in zone add command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9638a4ee (ceph): radosgw-admin: check for valid input in zone delete command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c9269031 (ceph): rgw: print zone name and id in the begining of the dump
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision ef641572 (ceph): rgw: remove is_master flag from zoneparams
- make it easier to change master zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 12:13 AM Revision 452c8eed (ceph): radosgw-admin: fix zonegroup and master usage text
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e65afc56 (ceph): rgw: add zonegroup modify command to allow setting/clearing zonegroup m...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9954bb5c (ceph): rgw: add zone modify command to change master zone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 4517bf77 (ceph): rgw: fix RGWZone::dump
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 824a05bf (ceph): radosgw-admin: use realm_id from zonegroup if not provided
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9dfbae6d (ceph): rgw: fix compilation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision 3bd29b4e (ceph): rgw: zone config related changes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:13 AM Revision bc70d67f (ceph): rgw: move dump functions into rgw_json_enc.cc
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 189c1b13 (ceph): rgw: move rgw_meta_sync_status, rgw_meta_sync_marker and rgw_meta_sync_...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 98178094 (ceph): rgw: add decode_json method to rgw_meta_sync_status structures
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 58065620 (ceph): rgw: store latest sync status when activating a period
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c05e6321 (ceph): radosgw-admin: fix zone create to check for zonegroup name
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c1e1f12f (ceph): rgw: remove debug message from decode_zones
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision bded7eb7 (ceph): rgw: add RGWRegionMap for backward support
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 220e8e86 (ceph): rgw: add backward support for old regionmap format
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 852ead59 (ceph): rgw: fix whitespace and remove debug messages
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9272d7ef (ceph): rgw: add period_map to period dump and encode_json
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e18b72f7 (ceph): rgw: add bucket_quota to RGWRegionMap::encode_json
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 208a3873 (ceph): rgw: don't try to unregister request on destructor
- We already unregister the request earlier, and the locking here
was weird and wrong anyway.
Signed-off-by: Yehuda Sa... - 12:13 AM Revision d12836d0 (ceph): radosgw-admin: fix zonegroup default
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision dbd70b04 (ceph): radosgw-admin: zone create should update zonegroupmap for non standalon...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 57cb5184 (ceph): rgw: add id to RGWZone dump and decode_json functions
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision e020790a (ceph): radosgw-admin: zone set should handle old format json (without name or id)
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 6c45a2ad (ceph): rgw: systemmetaobj::create don't generate random id if id is provided
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 6705fe73 (ceph): rgw: rgwzone decode_json should handle empty id for backward compatabiltiy
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 1882243b (ceph): radosgw-admin: remove extra print from zonegroup set command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 3d9eb7f3 (ceph): radosgw-admin: add --rgw-zone for backward compatability
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 117bb62d (ceph): rgw: backward compatabilty for zone set command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c3907af4 (ceph): radosgw-admin: fix zonegroupmap update
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 674087ec (ceph): radosgw-admin: zonegroup set needs to update zonegroupmap
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision a320a442 (ceph): radosgw-admin: realm set should update zonegroup map
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9082ed6c (ceph): radosgw-admin: zone set command should update zonegroupmap
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 922721cc (ceph): radosgw-admin: add --rgw-zonegroup for backward compatability
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 23cafb0e (ceph): rgw: use encode_map for zonegroups
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 0e4cdb65 (ceph): radosgw-admin: update zonegroupmap when adding a zone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 76df9117 (ceph): rgw: add realm_id to zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision cd120d84 (ceph): radosgw-admin: use zonegroup realm id in zone add command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision eb6fe357 (ceph): radosgw-admin: use the correct realm id when creating a new zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d6d57aeb (ceph): rgw: use realm provided in the command line
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 695b48be (ceph): rgw: fix zonegroupmap initialization in init_complete
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 265e0933 (ceph): radosgw-admin: update zonegroupmap when activating a period
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 6f80c92b (ceph): rgw: fix realm create
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d178f99b (ceph): rgw: fix zonegroup create
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision ae7f8042 (ceph): rgw: add zonegroup_map period update
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 88515686 (ceph): rgw: add period_map to encode/decode
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 84f9a26c (ceph): rgw: update zonegroupmap when creating new realm
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision fe8c3440 (ceph): rgw: fix zonegroup update
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 60f948d1 (ceph): radosgw-admin: fix error messages for zonegroup create
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 3c45e433 (ceph): rgw: fix init_complete when there is no realm
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 993481a7 (ceph): rgw: cleanup period init
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision c04e688f (ceph): rgw: move zonegroup data into rgwperiodmap
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 10adb672 (ceph): rgw: zonegroup map contains a map of periods
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision b8b237a8 (ceph): rgw: add realms to zonegroupmap
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9af5152d (ceph): rgw: fix encoding and decoding of realms and periods
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 11500473 (ceph): rgw: add zonegroupmap realm update
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 66eb0200 (ceph): rgw: Rename Region to ZoneGroup only internal structures and class
- User visuable are not changed: admin commands, jsons and rados objects names
Signed-off-by: Orit Wasserman <owasserm... - 12:13 AM Revision 9451af69 (ceph): cmake: fix erasure-code
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision d4b58baa (ceph): rgw: RGWZoneGroup should inheirt from RGWSystemMetaObj
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 9a0d4170 (ceph): rgw: RGWZoneParams should inherit from RGWSystemMetaObj
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision ea0a4202 (ceph): radosgw-admin: add zone create, delete and rename commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 0d83cfe3 (ceph): rgw: add use_next_epoch method
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:13 AM Revision 660fc7ca (ceph): rgw: use RGWZoneGroupMap in RGWPeriod
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 966dd3ee (ceph): rgw: propagate olh_epoch for obj sync correctly
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 3c6e5e7b (ceph): cls/rgw: rgw_bi_log_entry::decode_json(), decode ver
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision beac57f2 (ceph): rgw: don't require system pools to start with a period
- Make sure cache operations are being done on system objects.
Separate calls where needed to make sure that separate p... - 12:12 AM Revision 9744de72 (ceph): rgw: add new class to create resource request
- RGWRESTReadResource holds the request input and output. Previously
we were using stack variables that couldn't be use... - 12:12 AM Revision 94db324c (ceph): rgw: async rados requests through a work queue
- Tie in the async rados requests to the async framework.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision daaf7b41 (ceph): rgw: Add RGWNameToId and RGWDefaultSystemMetaObjInfo
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 1680bb75 (ceph): rgw: Add RGWSystemMetaObj class
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Conflicts:
src/rgw/rgw_rados.cc - 12:12 AM Revision a8d765d2 (ceph): rgw: Add period admin commands and rest api to handle period
- the new commands are prepare,delete, get, activate, pull and push
Signed-off-by: Orit Wasserman <owasserm@redhat.com... - 12:12 AM Revision 0bdf1505 (ceph): rgw: don't create connection object for zone without endpoints
- warn about it though
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 01608a84 (ceph): rgw: minor cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision beba94bc (ceph): rgw: data sync locking fixes
- and other fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision ddfb0193 (ceph): rgw: tie incremental data sync
- and other fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 9c6a962f (ceph): rgw: handle object removal in incremental data sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 5e368857 (ceph): rgw: fetch_remote_obj() uses correct version_id
- This fixes one aspect of the versioned objects sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 6e243c34 (ceph): cls_rgw: reset dirent flag appropriately
- Need to mark dirent as versioned if it has instance.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 8ff39798 (ceph): rgw: incremental data sync
- still needs some more work, but basic structure is there.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 579bd3a1 (ceph): rgw: incremental data sync adjustments
- update marker, close a race
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision c43f7362 (ceph): rgw: only account actual io for coroutine io window
- stacks that are put in interval_wait shouldn't be accounted.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 35d48c04 (ceph): rgw: eliminate window for data sync marker
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision b334c03b (ceph): rgw: work towards datalog sync notification
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 5a7e4e32 (ceph): rgw: async data changes notifications
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision f6788b75 (ceph): rgw: multiple fixes related to coroutines draining
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 390f64a0 (ceph): rgw: data sync work
- Instead of just keeping map of bucket instances, keep map of all the shards.
Also prepare the CRs that will call into... - 12:12 AM Revision 1403b23c (ceph): rgw: move top level data sync function into coroutine
- So that it can be called from a coroutine
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 04cd5921 (ceph): rgw: data sync, spawn sync on all shards
- full sync should work now
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 3dff6252 (ceph): rgw: revive io window
- and several other fixes. Don't send unbounded number of IO requests,
send back http related errors (that didn't have ... - 12:12 AM Revision cf3bbddc (ceph): rgw: reduce the use of obj_ctx
- Should really get rid of all the obj_ctx use, unless it's really needed. It's
not thread safe.
Signed-off-by: Yehuda... - 12:12 AM Revision aefa0884 (ceph): rgw: add rwlock to RGWObjectCtx
- It can be used from multiple threads now.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision a8dc84e9 (ceph): rgw: fix data sync init
- Need to wait for shards' status.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 9422936d (ceph): rgw: no need to yield while collecting
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision b8d57a22 (ceph): rgw: add RGWCoroutine::wait_for_child()
- Will yield until one of the spawned stacks finished execution.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision c4cdb396 (ceph): rgw: finish execution when done with bucket sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 649b6723 (ceph): rgw: simplify unblocked by stack state change
- If blocked by another stack that is finished, just schedule, not waiting
on IO.
Signed-off-by: Yehuda Sadeh <yehuda@... - 12:12 AM Revision aa829e39 (ceph): rgw: clean up child draining a bit
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 27450d72 (ceph): Revert "rgw: simplify unblocked by stack state change"
- This reverts commit 8509ef5034818e163bebc8fd2de039a96b4a8f1a.
- 12:12 AM Revision cd1ad88d (ceph): rgw: move bucket shard full sync to its own coroutine
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 23e083ab (ceph): rgw: fix shard_id use
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 6b2df0e1 (ceph): rgw: init shard_id param for bucket listing
- shard_id can now be specified in the bucket instance http param
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 800f391c (ceph): rgw: add rgw_bi_log_entry::decode_json
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 7cc81c47 (ceph): rgw: skeleton for bucket index incremental sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 092cf681 (ceph): rgw: url_encode http params in requests that we send
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 0f42103c (ceph): rgw: collect spawned requests before completing coroutine
- Need to finish all processing before we return
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 65308b51 (ceph): rgw: fix pending operations accounting
- create RGWCoroutine::num_pending() to get the number of
pending spawned coroutines.
Signed-off-by: Yehuda Sadeh <yeh... - 12:12 AM Revision df001d8b (ceph): rgw: can read attrs when reading system obj
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 0ffbd84f (ceph): rgw: keep bucket sync markers in object attrs
- This allows to set the status separately for each of the
different stages (full, incremental), while allowing also
to... - 12:12 AM Revision 24373fd7 (ceph): radosgw-admin: bucket sync commands don't require bucket id
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 82db4777 (ceph): rgw: silence some verbose logs
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision e833021a (ceph): rgw: fix iteration over bucket entries in full sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 6d6cdc70 (ceph): rgw: switch sync state when done with full bucket sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 442edc82 (ceph): rgw: list bucket instance shard entries for data sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 07f3754b (ceph): rgw: fix signing for generated requests
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 4d69b8fa (ceph): rgw: extend list bucket versions api
- System user can now provide 'objs-container=true' in conjuction
with 'format=json' so that response is json and entri... - 12:12 AM Revision cd20ec84 (ceph): rgw: bucket sync, send marker when listing bucket shard
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 8659ff19 (ceph): rgw: bucket sync fetches remote objects
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 9f63b15b (ceph): rgw: fix identification of canceled operation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 868dccf2 (ceph): rgw: api adjustment following rebase
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 727db686 (ceph): rgw: window of full sync operations per bucket
- also store marker periodically, reuse marker logic from md sync.
Marker still needs some work.
Signed-off-by: Yehuda... - 12:12 AM Revision fa96d4e4 (ceph): rgw-admin: skeleton for data sync commands
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 29db3ce6 (ceph): rgw: initial data sync work
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 3d49dced (ceph): rgw-admin: data sync status command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 5fb66152 (ceph): rgw-admin: implement data sync init
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 2b4de2d2 (ceph): rgw: initial work on data sync run
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision f0e351d4 (ceph): rgw: per-bucket instance shard state
- add 'radosgw-admin bucket sync init' command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision f5a27f9d (ceph): rgw: read bucket sync status
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision c90d7cb5 (ceph): cls/rgw: add an objclass method to check obj mtime
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 0f7e3e0a (ceph): rgw: add mtime check to object removal if needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 9751d612 (ceph): rgw: add no-precondition-error http param for object delete
- In case we don't want to get an error response when a precondition
failed.
Signed-off-by: Yehuda Sadeh <yehuda@redha... - 12:12 AM Revision a3b0d200 (ceph): rgw: fix time parsing for delete precondition
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 14cb57a0 (ceph): rgw: propagate rgwx-bucket-instance for copying objects
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 15c530b4 (ceph): build: add cls_timeindex_client to DENCODER_DEPS
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:12 AM Revision 2aa6fd94 (ceph): radosgw-admin: switch mdlog sync commands to metadata sync
- radosgw-admin mdlog sync init -> metadata sync init
etc.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 8813a440 (ceph): rgw: add rgwx-copy-if-newer http header
- Similar to IF_MOD_SINCE, but does not take a time argument, and should
protected against races (not there yet).
Sign... - 12:12 AM Revision 27946e8b (ceph): rgw: fix if-modified-since boundary
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 20d24e96 (ceph): rgw: translate http error 304 to appropriate status
- So that we can return the appropriate response on a conditioinal multi
zone copy operation.
Signed-off-by: Yehuda Sa... - 12:12 AM Revision fe9c64b7 (ceph): rgw: identify racing writes when using copy-if-newer
- When copying an object from a different zone, and copy-if-newer is
specified, if the final meta write is canceled che... - 12:12 AM Revision babbf672 (ceph): rgw: adjust calls
- as part of a rebase work
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision e36db984 (ceph): rgw: more api adjustments
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision fc01f16f (ceph): rgw: add DELETE_IF_UNMODIFIED_SINCE header to obj delete
- Will delete object only if not modified after the specified time. Still
need to close a race where object is modified... - 12:12 AM Revision 413ac34b (ceph): rgw: fix uninitialized variable
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 654f203a (ceph): rgw: bilog info can get shard id
- We would like to be able to get bilog info by shard if needed.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 9cb1d6f6 (ceph): rgw: get_bucket_stats() returns a plain marker if shard specified
- E.g, will return 00001234 vs. 2#00001234 if shard 2 specified.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 359325b5 (ceph): rgw: system user can list bucket shard
- By setting the HTTP-Rgwx-Shard-Id header to the shard id.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 22f766eb (ceph): rgw: dump internal object tag when system user lists bucket
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 142c5a83 (ceph): rgw: access zone.name, zonegroup_name through accessor
- fix as part of a rebase
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 5d924904 (ceph): rgw: make rgw_user::empty() const
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision e6548ecd (ceph): rgw: rearrange full metadata sync order
- Users need to exist before their buckets, better have bucket instances
before bucket entry points
Signed-off-by: Yeh... - 12:12 AM Revision f2eb0d75 (ceph): rgw: move code around
- move code from rgw_sync.cc to rgw_cr_rados.{h,cc}
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 9ca266a1 (ceph): rgw: move more code around
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 07feb134 (ceph): rgw: coroutine stack wait util
- Instead of using a separate coroutine for waiting on
a condition.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision be3e2727 (ceph): rgw: use internal wait instead of special coroutine
- Instead of using a special coroutine that spawns a separate thread
and waits on a condition, use the internal corouti... - 12:12 AM Revision 9ab02a8c (ceph): rgw: trivial fix
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 73a21475 (ceph): rgw: move more code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision a848353e (ceph): rgw: simple thread base class
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision f7ac1222 (ceph): rgw: run and stop sync thread
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 18a9a436 (ceph): rgw: a few sync thread init/finalization fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 3e7b86e6 (ceph): rgw: wake up appropriate shard sync handler
- When receiving notification about modified shard, wake up the appropriate handler
Signed-off-by: Yehuda Sadeh <yehud... - 12:12 AM Revision 4b80edb1 (ceph): rgw: http client req handling fixes
- The error buffer for the async requests was on the stack, and not
on the request structure. Some other use after free... - 12:12 AM Revision 5cc80b0e (ceph): rgw: fix shutdown
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 6adf75c2 (ceph): rgw: trivial fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 766d52ae (ceph): rgw: keep track of modified mdlog shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 30bf776a (ceph): rgw: handle mdlog post request
- with 'notify' subresource. Will be used later for handling notifications
about modified mdlog shards.
Signed-off-by:... - 12:12 AM Revision 4ce51091 (ceph): rgw: periodical thread that tracks mdlog changes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 0f65f565 (ceph): ceph_json: add json encoder / decoder for std::set
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision c26ff96a (ceph): rgw: add simple POST requests interfaces
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision a7a9ca70 (ceph): rgw: send mdlog changes notifications to zones
- Will probably need to rework this, as it is now zones may interfere
with each other which is not optimal.
Signed-off... - 12:12 AM Revision 11dd2b86 (ceph): rgw: decode mdlog notification shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 669b9fc5 (ceph): rgw: RGWRESTSimpleRequest::forward_request params
- forward_request() uses new_info.build_from(info) to initialize the new
request info. but this doesn't copy the RGWHTT... - 12:12 AM Revision 7a760fe7 (ceph): radosgw-admin: fixes for period push/pull
- for send_to_remote_gateway() to work, the push and pull commands had to
be moved to the not-raw-storage section, beca... - 12:12 AM Revision 9da07070 (ceph): radosgw-admin: period pull supports --url
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:12 AM Revision c6be10df (ceph): rgw: add master flag to zonegroup create command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision c4795043 (ceph): radosgw-admin: allow creating a zone without a zone group
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 1f0c2c57 (ceph): rgw: Add zone add command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 390e1e1f (ceph): rgw: create the first period when creating a new realm
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision b9e51fc0 (ceph): rgw: fix period init and activate
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 7b81c27d (ceph): radosgw-admin: add json output to create commands
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:12 AM Revision 68232485 (ceph): radosgw-admin: add realm set command
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:12 AM Revision a0d76ec5 (ceph): rgw: fixes for RGWZoneGroupMap::decode_json
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:12 AM Revision dfadc9f7 (ceph): rgw: add handler for /admin/realm/period
- the handler returns the existing RGWOp_Period_Get/Post ops from
rgw_rest_config.h
Signed-off-by: Casey Bodley <cbodl... - 12:12 AM Revision be17da5e (ceph): rgw: delay allocation of RGWPeriod
- RGWOp_Period_Get and _Post don't have a valid RGWRados pointer until
they get the init() call, so the constructors we... - 12:12 AM Revision 6693737f (ceph): rgw: POST /admin/realm/period reads in json data
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:12 AM Revision 4a2f1681 (ceph): common: expose Formatter::flush to derived classes
- class Formatter declares both a 'virtual void flush(ostream&)' and a
'void flush(bufferlist&)'. however, because its ... - 12:12 AM Revision 750074b2 (ceph): radosgw-admin: Add period list command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 589fe2ed (ceph): radosgw-admin: Add master_zonegroup and master_zone to period prepare
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 92504ddc (ceph): rgw: Add realm list-periods command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 27fda3aa (ceph): rgw: realm id and epoch should be part of period oid
- fixes period get and activate command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 12:12 AM Revision d259066f (ceph): rgw: fix realm list-periods
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 7f683ed4 (ceph): rgw: update period predecessor when it is activated
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 297de47e (ceph): rgw: use id for master zone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 550d84f6 (ceph): rgw: RGWZoneParams should inherit from RGWSystemMetaObj
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 12ce5128 (ceph): radosgw-admin: add zone create, delete and rename commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision ef5544fd (ceph): rgw: default zone should not be master
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 27af8930 (ceph): rgw: remove debug messages
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 3fc65d14 (ceph): rgw: fix zone set command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 8190047f (ceph): radosgw-admin: print new perion in period perpare command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 7a1cb789 (ceph): rgw: fix typo
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 10b3fe76 (ceph): rgw-admin: fix realms list
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 1adf6a5d (ceph): rgw: pass const string reference
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision f5a05674 (ceph): rgw-admin: use default realm on realm get
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 199ee222 (ceph): rgw-admin: adjustments to period get-current output
- Make it output through the formatter
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 5fa07644 (ceph): rgw: Add RGWSystemMetaObj class
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Conflicts:
src/rgw/rgw_rados.cc - 12:12 AM Revision a6acb1a0 (ceph): rgw: add id to RGWZoneParams
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision dc3feb6a (ceph): Add zone create admin command - wip
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 814fe66b (ceph): rgw: wake up wait coroutine thread on destruction
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision fe113730 (ceph): rgw: sync local mdlog if needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision e332d17c (ceph): rgw: fix busy wait in RGWHTTPManager
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 311c105c (ceph): rgw: don't force wait on blocked coroutines
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision fe38269b (ceph): rgw: track mdlog marker
- sync entries if the sync marker is < mdlog marker, otherwise
try to fetch more entries.
Signed-off-by: Yehuda Sadeh ... - 12:12 AM Revision 764dc5b3 (ceph): rgw: do the actual incremental metadata sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision bd5a6b37 (ceph): rgw: update meta sync markers during full sync operation
- update marker per shard, keep a window so that we don't update after each change
Signed-off-by: Yehuda Sadeh <yehuda... - 12:12 AM Revision 46445a65 (ceph): rgw: update global sync state after building meta indexes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 528aff10 (ceph): rgw: switch to incremental sync when done full meta sync
- each shard need to collect the coroutines it spawned before continuing.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM Revision 3db4e98e (ceph): rgw: hash full sync keys to shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 12926239 (ceph): rgw: get remote mdlog status when initializing
- Use that as the lowerbound for the meta marker when we start
the incremental sync.
Signed-off-by: Yehuda Sadeh <yehu... - 12:12 AM Revision 6bf77a7e (ceph): rgw: read mdlog entries for incremental sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision 8f7b6712 (ceph): rgw: poll mdlog for incremental sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:12 AM Revision c169b75f (ceph): rgw: add id to RGWZone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 95f71261 (ceph): rgw: RGWZoneGroup should inheirt from RGWSystemMetaObj
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision 242f2c88 (ceph): rgw: add current_period to RGWRealm
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision d07306cc (ceph): rgw: add period activate admin command and fix get current command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision f4be2693 (ceph): rgw: Add zonegroup create, delete and rename admin commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:12 AM Revision f176c587 (ceph): rgw: add zonegroup name or id to zonegroup get and set commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
02/11/2016
- 11:48 PM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
- This one's odd. The problem in #14697 is different; it's actually calling timer.shutdown() twice there. Here, that is...
- 11:39 PM CephFS Bug #14697: mds: assert in SafeTimer while suiciding
- 11:38 PM CephFS Bug #14697: mds: assert in SafeTimer while suiciding
- > 2016-02-08T02:00:34.587 INFO:tasks.ceph.mds.a-s.mira064.stderr:Thread::join(): pthread_join failed with error 22
... - 11:26 PM Revision 03800546 (ceph): mds: don't double-shutdown the timer when suiciding
- Fixes: #14697
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 10:07 PM CephFS Bug #14735 (Resolved): ceph-fuse does not mount at boot on Debian Jessie
- 01:58 PM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
- Fixed by https://github.com/ceph/ceph/pull/7607
- 08:58 AM CephFS Bug #14735 (Resolved): ceph-fuse does not mount at boot on Debian Jessie
- I have a problem with ceph-fuse on Debian Jessie.
I have this in my fstab :
@id=my_user,daemonize=false,mon_hos... - 10:06 PM CephFS Bug #14365 (Resolved): unsafe handle_config_change() methods
- Fixed in https://github.com/ceph/ceph/pull/7312 and https://github.com/ceph/ceph/pull/7581 (both required).
- 09:32 PM Revision 90d93fe9 (ceph): Merge pull request #7613 from wjwithagen/patch-1
- osd: add missing newline to usage message
Reviewed-by: Sage Weil <sage@redhat.com> - 09:30 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
- 09:30 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
- I think it's already done https://github.com/ceph/ceph-qa-suite/commit/1f322cbb478025c439c09ccffa1403e55e6be41c
- 09:25 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
- easiest fix is to run teh rgw test from client.2, and exclusive it from the concurrently running upgrade.
need to ... - 07:00 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
- The s3test task both creates users, and run the s3-tests suite. We need to split the different actions so that the up...
- 08:29 PM Revision 34f896b0 (ceph): src/ceph_osd.cc Add missing newline to usage message
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 07:45 PM rgw Feature #2473 (Resolved): rgw: revisit operation logging
- 07:45 PM rgw Feature #2257 (Rejected): rgw: detect fastcgi module 100-continue support automatically
- 07:44 PM rgw Feature #3856 (Resolved): rgw: list buckets S3 api should be paginated
- 07:43 PM rgw Tasks #3265 (Closed): test Amanda against RGW
- 07:42 PM rgw Feature #5821 (Resolved): Alias --secret-key to --secret for radosgw-admin
- 07:41 PM rgw Cleanup #4541 (Resolved): refactor RGWUser class
- 07:40 PM rgw Tasks #3118 (Closed): QA: radosgw upstart: test the radosgw upstart script respawn functionality
- 07:36 PM rgw Bug #14534: rgw: cannot limit users to not create buckets
- Currently the max_buckets param on the user info cannot limit users to not be able to create any buckets. Either we a...
- 07:29 PM rgw Bug #14025: Bucket DELETE fails, 404 NoSuchKey, but cannot reproduce on other bucket names or users
- There are a few operations that happen when removing a bucket:
- remove bucket instance
- remove bucket entry poi... - 07:23 PM RADOS Feature #14527: Lookup monitors through DNS
- Ricardo Dias wrote:
> Dan van der Ster wrote:
> > Ahh OK. DNS SRV records might be better than a hardcoded hostname... - 05:38 PM RADOS Feature #14527: Lookup monitors through DNS
- Dan van der Ster wrote:
> Ahh OK. DNS SRV records might be better than a hardcoded hostname. See the DNS section her... - 05:34 PM RADOS Feature #14527 (In Progress): Lookup monitors through DNS
- 07:11 PM rgw Bug #14678: rgw: when putting metadata object, cache info doesn't keep object's metadata (size, m...
- https://github.com/ceph/ceph/pull/7615
- 07:09 PM rgw Bug #14665 (Duplicate): radosgw-admin -n client.0 user create : permission denied
- closing this one, same as 14652
- 07:07 PM rgw Bug #14361 (Closed): swift/test/functional -v -a '!fails_on_rgw'
- slow env issues
- 07:06 PM rgw Bug #14375 (Resolved): subuser rm fails with status 125
- Fixed, commit:bbc06e70b49b2917ee63985727cb92724fb99209
- 07:05 PM rgw Bug #13644 (Resolved): get_quota_info returns json in headers
- 07:04 PM rgw Tasks #10855 (Closed): rgw: set up federated gateway
- 07:02 PM rgw Bug #13900 (Closed): "test_s3.test_non_versioned_concurrent_object_create_concurrent_remove ... E...
- Feel free to reopen if happens again, sounds like slow backend.
- 06:44 PM rgw Bug #14653 (Closed): "test_s3.test_abort_multipart_upload ... FAIL" in upgrade:hammer-hammer-dist...
- Feel free to reopen if it happens again, we think it's env related
- 06:38 PM rgw Feature #14713: [RFE] remove libfcgi from build
- I.e., make fcgi build conditionally.
- 06:24 PM Revision d7f0304a (ceph): common: fix build error with Graylog
- Graylog includes boost stuff, which clobbers our assert macros.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:45 PM Revision d8675cf4 (ceph): Log: Adding UT to catch an issue with huge line logging
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 05:43 PM Revision 05a4811c (ceph): Merge pull request #6920 from oritwas/wip-mstart-cmake
- ajdust mstart and mstop script to run with cmake build
- 05:40 PM Revision aa6d0a9c (ceph): Merge pull request #7523 from tchaikov/wip-fix-cmake
- cmake: fix the build of tests
- 05:30 PM Revision 6adb6944 (ceph): Merge pull request #7607 from FlorentCoppint/master
- mount.fuse.ceph: better parsing of arguments passed to mount.fuse.ceph by mount command
Reviewed-by: Sage Weil <sage... - 05:19 PM Revision dd533a9e (ceph): Log: Fixing stack overflow when flushing large log lines.
- See http://tracker.ceph.com/issues/14707
Signed-off-by: Igor Fedotov <ifedotov@mirantis.com> - 04:53 PM Revision 44c03072 (ceph): rbd: add fsx journal replay test case
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:32 PM rbd Subtask #14739 (Can't reproduce): Support deleting a journal when its being replayed by the RBD m...
- Attempting to delete an image which is being mirrored will not work if the RBD mirroring daemon is watching the journ...
- 04:26 PM rbd Feature #14738 (Resolved): Optionally unregister "laggy" journal clients
- Support an optional configuration setting for the maximum number of object sets a journal client can be behind before...
- 03:32 PM Revision 71f380a8 (ceph): Merge pull request #7484 from dillaman/wip-14610-infernalis
- librbd: flattening an rbd image with active IO can lead to hang
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:32 PM Revision 83502159 (ceph): Merge pull request #7406 from dillaman/wip-14542-infernalis
- librbd: ImageWatcher shouldn't block the notification thread
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:32 PM Revision f5e33cd3 (ceph): Merge pull request #6981 from dillaman/wip-14062-infernalis
- librbd: fix merge-diff for >2GB diff-files
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:20 PM Linux kernel client Bug #14737 (Resolved): libkrbd vs udev event ordering
- I sat down and looked into a few rare instances of "rbd map" hangs, mostly during fsx runs from the last year. The o...
- 03:08 PM Linux kernel client Bug #14736 (Resolved): Kernel cephfs bind-mounts break if parent dir modified elsewhere
- ISSUE
If you have used mount with the --bind option to overlay one cephfs location on another, then creating any f... - 03:02 PM Revision da772fa8 (ceph): WorkQueue: PointerWQ drain no longer waits for other queues
- If another (independent) queue was processing, drain could
block waiting. Instead, allow drain to exit quickly if
no... - 03:02 PM Revision f3987367 (ceph): librbd: simplify IO flush handling
- Add a new convenience method to ImageCtx for handling flush
requests and cleanup flush handling with dealing with the... - 03:02 PM Revision b0c91768 (ceph): librbd: ensure librados callbacks are flushed prior to destroying image
- Fixes: #14092
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 98157ab3274bd960e4487e34... - 03:01 PM Revision 5593e57c (ceph): test: new librbd flatten test case
- AIO operations after a flatten operation were previously
hanging during the close of the parent image.
Signed-off-by... - 03:01 PM Revision 5b3a4d2c (ceph): test: new librbd flatten test case
- AIO operations after a flatten operation were previously
hanging during the close of the parent image.
Signed-off-by... - 02:56 PM Linux kernel client Bug #13905: "BUG: held lock freed!"
- No - this occurrence is on a very recent kernel, so could be a kernel bug. I'll look into it as time allows.
- 02:41 PM Revision 46ed443b (ceph): librbd: ImageWatcher shouldn't block the notification thread
- Blocking the notification thread will also result in librados async
callbacks becoming blocked (since they use the sa... - 02:41 PM Revision 2be722a3 (ceph): librados_test_stub: watch/notify now behaves similar to librados
- Notifications are executed via the same librados AIO callback
thread, so it's now possible to catch deadlock.
Signed... - 02:40 PM Revision 8990ee87 (ceph): tests: simulate writeback flush during snap create
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 5e564ea9f869b987f3ada2465edfbe5edf9f6435) - 02:39 PM Revision 389ed346 (ceph): librbd: fix merge-diff for >2GB diff-files
- Fixes: #14062
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(derived from commit 68125dd01349edf93cfa1af5028c2d... - 02:39 PM Bug #14622: initsystem: 30s time out leads to osd daemon start fail
- Could be a problem with ceph-disk - Loic, could you take a look? Not a kernel client issue.
- 01:53 PM Revision 0da0eda7 (ceph): unittest_[ceph_]crypto: fix warnings
- test/crypto.cc:20:31: warning: ‘crypto_env’ defined but not used [-Wunused-variable]
::testing::Environment* const c... - 01:53 PM Revision c6332585 (ceph): unittest_compression_[*_][plugin]: fix warnings
- test/compressor/test_compression_plugin.cc: In function ‘int main(int, char**)’:
test/compressor/test_compression_plu... - 01:53 PM Revision fd85a9b5 (ceph): unittest_bufferlist: fix warning
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:51 PM Revision 8fe75846 (ceph): Better parsing of arguments passed to mount.fuse.ceph by mount command.
- Signed-off-by: Florent Bautista <florent@coppint.com>
- 01:46 PM Revision 63e671a9 (ceph): Merge pull request #5961 from majianpeng/small-fix
- osd: clean up CMPXATTR checks
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 01:45 PM Revision e211b5b2 (ceph): Merge pull request #7533 from Cdiscount/master
- debian: include cpio in build-requiers
Reviewed-by: Sage Weil <sage@redhat.com> - 01:45 PM Revision 856e6daf (ceph): ceph_test_libcephfs: fix warnings
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:44 PM Revision cc2200c5 (ceph): Merge pull request #7537 from ifed01/wip-no-promote-for-delete-fix
- osd: fix unnecessary object promotion when deleting from cache pool
Reviewed-by: Sage Weil <sage@redhat.com> - 01:43 PM Revision f8d58071 (ceph): Merge pull request #7567 from branch-predictor/bp-slimdown-conns
- msg: significantly reduce minimal memory usage of connections
Reviewed-by: Sage Weil <sage@redhat.com> - 01:43 PM Bug #14706 (Pending Backport): systemd escaping of block devices in ceph-disk incorrect
- 01:42 PM Revision 88d25147 (ceph): Merge pull request #7579 from javacruft/wip-systemd-escaping
- systemd: correctly escape block device paths
Reviewed-by: Sage Weil <sage@redhat.com> - 01:42 PM Revision 0d819d54 (ceph): Merge pull request #7581 from jcsp/wip-asok-lockdep
- librados: mix lock cycle (un)registering asok commands
Reviewed-by: Sage Weil <sage@redhat.com> - 01:37 PM Revision 62ecb28f (ceph): Merge pull request #7604 from ceph/wip-selinux-update-radosgw-log
- selinux: allow log files to be located in /var/log/radosgw
Reviewed-by: Sage Weil <sage@redhat.com> - 12:18 PM Revision 4056ee29 (ceph): Merge pull request #7606 from tchaikov/wip-fix-ceph-disk
- tests: ceph-disk.sh: use "readlink -f" instead for fullpath
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:08 PM Revision 8f42f899 (ceph): tests: ceph-disk.sh: use "readlink -f" instead for fullpath
- if $PATH has ".." in it, and the program happen to be located in
"..", `which program` will print `../program` instea... - 11:37 AM Revision bcf12049 (ceph): selinux: Allow log files to be located in /var/log/radosgw
- We do suggest users to put their logs in /var/log/radosgw in the
documentation at times. We should also label that di... - 10:27 AM Bug #14723: make check bot broken: execvp: /bin/sh: Argument list too long
- https://jenkins.ceph.com/job/ceph-pull-requests/1308/console
- 08:17 AM Bug #14734 (Resolved): ceph-detect-init is missing pkg_resources dependency
- I deployed Ceph via ceph-deploy to a new host:...
- 06:59 AM Revision a474c096 (ceph): Merge pull request #6629 from Abhishekvrshny/wip-13733-infernalis
- rbd: misdirected op in rbd balance-reads test
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:54 AM Revision 36a82b30 (ceph): xio: fix error from explicit ctor of entity_name_t
- entity_name_t ctor is now explicit.
Signed-off-by: Roi Dayan <roid@mellanox.com> - 06:54 AM Revision 1304e949 (ceph): xio: check for xio connection error before set as connected
- Also go through the disconnect method that checks we are connected
before passing the conn to xio_disconnect as it mi... - 06:54 AM Revision bfafc3b3 (ceph): xio: avoid trying bind to port we know will fail
- When going over range from port_min to port_max to find open
port to bind we can increase port_min after successful b... - 06:54 AM Revision b448f3c0 (ceph): xio: thread name must be less than 16 chars
- portal_id string can pass the 16 chars thread name limit so
we can't use it.
Signed-off-by: Roi Dayan <roid@mellanox... - 06:36 AM Revision 765c7592 (ceph): Merge pull request #7601 from jjhuo/master
- os/bluestore: fix a typo in SPDK path parsing
Reviewed-by: Haomai Wang <haomai@xsky.com> - 05:27 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. fs
Verifying if the bug found at http://tracker.ceph.com/issues/13750#note-19 is in infernalis. See also http:... - 04:45 AM Backport #14719 (In Progress): infernalis: OSDMap: reset osd_primary_affinity shared_ptr when dee...
- 04:37 AM CephFS Bug #14384 (Resolved): fsx failed to compile
- 04:37 AM rbd Bug #14280 (Resolved): cls_rbd: object_map_save should enable checksums
- 04:37 AM rbd Bug #14164 (Resolved): [ FAILED ] TestLibRBD.SnapRemoveViaLockOwner
- 04:37 AM Bug #13785 (Resolved): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- 04:37 AM CephFS Bug #13777 (Resolved): Ceph file system is not freeing space
- 04:37 AM CephFS Bug #13714 (Resolved): Segmentation fault accessing file using fuse mount
- 04:14 AM CephFS Bug #14732 (Duplicate): open returns EACCES when O_TRUNC is specified and write permission is den...
- See http://tracker.ceph.com/issues/14692#note-2 for a few runs with this issue...
- 02:12 AM rbd Tasks #13959: add python3-specific packages for rbd and rados python bindings
- The conversion of rbd.py to cython makes this a little more complex - we'll need to build separate versions of the rb...
- 01:44 AM Revision 40936fb1 (ceph): os/bluestore: fix a typo in SPDK path parsing
- SPDK block path with bluestore is something like spdk:55cd2e404bd73932.
The size of the prefix to compare should be 5... - 01:02 AM Revision e03cee48 (ceph): rados/upgrade: add '%' to combine rados.yaml with other yamls
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit a13d9e89a8fb280ef1538104e2f4f9c77d288501) - 01:02 AM Revision 9c8d2fb7 (ceph): rados/: remove unnecessary rados.yaml entries
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit ebea8ade8ec0aa41058fabed5ac7796ee60b20a7) - 12:56 AM Revision 50a26b96 (ceph): Merge pull request #820 from ceph/wip-rados-yaml
- Wip rados yaml
Reviewed-by: Yuri Weinstein <yweinste@redhat.com> - 12:06 AM Revision b92eb668 (ceph): librbd: protect journal replay against overlapping writes
- If fsx issues a back-to-back synchronous write, these will be
replayed as AIO writes. If object map is enabled, it's...
02/10/2016
- 11:22 PM Documentation #14731 (Resolved): contact Inktank for support
- in URL:
http://docs.ceph.com/docs/master/rados/troubleshooting/troubleshooting-osd/#osd-not-running
at bottom o... - 11:16 PM Documentation #14730 (Resolved): description of upgrade procedure - stopping/starting OSDs
- In URL:
http://docs.ceph.com/docs/master/rados/troubleshooting/troubleshooting-osd/#stopping-w-out-rebalancing
... - 10:40 PM Revision bb662311 (ceph): librbd: track in-flight AIO flush requests during journal replay
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:39 PM Revision 1cc409b4 (ceph): test: possible librbd journal replay flush race
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:26 PM Bug #14707 (Fix Under Review): log: segv during _flush on very big long lines
- 06:30 PM Bug #14707: log: segv during _flush on very big long lines
- PR is at https://github.com/ceph/ceph/pull/7599
- 10:08 PM Revision 78799a9c (ceph): Merge pull request #7405 from ceph/wip-diag-14438
- osd: build_past_intervals_parallel() add diagnostics before assert
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:02 PM Revision 0148eacb (ceph): Merge pull request #7588 from dmick/master
- common/page.cc: _page_mask has too many bits
Reviewed-by: Sage Weil <sage@redhat.com> - 08:55 PM Revision 3969b831 (ceph): os/bluestore/KernelDevice: force block size
- Ignore what the file or block device IO Block is.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:16 PM Revision da554ae9 (ceph): Merge pull request #7413 from YankunLi/dev
- rgw: remove duplicated code in RGWRados::get_bucket_info()
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 07:15 PM Revision 4d36bc79 (ceph): Merge branch 'wip-11642-0203'
- 07:15 PM Revision fce9b274 (ceph): rgw: make function parameter 'errordoc_key' passed by reference
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
- 07:03 PM Revision d3e0ca4e (ceph): Merge pull request #7544 from ceph/wip-rh-covscan
- rgw/rgw_orphan: check the return value of save_state
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 07:01 PM Revision 709ab2dd (ceph): Merge pull request #7586 from bsedyang/master
- rgw: user quota may not adjust on bucket removal
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:58 PM Revision cb82fc69 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 06:57 PM Revision 7d10a446 (ceph): doc/release-notes: v10.0.3
- Finalized release notes.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:29 PM Revision a13d9e89 (ceph): rados/upgrade: add '%' to combine rados.yaml with other yamls
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:29 PM Revision ebea8ade (ceph): rados/: remove unnecessary rados.yaml entries
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:17 PM Revision ccd5531e (ceph): common/admin_socket: add chown
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:17 PM Revision 676c489e (ceph): global/global_init: chown log, asok if drop privs is deferred
- If we are deferring the drop privileges, then we are still root
and need to explicitly chown the log file and admin s... - 06:17 PM Revision 32da9626 (ceph): log: add option fchown on log file
- Add explicit call to set the log file uid/gid. fchown it
immediately, and do the same if it is reopened.
Signed-off... - 04:41 PM Revision 2f7463b7 (ceph): Merge branch 'jewel' of https://github.com/ceph/ceph-qa-suite into jewel
- 04:27 PM Revision 9fb57787 (ceph): Whitelisted 'soft lockup' and 'detected stalls on CPUs'
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 367bd5b49c1584b8132fb312be3af83486001fa9) - 04:27 PM Revision f4d1cb01 (ceph): Merge pull request #819 from ceph/wip-whitelist-jewel
- Whitelisted 'soft lockup' and 'detected stalls on CPUs'
- 04:25 PM Revision 367bd5b4 (ceph): Whitelisted 'soft lockup' and 'detected stalls on CPUs'
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 04:00 PM Bug #14724 (Resolved): ceph-disk: list test fail
- ...
- 03:24 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- Attached is a log from osd.0 in a new deployment where I've performed some tests with rbd snapshots. Based on the mon...
- 03:19 PM Revision 8ca144e7 (ceph): OSD/ReplicatedPG: Adding test case to catch issue #14511
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 02:36 PM Revision 4e3ce256 (ceph): Add better documentation of --setuser and --setgroup options for ceph-d...
- Signed-off-by: Mike Shuey <shuey@purdue.edu>
- 02:30 PM Revision 17fe9d22 (ceph): Add --setuser and --setgroup options to ceph-disk(8).
- Signed-off-by: Mike Shuey <shuey@purdue.edu>
- 02:30 PM Revision 3adbe100 (ceph): Add support to override ceph-disk's user and group choices
- Signed-off-by: Mike Shuey <shuey@purdue.edu>
- 02:24 PM Revision dbe0fc61 (ceph): Merge pull request #7592 from dachary/wip-release-notes
- release-notes: draft v10.0.3 release notes
- 02:17 PM Bug #14723 (Resolved): make check bot broken: execvp: /bin/sh: Argument list too long
- A number of errors similar started happening in the past few days. Noone has been able to reproduce it outside of the...
- 02:06 PM Revision efab230b (ceph): tests: sync ceph-erasure-code-corpus for mktemp -d
- Because it's posix and --directory is not.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 01:58 PM Revision c6947b02 (ceph): Merge pull request #7594 from tchaikov/fix-ceph-disk-test
- tests: ceph-disk.sh: should use "readlink -f" instead
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:55 PM Revision 30b257c6 (ceph): ghobject_t: use ! instead of @ as a separator
- @ confuses less's search (/ then @ does not do what you want). !
behaves as expected.
Signed-off-by: Sage Weil <sag... - 01:31 PM Revision 7ba68890 (ceph): tests: ceph-disk.sh: should use "readlink -f" instead
- turns out trusty does not have `realpath` unless the package named
`realpath` is installed.
Reported-by: Joao Eduard... - 12:22 PM Revision 17e310f5 (ceph): tasks/cephfs: add TestConfigCommands
- Get some coverage on the otherwise rarely touched
injectargs and `config set` interfaces.
Fixes: #14365
Signed-off-b... - 12:22 PM Revision 9fd891f0 (ceph): tasks/cephfs: make FuseMount.admin_socket public
- For tests that specifically want to exercise an
asok operation (the test is responsible for
verifying that its mount ... - 12:22 PM Revision 08c28765 (ceph): tasks/cephfs: optionally check result of fuse proc on umount
- For cases where the client process successfully unmounts,
but then crashes before finishing.
Signed-off-by: John Spr... - 12:22 PM Revision 86b4231a (ceph): tasks/cephfs: run ceph-fuse in foreground
- Previously was running this in background, which prevented
checking for nonzero exit codes.
Signed-off-by: John Spra... - 10:12 AM Revision ca5ec8a4 (ceph): release-notes: draft v10.0.3 release notes
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:19 AM Revision 5591cdf4 (ceph): scripts: ceph-release-notes fix merge messages handling
- Strip the title line if it is the same as the pr title instead of
ignoring the message entirely.
Signed-off-by: Loic... - 07:35 AM rgw Backport #14721 (In Progress): hammer: rgw: S3 authentication subsystem should be able to use adm...
- 05:51 AM rgw Backport #14721 (Rejected): hammer: rgw: S3 authentication subsystem should be able to use admin ...
- https://github.com/ceph/ceph/pull/7591
- 07:28 AM Bug #14213 (Resolved): osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- a0b0ae00f25706e702377a915188f7e9a316272f
- 07:26 AM Bug #14372 (Rejected): ENOTSUPP on trimtrunc (EC with cache pool on top)
- I don't think there should be anything in a journal for an unsupported operation.
Everything is working now as exp... - 12:07 AM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- Since we updated the real cluster to Hammer now, I tried using _cephfs-journal-tool event recover_dentries summary_ o...
- 07:25 AM Backport #14720 (In Progress): hammer: OSDMap: reset osd_primary_affinity shared_ptr when deepish...
- 05:42 AM Backport #14720 (Resolved): hammer: OSDMap: reset osd_primary_affinity shared_ptr when deepish_co...
- https://github.com/ceph/ceph/pull/7590
- 07:25 AM Revision d5ba063c (ceph): OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from
- Base on current logic, OSDMonitor may call create_pending and
encode_pending twice for the some epoch.
In encode_pen... - 07:22 AM Backport #14718 (In Progress): hammer: rados cppool omap to ec pool crashes osd
- 05:42 AM Backport #14718 (Rejected): hammer: rados cppool omap to ec pool crashes osd
- 06:19 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. upgrade...
- 06:18 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rados...
- 06:07 AM Stable releases Tasks #13750: infernalis v9.2.1
- ...
- 06:08 AM Backport #13792 (Resolved): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- 06:08 AM CephFS Backport #13889 (Resolved): infernalis: Segmentation fault accessing file using fuse mount
- 06:07 AM CephFS Backport #13931 (Resolved): infernalis: kclient: intermittent log warnings "client.XXXX isn't res...
- 06:07 AM CephFS Backport #14067 (Resolved): infernalis : Ceph file system is not freeing space
- 06:06 AM CephFS Backport #14490 (Resolved): infernalis: fsx failed to compile
- 06:00 AM Revision 4c040503 (ceph): Merge pull request #7431 from Abhishekvrshny/wip-14067-infernalis
- infernalis : Ceph file system is not freeing space
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 05:59 AM Revision 1aa60f66 (ceph): Merge pull request #7429 from Abhishekvrshny/wip-14490-infernalis
- infernalis: fsx failed to compile
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:57 AM Revision 4dc97912 (ceph): Merge pull request #6853 from Abhishekvrshny/wip-13889-infernalis
- infernalis: Segmentation fault accessing file using fuse mount
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 05:57 AM Revision 2bfc75a0 (ceph): Merge pull request #6752 from ukernel/infernalis-11482
- mds: fix client capabilities during reconnect (client.XXXX isn't responding to mclientcaps warning)
Reviewed-by: Yan... - 05:53 AM Revision e71d0629 (ceph): Merge pull request #6628 from Abhishekvrshny/wip-13792-infernalis
- rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:42 AM Backport #14719 (Rejected): infernalis: OSDMap: reset osd_primary_affinity shared_ptr when deepis...
- https://github.com/ceph/ceph/pull/7602
- 05:28 AM Revision 075e595e (ceph): cmake: remove Boost libraries from EXTRALIBS
- * and remove ${Boost_SYSTEM_LIBRARY} from test_rados_api_tier
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:27 AM Revision f5cad7ac (ceph): log: remove "boost/asio.hpp" from Log.h
- graylog uses boost/asio.hpp which introduces the link-time dependency on
libboost_system to the compilation units whi... - 05:20 AM Revision aef2006e (ceph): Revert "cmake: add libboost_system to EXTRALIBS"
- This reverts commit 21438a6773a3153556de07096919ab46c4540eee.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:20 AM Revision ef1573b1 (ceph): cmake: disable warnings introduced by 457f023
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:35 AM Revision 27212c5e (ceph): common/page.cc: _page_mask has too many bits
- It's not used anywhere, but in case it is one day...
Signed-off-by: Dan Mick <dan.mick@redhat.com> - 03:10 AM Linux kernel client Bug #14717 (Closed): "Failures: xfs" in krbd-hammer-testing-basic-smithi
- hammer v0.94.6 QE validation
Run: http://pulpito.ceph.com/teuthology-2016-02-09_08:48:25-krbd-hammer-testing-basi... - 01:18 AM rbd Bug #14147 (Closed): coredumps in rbd-jewel-distro-basic-mira
- no longer happening on jewel
- 01:16 AM rbd Bug #8385: RBD / QEMU Crash: Invalid fastbin entry (free)
- This may be related to http://tracker.ceph.com/issues/14620
- 12:48 AM Revision e85ce445 (ceph): test_rados_api_misc: disconnected rados_monitor_log test
- Piggy-back on LibRadosMiscConnectFailure to confirm that
rados_monitor_log() against a disconnected cluster context f... - 12:22 AM Revision 8c43c2de (ceph): rgw: add id to zonegroup
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 12:22 AM Revision 25a4fbdb (ceph): rgw: Add old_format support to RGWSystemMetaObj
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
02/09/2016
- 11:58 PM CephFS Bug #14716 (Won't Fix): "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
- Jobs:
http://qa-proxy.ceph.com/teuthology/teuthology-2016-02-09_08:45:22-fs-hammer---basic-smithi/1624/teuthology.... - 11:17 PM Revision 1f322cbb (ceph): suites/hammer/older: do not upgrade client while running RBD import/export
- Between the Giant and Hammer releases, the symbols exported from librados/librbd
were cleaned up. This creates a sho... - 10:57 PM Revision b6574f2d (ceph): memstore: fix alignment of Page for test_pageset
- test_pageset creates Pages with size=1, which messes up alignment of the
Page contents and leads to a bus error on ar... - 10:36 PM Revision 29f34b8b (ceph): fix ceph-dencoder link
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 10:36 PM Revision d67cf632 (ceph): rgw: convert old region configuration to zonegroups during init
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 10:36 PM Revision 6b46abcc (ceph): rgw: change RGWZoneGroup::get_pool_name to return string
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 10:36 PM Revision 95770b02 (ceph): rgw: remove region
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 10:34 PM Revision cdc47a34 (ceph): cmake: add rgw_sync.cc and rgw_coroutine.cc
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:51 PM Linux kernel client Bug #14715 (Resolved): "rbd: sysfs write failed" in krbd-hammer-testing-basic-smithi
- this is for QE validation of hammer v0.94.6
Per ICR chat with Jason ... - 09:41 PM CephFS Bug #14714 (Won't Fix): three jobs in samba suite failing for hammer v0.94.6 QE validation
- Runs:
mira
http://pulpito.ceph.com/teuthology-2016-02-09_13:11:14-samba-hammer---basic-mira/
smithi
http://p... - 09:40 PM Revision 647888bb (ceph): rgw: coroutines producer consumers
- Create a new producer-consumer(s) abstraction for the coroutines
infrastructure.
Move environment info from the op in... - 09:40 PM Revision 78192d3c (ceph): rgw: fix async sleep and wakeup logic
- lot's of cleanups and fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 0f18d6e1 (ceph): rgw: fix the simple coroutine
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 48587f02 (ceph): rgw: replace omap_set coroutine code
- No need to use the async rados worker.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 68fd306b (ceph): rgw: keep track of spawned coroutines under the current op
- instead of keeping a per-stack list of spawned coroutines, keep it
on the op that spawned it. Otherwise, we might spa... - 09:40 PM Revision f94164e4 (ceph): rgw: coroutie for omap_get_vals()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 9034bd74 (ceph): rgw: modify sync state, sync run uses state
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 085a9927 (ceph): rgw: read full sync indexes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 89f9d0a9 (ceph): rgw: read remote meta coroutine
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 390c421e (ceph): rgw: naively fetch all meta objects
- doing it one by one, later will spawn these concurrently
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 26e1b7ca (ceph): rgw: full meta sync
- need to handle errors, and update markers, but full meta sync is functional
Signed-off-by: Yehuda Sadeh <yehuda@redh... - 09:40 PM Revision da7940a1 (ceph): rgw: fix async sleep and wakeup logic
- lot's of cleanups and fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 34090518 (ceph): rgw: fix init mdlog sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision d2a17433 (ceph): rgw: adjust mdlog fetch to use new interfaces
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision bfeb6931 (ceph): rgw: remove unused code, cleanups
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision c06e3108 (ceph): rgw: iterate through all mdlog sync status shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 660e21ea (ceph): rgw: return error if any spawned op errored
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 640b49e5 (ceph): rgw: initialize all shard markers
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 42a02224 (ceph): radosgw-admin: dump shard status on mdlog sync status
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision e5521455 (ceph): rgw: remove calls for synchronous rados ops
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision d2fdee3e (ceph): rgw: meta sync cleanups
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 8451effc (ceph): rgw: fetch all metadata entries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 2bcad244 (ceph): rgw: create a coroutine for fetching REST api objects
- this simplifies the code that yanks all the metadata from the master
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 9171db73 (ceph): rgw: build index of all master zone meta keys
- still wip, but getting there
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 9e334eb4 (ceph): rgw: Fix init_complete
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:40 PM Revision 874ff632 (ceph): rgw: fail if master zone tries to use meta sync
- We'll change it later, but as it is now that's the way to handle it
gracefully.
Signed-off-by: Yehuda Sadeh <yehuda@... - 09:40 PM Revision 9457f8b5 (ceph): rgw: rename async ops to coroutines
- which they basically are
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision a1abe968 (ceph): rgw: return retcode of failing coroutine
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 3b07e1a4 (ceph): rgw: move coroutines code
- move the generic code to rgw_coroutine.{h,cc}
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:40 PM Revision 36f0f81b (ceph): rgw: simple rgw metadata write coroutine
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 737f8ba5 (ceph): rgw: prepare rados lock operation to be used with coroutines
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision c510acd9 (ceph): rgw: more lock/unlock coroutines work
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision c31276fa (ceph): rgw: add cookie to lock coroutines
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision 4be55f13 (ceph): rgw: use boost for stackless coroutine flow
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:40 PM Revision b14f85ab (ceph): rgw: mdlog sync init
- initialize mdlog sync state, uses the implicit yield scheme (from boost)
Signed-off-by: Yehuda Sadeh <yehuda@redhat.... - 09:40 PM Revision 796e4703 (ceph): rgw: Rename Region to ZoneGroup only internal structures and class
- User visuable are not changed: admin commands, jsons and rados objects names
Signed-off-by: Orit Wasserman <owasserm... - 09:40 PM Revision c46e5ccf (ceph): rgw: zonegroup json encoding/decoding with backward compatability
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:40 PM Revision db0e2b08 (ceph): rgw: Add zone group admin commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:40 PM Revision 27374b00 (ceph): rgw: Remove region admin commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:40 PM Revision aefa7d16 (ceph): rgw: support old region configurations
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:30 PM rgw Feature #14713 (New): [RFE] remove libfcgi from build
- Deprecate FCGI integration, now that Civetweb is mature.
If we need an embedded configuration again in future, we ... - 09:15 PM Revision 63d7c34f (ceph): global: add DEFER_DROP_PRIVILEGES flag
- This will allow radosgw (or whoever) to drop privileges themselves
in their own special way based on cct->_set_{uid,g... - 09:11 PM Revision 7099e9a9 (ceph): rgw: Add period admin commands and rest api to handle period
- the new commands are prepare,delete, get, activate, pull and push
Signed-off-by: Orit Wasserman <owasserm@redhat.com... - 09:10 PM Revision 95a5130a (ceph): rgw: Add RGWRealm class and admin commands to handle it
- admin realm commands: create, get, delete, rename, set-default and get-default
Signed-off-by: Orit Wasserman <owasse... - 09:10 PM Revision 53426600 (ceph): rgw: Add RGWPeriod
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:59 PM Revision 787ee9ac (ceph): cmake: add rgw_sync.cc
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:59 PM Revision ced45f4e (ceph): rgw: fix test_rgw_admin_log.cc
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:59 PM Revision 065fa7c5 (ceph): rgw: Add RGWNameToId and RGWDefaultSystemMetaObjInfo
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:59 PM Revision 2196eeb3 (ceph): rgw: Add RGWSystemMetaObj class
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Conflicts:
src/rgw/rgw_rados.cc - 08:59 PM Revision 417ac39e (ceph): rgw: use string for default realm
- Conflicts:
src/rgw/rgw_rados.cc - 08:59 PM Revision c77a5e5f (ceph): rgw: Use switch for raw storage opcodes
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:59 PM Revision 3e037249 (ceph): rgw: async rados requests through a work queue
- Tie in the async rados requests to the async framework.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:59 PM Revision 72b0986a (ceph): rgw: create simple async op handler
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:59 PM Revision b8399ffb (ceph): rgw: some cleanup, keep async env structure
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:59 PM Revision 7daa80a7 (ceph): rgw: more simplification, no need to take reference to op
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:59 PM Revision 901ebb50 (ceph): rgw: more simplification
- create a helper method in the ops manager to run a single op, it
builds the needed env
Signed-off-by: Yehuda Sadeh <... - 08:59 PM Revision 9a7a2292 (ceph): rgw: add another state for simple async ops
- so that these ops can chain other ops and handle their
response
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:59 PM Revision dee7505d (ceph): rgw: add a generic op to pull data off metadata obj
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:59 PM Revision 2534452b (ceph): rgw: a few bug fixes related to async operations
- fix uninitialized state, trim stacks, etc.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:59 PM Revision 4396fd4a (ceph): rgw: async ops can generate new stacks for parallel execution
- Can now have an op generating another op that will be called at
a different stack. The current op will halt execution... - 08:59 PM Revision 5e2c2e4c (ceph): rgw-admin: command to show mdlog sync status
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:59 PM Revision a736c25a (ceph): rgw: retrieve a specific sync shard info
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:58 PM Revision 9e233880 (ceph): rgw: md log cloning completely async
- hook librados completions into the rgw completion notifier, split the
md log write into two different states.
Signed... - 08:58 PM Revision 601018a5 (ceph): some error handling work, not ready yet
- 08:58 PM Revision 38424cdc (ceph): rgw: mdlog sync error reporting on failed request
- Basic error reporting. We'll need to dump this to the backend and
add admin commands to read.
Signed-off-by: Yehuda ... - 08:58 PM Revision 0c0d8b0c (ceph): rgw: create some abstraction around async ops infrastructure
- This will be reused later for other operations.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:58 PM Revision ff05ddbf (ceph): rgw: hide the completion manager
- some more layer separation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:58 PM Revision d4a9051a (ceph): rgw: don't reference msg after finish_request()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:58 PM Revision 8f36e609 (ceph): rgw: clean up mdlog clone states, other fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:58 PM Revision 1c9079ab (ceph): rgw: read mdlog marker
- Use our local marker as a starting point for fetching the mater mdlog.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:58 PM Revision 624a3fa0 (ceph): rgw: initial work on sync status marker
- Also, rename radosgw-admin mdlog sync to radosgw-admin mdlog-fetch.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:58 PM Revision dd472a16 (ceph): rgw: stackable ops infrastructure
- ops can now call other ops, so that we could simplify
the different states each ops need to keep.
Signed-off-by: Yeh... - 08:58 PM Revision 66c1e52b (ceph): rgw: can now wait on async rest requests
- In addition to waiting on a specific request, added a
completion manager that we can wait on so that we get
which req... - 08:58 PM Revision c3206b9b (ceph): rgw: rework metadata log sync to use async capabilities
- We now have a window of operations. The next step will be to
asynchronously write to the local mdlog, so that we don'... - 08:57 PM Revision fe0c7858 (ceph): rgw: add new class to create resource request
- RGWRESTReadResource holds the request input and output. Previously
we were using stack variables that couldn't be use... - 08:52 PM Revision 18bee31a (ceph): rgw: threaded http manager groundwork
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:52 PM Revision 2fbf80ff (ceph): rgw: more http aio stuff
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:52 PM Revision fbc5ef11 (ceph): rgw: can list mdlog entries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:52 PM Revision eac4e794 (ceph): rgw: initial mdlog clone implementation
- naive handling, not paging, unbalanced.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:52 PM Revision 55255b21 (ceph): rgw: paginated mdlog clone
- still need to iterate by going through over older entries first
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:52 PM Revision ad161bc5 (ceph): rgw: rework http client to handle multiple async requests
- Currently we use the curl multi handler using only a single handle. Rework
things a bit to prepare for multiple handl... - 08:52 PM Revision 866fd740 (ceph): rgw: more work on cleaning up http client interfaces
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:45 PM Revision 12a32373 (ceph): rgw: don't do set_attr on meta objects
- only complete object writes (and attributes) is now available. This helps
managing the meta heap and simplifies the s... - 08:45 PM Revision d5484ff2 (ceph): rgw: initial work on mdlog sync
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:45 PM Revision cdc953f6 (ceph): rgw-admin: initial mdlog sync work
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:45 PM Revision a3d500e8 (ceph): rgw: fix use of zone name
- zone_name doesn't really hold what we need
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:45 PM Revision 2c48adec (ceph): rgw: decode number of mdlog shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:45 PM Revision deb72c5a (ceph): ceph_json: make sure header doesn't clobber _ASSERT_H
- _ASSERT_H is needed for dout() compilation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:45 PM Revision 2124ee5d (ceph): rgw: move json helper into RGWRESTConn
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:03 PM Revision 06507992 (ceph): rgw: user quota may not adjust on bucket removal
- Description:
If the user/admin removes a bucket using --force/--purge-objects options with s3cmd/radosgw-admin respec... - 07:31 PM rgw Bug #13644: get_quota_info returns json in headers
- This fix is in hammer since 0.94.3. Do you still have an issue there?
- 07:29 PM rgw Bug #14375: subuser rm fails with status 125
- master pr: https://github.com/ceph/ceph/pull/7301
- 07:25 PM rgw Bug #14361: swift/test/functional -v -a '!fails_on_rgw'
- seems like osd wasn't responding, so after restarting rgw it timed out.
- 07:15 PM rgw Bug #14665: radosgw-admin -n client.0 user create : permission denied
- This looks like a racing yum update and radosgw-admin execution.
- 05:33 AM rgw Bug #14665: radosgw-admin -n client.0 user create : permission denied
- You're correct, it looks like something related to permissions is not right when testing with infernalis. I searched ...
- 07:10 PM rgw Bug #14653: "test_s3.test_abort_multipart_upload ... FAIL" in upgrade:hammer-hammer-distro-basic-...
- Looks like some environment issue, or just regular timeout due to slow osds maybe.
2016-02-03T20:49:51.772 INFO:ta... - 07:06 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
- This is a bogus test. The upgrade is done while spawning radosgw-admin. We can see librados being upgraded through th...
- 06:44 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- http://pulpito.ceph.com/gregf-2016-02-08_22:02:06-fs-greg-fs-testing-27-1---basic-mira/1009/
Also this failure see... - 03:06 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- Dunno — it's QuotaFull rather than ClusterFull so I created a new ticket.
- 11:17 AM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- Different to http://tracker.ceph.com/issues/14258 ?
- 06:24 PM Bug #14511: cache-flush-evict-all causes OSD stuck ops on unevictable objects
- PR is at
https://github.com/ceph/ceph/pull/7584
- 06:23 PM Revision 5dfcdf69 (ceph): librados: check connection state in rados_monitor_log
- rados_monitor_log() may abort the calling process if called with a
disconnected rados cluster context. Return -ENOTCO... - 06:21 PM Revision 676699dc (ceph): rgw: rename default pool names
- Name default pools a bit better
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 06:21 PM Revision 89784aa8 (ceph): rgw: store immutable metadata entries in heap pool
- Define a new pool for immutable metadata, store new meta objects
in that pool.
(still need to work on the set_attrs c... - 06:21 PM Revision 1fe7372f (ceph): rgw: don't require system pools to start with a period
- Make sure cache operations are being done on system objects.
Separate calls where needed to make sure that separate p... - 06:19 PM Revision 4cc98434 (ceph): OSD/ReplicatedPG: Fixing lack of object unblock when flush fails.
- See: http://tracker.ceph.com/issues/14511
Signed-off-by: Igor Fedotov <ifedotov@mirantis.com> - 05:59 PM Revision ee7ac8f6 (ceph): cmake: add cls_timeindex to rgw targets
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:46 PM Revision f3ac0513 (ceph): test: fsx now exercises librbd journal replay
- write, discard, snap create, snap protect, flatten, and resize journal
events are tests when using the new '-j' optio... - 05:44 PM Revision 851395a8 (ceph): librbd: do not fire flush completions before associated write
- Prevents a race condition in journal replay when committing events
to the journal.
Signed-off-by: Jason Dillaman <di... - 05:44 PM Revision f08ccc5b (ceph): librbd: missing lock on maint operation replay callback
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:27 PM Bug #14711 (Can't reproduce): OSD crashes with Suicide timeout due to timeout on FileStore::op_tp...
- Doing migrations from Ubuntu 14.04 to RHEL 7.1.
- First cluster was migrated successfully and it is running RHEL-7.... - 04:52 PM Bug #14710 (Duplicate): Bad output from 'ceph df' causes problems for cinder
- When adding OSD's to a cluster using 'ceph-disk prepare' (by way of ceph-ansible) on all the new OSDs. This brings t...
- 04:34 PM Revision ee1fafa3 (ceph): OSD/ReplicatePG: Fixes return value from maybe_handle_cache_detail() de...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com
- 03:49 PM Bug #14709 (Resolved): check_PROGRAMS used instead of check_TESTPROGRAMS
- This causes some tests to not be run on make check...
- 03:41 PM Bug #14521 (Won't Fix): Failure on restart after repairing corrupted PG
- we don't plan to handle this level of damage. recreate the osd.
- 03:40 PM rbd Backport #14620: hammer: unsafe use of libnss PK11_GetBestSlot()
- Maybe http://tracker.ceph.com/issues/14367 is the corresponding issue ?
- 06:34 AM rbd Backport #14620 (Fix Under Review): hammer: unsafe use of libnss PK11_GetBestSlot()
- 06:22 AM rbd Backport #14620 (In Progress): hammer: unsafe use of libnss PK11_GetBestSlot()
- 06:21 AM rbd Backport #14620: hammer: unsafe use of libnss PK11_GetBestSlot()
PK11_GetBestSlot() does not appear to be threadsafe, and can be called from multiple threads, leading to a crash si...- 03:39 PM Bug #14544 (Closed): the pool usage data reported in ceph df is misleading
- MAX AVAIL is free space that you can write to.
- 03:39 PM Bug #14367: auth: possible race by using PK11_CreateContextBySymKey from multiple threads
- Does https://github.com/ceph/ceph/pull/3896 fix this ? In which case http://tracker.ceph.com/issues/14620 would be th...
- 03:38 PM Bug #14560 (Resolved): bluestore: assertion failed when starting scrub
- 03:37 PM Bug #14590 (Won't Fix): cephfs set directory layout datapool to 0 failed
- 03:32 PM Bug #14568: "Caught signal" (out of memory?) in rados-hammer-distro-basic-vps
- ignore enomem on vps
- 03:32 PM Bug #14568 (Rejected): "Caught signal" (out of memory?) in rados-hammer-distro-basic-vps
- vps oom
- 03:30 PM Bug #14623 (Resolved): Crush:add safe judgment for get parent hierarchy methond.
- 03:30 PM Bug #14634 (Duplicate): "Command failed (workunit test rest/test.py)" in rados-jewel-distro-basic...
- 03:29 PM Bug #13953: ceph-disk command used with --log-stdout failing.
- 03:28 PM Bug #14658 (Resolved): "Failed to execute command: systemctl enable ceph.target" in smoke-master-...
- 03:27 PM Bug #14633 (Can't reproduce): (KStore) "(Segmentation fault)" in rados-jewel-distro-basic-smithi
- 03:27 PM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- 03:24 PM Bug #14706: systemd escaping of block devices in ceph-disk incorrect
- 11:54 AM Bug #14706: systemd escaping of block devices in ceph-disk incorrect
- Pull request raised to resolve this in master:
https://github.com/ceph/ceph/pull/7579 - 10:56 AM Bug #14706 (Resolved): systemd escaping of block devices in ceph-disk incorrect
- ceph-disk currently does a replace on '-' to generate the name of the unit for the ceph-disk activation:
# http:... - 03:23 PM Bug #14695 (Pending Backport): osd: rados cppool omap to ec pool crashes osd
- Yeah, that looks like the one that needs to be backported.
- 03:16 PM Bug #14708 (Rejected): Semi-crashed OSDs cause cluster to hang
- We triggered a weird kernel/ext4 bug on a server this weekend which caused the OSD processes to keep running but beco...
- 02:25 PM Bug #14707 (Resolved): log: segv during _flush on very big long lines
- Easy to reproduce with debug bdev = 40 and bluestore....
- 02:02 PM Revision 2c79a5e4 (ceph): Merge pull request #7496 from xiexingguo/xxg-wip-fixnvme
- osd: BlueStore/NVMEDevice: fix compiling and fd leak
Reviewed-by: Haomai Wang <haomai@xsky.com> - 01:58 PM Revision a20134d9 (ceph): Merge pull request #7349 from yuyuyu101/add-pwritev
- osd: FileStore: use pwritev instead of lseek+writev
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil... - 01:57 PM Revision a710dcd8 (ceph): Merge pull request #7504 from renhwsky/renhw-wip-mon-shutdown
- mon: unregister command on shutdown
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 01:56 PM Revision c2342b53 (ceph): Merge pull request #7550 from tchaikov/wip-osd-cleanup
- osd: a fix for HeartbeatDispatcher and cleanups
Reviewed-by: Sage Weil <sage@redhat.com> - 01:56 PM Bug #14686 (Pending Backport): OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from
- 01:56 PM Revision 8895416a (ceph): Merge pull request #7553 from XinzeChi/wip-osdmap-affinity
- osd: OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from
Reviewed-by: Sage Weil <sage@redhat.com> - 01:55 PM Revision 8205c873 (ceph): Merge pull request #7560 from tchaikov/wip-fix-icl
- crush/CrushTester: workaround a bug in boost::icl
- 01:55 PM Revision be5544b2 (ceph): Merge pull request #7568 from liewegas/wip-bluestore-mutex
- osd: bluestore/blockdevice: use std::mutex et al
- 01:55 PM Revision ee39f436 (ceph): Merge pull request #7570 from dzafman/wip-14213
- osd: revert "osd: do not keep ref of old osdmap in pg"
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: S... - 01:41 PM Revision 66663000 (ceph): debian: fix build-depends
- Signed-off-by: Rémi BUISSON <remi.buisson@cdiscount.com>
- 12:57 PM Revision 278acb6a (ceph): Merge pull request #7578 from ceph/fix-stripper
- Stripper: Fix incorrect push_front -> append_zero change
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:19 PM Revision f06c4dc1 (ceph): osdc/Objecter: drop lock to unregister asok hooks
- unregister blocks until any running hook has
completed, and that running hook might
be one that takes the objecter lo... - 12:18 PM Revision be5748a8 (ceph): common: asok should drop lock to call hook
- Otherwise, hooks cannot take any locks which
were held during registration of hooks, because
it creates a cycle.
Sig... - 11:17 AM RADOS Feature #14527: Lookup monitors through DNS
- Dan van der Ster wrote:
> Ahh OK. DNS SRV records might be better than a hardcoded hostname. See the DNS section her... - 11:06 AM RADOS Feature #14527: Lookup monitors through DNS
- Assigning this to Ricardo. He's looking into it.
- 11:13 AM Revision c28c0b18 (ceph): Correctly escape block device paths for systemd
- Ensure that the leading / is stripped from block device
paths before escaping for using in systemd unit names.
Fixes... - 10:05 AM Revision 1bdd3b06 (ceph): mailmap: Kevin Jones affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision ee4ca535 (ceph): mailmap: JP François affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 70848c4b (ceph): mailmap: Jeffrey Lu affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 3bb9f86b (ceph): mailmap: Ivan Grcic affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 4ba58fe0 (ceph): mailmap: Gu Zhongyan affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision a03c3f07 (ceph): mailmap: Chuanhong Wang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 63d38683 (ceph): mailmap: Benoît Knecht affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 8b750bf7 (ceph): mailmap: Alexey Sheplyakov affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 18d3a166 (ceph): mailmap: Alan Grosskurth affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 0312174b (ceph): mailmap: Jonas Keidel affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 23f27385 (ceph): mailmap: Emile Snyder affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 8c035335 (ceph): mailmap: Matt Benjamin affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision afcc6666 (ceph): mailmap: Erwan Velu affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision b27bc0da (ceph): mailmap: Robert LeBlanc affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 230bb728 (ceph): mailmap: Marcel Lauhoff affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision bbbd2ecf (ceph): mailmap: Sahithi R V affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 712c52bb (ceph): mailmap: Jianjian Huo affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 5736f9c3 (ceph): mailmap: Wei Jin affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 951c3312 (ceph): mailmap: Roi Dayan affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision a71ae4a6 (ceph): mailmap: Rachana Patel affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 8c317ea7 (ceph): mailmap: Patrick Donnelly affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 26035b5f (ceph): mailmap: Mauricio Garavaglia affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 6a0c84bb (ceph): mailmap: Lukasz Jagiello affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:05 AM Revision 28c21080 (ceph): mailmap: Barbora Ančincová affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:46 AM Revision 12ea474c (ceph): Stripper: Fix incorrect push_front -> append_zero change
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 08:16 AM CephFS Backport #13932 (New): hammer: kclient: intermittent log warnings "client.XXXX isn't responding t...
- 08:02 AM CephFS Backport #13932 (In Progress): hammer: kclient: intermittent log warnings "client.XXXX isn't resp...
- 07:59 AM CephFS Backport #13932: hammer: kclient: intermittent log warnings "client.XXXX isn't responding to mcli...
- I think the PR to backport is https://github.com/ceph/ceph/pull/6432 - it was merged on November 30.
- 06:04 AM CephFS Backport #13932: hammer: kclient: intermittent log warnings "client.XXXX isn't responding to mcli...
- Zheng, was there something wrong with that PR or something?
- 06:01 AM CephFS Backport #13932 (New): hammer: kclient: intermittent log warnings "client.XXXX isn't responding t...
- The proposed PR has been closed, assuming no work is otherwise being done.
- 07:56 AM Bug #8885: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
I wasn't able to reproduce.
Based on the location of what I assume is a segfault the value of register bp was co...- 06:48 AM Stable releases Tasks #14692: hammer v0.94.7
- h3. rbd...
- 06:46 AM Stable releases Tasks #14692: hammer v0.94.7
- h3. rados...
- 06:46 AM Stable releases Tasks #14692: hammer v0.94.7
- h3. upgrade...
- 06:45 AM Stable releases Tasks #14692: hammer v0.94.7
- h3. powercycle...
- 06:45 AM Stable releases Tasks #14692: hammer v0.94.7
- h3. rgw...
- 06:44 AM Stable releases Tasks #14692: hammer v0.94.7
- h3. fs...
- 06:40 AM Stable releases Tasks #14692: hammer v0.94.7
- ...
- 06:33 AM Backport #14689 (In Progress): hammer: consume_maps clearing of waiting_for_pg needs to check the...
- 06:33 AM Revision 9e0a1656 (ceph): OSD::consume_map: correctly remove pg shards which are no longer acting
- A particular shard may be non-active even if the osd is in the acting
set.
Fixes: 14278
Backport: hammer
Signed-off-... - 06:32 AM Backport #14579 (In Progress): hammer: mon sync does not copy config-key
- 06:31 AM Revision 5a450e67 (ceph): mon: add mon_config_key prefix when sync full
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
(cherry picked from commit b77cd31b161e78467bbb6476776c0f1d43e615cf) - 06:14 AM rgw Bug #14516 (Resolved): rgw: radosgw-admin --help doesn't show the "orphans find" command
- 06:14 AM rbd Bug #14476 (Resolved): rbd: TaskFinisher::cancel should remove event from SafeTimer
- 06:14 AM rbd Feature #13633 (Resolved): Verify self-managed snapshot functionality on image create
- 06:14 AM rbd Bug #14452 (Resolved): rbd-replay does not check for EOF and goes to endless loop
- 06:14 AM Bug #12946 (Resolved): Heavy memory shuffling in rados bench
- 06:14 AM devops Bug #12927 (Resolved): ceph.spec.in libcephfs_jni1 has no %post and %postun
- 06:14 AM Bug #12012 (Resolved): IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from...
- 06:14 AM Bug #11101 (Resolved): ceph tell: broken error message / misleading hinting
- 06:14 AM Bug #10930 (Resolved): mon: map_cache can become inaccurate if osd does not receive the osdmaps
- 06:14 AM rgw Feature #6999 (Resolved): Make RGW_MAX_PUT_SIZE configurable
- 06:11 AM Backport #13288: hammer: stuck recovering, unfound hit set due to removing it while !active
- @Kefu, assigning to you as I'm not familiar with the original patch
- 05:59 AM CephFS Backport #14668: hammer: Wrong ceph get mdsmap assertion
- It is unfortunately too late, v0.94.6 is already frozen and being tested.
- 05:58 AM Backport #12835 (Resolved): mon: map_cache can become inaccurate if osd does not receive the osdmaps
- 05:48 AM Backport #12835 (In Progress): mon: map_cache can become inaccurate if osd does not receive the o...
- 05:57 AM rbd Backport #14142 (Resolved): infernalis: Verify self-managed snapshot functionality on image create
- 05:57 AM rbd Backport #14199 (Resolved): infernalis: [ FAILED ] TestLibRBD.SnapRemoveViaLockOwner
- 05:57 AM Backport #14236 (Resolved): "OSDMonitor.cc: 2116: FAILED assert(0)" in rados-hammer-distro-basic-...
- 05:48 AM Backport #14236 (In Progress): "OSDMonitor.cc: 2116: FAILED assert(0)" in rados-hammer-distro-bas...
- 05:57 AM rbd Backport #14321 (Resolved): infernalis: cls_rbd: object_map_save should enable checksums
- 05:56 AM Backport #14643 (Resolved): hammer: rgw: radosgw-admin man page doesn't contain the "orphans" com...
- 05:53 AM Backport #14643 (In Progress): hammer: rgw: radosgw-admin man page doesn't contain the "orphans" ...
- 05:49 AM Backport #14087 (In Progress): FAILED assert(old_size == total_chunk_size) in 0.94.5 / strange fi...
- 04:58 AM Revision 6552eeb2 (ceph): Merge pull request #7079 from Abhishekvrshny/wip-14199-infernalis
- infernalis: [ FAILED ] TestLibRBD.SnapRemoveViaLockOwner
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:58 AM Revision e507a5f9 (ceph): Merge pull request #7080 from Abhishekvrshny/wip-14142-infernalis
- infernalis: Verify self-managed snapshot functionality on image create
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:57 AM Revision 930ef946 (ceph): Merge pull request #7428 from Abhishekvrshny/wip-14321-infernalis
- infernalis: cls_rbd: object_map_save should enable checksums
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:39 AM devops Cleanup #14705 (Closed): Reinstate ceph-osd@.service.in
- On RH and derivatives, ...
- 04:16 AM devops Bug #14687: RPM: no /usr/libexec directory on SUSE
- Discussed on ceph-devel mailing list. Consensus seems to be to use ...
- 01:12 AM CephFS Bug #13980: all nfs v3 mounts fail in ovh lab
- and in http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-07_20:10:01-knfs-hammer-testing-basic-openstack/
- 12:48 AM Revision 7731ae92 (ceph): Merge pull request #7444 from dreamhost/wip-rgw-static-website-robbat2
- rgw: approximate AmazonS3 HostId error field.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
02/08/2016
- 10:40 PM Revision 3fe17c6c (ceph): mailmap: fangdong affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision ab6baa95 (ceph): mailmap: Shishir Gowda affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision 2a35e185 (ceph): mailmap: Tao Chang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision 30392482 (ceph): mailmap: Harry Harrington affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision 833c8e2b (ceph): mailmap: Jingkai Yuan affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision f59db3cf (ceph): mailmap: Luo Kexue affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision 5bda3a25 (ceph): mailmap: some duplicates found on .organizationmap
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision e8e0521c (ceph): mailmap: Shun Song affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision 78d91d6e (ceph): mailmap: Adam Twardowski affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:36 PM Revision 588eeea4 (ceph): mailmap: Aron Gunn affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:26 PM Revision 117041ef (ceph): Merge remote-tracking branch 'gh/jewel'
- 10:26 PM Revision f22b6714 (ceph): Merge remote-tracking branch 'gh/jewel'
- 10:10 PM Revision efc8134f (ceph): v10.0.3
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:02 PM Revision e96a3fe0 (ceph): Changed centos version to 7.2
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 3f4a5caeb2f1fffc302be69d3ef06fff3566fe7e) - 10:00 PM Revision aa207c29 (ceph): Changed centos version to 7.2
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 3f4a5caeb2f1fffc302be69d3ef06fff3566fe7e) - 09:17 PM devops Bug #14694: ceph.spec.in missing copyright notice; cannot submit package to openSUSE
- *jewel PR*: https://github.com/ceph/ceph/pull/7569
- 03:48 PM devops Bug #14694 (Resolved): ceph.spec.in missing copyright notice; cannot submit package to openSUSE
- 02:57 PM devops Bug #14694 (In Progress): ceph.spec.in missing copyright notice; cannot submit package to openSUSE
- 02:57 PM devops Bug #14694 (Resolved): ceph.spec.in missing copyright notice; cannot submit package to openSUSE
- $SUBJ pretty much says it all
- 09:00 PM Revision ac61c112 (ceph): mailmap: Ren Huanwen affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:00 PM Revision eaf5bc7d (ceph): mailmap: Yehua Chen affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:00 PM Revision b57a3ac1 (ceph): mailmap: Li Tianqing affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:00 PM Revision 2a3ce4ef (ceph): mailmap: Ilya Shipitsin affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:00 PM Revision 467990a5 (ceph): mailmap: Darrell Enns affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:00 PM Revision 17d2622b (ceph): mailmap: Abhishek Lekshmanan affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:00 PM Revision 8556b9d5 (ceph): mailmap: further cleanup.
- Somehow a followup to #581c65dd48807a516b43adec4b5be29c040db8c7
Work was half-done, and mailmap can be further simpl... - 08:54 PM rgw Bug #14665: radosgw-admin -n client.0 user create : permission denied
- From the logfile, radosgw-admin can't bind to the radosgw admin socket (Permission denied error).
On a test system... - 08:46 PM Revision c423d5fc (ceph): mailmap: Zhi Zhang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:46 PM Revision 20783f83 (ceph): mailmap: YiQiang Chen affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:46 PM Revision f5bcdae8 (ceph): mailmap: François Lafont affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:46 PM Feature #14701 (Resolved): allow add --pg-num to osdmaptool --test-map-pgs to override the map's ...
- This way, users could test pg_num changes before doing them live.
- 08:45 PM Revision fcd3bba6 (ceph): mailmap: Adam C. Emerson affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:45 PM Revision 84f58b57 (ceph): mailmap: Xiangwei Wu affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:45 PM Revision c2e0b8f1 (ceph): mailmap: Zhiqiang Wang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:45 PM Revision f960bcc4 (ceph): mailmap: Song Baisen affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:45 PM Revision 0fe93736 (ceph): mailmap: Xie Xingguo affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:45 PM Revision 638c6369 (ceph): mailmap: Dunrong Huang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:45 PM Revision 10bb9a45 (ceph): mailmap: Liu Peiyan affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:44 PM Revision b5d76886 (ceph): mailmap: Cleanup.
- Over time, some entries were unnecessarily complicated.
Entries were sometimes of the form :
Canonical name <canoni... - 08:43 PM rbd Feature #14700 (Rejected): rbd map should optionally support the advisory locking and blacklisting
- Original proposal:...
- 08:00 PM Revision 4815a466 (ceph): Merge pull request #7572 from ceph/wip-cmake-2-8-16
- cmake: Added new unittests to make check
- 07:12 PM Revision c8c1603f (ceph): global: record target uid/gid in cct
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:04 PM CephFS Bug #14698 (Duplicate): Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
- http://pulpito.ceph.com/gregf-2016-02-08_00:50:24-fs-greg-fs-testing-27-1---basic-mira/10806/
http://pulpito.ceph.co... - 06:43 PM Revision 07dda1aa (ceph): Merge pull request #7574 from SUSE/wip-spec-license
- ceph.spec.in: add license declaration
Reviewed-by: Sage Weil <sage@redhat.com> - 06:32 PM CephFS Bug #14697 (Resolved): mds: assert in SafeTimer while suiciding
- http://pulpito.ceph.com/gregf-2016-02-08_00:50:24-fs-greg-fs-testing-27-1---basic-mira/10767/...
- 06:19 PM Bug #14660: selinux denials during rbd test run
- Boris, you are looking at the end of the logs, I think during the test end it does try to stop those daemons as you h...
- 04:51 PM Bug #14660: selinux denials during rbd test run
- Yes, the policy is installed in both cases. However, there is an issue with the way daemons are being started/stopped...
- 05:57 PM Revision db9408bf (ceph): ceph.spec.in: add license declaration
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 05:30 PM Revision 51a15726 (ceph): cmake: Added new unittests to make check
- Added unittest_shunique_lock & unittest_mutex_debug
to make check, and made them link ALLOC_LIBS
Signed-off-by: Ali ... - 05:27 PM rgw Feature #13302 (Pending Backport): rgw: S3 authentication subsystem should be able to use admin c...
- 04:40 PM Bug #14695 (Resolved): osd: rados cppool omap to ec pool crashes osd
- If we do cppool from a replicated pool to erasure in hammer 0.94.5, this will cause an OSD assert error when it tries...
- 04:34 PM Revision 0ca8f07a (ceph): global/global_init: ensure setuser etc messages get logged
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:19 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. QE VALIDATION (STARTED 2/8/16)
*re-runs command lines and filters are captured in http://pad.ceph.com/p/hammer... - 04:12 PM Revision 8290536d (ceph): global/global_init: do not apply_changes until after dropping privs
- This ensures we open the log file a the final user, not as root.
Fixes: #14613
Signed-off-by: Sage Weil <sage@redhat... - 04:11 PM CephFS Bug #14672 (Rejected): MDS crashes with FAILED assert(inode_map.count(in->vino()) == 0) in 9.2.0
- Yeah, I'm pretty sure about that.
- 11:55 AM CephFS Bug #14672: MDS crashes with FAILED assert(inode_map.count(in->vino()) == 0) in 9.2.0
- Was this the system that you ran newfs on? I think I was concerned that this might be from running newfs while the m...
- 04:06 PM Bug #14213: osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- quote from sam
> we need to hold the reference to prevent the map from being trimmed. that reference is the map ep... - 03:48 PM Revision 4235af3c (ceph): Merge pull request #7569 from SUSE/wip-copyright2
- ceph.spec.in: add copyright notice
Reviewed-by: Sage Weil <sage@redhat.com> - 03:45 PM Revision a0b0ae00 (ceph): Revert "osd: do not keep ref of old osdmap in pg"
- This reverts commit 8978cd6fcf40076dbd944a2938b335d26c62b8d5.
Fixes: #14213 - 03:44 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- A fix related to this tracker caused 14213.
- 03:38 PM rgw Bug #13824 (Pending Backport): orphans finish segfaults
- Will be marked Resolved after infernalis backport is merged.
- 02:33 PM rgw Bug #13824: orphans finish segfaults
- Please mark as resolved.
- 03:34 PM Bug #13471 (Resolved): OSD::build_past_intervals_parallel() shall reset primary and up_primary wh...
- 03:33 PM Bug #13639 (Resolved): Objecter: potential null pointer access when do pool_snap_list.
- 03:33 PM Bug #14015 (Resolved): osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info.history.last...
- 03:33 PM Bug #13962 (Resolved): "shard missing" errors in logs during Teuthology run
- 03:32 PM Bug #13840 (Resolved): Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- 03:32 PM Bug #13862 (Resolved): pgs stuck inconsistent after infernalis upgrade
- 03:32 PM Bug #13642 (Resolved): Objecter: pool op callback may hang forever.
- 03:26 PM rbd Backport #14465 (Resolved): infernalis: rbd-replay does not check for EOF and goes to endless loop
- 03:26 PM rbd Backport #14552 (Resolved): infernalis: rbd: TaskFinisher::cancel should remove event from SafeTimer
- 03:25 PM rgw Backport #14676 (Resolved): infernalis: rgw: radosgw-admin --help doesn't show the "orphans find"...
- 03:24 PM devops Bug #13958 (Resolved): 'sudo yum install ceph-radosgw -y' errors in upgrade:firefly-hammer-x-infe...
- @Loic: librbd is a dependency of qemu so ansible probably installs qemu(-kvm) which in-turn installs librbd1 and libr...
- 03:54 AM devops Bug #13958: 'sudo yum install ceph-radosgw -y' errors in upgrade:firefly-hammer-x-infernalis-dist...
- Another variation of the same problem ?
* http://pulpito.ceph.com/loic-2016-02-04_22:33:36-rados-infernalis-backpo... - 03:23 PM Revision 1061db6b (ceph): Merge pull request #7427 from Abhishekvrshny/wip-14465-infernalis
- infernalis: rbd-replay does not check for EOF and goes to endless loop
Reviewed-by: Jason Dillaman <dillaman@redhat.... - 03:23 PM Revision 2de60165 (ceph): Merge pull request #7426 from Abhishekvrshny/wip-14552-infernalis
- infernalis: rbd: TaskFinisher::cancel should remove event from SafeTimer
Reviewed-by: Jason Dillaman <dillaman@redha... - 03:10 PM Feature #14677 (Resolved): ceph-disk list should have json output option
- already exists in infernalis, yay!
- 03:04 PM Revision 23ec516b (ceph): ceph.spec.in: add copyright notice
- http://tracker.ceph.com/issues/14694 Fixes: #14694
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 02:53 PM Revision 434620ba (ceph): os/bluestore/BlockDevice: use std::mutex and std::condition_variable
- Pull aio wait code into an IOContext method too.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:53 PM Revision 37b517eb (ceph): os/bluestore/BlockDevice: std::atomic_int
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:23 PM Revision 3f66231e (ceph): Merge pull request #7513 from athanatos/wip-ceph-test-rados-2
- ceph_test_rados: use less CPU
- 02:23 PM Revision 6a8cafe1 (ceph): Merge pull request #5931 from ceph/wip-cxx11concurrency
- librados: move to c++11 concurrency types
Reviewed-by: Matt Benjamin <mbenjami@redhat.com>
Reviewed-by: Casey Bodley... - 02:18 PM Revision 7181a6f1 (ceph): msg/simple: significantly reduce minimal memory usage of Pipes
- Pipe class instance weights over 17 KB in size, and most of it is used by
msgvec structure, which weights 16 KB. Redu... - 02:18 PM Cleanup #6634 (Resolved): MOSDSubOp: remove unused snapc/snapcontext members
- 02:17 PM Revision f17dbc65 (ceph): Merge pull request #6608 from esnyder/wip-6634
- osd: remove unused SnapContext member snapc from MOSDSubOp message
Reviewed-by: Xiaoxi Chen <xiaoxi.chen@intel.com>
... - 02:16 PM Revision 69d98b65 (ceph): msg/async: significantly reduce minimal memory usage of AsyncConnections
- AsyncConnection class instance weights over 18 KB in size, and most of it
is used by msgvec structure, which weights ... - 02:16 PM Revision a981c1ec (ceph): Merge pull request #7181 from songbaisen/song5
- crush: reply quickly from get_immediate_parent
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:15 PM Revision 20228cb0 (ceph): Merge pull request #7437 from Ved-vampir/wip_zlib_plugin
- common: add zlib compression plugin
Reviewed-by: Sage Weil <sage@redhat.com> - 02:14 PM Revision 7e442996 (ceph): Merge branch 'print-blocked-op' of git://github.com/majianpeng/ceph
- Reviewed-by: Sage Weil <sage@redhat.com>
- 02:13 PM Revision 34d33bcc (ceph): Merge pull request #7527 from liewegas/wip-no-rgw-prestart
- systemd/ceph-radosgw-prestart.sh: remove
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 02:12 PM Revision 65878073 (ceph): Merge branch 'master' of git://github.com/joconcepts/ceph
- Reviewed-by: Sage Weil <sage@redhat.com>
- 02:11 PM Bug #14693 (Duplicate): osd: valgrind uninitcondition in PG::choose_acting(pg_shard_t&)
- <ip>0x549E7C</ip>
<obj>/usr/bin/ceph-osd</obj>
<fn>PG::choose_acting(pg_shard_t&)</fn>
... - 01:49 PM Backport #13615 (Resolved): OSD::build_past_intervals_parallel() shall reset primary and up_prima...
- 01:49 PM Revision a8d147e8 (ceph): Merge pull request #6397 from SUSE/wip-13615-infernalis
- OSD::build_past_intervals_parallel() shall reset primary and up_primary when begin a new past_interval.
Reviewed-by:... - 01:49 PM Backport #13791 (Resolved): Objecter: potential null pointer access when do pool_snap_list.
- 01:49 PM Revision 77a26d8e (ceph): Merge pull request #6840 from SUSE/wip-13791-infernalis
- Objecter: potential null pointer access when do pool_snap_list.
Reviewed-by: Sage Weil <sage@redhat.com> - 01:48 PM Backport #14018 (Resolved): infernalis: osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= ...
- 01:48 PM Revision cea356a9 (ceph): Merge pull request #6851 from Abhishekvrshny/wip-14018-infernalis
- infernalis: osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info.history.last_epoch_started)
Reviewed-by: S... - 01:48 PM Backport #13979 (Resolved): infernalis : "shard missing" errors in logs during Teuthology run
- 01:48 PM Revision 5469e990 (ceph): Merge pull request #6849 from Abhishekvrshny/wip-13979-infernalis
- osd: call on_new_interval on newly split child PG
Reviewed-by: Sage Weil <sage@redhat.com> - 01:48 PM Backport #13929 (Resolved): infernalis: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- 01:48 PM Revision ba4583f3 (ceph): Merge pull request #6907 from Abhishekvrshny/wip-13929-infernalis
- infernalis: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
Reviewed-by: Sage Weil <sage@redhat.com> - 01:47 PM Backport #14494 (Resolved): infernalis: pgs stuck inconsistent after infernalis upgrade
- 01:47 PM Revision fbd96c8a (ceph): Merge pull request #7421 from Abhishekvrshny/wip-14494-infernalis
- infernalis: pgs stuck inconsistent after infernalis upgrade
Reviewed-by: Sage Weil <sage@redhat.com> - 01:46 PM Backport #13771 (Resolved): Objecter: pool op callback may hang forever.
- 01:46 PM Revision cef8fc30 (ceph): Merge pull request #6627 from Abhishekvrshny/wip-13771-infernalis
- Objecter: pool op callback may hang forever.
Reviewed-by: Sage Weil <sage@redhat.com> - 12:39 PM Revision 12c083ed (ceph): OSD/ReplicatedPG: Fixes unneccessary object promotion when deleting fro...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 12:09 PM Stable releases Tasks #14692 (Resolved): hammer v0.94.7
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 11:18 AM Revision 15c27ce7 (ceph): Merge pull request #7543 from SUSE/wip-14676-infernalis
- infernalis: rgw: radosgw-admin --help doesn't show the orphans find command
Reviewed-by: Loic Dachary <ldachary@redh... - 11:02 AM rgw Bug #11241 (Resolved): Incorrect ETAG calculated for POST uploads
- 11:02 AM Bug #2390 (Resolved): dencoder: depends on expat
- 10:04 AM Bug #2390: dencoder: depends on expat
- This was fixed via:
https://github.com/ceph/ceph/pull/7476
This bug can be closed. - 11:00 AM Bug #13192 (Pending Backport): stuck recovering, unfound hit set due to removing it while !active
- 08:52 AM devops Bug #14687: RPM: no /usr/libexec directory on SUSE
- 08:52 AM rgw Backport #14570 (Resolved): hammer: Incorrect ETAG calculated for POST uploads
- 08:50 AM rgw Backport #14570 (In Progress): hammer: Incorrect ETAG calculated for POST uploads
- 08:49 AM rgw Backport #14141 (Need More Info): hammer: rgw: leak from RGWWatcher::handle_error
- 08:48 AM Backport #14491 (Need More Info): hammer: ceph-disk: duplicate osd mount points
- 08:48 AM Backport #14326 (Need More Info): hammer: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to...
- (missing commit)
- 08:47 AM Backport #14323 (Need More Info): hammer: OpTracker needs to release the message throttle in _unr...
- (missing commit)
- 08:47 AM Backport #13807 (Need More Info): hammer: segfault in Objecter::handle_watch_notify
- (missing commit in the original issue)
- 07:25 AM CephFS Backport #14624 (Resolved): hammer: fsx failed to compile
- 07:19 AM Revision 7abb6ae8 (ceph): Merge pull request #7501 from SUSE/wip-14624-hammer
- hammer: fsx failed to compile
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:41 AM Bug #14004 (Resolved): ceph-disk workunits must not rely on augtool
- 06:22 AM Backport #14582 (In Progress): infernalis: pid file that was deleted after ceph restart leads to ...
- 06:17 AM Bug #14679 (Resolved): msg/async: segv from ceph_test_msgr, cleanup_handler
- 06:15 AM Revision 90561b46 (ceph): Merge pull request #7547 from yuyuyu101/wip-14679
- AsyncConnection: avoid debug log in cleanup_handler
- 06:09 AM Bug #13422: pid file that was deleted after ceph restart leads to osd process lose control
- https://github.com/ceph/ceph/pull/7075 followed by https://github.com/ceph/ceph/pull/7463
- 06:07 AM Bug #13422 (Pending Backport): pid file that was deleted after ceph restart leads to osd process ...
- 06:05 AM Backport #14688 (In Progress): infernalis: consume_maps clearing of waiting_for_pg needs to check...
- 05:08 AM Backport #14688 (Rejected): infernalis: consume_maps clearing of waiting_for_pg needs to check th...
- https://github.com/ceph/ceph/pull/7563
- 06:04 AM Bug #14278: consume_maps clearing of waiting_for_pg needs to check the spg_t shard for acting set...
- https://github.com/ceph/ceph/pull/7510
- 06:02 AM Backport #14578 (In Progress): infernalis: mon sync does not copy config-key
- 06:01 AM Bug #14577: mon sync does not copy config-key
- https://github.com/ceph/ceph/pull/7363
- 05:57 AM Backport #14469 (In Progress): infernalis: osd/ReplicatedPG: fix promotion recency logic
- 05:43 AM Backport #14286 (In Progress): infernalis: ReplicatedPG: wrong result code checking logic during ...
- 05:41 AM Backport #14284 (In Progress): infernalis: osd/OSD.cc: 2469: FAILED assert(pg_stat_queue.empty())...
- 05:38 AM Backport #13933 (In Progress): infernalis: ceph-disk prepare fails if device is a symlink
- 05:37 AM Revision 3395fb9e (ceph): crush/CrushTester: workaround a bug in boost::icl
- the boost::icl in boost v1.55 has a bug when working with libc++,
> Assertion failed: (this->_map.find(inter_val) ==... - 05:30 AM Backport #13808 (Need More Info): infernalis: segfault in Objecter::handle_watch_notify
- 05:28 AM Bug #13993 (Resolved): Use of syslog results in all log messages at priority "emerg"
- 05:28 AM Backport #14138 (Resolved): hammer: Use of syslog results in all log messages at priority "emerg"
- 05:09 AM rgw Backport #14691 (Rejected): infernalis: Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::for...
- 05:09 AM CephFS Backport #14690 (Rejected): infernalis: Client::_fsync() on a given file does not wait unsafe req...
- 05:08 AM Backport #14689 (Resolved): hammer: consume_maps clearing of waiting_for_pg needs to check the sp...
- https://github.com/ceph/ceph/pull/7577
- 05:07 AM Bug #14080 (Resolved): ceph-disk: use blkid instead of sgdisk -i
- 05:07 AM Bug #13975 (Resolved): systemd/ceph-disk@.service assumes /bin/flock
- 05:07 AM Bug #13821 (Resolved): OSD: race condition detected during send_failures
- 05:07 AM Bug #13664 (Resolved): tests: testprofile must be removed before it is re-created
- 05:07 AM Bug #13610 (Resolved): auth/cephx: large amounts of log are produced by osd
- 05:06 AM Bug #13597 (Resolved): FileStore: potential memory leak if getattrs fails.
- 05:06 AM Bug #13525 (Resolved): mon: should not set isvalid = true when cephx_verify_authorizer return false
- 05:06 AM Bug #13477 (Resolved): crush: crash if we see CRUSH_ITEM_NONE in early rule step
- 05:06 AM Bug #13474 (Resolved): Ceph daemon failed to start, because the service name was already used.
- 05:06 AM CephFS Bug #13443 (Resolved): Ceph-fuse won't start correctly when the option log_max_new in ceph.conf s...
- 05:01 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rgw...
- 03:48 AM Stable releases Tasks #13750: infernalis v9.2.1
- ...
- 05:01 AM Backport #13638 (Resolved): FileStore: potential memory leak if getattrs fails.
- 05:01 AM Backport #13655 (Resolved): crush: crash if we see CRUSH_ITEM_NONE in early rule step
- 05:01 AM Backport #13671 (Resolved): tests: testprofile must be removed before it is re-created
- 05:01 AM Backport #13869 (Resolved): infernalis: OSD: race condition detected during send_failures
- 05:00 AM Backport #13891 (Resolved): infernalis: auth/cephx: large amounts of log are produced by osd
- 05:00 AM Backport #13935 (Resolved): infernalis: Ceph daemon failed to start, because the service name was...
- 05:00 AM Backport #14013 (Resolved): infernalis: systemd/ceph-disk@.service assumes /bin/flock
- 04:59 AM rgw Backport #14569 (Resolved): hammer: Make RGW_MAX_PUT_SIZE configurable
- 04:44 AM Backport #14137 (Resolved): infernalis: Use of syslog results in all log messages at priority "em...
- 04:22 AM Revision d1da0313 (ceph): Merge pull request #6993 from badone/wip-13993-infernalis
- log: Log.cc: Assign LOG_DEBUG priority to syslog calls
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:21 AM Revision 22e0c6a7 (ceph): Merge pull request #6882 from dachary/wip-13988-reuse-osd-id-infernalis
- tests: verify it is possible to reuse an OSD id
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:18 AM Revision 489a13d4 (ceph): Merge pull request #6852 from Abhishekvrshny/wip-14013-infernalis
- infernalis: systemd/ceph-disk@.service assumes /bin/flock
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:16 AM Revision de01ba4e (ceph): Merge pull request #6846 from Abhishekvrshny/wip-13638-infernalis
- FileStore: potential memory leak if getattrs fails.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:14 AM Revision b5427f46 (ceph): Merge pull request #6836 from SUSE/wip-13891-infernalis
- infernalis: auth/cephx: large amounts of log are produced by osd
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:12 AM Revision 5dbd9984 (ceph): Merge pull request #6833 from SUSE/wip-13935-infernalis
- infernalis: Ceph daemon failed to start, because the service name was already used.
Reviewed-by: Loic Dachary <ldach... - 04:12 AM Revision 20164688 (ceph): Merge pull request #6694 from xiexingguo/xxg-wip-13869
- osd: fix race condition during send_failures
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Sage Weil <... - 04:09 AM Revision b09670fe (ceph): Merge pull request #6626 from Abhishekvrshny/wip-13655-infernalis
- crush: crash if we see CRUSH_ITEM_NONE in early rule step
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:06 AM Revision 59df52df (ceph): Merge pull request #6449 from dachary/wip-13671-infernalis
- tests: testprofile must be removed before it is re-created
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:29 AM Linux kernel client Bug #13905: "BUG: held lock freed!"
- Happened twice in three runs of the powercycle suite. Should we rule that as environmental and whitelist the message ...
02/07/2016
- 06:08 PM Bug #14686 (Fix Under Review): OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from
- https://github.com/ceph/ceph/pull/7553
- 02:10 PM Bug #14686 (Resolved): OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from
- Base on current logic, OSDMonitor may call create_pending and
encode_pending twice for the some epoch.
In encode_... - 05:52 PM Revision d21724a1 (ceph): Merge pull request #7554 from tchaikov/wip-ceph-disk-test
- tests: ceph-disk.sh should compare with the resolved path
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:49 PM devops Bug #14687 (Resolved): RPM: no /usr/libexec directory on SUSE
- The ceph-osd-prestart.sh script is installed in /usr/libexec/ceph/ and indeed this directory is hard-coded in the fil...
- 02:19 PM Revision 990b437f (ceph): OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from
- Base on current logic, OSDMonitor may call create_pending and
encode_pending twice for the some epoch.
In encode_pen... - 02:01 PM Revision e604d681 (ceph): Merge pull request #7551 from JevonQ/update-libcephfs-version
- libcephfs: update LIBCEPHFS_VERSION to indicate the interface was changed
Reviewed-by: Sage Weil <sage@redhat.com> - 12:39 PM Revision d267aaf8 (ceph): tests: ceph-disk.sh should compare with the resolved path
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:58 AM Feature #14669 (In Progress): ceph-disk: support indirect dmcrypt key retrieval
- https://github.com/ceph/ceph/pull/7552
- 08:20 AM CephFS Bug #14685 (New): dbench hang on native cifs mount
- http://pulpito.ceph.com/teuthology-2016-02-03_19:14:02-samba-jewel---basic-mira/5717/
http://pulpito.ceph.com/teutho... - 06:00 AM Revision 4d383022 (ceph): libcephfs: Update LIBCEPHFS_VERSION to indicate the interface was changed
- Signed-off-by: Jevon Qiao <scaleqiao@gmail.com>
- 05:34 AM CephFS Bug #14684 (Resolved): test_scrub_checks fails
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-02-03_14:03:10-fs-jewel---basic-smithi/5365/teuthology.log
<pr...
02/06/2016
- 06:37 PM Revision c21de4d0 (ceph): AsyncMessenger: remove unused variables
- * remove AsyncMessenger::listen_sd
* remove `ee` in KqueueDriver::del_event()
Signed-off-by: Kefu Chai <kchai@redhat... - 05:59 PM Revision c45854a8 (ceph): crypto: remove unused Digest::sec_type
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:59 PM Revision 64361c39 (ceph): ECUtil: remove unused stripe_info_t::stripe_size
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:59 PM Revision 9c3f8219 (ceph): librbd: replace atomic_t with std::atomic<int>
- it fails to compile with clang, and turns out it should be
`ceph::atomic_t`, but I take this chance to replace it
wit... - 05:59 PM Revision 2a537370 (ceph): librbd: remove unused C_DiffObject::m_request_num
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:59 PM Revision 93ac31c7 (ceph): journal: remove unused ObjectPlayer::m_fetch_interval
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:59 PM Revision 7d08bbf5 (ceph): osd: init HeartbeatDispatcher using OSD->cct
- its base class 'Dispatcher' is uninitialized when used here to access
'Dispatcher::cct', so we'd better use OSD::cct ... - 03:43 PM Revision 7f854cc1 (ceph): Merge pull request #7549 from tchaikov/wip-fix-ceph-disk-tests
- ceph-disk/test: fix test_prepare.py::TestPrepare tests
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:27 PM Revision 08364c2f (ceph): ceph-disk/test: fix test_prepare.py::TestPrepare tests
- actually we are verifying if the variable is an instance of
specified class. for example, the `prepare.data` should b... - 07:40 AM Revision 8569d38f (ceph): AsyncConnection: avoid debug log in cleanup_handler
- local connection will be stop and call cleanup_handler after messenger
is down
introduced in
commit(https://github.co... - 02:41 AM Bug #14660: selinux denials during rbd test run
- Policy is installed as i see in the logs...
- 02:09 AM Bug #14660: selinux denials during rbd test run
- It looks like there is a lot of stuff happening, here:
Some of the processes are mislabelled. This suggests that e... - 02:10 AM Revision ceb6fcc5 (ceph): Merge pull request #7524 from ktdreyer/wip-14637-hammer-man-radosgw-adm...
- hammer: doc: regenerate man pages, add orphans commands to radosgw-admin(8)
- 01:46 AM Bug #13422 (Resolved): pid file that was deleted after ceph restart leads to osd process lose con...
- woot!
- 01:41 AM Revision 0c6a7248 (ceph): Merge pull request #7540 from dillaman/wip-librados-test-stub-unwatch
- librados_test_stub: protect against notify/unwatch race
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:39 AM Revision 2b2ce9b9 (ceph): Merge pull request #7529 from dillaman/wip-14412
- librbd: journal framework for tracking exclusive lock transitions
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:09 AM Revision a48c081d (ceph): rgw/rgw_orphan: check the return value of save_state
- It was discovered by covscan that we do not check the return value of
save_state in this one case.
Signed-off-by: Bo... - 01:03 AM Revision 2e4fa4b3 (ceph): Merge pull request #7377 from liewegas/wip-datadir-search
- config: add $data_dir/config to config search path
- 01:03 AM Revision f3a01575 (ceph): Merge pull request #7466 from adamemerson/wip-bsd-time-second-try
- common: time: have skewing-now call non-skewing now
- 01:03 AM Revision 220a4730 (ceph): Merge pull request #7463 from dachary/wip-13422-pid-file
- global: do not start two daemons with a single pid-file (part 2)
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:02 AM Revision c6ff94c2 (ceph): Merge pull request #7460 from xiexingguo/xxg-wip-block
- osd: blockdevice: avoid implicit cast and add guard
Reviewed-by: Sage Weil <sage@redhat.com> - 01:02 AM Revision 5f993610 (ceph): Merge pull request #7530 from xiexingguo/xxg-wip-nid
- osd: bluestore: assign nid for newly created onode
Reviewed-by: Sage Weil <sage@redhat.com> - 01:01 AM Revision 3ac4d711 (ceph): Merge pull request #7521 from liewegas/wip-memstore
- osd: memstore: set Collection::cid on create
- 01:01 AM Revision 86978957 (ceph): Merge pull request #7486 from ceph/wip-bluestore-oref
- osd: bluestore: fix two wal bugs; reuse OnodeRefs when applying txc
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:01 AM Revision 4dbd727f (ceph): Merge pull request #7531 from jjhuo/master
- osd: bluestore: remove unused intrusive member hook in enode
Reviewed-by: Sage Weil <sage@redhat.com> - 01:00 AM Revision caab2e1d (ceph): Merge pull request #7535 from liewegas/wip-bluefs-mkfs
- osd: bluestore/BlueFS: initialize super block_size earlier in mkfs
Reviewed-by: Dan Mick <dmick@redhat.com> - 01:00 AM Revision 7813776a (ceph): Merge pull request #7536 from liewegas/wip-bluestore-block
- osd: bluestore: fix block device file creation
- 12:53 AM Revision 05946147 (ceph): Merge pull request #7541 from linuxbox2/cmake-feb5
- Cmake feb5
02/05/2016
- 11:27 PM rgw Backport #14676 (In Progress): infernalis: rgw: radosgw-admin --help doesn't show the "orphans fi...
- 05:49 PM rgw Backport #14676 (Resolved): infernalis: rgw: radosgw-admin --help doesn't show the "orphans find"...
- https://github.com/ceph/ceph/pull/7543
- 11:26 PM Revision 2b6d8171 (ceph): rgw-admin: document orphans commands in usage
- Fixes: #14516
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 105a76bf542e05b739d5a03ca8a... - 11:13 PM CephFS Backport #14668: hammer: Wrong ceph get mdsmap assertion
- Hammer backport is staged. Maybe it's not too late to squeeze it into 0.94.6 - we'll see.
- 11:12 PM CephFS Backport #14668 (In Progress): hammer: Wrong ceph get mdsmap assertion
- 11:08 PM CephFS Backport #14668: hammer: Wrong ceph get mdsmap assertion
- h3. Original description
One of our hammer clusters won't start now after running ceph mds getmap.
I did:... - 11:04 PM CephFS Backport #14668: hammer: Wrong ceph get mdsmap assertion
- https://github.com/ceph/ceph/pull/4203
I will stage hammer backport. - 10:54 AM CephFS Backport #14668: hammer: Wrong ceph get mdsmap assertion
- This was fixed in >=infernalis, but apparently never backported....
- 08:57 AM CephFS Backport #14668: hammer: Wrong ceph get mdsmap assertion
- After a few more retries the mon's eventually started.
- 08:51 AM CephFS Backport #14668 (Resolved): hammer: Wrong ceph get mdsmap assertion
- https://github.com/ceph/ceph/pull/7542
- 11:11 PM Revision b9a4ad9d (ceph): Fixed the ceph get mdsmap assertion.
- When we want to get mdsmap, we try to get_version()
and the return value err = 0 means success.
The assert v... - 11:05 PM CephFS Bug #14681 (Resolved): Wrong ceph get mdsmap assertion
- https://github.com/ceph/ceph/pull/4203
- 10:20 PM Bug #14443: "[ FAILED ] LibRadosTwoPoolsPP.Flush" in upgrade:infernalis-x-jewel-distro-basic-vps
- Run: http://pulpito.ceph.com/teuthology-2016-02-05_02:10:02-upgrade:infernalis-x-jewel-distro-basic-vps/
Job: 7509
... - 10:07 PM Revision f4b083a5 (ceph): osdc: Update to use C++11 concurrency
- The only externally visible change is that Objecter::get_osdmap_read
and Objedcter::put_osdmap_read have been removed... - 10:00 PM devops Bug #11489: jenkins parameterized branches do not support polling
- Do we still need this?
- 09:46 PM Revision 21438a67 (ceph): cmake: add libboost_system to EXTRALIBS
- This concisely fixes several unittest builds, and reflects the
fact that this library dependency has moved into sever... - 09:46 PM Revision 2669e0c2 (ceph): cmake: don't try to install src/ceph-disk directory
- The proper cmake boilerplate to call ceph-disk/ceph-disk's
python installer is not present, FYI.
Signed-off-by: Matt... - 09:46 PM Revision 33bc2ba5 (ceph): cmake: don't add_test cephtool_test_osd twice
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 09:20 PM Bug #14267: ceph-post-file doesn't work
- Will move to physical host with public IP and access to LRC
- 09:17 PM devops Bug #14275: Ceph "giant" packages no longer available for installation on Ubuntu 14.04 "trusty"
- Package experts: can you render an opinion here? I don't see whether it's obviously a client config, package repo, o...
- 12:43 PM devops Bug #14275: Ceph "giant" packages no longer available for installation on Ubuntu 14.04 "trusty"
- I started with a freshly installed Ubuntu 14.04 "trusty" system and followed the steps outlined in http://docs.ceph.c...
- 09:14 PM Revision 38b9be2a (ceph): librados_test_stub: protect against notify/unwatch race
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:05 PM Bug #14679 (Resolved): msg/async: segv from ceph_test_msgr, cleanup_handler
- ...
- 08:57 PM Revision c1b3138f (ceph): concurrency: Add shunique_lock
- Locker class tracking shared/unique/unlocked state of SharedMutex
concept.
Signed-off-by: Adam C. Emerson <aemerson@... - 08:54 PM rgw Bug #14678 (Resolved): rgw: when putting metadata object, cache info doesn't keep object's metada...
- This means that later on if we need object's metadata we need to fetch it from the backend which is a waste.
- 08:21 PM Revision 5eda2859 (ceph): cls_journal: new get_client / client_update methods
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:21 PM Revision 608947cb (ceph): journal: added tag support methods
- librbd, for example, will allocate a new tag after acquiring
the exclusive lock.
Signed-off-by: Jason Dillaman <dill... - 08:21 PM Revision 8443e507 (ceph): librbd: initial version of journal client and tag metadata
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:21 PM Revision 9418f055 (ceph): librbd: partial implementation of journal client / tag allocation
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:21 PM Revision 3f29e7b8 (ceph): cls_journal: client registration should hold opaque data structure
- The opaque structure will support journal client applications to
store and retrieve complex state.
Fixes: #13298
Si... - 08:21 PM Revision fa6d0ba9 (ceph): cls_journal: new tag management methods and handling
- In the case of librbd, a new tag will be allocated when the
exclusive lock is acquired. All tags for the same datase... - 07:39 PM Feature #14677 (Resolved): ceph-disk list should have json output option
- We'll need to generate ceph-disk list output in json.
- 06:15 PM Revision b725fdf5 (ceph): Made disk size in openstack 40GB, so osd won't run out of space
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 9e28d21adc7d891a9ad3426170f147164b2778ae) - 06:11 PM Revision 0cf150f5 (ceph): Adde + in the openstack.yaml dir
- Fixes failures in #14635
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit d4fd02e9d804... - 06:09 PM Revision 0a66bee9 (ceph): Merge branch 'jewel' of https://github.com/ceph/ceph-qa-suite into jewel
- 06:03 PM Revision 243d91db (ceph): journal: switched entry tags to use id instead of string
- Later commits will add the ability to allocate tags and
associate them with registered clients.
Signed-off-by: Jason... - 05:57 PM rgw Bug #14361: swift/test/functional -v -a '!fails_on_rgw'
- Persisting on centos 7.2
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-05_10:02:03-upgrade:hammer-x... - 08:04 AM rgw Bug #14361: swift/test/functional -v -a '!fails_on_rgw'
- * http://pulpito.ceph.com/loic-2016-02-04_00:40:51-rgw-infernalis-backports---basic-multi/6180/
setting to high as... - 05:44 PM Bug #14660: selinux denials during rbd test run
- Few others: http://qa-proxy.ceph.com/teuthology/vasu-2016-02-04_17:44:39-selinux-jewel---basic-vps/7216/teuthology.log
- 01:11 AM Bug #14660: selinux denials during rbd test run
- hopefully this format is better, some tag above is messing up the format,
copied from one of the audit logs
<pre... - 12:59 AM Bug #14660: selinux denials during rbd test run
- ...
- 12:58 AM Bug #14660 (Closed): selinux denials during rbd test run
- Following denails are seen for ceph-osd during rbd test with ceph-deploy...
- 05:43 PM Bug #14230 (Resolved): ceph-disk list missing information when dmcrypt
- 05:42 PM Bug #13970 (Resolved): ceph-disk list fails on /dev/cciss!c0d0
- 05:36 PM rgw Backport #14651 (Resolved): hammer: rgw: radosgw-admin --help doesn't show the "orphans find" com...
- 05:15 PM Revision 48c542ac (ceph): concurrency: make C++11 style debugging mutices
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 05:14 PM Revision cb2fc91e (ceph): Merge pull request #7474 from jack-changtao/wip-cmake2
- CMake: For CMake version <= 2.8.11, use LINK_PRIVATE and LINK_PUBLIC
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:02 PM Revision 3c1f0973 (ceph): Merge pull request #7108 from jdurgin/wip-rbd-mirroring
- rbd-mirror: daemon skeleton
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:29 PM rbd Subtask #14673 (Resolved): Asynchronously open and close image replayers
- As new mirrored images are detected and old images are no longer mirrored, asynchronously start / stop the replayer.
- 04:22 PM Revision 672a694a (ceph): time: Remove constexpr from non-literal type in test
- This fixes a compile error under clang and fixes another FreeBSD porting
issue.
Signed-off-by: Adam C. Emerson <aeme... - 04:21 PM Revision 0fcb3070 (ceph): time: Have skewing-now call non-skewing now
- For the real-time clocks, Ceph's testing infrastructure likes to be able to
inject a skew. To avoid pulling CephConte... - 03:52 PM Revision ed8b675a (ceph): Merge pull request #7538 from tchaikov/wip-fix-exe-test
- tests: mon: "chmod +x mon-created-time.sh"
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:46 PM CephFS Bug #14672: MDS crashes with FAILED assert(inode_map.count(in->vino()) == 0) in 9.2.0
- added log
- 03:45 PM CephFS Bug #14672 (Rejected): MDS crashes with FAILED assert(inode_map.count(in->vino()) == 0) in 9.2.0
- Full log in attach
-9> 2016-02-05 15:26:29.015197 7f177de2f700 10 mds.0.locker got rdlock on (ipolicy sync r... - 03:45 PM Revision 47c9b621 (ceph): tests: mon: "chmod +x mon-created-time.sh"
- otherwise it always fails to run.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 03:22 PM Bug #13897: (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED assert(r == 0)
- I don't think we've seen this on master.. some missing backport?
- 03:21 PM Bug #14666 (Fix Under Review): memstore: fails to set cid on collection
- https://github.com/ceph/ceph/pull/7521
- 07:05 AM Bug #14666 (Resolved): memstore: fails to set cid on collection
- One example here http://pulpito.ceph.com/gregf-2016-02-04_07:29:11-fs-master---basic-mira/6616/ but I've been getting...
- 03:10 PM Bug #14671 (Duplicate): ceph-objectstore-tool: Can't find OSDMap for pg epoch 232
- ...
- 02:51 PM Revision 08517578 (ceph): os/bluestore/KernelDevice: use _exit(1) for failure injection
- This way we don't generate a core file, which spams the log and trips up
teuthology.
Signed-off-by: Sage Weil <sage@... - 02:48 PM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- PR for delete proxying is at
https://github.com/ceph/ceph/pull/7537 - 02:21 PM Revision a297261a (ceph): os/bluestore: fix block device file creation
- Just make a separate flag to indicate whether we create a block
file. This lets us drop the weird touch in vstart.sh... - 02:17 PM Revision c4f9d265 (ceph): Merge pull request #7519 from xiexingguo/xxg-wip-finisher
- librados: shutdown finisher in a more graceful way
Reviewed-by: Sage Weil <sage@redhat.com> - 02:17 PM Revision 33689975 (ceph): Merge pull request #7506 from liewegas/wip-bluestore-block
- osd: bluestore: set default wal size; improve weird implicit block file creation logic
Reviewed-by: Loic Dachary <ld... - 02:16 PM Revision c87f3f34 (ceph): Merge pull request #7503 from tchaikov/wip-cmake-spdk
- build: spdk submodule; cmake
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:15 PM Feature #13942 (Resolved): ceph-disk: support bluestore
- 02:15 PM Revision adfc653e (ceph): Merge pull request #7218 from dachary/wip-13942-ceph-disk
- ceph-disk: support bluestore
Reviewed-by: Sage Weil <sage@redhat.com> - 02:12 PM Bug #14213: osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- /a/sage-2016-02-04_12:56:11-rados-wip-sage-testing---basic-smithi/6933
definitely in master - 01:41 PM Revision 4c13f9d7 (ceph): os/bluestore/BlueFS: initialize super block_size earlier in mkfs
- Reported-by: Dan Mick <dmick@redhat.com>
Signed-off-by: Sage Weil <sage@redhat.com> - 12:56 PM Revision e4abb95a (ceph): cmake: add cls_cephfs to cephfs_testing target
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:56 PM Revision 168e142b (ceph): librados: enable filtering in object_list API
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:56 PM Revision bacfce51 (ceph): tools/cephfs: sharded pgls in cephfs-data-scan
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:45 AM CephFS Bug #13583: Client::_fsync() on a given file does not wait unsafe requests that create/modify the...
- @yan do you think it should be backported to infernalis as well ? It showed up when running tests:
* http://pulpit... - 10:41 AM CephFS Bug #13583 (Pending Backport): Client::_fsync() on a given file does not wait unsafe requests tha...
- 10:42 AM Revision 23d39cbc (ceph): os/kstore: kill dead code
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 10:15 AM Feature #14669 (Resolved): ceph-disk: support indirect dmcrypt key retrieval
- See Feb 2016 CDM session at:
* http://pad.ceph.com/p/osd-key-management
See SUSE ftp implementation at:
* ht... - 09:59 AM Bug #13089: mon: check for store writeablility before participating in election
- please note that the background compaction fails, if leveldb can not create new tables or remove merged tables.
so... - 09:37 AM Revision 5d5e4200 (ceph): os/kstore: fix race condition
- The get_omap_iterator shall check the existence of onode too,
which may race with the rename method.
Signed-off-by: ... - 09:34 AM Revision 1e8719f9 (ceph): os/bluestore: fix race condition
- The get_omap_iterator shall check the existence of onode too, which may
race with the rename method.
Signed-off-by: ... - 09:30 AM Revision 2f4e1d1f (ceph): Merge pull request #7526 from ceph/wip-14516-hammer
- hammer: rgw-admin: document orphans commands in usage
- 08:22 AM rgw Bug #14667 (New): inconsistent container size reported
- Radosgw returns different answers for the same bucket. Bucket *Test2* contains 1 object with length 1488913 bytes.
H... - 08:09 AM rgw Bug #13239: Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_request(RGWAccessKey&, ...
- * http://pulpito.ceph.com/loic-2016-02-04_00:40:51-rgw-infernalis-backports---basic-multi/6170/
- 08:09 AM rgw Bug #13239 (Pending Backport): Seg fault 9.0.3-1845-gf1ead76 : RGWRESTSimpleRequest::forward_requ...
- 07:19 AM Revision 0cef3239 (ceph): mon: get_leader_supported_commands is unused
- get_leader_supported_commands is unused, delete it
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 07:15 AM Revision 17d37be5 (ceph): mon/handle_probe_probe: redundant definition
- Move the first "MMonProbe *r" to the right location
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 06:51 AM rgw Bug #14665 (Duplicate): radosgw-admin -n client.0 user create : permission denied
- http://pulpito.ceph.com/loic-2016-02-04_00:37:12-upgrade:infernalis-infernalis-backports---basic-vps/6158/...
- 06:16 AM devops Bug #13958: 'sudo yum install ceph-radosgw -y' errors in upgrade:firefly-hammer-x-infernalis-dist...
- Also happens in infernalis see http://pulpito.ceph.com/loic-2016-02-04_00:33:20-rados-infernalis-backports---basic-mu...
- 05:47 AM Revision 2ca3c3e5 (ceph): Merge pull request #7441 from odivlad/backport-pr-14569
- [backport] hammer: rgw: Make RGW_MAX_PUT_SIZE configurable
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com> - 05:46 AM Revision 02353f6b (ceph): Merge pull request #7442 from odivlad/backport-pr-14570
- [backport] rgw: fix wrong etag calculation during POST on S3 bucket.
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com> - 05:44 AM Revision d5cdc7a5 (ceph): os/bluestore: remove unused intrusive member hook in enode
- Enode only uses intrusive unordered_set base hook, member hook is not neccesary.
This should save some memory space, ... - 05:17 AM Revision 9828d49d (ceph): global: do not start two daemons with a single pid-file (part 2)
- Fixes the following bugs:
* the fd is open(O_WRONLY) and cannot be read from, safe_read
always fails and never rem... - 04:50 AM rbd Subtask #14663 (Resolved): Integrate librbd with journal tag allocation
- Prior to unblocking writes, a new tag should be allocated in the journal. This tag will link to the predecessor tag t...
- 04:46 AM rbd Subtask #13298 (Fix Under Review): Journal registered client entry should store bufferlist payload
- *master PR*: https://github.com/ceph/ceph/pull/7529
- 04:45 AM rbd Subtask #14412 (Fix Under Review): Track epoch and period for mirrored images
- 04:45 AM rbd Subtask #14412: Track epoch and period for mirrored images
- *master PR*: https://github.com/ceph/ceph/pull/7529
- 04:07 AM Revision dca8111a (ceph): os/kstore: assign nid for newly created onode
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 04:06 AM Revision d5dfb007 (ceph): os/bluestore: assign nid for newly created onode
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:31 AM Revision 8f13194b (ceph): Merge pull request #7522 from ktdreyer/wip-admin-build-doc-deps
- admin/build-doc: depend on zlib1g-dev and graphviz
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:08 AM rgw Bug #14662 (Can't reproduce): Failed to shutdown radosgw gracefully
- When we run a single radosgw which is listening both 80 and 443(ssl) ports and then stop it by `sudo stop radosgw id=...
- 02:21 AM Revision b7bbcee2 (ceph): mon: unregister command on shutdown
- unregister command on shutdown
include: "quorum enter" && "quorum exit"
Signed-off-by: huanwen ren <ren.huanwen@zte.... - 12:46 AM Bug #14474 (Resolved): BlueFS: miss log for updating fnode during open_for_write
- https://github.com/xiexingguo/ceph/commit/09d26448ea98a971f42adefa5bc2455717df919b
- 12:45 AM Bug #14480 (Resolved): BlueFS: race condition detected.
- https://github.com/xiexingguo/ceph/commit/881ac7addac68add3d048f5fca4b3a72535e6c46
- 12:42 AM Bug #14603 (Resolved): Objecter: race condition and result code overflow
- https://github.com/ceph/ceph/pull/7477
02/04/2016
- 11:56 PM CephFS Bug #14641: don't let users specify 0 on stripe count or object size
- This is based on http://www.spinics.net/lists/ceph-users/msg25363.html
Perhaps the cluster is old and they broke i... - 11:43 PM CephFS Bug #14641: don't let users specify 0 on stripe count or object size
- We already validate layouts in Server.cc. We *could* also validate them on load from disk or during scrub...?
- 03:15 PM CephFS Bug #14641 (Duplicate): don't let users specify 0 on stripe count or object size
- Those are fairly nonsensical. Amongst other things, they induce a divide-by-zero in the StrayManager right now.
- 11:04 PM Bug #14658 (Resolved): "Failed to execute command: systemctl enable ceph.target" in smoke-master-...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-04_05:00:02-smoke-master-distro-basic-openstack/
Job:... - 10:48 PM Revision 9da41fee (ceph): systemd/ceph-radosgw-prestart.sh: remove
- This is unpackaged and unused.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:34 PM Bug #14654 (Can't reproduce): "failed: mon_thrash" in upgrade:hammer-hammer-distro-basic-openstack
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-03_20:05:02-upgrade:hammer-hammer-distro-basic-opensta...
- 10:31 PM rgw Bug #14653 (Closed): "test_s3.test_abort_multipart_upload ... FAIL" in upgrade:hammer-hammer-dist...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-03_20:05:02-upgrade:hammer-hammer-distro-basic-opensta...
- 10:28 PM rgw Bug #14652 (Resolved): "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-bas...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-03_20:05:02-upgrade:hammer-hammer-distro-basic-opensta...
- 10:18 PM rgw Bug #14516: rgw: radosgw-admin --help doesn't show the "orphans find" command
- I fail at Redmine... the Hammer backport ticket is #14651 , PR is https://github.com/ceph/ceph/pull/7526
- 02:56 AM rgw Bug #14516: rgw: radosgw-admin --help doesn't show the "orphans find" command
- (corresponding man page change in #14637)
- 10:17 PM rgw Backport #14651 (Resolved): hammer: rgw: radosgw-admin --help doesn't show the "orphans find" com...
- PR for hammer: https://github.com/ceph/ceph/pull/7526
- 10:17 PM Revision 85e00b74 (ceph): Merge pull request #816 from ceph/wip-14618-hammer
- Whitelisted soft lockup, detected stalls on CPUs to avoid failures in ov
- 10:16 PM Revision a94553b8 (ceph): Whitelisted soft lockup, detected stalls on CPUs to avoid failures in ovh
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 10:14 PM Revision 9ab5fd9d (ceph): rgw-admin: document orphans commands in usage
- Fixes: #14516
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 105a76bf542e05b739d5a03ca8a... - 10:06 PM Revision 3944d560 (ceph): global: add data_dir_option for all daemons
- This let's us use a generic $data_dir substitution that will map
to rgw_data, osd_data, etc.
Signed-off-by: Sage Wei... - 10:06 PM Revision 25929099 (ceph): common/config: expand $data_dir in config path
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:06 PM Revision 78592fd8 (ceph): common: add $data_dir/config to config search path
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:06 PM Revision b9ce1df0 (ceph): unittest_config: cope with $data_dir not being expanded on non-daemons
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:04 PM Revision 2484ec28 (ceph): Merge pull request #815 from ceph/wip-14618-hammer
- Whitelisted
- 10:01 PM Revision 0407919c (ceph): Whitelisted
- soft lockup
detected stalls on CPUs
to avoide failures in ovh
Signed-off-by: Yuri Weinstein <yweinste@redhat.com> - 09:34 PM Revision 0e1378ef (ceph): [backport] rgw: fix wrong etag calculation during POST on S3 bucket.
- Closes: #14570
(cherry picked from commit 742906a)
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
Signe... - 09:33 PM Revision 5c8d1d74 (ceph): [backport] rgw: Make RGW_MAX_PUT_SIZE configurable
- The 5GB limit of a single operation uploading was part of S3 spec.
However some private setups may have some special ... - 09:24 PM Backport #14282 (Resolved): infernalis: ceph-disk list missing information when dmcrypt
- 09:24 PM Backport #14044 (Resolved): infernalis: ceph-disk list fails on /dev/cciss!c0d0
- 09:23 PM Revision f8f36b68 (ceph): Merge pull request #6880 from dachary/wip-14044-infernalis
- infernalis: ceph-disk list fails on /dev/cciss!c0d0
- 09:17 PM Revision 3760a024 (ceph): Merge pull request #7478 from jack-changtao/wip-cache-tier
- osd: enforce cache_min_evict_age
Reviewed-by: Sage Weil <sage@redhat.com> - 09:15 PM Revision 2caed6a1 (ceph): Merge pull request #7512 from athanatos/wip-admin-malloc
- common: admin socket commands for tcmalloc heap get/set operations
Reviewed-by: Sage Weil <sage@redhat.com> - 09:06 PM Bug #14278 (Pending Backport): consume_maps clearing of waiting_for_pg needs to check the spg_t s...
- 09:06 PM Revision f97fcf27 (ceph): Merge pull request #7510 from athanatos/wip-14278
- osd: correctly remove pg shards which are no longer acting
Reviewed-by: Sage Weil <sage@redhat.com> - 09:04 PM Bug #14423 (Resolved): Segmentation fault in rados-hammer-distro-basic-mira
- 09:04 PM Revision 3bde8955 (ceph): Merge pull request #7511 from athanatos/wip-14423
- Wip 14423
Reviewed-by: Sage Weil <sage@redhat.com> - 08:25 PM Revision 8ec24d51 (ceph): Merge pull request #7401 from batrick/systemd-sandbox
- systemd: add systemd sandboxing to services
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Boris Ranto <brant... - 08:11 PM rbd Subtask #14419 (In Progress): RBD mirroring settings should be moved to new pool object
- 07:42 PM Revision 28dcf0bc (ceph): .gitignore: add rbd-mirror
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 07:35 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- I think I'm seeing this problem as well, and would prefer not to upgrade to Infernalis. Currently I'm partially work...
- 06:06 PM Revision f2ca42b1 (ceph): doc: add orphans commands to radosgw-admin(8)
- The --help text was added in 105a76bf542e05b739d5a03ca8ae55432350f107.
Add the corresponding entries to the man page.... - 06:05 PM Revision aedb9288 (ceph): os/bluestore/BlueStore: fix enode uniqueness
- We were failing to set o->enode, which meant that there were
multiple instances of the same enode alive at once. Avo... - 06:05 PM Revision e42ed6d6 (ceph): man: rebuild manpages
- following the procedure in admin/manpage-howto.txt.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com> - 05:41 PM Revision dada290b (ceph): admin/build-doc: depend on zlib1g-dev and graphviz
- The docs currently require zlib1g-dev (on Ubuntu) and graphviz (on RHEL
and Ubuntu) in order to build.
Signed-off-by... - 04:36 PM Revision 995a6029 (ceph): Merge pull request #7328 from ceph/wip-mtime-bugfix
- Bug fix for mtime anomalies in RadosGW and other places
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:39 PM Documentation #14637 (Resolved): rgw: radosgw-admin man page doesn't contain the "orphans" commands
- 02:55 AM Documentation #14637: rgw: radosgw-admin man page doesn't contain the "orphans" commands
- 02:55 AM Documentation #14637: rgw: radosgw-admin man page doesn't contain the "orphans" commands
- PR for master: https://github.com/ceph/ceph/pull/7518
- 02:51 AM Documentation #14637 (Resolved): rgw: radosgw-admin man page doesn't contain the "orphans" commands
- The orphans commands were added to @radosgw-admin@ --help" in #14516. We should add them to the man page as well.
- 03:30 PM Revision 84970995 (ceph): os/bluestore/BlueStore: default Onode::true to false
- This patch is mostly a wash, except that _rename now avoids doing the
_do_remove() work in the case where the object ... - 03:18 PM Backport #14643 (Resolved): hammer: rgw: radosgw-admin man page doesn't contain the "orphans" com...
- https://github.com/ceph/ceph/pull/7524
- 03:16 PM CephFS Feature #14642 (New): Validate layouts everywhere we load them
- See _calculate_ops_required, wherein we divide by their product without checking it's non-zero.
- 03:10 PM Bug #14566 (Resolved): AsyncMessenger: dispatch reset event after connection closed
- 03:10 PM Revision 0e42ee9a (ceph): Merge pull request #7453 from ceph/wip-14566
- msg/async: fix potential race condition
- 02:34 PM CephFS Bug #14607 (Duplicate): Some fuse tests fail with: failed to remove ‘/home/ubuntu/cephtest’: Dire...
- Dupe of: http://tracker.ceph.com/issues/13422
- 07:13 AM CephFS Bug #14607: Some fuse tests fail with: failed to remove ‘/home/ubuntu/cephtest’: Directory not empty
- I'm seeing this a *bunch* now as well. eg http://pulpito.ceph.com/gregf-2016-02-03_09:19:17-fs-greg-fs-testing-23---b...
- 02:24 PM Revision 70f7b1e3 (ceph): os/memstore/MemStore: set Collection::cid on create
- This was broken by the collection handles merge in
2e52a8b17c348bb3356eb76a8a0f6ef6efbe5bd3 because the c->cid
value ... - 02:08 PM Revision ab7d3dec (ceph): CacheTier: set cache_min_evict_age is effective
- Signed-off-by: Tao Chang <changtao@hihuron.com>
- 01:43 PM Revision 300106a9 (ceph): Merge pull request #7505 from xiexingguo/xxg-wip-kstorelru
- os/kstore: insert new onode to the front position of onode LRU
Reviewed-by: Sage Weil <sage@redhat.com> - 01:43 PM Revision bb691732 (ceph): Merge pull request #7492 from jjhuo/master
- os/bluestore: insert new onode to the front position of onode LRU
Reviewed-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision 21a65fca (ceph): Merge pull request #7380 from yuyuyu101/async-nip
- msg/async: reduce extra tcp packet for message ack
- 01:38 PM Bug #12744 (Resolved): ceph -s output shows "N pgs backfill", should be "waiting for backfill"
- 01:38 PM Revision a637dcd2 (ceph): Merge pull request #7398 from theanalyst/fix/12744
- mon: PG Monitor should report waiting for backfill
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:38 PM Revision 30ff2513 (ceph): Merge pull request #7447 from liewegas/wip-parallel-rados-test
- test: run rados api tests in parallel
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:37 PM Revision fb1abc3d (ceph): Merge pull request #7455 from yuyuyu101/bufferlist-move
- buffer: use move construct to append/push_back/push_front
Reviewed-by: Sage Weil <sage@redhat.com> - 01:37 PM Bug #14130 (Resolved): mon: monmap created is 0.000000 use ceph-deploy installed
- 01:37 PM Revision 408ae365 (ceph): Merge pull request #7459 from dwj192/mon-created
- mon: fix monmap creation stamp
Reviewed-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 0dd5147c (ceph): Merge pull request #7477 from xiexingguo/wip-fix-obj
- osdc/objecter: fix race condition and result code overflow
Reviewed-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 76e79141 (ceph): Merge branch 'xxg-wip-14474' of git://github.com/xiexingguo/ceph
- Reviewed-by: Sage Weil <sage@redhat.com>
- 01:33 PM Revision d0ce8008 (ceph): Merge pull request #7482 from branch-predictor/bp-faster-health
- mon: reduce CPU and memory manager pressure of pg health check
Reviewed-by: Sage Weil <sage@redhat.com> - 10:05 AM Revision d06da59b (ceph): Merge pull request #7518 from ceph/wip-14637-man-radosgw-admin-orphans
- doc: add orphans commands to radosgw-admin(8)
- 10:01 AM Revision 2591f637 (ceph): ceph-disk: use the type file for bluestore
- The type file in the OSD bluestore data exists and contains the
bluestore string. ceph-disk activate should use it in... - 10:01 AM Revision 65bc36e6 (ceph): ceph-disk: bluestore prepare
- Only support the block file for now. It is handled the same as the
journal, only with a different name (block) and it... - 10:01 AM Revision 170dca3a (ceph): ceph-disk: bluestore activate
- Only support the block file for now. The refactoring consist of
replacing main_activate_journal with main_activate_sp... - 10:01 AM Revision fbc0984b (ceph): ceph-disk: bluestore trigger
- Copy paste the journal code and s/journal/block/
More work will be needed to support multiple auxiliary
devices (blo... - 10:01 AM Revision cfea72ee (ceph): ceph-disk: bluestore list
- The objectstore journal and the bluestore block auxiliary device are
handled in the same way. Each occurrence of jour... - 10:01 AM Revision 7b9a8042 (ceph): ceph-disk: bluestore deactivate / destroy
- It is straightforward because it entirely relies on information
collected by ceph-disk list which has full support fo... - 10:01 AM Revision c50f3b9f (ceph): tests: ceph-disk qa workunit for bluestore
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:01 AM Revision 36656c8d (ceph): tests: ceph-disk tests pid files must exist
- http://tracker.ceph.com/issues/13422 made it so ceph-osd won't start
unless the pidfile can be created successfully. ... - 10:00 AM Revision a547bd29 (ceph): ceph-disk: refactor prepare
- The logic / code path is only modified to the extent necessary for the
refactor.
The Prepare class roughly replaces ... - 08:46 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. fs...
- 08:44 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rbd...
- 08:41 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rgw...
- 08:39 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. powercycle...
- 08:38 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. upgrade...
- 08:34 AM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rados...
- 05:27 AM Stable releases Tasks #13750: infernalis v9.2.1
- ...
- 08:24 AM Revision 501ddff4 (ceph): librados/RadosClient: stop client's finisher in a more graceful way
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 08:19 AM Revision be9c0efc (ceph): os/filestore/JournalingObjectStore: stop journal in a more graceful way
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 08:10 AM Revision b35061a7 (ceph): man: stub manpage for rbd-mirror
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 08:10 AM Revision 8f016672 (ceph): packaging: add an rbd-mirror package
- Depend on ceph-common for /etc/ceph. Startup scripts will be added later.
Signed-off-by: Josh Durgin <jdurgin@redhat... - 07:59 AM rbd Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- Sure thing, thanks for picking this up. Let me know if you need more data - I can reproduce the issue easily.
- 07:56 AM CephFS Feature #14640 (New): nfs: qa: evaluate connectathon NFS tests for applicability to our suite
- https://fedorapeople.org/cgit/steved/public_git/cthon04.git/tree/README
Is there anything in there that might be u... - 07:44 AM Revision 3d263840 (ceph): rbd-mirror: skeleton of a mirroring daemon
- This isn't functional yet, since ImageReplayer doesn't do any replay
yet. Just the parts for monitoring other cluste... - 07:38 AM Revision e3b0395d (ceph): ceph-disk: flake8 fixes
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:38 AM Revision ca97b67b (ceph): tests: remove ceph-disk dead code
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:38 AM Revision c7fbe212 (ceph): tests: instructions to collect ceph-disk coverage
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:38 AM Revision b030d8fc (ceph): ceph-detect-init: make all must setup.py install
- When make all runs in the ceph-detect-init module, it does a "setup.py
build" which is not used. Replace it with a py... - 07:38 AM Revision 17c5287d (ceph): tests: fix ceph-disk unit tests
- Because ceph-disk unit tests were not run as part of make check, part of
the most recent changes broke them. This is ... - 07:38 AM Revision 7f6295d2 (ceph): ceph-disk: make all must setup.py install
- Refactor the test / virtualenv setup in the same way it was done for
ceph-detect-init.
All shell tests use ceph-help... - 07:38 AM Revision ef702ef7 (ceph): ceph-disk: cleanup unused argument in list_format
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:38 AM Revision 53014bf4 (ceph): ceph-disk: move check_journal_reqs (no change)
- To help with the prepare refactor.
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:38 AM Revision c9e3e8a5 (ceph): tests: workaround ceph-disk global side effects
- Because some variables are global in ceph-disk, tests that modify them
interact with each other in non-predictable wa... - 07:38 AM Revision 3d9c4a81 (ceph): tests: ceph-disk no longer test separate journals
- Remove unused argument.
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:38 AM Revision 76606c93 (ceph): tests: pytest must not truncate data structures
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:38 AM Revision ec4a2888 (ceph): tests: generic ceph-disk qa check_osd_status
- The helper function no longer has journal hardcoded.
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:36 AM Revision 43dce135 (ceph): ceph-osd: don't mention journal on mkfs
- Some backends don't use it, almost all clusters use the default
path, and there'll always be a symlink.
Signed-off-b... - 07:36 AM Revision f4dd1c67 (ceph): tests: ceph-disk command returns stderr
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:36 AM Revision 9429c040 (ceph): tests: ceph-disk deactivate takes the activate lock
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:36 AM Revision 5151063f (ceph): ceph-disk: refactor into a proper python module
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:36 AM Revision 2e05e474 (ceph): tests: run ceph-disk tests via tox
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:05 AM Revision 7ab19fdb (ceph): makefile: include spdk source in dist tar ball.
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 06:05 AM Revision 09e55d0c (ceph): autotools: enable NVMEDevice if SPDK is found
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 06:03 AM Revision ff561546 (ceph): NVMEDevice: fix the build error with latest spdk
- * include spdk headers in source file
* declare const string with "const" specifier
* pass flag to nvme_ns_cmd_{write... - 06:03 AM Revision 8c2bb7e5 (ceph): cmake: add Find{dpdk,pciaccess}.cmake
- to ready the SPDK support
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:03 AM Revision fd630dc7 (ceph): spdk: add submodule spdk for the nvme support
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 06:03 AM Revision ecb12569 (ceph): cmake: enable NVMEDevice if SPDK is found
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:16 AM Revision b04e1768 (ceph): Merge pull request #6268 from dachary/wip-13453-recovery-counters
- recovery counters
Reviewed-by: Samuel Just <sjust@redhat.com> - 02:53 AM Revision ec162f06 (ceph): doc: add orphans commands to radosgw-admin(8)
- The --help text was added in 105a76bf542e05b739d5a03ca8ae55432350f107.
Add the corresponding entries to the man page.... - 02:43 AM Revision 316810d7 (ceph): os/bluestore: change block file mkfs behavior
- Previously, if path was set, we'd make a symlink. Otherwise, if
size was set, we'd create a file and resize it accor... - 02:43 AM Revision c77e8fd6 (ceph): config: set default bluestore wal size to 96 MB
- Signed-off-by: Sage Weil <sage@redhat.com>
02/03/2016
- 11:09 PM Bug #14520 (Duplicate): VM permanently tries to read /dev/shm/lttng-ust-wait-5
- 10:57 PM Bug #14520: VM permanently tries to read /dev/shm/lttng-ust-wait-5
- See #13274 for the original bug
- 11:01 PM Bug #14634: "Command failed (workunit test rest/test.py)" in rados-jewel-distro-basic-smithi
- Perhaps relevant:
(02:59:32 PM) gregsfortytwo: we switched the mds setmap command to require --yes-i-really-mean-i... - 10:50 PM Bug #14634 (Duplicate): "Command failed (workunit test rest/test.py)" in rados-jewel-distro-basic...
- Run: http://pulpito.ceph.com/teuthology-2016-02-01_22:00:12-rados-jewel-distro-basic-smithi/
Jobs: 2091, 1975
Logs:... - 10:43 PM Bug #14633 (Can't reproduce): (KStore) "(Segmentation fault)" in rados-jewel-distro-basic-smithi
- Run: http://pulpito.ceph.com/teuthology-2016-02-01_22:00:12-rados-jewel-distro-basic-smithi/
Job: 2081
Logs: http:/... - 10:43 PM Backport #14580 (In Progress): infernalis: should compact full epochs in monitor
- 10:39 PM Backport #14581 (Resolved): hammer: should compact full epochs in monitor
- 06:39 PM Backport #14581: hammer: should compact full epochs in monitor
- Merged to hammer in https://github.com/ceph/ceph/pull/7446
- 10:31 PM Bug #14547: "[ FAILED ] LibRadosTwoPoolsECPP.Flush" in upgrade:infernalis-x-jewel-distro-basic-vps
- Run: http://pulpito.ceph.com/teuthology-2016-02-03_02:10:02-upgrade:infernalis-x-jewel-distro-basic-vps/
Jobs: 3397,... - 09:29 PM Feature #13702: 'ceph osd pool create' should not require pg_num
- -https://github.com/ceph/ceph/pull/7509-
- 09:12 PM Revision 31649e5c (ceph): test/osd/: rework ceph_test_rados buffer generation and verification
- The previous implementation was staggeringly inefficient.
Signed-off-by: Samuel Just <sjust@redhat.com> - 09:11 PM Revision 67b6fac6 (ceph): ceph_test_rados: switch to std::minstd_rand0
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 08:16 PM Revision 96f23eb2 (ceph): os/bluestore/BlueStore: fix wal tail block padding on zero
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:16 PM Revision dbf69792 (ceph): os/bluestore/BlueStore: tweak whitespace in _txc_finalize
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:16 PM Revision b3903b8c (ceph): os/bluestore/KernelDevice: make flush delay on inject crash tunable
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:16 PM Revision 15c09987 (ceph): os/bluestore/KernelDevice: crash even when there is no io
- If we set bdev_inject_crash, ensure we crash even if the device is
idle.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:16 PM Revision abe31b1a (ceph): msg/simple: fix warning
- msg/simple/Pipe.cc: In member function 'void Pipe::writer()':
msg/simple/Pipe.cc:1721:26: warning: suggest braces aro... - 08:16 PM Revision 8eac9c6b (ceph): os/bluestore/BlueStore: wr lock collection in _txc_add_transaction
- Do this in the caller to simplify the callees slightly.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:16 PM Revision f1bf983e (ceph): os/bluestore/BlueStore: fix wal tail block padding
- If the wal write starts partway into the tail block, we need to allocate
less than a full block.
Signed-off-by: Sage... - 08:16 PM Revision dd6fdc7c (ceph): os/bluestore/BlueStore: dump txn in _txc_add_transaction at high debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:16 PM Revision 9a6e6619 (ceph): os/bluestore/BlueStore: load OnodeRef in _txc_add_transaction
- Get OnodeRef ready in the caller, and keep it in a vector so that it
can be reused for any subsequent operations in t... - 06:40 PM Revision 4453b462 (ceph): Merge pull request #7507 from tchaikov/wip-cmake
- cmake: add KernelDevice.cc to libos_srcs
Reviewed-by: Samuel Just <sjust@redhat.com> - 06:39 PM rgw Bug #14613: daemon logfiles potentially created with root:root ownership
- Digging a bit deeper into this, it appears to only happen when "log_file" is explicitly set in ceph.conf.
During g... - 03:16 AM rgw Bug #14613: daemon logfiles potentially created with root:root ownership
- After a bit of instrumentation of global_init()/global_pre_init(), it appears the first attempt at opening/creating t...
- 05:28 PM Revision 82637be7 (ceph): cmake: add KernelDevice.cc to libos_srcs
- which fixes the build
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:12 PM devops Bug #14275: Ceph "giant" packages no longer available for installation on Ubuntu 14.04 "trusty"
- I'm leaning toward apt configuration problem.
Can you paste or upload your apt configs and verify you've followed ... - 04:54 PM devops Bug #14275: Ceph "giant" packages no longer available for installation on Ubuntu 14.04 "trusty"
- Just verified this and it is still the case. Adding the ceph-giant apt repo and running apt-get install ceph still in...
- 05:03 PM rgw Bug #14516 (Pending Backport): rgw: radosgw-admin --help doesn't show the "orphans find" command
- Fixed in master: https://github.com/ceph/ceph/pull/7473
- 04:59 PM Revision cd1b1c67 (ceph): Merge pull request #804 from ceph/wip-14388-hammer
- Added v0.94.3 to the mix
- 04:49 PM Revision 9837e4f1 (ceph): Merge pull request #813 from ceph/wip-whitelist-jewel
- Whitelisted "wrongly marked me down" for the tiering tests
- 04:47 PM Revision 183c7822 (ceph): Whitelisted "wrongly marked me down" for the tiering tests
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 04:46 PM rbd Documentation #14629 (Closed): rbd-replay documentation should be updated
- Now that tracing is optionally enabled, document the new configuration option (rbd tracing = true). Also note that i...
- 04:43 PM rbd Documentation #14628 (Closed): libvirt documentation should suggest log path, admin socket, and S...
- Update the libvirt documentation to suggest "log path = xyz" and "admin socket = xyz" under the appropriate [client.<...
- 04:16 PM Revision 457f023d (ceph): CMake: For CMake version <= 2.8.11, use LINK_{PRIVATE,PUBLIC} instead o...
- Signed-off-by: Tao Chang <changtao@hihuron.com>
- 02:46 PM Revision 2aeadc9a (ceph): Merge remote-tracking branch 'gh/jewel'
- 02:46 PM Revision cc2ce6ad (ceph): Merge branch 'wip-rados-bench'
- 02:45 PM Revision 669b9329 (ceph): rados: Add units to rados bench output
- Fixes: #12248
Signed-off-by: Gu Zhongyan <guzhongyan@360.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 02:44 PM Revision bf773084 (ceph): Merge pull request #7386 from liewegas/wip-features
- osd: skip redirect encoding if we can
Reviewed-by: Sage Weil <sage@redhat.com> - 02:41 PM Revision 06af9f09 (ceph): os/kstore: insert new onode to the front position of onode LRU
- See https://github.com/jjhuo/ceph/commit/caed88264d77f860376d4213cc98309a5daf3af2 for detail information.
Signed-off... - 01:58 PM Revision ed828d35 (ceph): Merge pull request #807 from ceph/wip-config
- suites/rados: test random queue options
- 01:53 PM Revision e478a4f2 (ceph): Merge branch 'weighted-priority-queue' of git://github.com/rldleblanc/ceph
- Reviewed-by: Samuel Just <sjust@redhat.com>
- 01:52 PM Revision 2e6db00d (ceph): Merge pull request #7357 from zhengbinh3c/master
- osd: fix memory leak in ReplicatedPG.cc error path
Reviewed-by: Sage Weil <sage@redhat.com> - 01:50 PM Revision 178c52ac (ceph): Merge pull request #7362 from xiexingguo/xxg-wip-fixbs
- osd: BlueStore: fix fsck and blockdevice read-relevant issue
Reviewed-by: Sage Weil <sage@redhat.com> - 01:49 PM Revision 680a999f (ceph): Merge pull request #7468 from liewegas/wip-test-fuse
- qa/workunits/objectstore/test_fuse.sh: fix root check
- 01:49 PM Revision 6c9a35b2 (ceph): Merge pull request #7476 from tchaikov/wip-include-expat-in-source
- rgw: do not include "expat.h" in header file
Reviewed-by: Sage Weil <sage@redhat.com> - 01:48 PM Revision a76755c4 (ceph): Merge pull request #7479 from roidayan/fix_xio_compilation
- msg/xio: fix compilation
- 01:48 PM Revision 9a804774 (ceph): Merge branch 'gelf-logging-backend' of git://github.com/irq0/ceph
- Reviewed-by: Kefu Chai <kchai@redhat.com>
- 01:47 PM Revision e85ffacb (ceph): scripts/run-coverity: fix upload process
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:52 AM Bug #14626 (New): Ceph CLI + python bindings restrict string inputs to ASCII, but mon doesn't
- @CephString.__init__@ does this:...
- 10:18 AM Revision c4e064fa (ceph): add test for norstats functionality
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 09:37 AM CephFS Backport #14624 (In Progress): hammer: fsx failed to compile
- 09:32 AM CephFS Backport #14624 (Resolved): hammer: fsx failed to compile
- https://github.com/ceph/ceph/pull/7501
- 09:35 AM Revision a8fc6a9f (ceph): fsx: checkout old version until it compiles properly on miras
- I sent a patch to xfstests upstream at
http://article.gmane.org/gmane.comp.file-systems.fstests/1665, but
until that'... - 09:14 AM Bug #14340: client command stuck forever
- i think i have reproduced this situation at the moment of trying to give up.
my reproduction is as follows:
1. ... - 08:58 AM Revision 41c3dc2e (ceph): test_bufferlist: add move tests for bufferlist
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 08:57 AM Revision 573a2d95 (ceph): bluestore/NVMEDevice: remove unused local variables
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 08:50 AM Bug #13098 (Resolved): OSD crashed when reached pool's max_bytes quota
- 08:49 AM CephFS Bug #12710 (Resolved): fsstress.sh fails
- 08:41 AM rbd Backport #14620: hammer: unsafe use of libnss PK11_GetBestSlot()
- @Loic, this appears to be a backport of https://github.com/ceph/ceph/pull/3896 which has no associated tracker issue.
- 01:20 AM rbd Backport #14620 (Resolved): hammer: unsafe use of libnss PK11_GetBestSlot()
- https://github.com/ceph/ceph/pull/7488
- 08:24 AM Linux kernel client Bug #14621 (Closed): 30s time out
- 02:50 AM Linux kernel client Bug #14621 (Closed): 30s time out
- 08:18 AM Revision 83ca8302 (ceph): bluestore/NVMEDevice: fix fd leak
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 07:54 AM Revision a5714fbe (ceph): bluestore/NVMEDevice: fix wrong remove_device logic
- It actually will reserve the device to be romoved only and clear others.
Signed-off-by: xie xingguo <xie.xingguo@zte... - 07:53 AM Revision 06f38373 (ceph): bluestore/NVMEDevice: fix compiling error
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:52 AM Bug #14623: Crush:add safe judgment for get parent hierarchy methond.
- https://github.com/ceph/ceph/pull/7493
- 05:59 AM Bug #14623 (Resolved): Crush:add safe judgment for get parent hierarchy methond.
- We should juge the id wheather is vaild.
- 06:49 AM rgw Bug #14382: Remove bucket,data and usage Not cleared
- 0.94.5
the same problem - 06:40 AM CephFS Bug #10436 (Fix Under Review): ceph-fuse: snapshot flushing from page cache to Client is not cohe...
- https://github.com/ceph/ceph/pull/7495
- 06:35 AM Revision 2e6e65d1 (ceph): suites/fs: enable all snapshost test scripts
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:26 AM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 06:23 AM Revision 07464701 (ceph): Mon: show the pool quota info on ceph df detail command
- Fixes: #14216
Signed-off-by: song baisen <song.baisen@zte.com.cn> - 06:01 AM Backport #13335 (Resolved): hammer: OSD crashed when reached pool's max_bytes quota
- 05:46 AM CephFS Backport #14584 (Resolved): hammer: fsstress.sh fails
- 05:45 AM rbd Bug #14225 (Resolved): rbd: fix bench-write
- 05:41 AM Revision f3bab8c7 (ceph): Merge pull request #7454 from dachary/wip-14584-hammer
- hammer: fsstress.sh fails
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:19 AM Revision caed8826 (ceph): os/bluestore: insert new onode to the front position of onode LRU
- When new added onode comes, it should go to the front of the LRU,
since it's least recently used.
Signed-off-by: Jia... - 04:38 AM Revision 31d86b15 (ceph): Merge pull request #6918 from asheplyakov/hammer-bug-12449
- osd: check for full before changing the cached obc (hammer)
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:26 AM Bug #14562: hammer: rados/test.sh: erasure-code-profile set name:testprofile failed
- Also at http://pulpito.ceph.com/loic-2016-02-01_19:50:11-rados-hammer-backports---basic-multi/1658/...
- 04:19 AM Revision 902abe73 (ceph): qa/workunits/post-file.sh: use /etc/default
- base-files doesn't existing on rhel. /etc/default is everywhere and it's
small.
Signed-off-by: Sage Weil <sage@redh... - 04:19 AM Revision e9039f4f (ceph): qa/workunits/post-file: pick a dir that's readable by world
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 04b00029e16971abf1937facbbff8da00d6a3452) - 04:19 AM Revision eb048a39 (ceph): qa/workunits/post-file.sh: sudo
- Only root can read the key in /usr/share/...
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 8... - 04:03 AM Revision 7c86775d (ceph): bluestore/bluefs_types: fix imcomplete output message
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:38 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- I encountered this issue only when selinux is enabled and type is mls (Multi Level Security protection). No problem w...
- 03:18 AM Revision 8167a22f (ceph): mds: function parameter 'df' should be passed by reference
- Signed-off-by: Na Xie <xie.na@h3c.com>
- 03:04 AM Revision 1c9c49ed (ceph): Crush when get immediate parent quickly reply.
- Fixes: #14334
Signed-off-by: song baisen <song.baisen@zte.com.cn> - 03:00 AM Revision 1c8c708e (ceph): librbd: ensure librados callbacks are flushed prior to destroying image
- Fixes: #14092
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 98157ab3274bd960e4487e34... - 03:00 AM Revision e5dfd3dd (ceph): WorkQueue: PointerWQ drain no longer waits for other queues
- If another (independent) queue was processing, drain could
block waiting. Instead, allow drain to exit quickly if
no... - 03:00 AM Revision f892566f (ceph): librbd: simplify IO flush handling
- Add a new convenience method to ImageCtx for handling flush
requests and cleanup flush handling with dealing with the... - 03:00 AM Revision edf60b45 (ceph): test: new librbd flatten test case
- AIO operations after a flatten operation were previously
hanging during the close of the parent image.
Signed-off-by... - 02:57 AM Bug #14622 (Won't Fix): initsystem: 30s time out leads to osd daemon start fail
- excute command : service ceph start (about ten osd start)
result: only osd.15 failed, because of timeout
log:... - 02:54 AM Revision b675b2eb (ceph): KernelDevice: put a guard for sync read
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:54 AM Revision cdbea720 (ceph): KernelDevice: remove unused local variables
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:54 AM Revision 627535a7 (ceph): KernelDevice: add aio_log_finish for write
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:54 AM Revision edf4e2e4 (ceph): KernelDevice: add error handling for sync_file_range
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:53 AM Revision 4d535f09 (ceph): KernelDevice: use standard errno for better tracing
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:31 AM Cleanup #14334 (In Progress): Crush when get immediate parent quickly reply.
- 02:31 AM Revision f0534bb1 (ceph): KernelDevice: use local aio config for start/stop logic
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:26 AM Revision 6325dea5 (ceph): BlockDevice: fix result code overflow
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:10 AM Bug #13778: OSD crash (giant)
- Ugh, sorry for the duplicate comment. I was trying to edit my previous comment to fix the formatting and not only did...
- 02:02 AM Bug #13778: OSD crash (giant)
- I appear to have run into this same problem, but I am running hammer:
ceph-0.94.5-0.el6.x86_64
I have one OSD t... - 02:00 AM Bug #13778: OSD crash (giant)
- I appear to have run into this same problem, but I am running hammer:
ceph-0.94.5-0.el6.x86_64
I have one OSD t... - 01:59 AM Revision 09d26448 (ceph): BlueFS: add log after updating prefer_bdev field.
- Fixes: #14474
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:59 AM Revision a3789e8c (ceph): BlueFS: fix unprecise calculation of sync interval
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:59 AM Revision 65e1a211 (ceph): BlueFS: stop alloc if unable to replay
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:59 AM Revision b593e1c1 (ceph): BlueFS: remove redundant intermediate buffer pad
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:59 AM Revision baf10b9b (ceph): BlueFS: remove unused local variable
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:59 AM Revision d8eb57da (ceph): BlueFS: fix typo
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:59 AM Revision 881ac7ad (ceph): BlueFS: fix race condition
- Fixes: #14480
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:59 AM Revision 32789684 (ceph): BlueFS: add a guard for log space allocation during mkfs
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:40 AM rgw Bug #13644: get_quota_info returns json in headers
- Presumably fix for this issue is in commit: 64fceed2202c94edf28b8315fe14c9affa8c0116
diff --git a/src/rgw/rgw_rest... - 01:24 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- This resurfaced in a similar form on a hammer cluster. After some analysis of the core file, it appeared that some of...
- 12:14 AM Revision a13cbf4f (ceph): Added v0.94.3 to the mix
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
02/02/2016
- 11:42 PM Revision e1faa316 (ceph): Whitelisted "soft lockup"
- to avoid failures on slow nodes like in #14618
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked fr... - 11:06 PM Bug #14568: "Caught signal" (out of memory?) in rados-hammer-distro-basic-vps
- Run: http://pulpito.ceph.com/teuthology-2016-01-31_09:00:02-rados-hammer-distro-basic-vps/
Job: 53523
rados/singlet... - 10:45 PM Revision 93413b5f (ceph): qa/workunits/rados/test.sh: bash
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:25 PM Bug #14461: test hung "joining thrashosds" in hammer tests
- Run: http://pulpito.ceph.com/teuthology-2016-02-02_02:10:12-upgrade:hammer-x-jewel-distro-basic-vps/
Job: 2128 - 09:58 PM Revision a9879aa9 (ceph): Merge pull request #810 from ceph/wip-schedule_rados-master
- Made rados runs in ovh call vps.yaml
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:50 PM Revision 97b0b2b9 (ceph): Made rados runs in ovh call vps.yaml
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 09:14 PM Revision ec36dcdf (ceph): rgw: approximate AmazonS3 HostId error field.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 08:47 PM Bug #14615: ceph_manager task hanging indefinitely, instead of failing
- Filed #14616 against ceph because I believe the logging is excessive.
- 08:43 PM Bug #14615 (Can't reproduce): ceph_manager task hanging indefinitely, instead of failing
- Seen in http://pulpito.front.sepia.ceph.com/haomai-2016-01-30_15:25:39-rados:thrash-wip-14566-distro-basic-smithi/524...
- 08:46 PM Bug #14616 (Resolved): When logging to a file fails, ceph logs excessively to stderr
- Seen in http://pulpito.front.sepia.ceph.com/haomai-2016-01-30_15:25:39-rados:thrash-wip-14566-distro-basic-smithi/524...
- 08:15 PM rbd Backport #14611 (Fix Under Review): hammer: Flattening an rbd image with a running Qemu instances...
- 06:46 PM rbd Backport #14611 (In Progress): hammer: Flattening an rbd image with a running Qemu instances caus...
- 03:57 PM rbd Backport #14611 (Resolved): hammer: Flattening an rbd image with a running Qemu instances causes ...
- https://github.com/ceph/ceph/pull/7485
- 07:56 PM rbd Backport #14610 (Fix Under Review): infernalis: Flattening an rbd image with a running Qemu insta...
- 06:46 PM rbd Backport #14610 (In Progress): infernalis: Flattening an rbd image with a running Qemu instances ...
- 03:57 PM rbd Backport #14610 (Resolved): infernalis: Flattening an rbd image with a running Qemu instances cau...
- https://github.com/ceph/ceph/pull/7484
- 06:36 PM Revision 669f1438 (ceph): buffer: add operator= for ptr/bufferlist rvalue
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 06:36 PM Revision 0305ceef (ceph): misc: using move construct to avoid extra atomic inc/dec
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 06:32 PM CephFS Bug #13903 (Resolved): Failure in TestStrays.test_ops_throttle
- Whoops, merged this last week.
- 05:58 PM rgw Bug #14613 (Resolved): daemon logfiles potentially created with root:root ownership
- With a recent ceph/master build (up to and including commit 60d0df5), radosgw creates it's logfile with root:root own...
- 05:24 PM Revision dd4e6e18 (ceph): buffer: add ptr move construct
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 05:17 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Zheng, what's the scenario that causes that — just using SELinux on a CephFS mount?
- 04:25 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- It's caused by selinux. Selinux code calls a getxattr() while we are processing MClientReply.
mount cephfs with co... - 05:08 PM Bug #14306: "RadosModel.h: 854: FAILED assert(0)" in rados-hammer-distro-basic-openstack
- Run: http://pulpito.ceph.com/teuthology-2016-02-01_09:00:02-rados-hammer-distro-basic-vps/
Job: ['43']... - 04:29 PM Bug #14609: rados tool does not work with 0 length input (crashes if '--striper' enabled)
- Sorry, process substitution works. I did something stupid with dd. The only problem is 0 length input:...
- 03:30 PM Bug #14609 (Resolved): rados tool does not work with 0 length input (crashes if '--striper' enabled)
- Command:...
- 04:08 PM Revision 06cecb4b (ceph): ceph_test_objectstore: fix warning
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:03 PM Revision 75395c11 (ceph): Merge pull request #7438 from ifed01/wip-pgbackend-cleanup
- osd: cleanup OSD/PGBackend interface a bit
Reviewed-by: Sage Weil <sage@redhat.com> - 04:03 PM Revision 9a349338 (ceph): os/bluestore/KernelDevice: explicit on ctor
- This was lost in the wip-spdk merge.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:03 PM Revision dd3c87d7 (ceph): doc: update PG doc with the backfill change
- Since the state reported is `backfilling` and `backfill_wait`
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 04:03 PM Revision 4c0d1d74 (ceph): mon: PG Monitor should report backfill_wait
- Instead of backfill as it is actually waiting for backfill instead of
actually backfilling
Fixes: #12744
Reported-by... - 04:03 PM Revision d3925a50 (ceph): Merge pull request #7467 from liewegas/wip-scrub-start
- osd: fix scrub start hobject
- 04:02 PM Revision 87efba42 (ceph): Merge branch 'wip-spdk' of git://github.com/yuyuyu101/ceph
- Reviewed-by: Sage Weil <sage@redhat.com>
- 04:00 PM Revision dc50f310 (ceph): Merge remote-tracking branch 'me/wip-lockdep'
- 03:56 PM rbd Bug #14483 (Pending Backport): Flattening an rbd image with a running Qemu instances causes librb...
- 03:56 PM rbd Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- Christian, thank you for the logs!
- 03:08 PM rbd Bug #14483 (In Progress): Flattening an rbd image with a running Qemu instances causes librbd wor...
- 03:26 PM rgw Bug #14599 (Duplicate): rgw: user quota may not adjust on bucket removal
- The original issue is already tagged for backport.
- 03:21 PM Feature #14411 (In Progress): fix lost-unfound
- 03:20 PM Feature #14429: make ceph-test-rados faster
- 03:09 PM rbd Bug #14482 (Resolved): rbd:rbd-nbd does not have an argument check for nbds_max
- *PR*: https://github.com/ceph/ceph/pull/7337
- 02:58 PM Bug #13690 (Closed): why does osd.11 take a long time to start
- Try reproducing with
debug osd = 20
debug filestore = 20
debug ms = 1
You can reopen if it's still not clear. - 02:51 PM Revision 482d1ca5 (ceph): Merge pull request #7480 from trociny/fix-journal-commit_position_task
- journal: reset commit_position_task_ctx pointer after task complete
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:35 PM RADOS Feature #14527: Lookup monitors through DNS
- Ahh OK. DNS SRV records might be better than a hardcoded hostname. See the DNS section here to see how OpenAFS does t...
- 11:22 AM RADOS Feature #14527: Lookup monitors through DNS
- I meant for the daemons. They no longer need a mon_host in the config.
If none is found they perform a DNS lookup.... - 10:54 AM RADOS Feature #14527: Lookup monitors through DNS
- I might be misunderstanding your request, but we already do that on the clients:...
- 02:29 PM CephFS Bug #14608 (Can't reproduce): snaptests.yaml failure: [WRN] open_snap_parents has:" in cluster log
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-30_18:04:02-fs-master---basic-openstack/13302/- 02:18 PM CephFS Bug #14607 (Duplicate): Some fuse tests fail with: failed to remove ‘/home/ubuntu/cephtest’: Dire...
e.g. http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-30_18:04:02-fs-master---basic-openstack/13319/
& ...- 02:16 PM Bug #14606 (Resolved): rest.py fails
- ...
- 02:09 PM Revision 9c95bb04 (ceph): mon: reduce CPU and memory manager pressure of pg health check
- When we don't need details about which PGs are stuck, we can just iterate
once over pg_stat map and increase appropri... - 02:01 PM Revision a682e77a (ceph): script/run-coverity: fix user
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:57 PM CephFS Bug #10436 (In Progress): ceph-fuse: snapshot flushing from page cache to Client is not coherent
- 11:44 AM CephFS Bug #10436: ceph-fuse: snapshot flushing from page cache to Client is not coherent
- 01:46 PM Bug #14598: osd: pure virtual method called, abrt in TrackedOp::dump
- /a/sage-2016-02-01_16:19:44-rados-wip-sage-testing2-distro-basic-mira/1482
- 01:43 PM Revision 4f49c6be (ceph): journal: reset commit_position_task_ctx pointer after task complete
- Otherwise, schedule_commit_task() would never schedule the next task
and the commit position would not be committed u... - 01:42 PM Bug #14213: osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- /a/sage-2016-02-01_16:19:44-rados-wip-sage-testing2-distro-basic-mira/1453
- 01:10 PM Bug #14213: osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- /a/sage-2016-02-01_16:19:44-rados-wip-sage-testing2-distro-basic-mira/1453
- 01:08 PM Revision aa5e8db7 (ceph): Merge remote-tracking branch 'gh/wip-da-SCA-20150910'
- Reviewed-by: Kefu Chai <kchai@redhat.com>
- 12:43 PM devops Bug #14605 (Closed): ceph.com EU mirror link broken
- On the ceph.com website page "DOWNLOADING A CEPH RELEASE TARBALL" there is a link to the download site followed by a ...
- 11:52 AM devops Bug #14604 (Resolved): ceph-0.80.11.tar.bz2 missing at http://download.ceph.com/tarballs/
- All the previous Firefly releases have both .tar.gz and .tar.bz2, **except** for 0.80.11 - please fix.
- 11:50 AM Revision 122f4068 (ceph): xio: fix compilation
- Signed-off-by: Roi Dayan <roid@mellanox.com>
- 11:48 AM Revision 2445b5e7 (ceph): osdc/objecter: update crush location in a safer way
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 10:56 AM Bug #13844: ceph df MAX AVAIL is incorrect for simple replicated pool
- I'm seeing a similar issue on my small cluster:...
- 10:46 AM Revision 25738406 (ceph): test/librados: fix hash position overflow issue
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 10:45 AM Revision 48dc0bf7 (ceph): rados: fix result code overflow
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:21 AM CephFS Bug #14557 (Duplicate): snaps: failed snaptest-multiple-capsnaps.sh
- ...
- 09:10 AM Revision 73651d9e (ceph): Merge pull request #7473 from yehudasa/wip-14516
- rgw-admin: document orphans commands in usage
- 06:58 AM Revision a3360b55 (ceph): osdc/objecter: fix race condition
- Fixes: #14603
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 06:56 AM Revision 1650324f (ceph): Merge pull request #7451 from wjin/fix
- msg/async: fix array boundary
Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:26 AM Revision 636b8f11 (ceph): rgw: do not include "expat.h" in heade file
- Building Ceph without the Expat development library currently results in
the following build error:
~/ceph> ./config... - 06:24 AM Bug #14603 (Resolved): Objecter: race condition and result code overflow
- int64_t Objecter::get_object_hash_position
This method shall be under protection of rwlock.
And the below metho... - 06:22 AM Revision f5f3282c (ceph): BlueStore: fix wrong action scope of enode
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:20 AM Backport #14602 (In Progress): hammer: ceph-disk: use blkid instead of sgdisk -i
- 05:57 AM Backport #14602 (Resolved): hammer: ceph-disk: use blkid instead of sgdisk -i
- https://github.com/ceph/ceph/pull/7475
- 06:18 AM Revision 88ffcc2c (ceph): ceph-disk: use blkid instead of sgdisk -i
- sgdisk -i 1 /dev/vdb opens /dev/vdb in write mode which indirectly
triggers a BLKRRPART ioctl from udev (starting ver... - 06:11 AM Revision 2991e79f (ceph): Merge pull request #7472 from badone/wip-ceph-disk-typo
- ceph-disk: Fix trivial typo
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:04 AM Revision f761113a (ceph): BlueStore: add a guard for overlay loading
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision 10bd8add (ceph): BlueStore: add a guard for collection loading
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision 559a81b1 (ceph): BlueStore: fix enode verification logic
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision 3e61e3b0 (ceph): BlueStore: fix duplicated counting of errors
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision 9bc0c316 (ceph): BlueStore: try to scan as many errors as possible
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision 2d524386 (ceph): BlueStore: fix unhandled return code from blockdevice APIs
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision d1d6014d (ceph): BlueStore: fix wrong decode logic of nid_max
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision e10490ab (ceph): BlueStore: add error handling for clone_range
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:04 AM Revision 41ff579f (ceph): BlueStore: add error handling for clone
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 05:04 AM Bug #9570 (Need More Info): osd crash in FileJournal::WriteFinisher::entry() aio
- 03:51 AM Bug #13422 (Fix Under Review): pid file that was deleted after ceph restart leads to osd process ...
- 03:26 AM Revision 3b93bc47 (ceph): Merge pull request #6813 from manens/pybind_rados_snapshot_read
- pybind: Implementation of Ioctx.set_read to allow read from snapshots
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:19 AM Bug #14080: ceph-disk: use blkid instead of sgdisk -i
- There are a number of other problems that were fixed recently and that should be backported. I'm not sure how we shou...
- 12:33 AM Revision 105a76bf (ceph): rgw-admin: document orphans commands in usage
- Fixes: #14516
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:22 AM Revision 820a7605 (ceph): ceph-disk: Fix trivial typo
- Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
02/01/2016
- 10:50 PM Revision 3cf29729 (ceph): msg: ignore request_redirect_t encode/decode when we not need
- Signed-off-by: Xinze Chi <xinze@xsky.com>
- 10:12 PM Revision 1179ddc2 (ceph): Merge pull request #7445 from xiexingguo/xxg-wip-mem
- osd: memstore: fix blocksize for statfs
Reviewed-by: Sage Weil <sage@redhat.com> - 10:09 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
- Run: http://pulpito.ceph.com/teuthology-2016-01-31_17:10:11-upgrade:hammer-x-infernalis-distro-basic-vps/
Job: 53610 - 10:06 PM rgw Bug #14599 (Duplicate): rgw: user quota may not adjust on bucket removal
If the user/admin removes a bucket using --force/--purge-objects options with s3cmd/radosgw-admin respectively, the...- 09:29 PM Bug #13897: (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED assert(r == 0)
- Also in run
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-01_02:00:02-rados-infernalis-distro-basic-open... - 09:27 PM Bug #14598 (Duplicate): osd: pure virtual method called, abrt in TrackedOp::dump
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-01_02:00:02-rados-infernalis-distro-basic-openstack/
... - 08:49 PM Revision 15ea140b (ceph): qa/workunits/objectstore/test_fuse.sh: fix root check
- $EUID not defined everywhere.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:02 PM Revision eb5db371 (ceph): os/memstore: disable lockdep on Collection::lock
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:02 PM Revision ada41f46 (ceph): lockdep: dump lock names if we run out of IDs
- ..just in case we are doing something silly, like misnaming locks.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:02 PM Revision 622ed5ad (ceph): common/RWLock: alloc lockdep to be disabled
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:02 PM Revision 08df77a2 (ceph): os/filestore/CollectionIndex: disable lockdep on access_lock
- This overflows the lockdep table when there are too many PGs. This
code is static so I'm not worried about new lockin... - 08:02 PM Revision fe649a34 (ceph): os/bluestore: disable lockdep on Collection::lock
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:02 PM Revision 18d3a39a (ceph): os/kstore: disable lockdep on Collection::lock
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:02 PM Revision 300b15d5 (ceph): os/bluestore: fix typo (again)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:59 PM Revision 98586263 (ceph): os/bluestore: fix typo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:52 PM Bug #14080: ceph-disk: use blkid instead of sgdisk -i
- I adjusted it to try 20 times instead of 5 (waits 20 minutes) and only got a negligible improvement (1 more osd was d...
- 07:44 PM Revision 70704837 (ceph): Merge pull request #7400 from yuyuyu101/wip-13938
- librbd: Avoid create two threads per image
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Jason Dillaman... - 07:42 PM Revision f5419676 (ceph): Merge pull request #7409 from dillaman/wip-librbd-watch-notify
- tests: improve simulation of watch/notify handling
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:58 PM rbd Bug #14595 (New): Race between releasing exclusive lock and incoming write ops
- Should verify it's not an issue in master due to the major refactoring of librbd.
- 06:56 PM rbd Bug #14595 (Resolved): Race between releasing exclusive lock and incoming write ops
- A thread releasing the exclusive lock (and flushing the cache) might race with a thread submitting a new write operat...
- 06:56 PM Revision da9c3955 (ceph): Merge pull request #6562 from Aran85/authedpermcheck
- rgw: fix the condition of authenticated user's permit check .
- 06:55 PM Bug #14372 (New): ENOTSUPP on trimtrunc (EC with cache pool on top)
- 06:49 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- Is it possible that since I had no cache when I encountered the problem, that caused corrupt data to be written to th...
- 05:24 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- David, does this sequence of events seem like an issue you're aware of? Do you have any theories? I haven't checked t...
- 06:32 PM Revision 62906d88 (ceph): osd/PG: fix scrub start object
- This was changed in 05d79faa512210b0f0a91640d18db33b887a6e73 but it needs
to be more precise to avoid breaking BlueSt... - 06:02 PM Bug #14590: cephfs set directory layout datapool to 0 failed
- Greg Farnum wrote:
> Mixing pools probably isn't great, but we still want pool 0 to be available — not every user wi... - 05:49 PM Bug #14590: cephfs set directory layout datapool to 0 failed
- Mixing pools probably isn't great, but we still want pool 0 to be available — not every user will have RBD running.
- 05:46 PM Bug #14590: cephfs set directory layout datapool to 0 failed
- Why do you want to set the cephfs data pool to rbd? This is generally a bad idea and won't work in all circumstances...
- 05:35 PM Bug #14590: cephfs set directory layout datapool to 0 failed
- I don't think we're concerned about the ioctl since it's deprecated in favor of virtual xattrs. But please make sure ...
- 10:10 AM Bug #14590: cephfs set directory layout datapool to 0 failed
- @diff --git a/src/mds/Server.cc b/src/mds/Server.cc
index ba4fe15..b894233 100644
--- a/src/mds/Server.cc
+++ b/sr... - 09:31 AM Bug #14590 (Won't Fix): cephfs set directory layout datapool to 0 failed
- I want to use rbd pool(its poolid = 0) as data pool,
by doing follow steps:
1. mount -t ceph 192.168.3.101:/ /ceph
... - 04:42 PM rbd Feature #14593 (New): Support optional alignment of journal entries
- Writing out 4K aligned journal entries will avoid the potential for un-aligned (two block) writes in the OSD.
- 04:36 PM Bug #14400 (Resolved): Snappy decompressor may assert when handling segmented input bufferlist
- 04:26 PM Revision 0819509c (ceph): qa/workunits/rados/test.sh: run tests in parallel by default
- Faster! 8 min vs the original 21 min on my vstart cluster.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:52 PM Revision 5374e4f4 (ceph): Merge pull request #7291 from majianpeng/vstart.sh
- vstart.sh: If use '-n' delete related source rather than consider '-k'.
Reviewed-by: Sage Weil <sage@redhat.com>
Rev... - 03:42 PM rbd Feature #13274 (Resolved): LTTng-UST should be optionally enabled
- 03:34 PM Revision 4d2c0f50 (ceph): osd/ECTransaction: Removing unused local
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:33 PM Revision ccebf7a3 (ceph): osd/PGBackend: PGBackend interface cleanup - make some interface method...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:26 PM Revision 1dfc8ef8 (ceph): Merge pull request #7397 from tchaikov/wip-kill-warnings
- build: kill warnings
Reviewed-by: Sage Weil <sage@redhat.com> - 02:54 PM Revision 7fcfc280 (ceph): Compressor: add zlib unittests
- Signed-off-by: Alyona Kiseleva <akiselyova@mirantis.com>
- 02:54 PM Revision 7bde5c43 (ceph): Compressor: add Zlib compression plugin
- Signed-off-by: Kiseleva Alyona <akiselyova@mirantis.com>
- 02:51 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- the crash you spotted is root caused at #14592
- 02:49 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- @Steve,
i am sorry for the latency, was on another issue last week. the trimming behaviour is exactly what we expe... - 02:29 PM Backport #14592 (Closed): osd crashes when handling a stale pg-create message (hammer)
- see http://tracker.ceph.com/issues/13990#note-39.
reproduce steps:
# monitor sends pg-create messages, so the @... - 02:19 PM Bug #14566 (Fix Under Review): AsyncMessenger: dispatch reset event after connection closed
- https://github.com/ceph/ceph/pull/7453
- 02:05 PM Revision 7d02b822 (ceph): configure: remove unused lines
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:02 PM Revision 86cd2f8b (ceph): NVMEDevice: use the only aio thread to process task
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:02 PM Revision 55c99558 (ceph): BlueStore: use special symbol to distinguish backend type
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:02 PM Revision 55720640 (ceph): BlueStore: add logger to record state transition latency
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:02 PM Revision 81defd16 (ceph): NVMEDevice: add buffer write support
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:01 PM Revision bb5d9095 (ceph): RocksDB: add block cache size option to RocksDB
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:01 PM Revision 584f8f98 (ceph): NVMEDevice: add flush perf counter calculate
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:01 PM Revision 79f9d1e1 (ceph): NVMEDevice: add polling time perf counter
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:01 PM Revision 619c08c1 (ceph): NVMEDevice: no need to detach nvme device
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:01 PM Revision 5497e2fa (ceph): BlueStore: allow nvme driver read from path
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:01 PM Revision dd5c36d9 (ceph): NVMEDevice: add perf counter for queue time
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision b561d448 (ceph): NVMEDevice: delay nvme aio thread start in case of logger is null
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 91bf3bb3 (ceph): NVMEDevice: make flush wait for all write completed
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 6b637df7 (ceph): NVMEDevice: let perf counter do early
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 8e258ffb (ceph): NVMEDevice: add perf counter
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision cbe42e16 (ceph): NVMEDevice: disable flush command now
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 705fd5b7 (ceph): NVMEDevice: use stringify instead of std::to_string
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision b365d2c6 (ceph): NVMEDevice: add log message to reminder potential failed reason
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 30342ab6 (ceph): BlockDevice: Move KernelDevice reap ioc to BlockDevice
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 83c8261e (ceph): NVMEDevice: adjust indent
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 23fd140d (ceph): NVMEDevice: impl read_buffered method
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 47335108 (ceph): NVMEDevice: let aio_write submit request FIFO
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 69e5a6d1 (ceph): NVMEDevice: make controller global shared
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 3bdd068a (ceph): KernelDevice: Remove redundancy lines
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 6081a58f (ceph): NVMEDevice: Fix typo
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 8a59bd87 (ceph): NVMEDevice: fix multi ops in one IOContext bug
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 3776af0c (ceph): NVMEDevice: add flush support
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 87402561 (ceph): NVMEDevice: add retry support
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 19a3c7eb (ceph): NVMEDevice: make aio thread pause when idle
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 997716c6 (ceph): NVMEDevice: don't try to acquire lock always
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 263353bd (ceph): NVMEDevice: adjust request/task memory pool size
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 0525aae5 (ceph): NVMEDevice: wrap C header file
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 4e85f5ec (ceph): NVMEDevice: fix unknown serial number problem
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 2ad7c182 (ceph): NVMEDevice: SPDK only permit submit/poll within one thread
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 4689bd27 (ceph): NVMEDevice: Fix static method
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision a5748cb2 (ceph): NVMEDevice: make read/write all async
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision ac654f09 (ceph): BlockDevice: initialize backend_priv
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 53c8b775 (ceph): BlueFS: Use num_pending instead of pending_aios
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 39c13181 (ceph): NVMEDevice: reorder signal in case of signaled thread modify IOContext
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 153660c8 (ceph): BlockDevice: Add override to explicit
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision fbdcb12c (ceph): BlueFS: fix comparison warning
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision ba5973f7 (ceph): configure.ac: fix spdk external header location
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision abb19d68 (ceph): NVMEDevice: remove unused variables
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision b8994525 (ceph): NVMEDevice: let IOContext can use NVMEDevice pointer
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision bb1adcf4 (ceph): NVMEDevice: nvme.h use _Static_assert which from c11
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision f911e2bf (ceph): NVMEDevice: add spdk/pci.h
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 5aa1c86f (ceph): Makefile: let spdk/dpdk libraries linked in upper layer
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision ee4951d0 (ceph): makefile: add SPDK detect and NVMEDevice to Makefile
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 415111ff (ceph): NVMEDevice: use device name instead of path
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 3a604066 (ceph): NVMEDevice: fix compile error
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision e64d16d5 (ceph): BlockDevice: Fix compile error
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision e76f716a (ceph): bluestore: add NVMEDevice backend
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 35576154 (ceph): bluestore: rename BlockDevice to KernelDevice matching NVMEDevice
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision 1d9448ee (ceph): BlueStore: abostract BlockDevice based KernelDevice and NVMEDevice
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:00 PM Revision b771c02d (ceph): BlueStore: Add BlockDevice ability to create different backend
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 01:52 PM Bug #9570: osd crash in FileJournal::WriteFinisher::entry() aio
- I'd try with a newer kernel - as new as the environment allows. If it's still a problem, I'd bump in-memory (the num...
- 11:01 AM Bug #9570: osd crash in FileJournal::WriteFinisher::entry() aio
- @Ilya
If you were to hit this kind of crash not often but sometimes which is quite annoying, what would you do to ... - 12:21 AM Bug #9570: osd crash in FileJournal::WriteFinisher::entry() aio
- Loic Dachary wrote:
> journal aio to 165552576~80 got (8192) Unknown error 8192
> meaning an attempt to write 80 by... - 12:39 PM rgw Bug #14591: make check is looking for radosgw-admin even if --with-radosgw is not engaged in conf...
- It's pretty strange because after rebuilding with the proper option and getting radosgw-admin process being compile I...
- 10:21 AM rgw Bug #14591 (Closed): make check is looking for radosgw-admin even if --with-radosgw is not engage...
- While doing a make check on my local system (compiling the current master) I had the following error :
src/test/cl... - 10:10 AM Bug #13422: pid file that was deleted after ceph restart leads to osd process lose control
- https://github.com/ceph/ceph/pull/7075
- 10:00 AM Bug #13422 (In Progress): pid file that was deleted after ceph restart leads to osd process lose ...
- 10:01 AM Bug #14575 (Duplicate): daemons leave pid files behind in /home/ubuntu/cephtest
- Re-opened #13422 to help with backporting since fixing this problem is required for the 13422 backports to work prope...
- 07:53 AM Bug #14575: daemons leave pid files behind in /home/ubuntu/cephtest
- When running the ceph-disk suite, I get...
- 09:54 AM Backport #14583 (Need More Info): hammer: pid file that was deleted after ceph restart leads to o...
- 04:31 AM Backport #14583: hammer: pid file that was deleted after ceph restart leads to osd process lose c...
- loic, the fix is might need more work. see https://github.com/ceph/ceph/pull/7075#issuecomment-177181579.
could y... - 03:29 AM Backport #14583 (Resolved): hammer: pid file that was deleted after ceph restart leads to osd pro...
- https://github.com/ceph/ceph/pull/7671
- 09:53 AM Backport #14582 (Need More Info): infernalis: pid file that was deleted after ceph restart leads ...
- 04:31 AM Backport #14582: infernalis: pid file that was deleted after ceph restart leads to osd process lo...
- loic, the fix is might need more work. see https://github.com/ceph/ceph/pull/7075#issuecomment-177181579.
could y... - 03:29 AM Backport #14582 (Rejected): infernalis: pid file that was deleted after ceph restart leads to osd...
- https://github.com/ceph/ceph/pull/7564
- 09:51 AM rgw Bug #12728 (Resolved): rgw: value of Swift API's X-Object-Manifest header is not url_decoded duri...
- 09:51 AM Bug #13374 (Resolved): systemd: no rbdmap systemd unit file
- 09:50 AM rgw Bug #13709 (Resolved): init script reload doesn't work on EL7
- 09:49 AM Feature #14217 (Resolved): tool for artificially inflate the leveldb of the mon store for testing...
- 08:44 AM Support #14588: Can't add new osd an existing cluster.
- log file can't attach
[[http://keepalive.bcc.bilkent.edu.tr/osd.16.log]] - 08:40 AM Support #14588 (New): Can't add new osd an existing cluster.
- This is more than 8 year old cluster. I upgrade to infernalis.
It's working well.
i get a disk failure. i try to ... - 08:44 AM rgw Bug #14589 (Resolved): bucket check --check-objects has not return
radosgw-admin bucket check --bucket=bkt-keyuser --fix --check-objects- 07:28 AM Revision 2e2eb4cb (ceph): AsyncConnection: let ack reply use MSG_MORE flag
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:28 AM Revision f6b87d3b (ceph): AsyncConnection: use move instead of bufferlist copy construct
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:28 AM Revision 86883b25 (ceph): AsyncMessenger: add perf counter for inline message sent
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:28 AM Revision 6055d963 (ceph): AsyncConnection: add a debug option to test noninline way
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:23 AM Revision 30d079f7 (ceph): Merge pull request #808 from dachary/wip-smithi-disks-hammer
- smithi disks are too fast and fill quickly
- 07:21 AM Revision f92a64af (ceph): rados: 5m radosbench (not 10m)
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 04e41a608bf5f271bd062718051597977678d2db) - 07:20 AM Revision c5321628 (ceph): rados: run radosbench for 10m (not 15m)
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 6110421bcef2d0d1d4f921822a7161a423d763ca) - 07:20 AM Revision 53cebaba (ceph): rados: run radosbench for 15m instead of 30m
- The smithi disks fill after about 20m.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit e2f9ced... - 06:40 AM Revision 8c7261b0 (ceph): Rgw: check the return value when call fe->run()
- Fixes: #14585
Signed-off-by: wei qiaomiao <wei.qiaomiao@zte.com.cn> - 06:33 AM Revision e9872ad6 (ceph): civetweb: update submodule to silence a compile warning
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 06:33 AM Revision 493619a9 (ceph): common,osd: remove _process(T *t) to silence warnings
- * and mark the WorkQueue::_process(T *, TPHandle&) a pure virtual
method. so we must override it
* and mark all ove... - 06:26 AM Revision 127e7c07 (ceph): mon: monmap created is 0.000000 use ceph-deploy installed
- Fixed: #14130
Signed-off-by: duanweijun <duanweijun@h3c.com> - 06:02 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. rados...
- 06:01 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. upgrade...
- 06:00 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. powercycle...
- 05:05 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. fs...
- 05:02 AM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 05:17 AM Bug #13781: Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- it sounds like a dup of #13422, but it's not. because as sage pointed out
> messages shows no attempt to start osd... - 05:16 AM Bug #14559 (Resolved): bluestore broken in current master
- 04:59 AM rbd Bug #14058: Can't build Ceph with --without-rbd and --with-debug
- please note this also applies to hammer. but guess "rgw" is enabled most of the time, so we don't backport the fix..
- 04:58 AM Revision 3e469f6d (ceph): rgw: fix the condition of authenticated user's permit check
- before fix:
put a bucket under one user with authenticated-read permit
> ./s3curl.pl http://myobs.com/mybucket --put ... - 04:50 AM Backport #14587 (In Progress): hammer: qa/workunits/post-file.sh: sudo
- 04:44 AM Backport #14587 (Resolved): hammer: qa/workunits/post-file.sh: sudo
- https://github.com/ceph/ceph/pull/7456
- 04:43 AM Bug #14586 (Resolved): qa/workunits/post-file.sh: sudo
- https://github.com/ceph/ceph/commit/82b0243ec318457e376288a6b32487fbea059705
- 03:49 AM rgw Bug #14585 (Resolved): rgw_main.cc: fuction main should not ignore the return value when call fe-...
- rgw_main.cc: fuction main should not ignore the return value when call fe->run(), for the following example, the rado...
- 03:33 AM CephFS Backport #14584 (In Progress): hammer: fsstress.sh fails
- 03:30 AM CephFS Backport #14584 (Resolved): hammer: fsstress.sh fails
- https://github.com/ceph/ceph/pull/7454
- 03:33 AM Revision 1b028594 (ceph): qa/fsstress.sh: fix 'cp not writing through dangling symlink'
- On some test machines, /usr/lib/ltp/testcases/bin/fsstress is
dangling symlink. 'cp -f' is impotent in this case.
Fi... - 03:27 AM Backport #14581 (Resolved): hammer: should compact full epochs in monitor
- https://github.com/ceph/ceph/pull/7446
- 03:27 AM Backport #14580 (Rejected): infernalis: should compact full epochs in monitor
- https://github.com/ceph/ceph/pull/7514
- 03:27 AM Backport #14579 (Resolved): hammer: mon sync does not copy config-key
- https://github.com/ceph/ceph/pull/7576
- 03:27 AM Backport #14578 (Rejected): infernalis: mon sync does not copy config-key
- https://github.com/ceph/ceph/pull/7562
- 03:26 AM CephFS Bug #12710 (Pending Backport): fsstress.sh fails
- 03:08 AM Bug #11101 (Pending Backport): ceph tell: broken error message / misleading hinting
- 03:05 AM Backport #13769 (New): EC async "fast read" patchset for hammer (EC read latency improvements)
- Cool, please update the description with a URL to the pull request when you do so and switch the status back to *In P...
- 03:03 AM Revision f209819f (ceph): [ceph-fuse] fix ceph-fuse writing to stale log file after log rotation
- This fix should be applied to hammer branch. It can't be directly applied to master branch, because logrotate.conf is...
- 03:02 AM rgw Backport #13513 (Resolved): rgw: value of Swift API's X-Object-Manifest header is not url_decoded...
- 03:01 AM Backport #13672 (Resolved): tests: testprofile must be removed before it is re-created
- 03:01 AM Backport #13678 (Resolved): systemd: no rbdmap systemd unit file
- 03:01 AM rgw Backport #13831 (Resolved): hammer: init script reload doesn't work on EL7
- 03:01 AM rgw Backport #13888 (Resolved): hammer: orphans finish segfaults
- 03:00 AM Backport #14470 (Resolved): hammer: tool for artificially inflate the leveldb of the mon store fo...
01/31/2016
- 11:52 PM Bug #11298: aio gets EPERM when update-grub runs
- Not related to #12100 either - #12100 is half a #9570 half a hardware failure.
- 11:50 PM Bug #11298: aio gets EPERM when update-grub runs
- This isn't related to, let alone a duplicate of, #9570. The result (to the right of "wrote") is correct both here an...
- 03:03 PM Revision 64fbda83 (ceph): Merge pull request #7266 from sahithi-rv/master
- common/str_map: cleanup: replaced get_str_map() function overloading by using default parameters for delimiters
Revi... - 03:02 PM Cleanup #14496 (Resolved): Crush:add some safe judgment.
- 03:02 PM Revision ace46dad (ceph): Merge pull request #7344 from songbaisen/song8
- crush: add safety assert
Reviewed-by: Sage Weil <sage@redhat.com> - 03:01 PM Revision 159df429 (ceph): Merge pull request #7363 from cxwshawn/mon-sync-fix
- mon: add mon_config_key prefix when sync full
Fixes: #14577
Reviewed-by: Sage Weil <sage@redhat.com> - 03:01 PM Bug #14577 (Resolved): mon sync does not copy config-key
- fixed by commit:b77cd31
- 03:00 PM Revision 74c87566 (ceph): Merge pull request #7383 from liewegas/wip-bluestore
- osd: bluestore: some new c++11-isms, a couple reverts
- 12:35 PM Fix #12947 (Resolved): Race condition in rados bench
- 12:34 PM Bug #14330 (Resolved): configure.ac: no use to add "+" before ac_ext=c
- 12:34 PM Bug #11661 (Resolved): "FAILED assert(0 == "Running incompatible OSD")"
- 12:32 PM Bug #10093 (Resolved): ceph-monstore-tool: FAILED assert(!is_open)
- 12:31 PM Bug #14397 (Resolved): disable filestore_xfs_extsize by default
- 10:53 AM Revision a37b98a9 (ceph): Event: fix array boundary
- fd should be less than nevent when deleting
Signed-off-by: Wei Jin <wjin.cn@gmail.com> - 09:23 AM Bug #14537: should compact full epochs in monitor
- hammer backport was merged at https://github.com/ceph/ceph/pull/7446
- 08:30 AM Revision b8bd9cbf (ceph): cmake: fix "jobserver unavailable" warning
- use ${MAKE} so the make command can be properly propagated to their
children
Signed-off-by: Kefu Chai <kchai@redhat.... - 08:21 AM Revision a17ea399 (ceph): OSD:memory leak in ReplicatedPG.cc
- "return NULL" in "if (p == snapset.clones.end())" can not free the
memory of "*repop"
Signed-off-by: Bin Zheng <zhen... - 07:16 AM rgw Backport #13820 (Resolved): hammer: Setting ACL on Object removes ETag
- 07:15 AM devops Bug #12935 (Resolved): ceph.spec.in License line does not reflect COPYING
- 05:22 AM Revision 2292dd98 (ceph): Event: don't wakeup if caller is thread self
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 04:18 AM Revision 2699c474 (ceph): rgw: fix the signed/unsigned comparison warning
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:18 AM Revision f8adf409 (ceph): cmake: disable unused-variable warning for rocksdb
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:18 AM Revision d50bda5b (ceph): rados: bench: fix the signed/unsigned comparison warning
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 02:42 AM Backport #14376 (Resolved): scrub suicide timeout is the same as the regular timeout -- should pr...
- 02:42 AM Revision 2c8e5793 (ceph): Merge pull request #7236 from athanatos/wip-14376
- config_opts: increase suicide timeout to 300 to match recovery
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rado... - 02:42 AM Revision 1cab151a (ceph): Merge pull request #6450 from dachary/wip-13672-hammer
- tests: testprofile must be removed before it is re-created
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wi... - 02:41 AM devops Backport #13859 (Resolved): hammer: ceph.spec.in License line does not reflect COPYING
- 02:41 AM Revision a134c44d (ceph): Merge pull request #6680 from SUSE/wip-13859-hammer
- hammer: ceph.spec.in License line does not reflect COPYING
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wi... - 02:41 AM Backport #12949 (Resolved): Race condition in rados bench
- 02:41 AM Revision 520792d5 (ceph): Merge pull request #6791 from branch-predictor/bp-5812-backport
- Race condition in rados bench
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wip-sage-testing-hammer---basic... - 02:40 AM Backport #14331 (Resolved): hammer: configure.ac: no use to add "+" before ac_ext=c
- 02:40 AM Revision 4d0fafb2 (ceph): Merge pull request #6973 from dreamhost/wip-configure-hammer
- configure.ac: no use to add "+" before ac_ext=c
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wip-sage-test... - 02:40 AM Backport #14292 (Resolved): osd/PG.cc: 3837: FAILED assert(0 == "Running incompatible OSD")
- 02:40 AM Revision 211a093d (ceph): Merge pull request #7206 from dzafman/wip-14292
- osd/PG.cc: 3837: FAILED assert(0 == "Running incompatible OSD")
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rad... - 02:39 AM Revision 0c136561 (ceph): Merge pull request #7207 from rldleblanc/recency_fix_for_hammer
- hammer: osd/ReplicatedPG: Recency fix for Hammer
Reviewed-by: Sage Weil <sage@redhat.com> - 02:39 AM Backport #14329 (Resolved): hammer: osd/ReplicatedPG: fix promotion recency logic
- 02:39 AM Backport #14497 (Resolved): hammer: ceph-monstore-tool: FAILED assert(!is_open)
- 02:39 AM Revision 1ea14bae (ceph): Merge pull request #7347 from tchaikov/wip-hammer-10093
- tools: ceph-monstore-tool must do out_store.close()
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wip-sage-... - 02:38 AM Backport #14467 (Resolved): hammer: disable filestore_xfs_extsize by default
- 02:38 AM Revision 1740d8ce (ceph): Merge pull request #7411 from dachary/wip-14467-hammer
- hammer: disable filestore_xfs_extsize by default
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wip-sage-tes... - 02:38 AM Revision 7848cdc4 (ceph): Merge pull request #7412 from dachary/wip-14470-hammer
- tools: tool for artificially inflate the leveldb of the mon store for testing purposes
Reviewed-by: Sage Weil <sage@... - 02:37 AM Revision 57abeab1 (ceph): Merge pull request #7446 from liewegas/wip-14537-hammer
- mon: compact full epochs also
http://pulpito.ceph.com/sage-2016-01-30_09:58:32-rados-wip-sage-testing-hammer---basic...
01/30/2016
- 08:02 PM Backport #12940 (Resolved): IO error on kvm/rbd with an erasure coded pool tier (after an upgrade...
- 08:01 PM rbd Backport #14143 (Resolved): hammer: Verify self-managed snapshot functionality on image create
- 08:01 PM rbd Backport #14283 (Resolved): hammer: rbd: fix bench-write
- 08:01 PM rbd Backport #14466 (Resolved): hammer: rbd-replay does not check for EOF and goes to endless loop
- 08:01 PM rbd Backport #14553 (Resolved): hammer: rbd: TaskFinisher::cancel should remove event from SafeTimer
- 08:00 PM rbd Backport #14543 (Resolved): hammer: Cannot reliably create snapshot after freezing QEMU IO
- 08:00 PM rbd Backport #14063 (Resolved): hammer: rbd merge-diff doesn't properly handle >2GB diffs
- 07:45 PM Revision 4d7d7c33 (ceph): Merge pull request #7182 from dachary/wip-14143-hammer
- hammer: Verify self-managed snapshot functionality on image create
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:45 PM Revision 83604867 (ceph): Merge pull request #7183 from dachary/wip-14283-hammer
- hammer: rbd: fix bench-write
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:45 PM Revision 501e01ac (ceph): Merge pull request #7416 from dachary/wip-14466-hammer
- hammer: rbd-replay does not check for EOF and goes to endless loop
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:44 PM Revision 97d4f6a7 (ceph): Merge pull request #7417 from dachary/wip-14553-hammer
- hammer: rbd: TaskFinisher::cancel should remove event from SafeTimer
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:44 PM Revision 51cc015c (ceph): Merge pull request #7407 from dillaman/wip-14543-hammer
- librbd: ImageWatcher shouldn't block the notification thread
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:44 PM Revision 23c24fc5 (ceph): Merge pull request #6980 from dillaman/wip-14063-hammer
- librbd: fix merge-diff for >2GB diff-files
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:05 PM Revision b1e27a59 (ceph): configure.ac: add pwritev check
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:03 PM Revision aa7b5056 (ceph): cmake: add default pwritev support now
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:02 PM Revision 75a9ee20 (ceph): buffer: refactor write_fd to make readable
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 06:04 PM Revision dc289fe4 (ceph): AsyncConnection: avoid dispatch event to a closed connection
- 1. thread 1 call AsyncConnection::accept and create file event
2. the owner thread of connection is waked from file e... - 05:12 PM Revision 4633e8d9 (ceph): cmake: remove duplicated HAVE_EXECINFO_H macro
- fixes the `"HAVE_EXECINFO_H" redefined` warning
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:05 PM Revision 88a95b7b (ceph): os/*stores: fix hidden warnings
- the CollectionHandle variant methods are hidden by the subclasses
who do not override it. so the compiler complains. ... - 05:01 PM Revision 72d1984d (ceph): os/bluestore: fix unsigned/signed comparision warning
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:36 PM Feature #14348: systemd: support multiple clusters
- Loic Dachary wrote:
> Would you be so kind as to create a pull request with these proposed changes ?
https://gith... - 03:17 PM Revision 96cfa484 (ceph): ceph_test_rados_api_*: use unique ec profiles for each pool
- This lets us run tests in parallel.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:04 PM Revision d44365bc (ceph): Merge pull request #7014 from efirs/ef_replace_coll_t_by_const_coll_t_ref
- osd: reduce CPU usage by replacing coll_t by const coll_t&
Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: S... - 02:03 PM Revision c9a2c808 (ceph): Merge pull request #7333 from xdonghai/xdh1
- osd: FileStore: modify the format of colon
Reviewed-by: Sage Weil <sage@redhat.com> - 02:03 PM Bug #14536 (Resolved): tools/rados/rados.cc: race condition in complete callback
- 02:03 PM Revision 04ea77b9 (ceph): Merge pull request #7392 from tianshan/wip-14536
- rados: fix race condition in load-gen complete callback
Reviewed-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com> - 02:02 PM Revision 98289735 (ceph): Merge pull request #7395 from xiexingguo/xxg-wip-fuse
- os/fusestore: add error handling
Reviewed-by: Sage Weil <sage@redhat.com> - 02:00 PM Bug #14537 (Pending Backport): should compact full epochs in monitor
- 02:00 PM Revision 1c9f2bcc (ceph): Merge pull request #7396 from tchaikov/wip-14537
- mon: compact full epochs also
Reviewed-by: Sage Weil <sage@redhat.com> - 01:59 PM Revision 9ad361a3 (ceph): Merge pull request #7402 from liewegas/wip-rados-bench
- rados: make rados bench metadata backward compatible
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:59 PM Revision 27c0d2b1 (ceph): Merge pull request #7418 from renhwsky/renhw-wip-monmapmonitor-cleanup
- mon: some cleanup in MonmapMonitor.cc
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Joao Eduardo Luis <joao... - 01:59 PM Revision 34ff79f1 (ceph): Merge pull request #7420 from mikulely/fix-osd-mon-exit-issue
- osd, mon: fix exit issue
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:58 PM Revision be74b77e (ceph): Merge pull request #7430 from xiexingguo/xxg-wip-kstore
- osd: kstore: fix decode logic and add flush
Reviewed-by: Sage Weil <sage@redhat.com> - 01:57 PM Revision 91093041 (ceph): mon: compact full epochs also
- by compacting the ${prefix}.${start}..${prefix}..${end} does not
necessary compact the range of ${prefix}."full_"${st... - 01:49 PM Revision 5ba0fc70 (ceph): Merge pull request #7432 from branch-predictor/bp-fix-read-bench
- rados: fix wrong op/object sizes in rand/seq bench
Reviewed-by: Sage Weil <sage@redhat.com> - 01:48 PM Revision d6208d71 (ceph): Merge pull request #7436 from liewegas/wip-bash
- tests: qa/workunits/objectstore/test_fuse.sh: no bashism
- 01:47 PM Bug #14575 (Duplicate): daemons leave pid files behind in /home/ubuntu/cephtest
- 2016-01-29T23:37:58.059 INFO:teuthology.orchestra.run.smithi059:Running: 'find /home/ubuntu/cephtest -ls ; rmdir -- /...
- 11:34 AM Revision 9da2fffd (ceph): AsyncConnection: add log for reap_dead and clean_handler
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 09:29 AM Revision cdf3c900 (ceph): os/memstore: return empty list if offset overflows
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:13 AM Revision 2817ffcf (ceph): Check for full before changing the cached obc
- ReplicatedPG::prepare_transaction(): check if the pool is full before
updating the cached ObjectContext to avoid the ... - 08:59 AM Revision 7d232d1a (ceph): os/memstore: fix wrong blocksize for statfs
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:14 AM Revision 79401d5a (ceph): rgw: remove duplicated code in RGWRados::get_bucket_info()
- The effect of line 7664-7665 is the same as the line 7658-7660
Signed-off-by: liyankun <lioveni99@gmail.com> - 03:32 AM Bug #14561: BlueStore: null pointer access
- https://github.com/ceph/ceph/pull/7435
- 03:31 AM Bug #14481 (Resolved): BlueFS: space leak
- https://github.com/xiexingguo/ceph/commit/c2b5a685454398e4445f9d8f4a87eb1fcd426185
- 03:31 AM Bug #14484: BlueFS: potential log data lost during compact
- https://github.com/xiexingguo/ceph/commit/5088dfd34ab76d29e6039f942e102d742c45b0b9
01/29/2016
- 11:53 PM RADOS Cleanup #13768: Remove tmap support
- rbd format 1 images use tmap for the rbd_directory - can convert that to omap, or wait until format 1 is removed to r...
- 11:48 PM RADOS Cleanup #13768: Remove tmap support
First phase of this fix is walk tree and convert all tmaps in Jewel:
https://github.com/ceph/ceph/pull/7003
A...- 11:46 PM Bug #14568: "Caught signal" (out of memory?) in rados-hammer-distro-basic-vps
- Run: http://pulpito.ceph.com/teuthology-2016-01-28_15:17:14-rados-hammer-distro-basic-vps/
Job: 48402
- 05:45 PM Bug #14568 (Rejected): "Caught signal" (out of memory?) in rados-hammer-distro-basic-vps
- As per Sam's suspect, maybe be ran out of memory.
Run: http://pulpito.ceph.com/teuthology-2016-01-28_09:00:02-rados-... - 11:44 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
- Run: http://pulpito.ceph.com/teuthology-2016-01-28_15:17:14-rados-hammer-distro-basic-vps/
Jobs: ['48303', '48314', ... - 11:26 PM Revision 916dff30 (ceph): suites/rbd: disable pool validation for pool snaps test
- Fixes: #14113
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 46dddfc54b8d650f111007ae... - 11:14 PM Revision 7d1ede6b (ceph): Merge pull request #7404 from sahithi-rv/Mutex
- rbd_fuse: replaced pthread_mutex*() functions with ceph Mutex wrapper
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 11:12 PM Bug #14547: "[ FAILED ] LibRadosTwoPoolsECPP.Flush" in upgrade:infernalis-x-jewel-distro-basic-vps
- ALso in http://qa-proxy.ceph.com/teuthology/teuthology-2016-01-29_02:10:02-upgrade:infernalis-x-jewel-distro-basic-vp...
- 10:48 PM Revision 579fbc8d (ceph): add some cppcheck-suppress noExplicitConstructor comments
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:48 PM Revision bbf05823 (ceph): make ctors with one argument explicit
- Use explicit keyword for constructors with one argument to
prevent implicit usage as conversion functions.
Signed-of... - 10:09 PM Revision 58fd981e (ceph): Initial draft for infernalis stable upgrade tests
- Fixed indentation
Replace ‘description’ with ’meta’
Incorporated Josh's comments
Moved all overrides to the top
Sign... - 09:30 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Zheng is looking at this and said he found it "strange", but I'm not sure if he's figured anything out yet.
- 08:37 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Did you find something? Is there a commit you could point me to ;)
- 07:15 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Stephan Wienczny wrote:
> I've uploaded the kernel with all modules and the /proc/config.gz to https://stephan.wienc... - 09:26 PM rgw Backport #14570: hammer: Incorrect ETAG calculated for POST uploads
- *original description*
Original issue:
http://tracker.ceph.com/issues/11241
https://github.com/ceph/ceph/commi... - 07:47 PM rgw Backport #14570: hammer: Incorrect ETAG calculated for POST uploads
- https://github.com/ceph/ceph/pull/7442
- 07:01 PM rgw Backport #14570 (Resolved): hammer: Incorrect ETAG calculated for POST uploads
- https://github.com/ceph/ceph/pull/7442
- 09:24 PM rgw Bug #11241 (Pending Backport): Incorrect ETAG calculated for POST uploads
- 09:22 PM rgw Backport #14569 (In Progress): hammer: Make RGW_MAX_PUT_SIZE configurable
- 07:34 PM rgw Backport #14569: hammer: Make RGW_MAX_PUT_SIZE configurable
- https://github.com/ceph/ceph/pull/7441
- 07:02 PM rgw Backport #14569: hammer: Make RGW_MAX_PUT_SIZE configurable
- Original issue:
http://tracker.ceph.com/issues/6999
https://github.com/ceph/ceph/commit/4aa102f911db7e6928f80c421... - 06:59 PM rgw Backport #14569 (Resolved): hammer: Make RGW_MAX_PUT_SIZE configurable
- https://github.com/ceph/ceph/pull/7441
- 09:21 PM rgw Feature #6999 (Pending Backport): Make RGW_MAX_PUT_SIZE configurable
- 08:51 PM Revision fd8f18ac (ceph): ceph_mon.cc: replace string::find() with compare()
- Fix for:
[src/ceph_mon.cc:396]: (performance) Inefficient usage of string::find()
in condition; string::compare() w... - 08:51 PM Revision 1f262a12 (ceph): mds/Server.cc: use string::compare() instead of ::find()
- Replace inefficient use of string::find() in conditions with
string::compare().
Changed checks in handle_set_vxattr(... - 08:51 PM Revision 0cb44573 (ceph): mon/Monitor.cc: replace inefficient usage of string::find() with compare()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 5d143510 (ceph): crush/CrushTester.cc: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision e892f9aa (ceph): rbd-replay-prep.cc: replace inefficient string::find() w/ compare()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision cc83e802 (ceph): crush/CrushTester.cc: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision e7941263 (ceph): man/8/ceph.rst: fix man page --admin-daemon
- The option "--admin-socket ADMIN_SOCKET/DAEMON_NAME" was blocked
as fix for #3944, fix man page to reflect it.
Fix f... - 08:51 PM Revision e89cc6ad (ceph): ECBackend.cc: fix dynamic_cast error handling
- Fix for:
CID 1316232 (#1 of 1): Unchecked dynamic_cast (FORWARD_NULL)
dynamic_cast: Dynamic cast to pointer dynamic... - 08:51 PM Revision b838300c (ceph): tools/rados/rados.cc: fix UNINTENDED_INTEGER_DIVISION
- Fix for:
CID 1297882 (#1 of 1): Result is not floating-point (UNINTENDED_INTEGER_DIVISION)
integer_division: Dividi... - 08:51 PM Revision 922d0b22 (ceph): osd/OSD.cc: fix UNINTENDED_INTEGER_DIVISION
- Fix for:
CID 1297883 (#1 of 1): Result is not floating-point (UNINTENDED_INTEGER_DIVISION)
integer_division: Dividi... - 08:51 PM Revision 8d131ba7 (ceph): tools/cephfs/DataScan.cc: fix expression
- Fix for:
[src/tools/cephfs/DataScan.cc:1137] -> [src/tools/cephfs/DataScan.cc:1137]:
(style) Same expression on bot... - 08:51 PM Revision 3c899321 (ceph): global_init.cc: add tag for cppcheck to suppress intentional memleak
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 91279dfb (ceph): test_crc32c.cc: close memory leak, free 'b' after malloc
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision dddc21b5 (ceph): mon/PGMonitor.cc: assign result directly
- Fix for:
[src/mon/PGMonitor.cc:1514] -> [src/mon/PGMonitor.cc:1515]: (performance)
Variable 'pool' is reassigned a ... - 08:51 PM Revision 21ac9781 (ceph): mon/PGMonitor.cc: return error instead of '0' from dump_stuck_pg_stats()
- Fix for:
[src/mon/PGMonitor.cc:1667] -> [src/mon/PGMonitor.cc:1669]: (performance)
Variable 'r' is reassigned a val... - 08:51 PM Revision 6fac5a95 (ceph): msg/simple/Pipe.cc: silence cppcheck warning about reassign before use
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 94cd338d (ceph): bluestore/bluestore_types.h: fix UNINIT_CTOR warning
- Fix for:
CID 1322813 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member seq... - 08:51 PM Revision 06956298 (ceph): mon/OSDMonitor.h: fix UNINIT_CTOR
- Remove unused variable 'CephContext *cct'.
Fix for:
CID 1322818 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR... - 08:51 PM Revision e0a66539 (ceph): os/bluestore/BlueStore.cc: fix UNINIT_CTOR in BlueStore
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision b43497c6 (ceph): auth/Crypto.cc: close theoretical memory leak
- Fix for:
CID 1296382 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable ckh going out of scope leaks... - 08:51 PM Revision bffcb2c1 (ceph): rgw/rgw_rados.cc: close resource leak in error case
- Fix for:
CID 1297867 (#1 of 1): Resource leak (RESOURCE_LEAK)
alloc_arg: put_obj_init allocates memory that is stor... - 08:51 PM Revision cbbe79af (ceph): src/mds/MDSRank.cc: remove delete calls from handle_asok_command()
- The allocated 'Formatter' passed to the function should be
freed by the caller to avoid missusage.
If handle_asok_co... - 08:51 PM Revision dec345ba (ceph): test/encoding/ceph_dencoder.cc: fix null pointer deref
- Fix for:
test/encoding/ceph_dencoder.cc:452:11: warning: Called C++ object pointer is null
if (den->is_determi... - 08:51 PM Revision 5128ac2c (ceph): MergeDiff.cc: close 'sd' correctly at the end of do_merge_diff()
- Fix for:
CID 1265562 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_handle: Handle variable sd going out of scope ... - 08:51 PM Revision 0df5a006 (ceph): test/librbd/fsx.cc: clarify calculation precedence for '&' and '?'
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 27383684 (ceph): src/ceph_fuse.cc: init members in ctor
- There is no need to call parent class ctor directly in
ctor init list. Instead init some missing members.
Signed-off... - 08:51 PM Revision 52308069 (ceph): common/RWLock.h: init member in ctor init list
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 41e95e7c (ceph): rgw/rgw_common.h: init members in ctor init list instead of body
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 9e4722b1 (ceph): rgw/rgw_orphan.h: init member in ctor init list instead of body
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 10f5a46a (ceph): rgw/rgw_rados.h: init member in ctor list
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision a442f5a5 (ceph): test/osd/RadosModel.h: fix class member hiding member from base
- The 'done' member of derived class is hiding 'done' member from
TestOp base class. Remove 'done' from derived classes... - 08:51 PM Revision bc8bd27e (ceph): journal/JournalMetadata.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 7981f9be (ceph): librbd/LibrbdAdminSocketHook.cc: prefer ++operator for non-primitive it...
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 65f694f0 (ceph): librbd/internal.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision e91f072f (ceph): os/bluestore/BlueStore.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision adfe0f3e (ceph): osd/osd_types.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 15e4ef92 (ceph): tools/rbd/action/Journal.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 4b550e01 (ceph): tools/rbd/action/Nbd.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision b811760f (ceph): test/librados/list.cc: fix -Wsign-compare
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 65ed1927 (ceph): rgw/rgw_rest.cc: fix -Wsign-compare
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:46 PM devops Bug #14275: Ceph "giant" packages no longer available for installation on Ubuntu 14.04 "trusty"
- Have you had this issue appear again? You might've hit download.ceph.com while we were doing an actual release.
If... - 08:36 PM Fix #14556 (Resolved): man: document listwatchers cmd in "rados" manpage
- 04:16 AM Fix #14556 (Pending Backport): man: document listwatchers cmd in "rados" manpage
- 04:15 AM Fix #14556 (Resolved): man: document listwatchers cmd in "rados" manpage
- The man page change was done in master at https://github.com/ceph/ceph/pull/7021 ,
- 07:26 PM Bug #14080: ceph-disk: use blkid instead of sgdisk -i
- Wes Dillingham wrote:
> I am experiencing an identical issue with the updated ceph-disk as provided here:
> https:... - 07:22 PM Bug #14080: ceph-disk: use blkid instead of sgdisk -i
- I am experiencing an identical issue with the updated ceph-disk as provided here:
https://raw.githubusercontent.com... - 06:55 PM Backport #14441: hammer: man: document listwatchers cmd in "rados" manpage
- PR for hammer: https://github.com/ceph/ceph/pull/7434
- 01:51 PM Backport #14441 (Resolved): hammer: man: document listwatchers cmd in "rados" manpage
- 05:53 AM Backport #14441 (New): hammer: man: document listwatchers cmd in "rados" manpage
- there exists a backport already, waiting on a pull request
- 04:19 AM Backport #14441 (In Progress): hammer: man: document listwatchers cmd in "rados" manpage
- 06:54 PM Revision 09ca1472 (ceph): tools/rados/rados.cc: fix race condition in load-gen complete callback
- Fixes: #14536
Signed-off-by: Tianshan Qu <tianshan@xsky.com> - 06:30 PM Bug #13781: Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- Loic,
Yes, the service is enabled. This comes up for random OSDs, when the machine is rebooted after kernel update... - 06:22 PM Revision 552e3e4a (ceph): suites/rados: test random queue options
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:32 PM Bug #14566 (Resolved): AsyncMessenger: dispatch reset event after connection closed
- I don't know whether this is related to the previous one.
sjust@teuthology:/a/samuelj-2016-01-28_16:56:58-rados-ma... - 05:28 PM Revision 30162870 (ceph): Merge pull request #6131 from rzarzynski/wip-admincreds-in-s3-keystone
- rgw: support admin credentials in S3-related Keystone authentication.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:52 PM Revision 17a70326 (ceph): admin-socket: add set_heap_property tests
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:37 PM Bug #14562 (Won't Fix): hammer: rados/test.sh: erasure-code-profile set name:testprofile failed
- Run: http://pulpito.ceph.com/teuthology-2016-01-28_09:00:02-rados-hammer-distro-basic-vps/
Job: 47816
Logs: http://... - 04:34 PM Backport #14329: hammer: osd/ReplicatedPG: fix promotion recency logic
- Loic, I think I have the commit comments updated appropriately. We are really hopeful to get this in 0.94.6. Please l...
- 04:31 PM Revision 95133910 (ceph): Merge pull request #6353 from theanalyst/wip-13513-hammer
- rgw: value of Swift API's X-Object-Manifest header is not url_decoded during segment look up
Reviewed-by: Yehuda Sad... - 04:31 PM Revision e43aca51 (ceph): Merge pull request #6620 from SUSE/wip-13820-hammer
- hammer: rgw: Setting ACL on Object removes ETag
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com> - 04:30 PM Revision 7e20e6e9 (ceph): Merge pull request #7186 from dachary/wip-13888-hammer
- hammer: rgw: orphans finish segfaults
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com> - 04:29 PM Revision ae56de09 (ceph): osd: recency should look at newest (not oldest) hitsets
- Reported-by: xinxin shu <xinxin.shu@intel.com>
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit ... - 04:28 PM Revision 5cefcb97 (ceph): osd/ReplicatedPG: fix promotion recency logic
- Recency is defined as how many of the last N hitsets an object
must appear in in order to be promoted. The previous ... - 04:12 PM Revision 136433d5 (ceph): rgw: support admin credentials in S3-related Keystone authentication.
- Fixes: #13302
Backport: infernalis, hammer
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 03:12 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- Loic Dachary wrote:
> @Tushar Gohad do you have a pull request to backport this to hammer ?
Thanks for the remind... - 04:08 AM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- @Tushar Gohad do you have a pull request to backport this to hammer ?
- 04:06 AM Backport #13769 (In Progress): EC async "fast read" patchset for hammer (EC read latency improvem...
- 04:06 AM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- @Guang Yang is https://github.com/ceph/ceph-qa-suite/pull/503 backported to hammer ?
- 02:51 PM Bug #14559: bluestore broken in current master
- This is fixed with the commits that were just merged into master, probably d3fd52a.
- 12:45 PM Bug #14559: bluestore broken in current master
- 12:40 PM Bug #14559 (Resolved): bluestore broken in current master
- As loicd noticed in http://tracker.ceph.com/issues/13942#note-12 there is an issue with bluestore in current master. ...
- 02:44 PM Revision 20138c6d (ceph): Merge pull request #7298 from racpatel/wip-doc-rac2
- doc :- fixing image in section ERASURE CODING
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:33 PM Revision c4892d94 (ceph): Graylog: Integrate with Log{Client,LogMonitor}
- Adds graylog/GELF logging support to clog and monitor log.
Changes to Graylog class:
- Support Logging LogEntry clas... - 02:33 PM Revision 3968852c (ceph): graylog: Fix ptr to bool conversion
- Signed-off-by: Marcel Lauhoff <lauhoff@uni-mainz.de>
- 02:33 PM Revision 882672dc (ceph): cmake: Add Graylog logging backend build support
- Signed-off-by: Marcel Lauhoff <lauhoff@uni-mainz.de>
- 02:32 PM Revision a483168a (ceph): Graylog2 logging
- Add graylog2 as logger target. Format log entries as GELF and send them via UDP to log server
New config options
- ... - 02:32 PM Revision 92bb5424 (ceph): graylog: Move graylog logging to Ceph::Log::Graylog class
- Encapsulates all resources the graylog logging backend needs into the
Graylog class.
Signed-off-by: Marcel Lauhoff <... - 02:32 PM Revision f88fcf03 (ceph): debian: Add build dep 'libboost-iostreams-dev'
- Required by graylog logging backend
Signed-off-by: Marcel Lauhoff <ml@irq0.org> - 02:22 PM Revision 4ca6bfd4 (ceph): ceph_osd.cc: fix unreachable flush call
- The calling chain for generic_server_usage():
generic_server_usage()
->generic_usage(true)
->exit(1)
cou... - 02:06 PM Revision 95c4287b (ceph): Merge pull request #6399 from SUSE/wip-13487-firefly
- osd: object_info_t::decode() has wrong version
Reviewed-by: David Zafman <dzafman@redhat.com> - 02:05 PM Revision aa0f2d39 (ceph): Merge pull request #6393 from SUSE/wip-13591-firefly
- mon: should not set isvalid = true when cephx_verify_authorizer return false
- 02:05 PM Backport #13589 (Resolved): infernalis: mon: should not set isvalid = true when cephx_verify_auth...
- 02:05 PM Revision 7ffe6ff4 (ceph): Merge pull request #6392 from SUSE/wip-13589-infernalis
- mon: should not set isvalid = true when cephx_verify_authorizer retur…
Reviewed-by: Sage Weil <sage@redhat.com> - 01:55 PM Revision a8fd5ba7 (ceph): Merge pull request #6500 from SUSE/wip-13678-infernalis
- systemd: no rbdmap systemd unit file
- 01:52 PM devops Backport #12928 (Resolved): ceph.spec.in libcephfs_jni1 has no %post and %postun
- 01:52 PM Revision f1d5570b (ceph): Merge pull request #5789 from SUSE/wip-12928-hammer
- rpm: libcephfs_jni1 has no %post and %postun
Reviewed-by: Sage Weil <sage@redhat.com> - 01:50 PM Revision c4bb3432 (ceph): Merge pull request #7434 from tchaikov/wip-14441-hammer
- man: document listwatchers cmd in "rados" manpage
Reviewed-by: Sage Weil <sage@redhat.com> - 01:50 PM Revision 6d860ba4 (ceph): cmake: musl libc does not implement backtrace. Added feature check and ...
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:50 PM Revision 11cbe45c (ceph): Merge pull request #7264 from ceph/wip-doc-RGW
- doc: rgw: port changes from downstream to upstream
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:49 PM Revision fbe91037 (ceph): Merge pull request #7244 from mikulely/fix-authtool-doc
- doc: remove redundant space in ceph-authtool/monmaptool doc
- 01:46 PM Revision 1d2948fd (ceph): Merge pull request #7027 from mathslinux/fix-s3-csharp-doc
- doc: fix S3 C# example
- 01:46 PM Revision 04289a92 (ceph): Merge pull request #7000 from zhouyuan/fix_cache_tier_doc
- doc: fix misleading configuration guide on cache tiering
Reviewed-by: Sage Weil <sage@redhat.com> - 01:45 PM Revision 428805ad (ceph): Merge pull request #6930 from wido/rgw-key-docs
- doc: use 'ceph auth get-or-create' for creating RGW keyring
Reviewed-by: Sage Weil <sage@redhat.com> - 01:44 PM Revision 152f4eb0 (ceph): doc: Updated the RPM section for RHEL and CentOS
- Fixes: #10245
Signed-off-by: Aron Gunn <ritz_303@yahoo.com> - 01:43 PM Revision 6684d3c3 (ceph): Merge pull request #7384 from wido/mirroring
- doc: script and guidelines for mirroring Ceph
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com> - 01:41 PM Feature #13142 (Resolved): osd: warning if pg has not been scrubbed for a long time
- 01:40 PM Bug #13422 (Pending Backport): pid file that was deleted after ceph restart leads to osd process ...
- 01:39 PM Bug #14561 (Resolved): BlueStore: null pointer access
- 01:05 PM Bug #14561 (Resolved): BlueStore: null pointer access
- int BlueStore::_create_collection(
TransContext *txc,
coll_t cid,
unsigned bits,
CollectionRef *c)
{
... - 01:39 PM Revision 8d560f76 (ceph): Merge pull request #7435 from xiexingguo/xxg-wip-14561
- osd: BlueStore: fix null pointer access
Reviewed-by: Sage Weil <sage@redhat.com> - 01:33 PM Revision fb856af0 (ceph): Merge pull request #7271 from somnathr/wip-transaction-delete
- osd: avoid heap allocations for ObjectStore::Transaction
http://pulpito.ceph.com/sage-2016-01-28_12:50:51-rados-wip-... - 01:31 PM Bug #14213: osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- /a/sage-2016-01-28_12:50:51-rados-wip-sage-testing3---basic-mira/48261
this is master, plus somnaht's ObjectStore:... - 01:29 PM Revision a6da3706 (ceph): Merge pull request #6440 from stiopaa1/scrubbingInfo
- mon: warn if pg(s) not scrubbed
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: David Zafman <dzafman@redhat.com> - 01:28 PM Revision 71501a3a (ceph): Merge pull request #7075 from shun-s/shun-fix
- global: do not start two daemons with a single pid-file
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:28 PM Revision 8a40b37a (ceph): Merge pull request #7111 from chenji-kael/master
- osd: FileStore: print file name before osd assert if read file failed
Reviewed-by: Sage Weil <sage@redhat.com> - 01:27 PM Revision 50821fa2 (ceph): Merge pull request #7248 from ukernel/jewel-14379
- mon/MDSMonitor: add confirmation to "ceph mds rmfailed"
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 01:27 PM Revision ec00cad0 (ceph): Merge pull request #7268 from ifed01/wip-14400
- common: snappy decompressor may assert when handling segmented input bufferlist
Reviewed-by: Haomai Wang <haomai@xsk... - 01:26 PM Bug #14405 (Resolved): ceph-mon process crash when wrong message type in ceph.conf
- 01:26 PM Revision 5deb6fd1 (ceph): Merge pull request #7276 from caibo2014/fix-messager-null
- mon/MonClient: avoid null pointer error when configured incorrectly
Reviewed-by: Sage Weil <sage@redhat.com> - 01:26 PM Revision f642140b (ceph): Merge pull request #7330 from ifed01/wip-pool-stat-cleanup
- librados: remove duplicate definitions for rados pool_stat_t and cluster_stat_t
Reviewed-by: Josh Durgin <jdurgin@re... - 01:25 PM Revision 4cf7af5b (ceph): Merge pull request #7340 from ceph/wip-portable-time
- common: ake ceph_time clocks work under BSD
Reviewed-by: Erwan Velu <erwan@redhat.com> - 01:24 PM Bug #14495 (Resolved): Crush:When set pool crush rule should consite the pool size.
- 01:24 PM Revision c5a1455d (ceph): Merge pull request #7341 from songbaisen/song7
- mon: consider the pool size when setting pool crush rule
Reviewed-by: Sage Weil <sage@redhat.com> - 01:24 PM Revision 22734956 (ceph): Merge pull request #7355 from yuanjingkai/master
- os/fs: fix io_getevents argument
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:23 PM Bug #14484 (Resolved): BlueFS: potential log data lost during compact
- 01:23 PM Revision bd9e1f21 (ceph): Merge pull request #7348 from xiexingguo/xxg-wip-14484
- osd: BlueStore: fix space leak
http://pulpito.ceph.com/sage-2016-01-27_18:39:48-rados-wip-sage-testing---basic-smith... - 01:22 PM Revision f9a8c565 (ceph): Merge pull request #7368 from somnathr/wip-jemalloc-build
- build: allow jemalloc enabled build with rocksdb-static
http://pulpito.ceph.com/sage-2016-01-27_18:39:48-rados-wip-s... - 01:07 PM Revision d3fd52aa (ceph): BlueStore: fix null pointer access
- Fixes: #14561
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:06 PM Revision 2d602dd8 (ceph): qa/workunits/objectstore/test_fuse.sh: no bashism
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:47 PM Bug #14560 (Resolved): bluestore: assertion failed when starting scrub
- This seems to happen in Jewel as well as in master (with https://github.com/ceph/ceph/pull/7223 reverted):...
- 12:34 PM Feature #13942: ceph-disk: support bluestore
- ...
- 06:31 AM Feature #13942: ceph-disk: support bluestore
- Now fails with http://paste.debian.net/377343/
ceph.conf has ... - 12:30 PM Revision a5e4f70a (ceph): man: document listwatchers cmd in "rados" manpage
- Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit c2e391301efc43f0b431e89737246b2c43bf10a9)
man... - 12:22 PM Revision 8102d230 (ceph): include/str_map.h removed unnecessary function overloading of
- get_str_map()
Signed-off-by: Sahithi R V <sahithi.rv1@gmail.com>
tests successful
Signed-off-by: Sahithi R V <sahi... - 12:16 PM Revision da614b8c (ceph): BlueStore: fix typo
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:45 AM Revision fa7470a0 (ceph): rbd_fuse:replaced pthread_mutex*() functions with ceph Mutex wrapper
- Signed-off-by: Sahithi R V <tansy.rv@gmail.com>
- 11:35 AM Revision a19aa226 (ceph): kstore: flush before we really start a clone
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:35 AM Revision fb307c20 (ceph): kstore: flush before we really start a truncate
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:35 AM Revision b0bed156 (ceph): BlueStore: add fast check against empty list
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:35 AM Revision 06ad7849 (ceph): kstore: add fast check against empty list
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 10:38 AM Revision ddca0dc8 (ceph): tools/rados: fix wrong op/object sizes in rand/seq bench
- Metadata contain correct information about last bench write run, yet
these are ignored in subsequent bench rand/seq r... - 10:26 AM Bug #14558 (Resolved): journal AIO write error message is confusing
- Error handling in FileJournal incorrectly assumes that the content of res always is the size written. If negative, it...
- 10:26 AM Revision 9cf37080 (ceph): tasks/cephfs: test sharded cephfs-data-scan
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:25 AM CephFS Backport #14067 (In Progress): infernalis : Ceph file system is not freeing space
- 10:22 AM Revision 29d30ecd (ceph): mds: properly set STATE_STRAY/STATE_ORPHAN for stray dentry/inode
- Fixes: #13777
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 460c74a0b872336a7279f0b40b17ed67... - 10:19 AM Revision 5f54671e (ceph): mon: don't require OSD W for MRemoveSnaps
- Use ability to execute "osd pool rmsnap" command
as a signal that the client should be permitted
to send MRemoveSnaps... - 10:18 AM CephFS Backport #14490 (In Progress): infernalis: fsx failed to compile
- 10:13 AM Revision 7fd56eaf (ceph): fsx: checkout old version until it compiles properly on miras
- I sent a patch to xfstests upstream at
http://article.gmane.org/gmane.comp.file-systems.fstests/1665, but
until that'... - 10:12 AM rbd Backport #14321 (In Progress): infernalis: cls_rbd: object_map_save should enable checksums
- 10:10 AM Revision 8175e163 (ceph): cls_rbd: enable object map checksums for object_map_save
- object_map_save disables CRCs when an object map footer isn't provided.
Unconditionally re-enable object map CRCs bef... - 10:09 AM rbd Backport #14465 (In Progress): infernalis: rbd-replay does not check for EOF and goes to endless ...
- 10:08 AM Revision 2c5b90a2 (ceph): rbd-replay: handle EOF gracefully
- Fixes: #14452
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
(cherry picked from commit c59b84c3e2c9bbda68219e4d22... - 10:07 AM rbd Backport #14552 (In Progress): infernalis: rbd: TaskFinisher::cancel should remove event from Saf...
- 03:50 AM rbd Backport #14552 (Resolved): infernalis: rbd: TaskFinisher::cancel should remove event from SafeTimer
- https://github.com/ceph/ceph/pull/7426
- 10:05 AM Revision f870ba9a (ceph): rbd: remove canceled tasks from timer thread
- When canceling scheduled tasks using the timer thread, TaskFinisher::cancel
does not call SafeTimer::cancel_event, so... - 10:05 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. rados...
- 08:41 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. upgrade...
- 08:39 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. powercycle...
- 08:25 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. rgw...
- 08:19 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. fs...
- 05:55 AM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 10:04 AM rgw Backport #13887 (In Progress): infernalis: orphans finish segfaults
- 09:59 AM Revision beb4b66c (ceph): Fixing NULL pointer dereference
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
(cherry picked from commit 93d3dfe0441be50a6990d458ee0ee3289af39b20) - 09:57 AM Revision 4ad08582 (ceph): kstore: simplify open_collection logic a bit
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:55 AM rgw Backport #14324 (In Progress): infernalis: rgw: radosgw-admin bucket check --fix not work
- 09:53 AM Revision 43f0305e (ceph): rgw: radosgw-admin bucket check --fix not work
- Fixed:#14215
Signed-off-by: Weijun Duan <duanweijun@h3c.com>
(cherry picked from commit a17f4e27d608ef29cf499fe76246... - 09:53 AM Revision 21b6fe6e (ceph): kstore: fix unmatched type of decode
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:52 AM rgw Backport #14327 (In Progress): infernalis: rgw: the swift key remains after removing a subuser
- 09:43 AM Backport #14494 (In Progress): infernalis: pgs stuck inconsistent after infernalis upgrade
- https://github.com/ceph/ceph/pull/7421
- 09:40 AM Revision 2480fca9 (ceph): osd/OSD: clear_temp_objects() include removal of Hammer temp objects
- Fixes: #13862
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 10b4a0825d9917b6fdd0d64506... - 09:40 AM Revision 73564ac2 (ceph): osd/PG: For performance start scrub scan at pool to skip temp objects
- Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 05d79faa512210b0f0a91640d18db33b887a6e73) - 09:40 AM Revision 9ff90acc (ceph): osd: Improve log message which isn't about a particular shard
- Remove redundant dout()
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit e85907fcc5829229... - 09:38 AM Bug #11298 (Duplicate): aio gets EPERM when update-grub runs
- I think this is a duplicate of #9570.
The fact that it happens when update-grub runs is interesting. I kind of re... - 09:31 AM Bug #11298: aio gets EPERM when update-grub runs
- > I can't see why the aio code would return EPERM. :/
The error message was bugous in firefly and fixed later on,... - 09:19 AM Bug #9570: osd crash in FileJournal::WriteFinisher::entry() aio
- New facts from http://tracker.ceph.com/issues/12100
http://tracker.ceph.com/issues/12100#note-2
> The 1 minute ... - 08:25 AM Revision b99b61e9 (ceph): ceph_osd.cc/ceph_mon.cc: cleanup unreachable exit call
- The calling chain of usage() is:
usage()
->generic_server_usage()
->exit(1)
exit(0)
so the exit(0) af... - 08:06 AM Revision 994ac294 (ceph): qa: Add test for #13829
- qa/workunits/cephtool/test.sh: add test for setting negative int options
src/test/daemon_config.cc: remove tests for ... - 08:06 AM Revision 8b777a0c (ceph): common: Allow config set with negative value
- A recent commit disabled negative values but they are required for variables
such as filestore_merge_threshold.
Fixe... - 07:10 AM Revision 7973f1bf (ceph): Merge pull request #7419 from badone/wip-enconding-error-jewel
- os/bluestore: fix bluestore_wal_transaction_t encoding test
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: L... - 07:07 AM Revision c5c04375 (ceph): Merge pull request #7275 from badone/wip-OSD-typo
- OSDService: Fix typo in osdmap comment
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:27 AM Revision b0c2bcf0 (ceph): os/bluestore: fix bluestore_wal_transaction_t encoding test
- bluestore_wal_op_t::op is encoded/dumped but it is not
initialized in its ctor. so set it to 0 in its ctor. 0 is not ... - 05:42 AM Revision c8c5d0a4 (ceph): mon:some cleanup in MonmapMonitor.h
- delete unused "get_monmap(MonMap &m)"
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 05:40 AM Revision 698e4a1c (ceph): mon:some cleanup in MonmapMonitor.cc
- remove the processing of ”mon add“ && “mon remove” in the preprocess_command;
delete unused "get_monmap(MonMap &m)"
... - 05:28 AM Revision 248bec73 (ceph): Merge pull request #7312 from jcsp/wip-14365
- mds, client: fix locking around handle_conf_change
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 05:28 AM Revision 13062af1 (ceph): Merge remote-tracking branch 'origin/greg-fs-testing-126'
- 05:28 AM Revision e3e1e3b6 (ceph): Merge remote-tracking branch 'origin/jewel'
- 05:28 AM Revision 63b4d625 (ceph): Merge pull request #7297 from ukernel/jewel-13903
- client: properly trim unlinked inode
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:26 AM Revision 5aef0189 (ceph): Merge pull request #7262 from ukernel/jewel-14380
- Be more careful about the "mds setmap" command to prevent breakage.
Reviewed-by: John Spray <john.spray@redhat.com> - 05:25 AM Bug #13940: OSDs fail to start on reboot with dmcrypt/luks
- Submitter responded in email (which bounced):
Ok thanks for the update. We are evaluating Infernalis for our next ... - 05:23 AM rbd Backport #14553 (In Progress): hammer: rbd: TaskFinisher::cancel should remove event from SafeTimer
- 03:50 AM rbd Backport #14553 (Resolved): hammer: rbd: TaskFinisher::cancel should remove event from SafeTimer
- https://github.com/ceph/ceph/pull/7417
- 05:23 AM Revision 46d626d9 (ceph): rbd: remove canceled tasks from timer thread
- When canceling scheduled tasks using the timer thread, TaskFinisher::cancel
does not call SafeTimer::cancel_event, so... - 05:21 AM rbd Backport #14466 (In Progress): hammer: rbd-replay does not check for EOF and goes to endless loop
- 05:19 AM Revision 24c0b27c (ceph): rbd-replay: handle EOF gracefully
- Fixes: #14452
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
(cherry picked from commit c59b84c3e2c9bbda68219e4d22... - 05:19 AM CephFS Bug #14557 (Duplicate): snaps: failed snaptest-multiple-capsnaps.sh
- This is on a testing branch, but it's about to get merged to master.
http://pulpito.ceph.com/gregf-2016-01-26_15:35:... - 05:15 AM CephFS Backport #12350 (In Progress): Provided logrotate setup does not handle ceph-fuse correctly
- h3. original description
(move here because Backport issues only have a link to the PR in the description)
OS: ... - 05:08 AM Bug #13966 (Resolved): memory leak in PG/replica_scrub
- 05:07 AM Bug #13966: memory leak in PG/replica_scrub
- Sam : back in hammer the code was like that:...
- 05:02 AM Backport #14554 (In Progress): hammer: Unable to bring up OSD's after dealing with FULL cluster (...
- 03:50 AM Backport #14554 (Resolved): hammer: Unable to bring up OSD's after dealing with FULL cluster (OSD...
- https://github.com/ceph/ceph/pull/7415
- 05:01 AM Revision 3d844208 (ceph): PG::activate(): handle unexpected cached_removed_snaps more gracefully
- PGPool::update(): ditto
Fixes: #14428
Backport: infernalis, hammer, firefly
Signed-off-by: Alexey Sheplyakov <ashep... - 04:58 AM Backport #14493 (In Progress): hammer: make rgw_fronends more forgiving of whitespace
- 04:58 AM Revision ad4df3be (ceph): rgw: warn on suspicious civetweb frontend parameters
- Warns about incorrect spacing near 'port' (e.g., 'port = 80').
Fixes issue #12038.
Signed-off-by: Matt Benjamin <mb... - 04:55 AM Backport #14491: hammer: ceph-disk: duplicate osd mount points
- the backport cannot be a cherry pick from any of the commits at https://github.com/ceph/ceph/pull/5999/commits. I ass...
- 04:35 AM Backport #14470 (In Progress): hammer: tool for artificially inflate the leveldb of the mon store...
- 04:34 AM Revision fba65832 (ceph): tools:remove the local file when get map failed.
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
(cherry picked from commit 0b03b32d8ba76fe9f6f1158e68eb440e3670393a) - 04:34 AM Revision bd948475 (ceph): tools:print the map infomation in human readable format.
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
(cherry picked from commit 5ed8cdc19150382c946a373ec940d76f98e6ecb7) - 04:34 AM Revision a1d5728c (ceph): tools:support printing the crushmap in readable fashion.
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
(cherry picked from commit b7faf678ed0241abc7eb86b9baaa6db669a22d53) - 04:34 AM Revision 92601718 (ceph): tools: ceph_monstore_tool: add inflate-pgmap command
- this command repeatly add the latest pgmap to the monstore in order
to inflate it. the command helps with the testing... - 04:34 AM Revision 70f1ba33 (ceph): tools: monstore: add 'show-versions' command.
- Using this tool, the first/last committed version of maps will be shown.
Signed-off-by: Cilang Zhao <zhao.cilang@h3c... - 04:34 AM Revision 90aaed74 (ceph): tools: ceph-monstore-tool must do out_store.close()
- this change fixes the "store-copy" command.
Like the bug reported in http://tracker.ceph.com/issues/10093.
Signed-of... - 04:34 AM Revision 9035c694 (ceph): tools/ceph-monstore-tools: add rewrite command
- "rewrite" command will
- add a new osdmap version to update current osdmap held by OSDMonitor
- add a new paxos ver... - 04:34 AM Revision 1bb899a2 (ceph): tools: ceph_monstore_tool: describe behavior of rewrite command
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
(cherry picked from commit a881f9385feb0f5a61fa22357984d6f291c08177) - 04:21 AM Backport #14467 (In Progress): hammer: disable filestore_xfs_extsize by default
- 04:21 AM Revision c7252a3d (ceph): osd: disable filestore_xfs_extsize by default
- This option involves a tradeoff: When disabled, fragmentation is worse,
but large sequential writes are faster. When ... - 04:13 AM Bug #13965: jewel: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to == head)
- @sam which commit / pull request fixes this issue ?
- 04:13 AM Bug #14248: OpTracker needs to release the message throttle in _unregistered
- @sam which commit / pull request fixes this issue ?
- 04:11 AM Bug #13805: segfault in Objecter::handle_watch_notify
- @sage Do we have a commit hash for this one ?
- 04:03 AM Backport #13335 (In Progress): hammer: OSD crashed when reached pool's max_bytes quota
- 03:56 AM Bug #13843 (Resolved): ceph osd pool stats broken in hammer
- 03:55 AM Feature #10973 (Resolved): randomize scrub times
- 03:54 AM Backport #13653: crush: crash if we see CRUSH_ITEM_NONE in early rule step
- was for http://tracker.ceph.com/issues/13477
- 03:54 AM Backport #13591: mon: should not set isvalid = true when cephx_verify_authorizer return false
- http://tracker.ceph.com/issues/13525
- 03:53 AM Backport #13673: tests: testprofile must be removed before it is re-created
- was for http://tracker.ceph.com/issues/13664
- 03:36 AM Revision 96563c15 (ceph): librbd: use task finisher per CephContext
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 03:36 AM Revision 86ba6caf (ceph): Merge pull request #7316 from ceph/wip-deb-lttng-hammer
- deb: strip tracepoint libraries from Wheezy/Precise builds
All other "modern" Debian-based OSes have a functional LT... - 03:25 AM Revision 70e8f442 (ceph): Merge pull request #7369 from mauri/fix-message-typo
- rbd: fix error message typo
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:21 AM Revision b6b8ee41 (ceph): Merge pull request #7187 from dachary/wip-13831-hammer
- hammer: init script reload doesn't work on EL7
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:17 AM Bug #14536 (Fix Under Review): tools/rados/rados.cc: race condition in complete callback
- https://github.com/ceph/ceph/pull/7392
- 02:55 AM Revision 0a3822f1 (ceph): librados_test_stub: watch/notify now behaves similar to librados
- Notifications are executed via the same librados AIO callback
thread, so it's now possible to catch deadlock.
Signed... - 02:26 AM Revision 87b7e53e (ceph): FuseStore: fix unhandled error cases for open
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:26 AM Revision 6eb4aa4c (ceph): FuseStore: return error if encounter collection_list error
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:26 AM Revision 6f2de314 (ceph): FuseStore: fix mountpoint leak
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:26 AM Revision 97639f66 (ceph): FuseStore: fix memory leak
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:00 AM Revision a30bc39a (ceph): Merge pull request #7387 from theanalyst/fix/gitignore
- remove unused src/messages/#MOSDOp.h# file
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:50 AM rbd Bug #14522 (Duplicate): RBD Snapshot locks Libvirt Disk With Active Writes
- Excellent -- thanks for all your help with debugging. Closing this ticket as dup of issue #13755.
- 12:13 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Hello Jason/Josh,
I can confirm both of those changes will fix the issue. Thanks for your assistance! - 01:43 AM rbd Tasks #14551 (Resolved): Update RBD default features
- For Jewel, recommend updating default features to include exclusive lock, object map, fast-diff, and deep-flatten fea...
- 01:41 AM rbd Tasks #14550 (Resolved): Deprecate format v1 RBD images
- For Jewel, recommend that we warn on the creation and opening of v1 RBD images.
- 01:04 AM Revision 5e564ea9 (ceph): tests: simulate writeback flush during snap create
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:59 AM Revision 114d720a (ceph): Revert "basic/msgr: remove async and random for now"
- This reverts commit 0324772e23375b35c261a322fb82b2ff5a6b5db8.
- 12:18 AM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- I'm not sure how to update the fields on top but they can now be changed to:
Title: ENOTSUPP on trimtrunc (EC with... - 12:01 AM Revision d5ae7f86 (ceph): rgw: don't use s->bucket for metadata api path entry
- Fixes #14549
s->bucket is only initialized at the object store handler (post auth
callback). We don't want to initia...
01/28/2016
- 11:56 PM rgw Bug #14549 (Resolved): rgw: metadata api (rest) broken
- s->bucket does not hold the path entry off /admin/<path> following a few multi-tenancy fixes.
- 11:02 PM rbd Backport #14543 (Fix Under Review): hammer: Cannot reliably create snapshot after freezing QEMU IO
- 07:44 PM rbd Backport #14543 (In Progress): hammer: Cannot reliably create snapshot after freezing QEMU IO
- 07:43 PM rbd Backport #14543 (Resolved): hammer: Cannot reliably create snapshot after freezing QEMU IO
- https://github.com/ceph/ceph/pull/7407
- 11:00 PM Revision 73e03def (ceph): librbd: ImageWatcher shouldn't block the notification thread
- Blocking the notification thread will also result in librados async
callbacks becoming blocked (since they use the sa... - 10:46 PM Bug #14547 (Resolved): "[ FAILED ] LibRadosTwoPoolsECPP.Flush" in upgrade:infernalis-x-jewel-di...
- Run: http://pulpito.ceph.com/teuthology-2016-01-28_02:10:02-upgrade:infernalis-x-jewel-distro-basic-vps/
Logs: htt... - 10:10 PM Revision 5617166f (ceph): librados_test_stub: watch/notify now behaves similar to librados
- Notifications are executed via the same librados AIO callback
thread, so it's now possible to catch deadlock.
Signed... - 10:08 PM Revision 8fc82b23 (ceph): tests: simulate writeback flush during snap create
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit e9570fcf4be9cd5c06937769d074fa52ffb32e4b) - 10:07 PM rbd Backport #14542 (Fix Under Review): infernalis: Cannot reliably create snapshot after freezing QE...
- 07:43 PM rbd Backport #14542 (In Progress): infernalis: Cannot reliably create snapshot after freezing QEMU IO
- 07:43 PM rbd Backport #14542 (Resolved): infernalis: Cannot reliably create snapshot after freezing QEMU IO
- https://github.com/ceph/ceph/pull/7406
- 09:47 PM Bug #14544 (Closed): the pool usage data reported in ceph df is misleading
- ceph version: firefly
The command "ceph df" shows the data usage and i see that rbd pool reported used size is 2.... - 09:46 PM Revision 20614969 (ceph): test/common/test_prioritized_queue.cc: Fix random shuffle and remove un...
- Signed-Off-By: Robert LeBlanc <robert.leblanc@endurance.com>
- 09:46 PM Revision 3ba54cc4 (ceph): test/commom/test_weighted_priority_queue.cc: Add unit tests for the new...
- Signed-Off-By: Robert LeBlanc <robert.leblanc@endurance.com>
- 09:46 PM Revision 795fd8f2 (ceph): osd: Add runtime config option to select which queue to use and the
- priority of the cutoff between the strict queue and the normal queue.
osd_op_queue takes prio, wpq, or debug_random ... - 07:42 PM rbd Bug #14373 (Pending Backport): Cannot reliably create snapshot after freezing QEMU IO
- 02:31 AM rbd Bug #14373 (In Progress): Cannot reliably create snapshot after freezing QEMU IO
- Sorry for the delay, I somehow missed the email notification for this ticket. The logs are perfect and I can see the...
- 05:05 PM Revision 60d0df5c (ceph): Merge pull request #7345 from x11562/rbd_snap_rename
- rbd: add "--dest-snap" optional for snap rename
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Jason Dil... - 04:43 PM Revision 2d75c9d8 (ceph): Merge pull request #7393 from tchaikov/wip-cmake
- fix the autotools and cmake build (the new fusestore needs libfuse)
Reviewed-by: Piotr Dałek <piotr.dalek@ts.fujitsu... - 04:30 PM Revision 9f27053f (ceph): Merge pull request #7403 from rzarzynski/wip-rgw-dumpconlen-cosmetics
- rgw: cosmetic improvements in dump_content_length()
- 04:19 PM Revision 57db464e (ceph): rgw: cosmetic improvements in dump_content_length().
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 04:11 PM rbd Feature #14540 (Resolved): rbd disk-usage CLI command should support calculating full image usage
- Right now you would either need to dump the full pool or re-run "rbd disk-usage" for each snapshot within an image to...
- 04:10 PM rbd Documentation #14539 (Resolved): rbd CLI man page is missing several commands
- Ensure it is up-to-date with the latest commands in the CLI.
- 04:00 PM Revision 5b8c0444 (ceph): rados: make rados bench metadata backward compatible
- We recently made a distinction between op size and object size, and broke
our ability to read metadata from old runs.... - 03:50 PM Revision b65d9c54 (ceph): systemd: Add systemd sandboxing to services.
- This change makes it so the mon/osd/mds/radosgw daemons:
o Cannot write to /usr, /etc, and /boot.
o Cannot ac... - 03:36 PM Revision 63d3d2be (ceph): cmake: link against libfuse if HAVE_LIBFUSE
- * use ${FUSE_LIBRARIES} instead of "fuse" when referencing libfuse.
* do not compile FuseStore.cc if !HAVE_LIBFUSE.
*... - 03:36 PM Revision 563206cc (ceph): make: disable FuseStore if !WITH_FUSE
- * configure.ac: "#define HAVE_LIBFUSE" if libfuse is found
* os/Makefile.am: do not compile FuseStore.cc if libfuse i... - 03:36 PM Revision b2e5c558 (ceph): osd: disable FuseStore if !HAVE_LIBFUSE
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:36 PM Revision 157bf3eb (ceph): ceph-objectstore-tool: disable fuse support if !HAVE_LIBFUSE
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 02:11 PM Bug #14537 (Fix Under Review): should compact full epochs in monitor
- https://github.com/ceph/ceph/pull/7396
- 10:10 AM Bug #14537 (Resolved): should compact full epochs in monitor
- it is reported that there is inconsistency between mon store leveldbs in the same cluster.
4.0G /var/lib/ceph/mon
... - 02:08 PM Bug #14501 (Fix Under Review): "rados" command does not honor the "-f" short argument for generat...
- Things are a bit more complicated, here, as `-f` seemed to be already in use for setting the option as foreground in ...
- 02:06 PM Bug #12744 (Fix Under Review): ceph -s output shows "N pgs backfill", should be "waiting for back...
- Master PR: https://github.com/ceph/ceph/pull/7398
- 12:50 PM Revision fd8ab0bd (ceph): cmake: remove the copyright of FindSnappy.cmake
- as we've basically removed all the HyperTable code.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 12:19 PM rbd Bug #13674 (Resolved): Avoid re-writing old-format image header on resize
- 12:19 PM rbd Bug #13636 (Resolved): rbd: pure virtual method called
- 12:19 PM Bug #13462 (Resolved): object_info_t::decode() has wrong version
- 12:19 PM Bug #13192 (Resolved): stuck recovering, unfound hit set due to removing it while !active
- 12:19 PM rbd Bug #13164 (Resolved): librbd: reads larger than cache size hang
- 12:19 PM rbd Bug #12415 (Resolved): init-rbdmap uses distro-specific functions
- 12:19 PM Bug #12162 (Resolved): pg_interval_t::check_new_interval - for ec pool, should not rely on min_si...
- 12:19 PM devops Bug #11638 (Resolved): ceph.spec.in: ceph-common subpackage def needs tweaking for SUSE/openSUSE
- 12:19 PM Bug #10691 (Resolved): ceph-dencoder links to libtcmalloc, and shouldn't
- 12:17 PM Backport #14322 (Rejected): firefly: OpTracker needs to release the message throttle in _unregist...
- 12:17 PM rbd Backport #13752 (Rejected): Avoid re-writing old-format image header on resize
- 12:17 PM rbd Backport #13757 (Rejected): rbd: pure virtual method called
- 12:17 PM rbd Backport #13694 (Rejected): init-rbdmap uses distro-specific functions
- 12:17 PM Backport #13653 (Rejected): crush: crash if we see CRUSH_ITEM_NONE in early rule step
- 12:17 PM Backport #13673 (Rejected): tests: testprofile must be removed before it is re-created
- 12:17 PM Backport #13591 (Rejected): mon: should not set isvalid = true when cephx_verify_authorizer retur...
- 12:17 PM Backport #13487 (Rejected): object_info_t::decode() has wrong version
- 12:17 PM Backport #13287 (Rejected): stuck recovering, unfound hit set due to removing it while !active
- 12:17 PM rbd Backport #13388 (Rejected): librbd: reads larger than cache size hang
- 12:17 PM Backport #12965 (Rejected): Not logging missing_on_shards properly
- 12:17 PM Backport #12488 (Rejected): pg_interval_t::check_new_interval - for ec pool, should not rely on m...
- 12:17 PM Backport #12461 (Rejected): ceph-dencoder links to libtcmalloc, and shouldn't
- 12:17 PM devops Backport #12307 (Rejected): ceph.spec.in: ceph-common subpackage def needs tweaking for SUSE/open...
- 12:15 PM Bug #13940: OSDs fail to start on reboot with dmcrypt/luks
- This is most probably a timeout because individual udev actions take too long and abort or fail (I don't know exactly...
- 12:11 PM Bug #13940: OSDs fail to start on reboot with dmcrypt/luks
- 10:53 AM Revision 93d633a2 (ceph): mon: compact full epochs also
- by compacting the ${prefix}.${start}..${prefix}..${end} does not
necessary compact the range of ${prefix}."full_"${st... - 09:08 AM Revision 1e4dfae0 (ceph): Script and Guidelines for mirroring Ceph
- This commit introduces a script which admins can use to mirror
the Ceph packages to their local systems.
With this s... - 08:04 AM Bug #13213 (Resolved): stuck recovering apparently due to pg_query not sent by async messenger?
- 08:02 AM Feature #7518 (Closed): Add inline attrs support to KeyValueStore
- 08:02 AM Feature #7063 (Closed): Replace lfn_find call in omap* functions with more lighter implematation
- 08:01 AM Bug #11607 (Resolved): IPv6 in ceph_test_async_driver
- https://github.com/ceph/ceph/commit/dae7abd22d367cc597fe601f13883e49b0931f55
- 07:35 AM Revision 5d91e6d3 (ceph): Merge pull request #6875 from dx9/wip-cmake-ccache
- cmake: support ccache via a WITH_CCACHE build option
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Kef... - 06:42 AM Feature #13942: ceph-disk: support bluestore
- ceph.conf has ...
- 06:37 AM Bug #14536 (Resolved): tools/rados/rados.cc: race condition in complete callback
- race condition in rados load-gen complete callback function 'LoadGen::io_cb', the 'total_completed' should also below...
- 04:38 AM Bug #13829 (In Progress): config set with negative value results in "error setting 'filestore_mer...
- https://github.com/ceph/ceph/pull/7390
- 03:53 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- For OpenStack, to enable rbd caching you'll need to put this in the [libvirt] section of /etc/nova/nova.conf on each ...
- 02:06 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- I might have (semi-)good news for you: I believe this is the same issue as tracked under #13755. The fix is already ...
- 12:24 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- cache='none' is disabling the cache.
- 12:19 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Hello,
RBD Cache is enabled in ceph.conf (rbd_cache = true, rbd_cache_size = 67108864) for the client on all hyper... - 12:11 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Is this only occurring on VMs where the RBD cache is disabled?
- 12:05 AM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Perfect, thanks!
- 03:05 AM rbd Bug #14535 (Resolved): rbd CLI does not validate pool and snapshot name optionals
- The "--pool", "--snap", etc optionals are not validated to ensure they don't contain "/" nor "@".
- 02:50 AM CephFS Bug #13926 (Need More Info): lockup in multithreaded application
- did not find anything in the log
- 02:11 AM rbd Bug #14510 (Resolved): TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED assert(m...
- 02:10 AM rbd Bug #14434 (Resolved): intermittent errors in make check tests from journaling code
- 01:30 AM Bug #14524 (Closed): BlueStore: overlay leak
- 12:55 AM Revision 38e2f7a8 (ceph): rbd: simplify snap rename arguments
- Signed-off-by: Na Xie <xie.na@h3c.com>
- 12:37 AM rgw Bug #14534 (Resolved): rgw: cannot limit users to not create buckets
01/27/2016
- 11:51 PM Bug #14533: os/FileStore.cc: 2761: FAILED assert(0 == "unexpected error") upgrade:hammer-x-wip-di...
- Assigned to Sage. I think this is going to need a backport of _kludge_temp_object_collection() code, but I don't thi...
- 10:41 PM Bug #14533 (Can't reproduce): os/FileStore.cc: 2761: FAILED assert(0 == "unexpected error") upgra...
teuthology.ovh.sepia.ceph.com:/a/teuthology-2016-01-27_16:15:46-upgrade:hammer-x-wip-diag-14438-distro-basic-openst...- 11:46 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Tyler Wilson wrote:
> Hello Jason,
>
> I got the instance to lock once more and ran gdb attach $pid, then "thread... - 11:37 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Hello Jason,
I got the instance to lock once more and ran gdb attach $pid, then "thread apply all bt". Attached is... - 11:17 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Another option would be if you could install the ceph-debuginfo package, attach gdb to the hung qemu process, run "th...
- 11:03 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Correct;...
- 10:46 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Odd, no file named /var/log/qemu/qemu-guest-290624.log was created (based on the PID of your admin socket)? Can you ...
- 09:28 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Updated ceph.conf to that document;...
- 08:32 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Try updating your ceph.conf as described here: http://docs.ceph.com/docs/master/rbd/rbd-openstack/#configuring-nova
- 08:17 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- SELinux is enabled however no denies are in the audit log. I disabled SELinux and retried; same result.
- 08:04 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Hmm -- do you have SElinux enabled? You might be experiencing an SElinux denial preventing qemu from writing to /var/...
- 07:21 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Hello Jason,
Can't seem to get the logs that you are looking for, where can I retrieve that? Here is my current ce... - 07:04 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Thanks -- I was actually hoping to get the librbd logs from the qemu process itself before it locks up due to the sna...
- 06:34 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Hello Jason,
Thanks for taking assignment of this. Here is the output from creating a snapshot with debug enabled;... - 05:35 PM rbd Bug #14522: RBD Snapshot locks Libvirt Disk With Active Writes
- Tyler, would it be possible for you to attach the librbd log from qemu with "debug rbd = 20" from shortly before crea...
- 05:27 PM rbd Bug #14522 (In Progress): RBD Snapshot locks Libvirt Disk With Active Writes
- 12:25 AM rbd Bug #14522 (Duplicate): RBD Snapshot locks Libvirt Disk With Active Writes
- On the latest EL7 release of Libvirt (with RDO OpenStack Kilo) I am getting my RBD disks locked when I issue a simple...
- 10:54 PM Revision 18fe93c6 (ceph): osd: Pass coll_t by reference
- Signed-off-by: Evgeniy Firsov <evgeniy.firsov@sandisk.com>
Conflicts:
src/os/ObjectStore.h
src/os/bluestore/BlueSt... - 10:47 PM Revision 1e08b21f (ceph): Merge pull request #7337 from clever215/rbd_nbd
- rbd-nbd: Add an argument validation for nbds_max
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Jason Di... - 10:45 PM Revision 22e0c8f5 (ceph): Merge pull request #7385 from trociny/fix-journal-flush-commit-position
- journal: flush commit position on metadata shutdown
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Jason... - 10:44 PM Revision f721fbb2 (ceph): Merge pull request #7382 from dillaman/wip-14510
- librbd: block maintenance ops until after journal is ready
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:43 PM Revision 5e4eb3fc (ceph): OSD: Deleting transaction object right after applying transaction
- Presently, the transaction object is been deleted by the Finisher
thread asynchronously. In heavy load scenario speci... - 10:41 PM Revision bef4ef9a (ceph): Added point-to-point suite
- Added parallel suite
Added stree-split suite
Added stress-split-erasure-code suite
Added stress-split-erasure-code-x9... - 10:40 PM Revision b07a2edd (ceph): Added point-to-point suite
- Added parallel suite
Added stree-split suite
Added stress-split-erasure-code suite
Added stress-split-erasure-code-x9... - 10:35 PM Revision 22cecc43 (ceph): Merge pull request #7259 from trociny/wip-14264
- librbd: API: async open and close
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:34 PM Revision 8bb6c8c8 (ceph): Merge pull request #7302 from dillaman/wip-14434
- librbd: journal shut down flush race condition
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:34 PM Revision c7e5848a (ceph): Merge pull request #7299 from dillaman/wip-librbd-update-features
- librbd: fix internal handling of dynamic feature updates
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:23 PM Revision 464a0ada (ceph): gitignore: ignore backup files from editors etc.
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 10:16 PM Revision e9420511 (ceph): remove unused source file
- This file was possibly accidentally committed in the tree, thanks
@BranchPredictor for bringing this up in irc
Signe... - 08:36 PM Revision 7e0a7a3d (ceph): Merge pull request #7381 from ceph/wip-rgw-static-website-yehuda
- RGW static website feature
- currently disabled by default
- partial error page handling
- a few known failures
R... - 07:54 PM Revision bd2fdf8c (ceph): OSD::consume_map: correctly remove pg shards which are no longer acting
- A particular shard may be non-active even if the osd is in the acting
set.
Fixes: 14278
Backport: hammer
Signed-off-... - 07:50 PM Revision 75c5b0f2 (ceph): Merge pull request #797 from ceph/wip-fusestore
- rados/objecststore/fusestore.yaml: run ceph-objectstore-tool fuse test
- 07:45 PM Revision ab4b3732 (ceph): journal: flush commit position on metadata shutdown
- A crash was observed on JournalTrimmer destroy, which was called
by the Journaler after metadata shutdown. JournalTri... - 07:45 PM Revision 2e52a8b1 (ceph): Merge pull request #7223 from liewegas/wip-collection-handles
- osd: collection handles
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 07:39 PM Revision 96a7c663 (ceph): Merge pull request #7134 from liewegas/wip-fusestore
- osd: implement fuse interface for ObjectStore
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:34 PM rbd Subtask #14530 (Resolved): Journal close should be non-blocking
- The RBD replay daemon will potentially have to close thousands of journals on shutdown. To be more efficient, this p...
- 07:34 PM Revision 34fe2e8a (ceph): os/memstore: implement open_collection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:34 PM Revision 8e172a98 (ceph): os/memstore: implement handle-based read methods
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:34 PM Revision f3de2b87 (ceph): osd: associate a CollectionHandle with each PG
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:34 PM Revision 6560b14d (ceph): osd: associate a CollectionHandle& with PGBackend
- Make this a ref to the PG's handle because the backend is
constructed before the handle is opened.
Signed-off-by: Sa... - 07:34 PM Revision 17901f78 (ceph): osd: use collection handle where possible
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:34 PM Revision b6df3e1c (ceph): os/ObjectStore: add CollectionHandle
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:34 PM Revision 414d09bd (ceph): os/ObjectStore: add CollectionHandle wrappers for all read ops
- The backend can optionally implement the handle-based variant. If
it does not, the wrappers will call the legacy coll... - 07:34 PM Revision e81e3c08 (ceph): os/bluestore: implement open_collection
- Fix up create and remove so that they poison a Collection that
gets removed.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:34 PM Revision 765eb9f7 (ceph): os/bluestore: implement CollectionHandle based read methods
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:22 PM Revision 7d3579d3 (ceph): Revert "kstore: fix dest onode process logic of clone_range"
- This reverts commit 9ab7998fbe19d076c653ca78d328a2794ef29535.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:22 PM Revision dc3faedb (ceph): Revert "kstore: fix dest onode process logic of clone"
- This reverts commit 7ce6d068a1fd666940068df702f29bdd5ee8faf0.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:22 PM Revision 493afb46 (ceph): Revert "kstore: fix nid overwritten of write/zero"
- This reverts commit 8065b8ab34f06d8d5d8e7fbdc1d8a846d88b30df.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:22 PM Revision d7e21cb2 (ceph): Revert "BlueStore: fix nid overwritten of write/zero"
- This reverts commit fde0f0297aaf2f2717ec1b5a4c55295452817d0c.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:20 PM Revision fbd5cd4a (ceph): Revert "BlueStore: fix dest onode process logic of clone"
- This reverts commit 1c70f86316e5ff29ef7168ebfb3513def770b436.
The truncate is cheap if the object is empty, and we n... - 07:20 PM Revision d1d88ba0 (ceph): Revert "BlueStore: fix dest onode process logic of clone_range"
- This reverts commit 696584cf6523d997cac2bf43d3234fd8518ef40b.
_assign_nid is safe to call again, and we want to avoi... - 07:17 PM rbd Bug #14510 (Fix Under Review): TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED ...
- *master PR*: https://github.com/ceph/ceph/pull/7382
- 05:58 PM rbd Bug #14510 (In Progress): TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED asser...
- 05:58 PM rbd Bug #14510: TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED assert(m_state == S...
- Whoops -- I was thinking this was a different issue I just fixed with Journal::handle_op_event_safe.
- 07:14 PM Revision 2c353a85 (ceph): librbd: block maintenance until after journal is ready
- Ops were already blocked when the requests were received via
watch/notify. Requests are now blocked for local reques... - 07:10 PM Revision bd694d4a (ceph): os/bluestore/BlueFS: use std::atomic
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:10 PM Revision 4db22fdd (ceph): os/bluestore/BlueStore: use std::atomic
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:07 PM Revision bf9d1a06 (ceph): Merge branch 'wip-rgw-static-website-yehuda'
- Conflicts:
src/rgw/rgw_common.h
src/rgw/rgw_op.h
src/rgw/rgw_rest_s3.cc
src/rgw/rgw_rest_s3.h - 07:06 PM Revision 0613765a (ceph): os/FuseStore: improve readdir for omap and attr
- Use new-style fuse readdir interface for omap and attr. We aren't
particularly efficient, but we won't completely br... - 07:06 PM Revision ca4f077e (ceph): os/FuseStore: no-op chmod
- This makes mkdir(1) happy.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision b2a1c861 (ceph): os/FuseStore: do not call exists() on an out-of-bounds oid
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 614f1653 (ceph): ceph-objectstore-tool: 'whoami' is not required for an ObjectStore
- OSD creates it, but it won't be there if we did --op mkfs
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision 0ed0ec52 (ceph): ceph-objectstore-tool: simplify error message
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision c4f5a086 (ceph): ceph-objectstore-tool: add --op mkfs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision e1a371db (ceph): ceph-objectstore-tool: drop filestore-specific sanity check
- Just let mount() fail
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision 0638b118 (ceph): os/ObjectStore: add get_type()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 3e360655 (ceph): os/FuseStore: add 'type' file in root dir
- This also acts as a sentinel to indicate whether we have mounted.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision c3954e69 (ceph): qa/workunits/objectstore/test_fuse.sh: simple workunit test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision f84384ac (ceph): os/FuseStore: use offset for readdir
- This allows us to list large directories.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision a47f8ffb (ceph): os/FuseStore: wait for commit and flush in all updates
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision aa8f2c9f (ceph): ceph-objectstore-tool: no need to check for fsck here
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision f8de0177 (ceph): os/FuseStore: respect fuse_debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 17d3c9f4 (ceph): os/ObjectStore: add collection_bits
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 27dc220a (ceph): os/bluestore: implement collection_bits
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 27bae894 (ceph): os/FuseStore: present bitwise_hash_end
- Note this is the *last* hash value, inclusive.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision 2aa65322 (ceph): os/FuseStore: hide bitwise_hash_end if bits unknown; add bitwise_hash_bits
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 57289de4 (ceph): os/FuseStore: more ENOENT on getattr for non-existent items
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision 53a33362 (ceph): os/FuseStore: allow object and collection creates
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:06 PM Revision efa88a45 (ceph): [g]hobject_t: normalize operator<< result, and implement parse
- - print hash in *bitwise reverse* order
- include all fields, every time
- use : delimitor for hobject_t
- use @ deli... - 07:06 PM Revision f5d106ff (ceph): vstart.sh: put the OSD journal in the normal location
- Also, drop the ability to run without a journal.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision 96643e9c (ceph): ceph-objectstore-tool: mount an ObjectStore via fuse
- Currently only read-only.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:06 PM Revision d01967d3 (ceph): osd: osd_objectstore_fuse
- Expose underlying ObjectStore via fuse at $osd_data/fuse/. Can be enabled/
disabled at runtime.
Signed-off-by: Sage... - 07:06 PM Revision 0e371d2b (ceph): ceph-objectstore-tool: use myexit(1) for fsck
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:55 PM Revision b62318ea (ceph): os/bluestore/BlueFS: use std::mutex et al
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:55 PM Revision df53b167 (ceph): os/bluestore/BlueStore: use std::mutex et al
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:55 PM Revision e9721b8c (ceph): os/bluestore: fix FS creation by fs
- Reported-by: Allen Samuels <allen.samuels@sandisk.com>
Signed-off-by: Sage Weil <sage@redhat.com> - 06:55 PM Revision 8e5fbea4 (ceph): os/bluestore/StupidAllocator: use std::mutex
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:22 PM Revision f9dbf106 (ceph): Merge pull request #7195 from liewegas/wip-rados-bench
- rados: rados bench improvements
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:21 PM Revision 9c30be93 (ceph): Merge pull request #7269 from liewegas/wip-bluestore-btree
- bluestore: use btree_map for allocator
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Reviewed-by: Casey Bodley <... - 06:18 PM Revision d6c35c07 (ceph): Merge pull request #6 from ifed01/wip-bluestore-btree-test
- UT for interval_set implementations
- 06:14 PM Bug #14026 (Resolved): OSD utilization is abnormal after data disk lost
- 06:14 PM Revision 4ba18473 (ceph): Merge pull request #6869 from chuanhong-wang/chuanhong-wang-wip-14026
- osd: fix OSD utilization is abnormal after data disk lost
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:13 PM Revision a1c5385e (ceph): Merge pull request #7201 from ErwanAliasr1/evelu-cleanup-deadstuff
- cleanup: remove misc dead code
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:13 PM Cleanup #14356 (Resolved): cleanup filestore xattr use omap
- 06:13 PM Revision 391199d7 (ceph): Merge pull request #7217 from vumrao/wip-14356-vumrao
- osd: FileStore: cleanup: remove obsolete option "filestore_xattr_use_omap"
Reviewed-by: Loic Dachary <ldachary@redha... - 06:12 PM Revision 40907057 (ceph): Merge pull request #7245 from Sandy4999/wip-mon-election
- mon: add an independent option for max election time
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 06:10 PM Revision e19dd6a1 (ceph): Merge pull request #7253 from wido/mon-err-stuck-pg
- mon: go into ERR state if multiple PGs are stuck inactive
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Abhi... - 06:09 PM Revision 0a65d908 (ceph): Merge pull request #7281 from xuechendi/omap_sync_assert
- osd: FileStore: add error check for object_map->sync()
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:09 PM Bug #14428 (Pending Backport): Unable to bring up OSD's after dealing with FULL cluster (OSD asse...
- 06:08 PM Revision b4b01149 (ceph): Merge pull request #7309 from asheplyakov/bug-14428
- osd: PG::activate(): handle unexpected cached_removed_snaps more gracefully
Reviewed-by: Sage Weil <sage@redhat.com> - 06:07 PM Revision 3bc05b3a (ceph): Merge pull request #7319 from chenji-kael/wip-cls-clear-pool
- test/cls: clean useless pools
Reviewed-by: Sage Weil <sage@redhat.com> - 06:07 PM Revision 27784ff3 (ceph): Merge pull request #7320 from yuyuyu101/kill-keyvaluestore
- os/keyvaluestore: kill KeyValueStore
Reviewed-by: Sage Weil <sage@redhat.com> - 05:06 PM Revision 20c80b92 (ceph): tools/rbd: fix error message typo
- Signed-off-by: Mauricio Garavaglia <mauriciogaravaglia@gmail.com>
- 05:01 PM Bug #14525 (Rejected): why SSD cache pool can't improve RBD performance?
- A bug isn't really a good forum for this. I suggest you take this data and post to ceph-devel, people will be very in...
- 10:39 AM Bug #14525 (Rejected): why SSD cache pool can't improve RBD performance?
- software: centos7+ceph-0.94.5+openstack firefly
In my ceph cluster, pool "volumes" is used by openstack cinder. In o... - 04:59 PM Bug #14523 (Can't reproduce): osd slowrequest after tcp connection fault
- It sounds like you had a network hiccup that lasted 900s between those osds. I think the mon_osd_report_timeout part...
- 03:11 PM Bug #14523: osd slowrequest after tcp connection fault
- after
172.18.129.60:6801/14172 >> 172.18.129.121:6801/49670 pipe(0x7fee07d6f000 sd=158 :6801 s=0 pgs=0 cs=0 l=0 c=... - 06:14 AM Bug #14523: osd slowrequest after tcp connection fault
- the detail log is above
- 06:14 AM Bug #14523: osd slowrequest after tcp connection fault
172.18.129.108 Log (osd 35) :
2016-01-27 13:26:00.172881 7f064aacf700 0 -- 172.18.129.108:6804/141884 >> 172.18.1...- 06:07 AM Bug #14523 (Can't reproduce): osd slowrequest after tcp connection fault
- when we find the following log appears, osd will have slow request after 30 seconds
2016-01-27 13:33:12.321607 7fe... - 04:50 PM Revision 29990b38 (ceph): Merge pull request #7375 from rzarzynski/wip-14526
- rgw: fix dangeours usage of strtok in RGWAccessControlPolicy_SWIFT
- 04:25 PM Revision 130e8c6d (ceph): Add UT for interval_set implementations
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 04:02 PM RADOS Feature #14527 (Resolved): Lookup monitors through DNS
- Right now monitors have to be hardcoded into a configuration file which sometimes can be a problem.
Imagine a situ... - 03:54 PM Feature #4232 (Resolved): librados: Improve Java bindings
- 03:53 PM Bug #6380 (Resolved): Monitor tries to bind on IPv6 address while not available yet after boot
- 03:49 PM Revision c0132d16 (ceph): Merge pull request #7379 from branch-predictor/bp-async-fixes-0127
- msg/async: bunch of fixes
Reviewed-by: Haomai Wang <haomai@xsky.com> - 03:45 PM Revision 8a6f1f7f (ceph): qa/workunits/fs/misc: Add a workunit for tar kernel Documents
- the test fails if some files were changed while being archived
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 02:33 PM rgw Bug #14526 (Fix Under Review): rgw: parsing Swift ACLs may be dangerous in multi-thread environment
- Pull request: https://github.com/ceph/ceph/pull/7375.
- 01:46 PM rgw Bug #14526 (In Progress): rgw: parsing Swift ACLs may be dangerous in multi-thread environment
- 01:41 PM rgw Bug #14526 (Resolved): rgw: parsing Swift ACLs may be dangerous in multi-thread environment
- _RGWAccessControlPolicy_SWIFT::create_ method calls _parse_list_ function. It "uses":https://github.com/ceph/ceph/blo...
- 02:23 PM rbd Bug #14476 (Pending Backport): rbd: TaskFinisher::cancel should remove event from SafeTimer
- 02:17 PM Revision 5e2fc70e (ceph): msg/async: bunch of fixes
- 1. Use MSG_MORE in sendmsg to reduce number of actual sends and pass hint
to do_sendmsg in callers.
2. Move restor... - 02:11 PM Revision 92f4b517 (ceph): Merge pull request #7329 from fullerdj/wip-14476
- librbd: remove canceled tasks from timer thread
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:47 PM Revision 84175ba6 (ceph): rgw: fix dangeours usage of strtok in RGWAccessControlPolicy_SWIFT.
- Fixes: #14526
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 12:31 PM Support #8915: Ceph Firefly 0.80.4 : health HEALTH_WARN pool volumes has too few pgs; crush map h...
- Is this problem fixed??
- 11:46 AM Revision f1766646 (ceph): os/FileStore:clean up error message
- Signed-off-by: Donghai Xu <xu.donghai@h3c.com>
- 11:04 AM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
- Also this issue is reproducible when the running the ceph/daemon containers on Bare metal servers currently running R...
- 10:45 AM Bug #14501 (In Progress): "rados" command does not honor the "-f" short argument for generating o...
- 10:16 AM Bug #14501: "rados" command does not honor the "-f" short argument for generating output in JSON ...
- "force" option is not used at all. unless some unknown test is broken, we can just use '-f' as the alias of '--format'.
- 09:53 AM Bug #14501: "rados" command does not honor the "-f" short argument for generating output in JSON ...
- Unfortunately the short option `f` is already used up as a `force` option
- 09:26 AM Bug #14524 (Closed): BlueStore: overlay leak
- Check bool put_overlay_ref(uint64_t key) for detail information.
- 08:31 AM Bug #13422: pid file that was deleted after ceph restart leads to osd process lose control
- > Will patch be (able to be) backported to 0.80.8?
@Shinobu 0.80.8 is a firefly release, and since firefly is reti... - 07:42 AM Bug #14472: Activate OSD [WARNIN] message
- Thank you, I understand
- 07:27 AM Bug #14366: unsafe handle_conf_change() methods
- as a complementary side note for whom wants more context of this issue
> as this function is called from a thread,... - 07:14 AM Feature #13942: ceph-disk: support bluestore
- bluestore fails to initialize on a ceph-disk prepared device (no external journal).
- 06:38 AM Revision 12649ef4 (ceph): test: add unitest test_pidfile.sh
- Fixes: #13422
Signed-off-by: shun song <song.shun3@zte.com.cn> - 06:01 AM CephFS Bug #13926: lockup in multithreaded application
- Zheng, anything come out of this?
- 05:59 AM CephFS Bug #10336 (Can't reproduce): hung ffsb test
- 05:57 AM CephFS Bug #13546 (Resolved): mv of directories hung Ceph filesystem
- 02:49 AM Bug #14213: osd/OSD.cc: 2940: FAILED assert(0 == "Missing map in load_pgs")
- Not sure what changes were being tested in branch at 6479fc8a7c28c5eb3723fa2268d596d4588906aa, so I'm assigning back ...
- 02:44 AM Bug #14438 (In Progress): "FAILED assert(pg->info.history.same_interval_since == p.same_interval_...
- Trying to reproduce with branch wip-diag-14438 containing diagnostics.
- 02:29 AM Revision 4da5052c (ceph): Mon: When set pool crush rule should consider the pool size.
- Fixes: #14495
Signed-off-by: song baisen <song.baisen@zte.com.cn> - 02:24 AM Bug #13968: OSD:lock PG when get_pg_or_queue_for_pg method successfully return a PG
- Samuel Just wrote:
> The threads that use that method are not allowed to take the pg or osd lock (messenger ms_fast_... - 01:37 AM Revision 39e7fcdb (ceph): rbd: Add an argument-check for nbds_max in rbd-nbd
- Fixes: #14482
This modification adds several checks to the argument of nbds_max in the module of rbd-nbd. The value ... - 01:25 AM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- Having similar issue on http://tracker.ceph.com/issues/14522
- 12:34 AM Bug #14471: assert(last_e.version.version < e.version.version) failed
- ceph version is hammer v0.94.5.
The osd was crashed by "assert(last_e.version.version < e.version.version) failed",
... - 12:26 AM Bug #14406: osd aborted when try to decode osdmap with 0 bytes
- yes, i copy the osdmap from other osd, and restart osd, it works.
- 12:05 AM Revision a45f484a (ceph): Build: Allow jemalloc enabled build with rocksdb-static
- Presently, we can't do jemalloc enabled OSD build along with
rocksdb-static.Rocksdb is now mandatory with Bluestore a...
01/26/2016
- 11:48 PM Bug #14521 (Won't Fix): Failure on restart after repairing corrupted PG
- Test case:
1. Start 2 OSDs, 8 PGs, pool size = 2
2. Run write workload for some time.
3. Stop workload
4. rm -rf ... - 11:22 PM Bug #9570 (New): osd crash in FileJournal::WriteFinisher::entry() aio
- This resurfaced, again with a result of 8192 when writing 80 bytes. This time it was with ceph 0.94.1, but the kernel...
- 10:48 PM Revision ab3e1c6b (ceph): Merge pull request #7120 from zaitcev/wip-5073-update1
- rgw: fix up the use of tenant before it's available
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 10:27 PM Bug #14520 (Resolved): VM permanently tries to read /dev/shm/lttng-ust-wait-5
- This is already fixed in the hammer branch by 5d204db..a81bcf7
This series turns off lttng by default, and lets it... - 10:09 PM Bug #14520 (Duplicate): VM permanently tries to read /dev/shm/lttng-ust-wait-5
- Ubuntu 14.04
Ceph 94.5-1trusty
liblttng-ust0
libvert
Bug is open with Canonical: https://bugs.launchpad.net/ubun... - 10:19 PM Bug #14457: tcmalloc oom bug
- Suspect the same root cause of failures in this run http://pulpito.ceph.com/teuthology-2016-01-26_02:10:02-upgrade:ha...
- 09:51 PM Bug #13966 (Pending Backport): memory leak in PG/replica_scrub
- 03:52 PM Bug #13966: memory leak in PG/replica_scrub
- Fixed in 5b35eb8d27ea7bb3aee6d14ad2eaed5f42c1adb0. Should be backported to hammer.
- 09:48 PM Bug #13781: Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- @Loic: What I was trying to say was that ceph.spec.in in hammer does not support systemd.
- 03:40 PM Bug #13781 (Need More Info): Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- @nathan : rhel7.1 has hammer and systemd
@Vimal could you please confirm that the service was enabled ? If so it w... - 08:43 PM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
- Adding more info, the issue only happened while using '—net-host’, with the default networking mode it works fine.
- 04:04 PM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
- Hey Huamin,
We use Docker version 1.8.2-el7, build a01dc02/1.8.2 on RHEL 7.2 - 03:55 PM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
- Deepthi,
Want to have some information from you to debug this. Did you upgrade docker too while upgrading to RHEL ... - 07:22 PM Revision d1160a03 (ceph): time: Fix encode/decode for real_time values
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 07:22 PM Revision 0f6bfbec (ceph): test: add ceph-dencoder test for ceph::real_time
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:14 PM Revision 0ec5adcd (ceph): Merge branch 'wip-14374' of git://github.com/jcsp/ceph into greg-fs-tes...
- https://github.com/ceph/ceph/pull/7295
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Conflicts:
src/mds/MDSDaemon.cc
... - 07:06 PM Revision febcc065 (ceph): Merge branch 'wip-14365' of git://github.com/jcsp/ceph into greg-fs-tes...
- https://github.com/ceph/ceph/pull/7312
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 07:00 PM rgw Bug #14516 (Resolved): rgw: radosgw-admin --help doesn't show the "orphans find" command
- 07:00 PM Revision 95ce3ce2 (ceph): Merge branch 'jewel-13903' of git://github.com/ukernel/ceph into greg-f...
- https://github.com/ceph/ceph/pull/7297
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:53 PM Bug #14267 (In Progress): ceph-post-file doesn't work
- A temporary solution is in place (gitbuilder-archive has VPN tunnel to the lab with long running cluster mounted) but...
- 06:47 PM Revision fd64e3bf (ceph): Merge pull request #7343 from ukernel/jewel-dump-requests-lockdep
- objecter: avoid recursive lock of Objecter::rwlock
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:26 PM Revision 0d238b90 (ceph): Merge pull request #7366 from tchaikov/wip-cmake-snappy
- cmake: check for libsnappy in default path also
- 05:46 PM Linux kernel client Bug #13905 (Closed): "BUG: held lock freed!"
- This looks like a problem in the networking stack, the kernel client isn't in play here. Closing, given that it was ...
- 05:43 PM Linux kernel client Bug #14117 (Won't Fix): KRBD : Performance issues with kernel 4.1 series
- A bit more info on this: http://lists.ceph.com/pipermail/ceph-users-ceph.com/2015-December/006895.html, closing.
- 05:41 PM Linux kernel client Feature #14201: cope with a pool being removed from under a mapped image
- We currently don't cope very well with this - see #11960. When #9779 is finished, there will be a message printed to...
- 05:28 PM Linux kernel client Bug #14200 (Closed): The mounted image can not expansion
- Kernel client does support resize, both up and down.
"rbd resize" command resizes /dev/rbd* block device, not the ... - 04:22 PM Bug #8885 (New): SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- David, can you take a look?
- 04:18 PM Bug #14073: osd: hammer: fail to start due to stray pglog object after firefly->hammer upgrade
- Those should be updated atomically, please reproduce with filestore,osd,ms debugging.
debug filestore = 20
debug ... - 04:17 PM Bug #13398 (Closed): leveldb compaction error
- 04:16 PM Bug #14021 (Closed): osd coredump on rhel7.1
- 04:15 PM Bug #14097 (Closed): "rcu_sched self-detected stall on CPU" failed jobs in upgrade:hammer-hammer-...
- This doesn't seem likely to be a ceph bug.
- 04:15 PM Bug #13857 (Can't reproduce): tests: make check timeout occasionaly
- 04:14 PM Bug #14206 (Rejected): BlueStore Crashed
- It's moving a lot, hopefully this is fixed now :-) Thanks for your report !
- 04:11 PM Bug #14359 (Closed): test
- I think you meant to close this?
- 04:10 PM Bug #14197 (Rejected): Rados bench 4K write stops and reports pipe fault
- Rejecting for now (seems to be setup?). Feel free to reopen if there is new information.
- 04:10 PM Bug #14347 (Need More Info): Failed after 'ceph::buffer::bad_alloc' in upgrade:infernalis-x-jewel...
- Kefu: did this just hit an oom?
- 04:08 PM Bug #14340 (Can't reproduce): client command stuck forever
- Feel free to reopen if you have more information.
- 04:05 PM Bug #13511 (Rejected): core dump during osd start
- The root cause of these failures is a bad disk.
- 04:03 PM Bug #14406 (Can't reproduce): osd aborted when try to decode osdmap with 0 bytes
- Sounds like a corrupt osd store. You could probably try to copy the osdmap from another osd. If you can reproduce t...
- 04:01 PM Bug #14390 (Resolved): make error
- Supposedly fixed
- 04:00 PM Bug #14431 (Resolved): bluestore transaction "make check" is failing on rex004
- 03:58 PM Bug #13902: OSD:project_pg_history may not return the latest same_interval_since.
- 03:55 PM Bug #13937 (Can't reproduce): osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- I think this is an actual shortcoming with the way we handle corrupt osds, I'll open a feature ticket to improve that.
- 03:55 PM Feature #14513 (Resolved): Test and improve ec handling of reads on objects with shards unexpecte...
- 03:53 PM Revision 5efc5dce (ceph): cmake: check for libsnappy in default path also
- * some distros install libsnappy into /usr/lib/x86_64-linux-gnu
which is completely resonable. but this directory i... - 03:49 PM Feature #14216 (Fix Under Review): Show the pool quota info on ceph df detial command
- 03:49 PM Bug #13968 (Rejected): OSD:lock PG when get_pg_or_queue_for_pg method successfully return a PG
- The threads that use that method are not allowed to take the pg or osd lock (messenger ms_fast_dispatch threads). Th...
- 03:48 PM Bug #13995 (Need More Info): ceph-osd "nonce collision" due to unshared pid namespaces
- that's an interesting problem :-) It would be great if you could provide steps to reproduce the problem. I don't see ...
- 03:45 PM Bug #13995: ceph-osd "nonce collision" due to unshared pid namespaces
- I don't quite understand the problem, is it that the pid and hostname was the same?
- 03:40 PM Bug #13916 (Can't reproduce): erasure code profile name
- I'm closing this on the assumption that the original problem was an issue with the reporter's crush map. Reopen if I...
- 03:39 PM Bug #10671 (Rejected): rados cppool don't work if target is a ecpool
- Yeah, omap is fundamentally not supported on ec at the moment (probably ever). Trying to do a cppool from a pool wit...
- 03:39 PM Bug #14458 (Duplicate): "shared_cache.hpp: 104: FAILED assert(weak_refs.empty())" in rados-hammer...
- 03:38 PM Bug #14461 (Rejected): test hung "joining thrashosds" in hammer tests
- not enough info to tell what happened.
- 03:36 PM Feature #14348: systemd: support multiple clusters
- Would you be so kind as to create a pull request with these proposed changes ?
- 03:36 PM Bug #14471 (Need More Info): assert(last_e.version.version < e.version.version) failed
- what version is this? what caused the osd crash? are other osds failing, or was it able to recover with teh other r...
- 03:36 PM Bug #14075 (Resolved): OSD: wrongly placed assert during handle_pg_peering_evt.
- I don't think so. That assert is there because RES_PARENT can only happen if the pg we are resurrecting is going to ...
- 03:35 PM Bug #14463 (Resolved): configure: make --with-librocksdb-static=check the default
- commit:269c61a667a9146547a45c1ec48d5e8b9ac42a34
- 03:34 PM Bug #14472 (Won't Fix): Activate OSD [WARNIN] message
- it's informative... the file is created on the next line.
- 03:33 PM Bug #14449 (Won't Fix): KeyValueStore:Do not need to judge the return value of save_strip_header
- we're removing this
- 03:33 PM Bug #14136 (Won't Fix): "Error EINVAL: crushtool check failed with -22" in upgrade:infernalis-inf...
- 03:33 PM Bug #14136: "Error EINVAL: crushtool check failed with -22" in upgrade:infernalis-infernalis-dist...
- It's bound to happen from time to time when the machine is slow. The real fix for this would be for the check using c...
- 03:33 PM Bug #12865 (Can't reproduce): OSDs crashing and not resolving blocked requests after network split
- 03:31 PM Bug #14495 (Fix Under Review): Crush:When set pool crush rule should consite the pool size.
- 03:31 PM Bug #13827 (Resolved): OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer ...
- Marking resolved -- appears to be just flaky disks and too conservative defaults for this configuration (there is ano...
- 03:29 PM Messengers Bug #14386 (Resolved): async messenger segfault
- 03:29 PM Bug #14446 (Resolved): make failed
- Reopen if not actually resolved on current master
- 03:28 PM Revision db3dc4d3 (ceph): osd: build_past_intervals_parallel() add diagnostics before assert
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 03:27 PM Bug #14505 (Rejected): "kernel: BUG: soft lockup - CPU#1 stuck" in upgrade:infernalis-infernalis-...
- no need to open tickets for these unless it is ceph-releated. this looks like na ext4 kernel issue.
- 03:25 PM Bug #14511: cache-flush-evict-all causes OSD stuck ops on unevictable objects
- Sounds like we didn't remove the object from one of the blocked maps
- 10:42 AM Bug #14511 (Resolved): cache-flush-evict-all causes OSD stuck ops on unevictable objects
- Cluster is running Ceph 0.94.4.
Start with a pair of empty pools, one erasure, one replicated:... - 03:18 PM rbd Bug #14510: TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED assert(m_state == S...
- I see it in today master: https://github.com/ceph/ceph/blob/master/src/librbd/Journal.cc#L376
- 02:57 PM rbd Bug #14510 (Need More Info): TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED as...
- 02:56 PM rbd Bug #14510: TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED assert(m_state == S...
- I think you have an old version of code -- "assert(m_state == STATE_READY)" doesn't exist in the codebase.
- 10:29 AM rbd Bug #14510: TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED assert(m_state == S...
- Below is a debug log for the crash. librbd::SnapshotCreateRequest may be called when the journal has not finished the...
- 09:57 AM rbd Bug #14510 (Resolved): TestLibRBD.ObjectMapConsistentSnap librbd/Journal.cc: 376: FAILED assert(m...
- I saw this in a jenkins test: https://jenkins.ceph.com/job/ceph-pull-requests/545/console
And running the test man... - 03:12 PM Revision d54840bf (ceph): Merge pull request #7365 from liewegas/wip-tcmalloc-hammer
- osd: pass tcmalloc env through to ceph-osd
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 02:59 PM Revision 1acfec13 (ceph): Merge pull request #7304 from liewegas/wip-tcmalloc
- osd: pass tcmalloc env through to daemon
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 02:55 PM rbd Backport #14512 (Resolved): hammer: snapshot, flatten, and rollback of cloned image leads to data...
- https://github.com/ceph/ceph/pull/8535
- 02:41 PM Revision b8737584 (ceph): Merge pull request #7358 from chenyehua11692/master
- mds:judgment added to avoid the risk of visiting the NULL pointer
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 01:52 PM Revision 9f30fe18 (ceph): upstart/ceph-osd.conf: pass TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES through
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit a95a3d34cccb9f9f0782a96ca05e5fe9c2b01772) - 01:52 PM Revision a58873e2 (ceph): init-ceph: pass TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES through
- ..when set in the sysconfig/default file.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 03e0... - 01:43 PM Revision a95a3d34 (ceph): upstart/ceph-osd.conf: pass TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES through
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:56 AM Revision b77cd31b (ceph): mon: add mon_config_key prefix when sync full
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 10:48 AM Bug #14509 (Fix Under Review): When create pool use the crush rule we should consider the pool size.
- 07:13 AM Bug #14509: When create pool use the crush rule we should consider the pool size.
- https://github.com/ceph/ceph/pull/7359
- 07:03 AM Bug #14509 (Resolved): When create pool use the crush rule we should consider the pool size.
- When create pool use the crush rule we should consider the pool size.
- 09:40 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- I've uploaded the kernel with all modules and the /proc/config.gz to https://stephan.wienczny.de/linux.tar.xz
- 07:24 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- backtrace of your kernel are strange, If possible, please upload the whole kernel package to somewhere.
- 03:53 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- could you upload the ceph,ko.
- 09:12 AM rgw Bug #14475: Unable to upload files with the + character
- This is the log from the radosgw
2016-01-22 13:01:52.800011 7ff7e4ff9700 1 civetweb: 0x7ff7b00008c0: 127.0.0.1 - -... - 07:14 AM Revision f2c0ef40 (ceph): global/pidfile: do not start two daemons with a single pid-file
- add functions named pidfile_open and pidfile_verify to avoid starting two daemons by a single pid-file
Fixes: #13422... - 04:29 AM Cleanup #14356: cleanup filestore xattr use omap
- 04:26 AM Bug #14438: "FAILED assert(pg->info.history.same_interval_since == p.same_interval_since)" in upg...
- We should create a commit that changes the assert(pg->info.history.same_interval_since == p.same_interval_since) to o...
- 03:15 AM Bug #14508 (Resolved): mon: drop useless rank init assignment
- 01:57 AM Bug #14508: mon: drop useless rank init assignment
- https://github.com/ceph/ceph/pull/7321
- 01:26 AM Bug #14508 (Resolved): mon: drop useless rank init assignment
- ...
- 03:01 AM Revision 845f3f7f (ceph): mds:judgment added to avoid the risk of visting the NULL pointer
- Signed-off-by: chenyehua11692 chen.yehua@h3c.com
- 03:00 AM Bug #14393 (Resolved): BlueStore: shall return negative error code if unable to write lable
- https://github.com/xiexingguo/ceph/commit/5ff452bbf5be851bddb544c4ee0908323c30c5c3
- 02:59 AM Bug #14394 (Resolved): BlueStore: shall verify fsid in a more proper way during mkfs
- https://github.com/xiexingguo/ceph/commit/5183ff3df6a834bb04d3ccdc65a7a67fb0241892
- 02:56 AM Bug #14433 (Resolved): os/kstore: shall avoid create the destination onode during rename.
- https://github.com/xiexingguo/ceph/commit/797155222f8cb3b7ffb7d89c8680589f91dfab38
- 02:55 AM Bug #14407: kstore/bluestore: potential data lost
- https://github.com/xiexingguo/ceph/commit/8065b8ab34f06d8d5d8e7fbdc1d8a846d88b30df
- 01:59 AM Bug #14407 (Resolved): kstore/bluestore: potential data lost
- 02:33 AM rgw Backport #12635: swift smoke test fails on TestAccountUTF8
- rgw_rest_user.cc:25
void RGWOp_User_Info::execute()
||
V
rgw_user.cc:2090
int RGWUserAdminOp_User::info(RGWRados... - 02:28 AM Revision 831cc7a7 (ceph): Merge pull request #7251 from tchaikov/wip-rados-manpage
- doc: amend the rados.8
Reviewed-by: Sage Weil <sage@redhat.com> - 02:21 AM Bug #14473 (Resolved): mon:Monitor initialization bug fixes
- 01:57 AM Bug #14473: mon:Monitor initialization bug fixes
- huanwen ren wrote:
> https://github.com/ceph/ceph/pull/7321
change to https://github.com/ceph/ceph/pull/7353
- 02:21 AM Revision 0a72cf10 (ceph): Merge pull request #7353 from renhwsky/renhw-wip-14473-2
- mon: fix locking in preinit error paths
Reviewed-by: Sage Weil <sage@redhat.com> - 02:20 AM Revision e39e8f4c (ceph): Merge pull request #7321 from renhwsky/renhw-wip-14473
- mon: drop useless rank init assignment
Reviewed-by: Sage Weil <sage@redhat.com> - 02:12 AM Revision 508013d0 (ceph): mon: drop useless rank init assignment
- drop useless rank init assignment
Fixes:14508
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 02:05 AM Revision 8097adb2 (ceph): Merge pull request #7294 from branch-predictor/bp-buffer-spinlock
- common/buffer: replace RWLock with spinlocks
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: song baisen <song... - 02:04 AM Revision 94ba0061 (ceph): Merge pull request #7303 from cbodley/wip-tx-move
- os/ObjectStore: add custom move operations for ObjectStore::Transaction
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:59 AM Revision e9b26746 (ceph): Merge pull request #7283 from xiexingguo/xxg-wip-14407
- os/bluestore/kstore: fix nid overwritten logic
http://pulpito.ceph.com/sage-2016-01-25_07:39:08-rados-wip-sage-testi... - 01:58 AM Revision b08116b1 (ceph): Merge pull request #7267 from liewegas/wip-fiemap
- osd: drop fiemap len=0 magic
http://pulpito.ceph.com/sage-2016-01-25_07:39:08-rados-wip-sage-testing2---basic-smithi... - 01:58 AM Revision 54aef927 (ceph): Crush: add some safe judgment
- Fixes: #14496
Signed-off-by: song baisen song.baisen@zte.com.cn - 01:51 AM Revision 45f338df (ceph): mon: fix locking in preinit error paths
- fix locking in preinit error paths
Fixes: #14473
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 12:10 AM rgw Bug #14507 (Resolved): rgw: user quota may not adjust on bucket removal
If the user/admin removes a bucket using --force/--purge-objects options with s3cmd/radosgw-admin respectively, the...
01/25/2016
- 11:32 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- The blocked task occour even without cgroup limits. I did a test with 10M limit while reading large files. There are ...
- 10:48 PM Revision 3cf8465a (ceph): bluefs_types: fix test instance of fs transaction
- As ino 1 is reserved for log-file use only and
shall be made invisible for normal file.
Signed-off-by: xie xingguo <... - 10:48 PM Revision 07af5f6a (ceph): bluefs_types: fix device index overflow
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:55 PM Bug #14505 (Rejected): "kernel: BUG: soft lockup - CPU#1 stuck" in upgrade:infernalis-infernalis-...
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-24_13:18:03-upgrade:infernalis-infernalis-distro-b...- 09:08 PM Bug #14503 (Resolved): "[ FAILED ] LibRadosAio.IsSafe" in rados-infernalis-distro-basic-openstack
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-24_02:00:01-rados-infernalis-distro-basic-openstack/
... - 09:05 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
- Also in rados suite
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-24_02:00:01-rados-infernalis-dist... - 08:45 PM Revision 83950596 (ceph): time: Make ceph_time clocks work under BSD
- Linux's naming things _COARSE is non-standard. Other systems name them other
non-standard things. BSD names them _FAS... - 07:36 PM Revision e71057d0 (ceph): os/fs: fix io_getevents argument
- Signed-off-by: Jingkai Yuan <jingkai.yuan@intel.com>
- 07:19 PM Bug #14499 (Fix Under Review): librados rados_monitor_log() aborts if called prior to rados_conne...
- 04:28 PM Bug #14499: librados rados_monitor_log() aborts if called prior to rados_connect()
- Fix submitted via:
https://github.com/ceph/ceph/pull/7350 - 03:23 PM Bug #14499 (Resolved): librados rados_monitor_log() aborts if called prior to rados_connect()
- rados_moditor_log() must be called with a connected rados cluster context, otherwise the calling process may abort wi...
- 06:21 PM Bug #14136: "Error EINVAL: crushtool check failed with -22" in upgrade:infernalis-infernalis-dist...
- Also in rados run:
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-23_02:00:01-rados-infernalis-distro-bas... - 05:05 PM Bug #14501 (Resolved): "rados" command does not honor the "-f" short argument for generating outp...
- While the "rados" command honors the long option "--format=json" for generating JSON output, it does not accept the "...
- 04:49 PM Revision f1113512 (ceph): FileStore:Use pwritev instead of writev
- Signed-off-by: Tao Chang <changtao@hihuron.com>
- 04:28 PM Revision 1037d2e7 (ceph): doc: Add Ubuntu-specific steps to install RGW
- Signed-off-by: Bara Ancincova <bancinco@redhat.com>
- 04:28 PM Revision 2f3774b2 (ceph): doc: remove old install-ceph-gateway_old.rst file
- Signed-off-by: Bara Ancincova <bara@redhat.com>
- 04:28 PM Revision 68a571bc (ceph): doc: small edits according to review
- Signed-off-by: Bara Ancincova <bara@redhat.com>
https://github.com/ceph/ceph/pull/7264#discussion_r50227327
https://... - 04:28 PM Revision 46484e9c (ceph): doc: Adding headers to RGW quick.
- Signed-off-by: bancinco@redhat.com
- 04:28 PM Revision f66f9d73 (ceph): doc: Port changes from downstream (install-ceph-gateway)
- Signed-of-by: Bara Ancincova <bancinco@redhat.com>
- 04:28 PM Revision d7eae8c0 (ceph): doc: Edited RGW quick start according to peer review.
- Signed-off-by: Bara Ancincova <bancinco@redhat.com>
- 04:10 PM Revision 3ce648d3 (ceph): rados: bench: add --max-objects
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:55 PM Revision a76ea6fb (ceph): Merge pull request #7314 from tchaikov/wip-fix-cmake
- cmake: let ceph-client-debug link with tcmalloc
- 01:33 PM Revision d5287e2a (ceph): Merge pull request #7331 from XinzeChi/wip-RepModify-bytes-written
- osd: delete useless bytes_written defined in RepModify
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:20 PM Backport #14497 (In Progress): hammer: ceph-monstore-tool: FAILED assert(!is_open)
- 09:54 AM Backport #14497: hammer: ceph-monstore-tool: FAILED assert(!is_open)
- ...
- 09:53 AM Backport #14497: hammer: ceph-monstore-tool: FAILED assert(!is_open)
- https://github.com/ceph/ceph/pull/7347
- 09:52 AM Backport #14497 (Resolved): hammer: ceph-monstore-tool: FAILED assert(!is_open)
- https://github.com/ceph/ceph/pull/7347
- 11:01 AM Revision c2b5a685 (ceph): BlueFS: fix space leak during write
- Fixes: #14481
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 11:01 AM Revision 5088dfd3 (ceph): BlueFS: flush_wait log before update super
- Fixes: #14484
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 10:54 AM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
- Sorry my bad, Affected version is 0.94.5
- 10:50 AM Bug #14498 (Can't reproduce): cephx error: NSS AES final round failed: -8190 while bootstrapping ...
- I have been running ceph-docker project with ceph/daemon:centos-latest image based on 'hammer' release on RHEL 7.1 an...
- 10:53 AM Revision aba6746b (ceph): PG::activate(): handle unexpected cached_removed_snaps more gracefully
- PGPool::update(): ditto
Fixes: #14428
Backport: infernalis, hammer, firefly
Signed-off-by: Alexey Sheplyakov <ashep... - 09:51 AM Bug #10093 (Pending Backport): ceph-monstore-tool: FAILED assert(!is_open)
- 09:45 AM Revision 8d9e08c4 (ceph): tools: ceph-monstore-tool must do out_store.close()
- this change fixes the "store-copy" command.
Like the bug reported in http://tracker.ceph.com/issues/10093.
Signed-of... - 09:07 AM Cleanup #14496: Crush:add some safe judgment.
- https://github.com/ceph/ceph/pull/7344
- 08:59 AM Cleanup #14496 (Resolved): Crush:add some safe judgment.
- Crush:add some safe judgment.
- 08:59 AM Revision 211d4b48 (ceph): Merge pull request #7342 from tchaikov/wip-fix-ceph-dencoder
- os/bluestore: fix bluestore_wal_transaction_t encoding test
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:12 AM Revision 68c78775 (ceph): objecter: avoid recursive lock of Objecter::rwlock
- Objecter::RequestStateHook::call() already takes read lock of
Objecter::rwlock. Taking read lock again in Objecter::_... - 07:08 AM Revision 4d30e7cf (ceph): os/bluestore: fix bluestore_wal_transaction_t encoding test
- bluestore_wal_op_t::op is encoded/dumped but it is not
initialized in its ctor. so set it to 0 in its ctor. 0 is not ... - 07:01 AM Bug #13422: pid file that was deleted after ceph restart leads to osd process lose control
- Will patch be (able to be) backported to 0.80.8?
- 05:15 AM Bug #13422: pid file that was deleted after ceph restart leads to osd process lose control
- https://github.com/ceph/ceph/pull/7075
- 06:20 AM Revision 2488ad1a (ceph): Merge pull request #7315 from tchaikov/wip-kill-warnings
- Wip kill warnings
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:15 AM Revision acd4314c (ceph): Merge pull request #7284 from ceph/wip-make-remove-libedit
- makefile: remove libedit from libclient.la
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Loic Dachary ... - 05:50 AM Bug #14495: Crush:When set pool crush rule should consite the pool size.
- https://github.com/ceph/ceph/pull/7341
- 05:43 AM Bug #14495 (Resolved): Crush:When set pool crush rule should consite the pool size.
- If we change the pool crush rule,we should consider the pool size.
- 05:21 AM Backport #14494 (Resolved): infernalis: pgs stuck inconsistent after infernalis upgrade
- https://github.com/ceph/ceph/pull/7421
- 05:16 AM Backport #14493 (Resolved): hammer: make rgw_fronends more forgiving of whitespace
- https://github.com/ceph/ceph/pull/7414
- 05:14 AM Backport #14491 (Rejected): hammer: ceph-disk: duplicate osd mount points
- 05:10 AM CephFS Backport #14490 (Resolved): infernalis: fsx failed to compile
- https://github.com/ceph/ceph/pull/7429
- 04:10 AM CephFS Bug #14489 (New): ovh: ENOSPC on multiple_rsync.sh as part of cfuse_workunit_misc
- http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-16_18:04:01-fs-master---basic-openstack/4272/
- 04:07 AM CephFS Bug #14488: ovh: ENOSPC in kernel_untar_build
- http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-18_20:08:01-kcephfs-master-testing-basic-openstack/6824/
- 03:58 AM CephFS Bug #14488 (New): ovh: ENOSPC in kernel_untar_build
- http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-16_20:08:02-kcephfs-master-testing-basic-openstack/4363/
- 03:50 AM Linux kernel client Bug #14487 (Resolved): ctime may go backward in cephfs kernel client
- In cephfs code, we use CURRENT_TIME directly to get timestamp. But in setattr() case, Timestamp for ctime are truncat...
- 03:50 AM CephFS Bug #13977: ovh: sambatorture.scan-pipe_number fails on ENOMEM
- http://teuthology.ovh.sepia.ceph.com/teuthology/teuthology-2016-01-16_23:14:01-samba-master---basic-openstack/4432/
- 03:48 AM CephFS Bug #14486 (New): ovh: samba test filled up disk
- http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-17_23:14:01-samba-hammer---basic-openstack/5996/
- 03:41 AM Linux kernel client Bug #14485 (Resolved): cephfs kernel client does not flush ctime
- https://github.com/ceph/ceph-client/commit/d62f355721233c5177cadf2b635e0a5e26b27237
- 03:38 AM Bug #14481 (New): BlueFS: space leak
- 03:15 AM Bug #14484 (Resolved): BlueFS: potential log data lost during compact
- Shall call flush_wait before update super during compact log.
- 02:29 AM Revision bde03c7c (ceph): client: add option to control how directory size is calculated
- "recursive size" VS "number of entries"
Signed-off-by: Yan, Zheng <zyan@redhat.com>
01/24/2016
- 05:15 PM rbd Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- I ran the VM again without dropping privileges and without chroot. As soon as the image was flattened, all IO stalled...
- 05:07 PM rbd Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- Something else that I'm absolutely unsure whether it's relevant: we run Qemu with dropping privileges to 'noboyd' and...
- 05:01 PM rbd Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- Here's the full log of the last days, with multiple instances, including the ones I mentioned above:
http://shared00... - 04:57 PM rbd Bug #14483 (Resolved): Flattening an rbd image with a running Qemu instances causes librbd worker...
- This Ceph 0.94.5 and Qemu 2.2.1 with some backported live-migration fixes (but Live migration isn't involved here).
... - 04:33 PM Bug #12865: OSDs crashing and not resolving blocked requests after network split
- FYI: We're currently at 0.94.5 and we did some substantial cleanup over the year (basically rebuilding the whole clus...
01/23/2016
- 04:22 PM Revision 3d873120 (ceph): mon/PGMonitor.cc:warning if pg not scrubbed
- Added 2 flags for displaying a warning when pg is unscrubbed:
mon report not scrubbed
mon report not deep scrubbed
E... - 02:24 PM rbd Bug #14482 (Resolved): rbd:rbd-nbd does not have an argument check for nbds_max
- 1.The value of argument nbds_max can be set to -1, which logically can not be understood. I think 0 is the boundary.
... - 02:07 PM Revision ab01c0e3 (ceph): Removing duplicate definitions for rados pool_stat_t and cluster_stat_t
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 06:38 AM Bug #14481 (Closed): BlueFS: space leak
- 02:55 AM Bug #14481 (Resolved): BlueFS: space leak
- Check int BlueFS::_allocate for detail information.
- 02:33 AM Revision da6d6965 (ceph): osd: delete useless bytes_written defined in RepModify
- this would avoid calling encode function.
Signed-off-by: Xinze Chi <xinze@xsky.com> - 02:03 AM Bug #14480 (Resolved): BlueFS: race condition detected.
- Check int BlueFS::reclaim_blocks(unsigned id, uint64_t want,
uint64_t *offset, uint32_t *length)
Shall be... - 02:00 AM Bug #14383 (Resolved): BlueFS::dir_map usage issues
01/22/2016
- 09:33 PM Revision eea2689b (ceph): Merge pull request #7301 from oritwas/wip-14375
- rgw: fix subuser rm command failure
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 07:28 PM rbd Bug #14476 (Fix Under Review): rbd: TaskFinisher::cancel should remove event from SafeTimer
- 07:27 PM rbd Bug #14476: rbd: TaskFinisher::cancel should remove event from SafeTimer
- https://github.com/ceph/ceph/pull/7329
- 07:21 PM rbd Bug #14476 (Resolved): rbd: TaskFinisher::cancel should remove event from SafeTimer
- TaskFinisher needs to call SafeTimer::cancel_event, otherwise canceled events fire anyway.
- 07:23 PM Revision 2aa0f318 (ceph): rbd: remove canceled tasks from timer thread
- When canceling scheduled tasks using the timer thread, TaskFinisher::cancel
does not call SafeTimer::cancel_event, so... - 07:14 PM rgw Bug #14475 (Can't reproduce): Unable to upload files with the + character
- Hi,
I am getting an error when I try to upload files with the + character. I get a 403 error from the radosgw
... - 07:09 PM Revision 45a234de (ceph): Merge pull request #7327 from igrcic/master
- doc: Fixes a CRUSH map step take argument
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 06:38 PM Bug #14457: tcmalloc oom bug
- What is this updated tcmalloc you talk about? Do we need something later than the distro package?
- 04:11 PM Bug #14457: tcmalloc oom bug
- Run: http://pulpito.ceph.com/teuthology-2016-01-21_13:17:25-upgrade:infernalis-x-jewel-distro-basic-vps/
Further d... - 05:59 PM Revision 5003770f (ceph): doc: Fixes a CRUSH map step take argument
- Signed-off-by: Ivan Grcic <igrcic@gmail.com>
- 04:02 PM Revision 78cfe674 (ceph): os: move Transaction ctors closer to member variables
- this makes it easier to update constructors when adding/removing fields
Signed-off-by: Casey Bodley <cbodley@redhat.... - 04:02 PM Revision 496605c5 (ceph): os: Transaction sets default values to avoid duplication in ctors
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 04:02 PM Revision fd33668a (ceph): os: add custom move ctor/assignment for TransactionData
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 04:02 PM Revision 7f44acf7 (ceph): os: add custom move ctor/assignment for Transaction
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 04:02 PM Revision 9e37a87a (ceph): test: add unit test for Transaction move/copy
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 02:36 PM Bug #14383: BlueFS::dir_map usage issues
- Please mark this as resolved
- 12:31 PM Revision c00945eb (ceph): cleanup: remove obsolete option "filestore_xattr_use_omap"
- This patch does cleanup for option "filestore_xattr_use_omap",
as this option was removed in #7408.
Fixes: #14356
Si... - 11:35 AM Bug #14369 (Resolved): osd:osdmap some clean up
- 09:53 AM Revision fe4e1802 (ceph): rbd-replay: async open/close calls support
- It still uses sync open/close in replay, which can be improved later.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 09:14 AM Bug #14474 (Resolved): BlueFS: miss log for updating fnode during open_for_write
- 08:27 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- http://tracker.ceph.com/issues/14382
firefly0.80.10,The same problem.Data Delete is not clean
!12.png!
!13.png... - 06:11 AM Bug #14449: KeyValueStore:Do not need to judge the return value of save_strip_header
- https://github.com/ceph/ceph/pull/7307
- 06:10 AM Bug #14473: mon:Monitor initialization bug fixes
- https://github.com/ceph/ceph/pull/7321
- 03:45 AM Bug #14473 (Resolved): mon:Monitor initialization bug fixes
- ...
- 03:41 AM Bug #14472 (Won't Fix): Activate OSD [WARNIN] message
- Why have [WARNIN] messages ? did not provide Journal hard disk ?
admin-node@admin-deploy:~/my-cluster$ ceph-depl... - 03:35 AM Support #14448: Installation (Quick) mount disk question
- solved
- 03:15 AM Revision 19c39fae (ceph): KeyValueStore: Kill this
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:59 AM Bug #14471: assert(last_e.version.version < e.version.version) failed
- and the osd log:
@-9> 2016-01-22 10:58:10.056257 7fb4d099b800 20 read_log coll 1.7b_head log_oid 7b//head//1
-8... - 02:52 AM Bug #14471 (Can't reproduce): assert(last_e.version.version < e.version.version) failed
- hi, when i restart my osd, it failed in read_log,
here is the gdb log:
@(gdb) bt#0 0x0000003d26c0f5db in raise () ... - 01:51 AM Revision 4524708d (ceph): test/cls :clean useless pools
- After do ./ceph_test_cls_log ,pools remains
need be destroyed.
Signed-off-by: Ji Chen <insomnia@139.com> - 01:42 AM Backport #14470 (Resolved): hammer: tool for artificially inflate the leveldb of the mon store fo...
- https://github.com/ceph/ceph/pull/7412
- 01:40 AM Backport #14469 (Rejected): infernalis: osd/ReplicatedPG: fix promotion recency logic
- https://github.com/ceph/ceph/pull/7561
- 01:39 AM Bug #14468 (Resolved): osd: dup op detection doesn't handle guarded writes
- Ops 17682 and 17686 appear out of order to osd.3 in this log:...
- 01:38 AM Backport #14467 (Resolved): hammer: disable filestore_xfs_extsize by default
- https://github.com/ceph/ceph/pull/7411
- 01:31 AM rbd Backport #14466 (Resolved): hammer: rbd-replay does not check for EOF and goes to endless loop
- https://github.com/ceph/ceph/pull/7416
- 01:30 AM rbd Backport #14465 (Resolved): infernalis: rbd-replay does not check for EOF and goes to endless loop
- https://github.com/ceph/ceph/pull/7427
- 01:27 AM Revision 82f28a8f (ceph): rgw: fix up the use of tenant before it's available
- A big problem that cropped up with the multi-tenancy as it
went in was that it used tenant to initialize bucket names... - 01:20 AM Bug #13160 (Pending Backport): ceph-disk: duplicate osd mount points
- 01:20 AM Bug #14451 (Duplicate): ceph-disk: duplicate osd mount points and umount fails to unmount tempora...
- see #13160
- 12:35 AM Revision 056a10cc (ceph): rgw: add a configurable to enable/disable static website
- rgw_enable_static_website
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:09 AM Revision f55fe9f4 (ceph): rgw: fix null dereference
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:08 AM Revision d71b7003 (ceph): rgw: don't abort on op_ret < 0
- We'll later have op->execute() return a status
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
01/21/2016
- 11:38 PM Revision 67e3d951 (ceph): Merge pull request #7317 from dmick/master
- configure.ac: make "--with-librocksdb-static" default to 'check'
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 11:31 PM Bug #14463 (Resolved): configure: make --with-librocksdb-static=check the default
- ceph really needs to build with a static librocksdb. While --with-librocksdb-static is added with 'check' as the val...
- 11:31 PM Revision 269c61a6 (ceph): configure.ac: make "--with-librocksdb-static" default to 'check'
- Fixes: #14463
Signed-off-by: Dan Mick <dan.mick@redhat.com> - 11:16 PM Revision f27e9c4c (ceph): rgw: the big op_ret change
- Move protected "int ret" member from immediate descendants of
RGWOp to a RGWOp, renamed to "int op_ret."
The new mem... - 10:38 PM Bug #14461 (Can't reproduce): test hung "joining thrashosds" in hammer tests
- See in several runs lately
Run: http://pulpito.ceph.com/teuthology-2016-01-21_02:10:09-upgrade:hammer-x-jewel-distro... - 09:44 PM Bug #14458 (Duplicate): "shared_cache.hpp: 104: FAILED assert(weak_refs.empty())" in rados-hammer...
- Run: http://pulpito.ceph.com/teuthology-2016-01-20_09:00:09-rados-hammer-distro-basic-mira/
Job: 34745
Logs: http:/... - 08:55 PM Bug #14457 (Duplicate): tcmalloc oom bug
- Run: http://pulpito.ceph.com/teuthology-2016-01-20_14:48:08-upgrade:infernalis-x-jewel-distro-basic-vps/
Jobs: 25541... - 08:54 PM Revision 0325f8af (ceph): deb: strip tracepoint libraries from Wheezy/Precise builds
- These releases do not (by default) have a sane LTTng-UST environment,
which results in autoconf disabling support for... - 08:15 PM CephFS Feature #14456 (Resolved): mon: prevent older/incompatible clients from mounting the file system
- If the kernel client mounts something with quotas set, we should provide server-side warning messages. For now, this ...
- 08:06 PM Revision 458d8e59 (ceph): librbd: API: async open and close
- Fixes: #14264
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 05:40 PM Revision 3ebb584b (ceph): librbd: fixed "hidden" virtual methods
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:37 PM Revision c74eeb53 (ceph): test/objectstore: fix unused variable warnings
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:37 PM Revision 674fe18d (ceph): cmake: let ceph-client-debug link with tcmalloc
- to fix the link problem of
libcephfs.so.1.0.0: undefined reference to `IsHeapProfilerRunning'
when tcmalloc is used a... - 04:36 PM Feature #14454: mon: report pool deletion in "ceph -w"
- I see a few commands executed via the ceph cli getting logged in the cluster log, for eg. osd pool create/delete, inj...
- 04:16 PM Feature #14454: mon: report pool deletion in "ceph -w"
- Joao had this to say:
> personally, I don't think it would be too hard to get updates on deleted pools being outpu... - 04:13 PM Feature #14454 (New): mon: report pool deletion in "ceph -w"
- When a pool is deleted while watching "ceph -w", the former is not currently reflected in the latter. Pool deletion s...
- 04:00 PM Revision b86c40b1 (ceph): include/[btree_]interval_set: drop useless assert
- This mirrors the condition above.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:59 PM Revision 9cafe607 (ceph): include/[btree_]interval_set: use std::swap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:58 PM Revision 7ccd1d26 (ceph): os/bluestore/FreelistManager: use btree_map::erase return value
- The btree_map erase() returns an iterator for the next element.
Perfect!
Reported-by: Igor Fedotov <ifedotov@miranti... - 03:54 PM Bug #13862 (Pending Backport): pgs stuck inconsistent after infernalis upgrade
- 03:50 PM Revision 225b5fe6 (ceph): Merge pull request #6976 from dzafman/wip-13862
- osd: fix temp object removal after upgrade
http://pulpito.ceph.com/sage-2016-01-20_17:01:32-upgrade:hammer-x-wip-sag... - 02:12 PM rbd Bug #14452 (Pending Backport): rbd-replay does not check for EOF and goes to endless loop
- 01:58 PM rbd Bug #14452: rbd-replay does not check for EOF and goes to endless loop
- https://github.com/ceph/ceph/pull/7310
- 01:58 PM rbd Bug #14452 (Resolved): rbd-replay does not check for EOF and goes to endless loop
- BufferReader::fetch() goes to endless loop because it does not check for EOF.
- 02:05 PM Revision 93ad14d5 (ceph): Merge pull request #7310 from trociny/fix-rbd-replay-eof
- rbd-replay: handle EOF gracefully
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:59 PM Bug #14428: Unable to bring up OSD's after dealing with FULL cluster (OSD assert with /include/in...
- https://github.com/ceph/ceph/pull/7309
- 01:59 PM Revision c59b84c3 (ceph): rbd-replay: handle EOF gracefully
- Fixes: #14452
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 01:45 PM Bug #14451: ceph-disk: duplicate osd mount points and umount fails to unmount temporary mount
- From /var/log/messages
Jan 19 21:12:30 osd-node1 systemd-udevd: timeout: killing '/usr/sbin/ceph-disk-activate /de... - 01:41 PM Bug #14451: ceph-disk: duplicate osd mount points and umount fails to unmount temporary mount
- Issue came into picture when we rebooted one of the osd nodes and some of the osd was having this issue.
- 01:40 PM Bug #14451: ceph-disk: duplicate osd mount points and umount fails to unmount temporary mount
- Vikhyat Umrao wrote:
> ceph-disk: duplicate osd mount points and umount fails to unmount temprory mount
>
> Coul... - 01:39 PM Bug #14451 (Duplicate): ceph-disk: duplicate osd mount points and umount fails to unmount tempora...
- ceph-disk: duplicate osd mount points and umount fails to unmount temprory mount
Could be related to http://track... - 01:32 PM CephFS Support #14450 (New): ceph-fuse does not work without loaded ceph/rbd kernel module writing big data
- Hi,
i was installing different OS ( centos 6, centos 7, Debian 8 ).
I was installing ceph-fuse only ( hammer r... - 01:32 PM CephFS Bug #14365 (Fix Under Review): unsafe handle_config_change() methods
- 01:30 PM Revision e430f8e4 (ceph): mds: fix locking around handle_conf_change
- We have to be careful about holding mds_lock
while setting things up, and we also have
to handle either locked or unl... - 01:29 PM Revision fb6dea39 (ceph): vstart: enable lockdep
- Development clusters are the right place to enable
performance-degrading correctness checks.
Signed-off-by: John Spr... - 01:29 PM Revision 26d10326 (ceph): mds: Fix lock ordering around asok registration
- Because we acquire mds_lock inside asok handlers,
we must not hold mds_lock while registering our commands.
Fixes: #... - 01:29 PM Revision f4b0b2f3 (ceph): cmake: fix libcephfs linking
- This was a merge glitch between Ali's cmake
updates and my VolumeClient PR. My PR
was using the old TCMALLOC_LIBS vs... - 01:29 PM Revision 94d1aa26 (ceph): client: take lock in handle_conf_change
- Fixes: #14365
Signed-off-by: John Spray <john.spray@redhat.com> - 01:29 PM Revision 448bea4d (ceph): client: don't hold client_lock around objecter init
- Because by doing so we establish a dependency
between client lock and admin socket lock.
Signed-off-by: John Spray <... - 01:10 PM Revision 3b5e7184 (ceph): Merge pull request #7292 from tchaikov/wip-submittingpatches
- doc: revise SubmittingPatches
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com> - 01:01 PM Revision 4124e1df (ceph): Merge pull request #7263 from theanalyst/vstart/update-opts
- vstart: update help with a few more commandline opts
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:53 PM Revision 5793df4c (ceph): doc: vstart update a few commandline switches
- Add a few more available commandline switches to vstart quickstart
documentation
Signed-off-by: Abhishek Lekshmanan ... - 12:46 PM Revision 1b4ea9bc (ceph): Merge pull request #7240 from cxwshawn/org-fix
- organizationmap: modify org mail info.
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
Reviewed-by:... - 11:46 AM Bug #14220: run-make-check.sh fails
- Me too:
libos.a(libos_a-BlueStore.o): In function `BlueStore::_open_db(bool)':
/home/asheplyakov/work/ceph/ceph/s... - 02:07 AM Bug #14220: run-make-check.sh fails
- i hit this now, but i still can not get solution for it.
- 10:18 AM Bug #14449 (Won't Fix): KeyValueStore:Do not need to judge the return value of save_strip_header
- ...
- 09:40 AM Revision 4400b814 (ceph): vstart.sh: If use '-n' delete related source rather than consider '-k'.
- Exec './vstart.sh -k -n' will meet error. The messages:
2016-01-20 19:55:22.998169 7f8acea1c8c0 -1 bluestore(/mnt/cep... - 09:08 AM Support #14448 (New): Installation (Quick) mount disk question
- please help,i have two question,as follows :
If i Install Quick step "sudo mkdir /var/local/osd0 " ,
mount 1TB 2.... - 06:38 AM rgw Bug #14447 (Closed): etag and content type after changing ACL and adding headers
- Hi all!
Today I've tested the patch from http://tracker.ceph.com/issues/13820 in our testing environment and it work... - 05:12 AM Revision 18409a89 (ceph): SubmittingPatches: add doc for commit title
- explain that we need a prefix in the commit title
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:12 AM Revision a2c1b536 (ceph): SubmittingPatches: sending kernel patches to mailing list
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:12 AM Revision 4d00a141 (ceph): SubmittingPatches: rebase to resolve conflicts
- pull request is not supposed to contain merge commits
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:27 AM Revision 2b5588a1 (ceph): SubmittingPatches: update with reST syntax
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:27 AM Revision dbabbd03 (ceph): SubmittingPatches: add doc for "Fixes:" tag
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:05 AM Documentation #1817 (In Progress): document librados C++ api
- 02:15 AM Documentation #1817: document librados C++ api
- The C++ api is fundamentally similar to the C api, where the analogous functions have been documented. Perhaps http:/...
- 01:48 AM Documentation #1817: document librados C++ api
- Four years have come and gone, and http://docs.ceph.com/docs/master/rados/api/libradospp/ is still waiting for its au...
- 02:50 AM Bug #14446 (Resolved): make failed
- platform: 3.19.0-25-generic #26~14.04.1-Ubuntu SMP Fri Jul 24 21:16:20 UTC 2015 x86_64 x86_64 x86_64 GNU/Linux
g++: ... - 01:47 AM Bug #14436 (Resolved): os/StupidAllocator: wrong assert
- https://github.com/ceph/ceph/pull/7293
- 01:36 AM Revision d4b8a00e (ceph): Merge pull request #7293 from xiexingguo/xxg-wip-14436
- os/bluestore: fix assert
Reviewed-by: Sage Weil <sage@redhat.com> - 01:02 AM Bug #14392 (Resolved): BlueStore: improve wal_transaction replay logic
- https://github.com/xiexingguo/ceph/commit/a671448f90a97aba30fe318b464588c612fdc375
- 01:01 AM CephFS Bug #14395: cephfs_journal_tool fails
- Sorry~~ I made a mistake
- 12:44 AM Bug #14370 (Resolved): MemStore: shall drain finisher first before returning from the unmount method
- https://github.com/xiexingguo/ceph/commit/8b30f9d6bdba81639121cde19540e1b25fd80f70
01/20/2016
- 11:36 PM Revision 03e01ae2 (ceph): init-ceph: pass TCMALLOC_MAX_TOTAL_THREAD_CACHE_BYTES through
- ..when set in the sysconfig/default file.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:16 PM Revision 222488a5 (ceph): Merge pull request #7197 from ceph/wip-kill-warnings
- build: fix warnings
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:16 PM Revision 73769f61 (ceph): Merge pull request #7232 from lzhng2000/master
- cls/cls_rbd: pass string by reference
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:15 PM Revision 660b9d78 (ceph): Merge pull request #7242 from xiexingguo/xxg-wip-14370
- os/memstore: drain finisher first before we really begin a umount-process
os/bluestore: drain wal_wq on replay error
... - 11:13 PM Revision a91d7482 (ceph): Merge pull request #7247 from ifed01/wip-14383
- os/bluestore: use intrusive_ptr for Dir
Reviewed-by: Sage Weil <sage@redhat.com> - 11:13 PM Revision abab99d0 (ceph): Merge pull request #7254 from guangyy/wip-counter
- common: change the type of counter total/unhealthy_workers
Reviewed-by: Sage Weil <sage@redhat.com> - 11:12 PM Revision 3a6b627e (ceph): Merge pull request #7255 from yuyuyu101/wip-14386
- msg/async: fix send closed local_connection message problem
Reviewed-by: Sage Weil <sage@redhat.com> - 10:55 PM Revision 783f33f0 (ceph): admin-socket.yaml: add get_heap_property tests
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 10:54 PM Revision 37720061 (ceph): osd/: make heap properties settable via admin socket
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 10:54 PM Revision 99b054f1 (ceph): osd/: make heap properties gettable from admin_socket
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 10:35 PM Bug #14443 (Resolved): "[ FAILED ] LibRadosTwoPoolsPP.Flush" in upgrade:infernalis-x-jewel-dist...
- Run: http://pulpito.ceph.com/teuthology-2016-01-20_02:10:02-upgrade:infernalis-x-jewel-distro-basic-vps/
Jobs: 34229... - 09:54 PM rbd Tasks #14442 (New): Create test cases in support of rbd-replay
- 09:50 PM Revision 75a372fa (ceph): Merge remote-tracking branch 'gh/jewel'
- 09:49 PM Revision 14188860 (ceph): Merge remote-tracking branch 'gh/jewel'
- 09:39 PM rbd Bug #14434 (Fix Under Review): intermittent errors in make check tests from journaling code
- *master PR*: https://github.com/ceph/ceph/pull/7302
- 07:26 PM rbd Bug #14434 (In Progress): intermittent errors in make check tests from journaling code
- 05:41 AM rbd Bug #14434 (Resolved): intermittent errors in make check tests from journaling code
- One example: http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-amd64-basic/log.cgi?log=f3e58a054aed197b...
- 09:36 PM Revision e1da0856 (ceph): test: race condition in ReplayOnDiskPostFlushError test case
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:33 PM Revision 14426213 (ceph): journal: avoid race between in-flight notifications and flush
- If an async callback for a safely committed event was in-flight,
it could race with the flush of the journal. This w... - 09:12 PM Revision 11d1d1fc (ceph): Merge pull request #7300 from ceph/wip-cmake
- cmake: test_build_libcephfs needs ${ALLOC_LIBS}
- 08:00 PM Revision bbc06e70 (ceph): rgw: fix subuser rm command failure
- Fixes: 14375
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 07:52 PM Revision eeae702d (ceph): rgw: fix create bucket error handling
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 07:41 PM Revision 9183d436 (ceph): cmake: test_build_libcephfs needs ${ALLOC_LIBS}
- Signed-off-by: Ali Maredia <amaredia@redhat.com>
- 07:00 PM Revision f7d59c30 (ceph): test: new mock test cases for librbd image refresh state machine
- Specifically tests the ability to dynamically enable/disable RBD
features.
Signed-off-by: Jason Dillaman <dillaman@r... - 07:00 PM Revision f425ed9b (ceph): librbd: close object map when dynamically disabled
- This will handle the case where the object map lock needs to be
released.
Signed-off-by: Jason Dillaman <dillaman@re... - 06:59 PM Revision 5a421838 (ceph): test: correct v1 image format mock expectations
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:38 PM Revision d2c145e6 (ceph): doc :- fixing image in section ERASURE CODING
- Description:- When write is completed successfully and previous chunks of previous version of object is removed - log...
- 06:36 PM Revision 946af50e (ceph): librbd: open object map before journal
- When both object map and journaling are dynamically enabled together,
open object map before the journal to remain co... - 06:32 PM Revision 5b54ed3d (ceph): librbd: correct handling of enabling/disabling dynamic features
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:32 PM Revision 6c7ab5f1 (ceph): rgw: client io shouldn't try to write zero length buffer
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 06:14 PM Backport #14441 (Resolved): hammer: man: document listwatchers cmd in "rados" manpage
- https://github.com/ceph/ceph/pull/7434
- 05:13 PM Documentation #14439 (In Progress): ceph-crush-location manpage missing
- wip branch: https://github.com/ceph/ceph/tree/wip-14439-crush-location-manpage
- 05:10 PM Documentation #14439 (In Progress): ceph-crush-location manpage missing
- The ceph-crush-location utility has no man page, and it needs one.
- 05:01 PM Bug #14438 (Resolved): "FAILED assert(pg->info.history.same_interval_since == p.same_interval_sin...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-20_10:02:02-upgrade:hammer-x-jewel-distro-basic-openst...
- 04:52 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-20_10:02:02-upgrade:hammer-x-jewel-distro-basic-openst...
- 04:40 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
- Run: http://pulpito.ceph.com/teuthology-2016-01-19_17:10:08-upgrade:hammer-x-infernalis-distro-basic-vps/
Jobs: ['33... - 04:30 PM rgw Bug #11419: DragonDisk fails to create directories via S3: MissingContentLength
- Sorry for my late response.
Finally, I were able to figure out what happens:
When connecting nginx to RadosGW via... - 04:28 PM Bug #13971: "test/multi_stress_watch.cc: 61: FAILED assert(!ret)" in rados-hammer-distro-basic-op...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-20_02:00:02-rados-infernalis-distro-basic-openstack/
... - 03:48 PM Revision 87dbf0bf (ceph): include/cpp-btree: add google's cpp-btree library
- From https://github.com/algorithm-ninja/cpp-btree.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:48 PM Revision 23257c32 (ceph): include: add btree_interval_map
- A few small changes to interval_map to deal with the fact that any btree
change invalidates all iterators.
Signed-of... - 03:48 PM Revision 2439bb61 (ceph): ceph_test_rados: clean up std usage
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:48 PM Revision d06d645f (ceph): os/bluestore/FreelistManager: use btree_map instead of map
- btree_map is about twice as memory efficient.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:48 PM Revision 432fa9dd (ceph): os/bluestore/StupidAllocator: use btree_map<> instead of map<>
- btree_map uses about half the memory. According to the cpp-btree docs they
are also faster than STL maps... especial... - 03:48 PM Revision bb9343ea (ceph): include/interval_set: clean up std usage
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:42 PM CephFS Bug #13903 (Fix Under Review): Failure in TestStrays.test_ops_throttle
- 02:41 PM CephFS Bug #13903: Failure in TestStrays.test_ops_throttle
- https://github.com/ceph/ceph/pull/7297
- 02:55 AM CephFS Bug #13903: Failure in TestStrays.test_ops_throttle
- Zheng, please take a look.
- 02:34 PM Revision d74a7c10 (ceph): client: properly trim unlinked inode
- Client should trim inode from its cache when receiving a cap message
with nlink == 0. But the corresponding code has ... - 02:12 PM CephFS Bug #14365: unsafe handle_config_change() methods
- Also, MDSDaemon::handle_conf_change was broken because it was taking mds_lock, when mds_lock is already taken in the ...
- 01:00 PM CephFS Bug #14365: unsafe handle_config_change() methods
- Turns out there's a pre-existing lock cycle issue similar to #14374 here, we just never noticed because live config c...
- 12:58 PM CephFS Bug #14365 (In Progress): unsafe handle_config_change() methods
- 01:18 PM Revision e7420f12 (ceph): Merge pull request #7231 from renhwsky/renhw-wip-14369
- osd: remove unused OSDMap::set_weightf()
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:28 PM rgw Bug #13514: RGW Swift API: response for GET/HEAD on Swift's DLO returns wrong ETag
- Seems the etag on object manifest is the md5sum of an empty string (the content of the manifest)
echo -n '' | md5sum... - 11:43 AM CephFS Bug #14374 (Fix Under Review): MDS asok handlers trigger lock cycle assertion if they take mds_lock
- https://github.com/ceph/ceph/pull/7295
- 11:19 AM Revision 9588efe2 (ceph): mds: Fix lock ordering around asok registration
- Because we acquire mds_lock inside asok handlers,
we must not hold mds_lock while registering our commands.
Fixes: #... - 11:05 AM Revision cbffc3a0 (ceph): vstart: enable lockdep
- Development clusters are the right place to enable
performance-degrading correctness checks.
Signed-off-by: John Spr... - 09:28 AM Revision b041b532 (ceph): BlueStore/StupidAllocator: fix assert
- Fixes: #14436
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 09:22 AM Bug #14436 (Resolved): os/StupidAllocator: wrong assert
- Check void StupidAllocator::unreserve(uint64_t unused)
- 09:02 AM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- One more observation: sometimes there are such records in qemu logs when instance starts hanging:
2016-01-20 10:44... - 08:58 AM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- I also should say it is a very floating issue, meaning it may suddenly appear on one VM and after some time suddenly ...
- 07:50 AM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- Here is it. Hope that will help.
2016-01-20 10:33:47.954001 7fadb64ac700 20 librbd::AioRequest: send_pre 0x56262fd... - 08:37 AM Revision 9a61ac2e (ceph): Merge pull request #7164 from flaf/master
- doc: fix "mon osd down out subtree limit" option name
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:13 AM devops Tasks #10587: split ceph-mon, ceph-osd, and ceph-mds in the Debian and Red Hat packages
- Hi,Ken
Has the split work done for YUM, today when i try to deploy hammer ceph on rhel6, i notice the following err... - 07:19 AM Revision f526716e (ceph): doc: fix "mon osd down out subtree limit" option name
- The name of the parameter `mon osd down out subtree limit`
was incorrect (with `downout` instead of `down out`).
Furt... - 06:57 AM Revision 137d8393 (ceph): pybind/ceph_argparse: update test for "ceph mds setmap"
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:34 AM rgw Feature #14435 (Resolved): add SOCKET_BACKLOG setting in ceph.conf
- i use nginx+radosgw,and with cosbench for test,in one of my case with 2000 workers,a lot of 502 errs was appeared in...
- 06:24 AM Bug #14431: bluestore transaction "make check" is failing on rex004
- Yeah, I ran with...
- 02:36 AM Bug #14431: bluestore transaction "make check" is failing on rex004
- I'll see if I can run it with the same configure setup as the gitbuilders use, but I'm not sure why that would make a...
- 02:36 AM Bug #14431 (Resolved): bluestore transaction "make check" is failing on rex004
- Running against master (commit:dda9a083702e98e77794373f2057c191ce34f771) is failing when I run it locally (git clean ...
- 05:38 AM Revision 0cbc76be (ceph): BlueStore: fix rename logic
- Avoid creating a new destination object in advance, which is unnecessary and less efficient.
Signed-off-by: xie xing... - 05:38 AM Revision 79715522 (ceph): kstore: fix rename logic
- Avoid creating a new destination onode in advance, which is unnecessary and less efficient.
Fixes: #14433
Signed-off... - 05:28 AM Revision a9cd2575 (ceph): doc: rename SubmittingPatches to SubmittingPatches.rst
- for better reading experience
Signed-off-by: Kefu Chai <kchai@redhat.com> - 03:47 AM Revision 8af07586 (ceph): qa/workunits/cephtool/test.sh: update test for "ceph mds setmap"
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 03:28 AM Bug #14433 (Resolved): os/kstore: shall avoid create the destination onode during rename.
- It is OK if the destination object does not exist.
- 02:51 AM Revision 5da1d55c (ceph): Merge pull request #801 from ceph/jewel-14395
- suites/fs: cephfs_journal_tool: wait for health after restart
- 02:49 AM CephFS Bug #14395 (Resolved): cephfs_journal_tool fails
- 02:47 AM Revision 02d15bb4 (ceph): mon/MDSMonitor: Add confirmation to "ceph mds rmfailed"
- Fixes: #14379
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 02:47 AM Revision c200c52f (ceph): Merge branch 'greg-fs-testing'
- 02:46 AM Revision 853ce30f (ceph): Merge branch 'jewel-14395' into greg-fs-testing
- https://github.com/ceph/ceph-qa-suite/pull/801
Reviewed-by: John Spray <john.spray@redhat.com> - 02:40 AM Revision df3c40ea (ceph): Merge pull request #767 from ceph/wip-14048
- tasks: add TestSessionMap.test_[mount|tell]_conn_close
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:24 AM Revision e7107f87 (ceph): Merge pull request #7246 from ukernel/jewel-14377
- ceph_test_libcephfs: tolerate duplicated entries in readdir
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:24 AM CephFS Bug #14377 (Resolved): [ FAILED ] LibCephFS.DirLs
- 02:21 AM Revision 4087d373 (ceph): Merge pull request #680 from ceph/wip-manila
- Add testing for CephFSVolumeClient
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:21 AM Revision f3e58a05 (ceph): Merge pull request #6205 from jcsp/wip-volume-client
- pybind: add ceph_volume_client interface for Manila and similar frameworks
Reviewed-by: Greg Farnum <gfarnum@redhat.... - 02:19 AM Revision defdbeda (ceph): Merge pull request #7229 from david-z/wip-master-fix-failling-to-cache-...
- ceph-fuse: fix double decreasing the count to trim caps
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 02:18 AM Revision 96036217 (ceph): Merge pull request #798 from ceph/jewel-14254
- tasks/cephfs: test for race between cap flush and clientreplay
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:17 AM CephFS Bug #11517 (Resolved): Libcephfs: Doesn't check file's open mode when do read/write
- 02:17 AM Revision 7e0358fa (ceph): Merge pull request #7209 from ukernel/jewel-11517
- client: check if Fh is readable when processing a read
Reviewed-by: Sage Weil <sage@redhat.com> - 02:13 AM Revision c63ee051 (ceph): Merge pull request #7199 from ukernel/jewel-14254
- mds: fix client cap/message replay order on restart
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:13 AM CephFS Bug #14254 (Resolved): failed pjd chown test 117
- 01:25 AM Bug #14263: mon:Re join the Monitor alone to form a cluster when it's rank=0
- thanks
- 12:46 AM Revision e5585bc2 (ceph): Merge pull request #7279 from zaitcev/wip-5073-subuser
- rgw: Parse --subuser better
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 12:26 AM Revision 0880e5ce (ceph): rgw: a few minor cleanups
- delete getop, remove #warnings, add comments
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:14 AM Revision 11913b96 (ceph): WIP x-amz-website-redirect-location.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
Conflicts:
src/rgw/rgw_op.h
src/rgw/rgw_rest.cc
src...
01/19/2016
- 11:58 PM Revision 9bdbb1bb (ceph): S3Website: AmazonS3 changed RedirectAll HTTP response.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 11:33 PM Revision 195ceed0 (ceph): rgw: init_permissions() shouldn't return ENOENT in a specific case
- If op is bucket creation it should ignore ENOENT. Otherwise we should
make sure we return the appropriate error.
Sig... - 10:37 PM Feature #14429 (Resolved): make ceph-test-rados faster
- 10:26 PM Revision 2af2423d (ceph): FileStore: Replace Mutex with RWLock in IndexManager
- Signed-off-by: Evgeniy Firsov <evgeniy.firsov@sandisk.com>
- 10:07 PM Bug #14245 (New): "cluster [ERR] OSD full" in rados-jewel-distro-basic-smithi
- Run: http://pulpito.ceph.com/teuthology-2016-01-16_22:00:08-rados-jewel-distro-basic-smithi/
Jobs: ['31575', '31652'... - 10:06 PM Bug #14289: "No space left on device" + "FAILED assert(0 == "unexpected error")" in rados-inferna...
- Run: http://pulpito.ceph.com/teuthology-2016-01-16_22:00:08-rados-jewel-distro-basic-smithi/
Jobs: ['31554', '31624'... - 10:03 PM Bug #14244: "SELinux denials found" in rados-jewel-distro-basic-smithi
- Run: http://pulpito.ceph.com/teuthology-2016-01-16_22:00:08-rados-jewel-distro-basic-smithi/
Job: ['31673']
- 09:44 PM Revision 65a3fde9 (ceph): Merge remote-tracking branch 'origin/jewel'
- 09:41 PM Revision 727244ea (ceph): Merge remote-tracking branch 'origin/jewel'
- 08:30 PM Bug #14428: Unable to bring up OSD's after dealing with FULL cluster (OSD assert with /include/in...
- OSD logs:
https://api.access.redhat.com/rs/cases/01568711/attachments/1e95eff5-9d88-4ef4-a17b-ef051ea62018
https:... - 08:15 PM Bug #14428 (Resolved): Unable to bring up OSD's after dealing with FULL cluster (OSD assert with ...
- Cluster is running 94.5 Hammer. Cache tiering backed with replicated pool. This cluster is comprised of six nodes. T...
- 08:09 PM Revision 4ed95cc9 (ceph): test: use RBD v1 format when features not specified
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 07:48 PM Revision 750f162a (ceph): update copyright
- 07:44 PM Revision 976b80d1 (ceph): Merge pull request #678 from ceph/wip-fs-snaptests
- suites/fs: enable all snapshost test scripts
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:42 PM CephFS Feature #14427 (Resolved): qa: run snapshot tests under thrashing
- We run snapshot tests in their own subsuite right now to verify they keep functioning, but we do not test them under ...
- 07:41 PM CephFS Bug #10436: ceph-fuse: snapshot flushing from page cache to Client is not coherent
- Once this is fixed we need to re-enable snaptest-snap-rm-cmp.sh in the snaptests.yaml qa-suite config fragment.
- 07:39 PM CephFS Feature #3819 (Resolved): mds: re-add snaptests to qa suite
- https://github.com/ceph/ceph-qa-suite/pull/678
- 07:38 PM Revision ea3fd2e5 (ceph): Merge pull request #6496 from ceph/wip-fs-snaptests
- qa/workunits/snaps: move snap tests into fs sub-directory
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:37 PM Revision b3cb68bc (ceph): Merge pull request #6868 from H3C/wip-11642-cephfuse-useage
- ceph-fuse:print usage information when no parameter specified
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:34 PM CephFS Bug #13903: Failure in TestStrays.test_ops_throttle
- http://qa-proxy.ceph.com/teuthology/gregf-2016-01-18_19:56:11-fs-greg-fs-speculative-118---basic-mira/32912/
- 07:01 PM Revision 5f61d36d (ceph): Merge remote-tracking branch 'origin/master' into wip-rgw-static-websit...
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/global/Makefile.am
src/rgw/rgw_common.cc
src/rgw/r... - 06:58 PM devops Bug #14426 (Rejected): configure timezones to a uniform state
- See #14425 and #14399. Some of the machines are not running on the same timezones, and we need to fix them up.
- 06:50 PM Bug #14409 (Rejected): "ceph mds stat -fjson" always shows empty stopped list
- MDSes only go into the STOPPED state when you run the deactivate command. You probably haven't run this unless you're...
- 02:00 PM Bug #14409 (Rejected): "ceph mds stat -fjson" always shows empty stopped list
- Regardless of how many ceph MDS servers are running or not running the
output of "ceph mds stat -fjson" always has ... - 06:43 PM Revision 5e8325cd (ceph): librbd: hide object map lock/unlock behind open/close
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:31 PM Bug #14423: Segmentation fault in rados-hammer-distro-basic-mira
- Master and infernalis need both the proxy_write and proxy_read loops fixed. Hammer, just the proxy_read.
Testing:... - 06:21 PM Bug #14423: Segmentation fault in rados-hammer-distro-basic-mira
- Simple bug in the loop calling cancel_proxy_read, similar bug in master (also on proxy_write).
- 04:26 PM Bug #14423 (Resolved): Segmentation fault in rados-hammer-distro-basic-mira
- Run: http://pulpito.ceph.com/teuthology-2016-01-18_09:00:08-rados-hammer-distro-basic-mira/
Job: 32542
Logs: http:/... - 06:26 PM Revision 2c1576bb (ceph): ReplicatedPG::process_copy_chunk: fix invalid list traversal for proxy_...
- Fixes: 14423
Backport: infernalis, hammer
Signed-off-by: Samuel Just <sjust@redhat.com> - 06:26 PM Revision 97ed425f (ceph): ReplicatedPG::process_copy_chunk: fix invalid list traversal for proxy_...
- Fixes: 14423
Backport: infernalis
Signed-off-by: Samuel Just <sjust@redhat.com> - 06:20 PM Revision e38f390d (ceph): Merge pull request #7270 from cbodley/wip-cmake-execinfo
- cmake: add missing check for HAVE_EXECINFO_H
- 05:55 PM Revision 96087e26 (ceph): Merge pull request #7280 from zaitcev/wip-5073-update2
- rgw: Drop a debugging message
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:49 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- Kefu,
This took a little more time because some of the hardware I was using for this test needed to be repurposed ... - 05:46 PM Revision 11782713 (ceph): rgw: remove split formatter code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:44 PM Bug #14399: "ReplicatedPG.cc: 10483: FAILED assert(obc)" in rados-hammer-distro-basic-mira
- Per chat in IRC with Sam "simplest solution in the short term would be to fix the miras to be on the same timezone" a...
- 04:14 PM Bug #14399: "ReplicatedPG.cc: 10483: FAILED assert(obc)" in rados-hammer-distro-basic-mira
- More in run:
http://pulpito.ceph.com/teuthology-2016-01-18_09:00:08-rados-hammer-distro-basic-mira/
Jobs: ['32573',... - 05:01 PM Revision 7dd9af0a (ceph): init-ceph.in: skip ceph-disk if it is not present
- With the ceph-mon vs ceph-osd split packaging, users are expected to
have the ceph-mon package installed and not ceph... - 04:56 PM Revision a51fbf2d (ceph): rgw: Parse --subuser better
- This fixes a funny message "ERROR: 'tenant$user != tenant$user'"
in case --subuser='tenant$user' is supplied.
Signed... - 04:53 PM Revision e1536234 (ceph): rgw: Drop a debugging message
- A P3-tagged message escaped upstream.
Signed-off-by: Pete Zaitcev <zaitcev@redhat.com> - 04:35 PM Revision f5da1594 (ceph): makefile: remove dependency on libedit
- turns out we are not using it anymore
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:08 PM rbd Subtask #14421 (Resolved): Propagate image deletes from remote pool to local pool
- If a mirrored image was deleted in a remote peer's pool, the RBD mirroring daemon should also delete the image in the...
- 04:05 PM rbd Subtask #14412 (In Progress): Track epoch and period for mirrored images
- 03:22 PM rbd Subtask #14412 (Resolved): Track epoch and period for mirrored images
- Epoch is incremented whenever the exclusive lock is acquired and period is incremented (or could also perhaps be a UU...
- 04:05 PM rbd Subtask #14420 (Resolved): New RBD notification pool object for recording mirroring errors
- There are multiple possible failures that could occur during runtime with mirroring. There needs to be a way to aler...
- 04:00 PM rbd Subtask #14419 (Resolved): RBD mirroring settings should be moved to new pool object
- The current 'rbd_pool_settings' object which holds whether or not mirroring is enabled for the pool (and its peers) s...
- 03:59 PM Revision a9addc61 (ceph): mon: Go into ERR state if multiple PGs are stuck inactive
- If >=X PGs are stuck inactive longer than 'mon_pg_stuck_threshold'
we go into ERR state.
This is useful for situatio... - 03:56 PM rbd Subtask #14418 (New): rbd-mirror multi-peer: cleanly transition alive peers to new period
- If a new period has to be started due to loss of communication with the previous epoch owner, attempt to register the...
- 03:54 PM rbd Subtask #14414 (New): Add new "exclusive lock released" journal event to librbd
- 03:44 PM rbd Subtask #14414 (Closed): Add new "exclusive lock released" journal event to librbd
- 03:28 PM rbd Subtask #14414 (Closed): Add new "exclusive lock released" journal event to librbd
- This event will track the clean shutdown and transition of lock ownership (potentially between different clusters).
- 03:40 PM rbd Subtask #14417 (Resolved): Interlock RBD mirroring daemon and acquiring exclusive lock
- If a local librbd client attempts to acquire the exclusive lock when the previous epoch was owned by a different clus...
- 03:37 PM Feature #14416 (New): Write software version to data store after successful start
- Right now you can't tell for sure with which code version a daemon was running if you happen to loose the boot/OS dis...
- 03:30 PM rbd Subtask #14415 (Resolved): Pull journal events from remote peer to local journal
- The RBD mirroring daemon should fetch events from remote journals in monotonically increasing epoch order.
- 03:26 PM rbd Subtask #14413 (Resolved): Pull full image from remote peer when out-of-sync
- When the local image doesn't exist, RBD mirroring daemon should register as a client on the remote image's journal, s...
- 03:18 PM Revision 4f4017ef (ceph): Increase verbosity level on RGWObjManifest line
- My RadosGW log is filling with lines starting with RGWObjManifest::operator++() result: with debug at 0. I believe th...
- 03:15 PM Feature #14411 (Resolved): fix lost-unfound
- The version in master is problematic because the log message can race with a client update messing up the log segment...
- 03:13 PM rbd Feature #14410 (Resolved): snapshots need to support internal vs external use cases
- When copying an initial image to a remote cluster, the rbd mirroring daemon will need to take a snapshot after regist...
- 03:01 PM CephFS Bug #14255: qa: we are filling smithi disks with ffsb workloads
- ffsb (config is at qa/workunits/suites/random_write.32.ffsb) only use about 13G space, no matter how long it runs. I ...
- 02:02 AM CephFS Bug #14255: qa: we are filling smithi disks with ffsb workloads
- I haven't looked yet but I suspect we're just running for a set period of time and the smithis are so much faster tha...
- 02:56 PM Bug #14390: make error
- I saw a recommendation to run "make clean" in src/rocksdb folder.
Haven't tried it though.
Another option that wo... - 02:36 PM rbd Feature #14006 (Resolved): Track IO dependencies in journal
- 02:18 PM Feature #13942: ceph-disk: support bluestore
- Rebase to master complete, make check passes, working on ceph-disk suite problems now.
- 01:42 PM rgw Bug #14105 (Need More Info): adminops subuser specify S3 keys
- 11:47 AM Revision 44f78d84 (ceph): Merge pull request #7274 from dillaman/wip-helgrind-race-jewel
- helgrind: additional race conditionslibrbd: journal replay should honor inter-event dependencies
Reviewed-by: Josh D... - 11:37 AM Feature #13923 (Fix Under Review): Set health to ERR when one or more PGs is stuck inactive
- master PR: https://github.com/ceph/ceph/pull/7253
- 11:32 AM Revision eb17b8fa (ceph): BlueStore: fix typo
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:32 AM Revision 696584cf (ceph): BlueStore: fix dest onode process logic of clone_range
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:32 AM Revision 1c70f863 (ceph): BlueStore: fix dest onode process logic of clone
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:32 AM Revision fde0f029 (ceph): BlueStore: fix nid overwritten of write/zero
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:32 AM Revision 1fc9edfe (ceph): kstore: fix typo
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:32 AM Revision 6375870a (ceph): kstore: fix fsid validation logic during mkfs
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:31 AM Revision 9ab7998f (ceph): kstore: fix dest onode process logic of clone_range
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:31 AM Revision 7ce6d068 (ceph): kstore: fix dest onode process logic of clone
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:31 AM Revision 8065b8ab (ceph): kstore: fix nid overwritten of write/zero
- Fixes: #14407
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 10:05 AM Revision d03146d0 (ceph): os/bluestore/BlueStore: Removing dead code
- This assignement of r is misleading. It does assign a value to r that is never
used by any code.
When the code runs ... - 10:05 AM Revision 6a23b23c (ceph): os/filestore/FileJournal: Removing dead code
- Despite read_pos & last_committed_seq, the seq variable is local and created a
few lines before.
While the reinitili... - 10:05 AM Revision b3f7d02a (ceph): osd/OSD: Simplifying 'r' usage
- The r variable was created unassigned and lately assigned to -1.
Even if r is always defined before its usage, sounds... - 10:05 AM Revision 858f6068 (ceph): mon/PGMonitor: Removing dead code
- The assignation of head is useless as its never used after.
This patch simply remove dead/useless code.
Signed-off-b... - 10:05 AM Revision 39a5d978 (ceph): mon/MDSMonitor: Removing dead code
- The poolid variable is assigned just before returning ENOENT but this value is
never used.
This patch just remove de... - 10:05 AM Revision 1f21322f (ceph): mon/ConfigKeyService: Removing dead code
- This part of the code is setting up the ret variable just before returning
false. This code have no effect.
This pat... - 10:05 AM Revision fcac028d (ceph): os/bluestore/BlueStore: Simplifying default return value
- r variable wasn't initialized but set to 0 twice. Once just before an early
"goto out" code and the other before the ... - 09:50 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Zheng Yan wrote:
> yes, I'm not familiar with cgroup, But I think it accounts memory used by IO requests. Could you ... - 09:25 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Stephan Wienczny wrote:
> I can't say anything about 4.2. The first version we tested was 4.3.x. Have there been cha... - 08:45 AM CephFS Bug #14357 (Resolved): Delay in clientreplay on quiet clusters
- 08:44 AM Bug #14408 (Closed): kstore/bluestore: potential data lost
- 08:02 AM Bug #14408 (Closed): kstore/bluestore: potential data lost
- See int KStore::_write etc.
- 08:01 AM Bug #14405 (Fix Under Review): ceph-mon process crash when wrong message type in ceph.conf
- 05:43 AM Bug #14405: ceph-mon process crash when wrong message type in ceph.conf
- bo cai wrote:
> I have pull a git request for this:
>
> https://github.com/ceph/ceph/pull/7212
sorry, it's
http... - 05:42 AM Bug #14405: ceph-mon process crash when wrong message type in ceph.conf
- I have pull a git request for this:
https://github.com/ceph/ceph/pull/7212 - 02:44 AM Bug #14405 (Resolved): ceph-mon process crash when wrong message type in ceph.conf
- # I set a wrong message type in my ceph.conf
cat /etc/ceph/ceph.conf
[global]
fsid = b4c0f945-f80a-4092-b059-d7b7b... - 08:00 AM Bug #14407 (Resolved): kstore/bluestore: potential data lost
- Check int KStore::_write etc
- 07:35 AM Revision dece3be5 (ceph): Add error check for object_map->sync()
- There lacks error check after doing object_map->sync under
sync_entry, which is OK when omap deployed in the same dev... - 07:15 AM Feature #13578: a script to self-check the installation of monitor/OSD
- One more point we can add here we do not recommend any type of RAID for OSD or Journal disk.
- 05:47 AM Bug #14406 (Can't reproduce): osd aborted when try to decode osdmap with 0 bytes
- Our ceph cluster(v0.94.5) configured with cache tier + erasure code pool,
and when we adjust the osd weight by "ceph... - 02:56 AM Revision 3995b1c1 (ceph): mon/MonClient: avoid null pointer error when configured incorrectly
- fix: #14405
Signed-off-by: Bo Cai <cai.bo@h3c.com> - 01:56 AM Revision d26f2ed1 (ceph): suites/fs: fix ceph.restart syntax
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 01:46 AM Revision 4051bc2a (ceph): Merge pull request #7252 from ceph/wip-13483-hammer
- qa: remove legacy OS support from rbd/qemu-iotests
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:43 AM Revision bd56e170 (ceph): OSDService: Fix typo in osdmap comment
- Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
- 12:43 AM Bug #14178 (Resolved): KeyValueStore: fd leak during mount
- https://github.com/xiexingguo/ceph/commit/c198155cdf984fa32a9bc896cb29ae061b853918
- 12:42 AM Bug #14176 (Resolved): KeyValueStore: wrongly placed dump_open_fds() logic
- https://github.com/xiexingguo/ceph/commit/9fe0ddef6746b5d387780e8a51b0d46d9e2389c1
- 12:14 AM Revision 3b3d484a (ceph): Merge remote-tracking branch 'origin/wip-14195' into greg-fs-testing
- https://github.com/ceph/ceph-qa-suite/pull/791
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:06 AM Revision afbc90b9 (ceph): Merge remote-tracking branch 'origin/wip-full-msg' into greg-fs-testing
- https://github.com/ceph/ceph-qa-suite/pull/786
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:06 AM Revision 4169ca94 (ceph): Merge remote-tracking branch 'origin/wip-global-config' into greg-fs-te...
- https://github.com/ceph/ceph-qa-suite/pull/784
Conflicts:
tasks/cephfs/vstart_runner.py
Signed-off-by: Greg Farnum ...
01/18/2016
- 11:53 PM Revision 0e9b07f0 (ceph): Merge remote-tracking branch 'origin/wip-14048' into greg-fs-testing
- https://github.com/ceph/ceph-qa-suite/pull/767
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:30 PM rgw Bug #13635: radosgw duplicate email address
- Matt Benjamin wrote:
> This issue was addressed by Ceph upstream commit c227316 by Dunrong Huang ("rgw: add a new er... - 11:29 PM rgw Bug #13635 (Fix Under Review): radosgw duplicate email address
- This issue was addressed by Ceph upstream commit c227316 by Dunrong Huang ("rgw: add a new error code for email confl...
- 11:23 PM Bug #14400: Snappy decompressor may assert when handling segmented input bufferlist
- PR is at
https://github.com/ceph/ceph/pull/7268 - 06:01 PM Bug #14400: Snappy decompressor may assert when handling segmented input bufferlist
- Here is a backtrace for the assert:
common/buffer.cc: In function 'const char* ceph::buffer::ptr::c_str() const' t... - 05:46 PM Bug #14400 (Resolved): Snappy decompressor may assert when handling segmented input bufferlist
- The issue may occur when the first data segment in an input bufferlist for SnappyCompressor::decompress call is less ...
- 11:18 PM rbd Bug #14385 (Resolved): qemu-iotests: test case 055 repeatedly fails on CentOS 7
- 09:00 PM rbd Bug #14385 (Fix Under Review): qemu-iotests: test case 055 repeatedly fails on CentOS 7
- *jewel PR*: https://github.com/ceph/ceph/pull/7272
- 08:52 PM rbd Bug #14385: qemu-iotests: test case 055 repeatedly fails on CentOS 7
- qemu-kvm on CentOS 7 doesn't support commands like 'drive-backup' -- disable test 055.
- 07:22 PM rbd Bug #14385 (In Progress): qemu-iotests: test case 055 repeatedly fails on CentOS 7
- 11:15 PM Revision 326eb4c8 (ceph): tests: fix pybind path for RBD unit tests
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:53 PM Revision 1aa674c2 (ceph): librbd: missing lock on state transition
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:52 PM Revision 1215a1a9 (ceph): helgrind: annotate false-positive race conditions
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:42 PM Revision 10d9fe1d (ceph): Merge remote-tracking branch 'origin/wip-manila' into greg-fs-testing
- https://github.com/ceph/ceph-qa-suite/pull/680
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:39 PM Revision e4d3e9b2 (ceph): qa: disable rbd/qemu-iotests test case 055 on RHEL/CentOS
- Fixes: #14385
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 10:39 PM Revision f7acd44c (ceph): qa: remove legacy OS support from rbd/qemu-iotests
- RHEL7 derivatives were failing test 002 since they were using
legacy test cases for now unsupported OSes.
Fixes: #13... - 10:33 PM Revision 617d8cce (ceph): Merge remote-tracking branch 'origin/jewel-14254' into greg-fs-testing
- https://github.com/ceph/ceph-qa-suite/pull/798
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:30 PM Revision 2208e828 (ceph): Merge pull request #7272 from dillaman/wip-14385-jewel
- qa: disable rbd/qemu-iotests test case 055 on RHEL/CentOSlibrbd: journal replay should honor inter-event dependencies...
- 10:12 PM Revision b577f891 (ceph): Merge pull request #803 from ceph/wip-rbd-nbd-jewel
- rbd: rbd-nbd can only run on Ubuntu
librbd: journal replay should honor inter-event dependencies
Reviewed-by: Josh D... - 10:09 PM Revision dda9a083 (ceph): Merge pull request #7019 from dillaman/wip-14006
- librbd: journal replay should honor inter-event dependencies
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:05 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- Also in run:
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-01-16_11:18:01-upgrade:firefly-hammer-x-infernal... - 09:48 PM Bug #13511: core dump during osd start
- Yuri Weinstein wrote:
> Seems similar in ceph version 0.94.5
> Run: http://pulpito.ceph.com/teuthology-2016-01-16_0... - 08:54 PM Bug #13511: core dump during osd start
- Seems similar in ceph version 0.94.5
Run: http://pulpito.ceph.com/teuthology-2016-01-16_09:00:08-rados-hammer-distro... - 09:34 PM Revision 30e08957 (ceph): rbd: rbd-nbd can only run on Ubuntu
- NBD support is not available in RHEL/CentOS 7
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 09:32 PM Revision 2cde7042 (ceph): Merge pull request #802 from ceph/wip-whitelist-jewel
- Whitelisted 'wrongly marked me down'
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:25 PM Revision 05c678bd (ceph): Whitelisted 'wrongly marked me down'
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 09:13 PM rgw Bug #13598: radosgw-admin: inconsistency in uid/email handling
- Pushed PR #7273 addressing the material issues here, as discussed on #ceph-devel.
That is, it seems that
1. email... - 09:10 PM Feature #12038 (Pending Backport): make rgw_fronends more forgiving of whitespace
- 08:58 PM Revision bb4d7a72 (ceph): qa: disable rbd/qemu-iotests test case 055 on RHEL/CentOS
- Fixes: #14385
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 08:57 PM Bug #14372 (Rejected): ENOTSUPP on trimtrunc (EC with cache pool on top)
- Oh, I misread. CephFS doesn't function on top of uncached EC pools at all and won't for a long time.
- 08:52 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- Sorry for the misunderstanding but we do not use caching on any pool at the moment.
- 08:50 PM Bug #14372 (New): ENOTSUPP on trimtrunc (EC with cache pool on top)
- Looking at this log we're getting EOPNOTSUPP (Operation not supported) on a trimtrunc command. That is apparently not...
- 02:34 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- After fixing the inconsistent PG, I notice the the single defective object was one from a RBD device et that after de...
- 08:39 PM CephFS Bug #14365: unsafe handle_config_change() methods
- I think these should be okay, but it's easy to fix. John, can you establish that we don't need locks or else set them...
- 08:33 PM devops Bug #14402 (Resolved): ceph init script unconditionally sources /lib/lsb/init-functions
- In Hammer, the ceph init script unconditionally sources the @/lib/lsb/init-functions@ file. This is a problem because...
- 07:13 PM Revision 4c9345bb (ceph): cmake: add missing check for HAVE_EXECINFO_H
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:11 PM Bug #14397 (Pending Backport): disable filestore_xfs_extsize by default
- 03:32 PM Bug #14397 (Fix Under Review): disable filestore_xfs_extsize by default
- PR for master: https://github.com/ceph/ceph/pull/7265
- 03:24 PM Bug #14397 (Resolved): disable filestore_xfs_extsize by default
- _Description of problem:_
filestore_xfs_extsize defaults to "true" in Hammer. This option is designed to reduce frag... - 07:11 PM Revision 7537ac89 (ceph): Merge pull request #7265 from ceph/wip-14397-disable-xfs-extsize
- osd: disable filestore_xfs_extsize by default
Reviewed-by: Sage Weil <sage@redhat.com> - 06:24 PM Revision 887fbe1c (ceph): Fixes #14400 + some refactoring to avoid input buffer modification in f...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 05:50 PM Revision ccd65d27 (ceph): os/memstore: no magic len=0 to fiemap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:44 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- Steve,
seems the monitor is sending erroneous pg-create messages to osd after the PGs in question have already bee... - 03:08 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- the osd crashed when it was handling a pg_create message, it walked through the prior epochs looking for the acting s...
- 05:40 PM Revision 3c4eddb5 (ceph): os/kstore: no magic len=0 to fiemap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:40 PM Revision d794be4a (ceph): os/bluestore: no magic len=0 to fiemap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:39 PM Revision f9019a44 (ceph): ceph_test_objectstore: do not pass len=0 to fiemap
- Not all backends do this.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:39 PM Bug #14399 (Duplicate): "ReplicatedPG.cc: 10483: FAILED assert(obc)" in rados-hammer-distro-basic...
- Run: http://pulpito.ceph.com/teuthology-2016-01-17_09:00:09-rados-hammer-distro-basic-mira/
Jobs: ['31875', '31914']... - 04:50 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- I can't say anything about 4.2. The first version we tested was 4.3.x. Have there been changes in memory mangement be...
- 02:36 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- this problem seems related to memory allocation. could you try enlarging memory for these container.
- 02:25 PM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- Stephan Wienczny wrote:
> The problem was introduced between Coreos 899.1.0 and 926.0.0
do you mean there is no p... - 11:51 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- I checked the kernel build config and it already is compiled with "Compile the kernel with frame pointers".
The dump... - 09:43 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- ceph_send_cap_releases() never calls mutex_lock(). ceph_encode_locks_to_buffer() never calls ceph_put_wrbuffer_cap_re...
- 03:26 PM Revision aed85775 (ceph): osd: disable filestore_xfs_extsize by default
- This option involves a tradeoff: When disabled, fragmentation is worse,
but large sequential writes are faster. When ... - 02:55 PM Revision 32861063 (ceph): os/kstore: fix u64 decode checks
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 PM Revision f8ea3eb6 (ceph): Merge branch 'wip-bluestore'
- 02:52 PM Revision 1590b082 (ceph): os/bluestore: fix _key_decode_u64 error checks
- The data that follows may be binary encoded and null.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:32 PM Revision 92a5d1d4 (ceph): os/bluestore/FreelistManager: switch to std::mutex
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:28 PM Revision e0ca20b0 (ceph): Merge pull request #7211 from cxwshawn/clean-fix
- osd: ReplicatedPG: clean up unused function
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:27 PM Revision 453fdd9a (ceph): Merge pull request #7158 from yuyuyu101/wip-async-cleanup-deleted
- msg/async: cleanup dead connection and misc things
- 02:27 PM Messengers Bug #13985 (Resolved): Messenger: large message data content length cause int overflow
- 02:26 PM Revision e6884bb3 (ceph): Merge pull request #6809 from yuyuyu101/wip-13985
- msgr: fix large message data content length causing overflow
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:26 PM Revision 86d47bdd (ceph): Merge pull request #7047 from xiexingguo/xxg-wip-14176
- osd: KeyValueStore: fix wrongly placed assert
Reviewed-by: David Zafman <dzafman@redhat.com> - 02:25 PM Revision f0475a37 (ceph): Merge pull request #7142 from xiexingguo/xxg-wip-crush
- crushtool: improve usage/tip messages
Reviewed-by: Sage Weil <sage@redhat.com> - 02:24 PM Revision 7621a69e (ceph): Merge pull request #7203 from branch-predictor/bp-use-faster-is-zero
- osd: use optimized is_zero in object_stat_sum_t.is_zero()
Reviewed-by: Sage Weil <sage@redhat.com> - 02:23 PM Revision ae6c659b (ceph): Merge pull request #7169 from trociny/fix-bluestore-without-aio
- osd: bluestore: don't include when building without libaio
Reviewed-by: Sage Weil <sage@redhat.com> - 01:47 PM Bug #14263: mon:Re join the Monitor alone to form a cluster when it's rank=0
- if you only have one monitor, the simplest way is to rely on 'mon host' and 'mon initial members' only. No need to ru...
- 02:14 AM Bug #14263: mon:Re join the Monitor alone to form a cluster when it's rank=0
- @Joao Luis
thank for you attention
this way for cluster has existed more than two mon is(And mon is normal), but ... - 12:46 PM Revision 507774a9 (ceph): common/buffer: replace RWLock with spinlocks
- This decreases buffer::raw size by about 100 bytes (since RWLock occupies
104 bytes and simple_spinlock_t just 4) and... - 11:20 AM Revision b4bd72f2 (ceph): BlueStore: drain wal_wq first if we exit from mounting due to wal_repla...
- Because maybe we are in the middle of wal_replay and some wal transaction is already in process.
Signed-off-by: xie ... - 10:56 AM Revision aa28b58d (ceph): vstart: update help with a few more switches
- Add the `bluestore`, `memstore` and `cache` tier options to the vstart
help
Signed-off-by: Abhishek Lekshmanan <abhi... - 10:17 AM Linux kernel client Bug #14232: Kernel NULL pointer dereference in __dcache_readdir
- The patch list has grown rather long. If there have been any changes/fixes in dcache, I don't have them included. Wit...
- 09:54 AM Linux kernel client Bug #14232: Kernel NULL pointer dereference in __dcache_readdir
- Sorry for the delay, please upload your patches (which are applied to 4.1.15 kernel). If you can, please take 4.4 ker...
- 09:15 AM Bug #14390: make error
- its because the src/rocksdb/* too old ,the autogen.sh did not update the software.is there a bug?
- 08:44 AM rgw Bug #14382: Remove bucket,data and usage Not cleared
- I think this is a serious problem.
Set a quota, data and usage can not be cleared,Will cause Quota Exceeded.Users ca... - 08:33 AM Revision 5183ff3d (ceph): BlueStore: verify fsid in a more proper way during mkfs
- Fixes: #14394
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 08:26 AM CephFS Bug #14395 (Fix Under Review): cephfs_journal_tool fails
- https://github.com/ceph/ceph-qa-suite/pull/801
- 08:21 AM CephFS Bug #14395 (Resolved): cephfs_journal_tool fails
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-01-13_14:03:02-fs-jewel---basic-smithi/28198/teuthology.log
<p... - 08:22 AM Revision 67c00337 (ceph): suites/fs: cephfs_journal_tool: wait for health after restart
- Fixes: #14395
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 08:09 AM Bug #14394 (Resolved): BlueStore: shall verify fsid in a more proper way during mkfs
- Check int BlueStore::mkfs()
- 07:32 AM Revision f021f5a4 (ceph): tools: fix pool alignment API overflow issue
- The original APIs may overflow and are replaced by 1f855456cae96c91a67c169d2333e333c3b59671.
Signed-off-by: xie xingg... - 07:32 AM Revision 29a7d687 (ceph): tests: update pool alignment API
- The old ones are obsolete.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 07:30 AM Revision 8aa068d4 (ceph): librados: fix rados_ioctx_pool_requires_alignment2()
- we can not cast an "int *" pointer to a "bool *" and assign a bool
to it in hope to update the integer pointed by the... - 07:14 AM Revision 5ff452bb (ceph): BlueStore: negative return code if we unable to open path
- Because the caller is unable to catch a positive error code.
Fixes: #14393
Signed-off-by: xie xingguo <xie.xingguo@z... - 07:10 AM Bug #14393 (Resolved): BlueStore: shall return negative error code if unable to write lable
- See int BlueStore::_write_bdev_label
- 07:06 AM CephFS Bug #14380 (Fix Under Review): "ceph mds setmap" crashes mon on invalid input
- https://github.com/ceph/ceph/pull/7262
- 07:00 AM Revision fc3554e3 (ceph): mon/MDSMonitor: Add confirmation to "ceph mds setmap"
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:25 AM Revision b4023a46 (ceph): mon/MDSMonitor: handle invalid input for "ceph mds setmap"
- Fixes: #14380
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 05:45 AM rbd Feature #14264 (Fix Under Review): async rbd_open() option
- 05:25 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. rgw...
- 05:23 AM rgw Bug #14375: subuser rm fails with status 125
- Could it be a regression introduced by https://github.com/ceph/ceph/pull/6002/files ?
- 05:15 AM rgw Bug #14375: subuser rm fails with status 125
- Also happened on hammer this week-end ( see http://pulpito.ceph.com/loic-2016-01-12_13:56:55-rgw-hammer-backports---b...
- 04:31 AM Revision ce855821 (ceph): configure: detect new gperftool
- this is a follow-up of 6edaf4e, when tcmalloc is enabled,
perfglue/heap_profiler.cc is also compiled, it includes the... - 04:31 AM Revision 865ee53c (ceph): unittest_ipaddr: fix compile warnings
- silence warnings like
warning: test/test_ipaddr.cc:174:16: deprecated conversion from string
constant to char* [-Ww... - 04:31 AM Revision 055fcaac (ceph): erasure-code: create an internal isa lib for testing
- we were linking against a '--module' shared library using its
.la file, which is not portable on some platforms accro... - 04:31 AM Revision 1e426be0 (ceph): fsx: fix signed/unsigned comparison warnings
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:31 AM Revision d54a747c (ceph): kv/RocksDBStore: replace deprecated calls
- rocksdb::DB::CompactRange(Slice*, Slice*) is deprecated, so replace
it with its equivalent.
Signed-off-by: Kefu Chai... - 04:31 AM Revision 3b5e940b (ceph): os/bluestore: fix signed/unsigned comparison warnings
- Signed-off-by: Kefu Chai <kchai@redhat.com>
01/17/2016
- 11:47 PM Bug #14244: "SELinux denials found" in rados-jewel-distro-basic-smithi
- More in rgw run:
http://pulpito.ceph.com/teuthology-2016-01-13_13:02:01-rgw-jewel-distro-basic-smithi/
Jobs: 28068,... - 09:36 PM rbd Feature #14264: async rbd_open() option
- https://github.com/ceph/ceph/pull/7259
- 02:13 PM Revision a671448f (ceph): BlueStore: improve wal_replay logic a little bit
- Fixes: #14392
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:12 PM Revision 167bea5a (ceph): kstore: add metadata "type" to disk
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:11 PM Revision dea2d92d (ceph): BlueStore: fix fd leak during error fsck scan
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:11 PM Revision b04f1e2b (ceph): BlueStore: update obsolete content of comment
- Which does not match the reality anymore.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:11 PM Revision 475d97fc (ceph): BlueStore: remove reap_cond
- It has no consumers at present.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:11 PM Revision cb56320f (ceph): kstore: remove reap_cond
- It has no consumers at present.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:11 PM Revision e773794d (ceph): MemStore: remove apply_lock
- It doesn't block anything other than the umount caller itself.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:11 PM Revision 8b30f9d6 (ceph): MemStore: drain finisher first during umount
- Otherwise some caller specified contexts may be left hanging.
Fixes: #14370
Signed-off-by: xie xingguo <xie.xingguo@... - 01:56 PM Bug #14392 (Resolved): BlueStore: improve wal_transaction replay logic
- See BlueStore::_wal_replay()
01/16/2016
- 07:58 AM Bug #14390 (Resolved): make error
- when i pull the newest master branch and make, it was interrupted and prompt me :
libos.alibos.a(libos_a-BlueStore... - 04:49 AM Messengers Bug #14386 (Fix Under Review): async messenger segfault
- https://github.com/ceph/ceph/pull/7255
- 04:46 AM Revision 9cacdf1b (ceph): AsyncConnection: Dont send message when local connection is closed
- Fix: #14386
Signed-off-by: Haomai Wang <haomai@xsky.com> - 04:37 AM Revision 0771efaf (ceph): AsyncConnection: Fix leak event
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:56 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
- In 4.4.0 this looks a like bit different:...
- 12:59 AM Revision a9c5f99f (ceph): organizationmap: modify org mail info.
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 12:37 AM Revision e7631ef3 (ceph): common: change the type of counter total/unhealthy_workers
- Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
01/15/2016
- 11:05 PM Revision d74d9648 (ceph): Undo constant renaming: RGW_REST_*->RGW_PROTO_*.
- For clarity, RGW_REST_* should be renamed to RGW_PROTO_* in future.
For now, undo it to ease the merging speed for s... - 11:05 PM Revision e5607c07 (ceph): undo: clean up dead enum RGWEndpointType.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 11:05 PM Revision 981e1087 (ceph): cleanup: remove dead function.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 11:05 PM Revision 44c5d0cf (ceph): Copyright: add copyright blocks to new files, and update files with exi...
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 11:05 PM Revision 16687965 (ceph): s3website: update cmake.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 11:05 PM Revision c1456508 (ceph): Revert "common/*Formatters: Split Formatters"
- This reverts commit 2b21e3c595c23f409485b8c391d1bd579b13b8e7.
Conflicts:
src/common/Formatter.cc
src/common/JSONFo... - 10:50 PM devops Bug #14387 (Rejected): fabfile: does install_git still need to compile from source?
- we needed a new version in the past; do we still?
- 06:21 PM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- The logs only cover 04:49:13.858469 (when qemu-kvm first opened the device) to 04:49:59.784578. In these logs, there...
- 03:58 PM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- You are telling that blocked IO will resume after 30 seconds - how can I decrease that timeout?
And also I was tryin... - 03:42 PM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- Jason, qemu-kvm process was alive all the time, but when snapshot taking became stuck - VM completely lost its disk.
... - 06:03 PM Messengers Bug #14386 (Resolved): async messenger segfault
- /a/samuelj-2016-01-11_07:31:49-rados-master-distro-basic-smithi/23853/remote
- 05:14 PM rbd Bug #14385 (Resolved): qemu-iotests: test case 055 repeatedly fails on CentOS 7
- http://qa-proxy.ceph.com/teuthology/jdillaman-2016-01-13_17:39:05-rbd-wip-14006---basic-multi/30215/teuthology.log
h... - 05:12 PM Bug #12577: Inconsistent PGs that ceph pg repair does not fix
- I'd need to apply this on Firefly 0.80.11, is there a hash or branch for the backported Hammer version?
- 04:54 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
- one more: http://qa-proxy.ceph.com/teuthology/teuthology-2016-01-14_17:10:01-upgrade:hammer-x-infernalis-distro-basic...
- 04:48 PM Revision 4a2351eb (ceph): doc: amend the rados.8
- explain the run-name in more details.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:46 PM Documentation #12899 (Resolved): Update the 'rados' command "man" page
- 04:45 PM Revision 3daf908b (ceph): Merge pull request #5900 from ritz303/wip-doc-12899
- doc: Updated the rados command man page to include the --run-name opt…
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:11 PM Bug #14093: scripts/ceph-release-notes does not handle merge description
- can you give a particular example.. it shouldn't be very hard to do.. but need to understand when exactly we'll drop ...
- 04:07 PM Revision 1e9fc063 (ceph): Merge pull request #7249 from ceph/wip-fix-cmake-trusty
- cmake: fix the build on trusty
- 03:40 PM Revision d093d839 (ceph): tests: correct googlemock warnings
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 41987c86 (ceph): librbd: avoid recursive callback when replaying journal
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 7bcc960b (ceph): librbd: handle additional journal replay states
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 20b9b2e2 (ceph): tests: updated librbd test cases for updated maint ops API
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 37df5970 (ceph): librbd: AioImageRequest base class is now templated
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision ca71a3eb (ceph): librbd: initial integration of maintenance op journal replay
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 2b66a3be (ceph): tests: unit test cases for all available journal events
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 0fff6830 (ceph): librbd: asynchronously replay journal events
- Properly track when AIO operations are safely committed to
disk before marking the journal events are committed.
Sig... - 03:40 PM Revision 254c8f41 (ceph): librbd: track simple maintenance ops to coordinate replay
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 11f6a5f3 (ceph): librbd: snapshot rollback should block writes
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 532c9d23 (ceph): tests: new unit test for snap rollback state machine
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 15170e68 (ceph): librbd: journal events still possible during shutdown
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 9ab14f76 (ceph): librbd: initial hook points for snap create / resize journal replay
- After snap create has blocked IO and after resize has ensured clipped
IO boundaries, they will resume the playback of... - 03:40 PM Revision a2ad7ecb (ceph): tests: update tests to support replaying snap create / resize
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision eb057e1d (ceph): tests: compile RBD and RGW types into ceph-dencoder when enabled
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision a1f70068 (ceph): librbd: convert journal classes to templates for unit testing
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 1192e9c3 (ceph): librbd: journal replay flush should be async
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 8b2dc72e (ceph): tests: unit tests for librbd Journal
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 89d6c271 (ceph): librbd: allocate and associate op tids to maint op journal events
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 1a17f61f (ceph): librbd: handle journal and IO commits in either sequence
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision ac86521b (ceph): librbd: fixed "hidden" virtual methods
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision bf7a1f62 (ceph): librbd: properly order maintenance ops journal events
- In general, the op shoud only start after the jouranl event is
safely committed. Snapshot create and resize need spe... - 03:40 PM Revision ce8fa3d3 (ceph): tests: unit test case for librbd::operation::ResizeRequest
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 58069aa4 (ceph): tests: journal event handling test updates
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:40 PM Revision 629c6f0d (ceph): librbd: moved all maintenance ops to new Operations class
- This will permit unit testing and will facilitate proper
serialization of requests (when necessary).
Signed-off-by: ... - 03:40 PM Revision 588ccfb6 (ceph): librbd: move journal support classes to journal namespace
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 02:43 PM Bug #14354 (Resolved): an IOError happened when use 'ceph report | less' command
- 05:53 AM Bug #14354: an IOError happened when use 'ceph report | less' command
- I think this can be turned off... D:)
- 02:42 PM Revision 10335c50 (ceph): cmake: fix the build on trusty
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 02:38 PM CephFS Bug #14384 (Pending Backport): fsx failed to compile
- I sent a patch upstream and pushed a patch to the workunit in master branch so that it checks out a working commit in...
- 01:39 PM CephFS Bug #14384 (Resolved): fsx failed to compile
- http://teuthology.ovh.sepia.ceph.com/teuthology/teuthology-2016-01-11_23:04:01-fs-master---basic-openstack/2232/
htt... - 01:12 PM CephFS Bug #14379 (Fix Under Review): Add confirmation flag to "ceph mds rmfailed"
- https://github.com/ceph/ceph/pull/7248
- 12:30 AM CephFS Bug #14379 (Resolved): Add confirmation flag to "ceph mds rmfailed"
It's horribly dangerous but has a rather non-threatening name.
- 12:25 PM Bug #14383: BlueFS::dir_map usage issues
- PR is at
https://github.com/ceph/ceph/pull/7247 - 12:19 PM Bug #14383 (Resolved): BlueFS::dir_map usage issues
- It looks like following issues are present when using BlueFS::dir_map
1) No dir_map.clear() call in umount function
... - 12:20 PM Revision 275aaf40 (ceph): Fixing both the subissues from #14383 by using intrusive_ptr instead of...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:12 AM Revision 0a4d1a41 (ceph): mon: add an independent option for max election time
- add a new configure option mon_election_timeout, which is not dependent on mon_lease
Signed-off-by: Sangdi Xu <xu.sa... - 10:27 AM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 10:18 AM Revision 8c28f2f2 (ceph): librbd: optionally validate RBD pool configuration (snapshot support)
- Fixes: #13633
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 1fea4dadc60e13518e9ee55d... - 10:16 AM Backport #13440 (Resolved): ceph-disk prepare fails if device is a symlink
- 10:16 AM rbd Backport #13541 (Resolved): LTTng-UST should be optionally enabled
- 10:15 AM rgw Backport #13734 (Resolved): rgw: swift API returns more than real object count and bytes used whe...
- 10:15 AM Backport #14043 (Resolved): hammer: osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info...
- 10:15 AM Backport #14285 (Resolved): hammer: osd/OSD.cc: 2469: FAILED assert(pg_stat_queue.empty()) on shu...
- 10:15 AM Backport #14287 (Resolved): hammer: ReplicatedPG: wrong result code checking logic during sparse_...
- 10:15 AM Backport #14288 (Resolved): hammer: ceph osd pool stats broken in hammer
- 10:03 AM rgw Bug #14350: bucket create failed
- Not completely sure, but in the initialization phase I'm seeing the following line...
- 09:58 AM Bug #14263: mon:Re join the Monitor alone to form a cluster when it's rank=0
- I'm not sure what you mean, but assuming your aim is to add a new monitor without changing ceph.conf, especially if c...
- 02:04 AM Bug #14263: mon:Re join the Monitor alone to form a cluster when it's rank=0
- @Joao Luis
Thank you very much
We have automated deployment Monitor is a join the cluster, it will be in ceph.co... - 09:27 AM CephFS Bug #13546 (Fix Under Review): mv of directories hung Ceph filesystem
- I added it to https://github.com/ceph/ceph/pull/7199
- 09:22 AM CephFS Bug #14377 (Fix Under Review): [ FAILED ] LibCephFS.DirLs
- https://github.com/ceph/ceph/pull/7246
- 06:09 AM CephFS Bug #14377: [ FAILED ] LibCephFS.DirLs
- It's caused by duplicated entries in readdir result. This can happen when readdir requires several mds requests and t...
- 09:20 AM Revision 838b16aa (ceph): ceph_test_libcephfs: tolerate duplicated entries in readdir
- If a dirfrag get fragmented in the middle of readdir, the readdir
result may contain duplicated entries. (but there s... - 08:23 AM rgw Bug #14382 (Rejected): Remove bucket,data and usage Not cleared
- 1.New users to view usage
!1.新用户初始值.png!
2.New bucket
!2.新用户创建bucket后.png!
3.Upload 2G file
!3.新用户上传2G文件后.png!
... - 07:42 AM Revision 70cb0f1b (ceph): doc: remove redundant space in monmaptool doc
- Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
- 06:59 AM Revision 24d10e63 (ceph): doc: remove redundant space in ceph-authtool doc
- Signed-off-by: Jiaying Ren <jiaying.ren@umcloud.com>
- 06:26 AM Bug #14381: BlueStore: assert failed on get_object_key sanity check
- oh, it's introduced by https://github.com/ceph/ceph/commit/635bda363071dad9f89436cab15fd52bf2678c09
- 06:25 AM Bug #14381 (Resolved): BlueStore: assert failed on get_object_key sanity check
- When ghobject_t's hash = 0,
get_key_object will assert on:
uint64_t pool;
p = _key_decode_u64(p, &pool);
... - 05:49 AM Revision 9b0e2a3a (ceph): tasks/cephfs: test for race between cap flush and clientreplay
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 05:38 AM Revision cbaee849 (ceph): osd:osdmap some clean up
- remove set_weightf
Fixes: #14369
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 05:34 AM Revision 19dc272d (ceph): mds: add config option to suspend logging
- The option creates long-standing unsafe MDS requests. It help in
testing unsafe request related corner cases.
Signed... - 05:19 AM Revision 5d8d6662 (ceph): mds: fix completed cap flush handling
- Client re-send cap flush when MDS restarts. The cap flush message
may release some caps even if the corresponding flu... - 05:19 AM Revision dafb46ba (ceph): mds: delay handling client caps until corresponding inode is created
- When handling client caps in clientreplay stage, it's possible that
corresponding inode does not exist because the cl... - 05:15 AM Revision 73c36f32 (ceph): ceph-detect-init: fix py3 test
- * in python3, None can not be compared with a str. and
we should always set codename with a non empty str, so updat... - 03:21 AM Revision 0187a599 (ceph): cls/cls_rbd: pass string by reference
- Signed-off-by: Jeffrey Lu <lzhng2000@aliyun.com>
- 02:03 AM Bug #14207 (Resolved): BlueStore compiling error without libaio support
- 01:03 AM Bug #14344 (Resolved): bluefs: shall return if we are unable to decode a transaction
- 01:01 AM Bug #14344: bluefs: shall return if we are unable to decode a transaction
- https://github.com/xiexingguo/ceph/commit/181608b53327e67e0d0ccf78d086304a357c1f4d
- 01:03 AM Bug #14333 (Resolved): RBD: return code not checked before going on.
- https://github.com/xiexingguo/ceph/commit/bbb89c760095b1aef692b5b15d0450d226971fdc
- 01:00 AM Bug #14343 (Resolved): bluefs: memory leak during replay
- https://github.com/xiexingguo/ceph/commit/ca65fca584735ddf5a98877f8821d88bdfd9bb84
- 12:59 AM Bug #14351 (Resolved): kstore: unclosed formatter session
- https://github.com/xiexingguo/ceph/commit/d64d98cb607e98bada021a4fea941298e3dbd459
- 12:59 AM Bug #14260 (Resolved): os: memory leak if _open_db fails
- https://github.com/xiexingguo/ceph/commit/131b424de57bfca08d93d92b69fa0b5053d2fff8
- 12:58 AM Bug #14261 (Resolved): os: pointer leak during mount
- https://github.com/xiexingguo/ceph/commit/a4e2b8f635a5a21722eb6bb7f61e69839c0c0409
- 12:57 AM Bug #14352 (Resolved): kstore: fix wrong verification logic of object key
- https://github.com/xiexingguo/ceph/commit/ab3fc3a608190d21af693dd991e58425f75cdeec
- 12:56 AM Bug #14353 (Resolved): bluestore: fix wrong verification logic of object key
- https://github.com/xiexingguo/ceph/commit/635bda363071dad9f89436cab15fd52bf2678c09
- 12:42 AM Bug #14372 (Rejected): ENOTSUPP on trimtrunc (EC with cache pool on top)
- You'll need to track that with the RADOS guys. You can open a support ticket in the overall Ceph project or send an e...
- 12:34 AM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- I confirm for the CephFS on-EC-pool, without cache. The disk bad sector was repaired and now shows that everything i...
- 12:28 AM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- Are you running CephFS against an EC pool? (Perhaps with a cache pool in front?)
If so, yes, that's probably the i... - 12:35 AM CephFS Bug #14380 (Resolved): "ceph mds setmap" crashes mon on invalid input
- Needs exception handling around MDSMap::decode
- 12:04 AM Revision 31034f6d (ceph): Merge branch 'wip-compressor'
- Reviewed-by: Sage Weil <sage@redhat.com>
- 12:04 AM Revision 300c2f77 (ceph): Compressor: compressor plugins unit tests
- Signed-off-by: Alyona Kiseleva <akiselyova@mirantis.com>
- 12:04 AM Revision 2cadc416 (ceph): Compressor: compressor code extention: plugin system added
- Signed-off-by: Alyona Kiseleva <akiselyova@mirantis.com>
- 12:02 AM Revision c5a3c2b1 (ceph): Merge pull request #6425 from branch-predictor/bp-delayed-pglog-index-v2
- osd: delay populating in-memory PG log hashmaps
Reviewed-by: Sage Weil <sage@redhat.com> - 12:01 AM Revision 2f9f91b6 (ceph): Merge pull request #6797 from mathslinux/fix-parse-return
- rgw: fix wrong check for parse() return
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:00 AM Revision b8bc25b0 (ceph): Merge pull request #7087 from H3C/wip-yrf-cephdf
- mon: add RAW USED column to ceph df detail
Reviewed-by: Sage Weil <sage@redhat.com>
01/14/2016
- 11:59 PM Revision cae2e2c6 (ceph): Merge pull request #7106 from tchaikov/wip-11101
- ceph: improve the error message
Reviewed-by: Sage Weil <sage@redhat.com> - 11:59 PM Revision 852f076f (ceph): Merge pull request #7122 from xiexingguo/xxg-wip-bluefs
- osd: bluestore: fix several bugs
Reviewed-by: Sage Weil <sage@redhat.com> - 11:57 PM Revision 7241bf33 (ceph): Merge pull request #7196 from liewegas/wip-bluestore
- osd: bluestore: fix space rebalancing, collection split, buffered reads
- 11:57 PM Revision 1c85998b (ceph): Merge pull request #7200 from xiexingguo/xxg-wip-14343
- osd: bluestore: bluefs: fix several small bugs
Reviewed-by: Sage Weil <sage@redhat.com> - 11:56 PM Revision f6900b82 (ceph): Merge pull request #7213 from xiexingguo/xxg-wip-14351
- osd: kstore: several small fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 11:54 PM Bug #13827: OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer 94.5
- Samuel Just wrote:
> Alternately, those versions of firefly didn't have a deep scrub suicide timeout set, so the cur... - 04:44 PM Bug #13827: OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer 94.5
- Alternately, those versions of firefly didn't have a deep scrub suicide timeout set, so the current 60s default might...
- 04:42 PM Bug #13827: OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer 94.5
- Can they simply be removed?
- 01:34 AM Bug #13827: OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer 94.5
- Samuel Just wrote:
> osd.933 timed out while deep scrubbing cc40143e/.dir.default.120331675.42828/head//5
rados sta... - 11:39 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- # ceph -s
cluster 98f5178a-6c39-4fcf-8ebe-4250c09a8b69
health HEALTH_ERR 3 pgs degraded; 1 pgs inconsisten... - 09:25 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- Please provide the output of "ceph -s", and the log file[*]. This is one of the many asserts which check that operati...
- 09:19 PM Bug #14372: ENOTSUPP on trimtrunc (EC with cache pool on top)
- I'll be available as TiCPU on IRC if you need me to test any code. It is not _urgent_ but still a major inconvenience...
- 03:26 PM Bug #14372 (Rejected): ENOTSUPP on trimtrunc (EC with cache pool on top)
- After copying a new file on CephFS and issuing a ls on the folder, I/O were frozen on CephFS, our monitoring reported...
- 10:55 PM Revision addf313c (ceph): tasks/cephfs: add test case auth_list helper
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:55 PM Revision 7a19b6dc (ceph): tasks/cephfs: clear extra auth ids on test start
- Because new volumeclient tests will be creating IDs
instead of modifying the default ones.
Signed-off-by: John Spray... - 10:55 PM Revision b94b35b6 (ceph): tasks/cephfs: reset IDs of mounts between tests
- because volumeclient test twiddles the IDs to
match the auth identities it creates.
Signed-off-by: John Spray <john.... - 10:55 PM Revision cb699ccc (ceph): tasks/cephfs: write_n_mb optionally background
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:55 PM Revision 523d84b5 (ceph): tasks/cephfs: fix fuse killing in vstart
- The "ps au" output was truncating lines which could cause
processes to get missed in some cases, like where there
is ... - 10:55 PM Revision 627c3305 (ceph): tasks/cephfs: add test_volume_client
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:55 PM Revision 5055f128 (ceph): suites: add yaml for TestVolumeClient
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:55 PM Revision b06818cf (ceph): suites: add an extra client to fs/recovery
- The volumeclient test wants 3, and the rest of the tests
can just ignore it.
Signed-off-by: John Spray <john.spray@r... - 10:55 PM Revision 5c525219 (ceph): tasks/cephfs: fix wait in test_volume_client
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:55 PM Revision 55a04930 (ceph): tasks/cephfs: fix vstart's LocalDaemon.proc
- This class is meant to quack like a DaemonState,
so it needs to expose a .proc attribute. This
was breaking TestDama... - 10:55 PM Revision fb2e38f2 (ceph): tasks/cephfs: fix raising from RemoteProcess.wait()
- ...in the case where we call wait() on an already-finished
process.
Signed-off-by: John Spray <john.spray@redhat.com> - 10:55 PM Revision d1c3ef1f (ceph): tasks/cephfs: pg_num check in volume_client test
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:55 PM Revision 500aac59 (ceph): tasks/cephfs: override max_pgs_per_osd in TestVolumeClient
- Because volume client cues its PG counts from the
mon pg warn max per osd setting, the teuthology template's
ultra-hi... - 09:21 PM Revision a290d34e (ceph): Merge remote-tracking branch 'upstream/jewel'
- 08:49 PM Revision dd63cdce (ceph): Merge pull request #7222 from dack/master
- ceph-disk: add -f flag for btrfs mkfs
Reviewed-by: Sage Weil <sage@redhat.com> - 08:15 PM Documentation #10245: RPM quick start for RHEL should explain where to get tcmalloc & python-flask
- Updated the "quick-start-preflight.rst" file and submitted a pull request[1].
[1] - https://github.com/ceph/ceph/p... - 07:27 PM CephFS Feature #13569 (Resolved): ceph-fuse: support direct IO
- 07:26 PM Bug #13127 (Resolved): ObjectCacher: coalesce multiple writes to a single object into one IO
- 07:25 PM CephFS Bug #13546 (In Progress): mv of directories hung Ceph filesystem
- Do you have a PR or any other commits to go with that? Is it safe to unilaterally not drop caps in a case like this?
- 07:18 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- Here's a new log from the same osd. Same behavior.
- 04:38 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
- Steve, could you enable the "debug ms = 1" and "debug osd = 20", and post the log again? many thanks!
- 07:13 PM rgw Bug #14272: s3tests "... Exception in thread Thread-55" in upgrade:hammer-hammer-distro-basic-ope...
- look like time out, maybe for the osd thrashing tests we need to bump up the timeouts.
- 07:12 PM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- Here is what I see in the provided log:
* volume-26c89a0a-be4d-45d4-85a6-e0dc134941fd is opened @ 04:49:13.858469
... - 06:16 PM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- For some reason file attachment is not working.
Here is the log:
https://www.dropbox.com/s/dzgux81enrukd90/qemu-gue... - 05:00 PM rbd Bug #14373: Cannot reliably create snapshot after freezing QEMU IO
- Actually, for now snapshots are sometimes hanging even without calling FSfreeze in libvirt, so I believe the problem ...
- 03:28 PM rbd Bug #14373 (Resolved): Cannot reliably create snapshot after freezing QEMU IO
- ...
- 07:02 PM rgw Bug #14298: I can't get all user info using admin api return 403
- Seems like a documentation issue.
- 07:00 PM rgw Bug #14270 (Rejected): "testContainerSerializedInfo ... ERROR" in smoke-master-distro-basic-opens...
- looks like environment related issue:...
- 06:59 PM rgw Bug #14246 (Resolved): Segmentation fault ("failed lossy con, dropping message") in rados-jewel-d...
- This is the same as #14173
- 06:54 PM rgw Bug #14208: rgw: 500 returned on Put Bucket ACL (ECANCELLED/-125)
- Could be related to metadata cache disagreement between different rgws (as we've seen in your environment).
- 06:48 PM rgw Bug #13900: "test_s3.test_non_versioned_concurrent_object_create_concurrent_remove ... ERROR" in ...
- Also, no actual rgw logs. We'll need that to debug anything.
- 06:47 PM rgw Bug #13900: "test_s3.test_non_versioned_concurrent_object_create_concurrent_remove ... ERROR" in ...
- seems like unrelated time outs
- 06:37 PM Revision 3b37c245 (ceph): Merge pull request #743 from ceph/wip-root-metadata
- tasks/cephfs: add TestSessionMap.test_session_reject
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:35 PM rgw Bug #14173 (Resolved): rgw: segv in RGWWatcher::handle_error
- 06:35 PM rgw Bug #14180 (Resolved): rgw: segv in RGWWatcher::~RGWWatcher
- 06:34 PM Revision 7781bf07 (ceph): Merge pull request #611 from ceph/wip-libcephfs-acl
- suites/fs: test ceph-fuse with libcephfs permission check
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:27 PM Revision ee757a96 (ceph): Merge branch 'greg-fs-testing'
- 06:26 PM Revision 7d52372a (ceph): fsx: checkout old version until it compiles properly on miras
- I sent a patch to xfstests upstream at
http://article.gmane.org/gmane.comp.file-systems.fstests/1665, but
until that'... - 06:26 PM Revision 11cd84ca (ceph): Merge branch 'wip-13569' of git://github.com/ukernel/ceph into greg-fs-...
- https://github.com/ceph/ceph/pull/6463
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:25 PM Revision bf9790e1 (ceph): Merge branch 'wip-13127-master' into greg-fs-testing
- https://github.com/ceph/ceph/pull/5990
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:24 PM Revision e7dc5fb7 (ceph): Merge remote-tracking branch 'origin/wip-libcephfs-acl' into greg-fs-te...
- https://github.com/ceph/ceph/pull/5658
Reviewed-by: John Spray <jspray@redhat.com>
Conflicts:
src/common/config_op... - 06:23 PM Revision 1d3f80ac (ceph): Merge branch 'wip-root-metadata' of git://github.com/jcsp/ceph into gre...
- https://github.com/ceph/ceph/pull/6179
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:18 PM CephFS Bug #14377: [ FAILED ] LibCephFS.DirLs
- Zheng, you've been fixing a lot here lately, please take a look!
- 06:18 PM CephFS Bug #14377 (Resolved): [ FAILED ] LibCephFS.DirLs
- http://pulpito.ceph.com/gregf-2016-01-12_23:23:33-fs-greg-fs-testing-1-12-1---basic-mira/26500/
This failed the Di... - 05:09 PM Revision 700be56c (ceph): config_opts: increase suicide timeout to 300 to match recovery
- Fixes: 14376
Backport: hammer, firefly
Signed-off-by: Samuel Just <sjust@redhat.com> - 05:08 PM Backport #14376: scrub suicide timeout is the same as the regular timeout -- should probably matc...
- ...
- 04:37 PM Backport #14376: scrub suicide timeout is the same as the regular timeout -- should probably matc...
- 04:29 PM Backport #14376: scrub suicide timeout is the same as the regular timeout -- should probably matc...
- 04:26 PM Backport #14376 (Resolved): scrub suicide timeout is the same as the regular timeout -- should pr...
- https://github.com/ceph/ceph/pull/7236
- 04:38 PM rbd Feature #14264: async rbd_open() option
- Mykola Golub wrote:
> Wido, are you working or planning to work on this feature? I could do it if you aren't.
No,... - 03:06 PM rbd Feature #14264: async rbd_open() option
- Wido, are you working or planning to work on this feature? I could do it if you aren't.
- 04:32 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
- Run: http://pulpito.ceph.com/teuthology-2016-01-14_02:10:08-upgrade:hammer-x-jewel-distro-basic-vps/
Job: 28922 - 04:15 PM rgw Bug #14105: adminops subuser specify S3 keys
- Whenever you specify subuser create with a secret key, iirc only the swift secret key is created.. the access key is ...
- 03:57 PM rgw Bug #14375 (Resolved): subuser rm fails with status 125
- command radosgw-admin --log-to-stderr --format json key rm --subuser foo:foo1 --key-type swift
fails with error code... - 03:41 PM CephFS Bug #14374 (Resolved): MDS asok handlers trigger lock cycle assertion if they take mds_lock
http://pulpito.ceph.com/gregf-2016-01-12_23:29:42-fs-greg-fs-speculative---basic-mira/26556
The asok handler is ...- 02:55 PM Bug #14263 (Rejected): mon:Re join the Monitor alone to form a cluster when it's rank=0
- The only way for this actually happen is for the user to explicitly create the necessary circumstances for this to ha...
- 06:14 AM Bug #14263: mon:Re join the Monitor alone to form a cluster when it's rank=0
- another solution
https://github.com/ceph/ceph/pull/7230 - 02:47 PM Revision 256dc84d (ceph): doc/release-notes: v10.0.2
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:45 PM Backport #13789 (Resolved): Objecter: potential null pointer access when do pool_snap_list.
- 02:44 PM Backport #13892 (Resolved): hammer: auth/cephx: large amounts of log are produced by osd
- 02:31 PM Bug #14371 (Resolved): pybind build failures on current master
- 02:19 PM Bug #14371: pybind build failures on current master
- Likely introduced in https://github.com/ceph/ceph/pull/7224
- 02:05 PM Bug #14371: pybind build failures on current master
- Master PR https://github.com/ceph/ceph/pull/7235
- 02:03 PM Bug #14371 (Resolved): pybind build failures on current master
- rbd.pyx is failing to compile with the following error...
- 02:30 PM Revision 55a78e55 (ceph): Merge pull request #7235 from theanalyst/fix/pybind-build-failure
- pybind: fix build failure, remove extraneous semicolon in method
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:30 PM Backport #13930 (Resolved): hammer: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- 02:29 PM Backport #13936 (Resolved): hammer: Ceph daemon failed to start, because the service name was alr...
- 02:27 PM Backport #13870 (Resolved): hammer: OSD: race condition detected during send_failures
- 02:22 PM Revision 6a309c81 (ceph): pybind/rbd.pyx: drop stray semicolon
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:21 PM Revision 4e674189 (ceph): Merge pull request #7179 from dachary/wip-14287-hammer
- hammer: ReplicatedPG: wrong result code checking logic during sparse_read
Reviewed-by: Sage Weil <sage@redhat.com> - 02:20 PM Revision 28e99a90 (ceph): Merge pull request #7178 from dachary/wip-14285-hammer
- hammer: osd/OSD.cc: 2469: FAILED assert(pg_stat_queue.empty()) on shutdown
Reviewed-by: Sage Weil <sage@redhat.com> - 02:20 PM Revision 17a29658 (ceph): Merge pull request #7177 from dachary/wip-14043-hammer
- hammer: osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info.history.last_epoch_started)
Reviewed-by: Sage ... - 02:20 PM Revision a1459eac (ceph): Merge pull request #7180 from dachary/wip-14288-hammer
- hammer: ceph osd pool stats broken in hammer
Reviewed-by: Sage Weil <sage@redhat.com> - 02:19 PM Revision c9a13a12 (ceph): Merge pull request #6994 from badone/wip-13993-hammer
- log: Log.cc: Assign LOG_DEBUG priority to syslog calls
Reviewed-by: Sage Weil <sage@redhat.com> - 02:18 PM Revision 174a1a97 (ceph): Merge pull request #6839 from SUSE/wip-13789-hammer
- Objecter: potential null pointer access when do pool_snap_list.
Reviewed-by: Sage Weil <sage@redhat.com> - 02:18 PM Revision e92cbde5 (ceph): os/bluestore/FreelistManager: fix _dump locking
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:18 PM Revision cb167e99 (ceph): Merge pull request #6835 from SUSE/wip-13892-hammer
- hammer: auth/cephx: large amounts of log are produced by osd
Reviewed-by: Sage Weil <sage@redhat.com> - 02:17 PM Revision 1c4ba855 (ceph): Merge pull request #6834 from SUSE/wip-13930-hammer
- hammer: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
Reviewed-by: Sage Weil <sage@redhat.com> - 02:17 PM Revision 72b6b68f (ceph): Merge pull request #6832 from SUSE/wip-13936-hammer
- hammer: Ceph daemon failed to start, because the service name was already used.
Reviewed-by: Sage Weil <sage@redhat.... - 02:16 PM Revision d064f9f6 (ceph): Merge pull request #6755 from SUSE/wip-13870-hammer
- hammer: OSD: race condition detected during send_failures
Reviewed-by: Sage Weil <sage@redhat.com> - 02:15 PM rbd Bug #13560 (Resolved): unknown argument --quiet in udevadm settle
- 02:13 PM rbd Bug #13560: unknown argument --quiet in udevadm settle
- The hammer fix has been merged: https://github.com/ceph/ceph/pull/6530
It should be included in the 0.94.6 release. - 02:14 PM rbd Backport #13760 (Resolved): unknown argument --quiet in udevadm settle
- 02:04 PM Revision 386834ca (ceph): pybind: remove extraneous semicolon in method
- A semicolon on `rbd_build_object_map` method was causing build failures
in current master
Fixes: #14371
Signed-off-b... - 01:46 PM Revision 9e074820 (ceph): osd: less chatter about tick
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:27 PM Revision e22a8c6c (ceph): rados/objecststore/fusestore.yaml: run ceph-objectstore-tool fuse test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:44 PM Bug #14370 (Resolved): MemStore: shall drain finisher first before returning from the unmount method
- 12:23 PM Revision 4c4d9299 (ceph): Merge pull request #7212 from caibo2014/fix-cephin-pipe-error
- ceph.in: avoid a broken pipe error when use ceph command
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:10 PM Revision f6eb3e55 (ceph): ceph.in:avoid a broken pipe error when use ceph command
- Fixes: #14354
Signed-off-by: Bo Cai <cai.bo@h3c.com> - 12:01 PM Revision 2be865c5 (ceph): kstore: remove unreachable code
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:05 AM Revision a44968ad (ceph): Merge pull request #7210 from swamireddy/contrib_list_10
- mailmap update
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:21 AM rgw Bug #14368 (Resolved): mon: paxos is_recovering calc error
- 04:21 AM rgw Bug #14368 (Fix Under Review): mon: paxos is_recovering calc error
- https://github.com/ceph/ceph/pull/7227
- 02:25 AM rgw Bug #14368 (Resolved): mon: paxos is_recovering calc error
- ...
- 10:21 AM Revision fd305c81 (ceph): Merge pull request #7227 from dwj192/dwj-paxos
- mon: paxos is_recovering calc error
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Kefu Chai <kchai@redh... - 10:16 AM Revision 1eb13d96 (ceph): Merge pull request #7216 from jcsp/wip-14357
- mds: advance clientreplay when replying
- 09:37 AM Bug #14369: osd:osdmap some clean up
- https://github.com/ceph/ceph/pull/7231
- 08:13 AM Bug #14369 (Resolved): osd:osdmap some clean up
- osdmap some clean up
The definition of some no use in osdmap - 09:18 AM Bug #13238 (Duplicate): duplicate start of ceph-osd daemon
- dup of #13422
- 08:35 AM Revision 70b3d187 (ceph): Merge pull request #7219 from aiicore/affiliation
- mailmap: Igor Podoski affiliation
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:22 AM Revision 0ca62855 (ceph): Merge pull request #6415 from dillaman/wip-13541-hammer
- LTTng-UST tracing should be dynamically enabled
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:15 AM Revision e9f545b4 (ceph): Merge pull request #7176 from dachary/wip-13440-hammer
- ceph-disk prepare fails if device is a symlink
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:14 AM Revision 85219163 (ceph): Merge pull request #7150 from jecluis/wip-14236
- mon: OSDMonitor: do not assume a session exists in send_incremental()
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:49 AM Revision a987fc3a (ceph): BlueStore: decrease max listed object number from 5 to 1
- For the sake of performance.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 06:47 AM Revision c8aae0c1 (ceph): kstore: decrease max listed object number from 5 to 1
- For the sake of performance.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 06:43 AM Revision d3395549 (ceph): BlueStore: kill warnings
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision c64d3394 (ceph): BlueStore: fix shared_ptr leak during fsck
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision 4e124e57 (ceph): BlueStore: fix result code overwritten
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision dc94eb76 (ceph): BlueStore: fix potential null pointer access
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision 1f1f577d (ceph): BlueStore: remove redundant omap_head check
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision 2e77e9ac (ceph): BlueStore: remove unused local variable "empty"
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision 3cdf36b3 (ceph): BlueStore: fix unhandle error cases during block file setup
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision 635bda36 (ceph): BlueStore: fix wrong verification of object key
- Fixes: #14353
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 06:30 AM Revision a0112a21 (ceph): BlueStore: fix memory leak in several abnormal cases
- Fixes: #14260
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 06:30 AM Revision de0a5d29 (ceph): BlueStore: fix typo
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:30 AM Revision 0747e3bd (ceph): BlueStore: fix shared_ptr leak during mount
- Fixes: #14261
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 05:45 AM Revision b085a564 (ceph): BlueStore: differentiate error code for better tracing
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 05:45 AM Revision 295cdd60 (ceph): BlueStore: skip CRC verification if unable to read label
- Fixes: #14259
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 05:45 AM Revision d5900ea0 (ceph): BlueStore: reset result code to errno for better tracing
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 04:01 AM Revision 430bfafc (ceph): ceph_test_libcephfs: check file open mode
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 03:51 AM Revision eae97f8d (ceph): client: check if Fh is readable before read
- Fixes: #11517
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 03:14 AM CephFS Bug #14319: Double decreased the count to trim caps which will cause failing to respond to cache ...
- This issue also exists on master, so close original PR and create this new one.
https://github.com/ceph/ceph/pull/... - 03:04 AM Revision d8a3f6d8 (ceph): ceph-fuse: double decreased the count to trim caps
- Signed-off-by: Zhi Zhang zhangz.david@outlook.com
- 02:39 AM CephFS Backport #12350 (Pending Backport): Provided logrotate setup does not handle ceph-fuse correctly
- 02:16 AM Revision fa9c8e09 (ceph): mon: paxos is_recovering calc error
- Fix:#14368
Signed-off-by: Weijun Duan <duanweijun@h3c.com> - 01:19 AM rbd Tasks #13818 (Resolved): Update RBD notification workunit test to include new infernalis RPC mess...
- 01:15 AM rbd Tasks #13818 (Fix Under Review): Update RBD notification workunit test to include new infernalis ...
- 01:03 AM rbd Tasks #13818 (Resolved): Update RBD notification workunit test to include new infernalis RPC mess...
- *master PR*: https://github.com/ceph/ceph/pull/7224
- 01:17 AM Revision 475dd820 (ceph): Merge pull request #7224 from dillaman/wip-13818
- tests: snap rename and rebuild object map in client update test
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:16 AM rbd Bug #13810 (Resolved): "stderr:rbd.InvalidArgument: error writing to test_notify_clone)" in upgra...
- 01:13 AM rbd Bug #13810: "stderr:rbd.InvalidArgument: error writing to test_notify_clone)" in upgrade:client-u...
- *hammer PR*: https://github.com/ceph/ceph/pull/7226
*infernalis PR*: https://github.com/ceph/ceph/pull/7225
(thes... - 01:15 AM Revision 1296c2ba (ceph): Merge pull request #7225 from dillaman/wip-13810-infernalis
- tests: notification slave needs to wait for master
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:15 AM Revision ebfb3fbe (ceph): Merge pull request #7226 from dillaman/wip-13810-hammer
- tests: notification slave needs to wait for master
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:14 AM rbd Feature #13504 (Resolved): rbd: API: options on image create
- 01:14 AM rbd Bug #14163 (Resolved): Helgrind errors reported during teuthology runs
- 01:10 AM Revision 447ab1d7 (ceph): tests: notification slave needs to wait for master
- If the slave instance starts before the master, race
conditions are possible.
Fixes: #13810
Backport: infernalis, ha... - 01:10 AM Revision d4c41d04 (ceph): tests: notification slave needs to wait for master
- If the slave instance starts before the master, race
conditions are possible.
Fixes: #13810
Backport: infernalis, ha... - 01:07 AM Revision 2697b302 (ceph): Merge pull request #7220 from dillaman/wip-13810-jewel
- tests: notification slave needs to wait for master
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:56 AM Revision 0108b9a4 (ceph): Merge pull request #7208 from dillaman/wip-14163-jewel
- helgrind: fix real (and imaginary) race conditions
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:55 AM Bug #14367 (Resolved): auth: possible race by using PK11_CreateContextBySymKey from multiple threads
- helgrind warns about this function having races. It may not be threadsafe, like some other libnss methods.
We use it... - 12:42 AM Bug #14366 (New): unsafe handle_conf_change() methods
- The handle_conf_change() methods in these files look potentially unsafe (modifying data without locks):...
- 12:42 AM CephFS Bug #14365 (Resolved): unsafe handle_config_change() methods
- The handle_conf_change() methods in these files look potentially unsafe (modifying data without locks):...
- 12:29 AM Bug #14364 (Resolved): librados, objecter: op_submit() returns after request completion, AioCompl...
- The following line is problematic:...
- 12:28 AM Revision 9afe229b (ceph): Fixed symblink for os configs
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 0915747895b20b856a173d58f515af6b033814... - 12:16 AM Revision 4abdc391 (ceph): Fixed symblink for os configs
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 0915747895b20b856a173d58f515af6b033814... - 12:10 AM Revision e4ba609c (ceph): Merge pull request #796 from ceph/wip-fix-sumblink-distros
- Fixed symblink for os configs
- 12:03 AM Backport #14329: hammer: osd/ReplicatedPG: fix promotion recency logic
- Created a new PR since there wasn't a response to the original PR. https://github.com/ceph/ceph/pull/7207
- 12:03 AM Revision 4c3b6852 (ceph): tests: snap rename and rebuild object map in client update test
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:01 AM Revision 09157478 (ceph): Fixed symblink for os configs
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
Also available in: Atom