Activity
From 09/06/2016 to 10/05/2016
10/05/2016
- 10:36 PM Revision afbcece9 (ceph): Merge pull request #11336 from liewegas/wip-bluestore-spanning-map
- os/bluestore: switch spanning_blob_map to std::map
- 09:27 PM CephFS Bug #17518 (Resolved): monitor assertion failure when deactivating mds in (invalid) fscid 0
- Made a simple vstart cluster and tried this:...
- 09:27 PM Revision e5a66408 (ceph): mailmap: Thomas Serlin affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:27 PM Revision 7b070629 (ceph): mailmap: Daniel Gollub affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:27 PM Revision 4c70470a (ceph): mailmap: Peter Maloney affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:27 PM Revision 5d192d49 (ceph): mailmap: Harald Klein affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:27 PM Revision a82675cb (ceph): mailmap: Iain Buclaw affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:27 PM Revision af2f5d8f (ceph): mailmap: Roushan Ali affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:26 PM Revision 01dacd6e (ceph): mailmap: Bassam Tabbara affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:14 PM rgw Bug #13286 (Pending Backport): rgw:user email can modify to empty when it has values
- 08:35 PM rgw Bug #13286: rgw:user email can modify to empty when it has values
- merged to master - does this need backport?
- 07:59 PM rgw Bug #13286: rgw:user email can modify to empty when it has values
- https://github.com/ceph/ceph/pull/11340
- 09:12 PM CephFS Bug #17517 (Resolved): ceph-fuse: does not handle ENOMEM during remount
- When running 8 ceph-fuse clients on a single Linode VM with 2GB memory, I observed the clients would die under load w...
- 08:44 PM devops Bug #17516: aarch64: Compiler-based detection of crc32 extended CPU type is broken
- *master PR*: https://github.com/ceph/ceph/pull/11391
- 08:44 PM devops Bug #17516 (Resolved): aarch64: Compiler-based detection of crc32 extended CPU type is broken
- 08:34 PM Revision cf178588 (ceph): Merge pull request #11340 from yehudasa/wip-13286
- rgw-admin: allow unsetting user's email
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 08:27 PM Revision bb81f9dd (ceph): librbd: permit disabling journaling if in corrupt state
- Fixes: http://tracker.ceph.com/issues/16740
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from c... - 08:26 PM Revision b14d7f14 (ceph): librbd: new journal policy to disable initializing the journal
- This will be used in the case where the journal is being disabled.
Signed-off-by: Jason Dillaman <dillaman@redhat.co... - 08:15 PM rgw Backport #17505 (In Progress): jewel: rgw: doc: description of multipart part entity is wrong
- 07:04 PM rgw Backport #17505 (Resolved): jewel: rgw: doc: description of multipart part entity is wrong
- https://github.com/ceph/ceph/pull/11342
- 08:15 PM Revision 77ea5113 (ceph): doc/radosgw: fix description of response elements 'Part'
- Signed-off-by: weiqiaomiao <wei.qiaomiao@zte.com.cn>
(cherry picked from commit 9c3fe46a7eb89aedc52582737c200e58d6373... - 08:11 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
I think that 82fdacda1bf35b029ae8474ddf48c33e62ab81f6 may have caused this issue. I haven't look closely at the ex...- 12:12 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- A user who has corrupted cephfs metadata says he encountered this issue before. The way cephfs metadata get corrupted...
- 07:48 PM Revision 927a3733 (ceph): make-dist: set rpm_release correctly for release builds
- Similar to autobuild-ceph 17591db, only try to set rpm_release if there
is a release part to the git describe output ... - 07:43 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- I ended up going with a journal flush and a ceph fs reset. The mds is now up and clients can mount. Thank you both fo...
- 02:56 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- Digging through that patch, I'm not sure it is setup to work with the mdsmap->fsmap conversion that happened at some ...
- 01:24 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- Hmm, I guess the --yes-i-really-mean-it part isn't helping! (http://tracker.ceph.com/issues/14379)
I've attached Z... - 01:06 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- Well, crap. I don't remember running that, and it wasn't in the bash_history on the monitor I've been using, but:
... - 12:24 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- Anything rank that is in the 'in' set should also be in one of failed,stopped,damaged or up.
I notice that in the ... - 04:25 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- http://people.cs.ksu.edu/~mozes/ceph-mon.hobbit01-debug-branch.log
Unfortunately, it would seem we're bailing out ... - 12:26 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- mon level 20 should do it.
- 07:32 PM Revision cab233d5 (ceph): mon/PGMap: PGs can be stuck more than one thing
- This was inadvertantly changed waaay back in
9c95bb0454dbad781b6655f4c7116620005101f7.
This fixes the health warning... - 07:32 PM Bug #17515 (Resolved): mon: health does not report pgs stuck in more than one state
- https://github.com/ceph/ceph/pull/11339
- 07:30 PM Revision a35b7f6a (ceph): Merge pull request #11334 from ceph/wip-make-dist-tag
- make-dist: set rpm_release correctly for release builds
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 07:30 PM Revision f0dffe56 (ceph): tasks/dump_suck: mark down osds one at a time
- This forces them to be unclean, *then* stale. This ensures
that after they are both down they are both *always* uncl... - 07:24 PM Revision 5ef07c32 (ceph): tasks/dump_stuck: fix unclean count
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:24 PM Revision 50f20224 (ceph): tasks/dump_stuck: more verbose
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:08 PM rgw Backport #17514 (Resolved): jewel: rgw:bucket check remove _multipart_ prefix
- https://github.com/ceph/ceph/pull/11470
- 07:07 PM rgw Backport #17513 (Resolved): jewel: S3 object versioning fails when applied on a non-master zone
- https://github.com/ceph/ceph/pull/11367
- 07:06 PM rgw Backport #17512 (Resolved): jewel: multisite: metadata master can get the wrong value for 'oldest...
- https://github.com/ceph/ceph/pull/11868
- 07:06 PM rgw Backport #17511 (Resolved): jewel: s3tests-test-readwrite failing with 500
- https://github.com/ceph/ceph/pull/11471
- 07:05 PM rgw Backport #17510 (Resolved): jewel: ERROR: got unexpected error when trying to read object: -2
- https://github.com/ceph/ceph/pull/11472
- 07:05 PM rgw Backport #17509 (Resolved): jewel: Config parameter "rgw keystone make new tenants" in radosgw mu...
- https://github.com/ceph/ceph/pull/11473
- 07:04 PM rbd Backport #17508 (Resolved): jewel: rbd-mirror: potential crash during replay shut down
- https://github.com/ceph/ceph/pull/11433
- 07:04 PM rgw Backport #17507 (Resolved): jewel: multisite: 'radosgw-admin period prepare' is obsolete
- https://github.com/ceph/ceph/pull/11574
- 07:04 PM rbd Backport #17506 (Resolved): jewel: assert failure in run-rbd-unit-tests.sh
- https://github.com/ceph/ceph/pull/11433
- 06:58 PM rgw Backport #17161 (In Progress): jewel: multisite: StateBuildingFullSyncMaps doesn't check for erro...
- 03:09 PM rgw Backport #17161: jewel: multisite: StateBuildingFullSyncMaps doesn't check for errors before adva...
- https://github.com/ceph/ceph/pull/11330
- 06:55 PM rbd Backport #17060 (In Progress): jewel: Cannot disable journaling or remove non-mirrored, "non-prim...
- 06:51 PM rbd Backport #17060 (New): jewel: Cannot disable journaling or remove non-mirrored, "non-primary" image
- Neither of the two commits in https://github.com/ceph/ceph/pull/10712 appear to have been backported. I cannot find t...
- 03:00 PM rbd Backport #17060 (In Progress): jewel: Cannot disable journaling or remove non-mirrored, "non-prim...
- Not all associated commits backported
- 06:53 PM Revision 268ad74e (ceph): mds/SessionMap.cc: remove unneeded use of count
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 06:41 PM Revision 10dbfc54 (ceph): rgw: remove user email index using helper function
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 06:34 PM Revision ebfd713d (ceph): rgw:user email can modify to empty
- Fixes: http://tracker.ceph.com/issues/13286
Signed-off-by: Weijun Duan <duanweijun@h3c.com> - 06:26 PM Revision 1a7faefd (ceph): rgw_file: pre-assign times
- Set unix timestamps based on RGW values for creation, modification
time for buckets, objects in stat requests. Regar... - 06:26 PM Revision 0c932b90 (ceph): rgw_file: fix set_attrs operation
- The effective part of this change is to always set a value
for RGW_ATTR_UNIX_KEY1 (because it is expected later).
Se... - 06:26 PM Revision 0de33909 (ceph): rgw_file: implement rgw_setattr
- Introduce a new RGWSetattrs RGWOp descendant, to create or replace
sets of attrs on buckets or objects.
This version... - 06:25 PM Revision 00f3fbe7 (ceph): rgw: remove duplicated calls to getattr
- Signed-off-by: Weibing Zhang <zhangweibing@unitedstack.com>
(cherry picked from commit 87b550ed2fba472d4ef2e1f771bb5f... - 06:25 PM Revision c5399285 (ceph): rgw: rgw file fix bug of rgw_lookup can not exact match file name
- bug reproduce steps:
in nfs-client (connect to nfs-ganesha server):
1. mv file file.rename
2. stat file // get file a... - 06:25 PM Revision 9f5c7377 (ceph): rgw: fix the wrong return value
- Here `parent->readdir` will return negative numbers When there is an error.
so we should just return it.
Signed-off-... - 06:25 PM Revision cf1353c2 (ceph): rgw_file: restore local definition of RGWLibFS gc interval
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from commit 31936caa09b46e86700faad969adfa9d431762... - 06:25 PM Revision 7a648ed9 (ceph): rgw_file: explain semantics of RGWFileHandle::commit
- Add a comment explaining why the method currently returns 0
unconditionally.
Signed-off-by: Matt Benjamin <mbenjamin... - 06:25 PM Revision 0135da74 (ceph): ceph_timer: prefer using directive to typedef
- This change replaces the existing member-hook typedef as well as
the new set-type typedefs, so committed separately.
... - 06:25 PM Revision 2a9233f1 (ceph): librgw: add API version defines for librgw and rgw_file
- This change borrows the major, minor+extra format used by libcephfs.
The version numbering is starting at 1,1,0 on th... - 06:24 PM Revision 2d6966f7 (ceph): rgw file: allow RGWLibFS::write_completion_interval_s to be set in conf
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from commit 70dad0fba561edaf0bb4e746e29b92a4e9b014b2) - 06:24 PM Revision 7071845f (ceph): rgw_file: log on write completion events at level 10
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from commit d1e512d8c0e20df5a96ccb5f775a7a2ca123efbe) - 06:24 PM Revision 95310c7f (ceph): rgw_file: add RGW_OPEN_FLAG_STATELESS as a synonym for V3
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from commit da596eb3af69c2cdf191893eb44a8947662634cf) - 06:24 PM Revision 697d4ef7 (ceph): rgw_file: implement stateless write completion timer
- Implements a temporal mechanism to enforce write completion for setups
which lack open state tracking (e.g., NFS3).
... - 06:24 PM Revision 4a31509c (ceph): rgw_file: fix/update rgw_create flag arguments
- Allow passing POSIX open flags as well as api call flags. Needed
for NFS3 support.
Signed-off-by: Matt Benjamin <mb... - 06:24 PM Revision 73f9a0b1 (ceph): rgw_file: fix/update rgw_open flag arguments
- Allow passing POSIX open flags as well as api call flags. Needed
for NFS3 support.
Signed-off-by: Matt Benjamin <mb... - 06:24 PM Revision 4ceb70eb (ceph): rgw file: remove busy-wait in RGWLibFS::gc()
- This is a background thread. However, CPU is wasted.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry pi... - 06:23 PM Revision 8e1515b0 (ceph): rgw_file: unlock() must precede out label
- In lookup_handle(...).
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from commit 9f64f34e481278... - 06:23 PM Revision 88eeaa96 (ceph): rgw nfs: fix write continuations
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from commit b4d079f2b5a4d49b2ba7576b272a2a3f3b0d66c8) - 06:23 PM Revision f0b17999 (ceph): rgw nfs: don't leak fh->mtx in lookup_handle()
- This change fixes a serious latent locking problem, noticed after
updating the ganesha/rgw driver invalidation after ... - 06:23 PM Revision f16ac90f (ceph): rgw file: refuse to rename directories
- The representation of paths as an aggregate involving any
number of objects argues against ever permitting such
opera... - 06:18 PM Revision 0ff0c9a8 (ceph): make-dist: set rpm_release correctly for release builds
- Similar to autobuild-ceph 17591db, only try to set rpm_release if there
is a release part to the git describe output ... - 05:14 PM Revision 23b749f9 (ceph): rgw_file: refuse ops on deleted targets
- Detect these illegal cases, as they are indicate various incorrect
behaviors/bugs.
Signed-off-by: Matt Benjamin <mbe... - 05:14 PM Revision 345de45c (ceph): rgw_file: implement rgw_setattr
- Introduce a new RGWSetattrs RGWOp descendant, to create or replace
sets of attrs on buckets or objects.
This version... - 05:13 PM Revision 88b50278 (ceph): rgw_file: refuse partial, out-of-order writes
- A single file object may be opened only once per gateway
instance, and writes to that object must be complete, and in... - 05:13 PM Revision be243695 (ceph): rgw_file: fix rename cases and unify unlink
- Rather ordinary rename cases failed in the unlink step. Fix this,
unifying the unlink path while at it.
Signed-off-... - 04:46 PM Revision a10d7006 (ceph): add ldap auth custom search filter feature patch - http://tracker.ceph....
- Signed-off-by: Harald Klein <hari@vt100.at>
(cherry picked from commit c935885ae9d5fd413495448a0b0e5fce899c9b73)
Fix... - 04:46 PM Revision 74866385 (ceph): rgw ldap: protect rgw::from_base64 from non-base64 input
- Also adds unit tests for:
1. empty output from from_base64 (turns out to be harmless)
2. random and specific non-base... - 04:45 PM Revision 68788fb8 (ceph): rgw ldap: enforce simple_bind w/LDAPv3
- Found by Harald Klein <hklein@redhat.com>.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
(cherry picked from c... - 04:42 PM Revision 871caeb5 (ceph): rgw: add reinit/rebind logic (ldap)
- Gracefully handle stale LDAP connections by rebinding--verified
with MS AD. Rebind is attempted once per request unt... - 04:17 PM Revision 63d5b68d (ceph): os/bluestore: switch spanning_blob_map to std::map
- The intrusive map overhead on Blob is expensive when a tiny fraction of
Blobs actually end up in the spanning_blob_ma... - 04:07 PM rgw Bug #17293 (Pending Backport): Config parameter "rgw keystone make new tenants" in radosgw multit...
- 04:07 PM Revision 1b90ab37 (ceph): Merge pull request #11127 from SirishaGuduru/multitenancy-doc-change
- Changed config parameter "rgw keystone make new tenants" in radosgw multitenancy
Reviewed-by: Yehuda Sadeh <yehuda@r... - 04:04 PM rgw Documentation #16604 (Resolved): rgw_enable_usage_log = true option is missing in Rados Gateway a...
- 04:04 PM Revision 086cebc9 (ceph): Merge pull request #10159 from mhackett/wip-mhackett-16604
- doc: add rgw_enable_usage_log option in Rados Gateway admin guide
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:55 PM rgw Bug #17504 (Pending Backport): rgw: doc: description of multipart part entity is wrong
- 03:54 PM rgw Bug #17504 (Resolved): rgw: doc: description of multipart part entity is wrong
- https://github.com/ceph/ceph/pull/10641
- 03:55 PM Revision a1734272 (ceph): Merge pull request #10641 from weiqiaomiao/wqm-wip-rgw-s3api
- doc/radosgw: fix description of response elements 'Part'
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:22 PM rgw Bug #16930 (Pending Backport): s3tests-test-readwrite failing with 500
- 03:06 PM Revision de0c4e12 (ceph): rgw: RGWDataSyncCR fails on errors from RGWListBucketIndexesCR
- Fixes: http://tracker.ceph.com/issues/17073
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 03:00 PM rbd Bug #16740 (Pending Backport): Cannot disable journaling or remove non-mirrored, "non-primary" image
- 02:51 PM Revision 85224aef (ceph): Merge pull request #11286 from yehudasa/wip-16930
- rgw: don't fail if lost race when setting acls
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:34 PM Revision 478d0100 (ceph): rgw: remove unused variable "ostr" in rgw_b64.h and fix the comment
- Signed-off-by: Weibing Zhang <zhangweibing@unitedstack.com>
- 02:17 PM rgw Bug #17443: rgw: versioning is broken in current master
- https://github.com/ceph/ceph/pull/11270 is the pull request that needs backport
- 02:15 PM mgr Feature #17503 (Resolved): Enable python modules to subscribe to cluster log
Could either have mgr subscribe (using MonClient) at info level, and then pass everything into module notify() call...- 02:15 PM Revision fefd61f8 (ceph): Merge pull request #11319 from markhpc/wip-bluestore-optimize-size
- os/bluestore: optimize intrusive sets for size.
Reviewed-by: Sage Weil <sage@redhat.com> - 02:11 PM rbd Feature #17502: Thinly provisioned RBD image creation/resize should check RBD pool free size
- As this is a thin provision feature may be instead of error we can give WARNING and user should ack it to goahead wit...
- 01:00 PM rbd Feature #17502: Thinly provisioned RBD image creation/resize should check RBD pool free size
- This feature will be good to check RBD pool size before allowing create or resize to go beyond the MAX AVAIL. We shou...
- 12:56 PM rbd Feature #17502: Thinly provisioned RBD image creation/resize should check RBD pool free size
- Downstream Feature Request: https://bugzilla.redhat.com/show_bug.cgi?id=1381964
- 12:53 PM rbd Feature #17502 (Rejected): Thinly provisioned RBD image creation/resize should check RBD pool fre...
- Thinly provisioned RBD image creation/resize should check RBD pool free size
Additional info:
------------------... - 02:00 PM Revision 7176b61b (ceph): Merge pull request #11313 from ceph/wip-krbd-lock-on-read-option
- rbd: recognize lock_on_read option
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:59 PM rbd Subtask #17423 (In Progress): [data pool] add new non-dynamic feature bit for data pool
- 01:56 PM Revision 0932d39e (ceph): os/bluestore: simplify BufferSpace writing_map / list
- We were tracking buffers by seq. In reality, though, we
won't have very many buffers that have in flight IO to
the s... - 01:44 PM Revision 6bbac0e0 (ceph): unittest_bluestore_types: more type sizeofs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:44 PM Revision 7072be6a (ceph): Merge pull request #11264 from liewegas/wip-bluestore-blob-split
- os/bluestore: try to split blobs instead of spanning them
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 01:43 PM Revision 871aa4a3 (ceph): os/bluestore: make Buffer smaller
- 160 -> 152 bytes
Signed-off-by: Sage Weil <sage@redhat.com> - 01:17 PM Bug #17180: Osd restarts intermittently while running ceph FS IO
- Same here with 10.2.3. I was doing a test when it happened. I had a test cluster set up with 3 VMs. I just ran fio on...
- 12:11 PM Revision 06448acf (ceph): cls_rbd: add initial support for separate data pools
- Fixes: http://tracker.ceph.com/issues/17422
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 12:11 PM Revision c5f22900 (ceph): librbd: new RBD_FEATURE_DATA_POOL feature bit
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 11:04 AM Revision 4d077b14 (ceph): Merge pull request #11323 from liewegas/wip-bluestore-more-types
- unittest_bluestore_types: a few more types for sizeof
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 08:34 AM rgw Bug #16357: radosgw stats error
- I'm still able to reproduce this in master; these are the steps I did...
- 04:30 AM Revision 60cdb053 (ceph): ceph_manager: do_pg_scrub() don't resubmit a request for 2 minutes
- Add 6 minute fatal timeout
Warn when repair is being resubmitted because it causes races
Signed-off-by: David Zafman... - 04:30 AM Revision c7bcb2bd (ceph): multibench: Fixed so I can use this standalone
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 04:22 AM rgw Bug #14589 (Fix Under Review): bucket check --check-objects has not return
- 04:10 AM Linux kernel client Bug #17070 (Resolved): Kernel complains about "Bad page state" when cephfs tries to free page
- 04:09 AM Linux kernel client Bug #15432: kcephfs: umount -f can fail after mds reconnect failure
- It's not completed resolved. 'umount -f' hangs if there are hang OSD requests (caused by unhealth OSD cluster or libc...
- 03:40 AM rbd Subtask #17422 (Fix Under Review): [data pool] cls_rbd updates for data pool
- *PR*: https://github.com/ceph/ceph/pull/11327
- 02:19 AM Feature #17501 (New): ec overwrites write zeroes efficiently
- Zeroes to the data blocks are easy, zeroes to the parity blocks aren't -- not zeroes! Perhaps add some kinda writesa...
- 01:39 AM Feature #17500 (New): updated ec overwrites to support fadvise
- 01:34 AM rbd Bug #17416 (Fix Under Review): Improve resiliency of rbd-mirror stress test case
- *PR*: https://github.com/ceph/ceph/pull/11326
- 01:31 AM Revision dc77a629 (ceph): journal: avoid holding lock while sending journal append
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:31 AM Revision a9606581 (ceph): journal: use reverse iterator search to find flush record
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:31 AM Revision 4483531a (ceph): journal: delay moving overflowed buffers until quiesced
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:31 AM Revision 24faead0 (ceph): journal: clean up object recorder closed/overflow callback
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:31 AM Revision 355c79cb (ceph): librbd: ignore attempts to request lock if already lock owner
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:31 AM Revision 8c2ff9bc (ceph): rbd-mirror: potential race allocating tag during shut down
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:31 AM Revision a6dd6b50 (ceph): qa/workunits: reduce amount of client IO for rbd-mirror stress
- Journal IO is faster now, resulting in OSDs quickly filling up
under the stress test case.
Signed-off-by: Jason Dill... - 01:04 AM Feature #15623: EC Overwrites: ECBackend TPC support
- 01:04 AM Feature #14040: ECBackend support for RMW
- 01:04 AM Feature #14039: ECBackend cache extents with unapplied writes
- 12:12 AM Revision 5b3cd2ef (ceph): Merge pull request #10223 from mikulely/doc-s3-static-website-support
- doc: update s3 static webiste feature support status
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com> - 12:08 AM rgw Bug #14208: rgw: 500 returned on Put Bucket ACL (ECANCELLED/-125)
- @prallabh issue looks similar, but not the same problem afaict
- 12:06 AM Revision a8d33c08 (ceph): rgw: need to 'open_object_section' before dump stats in 'RGWGetUsage_Ob...
- Fixes: http://tracker.ceph.com/issues/17499
Signed-off-by: weiqiaomiao <wei.qiaomiao@zte.com.cn> - 12:03 AM rgw Bug #17499 (Resolved): rgw: need to modify getusage api to json encode stats correctly
- https://github.com/ceph/ceph/pull/11325
- 12:02 AM Revision c16929f6 (ceph): Merge pull request #11325 from yehudasa/wip-17499
- rgw: need to 'open_object_section' before dump stats in 'RGWGetUsage_…
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
10/04/2016
- 11:45 PM rgw Bug #17499: rgw: need to modify getusage api to json encode stats correctly
- https://github.com/ceph/ceph/pull/9495
- 11:45 PM rgw Bug #17499 (Resolved): rgw: need to modify getusage api to json encode stats correctly
- 11:34 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- I'm building it now. What logs and levels would you like me to collect?
- 10:57 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- I built a debug commit and merged in wip-17466-jewel; named the result wip-1746-jewel-debug.
- 10:05 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- there was definitely an encoding issue. I went back through the historical mdsmaps and it wasn't always insisting it ...
- 09:57 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- I think that if you use the repair tools to flush the MDS journal and then do an fs reset you should get everything b...
- 09:43 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- No, you're correct. The part you're missing is MDSMonitor::maybe_expand_cluster(), invoked from MDSMonitor::tick(). I...
- 07:37 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- https://github.com/ceph/ceph/blob/master/src/mon/MDSMonitor.cc#L2865
If I'm reading the code paths correctly, and ... - 11:02 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- Gah, I thought I saw it (created new FS and set standby_for_fscid, then saw it stuck in standby), but a few deamon re...
- 10:44 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- There is some other bug here with standby_for_rank and standby_for_fscid set correctly, I can reproduce it locally. ...
- 11:21 PM rgw Bug #17111 (Pending Backport): ERROR: got unexpected error when trying to read object: -2
- Note that we need to be careful here when backporting, there's an encoding change.
- 11:20 PM rgw Bug #17111: ERROR: got unexpected error when trying to read object: -2
- https://github.com/ceph/ceph/pull/10820
- 11:20 PM Revision 92c2c9bc (ceph): Merge pull request #10820 from yanghonggang/master
- rgw: fix get object instance returned NoSuchKey error
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 10:48 PM Revision 91a70c3e (ceph): Merge pull request #10726 from weiqiaomiao/wqm-wip-remove-ret
- rgw: remove the field ret from class RGWPutLC
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 10:34 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- What would really help here is a minimal reproducer that reliably demonstrates the issue. If we can get that it shoul...
- 10:19 PM Revision dba6a108 (ceph): Merge pull request #30 from codenrhoden/update_go_and_ceph_version
- Update Dockerfile to Go 1.7.1 and Ceph Jewel
- 10:14 PM Revision 02f45717 (ceph): os/bluestore: make BufferSpace smaller
- Saves 24 bytes!
BufferSpace 104 -> 80 bytes
SharedBlob 216 -> 192 bytes
Signed-off-by: Sage Weil <sage@redhat.com> - 10:04 PM Revision 7c5b77a6 (ceph): os/bluestore: pack SharedBlob
- 224 -> 216 bytes
Signed-off-by: Sage Weil <sage@redhat.com> - 10:03 PM Revision 2094168a (ceph): os/bluestore: pack Blob members
- 272 -> 264 bytes
Signed-off-by: Sage Weil <sage@redhat.com> - 10:00 PM Revision aefb922d (ceph): Update Dockerfile to Go 1.7.1 and Ceph Jewel
- This moves Go to 1.7.1, using Debian Jessie
Uses Ceph Jewel instead of Hammer
Uses download.ceph.com
Debian Jessie d... - 09:55 PM Revision 85256850 (ceph): rgw: dump objects in RGWBucket::check_object_index()
- Fixes: http://tracker.ceph.com/issues/14589
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:54 PM rgw Bug #14589: bucket check --check-objects has not return
- Issue was probably found by code inspection, and didn't really have any impact (other than that when running a specif...
- 09:38 PM Revision cd9d6145 (ceph): unittest_bluestore_types: a few more types for sizeof
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:03 PM rgw Backport #17339: jewel: objects in the metadata_heap pool are created, but never read or removed
- https://github.com/ceph/ceph/pull/11321
- 08:50 PM rgw Bug #13724 (Pending Backport): rgw:bucket check remove _multipart_ prefix
- https://github.com/ceph/ceph/pull/6501
- 08:49 PM Revision a8fe5554 (ceph): Merge pull request #6501 from dwj192/check-index-multipart
- rgw:bucket check remove _multipart_ prefix
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 08:10 PM rgw Bug #16894 (Pending Backport): multisite: metadata master can get the wrong value for 'oldest_log...
- 08:10 PM Revision 69b11838 (ceph): Merge pull request #10558 from cbodley/wip-rgw-mdlog-history
- rgw: store oldest mdlog period in rados
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 08:04 PM Revision ed4591c5 (ceph): os/bluestore: optimize intrusive sets for size.
- Signed-off-by: Mark Nelson <mnelson@redhat.com>
- 07:51 PM Bug #17496 (Duplicate): dump_stuck.py: assert len(unclean) == num_unclean
- ...
- 07:47 PM Bug #17021 (Can't reproduce): make check: unittest_bluefs crashes
- i haven't seen this in a while; pls reopen if you do.
- 07:44 PM Bug #17495 (Resolved): mon: bad EPERM
- ...
- 07:28 PM Revision 3ed80d97 (ceph): os/bluestore/KernelDevice: fix aio_submit race
- Behave if pending is empty.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:28 PM Revision f688302d (ceph): os/bluestore: fix has_aios -> has_pending_aios
- This is only called from safe callers (with exclusive access),
so we don't need a lock.
It also should only return t... - 06:41 PM Revision 1c6b6b49 (ceph): mds/SessionMap.cc:put classes in unnamed namespace
- So they have internal linkage.
Signed-off-by: Michal Jarzabek <stiopa@gmail.com> - 06:10 PM Revision 16e6e349 (ceph): Merge pull request #11312 from liewegas/wip-bluestore-assign-blob
- os/bluestore: fix crash in decode_some()
- 05:50 PM Revision e857b789 (ceph): rbd: recognize lock_on_read option
- Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
- 05:20 PM Revision b974dac0 (ceph): Merge pull request #10372 from cbodley/wip-rgw-data-log-trim
- rgw multisite: trim data logs as peer zones catch up
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:52 PM Revision 6b21e69a (ceph): os/bluestore: fix crash in decode_some()
- shared_blob must be non-null when we call Extent::assign_blob().
Signed-off-by: Sage Weil <sage@redhat.com> - 04:25 PM Revision 7625ebd8 (ceph): Merge pull request #1194 from ceph/wip-17416
- suites/rbd: increase timeout for rbd-mirror stress test
- 04:04 PM rbd Bug #17416: Improve resiliency of rbd-mirror stress test case
- *QA PR*: https://github.com/ceph/ceph-qa-suite/pull/1194
- 04:03 PM Revision 525e445f (ceph): suites/rbd: increase timeout for rbd-mirror stress test
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:00 PM RADOS Backport #17445: jewel: list-snap cache tier missing promotion logic (was: rbd cli segfault when ...
- Moving to core team to verify if the empty "snaps" vector in "librados::clone_info_t" is a newly introduced issue in ...
- 03:39 PM Revision 96707194 (ceph): Merge pull request #11295 from liewegas/wip-bluestore-cache
- os/bluestore: make cache settings process-wide
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 03:22 PM Revision 3e4a59d8 (ceph): Merge pull request #11291 from trociny/wip-qa-mirror-asok
- qa/workunits/rbd: check status also in pool dir after asok commands
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:17 PM rbd Subtask #17422 (In Progress): [data pool] cls_rbd updates for data pool
- 03:15 PM rgw Bug #17387 (Pending Backport): multisite: 'radosgw-admin period prepare' is obsolete
- 03:14 PM Revision 8c2dc6ea (ceph): Merge pull request #11278 from gaurav36/wip-obsolete-rgw-admin-period-p...
- rgw: obsolete 'radosgw-admin period prepare' command
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 03:14 PM Revision b16bd778 (ceph): unittest_bluestore_types: show sizeof for key types
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:03 PM Revision fcf61342 (ceph): Merge pull request #11307 from jcsp/wip-mgr-compile
- mgr: squash compiler warnings
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl> - 02:59 PM Revision 304a3b1b (ceph): os/bluestore: use Extent::assign_blob
- More explicit, less error-prone.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:44 PM Revision 7a93aa87 (ceph): Merge pull request #11299 from liewegas/wip-mgr-fix
- mgr: implement con reset handling
Reviewed-by: John Spray <john.spray@redhat.com> - 02:05 PM mgr Bug #17492 (Resolved): MgrMonitor: valgrind UninitCondition failures
- 01:23 PM mgr Bug #17492 (Fix Under Review): MgrMonitor: valgrind UninitCondition failures
- https://github.com/ceph/ceph/pull/11308
- 05:47 AM mgr Bug #17492 (Resolved): MgrMonitor: valgrind UninitCondition failures
- This is triggering failures in our valgrind tests. Among others, http://qa-proxy.ceph.com/teuthology/gregf-2016-10-03...
- 02:05 PM Revision d5c6a961 (ceph): Merge pull request #11308 from liewegas/wip-mgr-valgrind
- mgr/MgrMap: initialize all fields
Reviewed-by: John Spray <john.spray@redhat.com> - 02:01 PM Revision f48690eb (ceph): os/bluestore: only split blobs on min_alloc_size boundaries
- Otherwise we can throw off the allocator.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:58 PM Revision 1508c70d (ceph): rgw multisite: obsolete 'radosgw-admin period prepare' command
- All that the 'radosgw-admin period prepare' command does is create an
empty period and write it to rados. When we add... - 01:49 PM Revision c6a7d48f (ceph): pybind: clean up mgr stuff for flake8
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:37 PM Revision ed450d68 (ceph): os/bluestore: prune deallocated blob tails
- This saves us space: no invalid extent, and no unused csum_data.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 1a39872b (ceph): os/bluestore: try to split blobs instead of spanning them
- If a blob crosses a shard boundary, try to split it into pieces
instead of making it spanning. This is only possible... - 01:23 PM Revision 5b3e7162 (ceph): mgr/MgrMap: initialize all fields
- Fixes: http://tracker.ceph.com/issues/17492
Signed-off-by: Sage Weil <sage@redhat.com> - 01:21 PM rbd Feature #16212 (Resolved): Replicate image metadata settings
- 01:12 PM Revision a22bb9cb (ceph): mgr: squash compiler warnings
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:12 PM Revision 0aab9e27 (ceph): Merge pull request #11254 from xiexingguo/xxg-wip-fs-0929
- mds/MDCache: kill a comipler warning
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 01:06 PM rbd Bug #17494 (Resolved): memory leak in MirroringWatcher::notify_image_updated
- 01:05 PM rbd Bug #17494 (Pending Backport): memory leak in MirroringWatcher::notify_image_updated
- 01:04 PM rbd Bug #17494: memory leak in MirroringWatcher::notify_image_updated
- *PR*: https://github.com/ceph/ceph/pull/11306
- 01:04 PM rbd Bug #17494 (Resolved): memory leak in MirroringWatcher::notify_image_updated
- The librados::AioCompletion is not released
- 01:06 PM rbd Feature #16213 (Resolved): Replicate dynamic feature updates
- 01:05 PM Revision baa2202e (ceph): Merge pull request #11306 from trociny/fixup-notify_image_updated
- librbd: memory leak in MirroringWatcher::notify_image_updated
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:00 PM Revision 3b021d66 (ceph): Merge pull request #11303 from ceph/wip-rbd-clarify-size
- doc: clarify rbd size units
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:54 PM Revision 91d7de44 (ceph): librbd: memory leak in MirroringWatcher::notify_image_updated
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:49 PM rbd Bug #17355 (Pending Backport): rbd-mirror: potential crash during replay shut down
- Also requires changes from #17446
- 12:49 PM rbd Bug #17446 (Pending Backport): assert failure in run-rbd-unit-tests.sh
- 12:48 PM Revision 476820bf (ceph): Merge pull request #11257 from trociny/wip-17355-fixup
- journal: ensure in-flight ops are complete destroying journaler
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:38 PM CephFS Bug #17468: CephFs: IO Pauses for more than a 40 seconds, while running write intensive IOs
- 1. MDS runs with default configuration.
2. On MDS node, I ran following commands:
# ceph --admin-daemon ceph-md... - 11:32 AM CephFS Bug #17216: ceph_volume_client: recovery of partial auth update is broken
- Proposed fix: https://github.com/ceph/ceph/pull/11304
- 11:30 AM Revision 2d1f1646 (ceph): Merge pull request #11259 from b-ranto/wip-selinux-tmp-files
- selinux: Allow ceph to manage tmp files
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 11:23 AM Revision a95de788 (ceph): ceph_volume_client: check if volume metadata is empty
- ... when recovering from partial auth updates.
Auth update happens in the following order:
auth metadata update, vol... - 11:23 AM Revision 0ab8badc (ceph): ceph_volume_client: fix partial auth recovery
- ... for volumes whose group_id is None.
Signed-off-by: Ramana Raja <rraja@redhat.com> - 11:21 AM Revision 675cb91b (ceph): ceph_volume_client: fix _recover_auth_meta() method
- It needs to be an instance method.
Fixes: http://tracker.ceph.com/issues/17216
Signed-off-by: Ramana Raja <rraja@red... - 10:51 AM Revision 6dda2b93 (ceph): rbd-mirror HA: move librbd::image_watcher::Notifier to librbd::object_w...
- Fixes: http://tracker.ceph.com/issues/17017
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 09:57 AM Revision f1fb667d (ceph): messages: fix MMDSBeacon constructor
- This was leaving garbage in some fields during decode
when decoding messages with an older version.
Fixes: http://tr... - 08:21 AM Revision d38dc29e (ceph): doc: clarify rbd size units
- It wasn't clear from the man page that --size defaults to M.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com> - 06:39 AM Revision 5c291855 (ceph): doc: fix librados example programs
- basically s/rados_wait_for_(safe|complete)/rados_aio_wait_for_\1/g
Signed-off-by: Alexey Sheplyakov <asheplyakov@mir... - 05:32 AM CephFS Bug #17368 (Resolved): mds: allowed GIDs must be ordered in the cephx string
- 05:32 AM CephFS Bug #16367 (Resolved): libcephfs: UID parsing breaks root squash (Ganesha FSAL)
- 05:30 AM Revision 11023860 (ceph): Merge pull request #11218 from ceph/wip-getuid
- Client: pass "UserPerm" struct everywhere for security checks
Reviewed-by: Jeff Layton <jlayton@redhat.com> - 04:43 AM Revision 8833c644 (ceph): PG: block writes and scan log for scrub using inclusive upper bound
- See comment in commit.
Signed-off-by: Samuel Just <sjust@redhat.com> - 04:43 AM Revision 2176c847 (ceph): hobject: clarify is_snap and has_snapset for max
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit a2c27c9423b43b8c5633fb0af95f28b0de94b365) - 04:43 AM Revision 16f9d952 (ceph): src/osd: relax the requirement that we scrub a whole hash value
- Previously, we needed to scrub all objects in clones in a single
hash value mainly to ensure that _scrub had access t... - 04:43 AM Revision 0e2338e5 (ceph): osd_types,PG: force the map used in _scrub to be sorted correctly
- Previously, ScrubMap::objects was always sorted bitwise (nibblewise
before the comparator change was made. It didn't... - 04:05 AM Revision 6d410e97 (ceph): osd_types,PG: force the map used in _scrub to be sorted correctly
- Previously, ScrubMap::objects was always sorted bitwise (nibblewise
before the comparator change was made. It didn't... - 01:18 AM Revision d43b69e5 (ceph): rgw: fix versioned object IO error
- When accessing a copied destination object, its source object's instance ID
information is needed, however it's m...
10/03/2016
- 11:57 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- ceph-post-file: 731781d4-c78c-47f9-9de3-e151b5c1a5f9
Above is the Monitor log with a fresh boot of the mds. - 10:06 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- That FSMap contains a standby with '"standby_for_fscid": 0', but the existing filesystem is '"id": 2'.
Had him set i... - 03:18 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- In fact, the mdsmap epoch is quite a lot larger than I remember it. I think it was in the low 50's before this issue...
- 03:08 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- I've cherry-picked the mds and mon fixes from your pull-request onto jewel and built a new version. this allowed me t...
- 06:46 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- wip-17466-jewel is building with a minimal fix rebased on v10.2.3
https://github.com/ceph/ceph/pull/11281 has the ... - 06:39 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- I think this is happening when older MDSs send a beacon to newer mons, because MMDSBeacon isn't initialising POD fiel...
- 06:30 AM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- ...
- 11:51 PM Revision e7253b8e (ceph): rgw_admin: add bi purge command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_admin.cc - 10:42 PM Revision 8c4cabec (ceph): unittest_bluestore_types: attach blobs to cache
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:42 PM Revision a7069083 (ceph): os/bluestore: instrument cache blob and extent counts
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:42 PM Revision 05bb253c (ceph): os/bluestore: drop unnecessary assert
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:42 PM Revision 0118293a (ceph): os/bluestore: turn bluestore_onode_cache_size 16k -> 4k
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:40 PM Revision 33e26d02 (ceph): os/bluestore: add perf counters for cache size
- Onodes, buffers, buffer bytes.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:40 PM Revision c8a06ce1 (ceph): do_cmake.sh: set .ceph_port to random port
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:40 PM Revision cbfa540c (ceph): os/bluestore: fix cache tunables to be process-wide
- Divide by the shard count so that the user isn't totally
confused.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:40 PM Revision 60987610 (ceph): os/bluestore: fix typo in write_penalty_read_ops perf counter
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:15 PM Bug #17491 (Rejected): Hammer: PGBackend::objects_list_range includes end as well for ec pools
- This wasn't a problem for scrub before since end was always a boundary, but never a valid object. When end becomes a...
- 10:11 PM Revision 2efe0512 (ceph): Merge pull request #11300 from liewegas/wip-bluestore-onode-add
- os/bluestore: fix onode cache addition race
- 09:37 PM Revision 2150e991 (ceph): os/bluestore: fix onode cache addition race
- Two threads may try to add the same onode to the cache.
This is rare, but allowed (in the case of the meta
collection... - 09:33 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- "Me too!"
Of note:
* Ceph Jewel 10.2.2
* Started manifesting recently, after putting actual load onto cephfs (I.... - 09:24 PM rgw Bug #15896: S3: set EncodingType in ListBucketResult
- Well.
Our logs show that 0.94.9 was applied in our environment on August 31, 2016.
I created this ticket when ... - 08:02 PM rgw Bug #16494 (Pending Backport): S3 object versioning fails when applied on a non-master zone
- 07:16 PM Revision de749df5 (ceph): mds: add tests for mantle (programmable balancer)
- - rebased to add block rados pull test
Signed-off-by: Michael Sevilla <mikesevilla3@gmail.com> - 06:42 PM Revision f7a9a6f6 (ceph): mgr/MgrClient: implement con reset handling
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:25 PM Revision 70e02896 (ceph): rgw: Fix Host->bucket fallback logic inversion
- The logic (added in 46aae19ee) for falling back to just using the hostname as
the possible bucket name contained an a... - 06:25 PM Revision 7c7ad3cc (ceph): rgw: only enable virtual hosting if hostnames are configured
- if no hostnames are configured, all requests were treated as virtual
hosted buckets. require at least one hostname in... - 06:25 PM Revision 36203c28 (ceph): doc: configuring virtual hosted buckets for radosgw
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:25 PM Revision aa34b986 (ceph): rgw: filter out empty virtual bucket hostnames
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:25 PM Revision 2d6efe88 (ceph): rgw: add commas to hostname output
- std::accumulate() was appending hostnames without commas or spaces
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:13 PM Revision e8261e52 (ceph): fs: enable ceph-fuse permission checking for all pjd suites
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 06:13 PM Revision 8d37c68b (ceph): Merge pull request #11298 from liewegas/wip-mgr-fix
- mgr/MgrClient: fix ms_handle_reset
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:03 PM rgw Backport #17480: jewel: ACL request for objects with underscore at end and beginning
- (Note Yehuda's comment in the original bug, that we will also need to backport #17443 to jewel alongside this one.)
- 01:28 PM rgw Backport #17480 (Resolved): jewel: ACL request for objects with underscore at end and beginning
- https://github.com/ceph/ceph/pull/11563
- 05:59 PM Revision 848ee059 (ceph): mgr/MgrClient: fix ms_handle_reset
- Return false because we don't handle the reset.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:08 PM rbd Feature #17489 (Resolved): [iscsi]: add support for librbd via LIO TCMU userspace passthrough
- This would be similar to rbd-nbd but using iSCSI instead of NBD to present a userspace librbd image to the kernel.
- 04:44 PM rbd Feature #17488 (Resolved): rbd-nbd: support disabling auto-exclusive lock transition logic
- The librbd API now exposes the exclusive-lock API, it should support locking the image so that it cannot be mapped on...
- 03:53 PM Revision cfc0a16e (ceph): Merge pull request #11292 from rzarzynski/yj-wip-swift-build_token-cleanup
- rgw/swift: remove redundant assignment operation
Reviewed-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 03:52 PM Revision eb621207 (ceph): Merge pull request #11019 from liewegas/wip-autotools-must-die
- autotools: remove a few other remaining traces
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:50 PM Revision ada72704 (ceph): Merge pull request #11294 from trociny/fixup-qa-rbd_mirror-metadata_set
- qa/workunits/rbd: set image-meta on primary image and wait it is replicated
Reviewed-by: Jason Dillaman <dillaman@re... - 03:17 PM Revision 54134418 (ceph): osd: drop stray debug message
- This snuck in from 10da6d23cd447044ff38079807a7f36a5c347270
Signed-off-by: Sage Weil <sage@redhat.com> - 02:26 PM Revision 8242afb1 (ceph): Merge pull request #11288 from stiopaa1/osd_replicatedpg_moveCOSDOnAppl...
- osd/ReplicatedPG:move C_OSD_OnApplied class to cc
Reviewed-by: Sage Weil <sage@redhat.com> - 02:25 PM Revision dbef9d05 (ceph): Merge pull request #11289 from stiopaa1/mds_sessionmap_moveStatementUnd...
- mds/SessionMap.h: change statement to assertion
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 02:02 PM Revision eb4097b8 (ceph): qa/workunits/rbd: set image-meta on primary image and wait it is replic...
- After recently added image metadata replication it is not possible any
more to update it on non-primary image.
Signe... - 01:59 PM Revision 5e0daf66 (ceph): mon/OSDMonitor: encode canonical full osdmap based on osdmap flags
- If the JEWEL or KRAKEN flags aren't set, encode the full map without
those features. This ensure that older OSDs in ... - 01:50 PM Stable releases Tasks #17487: jewel v10.2.4
- h3. Upgrade...
- 01:49 PM Stable releases Tasks #17487: jewel v10.2.4
- h3. powercycle...
- 01:49 PM Stable releases Tasks #17487: jewel v10.2.4
- h3. fs...
- 01:49 PM Stable releases Tasks #17487: jewel v10.2.4
- h3. rados ...
- 01:48 PM Stable releases Tasks #17487: jewel v10.2.4
- h3. rgw...
- 01:48 PM Stable releases Tasks #17487: jewel v10.2.4
- h3. rbd...
- 01:47 PM Stable releases Tasks #17487: jewel v10.2.4
- ...
- 01:38 PM Stable releases Tasks #17487 (Resolved): jewel v10.2.4
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 01:46 PM Revision 5bd88a54 (ceph): make-debs.sh: use make-dist
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:46 PM Revision b424a35f (ceph): run-make-check.sh: use cmake exclusively
- ..and drop the separate cmake script
Signed-off-by: Sage Weil <sage@redhat.com> - 01:42 PM CephFS Bug #17468 (In Progress): CephFs: IO Pauses for more than a 40 seconds, while running write inten...
- 01:27 PM CephFS Bug #17468: CephFs: IO Pauses for more than a 40 seconds, while running write intensive IOs
- I collected stack unwind traces in MDS process while no I/O was observed during write ops on cephFS. Stack trace freq...
- 01:40 PM rbd Bug #16529 (Resolved): "[ FAILED ] TestClsRbd.mirror_image" in upgrade:jewel-x-master-distro-ba...
- 01:35 PM Stable releases Tasks #16344 (Resolved): jewel v10.2.3
- 01:30 PM rbd Backport #17486 (Resolved): jewel: Optionally unregister "laggy" journal clients
- https://github.com/ceph/ceph/pull/11433
- 01:30 PM rbd Backport #17485 (Resolved): jewel: Periodically update the sync point object number during sync
- https://github.com/ceph/ceph/pull/10678
- 01:29 PM rbd Backport #17484 (Resolved): jewel: performance: journaling results in 4X slowdown when writes are...
- https://github.com/ceph/ceph/pull/11433
- 01:29 PM rbd Backport #17483 (Resolved): jewel: RBD should restrict mirror enable/disable actions on parents/c...
- https://github.com/ceph/ceph/pull/11459
- 01:29 PM rbd Backport #17482 (Resolved): jewel: Enable/Disable of features is allowed even the features are al...
- https://github.com/ceph/ceph/pull/11460
- 01:29 PM rbd Backport #17481 (Resolved): jewel: Proxied operations shouldn't result in error messages if replayed
- https://github.com/ceph/ceph/pull/11461
- 01:28 PM CephFS Backport #17479 (Resolved): jewel: Duplicate damage table entries
- https://github.com/ceph/ceph/pull/11412
- 01:28 PM CephFS Backport #17478 (Resolved): jewel: MDS goes damaged on blacklist (failed to read JournalPointer: ...
- https://github.com/ceph/ceph/pull/11413
- 01:28 PM CephFS Backport #17477 (Resolved): jewel: Crash in Client::_invalidate_kernel_dcache when reconnecting d...
- https://github.com/ceph/ceph/pull/11414
- 01:28 PM CephFS Backport #17476 (Resolved): jewel: Failure in snaptest-git-ceph.sh
- https://github.com/ceph/ceph/pull/11415
- 01:27 PM rbd Backport #17475 (Resolved): jewel: rbd-mirror: potential race condition results in heap corruption
- https://github.com/ceph/ceph/pull/11433
- 01:27 PM CephFS Backport #17474 (Resolved): jewel: Failure in dirfrag.sh
- https://github.com/ceph/ceph/pull/11416
- 01:27 PM devops Backport #17472 (Resolved): jewel: rpm: /etc/ceph/rbdmap is packaged with executable access rights
- https://github.com/ceph/ceph/pull/11855
- 01:27 PM rgw Backport #17471 (Resolved): jewel: rgw: versioning is broken in current master
- https://github.com/ceph/ceph/pull/11563
- 12:11 PM Revision f0ae5fe1 (ceph): rgw/swift: remove redundant assignment operation
- Signed-off-by: Yan Jun <yan.jun8@zte.com.cn>
- 09:43 AM Revision 00873f26 (ceph): Merge pull request #11086 from bassamtabbara/wip-ec-simd-runtime-detection
- erasure-code: Runtime detection of SIMD for jerasure and shec
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Review... - 08:09 AM rbd Subtask #17018 (In Progress): rbd-mirror HA: add new lock released/acquired and heartbeat messages
- 07:10 AM Revision 2882f8c0 (ceph): qa/workunits/rbd: check status also in pool dir after asok commands
- wait_for_image_replay_stopped returns not when the state is stopped,
but when the state is not replaying. So a race w... - 07:08 AM rbd Subtask #17017 (Fix Under Review): rbd-mirror HA: move librbd::image_watcher::Notifier to librbd:...
- https://github.com/ceph/ceph/pull/11290
- 06:42 AM Revision 92fdcf36 (ceph): mon: don't crash on invalid standby_for_fscid
- Fixes: http://tracker.ceph.com/issues/17466
Signed-off-by: John Spray <john.spray@redhat.com> - 06:42 AM Revision 63d711d4 (ceph): mds: make mds_role_t member order match constructor
- Previously this was mildy confusing.
Signed-off-by: John Spray <john.spray@redhat.com> - 06:23 AM Linux kernel client Bug #17410: rbd image stale/stuck (mapped and mounted)
- When i investigate "cat /sys/kernel/debug/ceph/*/osdc" on problem node, i see stuck static picture.
When i restart o...
10/02/2016
- 09:06 PM Revision e3c26b94 (ceph): mds/SessionMap.cc: avoid copying and add const
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 08:34 PM CephFS Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
- Oliver: use "ceph daemon mds.<id> objecter_requests" to see if the MDS is stuck waiting for operations from the OSDs.
- 09:30 AM Revision 677c8f6a (ceph): mds/SessionMap.h: change statement to assertion
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
10/01/2016
- 04:49 PM Revision 675c1e44 (ceph): osd/ReplicatedPG:move C_OSD_OnApplied class to cc
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 04:26 PM Feature #17470 (Resolved): Improve deep-scrub performance with many snapshots
This is accomplished by improving the scrub boundary requirements, so that we don't have a scrub an entire hash val...- 03:47 PM Bug #17469 (Can't reproduce): Dead job rados, bench never finishes
/home/teuthworker/archive/dzafman-2016-09-30_13:00:52-rados-wip-zafman-testing2-distro-basic-smithi/445132
teuth...- 08:24 AM Revision 55762cca (ceph): journal: complete action only after notification completed
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 08:24 AM Revision a25b1d7c (ceph): journal: ensure in-flight ops are complete destroying journaler
- Fixes: http://tracker.ceph.com/issues/17446
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 06:02 AM CephFS Bug #17468 (Closed): CephFs: IO Pauses for more than a 40 seconds, while running write intensive IOs
- CephFs Environment:
1 MDS node
1 Ceph Kernel Filesystem, Ubuntu 14.04 LTS, kernel version 4.4.0-36-generic
Test ... - 05:29 AM Revision 5581510b (ceph): librbd: fix rollback if failed to disable mirroring for image
- Signed-off-by: runsisi <runsisi@zte.com.cn>
09/30/2016
- 11:43 PM Revision 27bdc8ce (ceph): src/osd: relax the requirement that we scrub a whole hash value
- Previously, we needed to scrub all objects in clones in a single
hash value mainly to ensure that _scrub had access t... - 11:22 PM rgw Bug #16930 (Fix Under Review): s3tests-test-readwrite failing with 500
- https://github.com/ceph/ceph/pull/11286
- 11:13 PM Revision 6e9a915b (ceph): rgw: don't fail if lost race when setting acls
- Fixes: http://tracker.ceph.com/issues/16930
When concurrently setting acls on object/bucket, we could lose in a race... - 10:40 PM Revision 62d8e60c (ceph): Merge pull request #11285 from liewegas/wip-mgr-rpm
- ceph.spec: fix ceph-mgr version requirement
Reviewed-by: Dan Mick <dmick@redhat.com> - 10:19 PM Revision 42b15729 (ceph): client: in UserPerm, correctly use delete[] and don't leak gids on copy
- gids is an array. We also need to clean it up when deep_copy()ing, which
requires initializing our member fields in t... - 10:18 PM Revision dc23fc88 (ceph): Squashed 'src/dmclock/' content from commit 1335fda
- git-subtree-dir: src/dmclock
git-subtree-split: 1335fda339ae3a8b76fca5159d596439ff348bc8 - 10:18 PM Revision 2c82ccfc (ceph): Merge commit 'dc23fc881d7f108d4fc776b68f645f0aa14c91aa' as 'src/dmclock'
- 10:17 PM Revision 230bfa60 (ceph): Add some comments to make clear the requirements of implementations of
- virtual functions.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 7b0501c5 (ceph): Change code to make sure removals visit client ops in reverse order
- and use push_front to maintain correct ordering. Use updated
interfaces for the dmclock library.
Signed-off-by: J. E... - 10:17 PM Revision 9e36372d (ceph): Update git subtree scripts to use dmclock ceph branch rather than
- master branch.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 224cc050 (ceph): Progress on removing requests by class/client and by filter. Add
- ability to collect requests removed by filter into a collection.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision b0e5a21a (ceph): Separate PGQueueable to its own file, so OSD and mClockOpClassAdapter
- could both depend on it. When PGQueueable is embedded in OSD, it and
mClockOpClassAdpter are mutually dependent.
Sig... - 10:17 PM Revision fdb505cc (ceph): Continue working on adapter.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 83f506ed (ceph): Make constructor for PGQueueable explicit to make references to that
- specific constructor easier to find. Was difficult With the implicit
constructor invokation plus use of make_pair. - 10:17 PM Revision b58ca2b1 (ceph): Finish filling out contract. Figure out what op_type_t we have based
- on the PGQueueable object.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision d672eb9b (ceph): Create some barely more realistic default values for mclock tagging
- config params.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision ba17be15 (ceph): Fix issues with changes in dmclock interface regarding filters.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 2c42c743 (ceph): Since mClockOpClassAdapter is OSD-specific, move it from common to
- osd. Update cmake files and #includes accordingly.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 658dd7d2 (ceph): Clean up ceph namespace and put types and variables only needed by
- mClockOpClassQueue in that class.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision d3876dc8 (ceph): Add infrastructure for ceph logging.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 6f5f8866 (ceph): Make minimal changes to autotools so it can build dmclock integration,
- knowing that autotools will disappear soon.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 2eb9868f (ceph): Create mclock queue where the classes tracked are combinations of
- client id and the operator type.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 6543727f (ceph): Make signature of queue filters to take a const reference to the "op"
- to both save on copying and to insure that if the "op" were in the
future to ever be something not copyable (e.g., st... - 10:17 PM Revision f380c2bf (ceph): Split off PGQueueable definitions into own .cc file.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 5df06449 (ceph): Modify autotools files that were modified to accomodate dmclock to use
- new location of gtest files.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 61ac717c (ceph): Add documentation.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision c9457e5c (ceph): Make get_osdmap_epoch const since it can be and so it can be called on
- const OSD instances.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 65190b47 (ceph): Move enqueue* and dequeue methods from .h to .cc file, to make it
- easier for future debugging output.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision b1beb897 (ceph): Add operator<< for const Request& type.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 6dcc159c (ceph): Add scripts to add and pull subtrees for convenience in future,
- especially if subtrees will be the preferred method over
submodules. Method used documented here:
https://develo... - 10:17 PM Revision 0dcb621d (ceph): Modify CMakeLists.txt files so that gtest is a target for an outer
- CMake file, it still works.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 5de2c660 (ceph): Include the dmclock subdirectory in the cmake tree.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision c11109bd (ceph): Add shell script to help pushing the subtree to its repo.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 4673da8b (ceph): Integrate implementation files and unit test files. Can now
- "make unittest_mclock_priority_queue", although currently does not
compile.
Signed-off-by: J. Eric Ivancich <ivancic... - 10:17 PM Revision 905d8368 (ceph): Check-in. Does not compile.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 6871ad12 (ceph): Progress.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision cb0a7d3b (ceph): Include cmath. Change client info func so it takes a const reference
- as a parameter.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision 6c2ec2c2 (ceph): Integrate mClock I/O queue option into OSDs.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 3b710d3c (ceph): Progress.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision b9f59587 (ceph): Allow io_queue objects to be displayed now that it's an enum class
- rather than enum.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 10:17 PM Revision c76c906c (ceph): Remove cmake warning by removing non-matching endif paramater.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 4ad249df (ceph): Progress.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision 9f6a0657 (ceph): Continue work on filling out OpQueue contract.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 10:17 PM Revision dd9a2a6e (ceph): For non-testing source files that use the FRIEND_TEST macro in gtest
- or anything similar, access to the gtest include files is necessary.
Signed-off-by: J. Eric Ivancich <ivancich@redha... - 10:13 PM Revision 3447601a (ceph): ceph.spec: fix ceph-mgr version requirement
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:58 PM rgw Bug #17272: S3: Batch operations fail
- @ayang I tried to reproduce the exact scenario you provided here. Verified that it works correctly in 0.94.9. Also ve...
- 09:54 PM Feature #17220 (Resolved): ceph-objectstore-tool: ability to perform filestore splits offline
- 09:54 PM Backport #17383 (Resolved): hammer: ceph-objectstore-tool: ability to perform filestore splits of...
- 09:54 PM Backport #17263 (Resolved): jewel: ceph-objectstore-tool: ability to perform filestore splits off...
- 09:50 PM CephFS Bug #17466: MDSMonitor: non-existent standby_for_fscid not caught
- So now it seems like although the order of members was whacky, calls to = {fsicd, rank} were actually assigning the v...
- 08:59 PM CephFS Bug #17466 (Fix Under Review): MDSMonitor: non-existent standby_for_fscid not caught
- https://github.com/ceph/ceph/pull/11281
- 08:48 PM CephFS Bug #17466 (Resolved): MDSMonitor: non-existent standby_for_fscid not caught
- We've got it using aggregate initialization (that is, the explicity {a, b} syntax), but we're ordering the rank and f...
- 09:40 PM Revision 3e343805 (ceph): rgw: set multipart copy source object as atomic, prefetch
- Object's head should only be read once.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:32 PM Revision f4e53b91 (ceph): mds: include legacy client fsid in FSMap print
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:19 PM CephFS Feature #17434: qa: background rsync task for FS workunits
- When we build this, we should include some performance metrics gathering. Many of our bugs around cap handling here a...
- 09:17 PM Revision ad6aeb0f (ceph): Merge pull request #11282 from liewegas/wip-bluestore-gc-fix
- os/bluestore: fix gc when blob extends past eof
- 09:06 PM Revision 570615b6 (ceph): os/bluestore: fix gc when blob extends past eof
- This can happen if we aren't referencing the bob. Don't try to
read what isn't logically referenced.
Signed-off-by:... - 08:34 PM rgw Bug #16854: the usage log record date is 16 hours later than the real operate time in jewel1 10....
- Some status: in my current attempts to reproduced, I see slightly different behavior:
1. after adding "rgw enable u... - 07:57 PM rgw Backport #16564 (Resolved): jewel: cors auto memleak
- 06:50 PM Revision 2dc57754 (ceph): Merge pull request #11279 from liewegas/wip-bluestore-gc
- os/bluestore: compaction fixes
- 06:49 PM Revision ea0aee60 (ceph): os/bluestore: fix compaction left-side length
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 1164a302 (ceph): os/bluestore: more concise SharedBlob print
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:23 PM Revision 506e4aed (ceph): os/bluestore: cosmetic gc cleanups
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:02 PM Revision 84adafe3 (ceph): Merge pull request #10656 from dachary/wip-16564-jewel
- jewel: cors auto memleak
- 05:57 PM Revision 75bf4d18 (ceph): Merge pull request #11271 from stiopaa1/osd_repicatedpg_addOverride
- osd/ReplicatedPG.h: add override to virtual funct
Reviewed-by: Sage Weil <sage@redhat.com> - 05:47 PM Revision ce9781ae (ceph): Merge pull request #11239 from liewegas/wip-bluestore-max-blob
- os/bluestore: add max blob size; fix compressed min blob size logic
Reviewed-by: Somnath Roy <somnath.roy@sandisk.com> - 05:47 PM Revision beed4332 (ceph): os/bluestore: set min compressed blob size floor at 2x min_alloc_size
- Otherwise there's not point in compressing--we won't be able to
allocation a smaller space to store it.
Signed-off-b... - 05:47 PM Revision f32b682f (ceph): os/bluestore: adjust compression blob sizes down
- These were way too big. 64KB is enough to get good compression,
and 4MB is way too big.
Signed-off-by: Sage Weil <s... - 05:47 PM Revision 87f6d23b (ceph): os/bluestore: introduce bluestore_max_blob_size
- This is enforced for compressed and non-compressed blobs alike.
We keep the separate compressoin min and max tunables... - 05:45 PM Revision a389a29e (ceph): os/bluestore: fix blob depth encoding
- 1) Fix the flag constnat
2) Redefine the meaning to be more intuitive.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:16 PM Revision 55e3e774 (ceph): rgw_admin: better bucket reshard logging
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_admin.cc - 05:16 PM Revision f07e22ae (ceph): rgw_admin: require --yes-i-really-mean-it for bucket reshard
- in the case where num shards are less or equal to current bucket
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 05:16 PM Revision 6503430d (ceph): cls/rgw: bi_list() fix is_truncated returned param
- is_truncated was never set. Also, make sure that we don't return
more entries than requested.
Signed-off-by: Yehuda ... - 05:16 PM Revision 4f605ebf (ceph): rgw: bucket resharding, adjust logging
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:16 PM Revision 6c3e734c (ceph): rgw: rgw_link_bucket, use correct bucket structure for entry point
- The bucket structure might be different than the one that we were using
before.
Signed-off-by: Yehuda Sadeh <yehuda@... - 05:16 PM Revision 37cda4ec (ceph): rgw_admin: reshard also links to new bucket instance
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:16 PM Revision 858bcf18 (ceph): cls/rgw: add bucket_update_stats method
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:16 PM Revision a68d56fe (ceph): rgw: bucket reshard updates stats
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/cls/rgw/cls_rgw_types.h
src/rgw/rgw_admin.cc - 05:16 PM Revision 6e91760e (ceph): rgw_admin: use aio operations for bucket resharding
- also created shards manager to make things slightly cleaner
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflic... - 05:16 PM Revision b6a15514 (ceph): rgw_admin: fix bi list command
- Changes scoping of json section, and push the --object param in so that
an object can be specified as a filter.
Sign... - 05:16 PM Revision 75f69da3 (ceph): rgw: limit bucket reshard num shards to max possible
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_admin.cc
src/rgw/rgw_rados.h - 05:16 PM Revision 53982a2e (ceph): rgw_admin: bucket rehsrading, initial work
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_admin.cc - 05:16 PM Revision b2cc000b (ceph): cls/rgw: fix bi_list objclass command
- was filtering entries, even if filter was not specified, and need to
set boundary for plain entries. Also, list_insta... - 05:16 PM Revision 7cc1de86 (ceph): radosgw-admin: bucket reshard needs --num-shards to be specified
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_admin.cc - 04:27 PM CephFS Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
- Hi,
i fully understand that this things might not be trivial.
But we have again that issue. Due to a network p... - 03:23 PM rgw Bug #17465 (Resolved): multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED errors
- An assert that detects deadlocks between coroutines in RGWCoroutinesManager::run() is triggered when a lot of corouti...
- 03:04 PM rgw Bug #17387 (Fix Under Review): multisite: 'radosgw-admin period prepare' is obsolete
- 12:07 PM rgw Bug #17387: multisite: 'radosgw-admin period prepare' is obsolete
- PR: https://github.com/ceph/ceph/pull/11278
- 02:52 PM RADOS Backport #17445: jewel: list-snap cache tier missing promotion logic (was: rbd cli segfault when ...
- Jason Dillaman wrote:
> The "snaps" vector in "librados::clone_info_t" is unexpectedly empty for cloneid 20 and 26.
... - 02:48 PM RADOS Backport #17445: jewel: list-snap cache tier missing promotion logic (was: rbd cli segfault when ...
- The "snaps" vector in "librados::clone_info_t" is unexpectedly empty for cloneid 20 and 26....
- 02:41 PM RADOS Backport #17445: jewel: list-snap cache tier missing promotion logic (was: rbd cli segfault when ...
- ...
- 01:51 PM RADOS Backport #17445: jewel: list-snap cache tier missing promotion logic (was: rbd cli segfault when ...
- Jason Dillaman wrote:
> @Bart: would it be possible for you to install the debug packages (librados2-dbg, librbd1-db... - 01:35 PM RADOS Backport #17445 (Need More Info): jewel: list-snap cache tier missing promotion logic (was: rbd c...
- @Bart: would it be possible for you to install the debug packages (librados2-dbg, librbd1-dbg, ceph-common-dbg) and r...
- 08:09 AM RADOS Backport #17445 (Resolved): jewel: list-snap cache tier missing promotion logic (was: rbd cli seg...
- https://github.com/ceph/ceph/pull/17707
- 02:43 PM Revision c72bcd66 (ceph): Merge pull request #11232 from Roushan81/wip-bluestore-blob-gc
- os/bluestore: garbage collect partially overlapped blobs
Reviewed-by: Sage Weil <sage@redhat.com> - 02:41 PM Revision 599b6e45 (ceph): Merge pull request #11263 from liewegas/wip-bluestore-reshard-slop
- os/bluestore: sloppy reshard boundaries to avoid spanning blobs
Reviewed-by: Somnath Roy <somnath.roy@sandisk.com> - 02:21 PM Revision 6bf86fef (ceph): Merge pull request #11275 from xiexingguo/xxg-wip-make-audit-buffer-option
- os/bluestore: drop redundant call of get_blob
Reviewed-by: Sage Weil <sage@redhat.com> - 02:12 PM Revision a2aaf2b4 (ceph): os/bluestore: drop redundant call of get_blob
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:51 PM Revision 09494423 (ceph): Merge pull request #11268 from liewegas/wip-bluefs-aio-leak
- os/bluestore/BlueFS: release completed aios
- 01:39 PM Revision 42d51117 (ceph): Merge pull request #11005 from jazeltq/add-sparse-read
- rbd-mirror: Add sparse read for sync image
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:37 PM Revision f3d39411 (ceph): Merge pull request #11168 from trociny/wip-16212
- rbd-mirror: replicate image metadata settings
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:33 PM Revision 71dacd88 (ceph): Merge pull request #1193 from ceph/wip-16016
- suites: update log whitelist for scrub msg
- 01:31 PM Revision 979c6e87 (ceph): Merge pull request #11274 from xiexingguo/xxg-wip-bluestore-0930
- os/bluestore: still more cleanups
Reviewed-by: Sage Weil <sage@redhat.com> - 01:26 PM rbd Bug #17446 (Fix Under Review): assert failure in run-rbd-unit-tests.sh
- *PR*: https://github.com/ceph/ceph/pull/11257
- 01:14 PM rbd Bug #17446: assert failure in run-rbd-unit-tests.sh
- The following patch seems to fix (or at least work around) the issue for me:
diff --git a/src/journal/Journaler.cc... - 10:06 AM rbd Bug #17446: assert failure in run-rbd-unit-tests.sh
- rbd unit tests fail for me too (more often than not) with a somewhat similar backtrace:
[----------] 12 tests from... - 08:18 AM rbd Bug #17446: assert failure in run-rbd-unit-tests.sh
- not consistently reproducible.
- 08:10 AM rbd Bug #17446 (Resolved): assert failure in run-rbd-unit-tests.sh
- see https://jenkins.ceph.com/job/ceph-pull-requests/12079/consoleFull#1073173703d63714d2-c8d8-41fc-a9d4-8dee30be4c32
... - 11:41 AM Revision 3707b30b (ceph): Merge pull request #11136 from jcsp/wip-16016
- mds: populate DamageTable from scrub and log more quietly
Reviewed-by: Douglas Fuller <dfuller@redhat.com> - 11:14 AM mgr Feature #17463 (New): Enable python modules to get() only a sub-tree of an object
Currently in rest.Module.get_sync_object, there is a "path" parameter which is used by the application code to requ...- 11:10 AM mgr Feature #17462 (Closed): Pagination on list GET methods
Pagination on the OSD list was dropped when the rest module code was migrated from Calamari into ceph-mgr. Reinsta...- 11:09 AM mgr Feature #17461 (Resolved): Enable python modules to operate in standby mode
Currently, python modules only get their serve() methods run when their hosting ceph-mgr daemon is the active one.
...- 11:07 AM mgr Feature #17460 (Resolved): Enable python modules to advertise services
- Currently, we rely on would-be consumers of services to know where to look (e.g. to know where the rest module is loa...
- 10:59 AM mgr Feature #17459 (Closed): Install rest module dependencies in test environment
- Currently when ceph-mgr runs inside teuthology, the rest module isn't running because its dependencies aren't there.
... - 10:53 AM Bug #17400 (Fix Under Review): mon/tool: PGMonitor::check_osd_map assert fail when the rebuild mo...
- https://github.com/ceph/ceph/pull/11276
- 10:20 AM mgr Feature #17458 (Closed): Port /crush_node/ API from Calamari
- The rest module code diverged from an earlier version of Calamari that didn't have this.
- 10:19 AM mgr Feature #17457 (Closed): Port REST API tests from Calamari
- The rest module would benefit from being tested by some subset of these: https://github.com/ceph/calamari/tree/master...
- 10:17 AM mgr Feature #17456 (Resolved): Migrate nonessential PGMap data away from ceph-mon
In Kraken, ceph-mon and ceph-mgr both maintain PGMaps with all the same information. For Luminous, we should get r...- 10:08 AM mgr Bug #17455 (Resolved): mgr ignores mgr_beacon_period setting
- There's a `mgr_beacon_period` configuration option but MgrStandby is still just using a hardcoded value: make it use ...
- 10:07 AM mgr Feature #17454 (Resolved): Don't force module classes to be called "Module"
- For simplicity, MgrPyModule currently just looks for a class called "Module" in anything it imports. That's kind of ...
- 10:04 AM mgr Bug #17453 (Resolved): ceph-mgr doesn't forget about MDS daemons that have gone away
- In handle_osd_map we call daemon_state.cull() to eliminate any daemons that no longer exist in the latest map. Need ...
- 10:02 AM mgr Feature #17452 (Resolved): Emit notifications on monmap updates
- From Mgr::ms_dispatch:...
- 10:01 AM mgr Feature #17451 (New): Add support for PERFCOUNTER_LONGRUNAVG perf counters
- Currently, the perf counter structures in ceph-mgr (PerfCounterInstance) just store an array of timestamp and value -...
- 09:59 AM mgr Feature #17450 (Resolved): Call python modules' handle_command in the background
Currently DaemonServer::handle_command calls into the python code inline. This potentially blocks the messenger th...- 09:57 AM mgr Feature #17449 (Resolved): Make stats period configurable
Currently the stats_period in DaemonServer::handle_open is hardcoded to 5 seconds. Make it a config option for peo...- 09:54 AM mgr Feature #17448 (Resolved): Enforce auth caps in DaemonServer::handle_command
Initially I suggest we rely on an "allow *" capability to permit people to run commands.- 08:42 AM rgw Bug #17443 (Pending Backport): rgw: versioning is broken in current master
- 01:34 AM rgw Bug #17443: rgw: versioning is broken in current master
- a regression, caused by fix to http://tracker.ceph.com/issues/16856.
- 01:29 AM rgw Bug #17443 (Resolved): rgw: versioning is broken in current master
- Versioned objects cannot be read.
- 08:41 AM Revision f555ddfa (ceph): Merge pull request #11270 from ceph/wip-17443
- rgw: set correct instance on the object
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 08:41 AM rbd Bug #17447 (Resolved): run-rbd-unit-tests.sh assert in lockdep_will_lock, TestLibRBD.ObjectMapCon...
- log: https://jenkins.ceph.com/job/ceph-pull-requests/12080/consoleFull#-1139993184d63714d2-c8d8-41fc-a9d4-8dee30be4c3...
- 08:21 AM Bug #17407 (Resolved): osdthrasher: reweight-by-utilizatoin hits min bytes per osd on upgrade test
- http://tracker.ceph.com/issues/17407
- 07:34 AM Revision fce16433 (ceph): Merge pull request #10328 from jcsp/wip-ceph-mgr
- Create ceph-mgr
Reviewed-by: Alfredo Deza <adeza@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by... - 07:30 AM Backport #17403 (In Progress): hammer: OSDMonitor: Missing nearfull flag set
- https://github.com/ceph/ceph/pull/11273
- 06:57 AM Revision adb274c6 (ceph): os/bluestore: avoid comparing object key and name twice
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:44 AM Backport #17402 (In Progress): jewel: OSDMonitor: Missing nearfull flag set
- https://github.com/ceph/ceph/pull/11272
- 06:35 AM Revision bea0e347 (ceph): os/bluestore: use id of shard_id_t for encoding
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:34 AM Revision 35660d1a (ceph): mon: OSDMonitor: Missing nearfull flag set
- Output from 'ceph -s -f json-pretty' wans't showing nearfull flag set.
Signed-off-by: Igor Podoski <igor.podoski@ts.... - 05:58 AM Revision 6cece53d (ceph): os/bluestore: kill struct DeferredCsum
- Which is dead, and kill some other dead lines too.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 05:40 AM Revision b3877478 (ceph): osd/ReplicatedPG.h: add override to virtual funct
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 05:20 AM Revision 66fbe938 (ceph): rgw: multipart part copy, fix regression
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:11 AM Revision 9cec7b6d (ceph): os/bluestore: add garbage collection
- Signed-off-by: Roushan Ali <roushan.ali@sandisk.com>
- 04:34 AM Revision 995d3a9c (ceph): Merge pull request #1192 from ceph/wip-offline-split-hammer2
- ceph_manager: test offline split via ceph-objectstore-tool
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:34 AM Revision 8e13e7ce (ceph): Merge pull request #11253 from ceph/wip-offline-split-hammer2
- ceph-objectstore-tool: add a way to split filestore directories offline
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:05 AM Bug #17444: Data object missing xattr attrbutes on primary OSD will not be discovered by scrub/de...
- 2016-09-30 04:03:48.798440 7f5f28dea700 0 log_channel(cluster) log [INF] : 3.fb scrub starts
2016-09-30 04:03:48.80... - 02:06 AM Bug #17444 (Rejected): Data object missing xattr attrbutes on primary OSD will not be discovered ...
- I just had a test on my ceph testing environment(Ceph 0.94.9) by removing xattr attrbutes for a data object, then scr...
- 03:34 AM CephFS Bug #17069: multimds: slave rmdir assertion failure
- snapshot bug, lower Priority
- 02:45 AM CephFS Bug #17069: multimds: slave rmdir assertion failure
- please don't run snapshot tests on multimds, they are know broken.
- 03:33 AM CephFS Bug #16768 (Need More Info): multimds: check_rstat assertion failure
- 03:26 AM CephFS Bug #16768: multimds: check_rstat assertion failure
- Patrick Donnelly wrote:
> Zheng, I think we already have "debug mds = 20", right? From the config for this run: http... - 03:28 AM CephFS Bug #16886 (Need More Info): multimds: kclient hang (?) in tests
- no debug log found in http://pulpito.ceph.com/pdonnell-2016-07-29_08:28:00-multimds-master---basic-mira/339886/
- 03:22 AM CephFS Bug #17392 (Resolved): ceph-fuse sometimes fails to terminate (failures with "reached maximum tri...
- the buggy code was newly introduced, which does not exist in jewel
the jewel hang is different bug... - 02:39 AM CephFS Bug #16926: multimds: kclient fails to mount
- I don't see any mount failure when using testing branch. Besides, I see lots of snapshot related failures. snapshot i...
- 02:22 AM Revision 76e120c7 (ceph): Merge pull request #11267 from liewegas/wip-bluestore-ref-map
- os/bluestore/bluestore_types: uint64_t for ref_map
- 01:37 AM rgw Bug #16856: ACL request for objects with underscore at end and beginning
- Note that when backporting this fix, also need to backport the fix to http://tracker.ceph.com/issues/17443.
- 01:35 AM Revision d2ada35c (ceph): rgw: set correct instance on the object
- Fixes: http://tracker.ceph.com/issues/17443
This was broken by commit bc840afafdfe5e528e5c1b711e71420ac3cb5a67
Sign... - 12:44 AM Revision 29fece35 (ceph): rgw: rgw_obj_key use adjustment in multipart copy part
- This fixes a case where objects start with double underscore.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:44 AM Revision 4919dc99 (ceph): rgw: minor optimization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:44 AM Revision 53521eff (ceph): rgw: multipart copy-part handle versionId
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:26 AM Bug #17442 (Resolved): EC Overwrites: for all scrubs, flush pending write-ahead updates on the ra...
- 12:24 AM Feature #14041: EC overwrites: deep scrub and checksumming
- Some thoughts.
We can actually store all checksums for all shards if we mediate them through the write-ahead log e...
09/29/2016
- 10:54 PM Revision b97c6136 (ceph): Merge pull request #1191 from ceph/wip-offline-split-jewel
- ceph_manager: test offline split via ceph-objectstore-tool
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:54 PM Revision 5246f813 (ceph): Merge pull request #11252 from ceph/wip-offline-split-jewel
- ceph-objectstore-tool: add a way to split filestore directories offline
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:07 PM rgw Bug #17440 (Resolved): disable virtual hosting of buckets when no hostnames are configured
- If no hostnames are configured (either via config variable 'rgw_dns_name' or the zonegroup's 'hostnames' list), then ...
- 10:05 PM Revision 812f8d3e (ceph): os/bluestore/BlueFS: be less complainy about fallback allocations
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:52 PM Revision 5fb4ea1a (ceph): os/bluestore/bluestore_types: uint64_t for ref_map
- We use this to track raw extents on disk for SharedBlob. We
also use it for the in-memory Blob with the blob namespa... - 09:52 PM Revision 5389133f (ceph): ceph_test_objecstore: use 1TB block device
- Big enough to get into 32-bit LBAs.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:24 PM Revision 6e9b824d (ceph): rgw: multipart copy part minor parsing cleanup
- no need for range.size()
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:15 PM Revision 2bcb3d28 (ceph): rgw: multipart copy, check for empty bucket, improve logging
- also reduce log level for non critical user errors.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:07 PM Revision 4049e47a (ceph): rgw: multipart copy part, chunked read
- Don't read the entire range from source object, read it in parts.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:05 PM Revision 276c02b4 (ceph): os/bluestore/BlueFS: release completed aios
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:17 PM Revision b020ea78 (ceph): Merge pull request #11266 from stiopaa1/osd_passSharedPtrByConstRef
- osd: pass shared_ptr by const reference
Reviewed-by: Sage Weil <sage@redhat.com> - 07:43 PM rgw Bug #17438: Building Ceph 10.2.3 without OpenLDAP fails
- Issue was likely added in commit fe57aceeb02ad9163feb2d196589b5927cedfa0f
- 07:35 PM rgw Bug #17438 (New): Building Ceph 10.2.3 without OpenLDAP fails
- Compiling Ceph v10.2.3 with configure options: --with-radosgw --without-openldap
fails to create a buildable produ... - 07:27 PM Revision 22104263 (ceph): Fix test-erasure-code-plugins.sh test on ARM
- The ISA plugin is not available on ARM, this test now excludes it.
Signed-off-by: Bassam Tabbara <bassam.tabbara@qua... - 06:52 PM rbd Backport #17062 (Resolved): jewel: "[ FAILED ] TestClsRbd.mirror_image" in upgrade:jewel-x-mast...
- 06:52 PM rgw Backport #17140 (Resolved): jewel: period commit loses zonegroup changes: region_map converted re...
- 06:47 PM rgw Bug #17367 (Pending Backport): rgw nfs: fix NFS creation (and other?) times for S3-created buckets
- 06:42 PM rgw Bug #17387 (In Progress): multisite: 'radosgw-admin period prepare' is obsolete
- 06:41 PM rgw Bug #17399: Period commit that changes default_placement can cause RGWs to crash.
- old radosgw-admin was still [re]running, at created new default region objects. This triggered period conversion agai...
- 06:38 PM rgw Bug #17401: rgw folder name with underscore (_) problem
- This looks like a duplicate:
http://tracker.ceph.com/issues/16856 - 06:35 PM rgw Backport #17122 (Resolved): jewel: COPY broke multipart files uploaded under dumpling
- 06:34 PM Revision 9c464a55 (ceph): Merge pull request #10866 from dachary/wip-17122-jewel
- jewel: COPY broke multipart files uploaded under dumpling
- 06:32 PM rgw Bug #17051 (Resolved): period commit loses zonegroup changes: region_map converted repeatedly
- 06:32 PM Revision 085e9e36 (ceph): Merge pull request #10890 from dachary/wip-17140-jewel
- jewel: rgw: period commit loses zonegroup changes: region_map converted repeatedly
- 06:29 PM rgw Bug #17186 (Can't reproduce): radosgw keystonev3 token revocation error
- 06:26 PM rgw Bug #16828 (Can't reproduce): radosgw swift interface put object response 500 error?
- 06:25 PM rgw Bug #17269 (Resolved): There is a question about the bucket link API parameters
- The bucket_id is specified when running the following command:...
- 05:59 PM rgw Feature #17437 (New): rgw: create a tool to remove old bucket index objects
- 05:56 PM rgw Bug #17372 (Fix Under Review): RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin ...
- 05:56 PM rgw Bug #17372: RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin works)
- 05:56 PM rgw Bug #17372 (Fix Under Review): RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin ...
- 05:54 PM rgw Bug #17372: RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin works)
- https://github.com/ceph/ceph/pull/11207
- 05:53 PM rgw Backport #16792 (Resolved): jewel: metadata sync can skip markers for failed/incomplete entries
- 05:52 PM rgw Bug #16742 (Resolved): multisite bucket sync doesn't retry objects that it fails to fetch
- 05:51 PM rgw Backport #16794 (Resolved): jewel: multisite bucket sync doesn't retry objects that it fails to f...
- 05:51 PM Revision cb46489b (ceph): Merge pull request #11021 from cbodley/wip-16794
- jewel: rgw: back off bucket sync on failures, don't store marker
- 05:49 PM rgw Bug #16759 (Resolved): metadata sync can skip markers for failed/incomplete entries
- 05:49 PM Revision a0fce630 (ceph): Merge pull request #10657 from dachary/wip-16792-jewel
- jewel: metadata sync can skip markers for failed/incomplete entries
- 05:47 PM Revision b868938d (ceph): Merge pull request #1184 from ceph/rgw-lifecycle-testing
- rgw - Add config for testing lifecycle expiration
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:34 PM Revision 2e333bdb (ceph): erasure-code: Move the EC factory code into separate header files
- This helps the EC factories be invokable directly for testing
and other uses.
Signed-off-by: Bassam Tabbara <bassam.... - 05:34 PM Revision e7e0b1bc (ceph): erasure-code: Backward compatibility with legacy EC plugins
- Resurrected jerasure_generic, jerasure_sse3, jerasure_sse4, jerasure_neon,
shec_generic, shec_sse3, shec_sse4 and she... - 05:34 PM Revision 421af3e2 (ceph): doc: Updated PendingReleaseNotes.
- Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com>
- 05:34 PM Revision feb224d7 (ceph): erasure-code: improve non-regression testing
- Pickup new ec corpus with improved testing.
Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com> - 05:34 PM Revision 6faace08 (ceph): build/ops: remove autoconf leftover
- Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com>
- 05:34 PM Revision 01696d9d (ceph): erasure-code: Pickup gf-complete v3 with runtime SIMD detection
- Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com>
- 05:34 PM Revision cc62c11a (ceph): erasure-code: Remove SIMD flavors for jerasure and shec
- By switching to a new gf-complete with SIMD runtime detection, we can now remove all the different flavors of jerasur...
- 05:34 PM Revision 10d06eb1 (ceph): cmake: normalize use of SIMD flags
- Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com>
- 04:30 PM Revision ea9b9721 (ceph): remove do_autogen.sh
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:27 PM Revision 9a33766b (ceph): pybind/mgr/rest: fix "sync_object" API endpoint
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 6537e634 (ceph): pybind/mgr/rest: remove unused DebugJob
- This dates back from the Calamari/Salt days.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision 042b6b44 (ceph): packaging: add debian packaging for ceph-mgr
- ...at least, try to! This is a copy-paste of the ceph-mds
packaging with a search and replace mds to mgr.
Signed-of... - 04:27 PM Revision f8514ef5 (ceph): mgr: remove hardcoded site-packages
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 592bb9c2 (ceph): vstart: include cython mods in PYTHONPATH
- This is useful for ceph-mgr because it means that
any in-mgr modules that want to use e.g. rbd
can find it when runni... - 04:27 PM Revision d8ded57a (ceph): systemd: add ceph-mgr service and target files
- Signed-off-by: Tim Serong <tserong@suse.com>
- 04:27 PM Revision 2e9e21eb (ceph): ceph.spec.in: add ceph-mgr package
- This adds ceph-mgr following the same pattern used for ceph-mon,
ceph-mds, ceph-osd. I've removed the boost-python B... - 04:27 PM Revision 61d77934 (ceph): systemd: encourage ceph-mgr to start in sync with ceph-mon
- This change introduces the following behaviour:
- When ceph-mon starts, it will try to start ceph-mgr with the same
... - 04:27 PM Revision 082199f6 (ceph): systemd: autogenerate ceph-mgr key during daemon startup
- This is a hack to inject a key for the mgr daemon, using whatever
key already exists on the mon on this node to gain ... - 04:27 PM Revision 1bb9edba (ceph): mgr: fix OSDMap notifications
- This broken when MgrStandby was separated out,
because it now eats the original OSDMap message
without calling maybe_... - 04:27 PM Revision da76c59e (ceph): pybind/mgr: clean up unused code
- ...and change the "if False" django-rest-framework
conditionals to actual version checks, with a view
to genuinely su... - 04:27 PM Revision c6972b98 (ceph): cmake: install ceph-mgr and its python modules
- Signed-off-by: Tim Serong <tserong@suse.com>
- 04:27 PM Revision 58dd3db0 (ceph): mgr: update for Dispatcher::ms_handle_refused
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision afa70787 (ceph): mon: refactor PGMap updating code for reuse in mgr
- ...and remove the copypasta from mgr.
mgr still doesn't do all the same logic (it doesn't
have osdmap history handy)... - 04:27 PM Revision 78b6eebf (ceph): mon: remove need for friending OSDMap to PGMapUpdater
- This used to be the friend relationship to PGMonitor. It
was never really needed anyway, it was only being used
to s... - 04:27 PM Revision 45b33934 (ceph): mgr: fixup ClusterState with_*map fns
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision fc3090fc (ceph): mgr: skip past broken modules and load the rest
- ...instead of stopping at the first python module
that fails to load.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision ba648478 (ceph): pybind/mgr: add fsstatus module
- A demonstration of creating a simple
ASCII-art status display by fusing
the metadata, perf counters, and maps that
ar... - 04:27 PM Revision 567b9fb6 (ceph): doc: add initial ceph-mgr docs
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 88977572 (ceph): packaging: add boost-python dependency
- Although ceph-mgr isn't packaged yet, builders
use these files to cue installation of dependencies.
Signed-off-by: J... - 04:27 PM Revision 2210772e (ceph): common: refactor CommandTable
- Avoid handling out raw pointers to the ops,
which are in fact owned by the table.
Signed-off-by: John Spray <john.sp... - 04:27 PM Revision 0812669c (ceph): mgr: dispose of connections after handle_command
- ...to avoid leaking them and eventually running out of fds.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision 7122fac0 (ceph): mgr: expose osd stats from pgmap
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 7b8179bd (ceph): mon: implement MgrMonitor.preprocess_beacon
- So that we're not throwing out new mgrmap epochs
every beacon.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision 8db0137d (ceph): mgrc: less vebose logging of messages
- ...no need to tell us about all the things you're *not* handling.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision ea46778e (ceph): mgr: expose "df" to python modules
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision e6de53aa (ceph): pybind/mgr: fix logging
- Previously only the errors were getting through, because
other stuff was getting held up in the python logging
framew... - 04:27 PM Revision c38d4915 (ceph): mgrc: mark down connections with dead sessions
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision fa147e3a (ceph): mgr: handle PGStats with a PGMap
- No longer need the mon to send us
the pg_summary json hack.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision f77276a5 (ceph): pybind/mgr: update rest module for pg_summary
- ...which is now generated properly from PGMap
instead of reconstituted from some JSON.
Signed-off-by: John Spray <jo... - 04:27 PM Revision ab240380 (ceph): common/TextTable: add include guards
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 519a01d9 (ceph): mon: move "df" dump code from PGMonitor to PGMap
- ...so that ceph-mgr can use it too.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision 80281ed2 (ceph): pybind/mgr: expose get_counter in MgrModule
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 803b66a3 (ceph): mgrc: enable sending pgstats
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 30dec8e2 (ceph): osd: send PGStats to mgr as well as mon
- This is a rough implementation that sends all the stats,
without the efficiency of the queue+acks that we use
when ta... - 04:27 PM Revision 7eb45729 (ceph): pybind/mgr: remove unused gevent code
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:27 PM Revision 5366980c (ceph): pybind/mgr: move rest into dir
- Let's make each module its own directory.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:27 PM Revision 9501bfdd (ceph): mgr: store some counter history
- ...and expose it to python modules.
Also fix some of the code around how we updated
DaemonState.
Signed-off-by: Joh... - 04:27 PM Revision e3104862 (ceph): mgrc: fix report sending after failover
- The send_report loop doesn't get kicked off
on configure messages unless the period is
set to its initial value (0).
... - 04:26 PM Revision 1643a7fc (ceph): mgrc: reset send_report timer on session change
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision fd537bc6 (ceph): mgr: enable active daemon to return to standby
- Rather than respawn a whole process, just fall back
to being a standby.
Signed-off-by: John Spray <john.spray@redhat... - 04:26 PM Revision 96e10e93 (ceph): mds: embed a MgrClient
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision 054708a6 (ceph): mgr: Use signed int log level in PyModules::log()
- Using an unsigned causes a build failure when expanding the dout macro.
Signed-off-by: Tim Serong <tserong@suse.com> - 04:26 PM Revision d9dfb436 (ceph): mgr: s/DaemonMetadata/DaemonState/g
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision c81e542b (ceph): mgr: enable multiple python modules
- serve() each one in a separate thread, include a shutdown()
hook so that we can tear down cleanly.
Signed-off-by: Jo... - 04:26 PM Revision 0bff7af0 (ceph): pybind/mgr: implement shutdown() in rest.py
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision 7845f8d7 (ceph): mgr: flesh out standby/HA
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision b7c9561a (ceph): mgr: fix locking in DaemonMetadata
- Locks are great but it helps if you actually
bother acquiring them...
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision a53dc646 (ceph): pybind/mgr: remove unused CalamariConfig
- No longer need to set CALAMARI_CONFIG when running.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision cc0b8fb7 (ceph): pybind/mgr: fix django request logging
- This was going to a text file, hook it in
to the proper logging.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision b3189d68 (ceph): cmake: update for ceph-mgr
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision 44c95af2 (ceph): pybind: create mgr python module folder
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision b82533fc (ceph): pybind/mgr: add the `rest` module
- This is derived from what used to be Calamari.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision eafe2e94 (ceph): mgr: api_docs.py: Update for use outside Calamari
- The ceph_state module is implemented in C++, and isn't available at
build time, which causes import failures when api... - 04:26 PM Revision 10da6d23 (ceph): osd: embed a MgrClient
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision 157f986d (ceph): librados: expose mgr_command
- This involves giving RadosClient an embedded
MgrClient.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision 3f4d80c7 (ceph): pybind: expose mgr commands
- This is "tell mgr" at the moment but it should
be a slicker syntax later (ceph.in is awkward
to refactor just now)
S... - 04:26 PM Revision bbc66310 (ceph): auth: add mgr service type
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision ac30e6ce (ceph): mgr: create ceph-mgr service
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision 3283b1e4 (ceph): common: accessors for list of perf counters
- ...and store the list by a string path, for
consumption by the world outside of integer
perf counter/subsystem IDs.
... - 04:26 PM Revision 88442d23 (ceph): mgrc: create MgrClient
- The ceph-mgr equivalent to monclient
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision e3b2225f (ceph): messages: add ceph-mgr messages
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision eaada77f (ceph): msg: introduce mgr entity_type_t
- Mgr will probably ultimately have different auth caps,
so let's make it a separate entity up front instead
of e.g. pr... - 04:26 PM Revision 84508408 (ceph): mon: add MgrMonitor
- This is responsible for learning the locations of
mgrs, picking an active one, and sharing that
info with MgrClient c... - 04:26 PM Revision e32f2a90 (ceph): vstart: set up and run ceph-mgr
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision 6caae0e3 (ceph): common/cmdparse: additional helpers
- For dumping a cmdmap to a Formatter, and for
checking the prefix of a cmddesc.
Used by ceph-mgr when routing command... - 04:26 PM Revision a11ff90f (ceph): pybind: fix handling bad cmd json
- The 'save_exception' local would otherwise
be referenced before assignment during
exception handling.
Signed-off-by:... - 04:26 PM Revision 7e6b4f1f (ceph): client: refactor command handling
- Create a CommandTable structure for places
in Client, MgrClient, Objecter where we do
basically the same kind of thin... - 04:26 PM Revision 85ba9a36 (ceph): mon: add with_monmap to MonClient
- Analogous to Objecter::with_osdmap, for safe access
to the map.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision 1a331234 (ceph): common: move ceph_version up into collect_sys_info
- ...so that we get this piece of metadata from every
service uniformly.
Signed-off-by: John Spray <john.spray@redhat.... - 04:26 PM Revision fefaac75 (ceph): common: add 'mgr' and 'mgrc' subsystems for logging
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision c4965fd0 (ceph): common: add mgr config settings
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision fbe7ae50 (ceph): vstart: fix warning when no CEPH_MAX_MDS set
- This was a typo in 29535caf
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision 27fdf87a (ceph): monc: remove unused AuthAuthorizeHandlerRegistry
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:26 PM Revision c5700ce4 (ceph): mon: fix missing osd metadata (again)
- The JSON output was getting broken by continuing
in the wrong place.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision d2a209f1 (ceph): msg: typedef uint8_t entity_type_t
- ...rather than having a mixture of explicit __u8
and implicit enums/ints.
Signed-off-by: John Spray <john.spray@redh... - 04:26 PM Revision 51a61051 (ceph): mon,mds: include 'addr' in daemon metadata
- This is useful for correlating daemon metadata
to cluster maps.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:26 PM Revision 3f6676a8 (ceph): mon: drop encoded buffer after decode
- This bufferlist was being kept around as a
class member but it didn't need to be.
Signed-off-by: John Spray <john.sp... - 04:19 PM Revision 79509462 (ceph): suites: update log whitelist for scrub msg
- Fixes: http://tracker.ceph.com/issues/16016
Signed-off-by: John Spray <john.spray@redhat.com> - 03:45 PM CephFS Support #17171 (Closed): Ceph-fuse client hangs on unmount
- 12:56 PM CephFS Support #17171: Ceph-fuse client hangs on unmount
- We can probably close this issue, we'll reopen or create new when we'll be able to reliably reproduce issue
- 03:38 PM CephFS Bug #17173 (Pending Backport): Duplicate damage table entries
- 03:38 PM Revision 27158854 (ceph): Merge pull request #11137 from jcsp/wip-17173
- mds: catch duplicates in DamageTable
Reviewed-by: Douglas Fuller <dfuller@redhat.com> - 03:38 PM Bug #17429 (Duplicate): ceph-objectstore-tool: specify both --op and object command syntax
- The relevant command is being backported, no need for any test changes http://tracker.ceph.com/issues/17383
- 08:30 AM Bug #17429: ceph-objectstore-tool: specify both --op and object command syntax
- @David does that ring a bell ? I ran into it while testing a pull request and not on master itself but I don't think ...
- 08:29 AM Bug #17429 (Duplicate): ceph-objectstore-tool: specify both --op and object command syntax
- http://pulpito.ceph.com/loic-2016-09-26_13:00:32-rados-wip-pr-11086---basic-smithi/438259/
This is an upgrade test... - 02:46 PM Revision e1822c16 (ceph): os/bluestore: sloppy reshard boundaries to avoid spanning blobs
- Make the extent map shard target size sloppy so that we can try to avoid
sharding boundaries that create spanning blo... - 01:45 PM Revision a5706d78 (ceph): Merge pull request #11244 from xiexingguo/xxg-wip-bluestore-0928
- os/bluestore: upgrade compression settings to atomics
Reviewed-by: Sage Weil <sage@redhat.com> - 01:20 PM Bug #17436 (Fix Under Review): selinux: Allow ceph to manage tmp files
- PR for master: https://github.com/ceph/ceph/pull/11259
- 01:01 PM Bug #17436 (Resolved): selinux: Allow ceph to manage tmp files
- Two new denials showed up in testing that relate to ceph trying to
manage (rename and unlink) tmp files. This commit... - 01:02 PM Revision f8a0e201 (ceph): selinux: Allow ceph to manage tmp files
- Two new denials showed up in testing that relate to ceph trying to
manage (rename and unlink) tmp files. This commit ... - 12:01 PM CephFS Bug #17270 (Fix Under Review): [cephfs] fuse client crash when adding a new osd
- Opened https://github.com/ceph/ceph/pull/11262 for the fix for the first crash.
Opened http://tracker.ceph.com/iss... - 12:01 PM CephFS Bug #17435 (New): Crash in ceph-fuse in ObjectCacher::trim while adding an OSD
From: http://tracker.ceph.com/issues/17270, in which there was initially a crash during writes, and this appears to...- 11:48 AM CephFS Feature #17434 (Fix Under Review): qa: background rsync task for FS workunits
- A client that just sits there trying to rsync the contents of the filesystem. Running this at the same time as any o...
- 11:29 AM Revision 88dbde2f (ceph): Revert "osdc: After write try merge bh."
- This reverts commit 1a48a8a2b222e41236341cb1241f0885a1b0b9d8.
Fixes: http://tracker.ceph.com/issues/17270
Signed-off... - 11:25 AM Backport #17383 (In Progress): hammer: ceph-objectstore-tool: ability to perform filestore splits...
- 10:58 AM Fix #17433 (New): [systemd]: Ceph doesn`t remove symlinks for systemd services
- Hi.
Just noticed that after unistalling ceph (for example, using ceph-deploy uninstall & purge & purgedata), there a... - 10:57 AM Bug #17432 (Closed): CephFS - Bonnie++: Can't create file
- Trying to run bonnie++ (v1.97) benchmark on cephfs mounted with kernel client and get error:
bonnie++ -u root -d /... - 09:24 AM Bug #17431 (Resolved): RocksDBStore memory leak valgrind
- http://pulpito.ceph.com/loic-2016-09-26_13:00:32-rados-wip-pr-11086---basic-smithi/438346/
has http://qa-proxy.cep... - 09:22 AM Bug #17386 (Fix Under Review): Upgrading 0.94.6 -> 0.94.9 saturating mon node networking
- https://github.com/ceph/ceph/pull/11258
https://github.com/ceph/ceph/pull/11284
https://github.com/ceph/ceph/pull/1... - 09:19 AM Bug #17366: "assert len(unclean) == num_unclean" in dump_stuck.py in rados suite
- Also found at "rados/singleton/{rados.yaml all/dump-stuck.yaml fs/xfs.yaml msgr/random.yaml msgr-failures/many.yaml}"...
- 08:55 AM Bug #17430 (Can't reproduce): rados -p rbd bench 15 write -b 4096 never completes
- http://pulpito.ceph.com/loic-2016-09-26_13:00:32-rados-wip-pr-11086---basic-smithi/438273/...
- 08:09 AM rbd Bug #17355 (Fix Under Review): rbd-mirror: potential crash during replay shut down
- 08:05 AM Bug #17428 (Closed): systemd: Incorrect path to ceph-osd-prestart.sh in ceph-osd@.service on gentoo
- On our Gentoo Linux systems Ceph helper binaries are installed into /usr/libexec/ceph. Unfortunately the systemd serv...
- 03:14 AM Revision 22cf74f2 (ceph): mds/MDCache: kill a comipler warning
- /home/jenkins-build/build/workspace/ceph-pull-requests/src/mds/MDCache.cc: In member function ‘void MDCache::request_...
- 02:18 AM Revision 83e93948 (ceph): os/bluestore: upgrade compression settings to atomics
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:02 AM Bug #17425 (Resolved): Remove the runtime dependency on lsb_release
- We have attempted to remove this dependency before as it pulls in various other dependencies and it would be nice to ...
- 01:13 AM Revision e4038a0c (ceph): ceph_manager: test offline split via ceph-objectstore-tool
- When killing an osd, split all pools with a low threshold.
This will slow down tests, but should not impact correctne... - 12:57 AM Revision 99bb9f60 (ceph): ceph-objectstore-tool: add a way to split filestore directories offline
- Use the usual split code, and split each dir that meets the
usual split criteria.
This can be run with lower than us... - 12:40 AM Revision a199dcd9 (ceph): ceph_manager: test offline split via ceph-objectstore-tool
- When killing an osd, split all pools with a low threshold.
This will slow down tests, but should not impact correctne... - 12:12 AM Revision 949480c2 (ceph): rgw: multipart uploads copy part support
- Add multipart uploads copy part feature.
Fixes: http://tracker.ceph.com/issues/12790
Signed-off-by: Javier M. Melli... - 12:12 AM Revision 8a7ebeee (ceph): rgw: doc: add multipart uploads copy part feature as supported
- Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
09/28/2016
- 10:31 PM Revision ff264ce6 (ceph): osd/ReplicatedPG: remove unneeded use of count
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 10:30 PM Revision 3cb0a5e0 (ceph): ceph-objectstore-tool: add a way to split filestore directories offline
- Use the usual split code, and split each dir that meets the
usual split criteria.
This can be run with lower than us... - 10:18 PM Revision be2b51de (ceph): osd: pass shared_ptr by const reference
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 08:25 PM Revision a2c27c94 (ceph): hobject: clarify is_snap and has_snapset for max
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 08:13 PM rbd Bug #17355 (Pending Backport): rbd-mirror: potential crash during replay shut down
- 08:12 PM Revision ba6785f0 (ceph): Merge pull request #11185 from dillaman/wip-17355
- rbd-mirror: quiesce in-flight event commits before shut down
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 08:08 PM rbd Subtask #17424 (Resolved): [data pool] update rbd CLI to permit "--data-pool" optionals
- All CLI commands where an image can be created (create, clone, copy, import) should support an optional "--data-pool"...
- 08:06 PM rbd Subtask #17423 (Resolved): [data pool] add new non-dynamic feature bit for data pool
- * add new 'RBD_IMAGE_OPTION_DATA_POOL' image option to API
* new data pool feature would be set if data pool specifi... - 08:04 PM rbd Subtask #17422 (Resolved): [data pool] cls_rbd updates for data pool
- * new "get_data_pool" cls method against image header
* existing "create" cls method should optionally expect data p... - 07:29 PM Revision b8d4a4a2 (ceph): Merge pull request #11250 from liewegas/wip-bluestore-leaks
- os/bluestore: fix leaks in our use of rocksdb
- 05:56 PM Revision 85fc1028 (ceph): os/bluestore: do not leak when using EnvMirror
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:56 PM Revision 2a4b87f3 (ceph): rocksdb: include EnvMirror leak fixes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:29 PM Bug #17365 (Resolved): mon: forwarded message is encoded with sending client's features
- I don't think we care about backporting this?
- 05:28 PM Revision b9f15e54 (ceph): Merge pull request #11180 from liewegas/wip-mon-forward
- messages/MForward: fix encoding features
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 04:53 PM Revision 84dd1a62 (ceph): Merge remote-tracking branch 'upstream/pull/1176/head'
- * upstream/pull/1176/head:
tasks/cephfs: add default paths to vstart_runner
Reviewed-by: Patrick Donnelly <pdonnel... - 03:44 PM Revision d4f5e88f (ceph): messages/MForward: fix encoding features
- We were encoding the message with the sending client's
features, which makes no sense: we need to encode with
the rec... - 03:40 PM Revision 56ccf8ea (ceph): Merge pull request #11243 from liewegas/wip-bluestore-deferred-csum
- os/bluestore: remove deferred_csum machinery
- 03:39 PM Revision 51a1f860 (ceph): Merge pull request #11113 from yuyuyu101/wip-fix-filestore-clone
- os/filestore: disable use of splice by default
Reviewed-by: Sage Weil <sage@redhat.com> - 03:38 PM Revision 4d6953a4 (ceph): tasks/cephfs: add default paths to vstart_runner
- So that for folks with sources in typical locations
(or typical on my workstation at least!) invoking
vstart_runner i... - 03:36 PM Bug #17421 (Won't Fix): dmcrypt is broken when passing a data-dir
- Calling:
`root@juju-c268c9-3:~# sudo -u ceph ceph-disk prepare --data-dir /srv/ceph --dmcrypt`
fails with a bad ass... - 03:06 PM Revision 641d2ca0 (ceph): Merge pull request #9652 from stiopaa1/osdc_ObjectCacher_constMember
- osdc/ObjectCacher.h: add const to member functions
Reviewed-by: Sage Weil <sage@redhat.com> - 02:32 PM Revision 91bc79ee (ceph): msg/async: remove unused code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:29 PM Revision ad50703c (ceph): Merge pull request #11248 from mikulely/cleanup-vstart-doc
- doc: cleanup outdated radosgw description
- 02:25 PM CephFS Feature #11171 (Resolved): Path filtering on "dump cache" asok
- 02:22 PM CephFS Bug #17392 (Pending Backport): ceph-fuse sometimes fails to terminate (failures with "reached max...
- 02:22 PM CephFS Bug #17253 (Pending Backport): Crash in Client::_invalidate_kernel_dcache when reconnecting durin...
- 02:22 PM CephFS Bug #17286 (Pending Backport): Failure in dirfrag.sh
- 02:21 PM CephFS Bug #17236 (Pending Backport): MDS goes damaged on blacklist (failed to read JournalPointer: -108...
- 02:21 PM CephFS Bug #17271 (Pending Backport): Failure in snaptest-git-ceph.sh
- 02:20 PM devops Cleanup #17395 (Pending Backport): rpm: /etc/ceph/rbdmap is packaged with executable access rights
- 02:20 PM Revision c48ee9d3 (ceph): Merge pull request #11217 from ceph/wip-17395-rbdmap-permissions
- rpm: fix permissions for /etc/ceph/rbdmap
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 02:13 PM Revision 4182ee66 (ceph): Merge pull request #11240 from liewegas/wip-bluestore-assert
- os/bluestore: add assert to compress_extent_map
- 02:12 PM Revision 8a9e41a2 (ceph): Merge pull request #11245 from xiexingguo/xxg-wip-bluestore-bsearch-shard
- os/bluestore: binary search specified shard
Reviewed-by: Sage Weil <sage@redhat.com> - 01:56 PM Revision 539a8622 (ceph): Merge pull request #11235 from xiexingguo/xxg-wip-bluestore-0926
- os/bluestore: more cleanups
Reviewed-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision cac8b17a (ceph): Merge pull request #11247 from majianpeng/msg-async-cleanup
- msg/async: remove unused code.
Reviewed-by: Haomai Wang <haomai@xsky.com> - 01:36 PM Revision be25f843 (ceph): rbd-mirror: replicate image metadata settings
- Fixes: http://tracker.ceph.com/issues/16212
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 01:28 PM Revision 7a434145 (ceph): cls::rbd: async methods to set/remove metadata
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 01:06 PM Revision cc40473f (ceph): Merge pull request #10980 from trociny/wip-16213
- rbd-mirror: replicate dynamic feature updates
Reviewed-by: Jason Dillaman <dillamana@redhat.com> - 12:17 PM Revision 953561f8 (ceph): librbd: async method to check journal tag owner
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision dcfb8aa1 (ceph): librbd: async methods to enable/disable mirroring
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision 4269a5fc (ceph): librbd: allow to call append_disabled for DisabledPolicy
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision 606344dd (ceph): librbd: templetize journal StandardPolicy
- It will be needed for unit tests with a mocked ImageCtx.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 12:17 PM Revision 3c270b57 (ceph): librbd: async state machine to enable/disable image features
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision 93cf63f9 (ceph): rbd-mirror: replicate dynamic feature updates
- Fixes: http://tracker.ceph.com/issues/16213
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 12:17 PM Revision 5a68e334 (ceph): librbd: use counter to track exclusive lock block/unblock requests
- It's possible the watch/notify message is duplicated resulting in two
concurrent block_requests() call.
Signed-off-b... - 12:17 PM Revision ac71dbca (ceph): librbd: interlock image state machine and update features operations
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision f99dbbd1 (ceph): librbd: potential null pointer dereference when requesting exclusive lock
- m_require_lock_on_read should be cleared when holding owner_lock.
For safety, also check that exclusive_lock is not ... - 12:17 PM Revision ac25cb19 (ceph): cls/journal: async client_list method
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision 28e576e2 (ceph): cls/rbd: alow to call set_features asynchronously
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision a0cf640d (ceph): librbd: async methods to create/remove object map
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:17 PM Revision 9026b515 (ceph): librbd: async image set flags method
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 11:14 AM Revision bfbb16ca (ceph): Merge pull request #11120 from renhwztetecs/renhw-wip-mds-server
- mds/server: clean up handle_client_open()
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:12 AM Revision 55243112 (ceph): Merge pull request #11078 from ukernel/wip-17271
- mds: remove fail-safe queueing replay request
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: John Spray ... - 11:10 AM Revision f9f8a36b (ceph): Merge pull request #11225 from ukernel/wip-17392
- client: protect InodeRef with client_lock
Reviewed-by: John Spray <john.spray@redhat.com> - 09:09 AM Revision 356377e1 (ceph): osd: Flush Journal on shutdown
- This way a data store is consistent and hot-swappable if a OSD had
a clean shutdown.
Make this behavior configurable... - 08:52 AM Revision ed659302 (ceph): doc: cleanup outdated radosgw description
- radosgw support is on by default, as built-in Civetweb, set up Apache
is no necessary any more.
Signed-off-by: Jiayi... - 07:53 AM Bug #17420 (In Progress): Erroneous WARNING: max attr value size (1024) is smaller than osd_max_o...
- https://github.com/ceph/ceph/pull/11246
- 07:45 AM Bug #17420 (Resolved): Erroneous WARNING: max attr value size (1024) is smaller than osd_max_obje...
- ...
- 07:52 AM Revision de672a09 (ceph): logrotate: Run as root/ceph
- Currently, we run the logrotate scripts as ceph/ceph but that way we
cannot rotate the scripts created by qemu (they ... - 07:50 AM Revision 895a76a4 (ceph): os/bluestore: add a counter to trace rejected compress ops
- This is useful for choosing a more proper bluestore_compression_required_ratio.
Signed-off-by: xie xingguo <xie.xing... - 07:24 AM Revision 9caae754 (ceph): os/bluestore: make allocated space calc a little faster
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 05:44 AM Revision 6b9988ac (ceph): os/bluestore: binary search specified shard
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 04:03 AM Bug #17411: Wierd deadlock in OSD
- Jeegn Chen wrote:
> This commits seems the fix for this issue?
> https://github.com/ceph/ceph/commit/63e44e32974c9b... - 03:41 AM Bug #17411: Wierd deadlock in OSD
- This commits seems the fix for this issue?
https://github.com/ceph/ceph/commit/63e44e32974c9bae17bb1bfd4261dcb024ad845c - 03:55 AM Revision c892eb40 (ceph): tools/rados: Fix do_put
- Signed-off-by: Tomy Cheru <tomy.cheru@sandisk.com>
- 03:53 AM Revision cb919cae (ceph): tools/rados: Added append functionality to rados tool.
- Signed-off-by: Tomy Cheru <tomy.cheru@sandisk.com>
- 12:32 AM Bug #17407: osdthrasher: reweight-by-utilizatoin hits min bytes per osd on upgrade test
Might be the same issue.
http://pulpito.ceph.com/dzafman-2016-09-22_17:11:48-rados-wip-zafman-testing-distro-bas...- 12:32 AM Revision a5dd191d (ceph): os/bluestore: move nid assignment into BlueStore::_zero()
- So other callers, such as BlueStore::_clone_range(),
won't do it twice.
Signed-off-by: xie xingguo <xie.xingguo@zte.... - 12:32 AM Revision c6adc6e0 (ceph): os/bluestore: remove dead local variables from BlueStore::_wctx_finish()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 12:32 AM Revision 9d909394 (ceph): os/bluestore: remove fadvise_flags from WriteContext
- Currently fadvise_flags is only used to check whether
buffered write is necessary, so there is no need
to keep it in ... - 12:32 AM Revision 9f6344e3 (ceph): os/bluestore: use std namespace for hex/dec output formatting
- Because we use std::hex/dec everywhere in bluestore except these two places.
Signed-off-by: xie xingguo <xie.xingguo... - 12:26 AM Bug #17419 (Can't reproduce): mon/crush_ops.sh fails with status 1
http://pulpito.ceph.com/dzafman-2016-09-22_17:11:48-rados-wip-zafman-testing-distro-basic-smithi/432001
CommandF...- 12:15 AM Bug #17418 (Duplicate): assert len(inactive) == num_inactive
http://pulpito.ceph.com/dzafman-2016-09-22_17:11:48-rados-wip-zafman-testing-distro-basic-smithi/431992...- 12:01 AM Bug #17417 (Can't reproduce): /var/log/ceph/valgrind/osd.1.log: <kind>Leak_DefinitelyLost</kind>
http://pulpito.ceph.com/dzafman-2016-09-22_17:11:48-rados-wip-zafman-testing-distro-basic-smithi/431916
09/27/2016
- 11:03 PM Revision c1b64c8f (ceph): rgw: rgw_obj encoding fixes
- Fix a few issues:
- conversion to and from rgw_obj_key
- strip_namespace_from_object() in the case where object sta... - 10:38 PM Revision c381cc5d (ceph): rgw: utilities to support raw bucket index operations
- and other related changes.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_rados.cc
src/rg... - 10:31 PM Revision d41cbb44 (ceph): rgw: use bucket_info.bucket_id instead of marker where needed
- We used to use these interchangeably, but they actually have diffent meaning.
The marker is the prefix we assign to t... - 10:31 PM Revision 228f52cc (ceph): cls/rgw: utilities to support raw bucket index operations
- New flavour of bi_put() call, and a function to extract key off
a raw bi entry.
Signed-off-by: Yehuda Sadeh <yehuda@... - 09:07 PM Revision ad7487d6 (ceph): os/bluestore: remove deferred_csum machinery
- When we added this way back in d4f4fa0312d943dd0ce3c27f5fc56c7a753bb471,
we did not have our own buffer cache, and we... - 08:37 PM rbd Feature #14738 (Pending Backport): Optionally unregister "laggy" journal clients
- 12:37 PM rbd Feature #14738 (Resolved): Optionally unregister "laggy" journal clients
- 08:37 PM Revision 4e61538d (ceph): Merge pull request #10888 from dachary/wip-17062-jewel
- jewel: tests: fix TestClsRbd.mirror_image failure in upgrade:jewel-x-master-distro-basic-vps
- 08:31 PM rbd Bug #17416 (Resolved): Improve resiliency of rbd-mirror stress test case
- 08:23 PM Revision e4ed13fe (ceph): unittest_bluestore_types: init g_ceph_context
- The methods we're testing use it for dout.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:42 PM Revision 39c3b8d5 (ceph): osd/ReplicatedPG: remove unneeded use of count
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:10 PM CephFS Feature #17276: stick client PID in client_metadata
- There's already a GID (just an increasing integer) that the monitor uniquely associates with each client session — I ...
- 07:00 PM CephFS Feature #17276: stick client PID in client_metadata
- I will take this as I've been wanting it for my performance work.
I'm also wondering if you think it'd be useful t... - 06:21 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- That sounds good to me.
It'll actually be a little finicky though — if we generate a new MDSMap that cuts the time... - 04:02 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- Oh dear, the MDS takes mds_session_timeout from its local config, but the client users mdsmap->get_session_timeout()....
- 06:02 PM Revision e8dd0883 (ceph): os/bluestore: add assert to compress_extent_map
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:02 PM Revision 67f26027 (ceph): Merge pull request #11238 from theanalyst/changelog-v10.2.3
- doc/changelog: add v10.2.3
- 04:00 PM Revision f4ce7f00 (ceph): Merge pull request #10814 from liewegas/wip-bluestore-precondition
- os/bluestore: precondition rocksdb/bluefs during mkfs
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 03:59 PM Revision 9c691776 (ceph): doc/changelog: add v10.2.3
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 03:56 PM Revision 03744204 (ceph): os/filestore: add merge_delete
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision 20c45678 (ceph): os/kstore: add merge_delete
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision fdb8345e (ceph): os/memstore: add merge_delete
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision 8105ded2 (ceph): os/bluestore: add merge_delete
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision e9244b19 (ceph): ceph_test_objectstore: add merge_delete tests
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision b92c767b (ceph): ceph_test_objectstore: test move_ranges_destroy_src from Synthetic
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:56 PM Revision e15cdb32 (ceph): os/ObjectStore: add merge_delete
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision 50ae9a3c (ceph): os/filestore: fix coll_t handling for CLONERANGE[2]
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:56 PM Revision 6a0f3c67 (ceph): os/filestore: fix typos
- Signed-off-by: Manali Kulkarni <Manali.Kulkarni@sandisk.com>
- 03:38 PM Revision 0e2198fa (ceph): os/bluestore: precondition rocksdb on mkfs
- Write N bytes of garbage to the kv store on startup. With rocksdb,
this ensures that our log files are preallocated.... - 03:22 PM Bug #17386: Upgrading 0.94.6 -> 0.94.9 saturating mon node networking
- so we need three patches for fixing this problem:
# for this specific issue. we need to re-encode the OSDMap when ... - 03:18 PM Revision 828c1006 (ceph): Merge pull request #11234 from theanalyst/jewel-release-notes
- doc/release-notes: v10.2.3 jewel
- 03:10 PM rgw Bug #17414 (New): multisite: handle runtime changes to number of mdlog/datalog shards
- After starting sync, restarting a gateway with a different value of rgw_md_log_max_shards or rgw_data_log_num_shards ...
- 02:45 PM Revision 5f5880d0 (ceph): Merge pull request #11216 from liewegas/wip-bluestore-compress-map
- os/bluestore: prevent extent merging across shard boundaries
Reviewed-by: Somnath Roy <somnath.roy@sandisk.com> - 02:38 PM Revision 9f97af26 (ceph): doc/release-notes: more fixes to 10.2.3
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 02:35 PM rbd Bug #15259: performance: journaling results in 4X slowdown when writes are not blocked by cache
- *PR*: https://github.com/ceph/ceph/pull/10445
- 02:35 PM rbd Bug #15259 (Pending Backport): performance: journaling results in 4X slowdown when writes are not...
- 02:35 PM Revision d4f144ec (ceph): Merge pull request #10445 from rjfd/wip-15259
- journal: increase concurrency/parallelism of journal recorder
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:28 PM Revision de0e0edb (ceph): doc: add v10.2.3 to releases table
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 02:28 PM Revision d12b5f6b (ceph): doc/release-notes: v10.2.3 jewel
- Adding release notes for the next jewel release
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 01:21 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- I created #17413 for that. Still waiting for this issue's issue to pop out
- 03:03 AM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- Henrik Korkuc wrote:
> it looks like this time I got a read request stuck for 2 days from OSD. Client is 0.94.9
>
... - 12:32 PM rbd Subtask #15688 (Resolved): Stub API integration between librbd and the new client-side cache
- 12:24 PM Bug #17413 (Closed): objecter read request stuck for 2 days from OSD
- while testing http://tracker.ceph.com/issues/17275 I stumbled upon read request which was stuck for more than 2 days....
- 11:31 AM Linux kernel client Bug #17410: rbd image stale/stuck (mapped and mounted)
- can you backport https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/commit/?id=922dab6134178cae317a...
- 06:01 AM Linux kernel client Bug #17410: rbd image stale/stuck (mapped and mounted)
- it's 100% seems like http://www.spinics.net/lists/ceph-users/msg24111.html
- 09:31 AM Bug #17412: Applying ruleset halts monitor
- This could be duplicate of http://tracker.ceph.com/issues/16653
@Arvydas, please check your monitor log, if you're... - 09:07 AM Bug #17412 (Duplicate): Applying ruleset halts monitor
- Hi,
I noticed strange behavior of monitors during changing pool's crush_ruleset parameter. In some cases monitor h... - 09:15 AM Revision 55824077 (ceph): doc: drop start development cluster area in index.rst, quick_start.rst ...
- Signed-off-by: Leo Zhang <nguzcf@gmail.com>
- 09:04 AM Revision ff59b380 (ceph): tool/cephfs: displaying "list" in journal event mode
- lack of displaying "list" when use the journal event mode of cephfs-journal-tool
Signed-off-by: huanwen ren <ren.hua... - 08:04 AM rbd Bug #16988 (In Progress): 'rbd feature disable' against non-primary image results in hung CLI
- Moved to resolved too quickly, should be done after PR#10980 is merged.
- 08:03 AM rbd Bug #16988 (Resolved): 'rbd feature disable' against non-primary image results in hung CLI
- Tested with PR#10980, no cli hang was seen:
> ./bin/rbd --cluster cluster2 -p mirror feature disable r0 journaling... - 07:45 AM Bug #17411: Wierd deadlock in OSD
- OS version: CentOS 6.5
Ceph version: 0.94.1 - 07:33 AM Bug #17411: Wierd deadlock in OSD
- which OS version and ceph version do you test?
- 02:13 AM Bug #17411 (Resolved): Wierd deadlock in OSD
- ...
- 07:43 AM Revision ee1de7dc (ceph): doc: fix start development cluster operation in index.rst
- Signed-off-by: Leo Zhang <nguzcf@gmail.com>
- 05:51 AM Backport #17376: jewel: Assign LOG_INFO priority to syslog calls
- downstream ticket: https://bugzilla.redhat.com/show_bug.cgi?id=1378675
- 02:28 AM Backport #17376 (In Progress): jewel: Assign LOG_INFO priority to syslog calls
- Created a PR as this has become urgent.
https://github.com/ceph/ceph/pull/11231 - 03:10 AM CephFS Bug #17368 (Fix Under Review): mds: allowed GIDs must be ordered in the cephx string
- A new patch on https://github.com/ceph/ceph/pull/11218
- 03:08 AM Revision a67f61f0 (ceph): mds: sort GID lists in MDSAuthCaps
- Fixes: http://tracker.ceph.com/issues/17368
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 02:11 AM Revision 9cb45e11 (ceph): log: Log.cc: Assign LOG_INFO priority to syslog calls
- LOG_DEBUG prio messages are not logged by a default syslog
configuration so log at LOG_INFO instead.
Fixes: http://t... - 12:55 AM Bug #17400: mon/tool: PGMonitor::check_osd_map assert fail when the rebuild mon store
- *for i in `seq 0 5`;do
ls /var/lib/ceph/osd/ceph-$i/current/meta/
done*...
09/26/2016
- 11:15 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- After looking into the hdparm thing, Brad dropped the requirement for hdparm from master, https://github.com/ceph/cep...
- 11:03 PM rbd Cleanup #16130 (Pending Backport): Proxied operations shouldn't result in error messages if replayed
- 11:03 PM rbd Bug #16473: Demotion/promotion results in the image syncing again from the beginning
- @Ken: most likely, yes -- but there isn't an explicit test case to verify that it is properly functioning.
- 10:56 PM rbd Bug #16473: Demotion/promotion results in the image syncing again from the beginning
- Jason, is this fixed by https://github.com/ceph/ceph/pull/10703 ?
- 10:58 PM rbd Subtask #15108 (Pending Backport): Periodically update the sync point object number during sync
- 09:46 PM rgw Bug #16856 (Pending Backport): ACL request for objects with underscore at end and beginning
- 09:24 PM Revision 6da13e96 (ceph): test: temporarily disable tests which relied on MDS' incorrect GID-addi...
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 09:22 PM Linux kernel client Bug #17410 (Closed): rbd image stale/stuck (mapped and mounted)
- Hello!
We have a problem:
three rbd images are formated and mounted in the system
linux kernel 3.18.35-35
S... - 08:48 PM Revision 1f5d75f3 (ceph): Merge pull request #11226 from zealoussnow/wip-0926
- doc: missing "make vstart" in quick_guide.rst
- 08:42 PM Revision 78e92a9a (ceph): Merge pull request #11228 from stiopaa1/osd_pg_removeUnneededCount1
- osd/PG.cc: remove unneeded use of count
Reviewed-by: Sage Weil <sage@redhat.com> - 08:39 PM rbd Feature #17409 (Resolved): Optional separate data pool support for v2 images
- In support of RBD images on EC pools, the image data block objects will need to be stored on a separate pool from the...
- 08:36 PM Revision 05c4c9e8 (ceph): Merge pull request #11229 from liewegas/wip-compressor
- cmake: remove more autotools hacks
Reviewed-by: Ali Maredia <amaredia@redhat.com> - 07:50 PM Revision b58d2303 (ceph): unittest_compression_*: remove lib dir hackery
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:50 PM Revision 784fe238 (ceph): doc: remove old .libs reference
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:50 PM Revision 404f476e (ceph): ceph: remove autotools detection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:50 PM Revision 4ccb6e34 (ceph): detect-build-env-vars.sh: drop autotools detection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:50 PM Revision 7e574da9 (ceph): vstart.sh: drop autotools detection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:50 PM Revision 24376933 (ceph): ceph-rest-api: drop autotools detection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:11 PM CephFS Bug #17408 (Can't reproduce): Possible un-needed wait on rstats when listing dir?
When a client does "ls -l" on a dir where other clients are doing lots of writes, it can't see an up to date size w...- 06:09 PM Revision ddafda88 (ceph): Merge pull request #10143 from majianpeng/bluefs-fix
- os/bluestore/BlueFS: don't inc l_bluefs_files_written_wal if overwrite.
- 04:54 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- Yes, there's session renewal, and the MDS shouldn't unilaterally revoke caps until that time has passed.
I think w... - 02:07 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- Ok, so to summarize (based on speculation here -- I haven't reproduced this).
After the first ls -l, client A has ... - 01:55 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- So we should change this to use the same value everywhere (from the mdsmap!)
- 04:29 PM Revision 699be445 (ceph): Merge pull request #1188 from ceph/revert-1128-wip-16805
- Revert "ceph_manager: lower mon_reweight_min_bytes_per_osd to 10"
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:01 PM Revision 80b30ec3 (ceph): Merge pull request #11138 from jcsp/wip-17236
- mds: handle blacklisting during journal recovery
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:25 PM Revision 9996b492 (ceph): doc: missing "make vstart" in quick_guide.rst
- Signed-off-by: Leo Zhang <nguzcf@gmail.com>
- 03:19 PM Revision 2e447eaf (ceph): rgw: librados aio wait_for_safe, not wait_for_complete
- We want to wait for the op to be durable, not ordered.
Note that wait_for_safe works for read ops as well, despite a... - 03:15 PM Revision 176811f8 (ceph): Revert "ceph_manager: lower mon_reweight_min_bytes_per_osd to 10"
- 03:02 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- it looks like this time I got a read request stuck for 2 days from OSD. Client is 0.94.9
client cache: ceph-post-f... - 01:58 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- check the cluster log, find lines "client.xxx failing to respond to capability release". client.xxx is the guy that c...
- 01:44 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- hey Zheng,
can you provide me instructions how can I trace client which blocks ops? client.2816210 in this case.
... - 02:27 PM Revision f6bac2c0 (ceph): Merge pull request #11220 from stiopaa1/mds_mdsdaemon_CMDSTickclass
- mds/MDSDaemon: move C_MDS_Tick class to .cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 02:27 PM Revision 49ecdac2 (ceph): Merge pull request #11224 from wjwithagen/patch-13
- osd-fast-mark-down.sh: fix typo in variable assignments
- 02:24 PM Bug #17407 (Resolved): osdthrasher: reweight-by-utilizatoin hits min bytes per osd on upgrade test
- 2016-09-24T06:50:27.084 INFO:teuthology.orchestra.run.vpm033.stderr:Error EDOM: Refusing to reweight: we only have 54...
- 01:56 PM rbd Bug #16056 (Pending Backport): RBD should restrict mirror enable/disable actions on parents/clones
- @mykola: Yes, probably an oversight. Thanks.
- 12:47 PM rbd Bug #16056: RBD should restrict mirror enable/disable actions on parents/clones
- @dillaman Should we backport this to jewel?
- 12:45 PM rbd Bug #16056 (Resolved): RBD should restrict mirror enable/disable actions on parents/clones
- 01:50 PM CephFS Bug #17308 (Fix Under Review): MDSMonitor should tolerate paxos delays without failing daemons (W...
- 01:45 PM Revision fc8e7f31 (ceph): Merge pull request #11212 from liewegas/wip-bluestore-spanning-leak
- os/bluestore: drop unreferenced spanning blobs
- 01:44 PM Revision 438b6f1c (ceph): Merge pull request #11223 from somnathr/wip-bluestore-leak-fix
- os/bluestore: fix spanning blob leak from ~ExtentMap
Reviewed-by: Sage Weil <sage@redhat.com> - 01:43 PM Revision 2c244545 (ceph): Merge pull request #11219 from xiexingguo/xxg-wip-fsck-0924
- os/bluestore: fix fsck() won't catch stray shard sometimes
Reviewed-by: Sage Weil <sage@redhat.com> - 01:25 PM Revision 7b740f5b (ceph): journal: make librados call async in ObjectRecorder
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 01:25 PM Revision aa959e71 (ceph): rbd: Fix race between journal flush and append events
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 01:25 PM Revision 5c737038 (ceph): rbd-mirror: test: Fixed timeout problem in rbd_mirror_stress.sh
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 01:22 PM CephFS Bug #17392 (Fix Under Review): ceph-fuse sometimes fails to terminate (failures with "reached max...
- https://github.com/ceph/ceph/pull/11225
- 01:20 PM Revision 748777dd (ceph): client: protect InodeRef with client_lock
- Fixes: http://tracker.ceph.com/issues/17392
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 12:44 PM Revision db603d8f (ceph): osd-fast-mark-down.sh: fix typo in variable assignments
- Assignments to variables do not want a '$' in front of them.
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl> - 12:43 PM rbd Bug #16079 (Pending Backport): Enable/Disable of features is allowed even the features are alread...
- 12:22 PM rbd Bug #16707 (Resolved): rbd-replay-prep doesn't record discard IO events
- 12:02 PM rbd Bug #15764 (Fix Under Review): rbd-mirror bootstrap fails with -EEXIST when creating local image
- PR: -https://github.com/ceph/ceph/pull/10896- (closed)
- 11:56 AM rbd Bug #16988: 'rbd feature disable' against non-primary image results in hung CLI
- Jason, I think Mykola's PR https://github.com/ceph/ceph/pull/10980 would automatically fix this, right?
- 10:34 AM rbd Bug #17283 (Pending Backport): rbd-mirror: potential race condition results in heap corruption
- 09:59 AM rbd Backport #17406 (Resolved): jewel: rbd-mirror: force-promoted image will remain R/O until local r...
- https://github.com/ceph/ceph/pull/11433
- 09:58 AM rbd Backport #17405 (Resolved): jewel: Sporadic failure in TestMockJournal.ReplayOnDiskPostFlushError
- https://github.com/ceph/ceph/pull/11433
- 09:58 AM rbd Backport #17404 (Resolved): jewel: update_features API needs to support backwards/forward compati...
- https://github.com/ceph/ceph/pull/11462
- 09:58 AM Backport #17403 (Resolved): hammer: OSDMonitor: Missing nearfull flag set
- https://github.com/ceph/ceph/pull/11273
- 09:58 AM Backport #17402 (Resolved): jewel: OSDMonitor: Missing nearfull flag set
- https://github.com/ceph/ceph/pull/11272
- 09:58 AM Bug #17390 (Pending Backport): OSDMonitor: Missing nearfull flag set
- 09:26 AM Revision 5c88edd6 (ceph): journal: increase concurrency of journal recorder
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 08:37 AM rgw Bug #17401 (New): rgw folder name with underscore (_) problem
- Our company have 4 different CEPH clusters and all of these have the same issue:
underscore (_) problem and how ... - 08:01 AM Bug #17400: mon/tool: PGMonitor::check_osd_map assert fail when the rebuild mon store
- sorry should be...
- 06:34 AM Bug #17400: mon/tool: PGMonitor::check_osd_map assert fail when the rebuild mon store
for i in `seq 0 5`; do
ls /var/lib/ceph/osd/ceph-3/current/meta/
done...- 06:11 AM Bug #17400 (Resolved): mon/tool: PGMonitor::check_osd_map assert fail when the rebuild mon store
- 1. ceph version
https://github.com/ceph/ceph/pull/11126
tchaikov:wip-17179-jewel
2. cluster info:... - 07:57 AM Bug #17331: ceph-disk list reports mount error for OSD having mount options with SELinux context
- A minimal reproducer using a dev cluster. Make sure selinux is enforcing....
- 07:18 AM Bug #16677 (Rejected): Unable to create rbd image format 2 on Hammer cluster from Jewel client
- Not a bug
- 04:17 AM Bug #17386: Upgrading 0.94.6 -> 0.94.9 saturating mon node networking
- > option 1: re-encode the MOSDMap message if GMT_HITSET feature bit is missing.
- downside
* larger memory fo... - 01:41 AM Revision b5db8bcb (ceph): rbd-mirror: Add sparse read for sync image
- Currently, the image sync do full read, and we shall add sparse read
to let the sync more efficiently.
Feature: http... - 12:52 AM Revision c5893088 (ceph): BlueStore: Fixed a memory leak
- If a Blob is spanning is not getting deleted as spanning_blob_map
is holding one ref.Explicitly decreasing Blob ref f...
09/25/2016
- 11:11 PM rgw Bug #17398: S3 CreateBucket should issue 409 BucketAlreadyOwnedByYou or 400 IllegalLocationConstr...
- I went and explicitly tested AWS S3 behavior for you, to confirm it, and as usual found it differed slightly from the...
- 08:27 PM Revision 928c3c30 (ceph): Merge pull request #11196 from tchaikov/wip-lttng-the-right-way
- lttng: build the tracepoint provider lib from .c files in repo
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:37 PM Revision 921aa6eb (ceph): osd/PG.cc: remove unneeded use of count
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 12:45 PM Revision f810c106 (ceph): rbd-mirror: wait for in-flight event commit notifications
- Fixes: http://tracker.ceph.com/issues/17355
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 12:44 PM Revision 72d8992f (ceph): common: move AsyncOpTracker to common library
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 11:35 AM Revision e6313f35 (ceph): osd/OSDMap.cc: remove unneeded use of count
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
09/24/2016
- 07:37 PM Revision 3321f100 (ceph): mds/MDSDaemon: move C_MDS_Tick class to .cc file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 05:14 PM rbd Bug #16974 (Pending Backport): rbd-mirror: force-promoted image will remain R/O until local rbd-m...
- 05:13 PM Revision 9aab326d (ceph): Merge pull request #11090 from dillaman/wip-16974
- rbd-mirror: force-promoted image will remain R/O until rbd-mirror daemon restarted
Reviewed-by: Mykola Golub <mgolub... - 06:52 AM Revision dd82ac18 (ceph): os/bluestore: fix dout of BlueStore::fiemap()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:42 AM Revision 01b9901f (ceph): os/bluestore: add a counter to trace checksum latency
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:34 AM Revision 77d3be69 (ceph): os/bluestore: remove a never reachable assert
- As this assert is deprecated by the
"else if (it->key() >= tail)"
checking lying ahead.
Signed-off-by: xie xingguo... - 03:14 AM CephFS Bug #16367 (Fix Under Review): libcephfs: UID parsing breaks root squash (Ganesha FSAL)
- https://github.com/ceph/ceph/pull/11218
- 02:55 AM Revision 84793583 (ceph): os/bluestore: promote output to derr on catching bad/stray objects
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:50 AM Revision 144199a7 (ceph): os/bluestore: fix fsck() won't catch stray shard sometimes
- which is introduced by https://github.com/ceph/ceph/pull/11210/commits/dcfbc72fcbb48f4ced0c1a2d46a77f43bff38c9f
Sign... - 01:48 AM CephFS Feature #3314: client: client interfaces should take a set of group ids
- Passing this off since he's been doing the statx interfaces and has more experience as a library consumer.
- 01:12 AM Revision 7d2a8b71 (ceph): Merge remote-tracking branch 'origin/master' into wip-getuid
- Conflicts:
src/client/Client.cc
src/client/Client.h
src/client/Makefile.am
src/client/fuse_ll.cc
Signed-off-by: ... - 12:05 AM rgw Bug #17398: S3 CreateBucket should issue 409 BucketAlreadyOwnedByYou or 400 IllegalLocationConstr...
- can you validate this behavior with the Amazon S3 api?
09/23/2016
- 11:46 PM rgw Bug #17399 (Duplicate): Period commit that changes default_placement can cause RGWs to crash.
- While testing for #17398, a change of default_placement caused my RGW instances to all exit after @period update --co...
- 11:41 PM rgw Bug #17398 (New): S3 CreateBucket should issue 409 BucketAlreadyOwnedByYou or 400 IllegalLocation...
- Old buckets have a placement pool of an empty string.
Newer configurations, per the multisite documentation have a... - 10:50 PM Revision 1c81ea29 (ceph): Merge pull request #11197 from yuyuyu101/wip-bluestore-misc
- os/bluestore: misc cleanups
Reviewed-by: Sage Weil <sage@redhat.com> - 10:09 PM Revision 01bf7a55 (ceph): Merge pull request #11215 from stiopaa1/mon_paxos_moveContextClassesToCC
- mon/Paxos: move classes to .cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 09:41 PM Bug #17396 (Resolved): "osd recovery max single start" is not documented
- @osd recovery max single start@ is the maximum number of recovery operations that will be newly started when an OSD i...
- 09:12 PM Revision 652d9b65 (ceph): Merge pull request #1185 from jcsp/wip-dirfrags-2
- tasks/ceph: enable dirfrags in cephfs
- 09:11 PM Revision 89efe19d (ceph): Merge pull request #1186 from ceph/wip-ubuntu-java
- suites/fs: pin java test to ubuntu
- 08:59 PM Revision 4ece5b70 (ceph): ceph_test_objectstore: add a test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:53 PM devops Cleanup #17395 (Fix Under Review): rpm: /etc/ceph/rbdmap is packaged with executable access rights
- PR for master: https://github.com/ceph/ceph/pull/11217
- 08:49 PM devops Cleanup #17395 (Resolved): rpm: /etc/ceph/rbdmap is packaged with executable access rights
- In the RPM packages, @/etc/ceph/rbdmap@ is installed with executable permissions, and it should not be executable.
... - 08:52 PM Revision d4b84a13 (ceph): rpm: fix permissions for /etc/ceph/rbdmap
- Prior to this change, the RPM packaging would install /etc/ceph/rbdmap
with exectuable permissions. The execute bit i... - 08:40 PM Revision e86ad687 (ceph): os/bluestore: prevent extent merging across shard boundaries
- We cannot have a single extent span a shard boundary. If we reach
a shard boundary, stop merging extents.
Note that... - 06:43 PM Revision d21357a7 (ceph): mon/Paxos: move classes to .cc file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 05:27 PM rgw Bug #15896: S3: set EncodingType in ListBucketResult
- @ayang, the fix for this has made it into 0.94.9, so what you're seeing could be a different issue. Can you provide a...
- 05:21 PM rgw Backport #17394 (Resolved): jewel: rgw: nfs: fix NFS creation (and other?) times for S3-created b...
- https://github.com/ceph/ceph/pull/11335
- 05:20 PM rgw Backport #17393 (Resolved): jewel: rgw: rgw_file: fix set_attrs operation
- https://github.com/ceph/ceph/pull/11335
- 05:00 PM CephFS Bug #17392 (Resolved): ceph-fuse sometimes fails to terminate (failures with "reached maximum tri...
- Seen here:
http://pulpito.ceph.com/jspray-2016-09-21_18:37:24-fs-wip-jcsp-greenish-distro-basic-smithi/429512/
http... - 04:54 PM Revision 8ddb7fe9 (ceph): Merge pull request #11170 from ukernel/wip-17253
- client: fix segment fault in Client::_invalidate_kernel_dcache().
Reviewed-by: John Spray <john.spray@redhat.com> - 03:51 PM Revision 6333fc27 (ceph): librados: set is_read for aio_stat and aio_stat2
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:29 PM Revision 9ecfed38 (ceph): Merge pull request #11142 from hzhang-wx/master
- cls_rbd: clean up status from rbd-mirror if image removed
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:24 PM Revision 2fda018d (ceph): Merge pull request #10939 from oritwas/wip-rgw-acl-underscore
- rgw: fix regression with handling double underscore
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:17 PM Revision d32654b7 (ceph): rgw: store oldest mdlog period in rados
- RGWMetadataManager no longer makes stat calls on logs shards to
determine its oldest_log_period. Instead, it records ... - 02:50 PM Bug #17248 (Fix Under Review): Reduce deep scrub impact on normal operations
- 02:41 PM rgw Bug #17387: multisite: 'radosgw-admin period prepare' is obsolete
- I will be working on it. I do not have assigned permission though.
- 02:28 PM Revision 7f228e97 (ceph): Merge pull request #11159 from linuxbox2/rgw-setattr-920
- rgw_file: fix set_attrs operation
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:16 PM Revision 5daca12b (ceph): os/bluestore: drop unreferenced spanning blobs
- Otherwise we can "leak" these and keep them around indefinitely.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:03 PM Bug #17388 (Closed): strange ceph-client git repository issue
- 01:59 PM Bug #17388: strange ceph-client git repository issue
- Ilya pointed out to me that my remote URL used git protocol.
git@github.com:ceph/ceph-client.git
Apparently that ... - 09:48 AM Bug #17388: strange ceph-client git repository issue
- I see it regularly - AFAICT it just means their blame-like thing didn't work. I suppose it has to do with the reposi...
- 01:45 PM CephFS Bug #17370: knfs ffsb hang on master
- there is no log and I can't reproduce this locally. lower the priority
- 01:45 PM Revision c6211460 (ceph): Merge pull request #11172 from batrick/ceph-conf-metavar
- doc: add $pid metavar conf doc
Reviewed-by: Sage Weil <sage@redhat.com> - 01:43 PM Revision c2ab1155 (ceph): Merge pull request #11200 from yuyuyu101/wip-upper-thread
- msg/async: avoid set out of range ms_async_op_threads option
Reviewed-by: Mark Nelson <mnelson@redhat.com> - 01:40 PM Revision ecfe7309 (ceph): Merge pull request #9170 from Yan-waller/yj-wip-fixrgwnew
- rgw/admin: fix some return values and indents
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 01:36 PM Revision e8cd945e (ceph): Merge pull request #11210 from xiexingguo/xxg-wip-bluestore-0923
- os/bluestore: more cleanups and fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 01:35 PM Revision d755a4a7 (ceph): mds: remove fail-safe queueing replay request
- MDSRank::queue_one_replay() does not create active request
immediately, it just queues corresponding C_MDS_RetryMessa... - 01:12 PM Revision dd46c786 (ceph): Merge pull request #10463 from gongchuang/gc-wip-test
- Client: fixup param type and return value
Reviewed-by: John Spray <john.spray@redhat.com> - 01:02 PM Revision dbbcecf4 (ceph): librbd: unify journal event callbacks into single interface
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:02 PM Revision 39d9e5cc (ceph): librbd: helper class for quiescing in-flight async ops
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:02 PM Revision fd005490 (ceph): librbd: new journal listener event for force promotion
- Fixes: http://tracker.ceph.com/issues/16974
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:02 PM Revision f1cd613e (ceph): journal: send update notification when tag allocated
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:01 PM Revision a43268a4 (ceph): qa/workunits/rbd: new mirroring forced promotion test
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:01 PM Revision a0f65b96 (ceph): qa/workunits/rbd: fix remove mirrored image race conditions
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:01 PM Revision 277b6dd9 (ceph): journal: expose ability to retrieve partial tag list
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:55 PM rbd Bug #17317 (Pending Backport): Sporadic failure in TestMockJournal.ReplayOnDiskPostFlushError
- 12:55 PM Revision 70d6b552 (ceph): Merge pull request #11153 from dillaman/wip-17317
- test/rbd: fix possible mock journal race conditions
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 12:20 PM Revision 6b520710 (ceph): Merge pull request #11054 from rzarzynski/wip-rgw-postobj-nodynalloc
- rgw: eradicate dynamic memory allocation in RGWPostObj.
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 11:13 AM Revision 9d2af1dc (ceph): Merge pull request #1181 from ceph/wip-jewel-release
- Add ceph-deploy tests for released builds
- 10:39 AM Bug #17386: Upgrading 0.94.6 -> 0.94.9 saturating mon node networking
- > It appears that starting with 0.94.7 that the osdmap encoding changed (which was unexpected by developers
the CR... - 10:23 AM rbd Bug #17330 (Pending Backport): update_features API needs to support backwards/forward compatibility
- 10:11 AM CephFS Bug #16640: libcephfs: Java bindings failing to load on CentOS
- Temporarily pinning tests to Ubuntu: https://github.com/ceph/ceph-qa-suite/pull/1186
- 10:11 AM CephFS Bug #16556: LibCephFS.InterProcessLocking failing on master and jewel
- Temporarily disabling: https://github.com/ceph/ceph/pull/11211
- 10:04 AM Revision f99e834d (ceph): suites/fs: remove duplicated frag_enable.yaml
- ...so that all these point back to basic/dirfrag
Signed-off-by: John Spray <john.spray@redhat.com> - 10:04 AM Revision cc8198d8 (ceph): tasks/ceph: enable dirfrags in cephfs
- Otherwise places we set mds_bal_frag have
no effect.
Signed-off-by: John Spray <john.spray@redhat.com> - 09:08 AM Revision dcfbc72f (ceph): os/bluestore: fix potential access violation during shard-key scan
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 08:25 AM Bug #17390: OSDMonitor: Missing nearfull flag set
- Fixed in https://github.com/ceph/ceph/pull/11082
- 08:24 AM Bug #17390 (Resolved): OSDMonitor: Missing nearfull flag set
- Output from 'ceph -s -f json-pretty' wans't showing nearfull flag set.
steps to reproduce:
> ceph pg set_nearfu... - 07:46 AM Revision dfa65e2b (ceph): os/bluestore: kill unused variables "ekey"
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 07:31 AM Bug #17380 (Resolved): ceph-helpers.sh fails in jenkins run
- 06:43 AM Bug #17380 (Fix Under Review): ceph-helpers.sh fails in jenkins run
- https://github.com/ceph/ceph/pull/11208
- 07:26 AM Revision f3cc0f7e (ceph): Merge pull request #11208 from tchaikov/wip-17380
- osd: should not look up an empty pg
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:16 AM Revision 83a1a7e8 (ceph): Merge pull request #10949 from avnerbh/avnerbh-preforker-fix
- preforker: prevent call to 'write' on an fd that was already closed
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:50 AM Revision 48e29fb8 (ceph): osd: should not look up an empty pg
- this fixes the scrub timeouts we spotted in jenkins run and qa run.
it's a regression introduced by c2b7cdb
Fixes: h... - 06:50 AM Revision b975e85a (ceph): test: re-enable test_pg_scrub() test in ceph-helper.sh
- this reverts d053705. i disabled this test in hope to bisect the
offending tests that fail the mysterious jenkins fai... - 06:45 AM Backport #17376: jewel: Assign LOG_INFO priority to syslog calls
- OK, I gt it now, thanks.
- 06:14 AM Backport #17376: jewel: Assign LOG_INFO priority to syslog calls
- That git describe output proves that the PR was merged after jewel release. This is also evident from the merge date ...
- 03:30 AM Backport #17376: jewel: Assign LOG_INFO priority to syslog calls
- I can't work out why this isn't in teh current Jewel master?
$ git describe 8817cac4e0e9fac4e5cf21895f0b688913848a... - 06:14 AM Revision dbe62d01 (ceph): os/bluestore: drop csum_enabled parameter from blob::get_chunk_size()
- The only two callers from bluestore now always set csum_enabled to true,
so there is no need to keep this parameter a... - 05:57 AM Revision 7d31e129 (ceph): os/bluestore: simplify BlueStore::_setup_block_symlink_or_file()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:26 AM Bug #17389: build failure
- When I check the branch master(893205645f6098eaba22dc06395e81765bda06fd), use 'do_cmake.sh' generate makefile, and do...
- 02:23 AM Bug #17389 (Can't reproduce): build failure
- When I check the branch master(893205645f6098eaba22dc06395e81765bda06fd) and I run 'do_cmake.sh'.
I got the followin... - 02:08 AM Bug #16351: jewel : 60-ceph-partuuid-workaround-rules still needed by debian jessie (udev 215-17)
- it's still not mount osd after reboot when the osd disk is raid0
- 01:54 AM Messengers Bug #17378 (Resolved): AsyncMessenger: OSD crash during librbd teuthology test case
- https://github.com/ceph/ceph/pull/11199
- 01:53 AM Revision 4619bc09 (ceph): Merge pull request #11205 from liewegas/wip-async-debug
- msg/async: less verbose debug messages at debug_ms=1
Reviewed-by: Haomai Wang <haomai@xsky.com> - 01:48 AM Revision 08afb40b (ceph): rgw_file: fix set_attrs operation
- The effective part of this change is to always set a value
for RGW_ATTR_UNIX_KEY1 (because it is expected later).
Se... - 01:02 AM RADOS Bug #17229 (Fix Under Review): crushtool will using the out of bound space when testing with "--s...
09/22/2016
- 11:47 PM rgw Bug #17372: RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin works)
- Patch from Yehuda, from cbodley's idea.
Confirmed working on the cluster.... - 05:54 PM rgw Bug #17372: RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin works)
- Slightly newer, also broken bucket as reported by user, but gives a 403, not a 404, so possibly not broken in the sam...
- 11:53 AM rgw Bug #17372: RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin works)
- @zone get@ as requested by Orit:...
- 11:34 AM rgw Bug #17372 (Resolved): RGW will not list Argonaut-era bucket via HTTP (but radosgw-admin works)
- DreamObjects has some very old Ceph production buckets: Argonaut or older.
They do list if you use radosgw-admin buc... - 11:26 PM rgw Bug #17371: RGW loses realm/period/zonegroup/zone data: period overwritten if somewhere in the cl...
- Ok, I traced where it is coming from; and I'd like to explicitly thank Orit for the suggestion.
Two different but ... - 10:59 AM rgw Bug #17371: RGW loses realm/period/zonegroup/zone data: period overwritten if somewhere in the cl...
- Also Also, I took a backup of .rgw.root after the last time it was set, and here's the mtimes to compare....
- 10:48 AM rgw Bug #17371: RGW loses realm/period/zonegroup/zone data: period overwritten if somewhere in the cl...
- stat on the contents of the .rgw.root pool shows some interesting mtimes that correspond with the times above....
- 10:39 AM rgw Bug #17371 (Resolved): RGW loses realm/period/zonegroup/zone data: period overwritten if somewher...
- Something in RGW is causing the active realm/zonegroup/zone data to be silently lost or overwritten. I thought I was ...
- 11:03 PM Revision 3d7169af (ceph): rgw: get_zonegroup() uses "default" zonegroup if empty
- Fixes: http://tracker.ceph.com/issues/17372
An empty zonegroup should be replaced with the "default" zonegroup.
This... - 10:55 PM Bug #16474: OSD scrubs same PG over and over
https://github.com/ceph/ceph/pull/11206
- 06:53 PM Bug #16474: OSD scrubs same PG over and over
- I easily reproduced this and found two entries for 0.c which is the pg repeating the scrubbing:...
- 03:02 PM Bug #16474: OSD scrubs same PG over and over
- Another instance came up on the list (subject: '[ceph-users] Same pg scrubbed over and over (Jewel)') Log available a...
- 04:02 AM Bug #16474: OSD scrubs same PG over and over
Two logs show that OSD::sched_scrub() is entered and the PG returned by service.first_scrub_stamp() is always the s...- 10:17 PM Revision 9e43346a (ceph): osd: Remove extra call to reg_next_scrub() during splits
- Add assert() to catch this in the future
Fixes: http://tracker.ceph.com/issues/16474
Signed-off-by: David Zafman <d... - 09:50 PM Bug #17388 (Closed): strange ceph-client git repository issue
- Alex Elder reported that he was having permission problems accessing the ceph-client git repository here https://gith...
- 08:27 PM Revision 89320564 (ceph): Merge pull request #11181 from linuxbox2/rgw-legacy-time
- rgw_file: pre-assign times
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 08:14 PM rgw Bug #17387 (Resolved): multisite: 'radosgw-admin period prepare' is obsolete
- All that the 'radosgw-admin period prepare' command does is create an empty period and write it to rados. When we add...
- 07:02 PM Revision 59caa3f7 (ceph): Merge pull request #11048 from jimifm/wip-FDCache-master
- os/filestore/FDCache: fix bug when filestore_fd_cache_shards = 0
Reviewed-by: Sage Weil <sage@redhat.com> - 06:57 PM Revision 71aa8237 (ceph): msg/async: no need for ..."started." suffix
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:56 PM Revision f4088ad2 (ceph): msg/async: less noisy about EventCenter owner
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:56 PM Revision 2a491649 (ceph): msg/async: make rx line look like normal debug
- The DispatchQueue prints the traditional ==== line.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:55 PM Revision 68f2158c (ceph): msg/async: make send debug line look like SimpleMessenger's
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:46 PM Revision 85901d92 (ceph): msg/async/AsyncConnection: less noisy about connection top
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:45 PM Revision 004abe0b (ceph): msg/async/EventCenter: less noisy debug on events
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:35 PM Revision 8269159d (ceph): librados: only request ack if AioComplete has an ack callback
- Probalby no librados users are actually using the ack callback, but we are
still requesting an ack message from the O... - 06:23 PM Revision c300da1b (ceph): osd/PG.cc: prevent repeated searching of map/set
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 06:21 PM Revision 3bb268a3 (ceph): Merge pull request #11190 from tchaikov/wip-memstore-clone-fixture
- tests: use a fixture for memstore clone testing
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:15 PM Revision 5a30f11d (ceph): rgw - Add config for testing lifecycle expiration
- Signed-off-by: Daniel Gryniewicz <dang@redhat.com>
- 05:45 PM Backport #17292: jewel: add a tool to rebuild mon store from OSD
- h3. original description
we've received reports from users that all the copies of monitor leveldb are corrupted af... - 05:43 PM Revision a0da15f1 (ceph): Merge pull request #1183 from ceph/wip-librbd-disable-helgrind-jewel
- jewel: suites/rbd: remove helgrind test cases
Reviewed-by: Ilya Dryomov <idryomov@gmail.com> - 05:43 PM Backport #17291: hammer: add a tool to rebuild mon store from OSD
- h3. original description
we've received reports from users that all the copies of monitor leveldb are corrupted af... - 05:39 PM Revision 06771893 (ceph): suites/rbd: remove helgrind test cases
- Helgrind cannot properly handle Ceph's use of std::mutex --
resulting in numerous false positives and potential asser... - 05:37 PM Revision 725b7147 (ceph): src/msg/simple/Accepter.cc: Update logging names and levels
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 05:33 PM Revision fff44962 (ceph): msg/simple/Accepter.cc: replace shutdown() with selfpipe event in poll(...
- In FreeBSD a shutdown on the socket here can generate:
accepter.stop shutdown failed: errno 57 (57) Socket is not con... - 05:32 PM Revision ec3f67f7 (ceph): Merge pull request #1177 from ceph/wip-librbd-disable-helgrind
- suites/rbd: remove helgrind test cases
Reviewed-by: Ilya Dryomov <idryomov@gmail.com> - 05:30 PM Bug #17386 (Resolved): Upgrading 0.94.6 -> 0.94.9 saturating mon node networking
- While attempting to upgrade a 1200+ OSD cluster from 0.94.6 to 0.94.9 serious performance issues are seen every time ...
- 05:29 PM rbd Bug #17182 (Resolved): "sysfs write failed" in smoke
- 05:29 PM rbd Backport #17375 (Resolved): jewel: "sysfs write failed" in smoke
- 12:13 PM rbd Backport #17375 (Resolved): jewel: "sysfs write failed" in smoke
- https://github.com/ceph/ceph-qa-suite/pull/1182
- 05:28 PM Revision f5be1f22 (ceph): Merge pull request #1182 from ceph/wip-smoke-krbd-iozone-jewel
- jewel: smoke: mask out unsupported image features for krbd iozone test
Reviewed-by: Jason Dillaman <dillaman@redhat.... - 05:23 PM Revision b0c20f93 (ceph): msg/async: avoid set out of range ms_async_op_threads option
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 04:36 PM devops Backport #17382 (In Progress): jewel: logrotate script permissions need to match qemu
- 04:34 PM devops Backport #17382 (Resolved): jewel: logrotate script permissions need to match qemu
- https://github.com/ceph/ceph/pull/11201
- 04:36 PM Backport #17385 (Resolved): jewel: ceph cli: Rados object in state configuring race
- https://github.com/ceph/ceph/pull/15762
- 04:35 PM rbd Backport #17384 (Resolved): jewel: helgrind: TestLibRBD.TestIOPP potential deadlock closing an im...
- https://github.com/ceph/ceph/pull/11463
- 04:34 PM Backport #17383 (Resolved): hammer: ceph-objectstore-tool: ability to perform filestore splits of...
- https://github.com/ceph/ceph/pull/11253
- 04:32 PM devops Bug #17381 (Resolved): logrotate script permissions need to match qemu
- Master PR: https://github.com/ceph/ceph/pull/10587
- 04:27 PM Bug #16649 (Rejected): ceph-disk prepare fails when running blkid
- 04:22 PM Revision bbf94ddf (ceph): Merge pull request #10587 from b-ranto/wip-logrotate-root
- logrotate: Run as root/ceph
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 04:17 PM Revision ab42f605 (ceph): Merge pull request #7338 from ceph/cls-lua
- Lua object class support
Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewe... - 04:13 PM Revision eb968f88 (ceph): Merge pull request #10135 from david-z/wip-enhance-ceph-disk-bluestore
- ceph-disk: support creating block.db and block.wal with customized size for bluestore
Reviewed-by: Loic Dachary <lda... - 04:10 PM Revision b846597f (ceph): Merge pull request #10371 from Yan-waller/yj-wip-msgsimple-0720
- msg/simple: close the failed socket fds
https://github.com/ceph/ceph/pull/11052 - 04:03 PM Revision 3edc5c0f (ceph): Merge pull request #11052 from yuyuyu101/wip-shutdown-deadlock
- OSD: avoid FileStore finisher deadlock in osd_lock when shutdown OSD
Reviewed-by: Sage Weil <sage@redhat.com> - 04:01 PM Revision 729a43f8 (ceph): Merge pull request #11082 from aiicore/nearfull_flag_fix
- mon: OSDMonitor: Missing nearfull flag set
Reviewed-by: Sage Weil <sage@redhat.com> - 03:29 PM Bug #16477 (Pending Backport): ceph cli: Rados object in state configuring race
- 03:26 PM Revision 8f8a7a46 (ceph): Merge pull request #11089 from dachary/wip-16477-ceph-helper
- cli: retry when the mon is not configured
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:25 PM Revision 4a6bb07e (ceph): Merge pull request #11199 from yuyuyu101/wip-17378
- msg/async: remove fd output in log prefix
Reviewed-by: Sage Weil <sage@redhat.com> - 03:18 PM Backport #17263: jewel: ceph-objectstore-tool: ability to perform filestore splits offline
- Non-trivial backport, will do next week.
- 03:14 PM Revision 233804ac (ceph): Merge pull request #11195 from xiexingguo/xxg-wip-csum-improve
- os/bluestore: a few fixes about the global csum setting
Reviewed-by: Sage Weil <sage@redhat.com> - 03:11 PM Revision 5588176b (ceph): msg/async: remove fd output in log prefix
- it's tricky to prevent fd racing in logs, otherwise we need to provide with
lock to totally avoid this. But I don't t... - 03:04 PM Feature #17042 (Duplicate): ceph-objectstore-tool with new option 'apply-layout-settings'
- 03:02 PM Bug #17380 (Resolved): ceph-helpers.sh fails in jenkins run
- at least test_repair fails
see https://jenkins.ceph.com/job/ceph-pull-requests/11829/consoleFull
the timestamp ... - 03:01 PM Bug #17361 (Duplicate): pg scrubbing far too often (with logs)
- 02:59 PM Revision 920418e1 (ceph): Merge pull request #11182 from ceph/wip-docs-rm-ink
- remove old references to inktank premium support
Reviewed-by: Sage Weil <sage@redhat.com> - 02:57 PM Revision 7f073e07 (ceph): Merge pull request #11194 from wjwithagen/wip-wjw-rocksdb-include
- src/kv/CMakeLists.txt: force rocksdb/include to first include directory
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:46 PM Revision 07f69779 (ceph): os/bluestore: fix race condition of global csum setting
- The global csum_type option can be changed dynamically and
can be fixed by upgrading into std::atomic.
Signed-off-by... - 02:46 PM Feature #13301: Request for method to track client versions which have connected to Ceph cluster
- My 2 cents re ceph-mgr: it would be nice if this feature was simple enough to be easily backported to jewel, otherwis...
- 11:18 AM Feature #13301: Request for method to track client versions which have connected to Ceph cluster
- thanks Greg, see the discussion in https://bugzilla.redhat.com/show_bug.cgi?id=1267636
the ceph-mgr can only take ... - 02:43 PM Revision ef901344 (ceph): os/bluestore: drop the global bluestore_csum option
- We don't need this option as it can be properly covered
by the bluestore_csum_type option.
Signed-off-by: xie xinggu... - 02:43 PM Revision 62ba4d4e (ceph): os/bluestore: use blob internal settings for csum checking
- This is because:
1. It is more accurate, as the global csum settings may change dynamically.
2. bluestore_blob_t::ver... - 02:31 PM Revision cfb1cab5 (ceph): smoke: mask out unsupported image features for krbd iozone test
- Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
(cherry picked from commit 77949e5cfc1231c96417e90aadc1573137c4b4d7) - 02:24 PM rbd Feature #17379 (New): rbd: journal: remove the image thread pool size limit
- The current thread pool in ImageCtx.cc is initialized with a size of 1. This should be changed to use the config opti...
- 02:17 PM Revision 36ea5710 (ceph): Merge pull request #11151 from ceph/wip-bluestore-error-injection
- os/bluestore: add error injection
- 02:15 PM Revision 545aac4a (ceph): Merge pull request #11184 from liewegas/wip-down-out
- mon: wait 10m (not 5m) before marking down OSDs out
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Gregory... - 02:15 PM Revision ece2507c (ceph): Merge pull request #11186 from majianpeng/bluestore-allocator
- os/bluestore: remove unused head file.
Reviewed-by: Sage Weil <sage@redhat.com> - 02:13 PM rgw Bug #17367 (Fix Under Review): rgw nfs: fix NFS creation (and other?) times for S3-created buckets
- PR for master: https://github.com/ceph/ceph/pull/11181
- 02:12 PM Messengers Bug #17378 (Resolved): AsyncMessenger: OSD crash during librbd teuthology test case
- http://qa-proxy.ceph.com/teuthology/rdias-2016-09-22_06:29:33-rbd-wip-rdias-testing---basic-smithi/430519/teuthology....
- 02:11 PM Revision 969750e9 (ceph): rgw_file: pre-assign times
- Set unix timestamps based on RGW values for creation, modification
time for buckets, objects in stat requests. Regar... - 02:03 PM Revision ed24107e (ceph): Merge pull request #11192 from xiexingguo/xxg-wip-bluestore-0922
- os/bluestore: a few cleanups
Reviewed-by: Sage Weil <sage@redhat.com> - 01:32 PM rbd Bug #17198 (Pending Backport): helgrind: TestLibRBD.TestIOPP potential deadlock closing an image ...
- 01:31 PM Revision ff7fda4c (ceph): Merge pull request #11152 from dillaman/wip-17198
- librbd: potential deadlock closing image with in-flight readahead
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 01:31 PM Revision 1f09557f (ceph): Merge pull request #10506 from wjwithagen/wip-wjw-clock-realtime
- FreeBSD: Define CLOCK_REALTIME_COARSE in compat.h
- 01:24 PM Revision eb3f7c55 (ceph): lttng: build the tracepoint provider lib from .c files in repo
- we should not have `TRACEPOINT_DEFINE` deinfed in both the application
we are tracing and the tracing provider librar... - 12:42 PM Revision 111d2cf2 (ceph): mds: tidy up ScrubHeader
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:42 PM Revision 9c82040b (ceph): mds: populate DamageTable from scrub and log more quietly
- Fixes: http://tracker.ceph.com/issues/16016
Signed-off-by: John Spray <john.spray@redhat.com> - 12:41 PM Revision 0c890282 (ceph): mds: remove redundant checks for null ScrubHeader
- This was originally optional but now all the paths
that kick off a scrub should be going through
enqueue_scrub and th... - 12:19 PM Revision 2757209d (ceph): src/kv/CMakeLists.txt: force rocksdb/include to first include directory
- - Otherwise on FreeBSD older packages could be used for include
this then can result to missing declared functions... - 12:16 PM Backport #17377 (In Progress): jewel: LIBRADOS modify Pipe::connect() to return the error code
- 12:14 PM Backport #17377 (Resolved): jewel: LIBRADOS modify Pipe::connect() to return the error code
- https://github.com/ceph/ceph/pull/11193
- 12:16 PM Revision 165e5abd (ceph): librados: modify Pipe::connect() to return the error code
- Fixes: http://tracker.ceph.com/issues/15308
Signed-off-by: Vikhyat Umrao <vumrao@redhat.com>
(cherry picked from com... - 12:14 PM Backport #17376 (Resolved): jewel: Assign LOG_INFO priority to syslog calls
- https://github.com/ceph/ceph/pull/11231
- 12:12 PM rbd Backport #17374 (Resolved): hammer: image.stat() call in librbdpy fails sometimes
- https://github.com/ceph/ceph/pull/11949
- 12:12 PM rbd Backport #17373 (Resolved): jewel: image.stat() call in librbdpy fails sometimes
- https://github.com/ceph/ceph/pull/11464
- 11:43 AM Revision c8dc8d39 (ceph): doc/rados: remove references to premium support from inktank.com
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 11:43 AM Revision 9bb7cf72 (ceph): doc/rados/troubleshooting: remove references to premium support from in...
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 11:42 AM Revision 6dea73d8 (ceph): Merge pull request #11147 from ukernel/wip-17286
- client: fix readdir vs fragmentation race
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:41 AM Revision 814a4cdd (ceph): Merge pull request #10393 from ukernel/wip-mds-log-flush
- reduce unnecessary mds log flush
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:54 AM Revision c4d88d46 (ceph): Merge pull request #11155 from dillaman/wip-17330
- librbd: backward/forward compatibility for update_features
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 10:50 AM rbd Bug #17310 (Pending Backport): image.stat() call in librbdpy fails sometimes
- 10:50 AM Revision 83697fd5 (ceph): Merge pull request #11148 from dillaman/wip-17310
- librbd: block name prefix might overflow fixed size C-string
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 09:00 AM Revision 765240a5 (ceph): os/bluestore: remove unused head file.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 08:56 AM Revision 1300a766 (ceph): Merge pull request #11176 from zealoussnow/wip-0922
- ceph_fuse: use sizeof get the buf length
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:50 AM Revision 0cad3dc1 (ceph): test_memstore_clone: use StoreTestFixture to do the setup/teardown
- rename test case name from `MemStore` to `MemStoreClone`, because
if we use `TEST_F` to group the tests into a fixtur... - 07:45 AM Revision 7f4dff22 (ceph): ceph_test_objectstore: extract StoreTestFixture into store_test_fixture.cc
- so it can be reused by other tests like test_memstore_clone.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 07:45 AM Revision afac9345 (ceph): ceph_test_objectstore: fail the test if SetUp() fails
- so it will issues a fatal error if anything goes wrong, instead of continuing
with the test cases.
Signed-off-by: Ke... - 07:16 AM Revision fcaeb67d (ceph): os/bluestore: clean up finishers properly
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:49 AM Revision 4213b43a (ceph): os/bluestore: move lookup() of SharedBlobSet back into .h
- Because the lookup() method is simple and easy,
and requires no dout for debugging.
Signed-off-by: xie xingguo <xie.... - 02:32 AM CephFS Bug #17370 (Can't reproduce): knfs ffsb hang on master
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-09-19_17:35:03-knfs-master-testing-basic-mira/424307/teuthology.l...
- 01:34 AM rgw Bug #17369 (New): Fail to show the object's origin size when delete one of the segments uploaded ...
- 1. Using the blow swift command to upload static large object.
@swift upload container --use-slo -S 10M largeOjbect@...
09/21/2016
- 11:45 PM rbd Bug #17199 (Won't Fix): helgrind: lock order warning with journal enabled + cache disabled
- Helgrind is non-functional under master branch due to std::mutex -- no need to fix warnings
- 11:43 PM rbd Bug #17201 (Won't Fix): helgrind: false positive lock order violation between journal and librbd
- Helgrind is non-functional under master branch due to std::mutex -- no need to fix warnings.
- 11:43 PM rbd Bug #17202 (Won't Fix): helgrind: lock order warning within AioCompletion
- Helgrind is non-functional under master branch due to std::mutex -- no need to fix warnings.
- 11:43 PM rbd Bug #17299 (Won't Fix): helgrind: async messenger fails to destruct spin lock
- Helgrind is non-functional under master branch due to std::mutex -- no need to fix warnings.
- 11:43 PM rbd Bug #17300 (Won't Fix): helgrind: boost intrusive_set data race with non-constant time size
- Helgrind is non-functional under master branch due to std::mutex -- no need to fix warnings.
- 11:42 PM rbd Bug #17301 (Won't Fix): helgrind: async messenger race condition warnings
- Helgrind is non-functional under master branch due to std::mutex -- no need to fix warnings.
- 11:38 PM rbd Bug #17355 (Fix Under Review): rbd-mirror: potential crash during replay shut down
- *PR*: https://github.com/ceph/ceph/pull/11185
- 12:15 PM rbd Bug #17355 (Resolved): rbd-mirror: potential crash during replay shut down
- If there is an in-flight event being committed to the journal as the replayer is being shut down, it's possible for a...
- 11:33 PM Revision 99bea1ec (ceph): mds: do not make use of GIDs which aren't included by the Client in its...
- We were previously iterating through all the GIDs allowed by a particular
MDSAuthCap::match, but there are plenty of ... - 11:33 PM Revision 0eb8e4ca (ceph): test: basic checks on gid list is_capable
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 28981f4c (ceph): client: use uid_t/gid_t in _getgrouplist
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 47fc83f7 (ceph): fuse: optionally (off by default) set the group lists on calls
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 5a1b9f84 (ceph): client: add a static pick_my_perms taking a CephContext
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision a8f214f7 (ceph): Client: always pass a Fh to _do_filelock
- We weren't passing in the Fh as a signal we were releasing locks (ie, don't
remove the lock ranges in question rather... - 11:33 PM Revision 550a59dd (ceph): client: include UserPerm contents in may_* debug output
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 24279ef8 (ceph): client: do a shallow copy for MetaRequest::perms
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision e35d0278 (ceph): libcephfs: repeatedly use new default_perms instead of pick_my_perms()
- There's no need to invoke it each time for library-using clients. Either they've
set the default uid/gid or they have... - 11:33 PM Revision fbda12b1 (ceph): mds: pass full gid list to MDSAuthCap checks, when present
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision c04c5203 (ceph): client: push UserGroups into _posix_acl_permission(), instead of passin...
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision ead687b9 (ceph): client: stop using UserGroups for posix ACL checks
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 07ed90ec (ceph): client: Actually handle gid lists in UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 94c35ab3 (ceph): client: stop using UserGroups for may_setattr() now that UserPerm does ...
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 07d6fc03 (ceph): client: remove the now-unused UserGroups entirely
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision d291e664 (ceph): MClientRequest: include the full gid list of the caller
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 36a18166 (ceph): client: give UserPerm a move constructor
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision d519f82e (ceph): client: remove now-unused owner_(uid|gid) from dir_result_t
- 11:33 PM Revision 06d177bc (ceph): client: pass UserPerm to mkdirs, rmdir, symlink, mknod
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision a81d962a (ceph): client: remove now-unused uid-based may_* functions
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 876c58e9 (ceph): client: remove get_(uid|gid) functions
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision d24966f4 (ceph): UserPerm: add trivial implementation of UserGroup interface equivalents
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 30c67879 (ceph): client: switch inode_permission() to UserPerm-based (over UserGroups)
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 8295afa3 (ceph): client: switch Inode::check_mode() to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision d7740fca (ceph): client: call _getattr() with UserPerm in posix checkers
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 4183205e (ceph): client: remove uid-based _geattr() functions
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 2c8403a7 (ceph): client: remove uid-based _create()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision a1d52fad (ceph): client: add a UserPerm to MetaRequest
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 0529a1d4 (ceph): client: move UserPerm into its own header file
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision a13b5b67 (ceph): client: include UserPerm.h in MetaRequest.h
- 11:33 PM Revision fa760479 (ceph): client: replace Inode's "best" logic with a UserPerm over gid/uid pair
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision e9156ad7 (ceph): client: pass UserPerm to ll_walk()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 98195878 (ceph): client: pass UserPerm to describe_layout()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 540c9a8d (ceph): client: pass UserPerm to get_caps_issued()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 78d83d8e (ceph): client: remove uid-based path_walk()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision d3cad9bd (ceph): client: use Fh::actor_perms for _read() and _write()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision c8cd75f4 (ceph): client: switch _posix_acl_create() to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 4cc7c40b (ceph): client: store "actor" UserPerm in Fh, use for requesting file locks and...
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 8e1cbfc6 (ceph): client: fill in _interrupt_filelock() with MetaRequest's uid/gid
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 3aeca21f (ceph): client: use Fh::actor_perm for _write()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 3caa4d23 (ceph): client: pass UserPerm to get_quota_root() and quota helpers
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision db3ec734 (ceph): client: use UserPerm for _posix_acl_chmod
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision a4409472 (ceph): client: pass UserPerm to readlink()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 5c6748d6 (ceph): client: pass UserPerm to all open() variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 193fb0af (ceph): client: pass UserPerm to lookup_ino()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 4d37088a (ceph): client: pass UserPerm to lookup_parent()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 898154fd (ceph): client: pass UserPerm to lookup_name()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 17d1f7e8 (ceph): client: track which request uid/gid granted a cap
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision b05e06ec (ceph): client: fill in cap renewals with the "best" uid/gid perms
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 885f848e (ceph): client: remove client reference from RequestUserGroups
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 0a2c8872 (ceph): client: remove uid/gid-based make_request, push up logic
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision ba678199 (ceph): client: pass UserPerm to chdir() and getcwd()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision dfbac033 (ceph): client: pass UserPerm to statfs() variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 56bd07bd (ceph): client: store UserPerms in dir_result_t and use on MDS requests
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 95df48b4 (ceph): client: pass UserPerm to lookup_hash()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 18f4b164 (ceph): client: switch _lookup() implementation to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision f7c57065 (ceph): client: switch path_walk() implementation to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 71878e3e (ceph): client: switch _getattr() implementation to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 78e20286 (ceph): client: switch _open() implementation to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision e482a509 (ceph): client: switch _create() implementation to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision e2b766bf (ceph): client: switch xattr_permission() implementation to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 7767a4e2 (ceph): client: remove spurious RequestUserGroups from xattr_permission
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 7a5cdaa1 (ceph): client: switch ll_open and ll_create to be UserPerm-based
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 73ad8b40 (ceph): client: remove unused ll_listxattr_chunks declaration
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 5c062752 (ceph): client: add a UserPerm param to mount
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 6a7a7439 (ceph): client: switch _do_lookup() to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 16b3fce6 (ceph): client: switch make_request implementation and verify_reply_trace to Us...
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 4b2771b9 (ceph): client: switch may_*() function implementations to UserPerm
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision acec3d3e (ceph): client: always pass a UserPerm to utime variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 9aae93ad (ceph): client: always pass a UserPerm to truncate variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 71306571 (ceph): client: remove non-UserPerm _setattr implementation
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 882468ab (ceph): client: always pass a UserPerm to stat variants
- Also remove the lstatlite() declaration, since it's not defined.
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 11:33 PM Revision be9e43e2 (ceph): client: always pass a UserPerm to seek variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision 94bac72f (ceph): client: generate UserPerm _open and _create variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:33 PM Revision f648baf9 (ceph): client: always pass a UserPerm to chown variants
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:22 PM rgw Bug #17364: rgw: Unable to commit period zonegroup change
- Downgraded priority & severity. As a workaround, I wiped out the .rgw.root pool, and recreated the content as zonegro...
- 07:46 PM rgw Bug #17364: rgw: Unable to commit period zonegroup change
- Even more minimal case that causes commit to fail....
- 07:28 PM rgw Bug #17364: rgw: Unable to commit period zonegroup change
- ...
- 07:23 PM rgw Bug #17364 (Resolved): rgw: Unable to commit period zonegroup change
- Legacy data on the DreamObjects production cluster .rgw.root pool causes it to be impossible to commit a new zonegroup.
- 10:25 PM CephFS Bug #17368 (Resolved): mds: allowed GIDs must be ordered in the cephx string
- If you do something like
> ASSERT_TRUE(cap.parse(g_ceph_context, "allow * uid=10 gids=10,11,12; allow * uid=12 gid... - 10:24 PM CephFS Bug #16926: multimds: kclient fails to mount
- Assignee changed accidentally. Sorry!
- 10:23 PM CephFS Bug #16926: multimds: kclient fails to mount
- Here was a run with -k testing:
http://pulpito.ceph.com/pdonnell-2016-08-11_20:40:52-multimds-master-testing-basic... - 05:10 PM CephFS Bug #16926: multimds: kclient fails to mount
- Pushing this to Zheng since it's another kclient issue.
- 10:06 PM Revision 817d65bd (ceph): mon: wait 10m (not 5m) before marking down OSDs out
- 5m isn't quite enough time for many boxes to reboot. 10m will do
a better job of masking transient crashes without h... - 09:37 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- Nathan / Zhen,
I will take a look at it.
- 07:42 AM CephFS Bug #17294: mds client didn't update directory content after short network break
- I checked this again. This issue happens only when mds' session_timeout config is non-default (which is smaller than ...
- 02:41 AM CephFS Bug #17294: mds client didn't update directory content after short network break
- Zheng Yan wrote:
> anyone interesting in this. this is easy to reproduce and it's good opportunity to how capability... - 09:09 PM Revision 3b404c6c (ceph): Merge pull request #1180 from ceph/wip-bluestore-code
- misc fixes to test bluestore, but not actual tests in the suite (yet)
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:07 PM Revision dccdb2eb (ceph): tasks/ceph_manager: add bdev_inject_crash_probability support
- Only do the failure injection 50% of the time; otherwise, just
kill as usual.
Signed-off-by: Sage Weil <sage@redhat.... - 09:01 PM Revision f4de41c2 (ceph): inject bdev failures when killing osd on bluestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:01 PM Revision 84bc367c (ceph): objectstore: add filestore and bluestore stubs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:01 PM Revision 0bc2d643 (ceph): objectstore/bluestore.yaml: debug rocksdb
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:01 PM Revision 173a7b27 (ceph): objectstore/bluestore: bluefs env mirror
- Catch bugs in bluefs or rocksdb env layer.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:01 PM Revision 2ae53848 (ceph): tasks/ceph_manager: respect bdev_inject_crash in kill_osd()
- Note that this will only work with bluestore osds.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:58 PM rgw Bug #17367 (Resolved): rgw nfs: fix NFS creation (and other?) times for S3-created buckets
- Buckets created via the S3 API report creation time of 0 (epoch, Jan 1 1970), but should report their RGW-internal cr...
- 08:51 PM Revision a8fd09e4 (ceph): Add basic testing of ceph bits
- simple test suite to test ceph from download.ceph.com
Signed-off-by: Vasu Kulkarni <vasu@redhat.com> - 08:50 PM Bug #15808 (Pending Backport): Assign LOG_INFO priority to syslog calls
- 08:49 PM Revision 5723a69f (ceph): os/bluestore: add error injection
- This is used by the teuthology repair_test.py.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:43 PM Feature #15308 (Pending Backport): LIBRADOS modify Pipe::connect() to return the error code
- 08:35 PM Bug #17366 (Resolved): "assert len(unclean) == num_unclean" in dump_stuck.py in rados suite
- Run: http://pulpito.ceph.com/yuriw-2016-09-20_14:50:21-rados-wip-yuri-testing2_2016_09_19-distro-basic-smithi/
Job: ... - 08:35 PM Bug #17365 (Resolved): mon: forwarded message is encoded with sending client's features
- The sending client's feature don't apply here; we need to encode it so that the receiving mon can decode it again.
- 08:28 PM Revision 9d6ff34b (ceph): rados/basic/tasks/repair_test: enable bluestore error injection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:28 PM Revision 4936d404 (ceph): tasks/thrashosds: fix powercycle, bdev_inject_crash
- The CephManager.kill_osd expects these in its config, not
Thrasher's.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:03 PM Bug #16685: "saw valgrind issues" in rados run
- /a/yuriw-2016-09-20_14:50:21-rados-wip-yuri-testing2_2016_09_19-distro-basic-smithi/425868/
/a/yuriw-2016-09-20_14:5... - 07:48 PM Revision 31b9ff0f (ceph): Merge pull request #11122 from branch-predictor/bp-zlib-improvements
- compressor/zlib: switch to raw deflate
Reviewed-by: Sage Weil <sage@redhat.com> - 07:47 PM Revision 6ce888dc (ceph): Merge pull request #11108 from liewegas/wip-bluefs-dirty-fnodes
- os/bluestore/BlueFS: log dirty files at sync time
- 07:11 PM Bug #17361: pg scrubbing far too often (with logs)
- Log available at http://filedump.ceph.com/samuelj/ceph-osd.12.log.bz2
- 03:17 PM Bug #17361 (Duplicate): pg scrubbing far too often (with logs)
- ceph-users thread '[ceph-users] Same pg scrubbed over and over (Jewel)' has a basically complete log, looks like the ...
- 06:08 PM Revision f25b156f (ceph): osd/PG.h: change PGRecoveryStats struct to class
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 05:02 PM Bug #15260 (Fix Under Review): ceph-disk and ceph-detect-init builds do check-only things on ever...
- Here is a tentative implementation, please let me know what you think: https://github.com/ceph/ceph/pull/11177
- 03:45 PM Bug #15260: ceph-disk and ceph-detect-init builds do check-only things on every build
- Please create an RFE to run flake8 on builds, but stop creating the virtualenv for non-test builds.
- 04:27 PM devops Bug #16169 (Resolved): ceph-detect-init target fails for Jewel build
- We are now having to allow network access when building. This sounds very unreasonable and it isn't something that ha...
- 04:25 PM Revision 92f59035 (ceph): ceph_fuse: use sizeof get the buf length
- Signed-off-by: LeoZhang <nguzcf@gmail.com>
- 04:21 PM Revision a3d13972 (ceph): Merge pull request #1179 from ceph/wip-16688-master
- Removed 11429 config
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:20 PM Bug #16688: Crash in "FileStore::queue_transactions" in rados run
- https://github.com/ceph/ceph-qa-suite/pull/1179
- 04:01 PM Bug #16688: Crash in "FileStore::queue_transactions" in rados run
- Just to keep record, also seen in http://qa-proxy.ceph.com/teuthology/yuriw-2016-09-20_14:50:21-rados-wip-yuri-testin...
- 04:14 PM Revision fde4d3bb (ceph): Removed 11429 config
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 03:53 PM rbd Bug #17182 (Pending Backport): "sysfs write failed" in smoke
- 02:38 PM rbd Bug #17182 (Fix Under Review): "sysfs write failed" in smoke
- https://github.com/ceph/ceph-qa-suite/pull/1178
- 02:10 PM rbd Bug #17182: "sysfs write failed" in smoke
- Ah, sorry - smoke does require a recent kernel since jewel, so 5 is fine.
- 11:52 AM rbd Bug #17182 (In Progress): "sysfs write failed" in smoke
- 5 won't do it because it doesn't install a kernel here - it should be 1. I'll send a PR.
- 03:52 PM Revision 2fd260c8 (ceph): Merge pull request #1178 from ceph/wip-smoke-krbd-iozone
- smoke: mask out unsupported image features for krbd iozone test
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:35 PM Revision bca2d370 (ceph): Merge pull request #11173 from tchaikov/wip-17306
- test/cli/crushtool: fix the test of compile-decompile-recompile.t
Reviewed-by: Samuel Just <sjust@redhat.com> - 03:18 PM Feature #17362 (Resolved): librados: let client specify watch timeout
- Currently the watch timeout is set directly by the osd. Clients like rbd (especially for iscsi) may want to customize...
- 03:05 PM Backport #17358 (In Progress): jewel: doc: fix description for rsize and rasize
- 03:04 PM Backport #17358 (Resolved): jewel: doc: fix description for rsize and rasize
- https://github.com/ceph/ceph/pull/11171
- 03:05 PM Backport #17360 (Resolved): jewel: ceph-objectstore-tool crashes if --journal-path <a-directory>
- https://github.com/ceph/ceph/pull/11407
- 03:05 PM Backport #17359 (Resolved): hammer: ceph-objectstore-tool crashes if --journal-path <a-directory>
- https://github.com/ceph/ceph/pull/11929
- 03:04 PM Bug #17357 (Resolved): doc: fix description for rsize and rasize
- https://github.com/ceph/ceph/pull/11101
- 03:00 PM Revision 40404398 (ceph): test/cli/crushtool: fix the test of compile-decompile-recompile.t
- should read the map from $TESTDIR,
it's a regression introduced by b2c0a07
Fixes: http://tracker.ceph.com/issues/173... - 02:58 PM Revision 8d7d24e0 (ceph): doc: add $pid metavar conf doc
- $pid introduced in 2012 via cf2a0454.
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com> - 02:17 PM Revision 5ab5e826 (ceph): doc: fix description for rsize and rasize
- Signed-off-by: Andreas Gerstmayr <andreas.gerstmayr@gmail.com>
(cherry picked from commit a004254a02cafdee848a382f893... - 02:11 PM Revision e52e2653 (ceph): Merge pull request #11166 from xiexingguo/xxg-wip-bluestore-0921
- os/bluestore: simplify calculation of collection key range
Reviewed-by: Sage Weil <sage@redhat.com> - 02:05 PM Revision ce97719c (ceph): Merge pull request #11131 from ceph/rgw-lifecycle-testing
- Rgw lifecycle testing
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:00 PM CephFS Bug #17253 (Fix Under Review): Crash in Client::_invalidate_kernel_dcache when reconnecting durin...
- https://github.com/ceph/ceph/pull/11170
- 06:40 AM CephFS Bug #17253: Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- there are some unconnected inodes (due to dirty data flush?) , root inode is deleted before the unconnected inodes ge...
- 01:57 PM Revision ddea9a5b (ceph): client: fix segment fault in Client::_invalidate_kernel_dcache().
- when umounting, root can be NULL
Fixes: http://tracker.ceph.com/issues/17253
Signed-off-by: Yan, Zheng <zyan@redhat.... - 01:50 PM Bug #16474: OSD scrubs same PG over and over
- We are also seeing this problem.
2016-09-21 13:19:00.417766 7f704106c700 0 log_channel(cluster) log [INF] : 4.c6 ... - 01:42 PM rbd Feature #17356 (Resolved): object-map: batch updates during trim operation
- When removing or shrinking a very large image, currently each individual object removal could result in an individual...
- 01:19 PM Revision 77949e5c (ceph): smoke: mask out unsupported image features for krbd iozone test
- Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
- 01:04 PM Revision 1707da26 (ceph): Lifecycle - Fix config locking
- The lifecycle config lock was not setting a cookie. This means that all
instances of that lock conflict, causing err... - 01:04 PM Revision 77853a41 (ceph): Lifecycle testing
- Add new config option - rgw_lc_debug_interval - that modifies the
lifecycle algorithm. It treats days as being the c... - 12:56 PM Revision e0e43dd2 (ceph): Merge pull request #11031 from yangdongsheng/du
- rbd: return error if we specified a wrong image name for rbd du
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 11:08 AM rbd Feature #16213 (Fix Under Review): Replicate dynamic feature updates
- PR: https://github.com/ceph/ceph/pull/10980
- 11:07 AM rbd Feature #16212 (Fix Under Review): Replicate image metadata settings
- PR: https://github.com/ceph/ceph/pull/11168
- 11:07 AM Bug #17331: ceph-disk list reports mount error for OSD having mount options with SELinux context
- We do have below given message in /var/log/messages when we see this issue in command line while running 'ceph-disk l...
- 09:18 AM Revision 99bb2f3f (ceph): Merge pull request #11163 from jcsp/wip-cmake-vstart
- doc: Update developer docs for cmake paths
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 09:08 AM Revision 3ab5ef39 (ceph): common/throttle: simplify Throttle::_wait()
- We don't have to check/set the "waited" member when falling into this branch,
which is deemed to be true.
Signed-off... - 09:04 AM Revision 18ccaeaa (ceph): doc: update vstart guide for cmake-ish paths
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:04 AM Revision d89b876d (ceph): doc: update build instructions for cmake
- Signed-off-by: John Spray <john.spray@redhat.com>
- 08:20 AM Revision 79a6611c (ceph): kv/RocksDBStore: no reason to make write_batch using new/delete
- discards new/delete for bat
Signed-off-by: Haomai Wang <haomai@xsky.com> - 07:50 AM CephFS Bug #17308: MDSMonitor should tolerate paxos delays without failing daemons (Was: Unexplained del...
- # leader (mon.b@0) sent begin to peons
* 2016-09-12 22:40:32.630175 7fe3407e7700 10 mon.b@0(leader).paxos(paxos u... - 06:52 AM Bug #13844: ceph df MAX AVAIL is incorrect for simple replicated pool
- Hi Sage Weil,
I see you so very clear about this case so that you can help me show more information ?
In this case:... - 06:50 AM Bug #17354: workunits/rest/test.py fails in qa run
- not reproducible, see
* http://pulpito.ceph.com/kchai-2016-09-21_05:00:32-rados-master---basic-mira/
* http://pul... - 04:02 AM Bug #17354 (Can't reproduce): workunits/rest/test.py fails in qa run
- ...
- 05:57 AM Revision 1a391ff5 (ceph): os/bluestore: simplify calculation of collection key range
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:59 AM Revision 6366d9fc (ceph): Merge pull request #11083 from ifed01/wip-load-plugins-fix
- common/compressor: add libcommon as a dependency for zlib and snappy p…
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:59 AM Revision 1d536901 (ceph): Merge pull request #10975 from stiopaa1/osd_replicatedbackend_moveSomeC...
- osd/PGBackend.h: move structs to .cc file
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:58 AM Revision 121043fa (ceph): Merge pull request #11073 from badone/wip-remove-check_disk_write_cache
- FileJournal: Remove obsolete _check_disk_write_cache function
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:57 AM Revision 4a8bc830 (ceph): Merge pull request #11060 from stiopaa1/mon_osdmonitor_removeAssign
- mon/OSDMonitor.cc: remove use of boost assign
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:56 AM Revision abf3b4d2 (ceph): Merge pull request #11039 from stiopaa1/osd_inprogress_removingCount
- osd/OSD.cc: remove unneeded searching of maps
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:32 AM Revision dc7f10f4 (ceph): bluestore/BitmapFreelistManager: remove extra if/else judgement
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 03:28 AM Revision 114b1e33 (ceph): os/filestore: disable splice since it can't pass store_test
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 03:27 AM Revision cbbfe63b (ceph): Merge pull request #1127 from ryneli/master
- suites/rados: add test case for rockdb's envlibrados
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:14 AM Revision bd79f98f (ceph): Merge branch 'wip-rocksdb-librados-test'
- qa: add test of envlibrados for rocksdb
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:12 AM Revision 958fa7dc (ceph): add qa test of envlibrados for rocksdb
- Signed-off-by: Ryne Li <lizhenqiangsnake@gmail.com>
- 02:56 AM Bug #17307 (Pending Backport): ceph-objectstore-tool crashes if --journal-path <a-directory>
- 02:56 AM Revision 2718e0f1 (ceph): Merge pull request #11146 from tchaikov/wip-17307
- os/filestore/FileJournal: error out if FileJournal is not a file
Reviewed-by: David Zafman <dzafman@redhat.com>
09/20/2016
- 10:36 PM Revision cbe2700c (ceph): Merge pull request #11103 from liewegas/wip-clone-range
- ceph_test_objectstore: test clone_range and fix a few bugs
- 10:35 PM Revision ecaa86f8 (ceph): os/ObjectStore: clarify clone_range semantics
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:35 PM Revision 07982d5d (ceph): os/memstore: fix bug in BufferlistObject::write
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:35 PM Revision 55b9cc4e (ceph): ceph_test_objectstore: exercise clone_range from synthetic
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:35 PM Revision 60ae186f (ceph): ceph_test_objectstore: disable filestore_fiemap
- This very reliably triggers a test failure for
ObjectStore/StoreTest.Synthetic/1.
FIEMAP is bad! Do not use it!
Si... - 10:35 PM Revision 2896d423 (ceph): Merge pull request #11157 from cbodley/wip-memstore-clone
- memstore: clone zero-fills holes from source range
Reviewed-by: Sage Weil <sage@redhat.com> - 10:12 PM rbd Bug #17182: "sysfs write failed" in smoke
- Should be resolved with a modification like the following:...
- 09:56 PM rbd Bug #17182: "sysfs write failed" in smoke
- Also in http://qa-proxy.ceph.com/teuthology/teuthology-2016-09-20_05:00:02-smoke-master-testing-basic-vps/425655/teut...
- 10:04 PM Revision ecc23778 (ceph): 10.2.3
- 09:17 PM Linux kernel client Bug #17329: modprobe test fails
- In any case, commenting out the assert coupled with scheduling without -k is *not* the way to go - that would defeat ...
- 08:24 PM Linux kernel client Bug #17329: modprobe test fails
- The default is to leave the kernel unchanged, or so it was the last time I checked. Even if that got changed and the...
- 08:04 PM Linux kernel client Bug #17329: modprobe test fails
- the default behaviour without -k option is distro, I mainly test on latest distro kernels and ignore known issues, I ...
- 07:48 PM Linux kernel client Bug #17329: modprobe test fails
- This test assumes that the suite is scheduled with -k <something>. If for some reason you wanted to test a distro ke...
- 04:26 PM Linux kernel client Bug #17329 (Closed): modprobe test fails
- Centos + ubuntu and latest jewel
Following test fails during modprobe test, is that line necessary to check?
ht... - 08:31 PM Revision c94244d3 (ceph): Add Install section to systemd rbdmap.service file
- Signed-off-by: Jelle vd Kooij <vdkooij.jelle@gmail.com>
(cherry picked from commit 57b6f656e17124a5ab4cd1400840d9c7c8... - 08:31 PM Revision 7d817e8b (ceph): Merge pull request #10991 from weiqiaomiao/wqm-wip-sync-error
- rgw: fix failed to create bucket if a non-master zonegroup has a single zone
Reviewed-by: Casey Bodley <cbodley@redh... - 08:31 PM Revision b1ce837a (ceph): Merge pull request #10942 from JellevdK/master
- systemd: add install section to rbdmap.service file
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:00 PM rgw Backport #17350 (Resolved): jewel: rgw:response information is error when geting token of swift a...
- https://github.com/ceph/ceph/pull/11474
- 08:00 PM rgw Backport #17349 (Resolved): jewel: Modification for "TEST S3 ACCESS" section in "INSTALL CEPH OBJ...
- https://github.com/ceph/ceph/pull/11475
- 08:00 PM CephFS Backport #17347 (Resolved): jewel: ceph-create-keys: sometimes blocks forever if mds "allow" is set
- https://github.com/ceph/ceph/pull/11417
- 08:00 PM Backport #17346 (Resolved): hammer: Ceph Status - Segmentation Fault
- https://github.com/ceph/ceph/pull/11930
- 08:00 PM Backport #17345 (Resolved): jewel: Ceph Status - Segmentation Fault
- https://github.com/ceph/ceph/pull/11408
- 07:59 PM Backport #17344 (Resolved): jewel: "line 16: exec: ceph-coverage: not found" in upgrade:client-up...
- https://github.com/ceph/ceph-qa-suite/pull/1201
- 07:59 PM rgw Backport #17343 (Resolved): jewel: radosgw Consumes too much CPU time to synchronize metadata or ...
- https://github.com/ceph/ceph/pull/11627
- 07:59 PM rgw Backport #17342 (Resolved): jewel: teuthology: assertion failure in a radosgw-admin related task
- https://github.com/ceph/ceph/pull/12764
- 07:59 PM Backport #17341 (Resolved): jewel: librados memory leaks from ceph::crypto (WITH_NSS)
- https://github.com/ceph/ceph/pull/11409
- 07:58 PM rbd Backport #17340 (Resolved): jewel: exclusive_lock::AcquireRequest doesn't handle -ERESTART on ima...
- https://github.com/ceph/ceph/pull/11465
- 07:58 PM rgw Backport #17339 (Resolved): jewel: objects in the metadata_heap pool are created, but never read ...
- https://github.com/ceph/ceph/pull/11321
- 07:58 PM rgw Backport #17338 (Resolved): hammer: radosgw-admin lacks docs for "--orphan-stale-secs"
- https://github.com/ceph/ceph/pull/11140
- 07:58 PM rgw Backport #17337 (Resolved): jewel: radosgw-admin lacks docs for "--orphan-stale-secs"
- https://github.com/ceph/ceph/pull/11139
- 07:58 PM rgw Backport #17336 (Resolved): hammer: radosgw-admin(8) does not describe "--job-id" or "--max-concu...
- https://github.com/ceph/ceph/pull/11140
- 07:58 PM rgw Backport #17335 (Resolved): jewel: radosgw-admin(8) does not describe "--job-id" or "--max-concur...
- https://github.com/ceph/ceph/pull/11139
- 07:58 PM Backport #17334 (Resolved): jewel: crushtool --compile is create output despite of missing item
- https://github.com/ceph/ceph/pull/11410
- 07:58 PM Backport #17333 (Resolved): hammer: crushtool --compile is create output despite of missing item
- https://github.com/ceph/ceph/pull/11931
- 07:58 PM rgw Backport #17332 (Resolved): jewel: rgw: file setattr
- https://github.com/ceph/ceph/pull/11335
- 07:56 PM rgw Bug #17311 (Pending Backport): rgw: file setattr
- 03:52 PM rgw Bug #17311 (Resolved): rgw: file setattr
- Master PR:
https://github.com/ceph/ceph/pull/8618 - 07:40 PM Revision f99b2836 (ceph): memstore: use const_iterator instead of const_cast
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:40 PM Revision f4d2f8db (ceph): memstore: clone zero-fills holes from source range
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:40 PM Revision 131dab8d (ceph): test: add tests for memstore clone_range
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:54 PM Revision 5a2bccc3 (ceph): Merge pull request #11070 from VictorDenisov/consistency_groups_extract...
- librbd: extract group module from librbd/internal
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 06:54 PM rbd Bug #17330 (Fix Under Review): update_features API needs to support backwards/forward compatibility
- *PR*: https://github.com/ceph/ceph/pull/11155
- 06:44 PM rbd Bug #17330 (Resolved): update_features API needs to support backwards/forward compatibility
- Attempting to disable exclusive lock using a Jewel+ client against an Infernalis OSD will result in an error. Since I...
- 06:52 PM Revision 8cb2ccda (ceph): librbd: update_features should handle Infernalis OSDs
- Fixes: http://tracker.ceph.com/issues/17330
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 06:52 PM Bug #17331 (Resolved): ceph-disk list reports mount error for OSD having mount options with SELin...
- ceph-disk list reports mount error for OSD having mount options with SELinux context...
- 06:34 PM Revision a26c7a5c (ceph): cls/rbd: set_features should adjust the mask to known features
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:28 PM Revision e3fc4dbd (ceph): osd/PG.h: move shared ptr instead of copying it
- When we move newmap into osdmap_ref we prevent unnecessary increase
and decrease of reference count when newmap goes ... - 06:18 PM Bug #15260: ceph-disk and ceph-detect-init builds do check-only things on every build
- It is not necessary to install tox to run flake8. This can easily be done with the flake8 system package.
Running ... - 06:08 PM Feature #14040: ECBackend support for RMW
- Updated the submit_log_entries code to pass back to the backend. Also added projected_last_update and delta_stats to...
- 05:34 PM rbd Bug #17317 (Fix Under Review): Sporadic failure in TestMockJournal.ReplayOnDiskPostFlushError
- *PR*: https://github.com/ceph/ceph/pull/11153
- 04:08 PM rbd Bug #17317 (Resolved): Sporadic failure in TestMockJournal.ReplayOnDiskPostFlushError
- ...
- 05:31 PM Revision 47189839 (ceph): test/rbd: fix possible mock journal race conditions
- Fixes: http://tracker.ceph.com/issues/17317
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 04:57 PM Revision 34b74e14 (ceph): Merge pull request #9844 from rzarzynski/wip-rgw-swift-website
- rgw: add support for Static Website of Swift API
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 04:15 PM rgw Backport #17327 (Resolved): jewel: rgw: remove duplicated calls to getattr
- https://github.com/ceph/ceph/pull/11335
- 04:15 PM rgw Backport #17326 (Resolved): jewel: rgw: rgw file fix bug of rgw_lookup can not exact match file name
- https://github.com/ceph/ceph/pull/11335
- 04:14 PM rgw Backport #17325 (Resolved): jewel: rgw: rgw_file: fix return value signedness (rgw_readdir)
- https://github.com/ceph/ceph/pull/11335
- 04:13 PM rgw Backport #17324 (Resolved): jewel: rgw: ldap: protect rgw::from_base64 from non-base64 input
- https://github.com/ceph/ceph/pull/11332
- 04:13 PM rgw Backport #17323 (Resolved): jewel: rgw: rgw_file: restore local definition of RGWLibFS gc interval
- https://github.com/ceph/ceph/pull/11335
- 04:12 PM rgw Backport #17322 (Resolved): jewel: rgw nfs v3 completions
- https://github.com/ceph/ceph/pull/11335
- 04:11 PM rgw Backport #17321 (Resolved): jewel: rgw: file: remove busy-wait in RGWLibFS::gc()
- https://github.com/ceph/ceph/pull/11335
- 04:10 PM rgw Backport #17319 (Resolved): jewel: rgw nfs 28
- https://github.com/ceph/ceph/pull/11335
- 04:04 PM rgw Backport #17313 (Resolved): jewel: rgw-ldap: add ldap lib to rgw lib deps based on build config
- https://github.com/ceph/ceph/pull/13183
- 04:04 PM rgw Backport #17312 (Resolved): jewel: build/ops: allow building RGW with LDAP disabled
- https://github.com/ceph/ceph/pull/11478
- 02:33 PM Revision e2d4f0af (ceph): Merge pull request #11140 from cbodley/wip-radosgw-admin-man-hammer
- hammer: add orphan options to radosgw-admin --help and man page
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 02:28 PM rbd Bug #17199 (In Progress): helgrind: lock order warning with journal enabled + cache disabled
- 02:21 PM rbd Bug #17198 (Fix Under Review): helgrind: TestLibRBD.TestIOPP potential deadlock closing an image ...
- *PR*: https://github.com/ceph/ceph/pull/11152
- 01:39 PM rbd Bug #17198 (In Progress): helgrind: TestLibRBD.TestIOPP potential deadlock closing an image with ...
- 02:20 PM Revision 3fff41d4 (ceph): os/bluestore: log kv transaction in queue latency
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:19 PM Revision c971d58f (ceph): librbd: potential deadlock closing image with in-flight readahead
- Fixes: http://tracker.ceph.com/issues/17198
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 02:14 PM rbd Bug #17296 (Closed): [teuthology] failure in cli-integration/rbd/formatted-output.t
- Jewel test branch accidentally used against master branch codebase.
- 01:37 PM rbd Bug #17296 (In Progress): [teuthology] failure in cli-integration/rbd/formatted-output.t
- 01:57 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- It seems ObjectCacher::maybe_wait_for_writeback() doesn't get woken up properly. Maybe following patch can fix it
... - 01:48 PM CephFS Bug #17294: mds client didn't update directory content after short network break
- anyone interesting in this. this is easy to reproduce and it's good opportunity to how capability works
- 01:40 PM devops Bug #16169: ceph-detect-init target fails for Jewel build
- The " parent directory is not owned by the current user and the cache has been disabled" error is misleading. Setting...
- 12:30 PM devops Bug #16169: ceph-detect-init target fails for Jewel build
- so we are using pbuilder to build the package, and pbuilder is basically a clean room created by chroot:
* [1] i... - 11:03 AM devops Bug #16169: ceph-detect-init target fails for Jewel build
- @loic I don't think this is a case of environmental leftovers from other builds. We can consistently replicate this p...
- 04:57 AM devops Bug #16169: ceph-detect-init target fails for Jewel build
- I think this may be another case of jenkins not cleaning after itself and starting a job that is under the influence ...
- 03:53 AM devops Bug #16169: ceph-detect-init target fails for Jewel build
- I can't figure out what in the jenkins build is doing the same job as install-deps.sh does, to prepopulate wheelhouse...
- 01:52 AM devops Bug #16169: ceph-detect-init target fails for Jewel build
- I seem to recall that the local wheelhouse is there to accommodate building in environments (like OBS) that aren't co...
- 12:18 AM devops Bug #16169: ceph-detect-init target fails for Jewel build
- It seems like trying to mix /usr/share/python-wheels and a local wheelhouse is doomed to failure. The /usr/share ver...
- 01:39 PM Linux kernel client Bug #17070: Kernel complains about "Bad page state" when cephfs tries to free page
- https://github.com/ceph/ceph-client/commit/ea482ac834bfa45830c868ae2f023640ca006d87
- 01:38 PM CephFS Bug #16397: nfsd selinux denials causing knfs tests to fail
- John Spray wrote:
> I notice a recent run that didn't have any of these failures, possibly the kernel got upgraded?
... - 01:26 PM CephFS Bug #16397: nfsd selinux denials causing knfs tests to fail
- I notice a recent run that didn't have any of these failures, possibly the kernel got upgraded?
http://pulpito.ceph.... - 01:27 PM Revision 0b420821 (ceph): man: add orphan options to radosgw-admin.8
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 01:26 PM Revision b29bf925 (ceph): suites/rbd: remove helgrind test cases
- Helgrind cannot properly handle Ceph's use of std::mutex --
resulting in numerous false positives and potential asser... - 12:52 PM CephFS Backport #17207 (In Progress): jewel: ceph-fuse crash on force unmount with file open
Setting In Progress because Zheng already created a PR
https://github.com/ceph/ceph/pull/10958- 12:50 PM CephFS Backport #17264 (In Progress): jewel: multimds: allow_multimds not required when max_mds is set i...
- Setting In Progress because Patrick already uploaded a PR for Jewel
https://github.com/ceph/ceph/pull/10997 - 12:50 PM Revision 7ba8d71f (ceph): Merge pull request #11149 from xiexingguo/xxg-wip-bluestore-0920
- os/bluestore: narrow condition of sanity check when get_object_key()
Reviewed-by: Sage Weil <sage@redhat.com> - 12:32 PM Revision d4e13191 (ceph): mds/server: merge the snapshot request judgment
- merge the snapshot request judgment,
and all return -EROFS
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 12:00 PM Revision 9b73e00d (ceph): Merge pull request #11121 from stiopaa1/osd_osd_moveMembersToPrivate
- osd/OSD.h: move some members under private
Reviewed-by: Sage Weil <sage@redhat.com> - 11:59 AM Revision 074bbb6b (ceph): Merge pull request #10563 from stiopaa1/mon_healthmonitor_removeUnneede...
- mon/HealthMonitor: remove unneeded include
Reviewed-by: Sage Weil <sage@redhat.com> - 11:58 AM Revision 613efe6c (ceph): Merge pull request #10515 from stiopaa1/mon_monitor_addOverride
- mon/Monitor.h: add override to virtual functions
Reviewed-by: Sage Weil <sage@redhat.com> - 11:58 AM Revision 69001a36 (ceph): Merge pull request #10333 from stiopaa1/msg_EventSelect_RemoveIncFromHe...
- msg/EventSelect: move includes to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 11:57 AM Revision 810567c0 (ceph): Merge pull request #10269 from stiopaa1/osd_watch_removeUnneededForward...
- osd/Watch.h: remove unneeded forward declaration
Reviewed-by: Sage Weil <sage@redhat.com> - 11:56 AM Revision d2b2158d (ceph): Merge pull request #9644 from stiopaa1/osdc_ObjectCacher_const
- osdc/ObjectCacher: change iterator to const_iterator and add const to member functions
Reviewed-by: Sage Weil <sage@... - 11:39 AM rbd Bug #17310 (Fix Under Review): image.stat() call in librbdpy fails sometimes
- *PR*: https://github.com/ceph/ceph/pull/11148
- 11:19 AM rbd Bug #17310 (In Progress): image.stat() call in librbdpy fails sometimes
- 10:18 AM rbd Bug #17310 (Resolved): image.stat() call in librbdpy fails sometimes
- I'm running a simple test script to reproduce this:...
- 11:28 AM Revision 61734d26 (ceph): librbd: block name prefix might overflow fixed size C-string
- The issue which resulted in too large v2 image ids was fixed
under #16887.
Fixes: http://tracker.ceph.com/issues/173... - 11:05 AM CephFS Bug #12909: cmake: client/fuse_ll.cc can't locate fuse_lowlevel.h
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #7867: client/Client.cc: 2087: FAILED assert(!unclean)
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #5289: mds closing stale session
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #5287: the permission of file in CephFS
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Support #5285: cephfs give permission to write files
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #4038: ceph-fuse: various hangs
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Documentation #3672: doc: how to mount ceph-fuse from fstab
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #3184: ceph-fuse should not segfault without a keyring
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #2293: admin sockets don't persist with ceph-fuse
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #2159: ceph-fuse: big_writes option not recognized
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1957: ceph-fuse: have "." and ".." entries consistently
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1746: PerfCounters::set segfault
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1737: ceph-fuse crash in xlist::remove
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1728: multiple cfuse tests failing with non-empty directories
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1603: ceph-fuse crash during unmount
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1510: fsx failure on cfuse
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1509: cfuse sometimes hangs after unmount
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1472: cfuse hangs with v0.34
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1467: cfuse crash during fsx workunit
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1437: cfuse can't change permissions of a file
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1429: cfuse assert failed assert(diri->dn_set.size() < 2)
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1324: cfuse: 2-MDS snaptest2 doesn't let client unmount
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1323: cfuse: 2-MDS snaptest2 doesn't complete
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1252: regression: cfuse fails snaptest-2 with 2-MDS system
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1139: cfuse crashes on exit
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1063: dbench breaks if MDS and client times aren't synced
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Bug #1031: dev node inconsistency between cfuse and kernel client
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Tasks #1039: cfuse: requests max_size from non-auth MDS
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:05 AM CephFS Tasks #862: cap_refs[CEPH_CAP_FILE_BUFFER] isn't cleared if truncation zaps changes
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #858: cfuse craps out with fsstress
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #712: cfuse crashes when Ceph daemons started with vstart.sh
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #596: crash during mds reconnect
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Cleanup #588: Allow Inodes to have multiple parent Dentries
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #583: cfuse fails snaptest-upchildrealms
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #551: cfuse crash on quick mds restart
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #529: Cfuse: Software caused connection abort
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #523: cfuse locks don't wake on mds reconnect?
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #383: cfuse: reimplement readdir
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #373: cfuse is degenerate with respect to ptmalloc
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #349: cfuse fails untar-snap-rm
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #348: cfuse fails fsx test
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #344: cfuse should pass all qa tests
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Feature #321: allow dns names for monitor switch
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #268: cfuse: return EROFS when writing to snaps
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #249: cfuse: pjd failures
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #241: cfuse: make sure fsync does the right thing; remove warning
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Feature #238: cfuse: log to file if run as daemon
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Tasks #237: cfuse: run through full qa suite
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Cleanup #236: cfuse: clean up mds session handling
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Feature #235: cfuse: allow specifying server path to mount on command line
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #232: ESTALE on many copies
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #229: cfuse freezes
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #219: Client doesn't properly flush snapshots
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #211: Cfuse won't unmount properly with snapshot activity
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Bug #188: cfuse crashes on snapshot file read
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Subtask #396: uclient: cleanly update cache with readdir result
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Feature #13: uclient: Make readdir use the cache
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:04 AM CephFS Feature #12: uclient: Make cap handling smarter
- Bulk updating project=ceph category=ceph-fuse issues to move to fs project so that we can remove the ceph-fuse catego...
- 11:01 AM CephFS Support #16528: Stuck with CephFS with 1M files in one dir
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:01 AM CephFS Support #16043: MDS is crashed
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:01 AM CephFS Feature #15589: Ceph status outputs mds slow request summary for better monitoring
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:48 AM CephFS Feature #15589 (Resolved): Ceph status outputs mds slow request summary for better monitoring
- 11:01 AM CephFS Bug #15449: [ceph-mds] mds service can not start after shutdown in 10.1.0
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:50 AM CephFS Bug #15449 (Can't reproduce): [ceph-mds] mds service can not start after shutdown in 10.1.0
(While tidying up cephfs tickets that weren't in the 'fs' project...)
Closing because presumably you've either g...- 11:01 AM CephFS Bug #15156: mds stuck in clientreplay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:01 AM CephFS Support #13267: mds heap stats cause warn message but working
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:01 AM CephFS Feature #9029: min/max uid for snapshot creation
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:01 AM CephFS Bug #8337: Logging too verbose in handle_client_file_setlock
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:01 AM CephFS Bug #8291: 0.80: fuse client hangs after wake-up from suspend until restart of active MDS
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #7980: 0.78: MDS crash (segmentation fault) on client wake-up from suspend.
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #5104: MDS crashed in Objecter::handle_osd_op_reply
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #5079: assert in MDCache::_recovered()
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Documentation #4727: upgrade doc has to be modified to include upgrading ceph-mds as well
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #3598: MDS should shut down cleanly on EBLACKLIST
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #3551: mds: journaler hang
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #3486: ceph-fuse, mds: admin socket lock cycle
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #3470: ceph-fuse: hang when Fr cap revoked
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #3186: mds: mds crash on client shutdown
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #2959: mds: returns null dentry on getattr
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #2596: mds: spinning on restart
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #2299: all MDS commit suicide on startup
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #2110: osdc/Journaler.cc: 360: FAILED assert(r >= 0)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #2018: mds: can't change file_max
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1996: mds: scatter_nudge() bad pointer on shutdown?
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1991: mds: crash during clean shutdown
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Feature #1912: mds: should time out slow monitors
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1902: mds: unittest_interval_tree bad memory access
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1806: MDS won't start
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1796: mds: exit cleanly on EBLACKLISTED
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1792: crash in ceph-mds
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 11:00 AM CephFS Bug #1788: msgr file descriptor leak
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1775: mds startup: _replay journaler got error -22, aborting, possible regresion?
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1756: mds crash right after successful recovery
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1753: ceph copy raw images from qemu incorrectly
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1748: mds segfault CDir::project_fnode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1702: Ceph MDS crash + client mount problem
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1682: mds: segfault in CInode::authority
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1677: mds interval_set.h: 385: FAILED assert(p->first <= start)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1640: mds: failed assert(trim_to > trimming_pos)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1589: MDS assert failure
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1586: failed pjd chmod test 00 on kclient
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1585: mds crash during shutdown
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1573: mds crash during multiple_rsync workunit
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1553: file locking test 2 fails
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1549: mds: zeroed root CDir* vtable in scatter_writebehind_finish
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1541: flock: a single request can get multiple locks set
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1538: mds: all clients can and up becoming unresponsive, mds locker waiting for unfreeze
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1464: mds crash during shutdown (after trivial_sync workunit on kclient)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1460: mds: file locks don't work right with 0-length locks
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1447: mds: does not validate pool IDs in handle_client_set[dir]layout
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1446: cephfs: pool option doesn't work
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1433: mds: assert in path_traverse
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1428: MDS: Load and pin stray dirs in memory
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1425: mds: stuck in prexlock
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1417: mds: failed assert on xlock
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:59 AM CephFS Bug #1405: cephfs: shouldn't have to specify all layout options
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1399: mds crash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1390: MDS crash in function 'bool Locker::issue_caps(CInode*, Capability*)', in thread '0x7f...
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1389: re-created snapshot gets removed by mds journal replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1368: mds crash after blogbench on cfuse
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1367: cfuse and mon crash after dbench
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1360: mds crash during pjd workunit on cfuse
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1366: mds segfault
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1350: mds: dup lookups on scp workload
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1349: mds: standby-replay leaks memory
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1346: failed Locker.cc assert
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1326: mds: project subtree_map changes due to rename
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1310: mds crash 'T interval_set<T>::range_start() const [with T = inodeno_t]'
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1302: mds: mds_caps_wanted vs migration
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1295: mds: handle rmdir of subtree root
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1289: misdirected mds request results in improper ENOENT during mds rename workunits
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1243: inest lock blocks dir create for a long time
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1238: mds: ~elist crash on untar_snap_rm
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1200: 4-MDS fsstress remote ino lookup cycle
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1199: 4-MDS fsstress: remote ino lookup assert
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1195: ceph mds crash on version upgrade
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1193: cmds crashes with stacktrace when using --reset-journal and an invalid rank
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1183: mds: snaptest-snap-rm-cmp.sh failing
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1178: cfuse doesn't shut down -- Fw cap doesn't flush on one inode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1170: 2-MDS fsstress: SR fails subtree assert
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:58 AM CephFS Bug #1169: 2-MDS fsstress: Active fails adjust_subtree_auth
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1168: fsstress 2-mds Standby-replay adjust_subtree asserts
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1167: Fsstress: bad rstat assert
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1166: mds: standby-replay bound asserts
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1158: Unfinished freeze hangs fsstress
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1153: Hang on 3-MDS fsstress
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1146: mds: correctly trim cache after rename witness replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1137: MDS Crash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1133: mds: journaler failed assertion on standby-replay -> replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1132: mds: missing parent in rename metablob
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1128: clustered mds: failed verify_subtree_bounds
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1111: file lock requests in wait queue not getting cleaned up after process exit
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1110: mds: ls -l hangs on concurrent writer
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1108: Large number of files in a directory makes things grind to a halt
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1104: Segmentation fault when deleting a folder
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1084: blogbench won't finish: waiting for Fr cap forever
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1065: mds: can't authenticate with --reset-journal
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1064: all mds's dies one by one after restart
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1041: standby-replay fails on multi-mds fsstress journals
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1023: just-recovered mds fails journaler assert (to > trimming_pos);
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1022: every mds crash: Program terminated with signal 11, Segmentation fault.
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1019: mds: ~MDSlaveUpdate while on LogSegment list
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #1006: clean up cmds journal-check mode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #994: EOpen reply on non-auth MDS is busted
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #968: mds: verify_bounds error
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #966: mds: scatterstat error
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #938: mds: rstats mismatch
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #937: journaler: _issue_read assert
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #933: mds: standby-replay incorrectly probed journal for live mds
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Bug #932: mds: standby-replay osd ops have bad entity_name_t
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:57 AM CephFS Cleanup #929: mds: make journal replay readahead less silly
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #1002: Assert failure in Locker::handle_file_lock
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #973: Dir failing to freeze
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #934: auth_unpin assert fail in Locker::xlock_finish
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #928: Assert failure on replica: has auth pins in _logged_slave_rename
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #923: Waiter does not get woken in fsstress
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #922: fsstress: Request ping-pongs when dentry and inode auth are separate
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Cleanup #886: journaler: rip out ack_barrier cruft
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #873: MDS journaler needs to truncate ahead of writes
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #861: handle_client_rename thinks nonexistent dir is in subtree map
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Subtask #879: Implement function to check fragstat and rstat on CDirs
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Feature #818: mds: robust lookuphash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #805: mds startup: _replay journaler got error -22, aborting
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #791: ls -al waits for writes to complete
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Tasks #797: Don't _commit_full just because dir is_complete()
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #725: mds: set_layout on root inode isn't persistent
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #724: mds: cmds ignores signals (like SIGTERM) after respawn
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #723: mds: cmds ignores signals (like SIGTERM) after respawn
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #721: mds crash with multiple mds
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #708: mds replay crash on slide0
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #689: cmds crash: mds/CInode.h:1088: FAILED assert(ref_set.count(by) == 0)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #684: unstable fails some workunits
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #678: What if period == 0 in MDCache...purge_stray?
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #671: mds: fragstat problem after mds restart
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #663: cmds segfaults
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #661: mds: mdlog recursion / scatter crash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Cleanup #638: mds: verify open+create resent/replayed event exception
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #637: mds: check replica scatterlock flush on rejoin
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #623: MDS: MDSTable::load_2
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #608: mds: MDCache::create_system_inode()
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Feature #602: mds: handle corrupt/missing journals
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Feature #600: mds: store full trace on directories
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:56 AM CephFS Bug #594: mds: frag split/merge vs replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #593: mds: fsck: anchor table repair
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #570: Locker::_do_null_snapflush assert failure
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #561: snaptest-2 doesn't execute properly
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #560: mds: alternate directory hashing
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #556: clustered mds: rename
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #548: mds: shadowreplay one-shot mode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #545: mds: use bloom filter to supplement dirfrag COMPLETE flag
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #542: mds journal corruption
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #525: Audit CInode creation code for initialization
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #519: mds: dirfrag merge
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Cleanup #514: Optimize MIX/MIX_STALE reconnects, etc
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #500: mds: FAILED assert("shouldn't be called if we are already xlockable" == 0)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #495: mds: add MIX_STALE
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Cleanup #493: mds: allow scatter_pinned inode to go from mix -> sync
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #483: mds: add timestamp to LogEvent
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #478: MDS crash: LogEvent::decode()
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #472: mds: fragstat crash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Cleanup #468: mds: use enum for LOCK_* in mds/locks.h
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Feature #466: mds: respawn on suicide
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #452: mds: failed assert(root) in MDCache::adjust_subtree_auth()
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #451: mds: replay error
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #447: mds: failed assert(cap) in void Locker::handle_client_caps(MClientCaps*)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Cleanup #431: mds: clean up inode journaling internal interfaces
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Cleanup #427: mds: tie scatter pins directly to freeze machinery
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #426: mds: rstat propagation
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #413: mds: avoid lookup/fetch/trim/lookup loop
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #408: mds: missing snap past parents
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #395: mds: interval_set assert(0) during journal replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #394: mds: scatterlock scatter dir accounted_fragstat writeback
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #393: mds: migration vs locking
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #385: Failed assertion in Locker::scatter_nudge
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #370: mds: need to re-eval caps after import
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Tasks #366: test snaptests against clustered mds failures
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Tasks #365: test snaptests against single mds failure
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #362: mds: rejoin crashes on snaptest-2 workload
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #360: mds: head/snapped snap_cap linkage may cross mdss
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #356: mds: cap writeback/release race with cow_inode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:55 AM CephFS Bug #351: mds: fix cow on xattrs
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Feature #340: large directories, directory fragmenting
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #329: mds: mislinked dentry found during journal replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #328: MDS crash: MDCache::remove_inode(CInode*)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #319: allows snaps in root directory
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #318: Multi-MDS snaptest-2 fails
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #316: mds: track dirty snapped metadata without faking a cap
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #312: MDS crash: LogSegment::try_to_expire(MDS*)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #297: MDS crash on Objecter::handle_osd_op_reply
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #296: Locker::simple_sync assert(0)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #295: mds: can't rmdir due to dir size underflow
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #288: cmds disappears under snapshot load
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #274: OSD crash during rsync
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #269: mds: don't crash when attempting to write to a snapshotted dir
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #259: MDS crash during log initialize
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #255: MDS crash while during journal replay
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #177: unlinked inode during try_to_expire()
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #172: OSD and MDS crash on rm -r
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #171: mds: MDSTableClient::_logged_ack(version_t) FAILED assert(pending_commit.count(tid))
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #170: null pointer dereference in journal_cow_dentry causes assertion failure
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #167: mds crash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #165: cmds crash
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #153: mds: fix snap dentry replication vs readdir on frag auth
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #92: mds: journal client_map for rename importing inode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Feature #91: mds: up:shadow mode
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Feature #88: mds: change stray commit strategy to avoid rolling stray dir commits
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #77: mds: anchor_create calls acquire_locks
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #75: mds: fix rdlock semantics
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Feature #57: mds: feature bits in mdsmap?
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #52: mds: dentry versionlock
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #51: delete directories don't appear in snap
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #46: Remove asker from MDiscover
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Feature #45: Investigate adding Connection * to mds Session
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #44: Make MDS use new connection-based send_message
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #34: mds: nonempty cap xlist on snaprealm during trim
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #30: multimds: slave_request on getattr
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #29: mds: rfiles underflow
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #16: mds restart vs dbench
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:54 AM CephFS Bug #15: mds rejoin: invented dirfrags (MDCache.cc:3469)
- Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid con...
- 10:49 AM rgw Bug #17256: objects in the metadata_heap pool are created, but never read or removed
- I'm not Abhishek, but AFAIK 10.2.3 has already been approved and release is imminent.
- 07:51 AM rgw Bug #17256: objects in the metadata_heap pool are created, but never read or removed
- Abhishek, what's the chance this making it to Jewel 10.2.3?
- 10:29 AM Revision d0bd0fcf (ceph): Merge pull request #11093 from ceph/wip-jlayton-statx
- Small interface cleanups for struct ceph_statx
- 10:26 AM Revision b332eed1 (ceph): client: always provide the file type in stx_mode
- The proposed statx interface does this, and this would allow ganesha
to get away without requesting CEPH_STATX_MODE w... - 10:26 AM Revision 6e332428 (ceph): client: convert ceph_statx to use dev_t for devices
- Signed-off-by: Jeff Layton <jlayton@redhat.com>
- 10:26 AM Revision ab1cf1df (ceph): Revert "client: move the device bitshift handling macros to Client.h"
- This reverts commit 2115de04a417e6df4272fc836829b70bd6a2b97e.
This is unnecessary now that we're using dev_t's in ce... - 10:26 AM Revision e64493c4 (ceph): client: remove unimplemented fields from ceph_statx
- We don't provide stx_version and stx_information is currently unused.
Signed-off-by: Jeff Layton <jlayton@redhat.com> - 10:26 AM Revision 897213d7 (ceph): client: switch ceph_statx time fields to struct timespec
- This is just much more convenient for applications that want to use
the API. We're not talking to the kernel here, so... - 10:25 AM Revision d1bfc9a5 (ceph): client: remove unneeded extra padding from ceph_statx
- Holdover from the proposed kernel API that doesn't really help anything
here. If we ever want to extend this struct, ... - 10:19 AM CephFS Bug #17286 (Fix Under Review): Failure in dirfrag.sh
- https://github.com/ceph/ceph/pull/11147
- 10:18 AM Revision feb63776 (ceph): client: fix readdir vs fragmentation race
- following sequence of events tigger the race
client readdir frag 0* -> got item 'A'
MDS merges frag 0* and frag 1*
c... - 10:11 AM CephFS Bug #17236: MDS goes damaged on blacklist (failed to read JournalPointer: -108 ((108) Cannot send...
- As for the mystery of why this started happening, I think the MDS failures are triggered by #17308
- 10:09 AM CephFS Bug #17253: Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- Zheng: do you have any ideas about why this path is crashing when called during unmount?
- 09:46 AM CephFS Bug #17253: Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- The beacons from the guy that got killed do make it eventually but with a severe delay:...
- 09:33 AM CephFS Bug #17253: Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- ...
- 08:41 AM CephFS Bug #17253: Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- Note this is happening during umount
- 10:04 AM CephFS Feature #17309 (Resolved): qa: mon_thrash test for CephFS
We don't currently have anything that thrashes the mons while running CephFS. It would be useful to run with a thr...- 10:01 AM CephFS Bug #17308 (Resolved): MDSMonitor should tolerate paxos delays without failing daemons (Was: Unex...
We have had a couple of mysterious new issues crop up in CephFS that I now think might be the result of some weirdn...- 09:43 AM Bug #17307 (Fix Under Review): ceph-objectstore-tool crashes if --journal-path <a-directory>
- https://github.com/ceph/ceph/pull/11146
- 09:37 AM Bug #17307 (Resolved): ceph-objectstore-tool crashes if --journal-path <a-directory>
- ...
- 09:42 AM Revision 7431eec6 (ceph): os/filestore/FileJournal: fail out if FileJournal is not block device o...
- otherwise JournalingFileStore will assert when deleting FileJournal
which still has the non block/regular file opened... - 06:54 AM Revision 5ee0b620 (ceph): msg: fix format specifier for unsigned value id
- Signed-off-by: Weibing Zhang <zhangweibing@unitedstack.com>
- 06:46 AM Bug #17306 (Pending Backport): crushtool --compile is create output despite of missing item
- 06:23 AM Bug #17306 (Fix Under Review): crushtool --compile is create output despite of missing item
- https://github.com/ceph/ceph/pull/11144
- 06:20 AM Bug #17306 (Resolved): crushtool --compile is create output despite of missing item
- 06:45 AM Revision c76824f8 (ceph): Merge pull request #11144 from tchaikov/wip-17306
- crush/CrushCompiler: error out as long as parse fails
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 06:36 AM CephFS Bug #17297: high cpu usage for ceph-fuse (>150%)
- ...
- 06:20 AM Revision b2c0a079 (ceph): crush/CrushCompiler: error out as long as parse fails
- do not output compiled crush map if anything goes wrong when parsing
crush map.
Fixes: http://tracker.ceph.com/issue... - 06:14 AM Revision 01a3f94b (ceph): os/bluestore: narrow condition of sanity check when get_object_key()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 04:46 AM Revision d80784e5 (ceph): RADOS: fix write op hangs
- if primary OSD handle a write op and do_osd_ops return errro code,
record_write_error will try to record it into pglo... - 04:15 AM Bug #13937: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- note, should revert https://github.com/ceph/ceph/commit/5bc55338f5a1645bc651811fae2f89ad855ff86e#diff-1b6e7a54c1cf4f2...
- 03:43 AM Revision 67b11b01 (ceph): ceph-disk: update/add ceph-disk test cases for bluestore
- Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
- 03:43 AM Revision 4c1cd4ab (ceph): ceph-disk: support creating block.db and block.wal with customized size...
- Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
- 03:35 AM Revision c36e8050 (ceph): cleanup status global from rbd mirror if image removed
- Signed-off-by: Huan Zhang <zhanghuan@chinac.com>
- 03:11 AM Revision 1f7d12d7 (ceph): Merge pull request #11129 from xiexingguo/xxg-wip-bluestore-0919
- os/bluestore: misc. fixes
Reviewed-by: Sage Weil <sage@redhat.com. - 03:08 AM Revision 2d97c24b (ceph): Merge pull request #11116 from badone/wip-rm-modprobe-run-cmake-check
- run-cmake-check.sh: Remove redundant calls
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Ilya Dryomov...
09/19/2016
- 11:41 PM Revision b0220362 (ceph): Merge pull request #10943 from jdurgin/wip-tox-coverage
- tox.ini: remove extraneous coverage --omit option
Reviewed-by: Dan Mick <dmick@redhat.com> - 11:32 PM Revision cce5810f (ceph): Merge pull request #11006 from iain-buclaw-sociomantic/pyaiostat
- python-rados: implement new aio_stat.
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:56 PM devops Bug #16169: ceph-detect-init target fails for Jewel build
- @Kefu would you mind taking a look ? There has been two dozen changes since I last modified this part of the code abo...
- 08:22 PM devops Bug #16169: ceph-detect-init target fails for Jewel build
- Hi Loic, this is still an issue and we have narrowed down to being a problem for building Jewel in a Xenial box.
N... - 09:56 PM ceph-ansible Bug #17304 (New): ceph-fuse not installed for clients on non-debian machines
- Specifically, I had this problem on CentOS 7.
- 09:39 PM CephFS Bug #17297: high cpu usage for ceph-fuse (>150%)
- Well, that function aborts if quota is disabled; it still gets called into.
Anyway I tried it locally with linux-4... - 08:09 PM CephFS Bug #17297: high cpu usage for ceph-fuse (>150%)
- Just tried to disable quotas, but https://github.com/ceph/ceph/blob/a033dc6f5b4cef357db6f5951062d680e880ba0e/src/clie...
- 07:32 PM CephFS Bug #17297: high cpu usage for ceph-fuse (>150%)
- Greg Farnum, nothing is warned/noticed regarding "slow" in OSD logs, cluster status is HEALTH_OK, but slowness someho...
- 07:28 PM CephFS Bug #17297: high cpu usage for ceph-fuse (>150%)
- ceph-fuse version:...
- 06:15 PM CephFS Bug #17297: high cpu usage for ceph-fuse (>150%)
- What version of ceph-fuse are you currently running? What config options have you set?
Do you have any evidence it... - 01:58 PM CephFS Bug #17297 (New): high cpu usage for ceph-fuse (>150%)
- Hi,
we noticed, that our CephFS deployment is very very slow. If we try to extract for instance kernel source unde... - 09:34 PM Revision 29203342 (ceph): radosgw-admin: add "--orphan-stale-secs" to --help
- The radosgw-admin --help did not include the description of the
`--orphan-stale-secs` option of the `orphans find` co... - 09:34 PM Revision 054e0d45 (ceph): Add two options to radosgw-admin.rst manpage
- Add '--job-id' and '--max-concurrent-ios' to Orphan Search Options
Fixes: http://tracker.ceph.com/issues/17281
Signe... - 09:34 PM Revision 34ecb358 (ceph): rgw_admin: improve the orphans find help
- Adding a few missing commandline switches and improve the help message
Signed-off-by: Abhishek Lekshmanan <abhishek... - 09:26 PM Revision 8328daa8 (ceph): fix test_rgw_ldap.cc for search filter
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 09:26 PM Revision 9b0cd553 (ceph): Merge branch 'ldap-auth-custom-searchfilter' of https://github.com/hakl...
- 09:21 PM Revision 22328b82 (ceph): mon/MonClient.h: remove repeated searching of map
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 09:15 PM rgw Documentation #17281: radosgw-admin(8) does not describe "--job-id" or "--max-concurrent-ios"
- backport prs opened,
jewel: https://github.com/ceph/ceph/pull/11139
hammer: https://github.com/ceph/ceph/pull/11140 - 08:21 PM rgw Documentation #17281 (Pending Backport): radosgw-admin(8) does not describe "--job-id" or "--max-...
- 07:20 PM rgw Documentation #17281 (In Progress): radosgw-admin(8) does not describe "--job-id" or "--max-concu...
- 07:18 PM rgw Documentation #17281: radosgw-admin(8) does not describe "--job-id" or "--max-concurrent-ios"
- Here's the PR: https://github.com/ceph/ceph/pull/11134
- 09:15 PM rgw Documentation #17280: radosgw-admin lacks docs for "--orphan-stale-secs"
- backport prs opened,
jewel: https://github.com/ceph/ceph/pull/11139
hammer: https://github.com/ceph/ceph/pull/11140 - 09:12 PM Revision 3f20c28f (ceph): mon/Monitor.h: add override to virtual functions
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 09:02 PM Revision 3575fa81 (ceph): doc: add "--orphan-stale-secs" to radosgw-admin(8)
- The radosgw-admin(8) manual page did not include the description of the
`--orphan-stale-secs` option of the `orphans ... - 08:58 PM Revision 132f3027 (ceph): mon/HealthMonitor: remove unneeded include
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 08:48 PM Revision bfa90a15 (ceph): doc: add "--orphan-stale-secs" to radosgw-admin(8)
- The radosgw-admin(8) manual page did not include the description of the
`--orphan-stale-secs` option of the `orphans ... - 08:48 PM Revision 4e66f9e9 (ceph): radosgw-admin: add "--orphan-stale-secs" to --help
- The radosgw-admin --help did not include the description of the
`--orphan-stale-secs` option of the `orphans find` co... - 08:48 PM Revision e2ce8576 (ceph): Add two options to radosgw-admin.rst manpage
- Add '--job-id' and '--max-concurrent-ios' to Orphan Search Options
Fixes: http://tracker.ceph.com/issues/17281
Signe... - 08:19 PM Revision b606ab1f (ceph): Merge pull request #11134 from tserlin/wip-tserlin-fix-radosgw-admin-ma...
- Add two options to radosgw-admin.rst manpage
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 07:32 PM CephFS Bug #17236 (Fix Under Review): MDS goes damaged on blacklist (failed to read JournalPointer: -108...
- https://github.com/ceph/ceph/pull/11138
- 07:31 PM Revision 5ba61288 (ceph): mds: use a random nonce in Messenger
- The MDS is a client to the OSDs, and responds
to blacklists by respawning itself. Usually
respawns of a daemonized p... - 07:31 PM Revision 19bb8c0d (ceph): mds: handle blacklisting during journal recovery
- EBLACKLISTED was being incorrectly handled as an
indication of metadata damage.
Fixes: http://tracker.ceph.com/issue... - 07:31 PM CephFS Bug #17173 (Fix Under Review): Duplicate damage table entries
- https://github.com/ceph/ceph/pull/11137
- 07:29 PM CephFS Feature #16016 (Fix Under Review): Populate DamageTable from forward scrub
- https://github.com/ceph/ceph/pull/11136
- 07:28 PM Revision 697f30d8 (ceph): Add two options to radosgw-admin.rst manpage
- Add '--job-id' and '--max-concurrent-ios' to Orphan Search Options
Fixes: http://tracker.ceph.com/issues/17281
Signe... - 07:26 PM rgw Bug #17256 (Pending Backport): objects in the metadata_heap pool are created, but never read or r...
- 07:25 PM Revision 96fde20b (ceph): Merge pull request #11051 from prallabh/wip-17256
- rgw: Do not archive metadata by default
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 07:20 PM Revision 436b7a66 (ceph): client: reinstate clearing of *fhp in ll_create and don't allow fhp == ...
- The logic in ll_create relies on *fhp being zeroed out on entry into the
function, but that's no longer being done si... - 06:59 PM Documentation #17302 (Closed): Undocumented options for rados command
- Some of the options for the rados cli tool are not properly documented. For example, "--id" is a valid option that is...
- 06:30 PM rgw Bug #17167 (Pending Backport): teuthology: assertion failure in a radosgw-admin related task
- 04:01 PM rgw Bug #17167 (In Progress): teuthology: assertion failure in a radosgw-admin related task
- 06:29 PM Revision 2515113c (ceph): Merge pull request #11132 from ceph/wip-17167
- rgw: fix decoding of creation_time and last_update.
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:12 PM rbd Bug #17301 (Won't Fix): helgrind: async messenger race condition warnings
- 05:35 PM rbd Bug #17300 (Won't Fix): helgrind: boost intrusive_set data race with non-constant time size
- 05:34 PM rbd Bug #17299 (Won't Fix): helgrind: async messenger fails to destruct spin lock
- 05:28 PM rbd Bug #14846 (Closed): teuthology: helgrind warnings
- Will track and fix as individual tracker tickets as helgrind warnings are always a moving target.
- 05:27 PM Bug #16025 (Resolved): unittest_chain_xattr failure in 'make check' bot
- 04:00 PM Revision 3afe7153 (ceph): rgw: fix decoding of creation_time and last_update.
- Fixes: http://tracker.ceph.com/issues/17167
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 03:52 PM Revision bf613881 (ceph): Merge pull request #11115 from petermaloney/peter-mds-docs3
- doc: manual instructions to set up mds daemon
Reviewed-by: John Wilkins<jowilkin@redhat.com> - 02:25 PM rgw Feature #17298 (New): rgw: partial mesh
- Provide a way to have a partial mesh architecture within a single zone-group.
- 02:21 PM Revision c9cfaef1 (ceph): mds: catch duplicates in DamageTable
- There was an implicit assumption in the code that callers
wouldn't hit the notify_*damaged paths twice because they w... - 12:40 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- sure. I am singler at OFTC #ceph
- 12:34 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- this is strange, could you do some interactive debug (through xchat)
- 12:32 PM rbd Bug #17296 (Closed): [teuthology] failure in cli-integration/rbd/formatted-output.t
- ...
- 12:31 PM Revision 22053d05 (ceph): Merge pull request #11063 from ceph/wip-doc-BZ#1368528
- Removed reference about pool ownership based on BZ#1368528
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:23 PM Revision c3ea9351 (ceph): os/bluestore: simplify marking unused logic of blob tail
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 11:36 AM Feature #16091 (Fix Under Review): Monclient: hunt for mons in parallel
- https://github.com/ceph/ceph/pull/11128
- 11:20 AM Revision 40b277b2 (ceph): Merge pull request #11104 from dillaman/wip-17283
- rbd-mirror: concurrent access of event might result in heap corruption
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 11:04 AM rgw Feature #8221 (Resolved): rgw: object versioning swift support
- Merged:
commit:e4e9c2c02194d3578f46edaeeacec7e836f16b4b -- initial support
commit:7554ef048d4d3613477a1facc390e187b... - 10:55 AM rgw Feature #17295: rgw: indexless buckets
- Merged in commit:155a53d649b0d611781488ffd515eb76b1913e7d.
- 10:55 AM rgw Feature #17295 (Resolved): rgw: indexless buckets
- 10:55 AM Bug #17288 (Resolved): ceph-deploy auth get client.admin fails in master branch
- I stand corrected! Patrick has posted a fix here: https://github.com/ceph/ceph/pull/11123 and I've merged it
- 10:47 AM Bug #17288: ceph-deploy auth get client.admin fails in master branch
- No, that PR was not a behavioural change outside of the case it fixed.
- 10:54 AM Revision db51b328 (ceph): Merge pull request #11123 from batrick/ceph-create-keys-bugfix
- ceph-create-keys: add missing argument comma
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: John Spray <john... - 10:45 AM Revision 440c360d (ceph): Merge pull request #10815 from ceph/wip-qa-workunits-py3
- Python 3 compatibility for workunits
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:59 AM Revision 179d3d16 (ceph): mon: OSDMonitor: fix the check error of pg creating
- The variable 'pgs_per_osd' set value from 'new_pgs' divided by 'expected_osds',
and its type is integer. So it would ... - 09:43 AM Bug #17169 (Fix Under Review): Wrong check of the limitation of creating PGs
- https://github.com/ceph/ceph/pull/10916
- 05:59 AM Bug #17169: Wrong check of the limitation of creating PGs
- Hi hung jun,
There have some misunderstanding.
In a cluster which have 3 OSDs, it could create new 96(32*3) pgs... - 08:38 AM Revision 1713a547 (ceph): os/bluestore: exercise handle when trying to get through throttlers
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 08:26 AM CephFS Bug #17294 (New): mds client didn't update directory content after short network break
- Client: ceph-fuse 0.8.5, 10.2.2
Server: ceph 10.2.1, single active mds
Sympton:
1. mount same cephfs on 2 nodes ... - 08:20 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- Hi john,I have been using the patch ceph-fuse(http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ref/wip-17270)...
- 06:36 AM Revision bd9695d5 (ceph): doc: Radosgw multitenancy config paramater change
- Radosgw multitenancy configuration parameter
"rgw keystone make new tenants" never works even
applied. When gone thro... - 05:39 AM rgw Bug #17293 (Fix Under Review): Config parameter "rgw keystone make new tenants" in radosgw multit...
- https://github.com/ceph/ceph/pull/11127
- 05:13 AM rgw Bug #17293 (Resolved): Config parameter "rgw keystone make new tenants" in radosgw multitenancy d...
- Radosgw multitenancy configuration parameter "rgw keystone make new tenants" never works even applied. When gone thro...
- 03:55 AM Backport #17292 (In Progress): jewel: add a tool to rebuild mon store from OSD
- https://github.com/ceph/ceph/pull/11126
- 03:52 AM Backport #17292 (Resolved): jewel: add a tool to rebuild mon store from OSD
- https://github.com/ceph/ceph/pull/11126
- 03:35 AM Backport #17291 (In Progress): hammer: add a tool to rebuild mon store from OSD
- https://github.com/ceph/ceph/pull/11125
- 03:34 AM Backport #17291 (Resolved): hammer: add a tool to rebuild mon store from OSD
- https://github.com/ceph/ceph/pull/11125
- 02:28 AM Revision fbca0137 (ceph): os/bluestore: confirm buffer is empty before moving it into AOUT queue
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:24 AM Revision 9b748eaf (ceph): os/bluestore: avoid reset cache_private if we haven't to
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:21 AM Revision b2f6bd11 (ceph): rgw: remove a redundant judgement in rgw_rados.cc:delete_obj.The value of
- the 'removed' is just the same as 'r>=0'. We can merge the two
judgement and remove the var 'removed'.
Signed-off-by... - 02:17 AM Revision 55852f75 (ceph): Merge pull request #11100 from bassamtabbara/rocksdb-build-improvements
- cmake: enable ccache for rocksdb too
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:15 AM Revision c79ca73d (ceph): Merge pull request #11105 from badone/wip-dnf-enable-build-scripts
- build scripts: Enable dnf for Fedora >= 22
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:57 AM Revision 229c60a2 (ceph): Merge pull request #11111 from bassamtabbara/wip-tcmalloc-minimal
- cmake: Support tcmalloc_minimal allocator
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:31 AM Revision 388b7e23 (ceph): os/bluestore: fix sanity check of object key length
- We now encode shard-id into exactly one byte.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 12:50 AM Revision c170616d (ceph): mds/server: clean up handle_client_open()
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
09/18/2016
- 11:49 PM Revision 354fbf53 (ceph): Merge pull request #11109 from dmick/master
- unittest_chain_xattr: account for existing xattrs
Reviewed-by: Sage Weil <sage@redhat.com> - 10:57 PM Revision d8e4443a (ceph): Merge pull request #9569 from stiopaa1/osdc_objectCacher_const
- osdc/ObjectCacher.h: add const to member functions
Reviewed-by: Sage Weil <sage@redhat.com> - 10:56 PM Revision be082882 (ceph): Merge pull request #9701 from stiopaa1/osd_removeUnneededReturn
- OSD.cc: remove unneeded return
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 10:55 PM Revision c395a1d0 (ceph): Merge pull request #9932 from stiopaa1/test_simple_dispatcher_removeUnu...
- test/simple_dispatcher.cc: remove unused variable
Reviewed-by: Sage Weil <sage@redhat.com> - 10:54 PM Revision aa0c1b3b (ceph): Merge pull request #10071 from stiopaa1/compatset_removeUnneededInline_mc
- CompatSet.h: remove unneeded inline
Reviewed-by: Sage Weil <sage@redhat.com> - 10:52 PM Revision b75a51a6 (ceph): Merge pull request #10503 from stiopaa1/msg_queuestrategy_addOverrideNew
- msg/QueueStrategy: add override to virtual functs
Reviewed-by: Sage Weil <sage@redhat.com> - 10:51 PM Revision 10461fb2 (ceph): Merge pull request #10575 from stiopaa1/mon_osdmonitor_removeUnneededCasts
- mon/OSDMonitor.cc: remove unneeded casts
Reviewed-by: Sage Weil <sage@redhat.com> - 10:46 PM Revision 673146aa (ceph): Merge pull request #10599 from stiopaa1/mon_monclient_deleteCopyConstrA...
- mon/MonClient.h: delete copy constr and assing op
Reviewed-by: Sage Weil <sage@redhat.com> - 10:45 PM Revision f8be35bf (ceph): Merge pull request #10618 from stiopaa1/mon_configkeyservice_passString...
- mon/ConfigKeyService: pass strings by const ref
Reviewed-by: Sage Weil <sage@redhat.com> - 10:44 PM Revision 2c629767 (ceph): Merge pull request #10639 from stiopaa1/common_trackedop_moveShardedTra...
- common/TrackedOp: move ShardedTrackingData to .cc
Reviewed-by: Sage Weil <sage@redhat.com> - 10:44 PM Revision 50e6eb8e (ceph): Merge pull request #10721 from stiopaa1/mon_logmonitor_moveCLogStruct
- mon/LogMonitor: move C_Log struct to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 10:43 PM Revision cc56a5fc (ceph): Merge pull request #10549 from stiopaa1/mon_healthmonitor_addOverride
- mon/HealthMonitor: add override to virtual functs
Reviewed-by: Sage Weil <sage@redhat.com> - 10:43 PM Revision 1842b85c (ceph): Merge pull request #10529 from stiopaa1/mon_paxosservice_moveClassesTocc
- mon/PaxosService: move classes to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 10:42 PM Revision c01cb28e (ceph): Merge pull request #10422 from stiopaa1/msg_accepter_addOverride
- msg/Accepter.h: add override to virtual function
Reviewed-by: Sage Weil <sage@redhat.com> - 10:42 PM Revision 16d20364 (ceph): Merge pull request #10416 from stiopaa1/mon_elector_moveCElectionExpire
- mon/Elector:move C_ElectionExpire class to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 10:40 PM Revision 3a6ea901 (ceph): Merge pull request #10383 from stiopaa1/mon_monclient_moveCTickClass
- mon/MonClient: move C_Tick struct to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 10:39 PM Revision a5b5ff56 (ceph): Merge pull request #10441 from stiopaa1/msg_accepter_moveIncludeToCC
- msg/Accepter: move include to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 10:39 PM Revision 25c432d7 (ceph): Merge pull request #10513 from stiopaa1/mon_monitor_moveCScrubCScrubTim...
- mon/Monitor: move C_Scrub, C_ScrubTimeout to .cc
Reviewed-by: Sage Weil <sage@redhat.com> - 10:38 PM Revision 882b9eb1 (ceph): Merge pull request #10482 from stiopaa1/msg_faststrategy_addOverride
- msg/FastStrategy.h: add override to virtual funct
Reviewed-by: Sage Weil <sage@redhat.com> - 10:37 PM Revision e9e918fc (ceph): osd/OSD.h: move some members under private
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 10:37 PM Revision 3733d767 (ceph): Merge pull request #10605 from stiopaa1/mon_monclient_passStringsByRef
- mon/MonClient.h: pass strings by const reference
Reviewed-by: Sage Weil <sage@redhat.com> - 10:36 PM Revision e61fb0b9 (ceph): Merge pull request #10734 from stiopaa1/osdc_objecter_moveRequestStatHook
- osdc/Objecter: move RequestStateHook class to .cc
Reviewed-by: Sage Weil <sage@redhat.com> - 10:36 PM Revision 8be78cc2 (ceph): Merge pull request #10833 from stiopaa1/os_memstore_moveBufferlistObject
- os/MemStore: move BufferlistObject to .cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 10:34 PM Revision f8d9bd9f (ceph): Merge pull request #11099 from stiopaa1/osd_osd_finalInitInitializeVar
- osd/OSD.cc: initialise variable at definition
- 10:34 PM Revision bc04d4ee (ceph): Merge pull request #11114 from stiopaa1/osd_osd_addConsts
- osd/OSD.h: add const to member functions
Reviewed-by: Sage Weil <sage@redhat.com> - 08:28 PM Revision 48202223 (ceph): ceph-create-keys: add missing argument comma
- The arguments "get" and "client.admin" were being concatenated into
"getclient.admin".
Found using ceph-ansible + st... - 05:16 PM Revision 43e9c260 (ceph): Support tcmalloc_minimal allocator
- Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com>
- 05:15 PM Revision 8811696c (ceph): enable ccache for rocksdb too
- Signed-off-by: Bassam Tabbara <bassam.tabbara@quantum.com>
- 02:38 PM rbd Backport #17290 (New): jewel: ImageWatcher: use after free within C_UnwatchAndFlush
- 02:37 PM rbd Backport #17290 (Duplicate): jewel: ImageWatcher: use after free within C_UnwatchAndFlush
- 02:36 PM rbd Backport #17290 (Resolved): jewel: ImageWatcher: use after free within C_UnwatchAndFlush
- https://github.com/ceph/ceph/pull/11466
- 05:50 AM Revision ce4c801c (ceph): rbd: return error if we specified a wrong image name for rbd du
- Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
- 05:05 AM Revision e1667dca (ceph): Merge pull request #11117 from xiexingguo/xxg-wip-mon-0918
- tools/rebuild_mondb: kill comipling warning and other fixes
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:34 AM Feature #17179 (Pending Backport): add a tool to rebuild mon store from OSD
- i will do the backport.
- 03:42 AM Revision f16a3147 (ceph): tools/rebuild_mondb: kill compiling warning
- As follow:
[ 72%] Building CXX object src/tools/CMakeFiles/ceph-objectstore-tool.dir/RadosDump.cc.o
/home/jenkins-bu... - 03:42 AM Revision a6cf4a45 (ceph): tools/ceph_objectstore_tool: set error code if path of mon-db does not ...
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:42 AM Revision ac7c1dca (ceph): tools/rebuild_mondb: return error if ondisk version of pg_info is incom...
- In this case "r" will be >= 0 and caller will be able to catch
this kind of error.
Signed-off-by: xie xingguo <xie.x... - 03:42 AM Revision 6a1c01d3 (ceph): tools/rebuild_mondb: avoid unnecessary result code cast
- In general we return negative codes for error cases, so there is
no need perform the cast here.
Signed-off-by: xie x...
09/17/2016
- 10:14 PM Revision b338a490 (ceph): run-cmake-check.sh: Remove redundant calls
- Calling "git submodule init" is redundant since it is called in do_cmake.sh and
there's no reason to do a modprobe of... - 10:10 PM Revision 9bb43350 (ceph): compressor/zlib: switch to raw deflate
- By using raw deflate instead of default zlib deflate, we're
saving 6 bytes on each compression stream and some CPU ti... - 09:38 PM Revision a32a1670 (ceph): tetst/compression_zlib: add simple benchmark
- Simple benchmark testing performance of 1024, 2048, 4096, 8192 and
16384 byte block compression and decompression.
S... - 08:29 PM Revision 9fd92a5e (ceph): doc: manual instructions to set up mds daemon
- Signed-off-by: Peter Maloney <peter.maloney@brockmann-consult.de>
- 03:48 PM Revision a033dc6f (ceph): Merge pull request #8558 from branch-predictor/bp-mark-down-on-perm-rst
- msg: mark daemons down on RST + ECONNREFUSED
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Gregory Farnum <g... - 03:45 PM Revision e9a6f4ed (ceph): Merge pull request #11050 from xiexingguo/xxg-wip-os-0912
- os/ObjectStore: fix return code of collection_empty() method
Reviewed-by: Sage Weil <sage@redhat.com> - 03:21 PM Bug #16266 (Pending Backport): Ceph Status - Segmentation Fault
- 02:16 AM Bug #16266: Ceph Status - Segmentation Fault
- Ugh, I just found this bug in my testing with ceph-ansible on v10.2.2. Can we get this backported to jewel?
- 02:22 PM rbd Bug #17289 (Pending Backport): ImageWatcher: use after free within C_UnwatchAndFlush
- 12:32 PM rbd Bug #17289 (Fix Under Review): ImageWatcher: use after free within C_UnwatchAndFlush
- *PR*: https://github.com/ceph/ceph/pull/11112
- 12:29 PM rbd Bug #17289 (Resolved): ImageWatcher: use after free within C_UnwatchAndFlush
- 02:21 PM Revision 3985ee2b (ceph): Merge pull request #11112 from dillaman/wip-17289
- librbd: corrected use-after-free in ImageWatcher
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 02:07 PM Revision b2452e2f (ceph): osd/OSD.h: add const to member functions
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 01:29 PM Revision affccb1a (ceph): Merge pull request #1169 from ceph/wip-kefu-17179
- tasks: add rebuild_mondb
Reviewed-by: Samuel Just <sjust@redhat.com> - 01:29 PM Revision 19acda71 (ceph): Merge pull request #10933 from tchaikov/wip-rebuild-monstore
- tools: rebuild monstore
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Re... - 12:29 PM Revision 2f4d4868 (ceph): librbd: corrected use-after-free in ImageWatcher
- Fixes: http://tracker.ceph.com/issues/17289
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
09/16/2016
- 10:41 PM Bug #16025: unittest_chain_xattr failure in 'make check' bot
- https://github.com/ceph/ceph/pull/11109
- 10:14 PM Bug #16025: unittest_chain_xattr failure in 'make check' bot
- (relatedly: how has this been here for 4 months at High priority? Are we doing bug scrubs?)
- 10:03 PM Bug #16025: unittest_chain_xattr failure in 'make check' bot
- It's true, files have a security.selinux attr under selinux and don't without. The test could get the current number...
- 09:44 PM Bug #16025: unittest_chain_xattr failure in 'make check' bot
- Seems like the test might be being confused by extra security.selinux xattrs
- 10:39 PM Revision 6d3dbe2a (ceph): unittest_chain_xattr: account for existing xattrs
- On CentOS with selinux enabled, files always have an
xattr 'security.selinux'. Account for that when adding/
removin... - 09:45 PM Revision 6e58ed90 (ceph): os/bluestore/BlueFS: log dirty files at sync time
- Instead of logging an updated fnode every time we dirty
the metadata, log it only once, right before we flush.
This g... - 09:27 PM Revision d5a9d0ee (ceph): Merge pull request #11107 from stiopaa1/msg_stack_deletecopyAssign
- msg/Stack.h: delete copy constr and assign op
- 08:38 PM Bug #17288: ceph-deploy auth get client.admin fails in master branch
- John,
Is there anything that needs to be handled in ceph-deploy for this pr https://github.com/ceph/ceph/pull/1041... - 08:32 PM Bug #17288 (Resolved): ceph-deploy auth get client.admin fails in master branch
- ceph-deploy seems to be broken for master branch...
- 08:26 PM rgw Documentation #17281: radosgw-admin(8) does not describe "--job-id" or "--max-concurrent-ios"
- Backporting note: #17280 and #17281 could be backported together.
- 07:47 PM rgw Documentation #17281: radosgw-admin(8) does not describe "--job-id" or "--max-concurrent-ios"
- whoops, thanks Nathan
- 06:52 PM rgw Documentation #17281: radosgw-admin(8) does not describe "--job-id" or "--max-concurrent-ios"
- @Ken: backport field empty?
- 07:34 PM Bug #13897: (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED assert(r == 0)
- The crash is *not* reproducible in Sepia:...
- 07:00 PM Bug #13897: (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED assert(r == 0)
- Reproduced in OVH again with the command:...
- 06:24 PM rbd Bug #17202 (In Progress): helgrind: lock order warning within AioCompletion
- 05:52 PM rgw Bug #13207: CVE-2016-7031 rgw: Anonymous user is able to read bucket with authenticated read ACL
- RH Security team has assigned CVE-2016-7031 to this issue.
- 05:43 PM Revision ac584940 (ceph): msg/Stack.h: delete copy constr and assign op
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 04:29 PM rgw Documentation #17280: radosgw-admin lacks docs for "--orphan-stale-secs"
- @Nathan: That's right!
There's *also* another upcoming change for the radosgw-admin.rst man page in the same gener... - 10:21 AM rgw Documentation #17280 (Pending Backport): radosgw-admin lacks docs for "--orphan-stale-secs"
- @Ken, should both PRs be backported, then?
- 04:18 PM Revision fb13a8ea (ceph): Merge pull request #11106 from liewegas/wip-bluestore-clone-range
- os/bluestore: make clone_range copy-on-write
- 03:56 PM Revision 8bf14af6 (ceph): Merge pull request #11101 from andihit/master
- doc: fix description for rsize and rasize
Reviewed-by: Ilya Dryomov <idryomov@gmail.com> - 03:26 PM Revision 8372b966 (ceph): Merge pull request #10267 from cbodley/wip-fio-objectstore
- fio engine for objectstore
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Reviewed-by: Samuel Just <sjust@redhat.... - 03:15 PM Revision 71a40cfd (ceph): os/bluestore: CLONE implicitly creates the target
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:15 PM Revision 78f0176f (ceph): os/bluestore: factor _do_clone_range out of _clone
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:15 PM Revision a931dd3e (ceph): os/bluestore: add cow clone_range via _do_clone_range
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:15 PM Revision e9407a37 (ceph): os/bluestore: do not dup Blob::id in dup()
- This field is local to a particular onode!
Signed-off-by: Sage Weil <sage@redhat.com> - 03:15 PM Revision 5a7b00b1 (ceph): os/bluestore: EINVAL bad clone_range args
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:43 PM Revision f51a6552 (ceph): Merge pull request #1136 from ceph/wip-16129
- rgw: add sleep to let the sync agent init
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:31 PM rgw Bug #16632 (Resolved): radosgw-admin zone modify --master --rgw-zone=default fails because of no ...
- 02:30 PM rgw Bug #16624 (Rejected): register the correct handler for cls_user_complete_stats
- 02:30 PM rgw Feature #11407 (Resolved): rgw: create a skeleton ganesha FSAL for rgw
- 02:30 PM rgw Feature #11408 (Resolved): rgw: implement initial API to use with ganesha
- 02:29 PM rgw Feature #11138 (Resolved): rgw: export data via nfs
- 02:29 PM rgw Feature #11933 (Resolved): rgw: create realm and period data structures
- 02:28 PM rgw Bug #15087 (Resolved): rgw zone set failure --log-to-stderr --format json -n client.1 -n client.1...
- 02:28 PM rgw Bug #15091 (Resolved): Exception during orig_placement_pools = len(out['placement_pools'])
- 02:27 PM rgw Bug #15195 (Pending Backport): rgw:response information is error when geting token of swift account
- 02:26 PM rgw Bug #16129 (Fix Under Review): HTTPConnectionPool(host='mira101.front.sepia.ceph.com', port=8000)...
- https://github.com/ceph/ceph-qa-suite/pull/1136
- 02:24 PM rgw Bug #17090 (Resolved): rgw: swift api return ``204 No Content`` when update metadata for an accou...
- 02:22 PM Revision 2b67c48c (ceph): Merge pull request #10841 from fiskn/master
- udev: add krbd readahead placeholder
Reviewed-by: Ilya Dryomov <idryomov@gmail.com> - 02:17 PM rgw Bug #16357: radosgw stats error
- I tried on latest master and cannot reproduce (I used s3cmd)
- 02:13 PM rbd Bug #16974 (Fix Under Review): rbd-mirror: force-promoted image will remain R/O until local rbd-m...
- *PR*: https://github.com/ceph/ceph/pull/11090#issuecomment-247567977
- 01:56 PM Revision 11c9039d (ceph): Merge pull request #11075 from badone/wip-run-cmake-check-ctest
- run-cmake-check.sh: Actually run the tests
- 01:54 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- {
"ops": [],
"linger_ops": [],
"pool_ops": [],
"pool_stat_ops": [],
"statfs_ops": [],
"... - 01:50 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- ...
- 06:56 AM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- it seems there is a blocked write in client.2816210. could you use gdb to attach that ceph-fuse, the run "thread appl...
- 01:45 PM rgw Bug #15445: multisite s3tests test_versioning_obj_create_versions_remove_special_names causes rad...
- We cannot remove the bucket instance on a syncing zone.
Log trimming should fix it. - 01:44 PM rgw Bug #15868 (Pending Backport): rgw: versioned object is still listed in bucket index after removal
- 01:43 PM rgw Bug #15868: rgw: versioned object is still listed in bucket index after removal
- fixed in master: https://github.com/ceph/ceph/pull/8597
- 01:42 PM rgw Bug #15868 (In Progress): rgw: versioned object is still listed in bucket index after removal
- 01:40 PM rgw Bug #15868 (Duplicate): rgw: versioned object is still listed in bucket index after removal
- duplicate of http://tracker.ceph.com/issues/15445
- 01:43 PM Revision 781ae3bb (ceph): udev: add krbd readahead placeholder
- Signed-off-by: Nick Fisk <nick@fisk.me.uk>
- 01:32 PM Revision 8ee372a5 (ceph): Merge pull request #10687 from rzarzynski/wip-rgw-is_admin-fix
- rgw: fix is_admin handling in RGWLDAPAuthEngine and introduce acct_privilege_t
Reviewed-by: Orit Wasserman <owasserm@... - 12:34 PM Bug #17213: As the cluster is filling up, write performance decreases
- This is the script we are using:...
- 12:20 PM Revision a5e5119b (ceph): test: timeout verification that mon is unreachable
- Without a timeout on the command, it may hang for a very long time,
hunting for new mons. If it hangs for more than 6... - 09:51 AM CephFS Backport #17285 (In Progress): ceph-mon leaks in MDSMonitor when ceph-mds process is running but ...
- https://github.com/ceph/ceph/pull/10238
- 09:51 AM CephFS Backport #17285: ceph-mon leaks in MDSMonitor when ceph-mds process is running but MDS is not con...
- h3. original description
Memory is leaking every time when you see in monitor log:
@mon.0@0(leader).mds e1 warn... - 07:38 AM CephFS Backport #17285: ceph-mon leaks in MDSMonitor when ceph-mds process is running but MDS is not con...
- PR https://github.com/ceph/ceph/pull/10238 is fixing this leak at hammer branch. After v10.0.5 there was massive MDSM...
- 07:33 AM CephFS Backport #17285 (Resolved): ceph-mon leaks in MDSMonitor when ceph-mds process is running but MDS...
- https://github.com/ceph/ceph/pull/10238
- 09:19 AM CephFS Bug #17286 (Resolved): Failure in dirfrag.sh
So, we've been running with dirfrags off for ages because we weren't setting the flag to allow it:
https://github....- 08:59 AM Revision 07a5a989 (ceph): build scripts: Enable dnf for Fedora >= 22
- The use of yum triggers a warning and reference to yum2dnf on Fedora >= 22.
Use either yum or dnf based on the Fedora... - 08:39 AM rgw Bug #17076: AWS S3 Version 4 signatures fail sometimes.
- I'm using s3cmd 1.6.1 (as it comes in Xenial). As server I have 10.2.2, both installed initially as Jewel and upgrade...
- 07:24 AM Revision 0029f997 (ceph): Merge pull request #11102 from ceph/wip-17279
- rgw: revert a commit that broke s3 signature validation
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 07:14 AM CephFS Bug #17284 (New): Bogus "unmatched fragstat", "unmatched rstat" after missing dirfrag object
- Ideally we should not spit out these mismatch messages, because they're just pointing out that the empty dirfrag (aft...
- 07:04 AM Revision d5a3c8d6 (ceph): cli: retry when the mon is not configured
- The mon may return on error if a command is sent to it while it is
still in configuring state.
Fixes: http://tracker... - 07:01 AM Bug #17180: Osd restarts intermittently while running ceph FS IO
- OSD logs:-
6-09-16 11:41:38.708334 7f9e52e24700 -1 osd.19 5702 heartbeat_check: no reply from osd.12 since back 20... - 04:47 AM Revision c511ba30 (ceph): run-cmake-check.sh: Actually run the tests
- Actually run the tests from run-cmake-check.sh
Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
09/15/2016
- 10:38 PM rbd Bug #17283 (Fix Under Review): rbd-mirror: potential race condition results in heap corruption
- *PR*: https://github.com/ceph/ceph/pull/11104
- 10:14 PM rbd Bug #17283 (Resolved): rbd-mirror: potential race condition results in heap corruption
- Changes introduced in commit 4df913d1 might result in concurrent writes to rbd::mirror::ImageReplayer::m_event_entry.
- 10:14 PM Revision ac9ad37a (ceph): rbd-mirror: concurrent access of event might result in heap corruption
- Fixes: http://tracker.ceph.com/issues/17283
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 09:02 PM Revision 80ecae21 (ceph): rgw: switch to boost::algorithm::equals in RGWSwiftWebsiteHandler.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 08:40 PM Revision 36d2d8a7 (ceph): librbd: Extract Group module from librbd/internal
- Signed-off-by: Victor Denisov <denisovenator@gmail.com>
- 08:38 PM rgw Fix #17136 (In Progress): Fix accidental logic inversion in RGW hostname fallback
- this fix leads to auth failures in teuthology. need to find a more complete solution
- 08:25 PM Revision b1a2e77b (ceph): Merge pull request #11098 from ktdreyer/wip-17280-help-orphan-stale-secs
- radosgw-admin: add "--orphan-stale-secs" to --help
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 08:19 PM rgw Bug #17279 (Fix Under Review): auth failures (SignatureDoesNotMatch) in teuthology runs
- https://github.com/ceph/ceph/pull/11102
- 04:48 PM rgw Bug #17279: auth failures (SignatureDoesNotMatch) in teuthology runs
- also in smoke runs
- 04:44 PM rgw Bug #17279 (Resolved): auth failures (SignatureDoesNotMatch) in teuthology runs
- running s3tests: http://pulpito.ceph.com/cbodley-2016-09-15_11:38:36-rgw-master---basic-mira/...
- 08:02 PM Revision a004254a (ceph): doc: fix description for rsize and rasize
- Signed-off-by: Andreas Gerstmayr <andreas.gerstmayr@gmail.com>
- 07:59 PM Revision b4dd18c6 (ceph): Revert "rgw: Fix Host->bucket fallback logic inversion"
- This reverts commit 0e0a4bc3dcb61c2e8dfe65daefe207c62b36306c.
this commit, while logically correct, causes us to add... - 07:49 PM Revision 354059ae (ceph): radosgw-admin: add "--orphan-stale-secs" to --help
- The radosgw-admin --help did not include the description of the
`--orphan-stale-secs` option of the `orphans find` co... - 07:06 PM rgw Documentation #17281 (Resolved): radosgw-admin(8) does not describe "--job-id" or "--max-concurre...
- @radosgw-admin -h@ shows the following options:...
- 07:05 PM Revision 02b205df (ceph): osd/OSD.cc: initialise variable at definition
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:02 PM rgw Documentation #17280: radosgw-admin lacks docs for "--orphan-stale-secs"
- @--help@ text PR for master: https://github.com/ceph/ceph/pull/11098
- 05:43 PM rgw Documentation #17280 (In Progress): radosgw-admin lacks docs for "--orphan-stale-secs"
- man page PR for master: https://github.com/ceph/ceph/pull/11097
- 05:38 PM rgw Documentation #17280 (Resolved): radosgw-admin lacks docs for "--orphan-stale-secs"
- The radosgw-admin(8) manual page does not include the description of the @--orphan-stale-secs@ option of the @orphans...
- 06:40 PM Revision fb1c5efa (ceph): Merge pull request #11097 from ktdreyer/wip-17280-doc-orphan-stale-secs
- doc: add "--orphan-stale-secs" to radosgw-admin(8)
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:19 PM CephFS Bug #16255 (Pending Backport): ceph-create-keys: sometimes blocks forever if mds "allow" is set
- https://github.com/ceph/ceph/pull/10415
- 06:19 PM Revision 5f4962d5 (ceph): Merge pull request #10415 from jcsp/wip-16255
- ceph-create-keys: fix existing-but-different case
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Alfredo Dez... - 06:18 PM Revision a4c16352 (ceph): rgw: implement HTTP redirection in Static Website of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:18 PM Revision 111dc5bc (ceph): rgw: Static Website's booleans are parsed in a case-insensitive manner.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:18 PM Revision 4a755e1c (ceph): rgw: rename get_swift_index_doc() to get_index_doc() in RGWBucketWebsit...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:18 PM Revision 46ed7ae3 (ceph): rgw: handle trailing slashes in Static Website in way compliant with Sw...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:18 PM Revision 1ef2dcf6 (ceph): rgw: select proper error page in Swift's Static Website implementation.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:18 PM Revision b7545202 (ceph): rgw: verify whether an index exists in Static Website of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:18 PM Revision c3ff3982 (ceph): rgw: share common Swift's Static Website code between bucket/object han...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 06:16 PM Revision 9dc57a80 (ceph): rgw: add support for the object-related part of Swift's Static Website.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 05:41 PM Revision a676c516 (ceph): doc: add "--orphan-stale-secs" to radosgw-admin(8)
- The radosgw-admin(8) manual page did not include the description of the
`--orphan-stale-secs` option of the `orphans ... - 04:54 PM Revision c6dc589f (ceph): Merge pull request #11095 from liewegas/wip-bluefs
- os/bluestore/BlueFS: prevent concurrent async compaction
- 04:20 PM Revision b9f714ff (ceph): os/bluestore/BlueFS: add assert for sanity/clarity
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:40 PM Revision e6058faf (ceph): Merge pull request #11096 from ifed01/wip-bluestore-compression-test-fix
- test/store_test: fix statfs results check to consider SSD min_alloc_size
Reviewed-by: Sage Weil <sage@redhat.com> - 03:37 PM Revision 455cc6ce (ceph): os/bluestore/BlueFS: prevent concurrent async compaction
- Tried to fix this in dbe23c94c0074358380a40d47a417f7999920696
but got the condition wrong (log_flushing is for
normal... - 03:33 PM Revision 6cf935b2 (ceph): test/store_test: fix statfs results check to consider SSD min_alloc_size
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:30 PM Bug #17278 (Can't reproduce): fail to start osd server with bluestore
- I have a server with 3 osd for testing bluestore as fielstore backend. Start osd.2 with error log:
-4> 2016-09... - 03:15 PM rbd Feature #16780 (Fix Under Review): rbd-mirror: use sparse read during image sync
- *PR*: https://github.com/ceph/ceph/pull/11005
- 02:35 PM Revision c1fd5ddd (ceph): Merge pull request #11081 from ifed01/wip-plugin-registry-fix
- common/PluginRegistry: improve error output for shared library load fa…
Reviewed-by: Sage Weil <sage@redhat.com> - 02:07 PM Revision d61cfb5c (ceph): Merge pull request #11092 from badone/wip-dry-run-run-make-check
- run-make-check.sh: Make DRY_RUN actually do a dry run
- 02:07 PM Revision 549fd7db (ceph): Merge pull request #11091 from badone/wip-submodule-init-run-cmake-check
- run-cmake-check.sh: Init submodules
- 01:47 PM Linux kernel client Bug #12763 (Closed): rbd: unmap failed: (16) Device or resource busy
- 01:32 PM Revision 89fb4576 (ceph): Merge pull request #11087 from liewegas/wip-bluefs-allocator
- os/bluestore/BlueFS: use StupidAllocator; fix async compaction bug
Reviewed-by: Varada Kari <varada.kari@sandisk.com> - 01:01 PM Revision c2824c5e (ceph): rgw: RGWGetObj_ObjStore_SWIFT delegates error handling.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision ea511b2a (ceph): rgw: add custom HTTP response code support to RGWGetObj of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision eca5a0ce (ceph): rgw: add support for error pages in Static Web of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision 80e050b3 (ceph): rgw: add a string-returning variant of url_encode.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision e5b0e4a3 (ceph): rgw: introduce a std::string-returning version of dump_time_header().
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision 2f299842 (ceph): rgw: unittest_formatter doesn't depend on rgw/rgw_formats.cc anymore.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision bde01d70 (ceph): rgw: add support for bucket listings for Static Website of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision e3083417 (ceph): rgw: alter data structures to accommodate Static Website of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision 2b432017 (ceph): rgw: control Swift's Static Websites through PUT/POST on container.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision 6150166d (ceph): rgw: dump Static Website headers of Swift API.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision bc74609e (ceph): rgw: add basic support for the bucket part of Swift's Static WebSite di...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision 91611ad7 (ceph): rgw: split rgw_process pipeline into two reusable parts.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 01:01 PM Revision 07a1c882 (ceph): rgw: retargeting in rgw_process_authenticated may be skipped now.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 11:25 AM Revision 84b389e8 (ceph): Merge pull request #11088 from tchaikov/do-freebsd-without-autotools
- do_freebsd*.sh: rename do_freebsd-cmake.sh to do_freebsd.sh
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl> - 10:08 AM Revision 2d5326e1 (ceph): run-make-check.sh: Make DRY_RUN actually do a dry run
- The "cd build" command will cause an error during a dry run if the directory
does not exist.
Signed-off-by: Brad Hub... - 09:57 AM CephFS Bug #16857 (Duplicate): Crash in Client::_invalidate_kernel_dcache
- 09:56 AM Revision 19ef4f16 (ceph): mon/AuthMonitor: make AuthMonitor::IncType public
- so ceph-objectstore-tool is able to use it when rebuilding monitor
db.
Fixes: http://tracker.ceph.com/issues/17179
S... - 09:56 AM Revision 24faea7c (ceph): tools/ceph-objectstore-tool: add "update-mon-db" command
- Fixes: http://tracker.ceph.com/issues/17179
Signed-off-by: Kefu Chai <kchai@redhat.com> - 09:56 AM Revision d909fa03 (ceph): tools/ceph_monstore_tool: add "rebuild" command
- Fixes: http://tracker.ceph.com/issues/17179
Signed-off-by: Kefu Chai <kchai@redhat.com> - 09:56 AM Revision 79a9f299 (ceph): doc: add rados/operations/disaster-recovery.rst
- document the process to recover from leveldb corruption.
Fixes: http://tracker.ceph.com/issues/17179
Signed-off-by: ... - 09:39 AM Revision 5c983f29 (ceph): run-cmake-check.sh: Init submodules
- If submodules are not initialised run-cmake-check.sh can fail.
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> - 09:01 AM Linux kernel client Bug #15432: kcephfs: umount -f can fail after mds reconnect failure
- Zheng - is this still an issue?
- 08:44 AM Bug #16477 (Fix Under Review): ceph cli: Rados object in state configuring race
- https://github.com/ceph/ceph/pull/11089
- 08:36 AM devops Bug #15221: ceph-0.80.11-0.el6.x86_64.rpm missing at http://download.ceph.com/rpm-firefly/el6/x86...
- Thanks!
- 08:11 AM devops Bug #15221 (Resolved): ceph-0.80.11-0.el6.x86_64.rpm missing at http://download.ceph.com/rpm-fire...
- This is now available http://download.ceph.com/rpm-firefly/el6/x86_64/ceph-0.80.11-0.el6.x86_64.rpm
- 08:26 AM CephFS Bug #17192 (Duplicate): "SELinux denials" in knfs-master-testing-basic-smithi
- 07:14 AM rgw Feature #8945 (Resolved): rgw: support swift /info api
- Merged upstream: https://github.com/ceph/ceph/pull/10280
- 06:42 AM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- Attaching.
btw as you'll probably notice, 2016-09-11-170046 directory is in another path in this dump. It was move... - 06:24 AM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- the client that causes problem is 2816210, please dump its cache
- 06:18 AM Revision e8cee252 (ceph): do_freebsd*.sh: rename do_freebsd-cmake.sh to do_freebsd.sh
- as autotools is dropped. and remove trailing spaces.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:46 AM rgw Documentation #15603 (Pending Backport): Modification for "TEST S3 ACCESS" section in "INSTALL CE...
- 05:26 AM rgw Documentation #15603: Modification for "TEST S3 ACCESS" section in "INSTALL CEPH OBJECT GATEWAY" ...
- This code got merged
https://github.com/ceph/ceph/pull/9089 - 04:43 AM Revision 371eb41b (ceph): Merge pull request #11072 from dmick/wip-17268
- ceph-disk tests: Let missing python interpreters be non-fatal
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 04:29 AM Revision 5ba26460 (ceph): Merge pull request #11076 from badone/wip-gitignore-pyc
- .gitignore: Add .pyc files globally
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:05 AM Documentation #11378 (Closed): ceph.com: http://ceph.com/resources/downloads/ needs updating
- 12:42 AM Revision 39d827c5 (ceph): Merge pull request #11042 from somnathr/wip-verbose-log
- kv/rocksdb: dump transactions on error
Reviewed-by: Sage Weil <sage@redhat.com>
09/14/2016
- 11:04 PM Revision 92c56827 (ceph): os/bluestore/StupidAllocator: use hex for debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:04 PM Revision 7c1a7848 (ceph): os/bluestore/BlueFS: do not dirty compacting log ino 0
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:04 PM Revision 3759e96f (ceph): os/bluestore/BlueFS: add safety checks on ino 0|1 op_file_update
- We only want to log updates on ino 1 in very specific
cases, and never on ino 0.
Signed-off-by: Sage Weil <sage@redh... - 11:04 PM Revision 5ef725d0 (ceph): os/bluestore/BlueFS: config option for allocator (default stupid)
- StupidAllocator is probably a more appropriate choice for bluefs.
Either way, it needn't be tied to what BlueStore is... - 09:51 PM Bug #17267 (Resolved): run-tox.sh hides errors
- 05:33 AM Bug #17267: run-tox.sh hides errors
- https://github.com/ceph/ceph/pull/11071
- 03:32 AM Bug #17267 (Fix Under Review): run-tox.sh hides errors
- 01:09 AM Bug #17267: run-tox.sh hides errors
- Argh. If it had even been "grep" as opposed to "grep -v" I would have seen this error.
As it is, I don't see any re... - 09:48 PM Revision 14c00baa (ceph): Logging proper message during read error from disk
- Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
- 09:47 PM Revision 46f1f9e5 (ceph): Logging rocksdb transaction in ceph log
- The rocksdb transaction is now been logged into ceph log based
on debug level. If transaction is failed, the error co... - 09:04 PM CephFS Feature #17276 (Resolved): stick client PID in client_metadata
- As best I can tell, we no longer provide any way for an admin to backtrack from a misbehaving client session to a spe...
- 07:48 PM Revision 9096ad37 (ceph): Merge pull request #11085 from stiopaa1/osd_osd_moveUnderPrivate
- osd/OSD.h: make some members private
- 05:39 PM Revision 6f274eca (ceph): osd/OSD.h: make some members private
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 05:38 PM Revision ca74bd9f (ceph): Merge pull request #11067 from stiopaa1/common_timer_replaceLongTypeswi...
- common/Timer.cc: replace long types with auto
- 05:30 PM Bug #17205 (Pending Backport): librados memory leaks from ceph::crypto (WITH_NSS)
- 05:29 PM Bug #17205: librados memory leaks from ceph::crypto (WITH_NSS)
- https://github.com/ceph/ceph/pull/10965
- 05:29 PM rgw Bug #16695 (Pending Backport): radosgw Consumes too much CPU time to synchronize metadata or data...
- 04:15 PM devops Bug #10374: Failed 'sudo rpm -i ceph-release-1-0.el7.noarch.rpm' in octo
- Yuri, Zack, I'm guessing this one is fixed now? (I'm resetting the priority back to normal under that assumption...)
- 04:15 PM Revision 0599b09c (ceph): common/compressor: add libcommonas a sependency for zlib and snappy plu...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 04:14 PM devops Tasks #13669: remove "rhev" packages from apt-mirror's "lab-extras"
- Zack I'm guessing this is fixed now? (I'm resetting the priority back to normal under that assumption...)
- 03:35 PM Revision 5fc0ac91 (ceph): Merge pull request #11068 from liewegas/wip-bluestore-leaks
- os/bluestore: fix a few leaks
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 03:33 PM Revision 0cf0e5f3 (ceph): os/bluestore: fix Extent leak from ~ExtentMap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:33 PM Revision 4174b42a (ceph): os/bluestore: fix SharedBlob leaks
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:33 PM Revision fa0f4110 (ceph): os/bluestore: make Cache::lock a recursive_mutex
- We need to remove items from the cache LRUs in their
destructors, and it is very awkward to ensure that all
releasing... - 03:33 PM Revision cdde7b6a (ceph): os/bluestore: clear SharedBlob cache in dtor
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:28 PM Revision 3a6b635f (ceph): common/PluginRegistry: improve error output forshared library load fail...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 02:57 PM Revision 8e69b628 (ceph): Merge pull request #11080 from ifed01/wip-compression-store-improvement
- test/store_test: extend Bluestore compression test to verify compress…
- 02:42 PM Revision 0492c232 (ceph): Merge pull request #11074 from badone/wip-dry-run
- run-*make-check.sh: Make DRY_RUN actually mean a dry run
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:36 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- as I killed that ceph-fuse, I hanged another ceph-fuse. Attaching outputs from that one
- 01:52 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- please run "dump cache", "mds_requests" and "objecter_requests" commands for client.7397637 and upload the outputs.
- 12:56 PM CephFS Bug #17275: MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- forgot to attach files... Attaching now. Also recompressed mds_cache with xz for it to go bellow 1MB (50% smaller fil...
- 12:52 PM CephFS Bug #17275 (Resolved): MDS long-time blocked ops. ceph-fuse locks up with getattr of file
- In 10.2.1 cluster we are having some blocked ceph-fuse (tested with 10.2.2) metadata accesses to files.
I cannot r... - 02:20 PM Revision 101be023 (ceph): test/store_test: extend Bluestore compression test to verify compressio...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 02:12 PM Revision 52b0689a (ceph): Merge pull request #10965 from ceph/wip-crypto-init
- common: only call crypto::init once per CephContext
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 02:10 PM Revision 0d414cea (ceph): os/bluestore: fix Extent leak on ExtentMap removal
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:10 PM Revision 3ae6929b (ceph): os/bluestore: fix Extent leak from _wctx_finish
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:10 PM Revision 32737575 (ceph): os/bluestore: add ExtentMap::add() helper
- Matches rm().
Signed-off-by: Sage Weil <sage@redhat.com> - 01:53 PM Revision c2ac1991 (ceph): Merge pull request #10998 from ceph/wip-16695
- rgw: work around curl_multi_wait bug with non-blocking reads
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 01:42 PM Revision 0f9c4345 (ceph): Merge pull request #11069 from liewegas/wip-rocksdb
- rocksdb: pull up to master (4.12 + a few patches)
- 01:41 PM Revision dd78904d (ceph): Merge pull request #11079 from ifed01/wip-fix-zlib
- compressor/zlib: zlib wrapper fix
Reviewed-by: Sage Weil <sage@redhat.com> - 01:40 PM Revision 4fa981fa (ceph): Merge pull request #11077 from xiexingguo/xxg-wip-bluestore-0914
- os/bluestore: add checks and kill unreachable code
Reviewed-by: Sage Weil <sage@redhat.com> - 01:39 PM Revision d3dac2a2 (ceph): Merge pull request #11014 from chhabaramesh/extent_alloc
- os/bluestore: make assert conditional with macro for allocator
Reviewed-by: Sage Weil <sage@redhat.com> - 12:48 PM Revision d113f0d4 (ceph): compressor/zlis: improve buffer allocation to avoid space waste
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 12:25 PM Revision d7b04ca9 (ceph): common/compressor: fix improper length value passed to zlib compressor
- Signed-off-by: Igor Fedotov <ifedotovo@miranitis.com>
- 12:24 PM Revision bd8efd83 (ceph): test/objectstore: extend compression test case to use both snappy & zlib
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:55 AM Revision 754887b5 (ceph): mon: OSDMonitor: Missing nearfull flag set
- Output from 'ceph -s -f json-pretty' wans't showing nearfull flag set.
Signed-off-by: Igor Podoski <igor.podoski@ts.... - 11:33 AM Revision 7e71cd2c (ceph): Remove dependency on sdparm/hdparm
- The code requiring a dependency on hdparm has been removed so we can remove it
as a dependency.
Signed-off-by: Brad ... - 10:36 AM CephFS Bug #17271 (Fix Under Review): Failure in snaptest-git-ceph.sh
- https://github.com/ceph/ceph/pull/11078
- 09:51 AM Revision 53660d1c (ceph): FileJournal: Remove obsolete _check_disk_write_cache function
- _check_disk_write_cache issues a warning about a bug that existed in the linux
kernel prior to version 2.6.33. This c... - 09:35 AM Revision fd6513c0 (ceph): .gitignore: Add .pyc files globally
- Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
- 09:05 AM devops Bug #17214 (Can't reproduce): SUSE build fails when cephfs_java is turned on
- 08:42 AM Linux kernel client Bug #17191: kclient accesses "/" when mounting a subpath
- Fixed by:
https://github.com/ceph/ceph-client/commit/fc8e8b4abf4eb96e08c38c200c56c81a71c558e1
https://github.com/... - 08:32 AM Revision 0a5d8946 (ceph): Merge pull request #11071 from dmick/wip-17267
- Stop hiding errors from run-tox.sh
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 08:24 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- I have tested the built ceph-fuse(ceph-fuse-10.2.2-2.g666cfe6.x86_64.rpm) in my environment(with osd-0.94.3). It work...
- 05:16 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- I will test your built ceph-fuse with OSD (0.94.3) later.
- 04:13 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- But you originally were running ceph-fuse-10.2.2-0.el7.centos.x86_64 so the osdc part was always jewel.
It's possi... - 02:10 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- I have tried all Jewel packages and it runs correctly and I think the problem is in osdc at ceph-0.94-3.
There mus... - 08:07 AM devops Bug #14604: ceph-0.80.11.tar.bz2 missing at http://download.ceph.com/tarballs/
- Any chance of checking another 0.80.11 package/build issue http://tracker.ceph.com/issues/15221 (ceph-0.80.11-0.el6.x...
- 07:20 AM devops Bug #14604 (Resolved): ceph-0.80.11.tar.bz2 missing at http://download.ceph.com/tarballs/
- Tarball is now available.
http://download.ceph.com/tarballs/ceph-0.80.11.tar.bz2
Nathan/Loic, feel free to assi... - 07:55 AM Bug #17228: Hammer OSD memory use very high (EL6)
- Thanks for the suggestions.
1. Replacing tcmalloc with jemalloc did not reduce memory consumption.
NB We also ... - 01:09 AM Bug #17228: Hammer OSD memory use very high (EL6)
- you can try jemalloc instead of tcmalloc,
options like osd_client_message_size_cap and osd_client_message_cap also m... - 07:19 AM Revision 16b5487a (ceph): os/bluestore: drop result check of OP_TRY_RENAME
- Because _rename() never returns -ENOENT, it only
returns -EEXIST on failure.
Signed-off-by: xie xingguo <xie.xingguo... - 07:15 AM Revision abe91446 (ceph): run-*make-check.sh: Make DRY_RUN actually mean a dry run
- DRY_RUN does not currently do an actual dry run as it actually runs an install
command.
Signed-off-by: Brad Hubbard ... - 07:11 AM CephFS Bug #17231 (Resolved): CephFS : IOs get terminated while reading/writing on larger files
- It was a tool use case problem, unrelated to CephFS. Closing the bug.
- 07:09 AM CephFS Bug #17231: CephFS : IOs get terminated while reading/writing on larger files
- The problem lied with usage of VDbench. If you have 256 threads, but 10 files, VDBench might fail.
From VDBench us... - 06:56 AM Revision be7346ce (ceph): os/bluestore: add sanity check for compress()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 06:33 AM Fix #5844 (Resolved): osd: snaptrimmer should throttle itself
- 06:29 AM Support #12455 (Closed): TEUTHOLOGY TEST RUN ERROR
- 05:30 AM Revision c617ea83 (ceph): rgw: Do not archive metadata by default
- Fixes: http://tracker.ceph.com/issues/17256
Signed-off-by: Pavan Rallabhandi <PRallabhandi@walmartlabs.com> - 04:10 AM CephFS Bug #17181 (Duplicate): "[ FAILED ] LibCephFS.ThreesomeInterProcessRecordLocking" in smoke
- 03:57 AM Bug #17226: Osd assert failed after large amount of write
- # ceph tell osd.90 bench
{
"bytes_written": 1073741824,
"blocksize": 4194304,
"bytes_per_sec": 231655... - 03:39 AM Bug #17226: Osd assert failed after large amount of write
- maybe you should do some basic bench on osd disk,
use ceph tell osd.$id bench or other ways. - 02:27 AM Bug #17226: Osd assert failed after large amount of write
- huang jun wrote:
> it seems that the filestore sync_entry thread was blocked for more than 600s,
> will do syncfs i... - 01:24 AM Bug #17226: Osd assert failed after large amount of write
- it seems that the filestore sync_entry thread was blocked for more than 600s,
will do syncfs in sync_entry, so you c... - 03:38 AM Revision 485ff7a4 (ceph): Stop hiding errors from run-tox.sh
- The grep -v should have been grep, but, why even bother?
Tox doesn't output that much; just dump it, and exit with
to... - 03:34 AM Revision 1d7b5d8b (ceph): ceph-disk tests: Let missing python interpreters be non-fatal
- Let tox ignore missing interpreters, and add py35 and py36 as well.
This lets tests work on Xenial, for example, whic... - 03:32 AM Bug #17268 (Fix Under Review): ceph-disk tox.ini calls for py34, not available on Xenial
- 03:19 AM Bug #17169: Wrong check of the limitation of creating PGs
- the code shows that:
(106-8)/3 = 32, which is not bigger than mon_osd_max_split_count(default:32);
so you can set i... - 02:46 AM Feature #12406: Support for building on Alpine Linux
- Three pieces left:
https://github.com/alpinelinux/aports/pull/295
https://github.com/ceph/ceph/pull/9853
htt... - 02:11 AM Bug #17180: Osd restarts intermittently while running ceph FS IO
- as i know the 'ceph-run' script will respawn osd after osd aborted.
you should see the osd log to find out why the o... - 01:34 AM Bug #17213: As the cluster is filling up, write performance decreases
- can you paste your rados bench command? do you have any overwrite operations?
it's werid there are so many reads aft... - 01:30 AM CephFS Bug #16914: multimds: pathologically slow deletions in some tests
- Okay so it appears Greg is right after looking through the mds logs for the client getattr op posted above. It appear...
09/13/2016
- 11:42 PM CephFS Bug #16914: multimds: pathologically slow deletions in some tests
- Looking at this new run which toggles fuse_default_permissions:
http://pulpito.ceph.com/pdonnell-2016-08-11_20:40:... - 10:54 PM Revision 855208ae (ceph): Merge pull request #10826 from xiexingguo/xxg-wip-fix-objecter-0823
- osdc/objecter: misc fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 10:52 PM Revision 5c431584 (ceph): Merge pull request #10859 from xiexingguo/xxg-wip-fix-osd-08-25
- osd/osd_type: check if pool is gone during check_new_interval()
Reviewed-by: Samuel Just <sjust@redhat.com> - 10:37 PM CephFS Bug #17181 (Need More Info): "[ FAILED ] LibCephFS.ThreesomeInterProcessRecordLocking" in smoke
- Ceph bug?
- 10:37 PM rbd Bug #17182 (Need More Info): "sysfs write failed" in smoke
- Ceph bug?
- 10:34 PM Revision e638336d (ceph): liblua: build Lua convenience library
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 10:34 PM Revision cb33c5c0 (ceph): cls-lua: write object classes in Lua
- Introduces cls_lua that allows object classes to be created dynamically
using the Lua language. Each request is proce... - 10:01 PM Revision 96c436a9 (ceph): Merge pull request #11059 from markhpc/wip-bluefs-wal-buffered
- bluestore/BlueFS: revert direct IO for WRITER_WAL
- 06:13 PM Revision fd6b1ccd (ceph): Merge pull request #11030 from amoxic/amoxic-wip-fix-do-write-small
- os/bluestore: fix offset bug in _do_write_small.
Reviewed-by: Sage Weil <sage@redhat.com> - 06:12 PM Revision 610c7676 (ceph): rocksdb: pull up to master (4.12 + a few patches)
- This includes Somnath's fix for log recycling.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:57 PM Revision 3ed8169e (ceph): test/osd: add test for fast mark down functionality
- Test checks both async and simple messenger and also checks whether
disabling "osd fast fail on connection refused" o... - 05:57 PM Revision 675a8dee (ceph): osdc: remove MOSDFailure include
- Doesn't seem to be necessary anymore.
Signed-off-by: Piotr Dałek <git@predictor.org.pl> - 05:57 PM Revision 75074524 (ceph): OSD: Implement ms_handle_refused
- Added implementation of ms_handle_refused in OSD code, so it sends
MOSDFailure message in case the peer connection fa... - 05:57 PM Revision fca6817d (ceph): messages/MOSDFailure.h: distinguish between timeout and immediate failure
- Change "is_failed" field to "flags" and use it to distinguish between timeout
and immediate, known OSD failure. Then ... - 05:57 PM Revision 50837428 (ceph): msg/async: implement ECONNREFUSED detection
- This commit adds code that detects ECONNREFUSED and dispatches appropriate
event further in Async messenger.
Signed-... - 05:57 PM Revision d58d7d3d (ceph): msg/simple: add ms_handle_refused callback
- Added new callback (ms_handle_refused) to dispatchers. It is called
once connection attempt fails with ECONNREFUSED.
... - 05:35 PM Revision c497fb6f (ceph): common/Timer.cc: replace long types with auto
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 03:40 PM rgw Bug #17273 (Fix Under Review): rgw: S3's Browser Upload is handled in incompliantly with the S3 d...
- https://github.com/ceph/ceph/pull/11066
- 03:10 PM rgw Bug #17273 (In Progress): rgw: S3's Browser Upload is handled in incompliantly with the S3 docume...
- 03:09 PM rgw Bug #17273 (Resolved): rgw: S3's Browser Upload is handled in incompliantly with the S3 documenta...
- According to the "Browser Uploads to S3 using HTML POST Forms ":https://aws.amazon.com/articles/1434 any field after ...
- 03:07 PM Revision d3d26875 (ceph): fio: use ref counting for Engine instance
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:04 PM Revision 3b2c0947 (ceph): Merge pull request #11046 from stiopaa1/common_timer_deleteCopyConstrAn...
- common/Timer.h: delete copy constr and assign op
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:02 PM Revision 1a763249 (ceph): fio: generalize for other ObjectStores
- * renamed target to fio_ceph_objectstore
* moved into src/test/fio subdirectory
* added to cmake build
* added suppor... - 03:02 PM Revision 8d57c6a3 (ceph): fio: add README and example job and config files
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 03:01 PM Revision 77b0cc53 (ceph): Merge pull request #11057 from liewegas/wip-os-fuse
- qa/workunits/objectstore/test_fuse.sh: make test_fuse.sh work with filestore
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:46 PM Revision bb46dcae (ceph): Ideally fio.h include would work like this
- Signed-off-by: Daniel Gollub <daniel.gollub@gmail.com>
- 02:46 PM Revision 39306617 (ceph): Fix redefinitions build errors/warnings
- due to not third-party include-safe fio.h
Signed-off-by: Daniel Gollub <daniel.gollub@gmail.com> - 02:46 PM Revision a05dd63c (ceph): Latest fio fixed double-declaration issues
- Signed-off-by: Daniel Gollub <daniel.gollub@gmail.com>
- 02:46 PM Revision b0cae2c1 (ceph): Initial fio_ceph_filestore integration in ceph buildenv
- Signed-off-by: Daniel Gollub <daniel.gollub@gmail.com>
- 02:27 PM Messengers Bug #16472 (Resolved): ./msg/DispatchQueue.h: 219: FAILED assert(mqueue.empty())
- 01:57 PM Revision 5f526617 (ceph): Merge pull request #11064 from ilc/make-srpm
- make-srpm.sh: A simple script to make the srpm for ceph.
- 01:56 PM Revision 935ca2d8 (ceph): Merge pull request #11061 from xiexingguo/xxg-wip-bs-0913
- os/bluestore: fix shard_info::dump()
Reviewed-by: Sage Weil <sage@redhat.com> - 01:51 PM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- Jason suggests that 1a48a8a is the culprit, I've pushed branch wip-17270 to the gitbuilders which is a revert of that...
- 12:12 PM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
The OSD op that's triggering this....- 11:24 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- I just add the debug objectcacher and objecter log level and reproducte the fuse-client crash. Please see the log att...
- 10:25 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- Thanks for the report, please could you try reproducing with --debug-objectcacher=10 and debug-objecter=7 so that we ...
- 10:01 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- Detail log is attached below.
- 09:54 AM CephFS Bug #17270 (Resolved): [cephfs] fuse client crash when adding a new osd
- Hello everyone,
I have met a ceph-fuse crash when i add osd to osd pool.
I am writing data through ceph-fuse,th... - 01:51 PM Revision 0576dacd (ceph): make-srpm.sh: A simple script to make the srpm for ceph.
- This is a simple script to make the srpm for ceph based
on make-dist.
Yes, it is short, but it will stop many people... - 01:44 PM Revision 93badb8e (ceph): Last stable version as of https://github.com/gcharot/ceph-lazy
- Signed-off-by: gcharot <gcharot@redhat.com>
- 01:40 PM Revision be607ab6 (ceph): qa/workunits/objecstore/test_fuse.sh: make it work with filestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:11 PM rgw Bug #17272 (Can't reproduce): S3: Batch operations fail
- Hi there,
We've been watching [[http://tracker.ceph.com/issues/15896]] with interest because this issue appears to... - 12:21 PM Linux kernel client Bug #17191 (In Progress): kclient accesses "/" when mounting a subpath
- 12:10 PM CephFS Bug #17236: MDS goes damaged on blacklist (failed to read JournalPointer: -108 ((108) Cannot send...
- http://pulpito.ceph.com/jspray-2016-09-13_08:34:56-fs-wip-no-recordlock-test-testing-basic-smithi/413348/
Promotin... - 12:08 PM Revision a9c0e7b7 (ceph): Removed reference about pool ownership based on BZ#1368528
- Signed-off-by: Bara Ancincova <bara@redhat.com>
https://bugzilla.redhat.com/show_bug.cgi?id=1368528
From email conv... - 10:45 AM CephFS Bug #17271: Failure in snaptest-git-ceph.sh
- Zheng, could you take a look please?
- 10:44 AM CephFS Bug #17271 (Resolved): Failure in snaptest-git-ceph.sh
Either in addition to http://tracker.ceph.com/issues/17172 or we didn't really fix it.
This test branch was runn...- 10:02 AM Revision 038b093f (ceph): Delete unnecessary parentheses.
- Signed-off-by: feng yu amoxic@126.com
- 08:46 AM Revision 6a3e5c49 (ceph): Merge pull request #11016 from wido/snap-max-uid
- mds: Set mds_snap_max_uid to 4294967294
Reviewed-by: John Spray <john.spray@redhat.com> - 08:39 AM Revision 93eb3605 (ceph): Merge pull request #978 from ceph/wip-ec-fast-read
- test fast ec read
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:15 AM Bug #16506 (Pending Backport): "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrad...
- 08:15 AM Revision a58c5aa2 (ceph): Merge pull request #1171 from dachary/wip-16506-ceph-coverage
- upgrade: ceph-test is needed for ceph-coverage
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Kefu Chai ... - 07:06 AM Revision d44f5834 (ceph): upgrade: ceph-test is needed for ceph-coverage
- Do not exclude the ceph-test package otherwise the ceph-coverage
executable is not installed.
Fixes: http://tracker.... - 06:47 AM Revision 24538e4a (ceph): min_min_alloc_size to accommodate changing min_alloc_size
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:42 AM Bug #16477: ceph cli: Rados object in state configuring race
- I think this is a race condition. It happened during a test as well and is apparently rare....
- 06:41 AM Revision 525d9899 (ceph): Merge pull request #1118 from ceph/wip-scrub
- tasks/scrub_test: use fuse path (do not assume filestore!)
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:06 AM Revision 87bf242b (ceph): os/bluestore: fix dump of shard_info
- which shall include the "extents" field too.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 05:58 AM CephFS Bug #17253: Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- This was not specific to that test configuration, happening in a normal test branch:
http://qa-proxy.ceph.com/teutho... - 03:58 AM rgw Bug #17269 (Resolved): There is a question about the bucket link API parameters
- #0 RGWBucket::link (this=0x7f55c8ff68d0, op_state=..., err_msg=0x0) at rgw/rgw_bucket.cc:591
#1 0x00007f588d75dd97... - 03:52 AM Bug #17266: virtualenv default paths not uniquely named
- virtualenv directories is put under @${CEPH_BUILD_VIRTUALENV}@ in cmake, which is in turn @/tmp@ by default. but one ...
- 03:31 AM Bug #17266 (Closed): virtualenv default paths not uniquely named
- virtualenvs are used in the build for testing the various python projects. They're created, by default, in /tmp/<too...
- 03:42 AM Bug #17268 (Resolved): ceph-disk tox.ini calls for py34, not available on Xenial
- tox.ini requests py34 for the ceph-disk test, but python 3.4 isn't available for Xenial, at least. The obvious fix f...
- 03:39 AM Bug #17267 (Resolved): run-tox.sh hides errors
- run-tox.sh runs the check tests for several python tools. It runs tox with stdout and stdout redirected to <virtuale...
09/12/2016
- 11:22 PM Bug #16025: unittest_chain_xattr failure in 'make check' bot
- i see the same on manual run:...
- 08:44 PM Revision c2b7cdbc (ceph): osd/OSD.cc: remove unneeded searching of maps
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 08:21 PM rgw Bug #15896: S3: set EncodingType in ListBucketResult
- Hi there,
We've been watching this ticket with interest (and https://github.com/ceph/ceph/pull/7712) because this ... - 05:39 PM rgw Fix #17136 (Pending Backport): Fix accidental logic inversion in RGW hostname fallback
- 05:38 PM Revision a879c151 (ceph): Merge pull request #10873 from dreamhost/wip-17136
- rgw: Fix Host->bucket fallback logic inversion
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 04:39 PM RADOS Bug #16133: rados bench: ./common/Mutex.h:96: void Mutex::_pre_unlock(): Assertion `nlock > 0' fa...
- Seen in a rados run (in Sepia) today: http://pulpito.ceph.com/smithfarm-2016-09-12_11:19:22-rados-jewel---basic-smith...
- 03:40 PM Revision 1101fcc7 (ceph): rgw: use non-blocking reads for clear_signal
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 03:40 PM Revision 0359be62 (ceph): rgw: detect and work around a curl_multi_wait bug
- Fixes: http://tracker.ceph.com/issues/15915
Fixes: http://tracker.ceph.com/issues/16695
Signed-off-by: Casey Bodley ... - 03:26 PM Revision f2f5cdf3 (ceph): rgw: factored clear_signal out of do_curl_wait
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 03:18 PM Revision bd3aa6ac (ceph): Merge pull request #10918 from tianshan/fix-bucket-decode-v
- rgw: fix rgw_bucket_dir_entry decode v
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:17 PM rbd Bug #16717 (Resolved): "[ FAILED ] TestLibRBD.TestCreateLsDeletePP" in upgrade:client-upgrade-j...
- *Jewel PR*: https://github.com/ceph/ceph-qa-suite/pull/1173
- 03:01 PM rbd Bug #16717 (Pending Backport): "[ FAILED ] TestLibRBD.TestCreateLsDeletePP" in upgrade:client-u...
- I think we still need to backport https://github.com/ceph/ceph-qa-suite/pull/1172 to jewel branch. AFAIR teuthology r...
- 12:51 PM rbd Bug #16717 (Resolved): "[ FAILED ] TestLibRBD.TestCreateLsDeletePP" in upgrade:client-upgrade-j...
- 11:33 AM rbd Bug #16717 (Fix Under Review): "[ FAILED ] TestLibRBD.TestCreateLsDeletePP" in upgrade:client-u...
- 11:32 AM rbd Bug #16717: "[ FAILED ] TestLibRBD.TestCreateLsDeletePP" in upgrade:client-upgrade-jewel-distro...
- PR: https://github.com/ceph/ceph-qa-suite/pull/1172
- 03:02 PM Revision 41104d2c (ceph): rgw: eradicate dynamic memory allocation in RGWPostObj.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 02:53 PM Revision 52fa3ba9 (ceph): bluestore/BlueFS: revert direct IO for WRITER_WAL
- Signed-off-by: Mark Nelson <mnelson@redhat.com>
- 02:20 PM Revision b8c203fb (ceph): Merge pull request #11040 from xiexingguo/xxg-wip-bluestore-0910
- os/bluestore: fix leak of result-checking of _fsck_check_extents
Reviewed-by: Sage Weil <sage@redhat.com> - 02:01 PM rbd Backport #17265 (In Progress): jewel: Possible deadlock race condition between image close and li...
- 01:52 PM rbd Backport #17265 (Resolved): jewel: Possible deadlock race condition between image close and libra...
- https://github.com/ceph/ceph/pull/11466
- 01:55 PM Revision 3aec5137 (ceph): Merge pull request #11047 from tchaikov/wip-long-live-readdir
- ceph_mon: use readdir() as readdir_r() is deprecated
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 01:37 PM Revision 7ba551ab (ceph): Merge pull request #11033 from xiexingguo/xxg-wip-bluestore-0909
- os/bluestore: fix potential access violation during rename
Reviewed-by: Sage Weil <sage@redhat.com> - 12:50 PM Revision c0cd594d (ceph): Merge pull request #1173 from ceph/wip-16717-jewel
- jewel: suites/upgrade: override rbd_default_features config back to pre-Jewel
Reviewed-by: Jason Dillaman <dillaman@... - 12:49 PM Revision c0ef05bf (ceph): suites/upgrade: override rbd_default_features config back to pre-Jewel
- Fixes: http://tracker.ceph.com/issues/16717
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
(cherry picked from com... - 12:48 PM Revision 5d304eb6 (ceph): Merge pull request #1172 from trociny/wip-16717
- suites/upgrade: override rbd_default_features config back to pre-Jewel
Reviewed-by: Jason Dillaman <dillaman@redhat.... - 11:24 AM Revision 47a41286 (ceph): suites/upgrade: override rbd_default_features config back to pre-Jewel
- Fixes: http://tracker.ceph.com/issues/16717
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 10:09 AM Revision aa8f2f13 (ceph): OSD: avoid FileStore finisher deadlock in osd_lock when shutdown OSD
- When OSD receive signal to shutdown, it will try to call ObjectStore->flush
to make sure all pending IO done. But pre... - 09:16 AM Bug #17260: ceph_test_rados_api_list assert() in lockdep_will_lock(const char*, int, bool)
- i tried to compile librados as a static library, and link ceph_test_rados_api_list against it. the problem disappears...
- 05:53 AM Bug #17260 (Resolved): ceph_test_rados_api_list assert() in lockdep_will_lock(const char*, int, b...
- ...
- 09:12 AM rgw Bug #17256 (Fix Under Review): objects in the metadata_heap pool are created, but never read or r...
- https://github.com/ceph/ceph/pull/11051
- 09:10 AM rbd Bug #17254 (Pending Backport): Possible deadlock race condition between image close and librados ...
- 09:10 AM rbd Bug #17227 (Pending Backport): exclusive_lock::AcquireRequest doesn't handle -ERESTART on image::...
- 09:10 AM Revision 30bbe656 (ceph): Merge pull request #11044 from dillaman/wip-17227
- librbd: ignore partial refresh error when acquiring exclusive lock
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 09:08 AM Revision d141b138 (ceph): Merge pull request #11037 from dillaman/wip-17254
- librbd: possible deadlock if cluster connection closed after image
Reviewed-by: Xiaoxi Chen <xiaoxchen@ebay.com>
Rev... - 09:03 AM Revision 5bc2ebcb (ceph): python-rados: implement new aio_stat.
- This change adds python API for the following C methods:
* rados_aio_stat
Signed-off-by: Iain Buclaw <iain.buclaw@so... - 07:59 AM CephFS Backport #17264 (Resolved): jewel: multimds: allow_multimds not required when max_mds is set in c...
- https://github.com/ceph/ceph/pull/10997
- 07:59 AM Backport #17263 (Resolved): jewel: ceph-objectstore-tool: ability to perform filestore splits off...
- https://github.com/ceph/ceph/pull/11252
- 07:40 AM rbd Backport #17262 (Resolved): jewel: rbd-nbd IO hang
- https://github.com/ceph/ceph/pull/11467
- 07:40 AM rbd Backport #17261 (Resolved): jewel: Potential seg fault when blacklisting a client
- 07:13 AM Revision 85752922 (ceph): filestore/FDCache.h:Fix bug when filestore_fd_cache_shards = 0
- Signed-off-by: jimifm <hong.zhangoole@gmail.com>
- 06:40 AM Revision f578fd63 (ceph): os/ObjectStore: fix return code of collection_empty() method
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 04:38 AM RADOS Bug #17257: ceph_test_rados_api_lock fails LibRadosLockPP.LockExclusiveDurPP
- test again at http://pulpito.ceph.com/kchai-2016-09-12_04:34:59-rados-master---basic-mira/ passed.
- 03:56 AM Revision 99b79963 (ceph): ceph_mon: use readdir() as readdir_r() is deprecated
- see https://lwn.net/Articles/696469/, readdir_r() is deprecated by glibc
since 2.24. so let's use readdir() instead.
... - 03:11 AM Revision 1e29fd17 (ceph): Merge pull request #10941 from ceph/8.31.16-fix-install-deps
- install-deps: exit non-zero when we cannot match distro
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:50 AM Revision 3ff9da12 (ceph): Merge pull request #11043 from stiopaa1/osd_osd_removeUnneededReturns
- osd/OSD.cc: remove unneeded returns
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:25 AM CephFS Bug #17259: multimds: ranks >= max_mds may be assigned after reducing max_mds
- Yeah, ranks are assigned out of the 'in' set rather than sequentially, so if you deactivate one in the middle of the ...
09/11/2016
- 11:23 PM CephFS Bug #17259 (Won't Fix): multimds: ranks >= max_mds may be assigned after reducing max_mds
- I'm not sure if this is really a problem or not but I noticed in:
http://pulpito.ceph.com/pdonnell-2016-09-10_15:1... - 09:52 PM Revision 1ddb2990 (ceph): osd/OSD.cc: remove unneeded returns
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 09:50 PM Revision 37ea6afb (ceph): mon/OSDMonitor.cc: remove use of boost assign
- we can now use C++11 initialisation
Signed-off-by: Michal Jarzabek <stiopa@gmail.com> - 07:19 PM Revision d4c48fdc (ceph): common/Timer.h: delete copy constr and assign op
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 06:52 PM rgw Backport #17150 (In Progress): hammer: rgw: Anonymous user is able to read bucket with authentica...
- 01:10 PM rbd Bug #17227 (Fix Under Review): exclusive_lock::AcquireRequest doesn't handle -ERESTART on image::...
- *PR*: https://github.com/ceph/ceph/pull/11044
- 01:08 PM Revision 24396dcb (ceph): librbd: ignore partial refresh error when acquiring exclusive lock
- Fixes: http://tracker.ceph.com/issues/17227
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 10:25 AM Revision d18d2e6b (ceph): suites: fix samba xfs symlink
- I broke this in bafbeebf
Signed-off-by: John Spray <john.spray@redhat.com> - 10:09 AM Revision 5999adba (ceph): Merge pull request #11041 from stiopaa1/osd_replicatedpg_removeClassRed...
- osd/ReplicatedPG: remove class redeclaration
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:03 AM Feature #17220 (Pending Backport): ceph-objectstore-tool: ability to perform filestore splits off...
- @josh, iirc, this change is meant to be backported to hammer? right? i am keeping the "Backport" field empty until ha...
- 04:01 AM devops Feature #16776 (Resolved): Enable RPM build without ceph-test subpackage
- 04:00 AM Bug #17258 (Can't reproduce): lost-unfound-upgrade.yaml times out in rados qa run
- see http://pulpito.ceph.com/kchai-2016-09-10_15:46:37-rados-wip-kefu-testing---basic-mira/408514/
- 03:57 AM RADOS Bug #17257: ceph_test_rados_api_lock fails LibRadosLockPP.LockExclusiveDurPP
- rerunning at http://pulpito.ceph.com/kchai-2016-09-11_03:15:51-rados-master---basic-mira/, and it failed also with a ...
- 03:56 AM RADOS Bug #17257 (Can't reproduce): ceph_test_rados_api_lock fails LibRadosLockPP.LockExclusiveDurPP
- ...
- 03:52 AM Revision 8ffaa6a8 (ceph): Merge pull request #10952 from codeyz/dev
- crush/CrushCompiler.cc:884
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:49 AM Revision 91eabb9c (ceph): Merge pull request #10986 from stiopaa1/osd_osd_remove_repeated_searchi...
- osd/OSD.cc: remove repeated searching of map
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:39 AM Revision bb4622f4 (ceph): Merge pull request #11000 from stiopaa1/osd_osd_removeUnneededSearchMap
- osd/OSD.cc: remove unneeded searching of map
Reviewed-by: Jun Huang <hjwsm1989@gmail.com>
Reviewed-by: Kefu Chai <kc... - 03:37 AM Revision 36b6be50 (ceph): Merge pull request #10935 from branch-predictor/bp-optimized-crush-ln
- crush: don't normalize input of crush_ln iteratively
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Sa... - 03:33 AM Revision 3f0ab86d (ceph): Merge pull request #1124 from ceph/wip-offline-split
- ceph_manager: test offline split via ceph-objectstore-tool
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:26 AM Revision 0e7dbb99 (ceph): Merge pull request #10776 from ceph/wip-offline-split
- ceph-objectstore-tool: add a way to split filestore directories offline
Reviewed-by: David Zafman <dzafman@redhat.co... - 03:23 AM Revision 2d3f1fc7 (ceph): Merge pull request #10011 from songbaisen/a16
- mon: remove the redundant list swap in paxos commit_proposal
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:22 AM Revision 64d8a793 (ceph): Merge pull request #10872 from rjfd/wip-16776
- Enable builds without ceph-test subpackage
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Ken Dreyer <kd...
09/10/2016
- 06:17 PM Revision b4fd5fd9 (ceph): osd/ReplicatedPG: remove class redeclaration
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 05:43 PM Revision 818c2f2a (ceph): librbd: possible deadlock if cluster connection closed after image
- Fixes: http://tracker.ceph.com/issues/17254
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 03:17 PM rgw Bug #14208: rgw: 500 returned on Put Bucket ACL (ECANCELLED/-125)
- Matt,
We ran into this on Jewel 10.2.2 clusters, while creating a container (bizarrely reproducible only with a sp... - 10:33 AM Revision 97848a8b (ceph): os/bluestore: drop bluestore_blob_id_t
- which is not used anymore.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 10:08 AM Revision 4fc48a6b (ceph): os/bluestore: kill fill() method from bluestore_extent_ref_map_t
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:58 AM Revision d133cc57 (ceph): os/bluestore: add sanity check during extent loading
- Otherwise there are potential extent leaks.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 08:54 AM CephFS Feature #9466: kclient: Extend CephFSTestCase tests to cover kclient
- Latest:
http://pulpito.ceph.com/jspray-2016-09-05_12:30:10-kcephfs:recovery-master-testing-basic-mira/... - 08:25 AM rbd Bug #17251 (Pending Backport): Potential seg fault when blacklisting a client
- 08:23 AM Revision 864f2acb (ceph): Merge pull request #11034 from dillaman/wip-17251
- librbd: potential seg fault when blacklisting an image client
Reviewed-by: Venky Shankar <vshankar@redhat.com>
Revie... - 07:35 AM Revision 4a5b395c (ceph): os/bluestore: fix leak of result-checking of _fsck_check_extents
- We shall not ignore the result of _fsck_check_extents() durint fsck().
Signed-off-by: xie xingguo <xie.xingguo@zte.c... - 03:08 AM rgw Bug #17256: objects in the metadata_heap pool are created, but never read or removed
- Thanks for the tracker Casey, will take a stab at it.
- 03:05 AM rgw Bug #16357: radosgw stats error
- After query stats with using "radosgw-admin user stats --uid=jiaopengju --sync-stats", the stats go back to normal.
... - 02:59 AM rgw Bug #16357: radosgw stats error
- This problem always exists in v10.2.2。
The different is, when create same bucket in 10.2.2, the stats didn't become ... - 02:12 AM Revision 1600d6f1 (ceph): os/bluestore: using is_spanning() for spanning checking
- Otherwise is_spanning() has no caller and shall be deleted.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:05 AM Revision 1ab12fa8 (ceph): os/bluestore: fix race condition
- The empty() method also needs to be called under the protection of lock.
Signed-off-by: xie xingguo <xie.xingguo@zte... - 01:25 AM Revision 836715af (ceph): os/bluestore: simplify extent_shard_key a little
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:22 AM Revision 728f69d9 (ceph): os/bluestore: make extent key generation a little faster
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:22 AM Revision ba69a2ce (ceph): os/bluestore: return onode_key to caller
- The get_key_extent_shard() method shall decompose extent_shard_key
into onode_key and offset, but currently we don't ... - 12:59 AM RADOS Bug #17252 (Fix Under Review): [Librados] Deadlock on RadosClient::watch_flush
- https://github.com/ceph/ceph/pull/11035
- 12:39 AM Revision a4f67893 (ceph): os/bluestore: fix potential access violation during rename
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
09/09/2016
- 09:15 PM Revision 01eb1327 (ceph): install-deps: exit non-zero when we cannot match distro
- Signed-off-by: Gregory Meno <gmeno@redhat.com>
- 07:58 PM Revision 20809844 (ceph): rgw: do_curl_wait uses ldout
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:42 PM rgw Bug #17256: objects in the metadata_heap pool are created, but never read or removed
- Example of metadata pool constantly increasing in size and number of objects:
NAME ID... - 06:00 PM rgw Bug #17256 (Resolved): objects in the metadata_heap pool are created, but never read or removed
- Metadata entries and their versions are being archived in the metadata_heap pool (.rgw.meta), but nothing is actually...
- 05:09 PM Revision 7635ed6c (ceph): Merge pull request #11001 from stiopaa1/client_barrier_moveCBlockSyncClass
- client/barrier: move C_Block_Sync class to .cc
Reviewed-by: John Spray <john.spray@redhat.com> - 04:49 PM rgw Backport #16794 (In Progress): jewel: multisite bucket sync doesn't retry objects that it fails t...
- 04:45 PM devops Feature #17255 (New): simplify package installation for deployment tools
- we need to simplify package installation for deployment tools and provide a single name that could install all requri...
- 04:03 PM CephFS Bug #16919 (Resolved): MDS: Standby replay daemons don't drop purged strays
- Not backporting because it's a behavioural cleanup rather than a bugfix
- 04:03 PM Revision 9faf7781 (ceph): Merge pull request #10606 from jcsp/wip-mds-standby-trim
- mds: trim null dentries proactively
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:24 PM Revision e7b0428e (ceph): ceph-objectstore-tool: add a way to split filestore directories offline
- Use the usual split code, and split each dir that meets the
usual split criteria.
This can be run with lower than us... - 02:59 PM rbd Bug #17254 (Fix Under Review): Possible deadlock race condition between image close and librados ...
- *PR*: https://github.com/ceph/ceph/pull/11037
- 02:37 PM rbd Bug #17254 (Resolved): Possible deadlock race condition between image close and librados shutdown
- librbd::ImageWatcher::C_UnwatchAndFlush instantiates a librados::Rados class to invoke aio_watch_flush. However, it's...
- 01:34 PM rbd Bug #16921 (Pending Backport): rbd-nbd IO hang
- 01:33 PM Revision 253cddaa (ceph): Merge pull request #10985 from dillaman/wip-16921
- rbd-nbd: fix kernel deadlock during teuthology testing
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 01:28 PM CephFS Bug #17253 (Resolved): Crash in Client::_invalidate_kernel_dcache when reconnecting during unmount
- ...
- 01:12 PM Revision a8f8598a (ceph): cmake: Use WITH_TESTS flag to guard the build of ceph-test scripts/bina...
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 01:12 PM Revision 0f347b82 (ceph): rpm: Added ceph_test_package bcond flag to control the build of ceph-te...
- Fixes: http://tracker.ceph.com/issues/16776
Signed-off-by: Ricardo Dias <rdias@suse.com> - 01:12 PM Revision d3ac8d18 (ceph): deb: Moved ceph-client-debug from ceph-base to ceph-test package
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 12:49 PM RADOS Bug #17252: [Librados] Deadlock on RadosClient::watch_flush
- cinder is explicitly closing the rados connection before closing the image?
- 12:36 PM RADOS Bug #17252: [Librados] Deadlock on RadosClient::watch_flush
- Fix should be passing lock to watch_flush, and use the lock instead of local variable "mylock" for condition wait.
- 12:33 PM RADOS Bug #17252 (Can't reproduce): [Librados] Deadlock on RadosClient::watch_flush
- https://github.com/ceph/ceph/blob/v10.2.2/src/librados/RadosClient.cc#L341, in the watch_flush, it is waiting on con...
- 12:47 PM rbd Bug #16974 (In Progress): rbd-mirror: force-promoted image will remain R/O until local rbd-mirror...
- *NOTE*: blocker for upstream cinder RBD replication driver feature
- 12:44 PM Revision 806bdfb8 (ceph): Merge pull request #1170 from ceph/wip-16921
- rbd: move nbd test workload to separate client host from OSDs
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 12:33 PM rbd Bug #17251 (Fix Under Review): Potential seg fault when blacklisting a client
- *PR*: https://github.com/ceph/ceph/pull/11034
- 12:31 PM rbd Bug #17251 (Resolved): Potential seg fault when blacklisting a client
- 12:31 PM Revision 7025fe89 (ceph): librbd: potential seg fault when blacklisting an image client
- Fixes: http://tracker.ceph.com/issues/17251
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 12:31 PM rgw Feature #16241: support torrent file in ceph
- PR url:
https://github.com/ceph/ceph/pull/10396 - 12:22 PM Revision 3f93a191 (ceph): librbd: invalidate cache before trimming image
- Any potential writeback outside the extents of a shrunk image
would result in orphaned objects.
Signed-off-by: Jason... - 12:22 PM Revision 4ce66384 (ceph): librbd: ignore cache busy errors when shrinking an image
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:22 PM Revision c6cfb616 (ceph): rbd-nbd: mask out-of-bounds IO errors caused by image shrink
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:21 PM Revision ce7c1520 (ceph): rbd-nbd: fix kernel deadlock during teuthology testing
- Fixes: http://tracker.ceph.com/issues/16921
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 12:14 PM CephFS Feature #17249 (Fix Under Review): cephfs tool for finding files that use named PGs
- https://github.com/ceph/ceph/pull/11026
- 11:55 AM Revision aaa75aeb (ceph): rpm: Moved ceph-client-debug from ceph-base to ceph-test package
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 11:55 AM Revision 06875b50 (ceph): rpm: Renamed bcond tests flag to make_check
- Signed-off-by: Ricardo Dias <rdias@suse.com>
- 09:55 AM rbd Bug #16717: "[ FAILED ] TestLibRBD.TestCreateLsDeletePP" in upgrade:client-upgrade-jewel-distro...
- Consistently happens:...
- 09:54 AM Bug #16506 (Fix Under Review): "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrad...
- @Yuri the test passed on VPS (modulo a known bug http://tracker.ceph.com/issues/16717) and a fix is ready for review....
- 09:30 AM Bug #16506: "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrade-jewel-distro-basi...
- https://github.com/ceph/ceph-qa-suite/pull/1171
- 09:26 AM Bug #16506: "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrade-jewel-distro-basi...
- The ceph-coverage executable is provided by the ceph-test package but it is excluded from the installation.
- 09:13 AM Bug #16506 (In Progress): "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrade-jew...
- Re-running twice on VPS...
- 09:33 AM Bug #17176: "FAILED assert(pg->peer_info.count(so))" in upgrade:infernalis-x-master-distro-basic-vps
- @Yuri I believe this missing backport is not a blocker in the context of the 10.2.3 release validation.
- 09:00 AM Bug #17176: "FAILED assert(pg->peer_info.count(so))" in upgrade:infernalis-x-master-distro-basic-vps
- @Yuri you are correct, https://github.com/ceph/ceph/pull/5780/commits/65dcc2da76750d0b6dd2cf0031c44f32749f33e5 was ba...
- 08:52 AM Bug #17176 (In Progress): "FAILED assert(pg->peer_info.count(so))" in upgrade:infernalis-x-master...
- ...
- 09:05 AM Bug #16718 (Duplicate): "/bin/adjust-ulimits: line 16: exec: ceph-coverage: not found" in upgrade...
- 08:40 AM Feature #17220 (Fix Under Review): ceph-objectstore-tool: ability to perform filestore splits off...
- 08:26 AM Revision 44e4ece6 (ceph): Merge pull request #10723 from ceph/wip-os-fuse
- os/FuseStore: fix several FuseStore issues
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:49 AM Revision e16a65e7 (ceph): os/bluestore: Something may be wrong with _do_write_small.
- The statement "if (ep->logical_offset + b->get_blob().get_ondisk_length() <= offset)" which try to judge if the writi...
- 05:47 AM Revision 994712fd (ceph): Merge pull request #9767 from dx9/wip-safe-io
- safe_io: Improve portability by replacing loff_t type usage with off_t.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:21 AM Bug #17250 (Resolved): arch flags not defined for armv8 crc
- 03:39 AM Bug #17250 (Fix Under Review): arch flags not defined for armv8 crc
- https://github.com/ceph/ceph/pull/11028
- 03:22 AM Bug #17250: arch flags not defined for armv8 crc
- This makes it work:...
- 03:19 AM Bug #17250 (Resolved): arch flags not defined for armv8 crc
- cmake/modules/SIMDExt.cmake tests and sets SIMD extension -march flags for the floating point compilations, but src/C...
- 05:21 AM Revision 7ebf562f (ceph): Merge pull request #11028 from ceph/wip-17450
- cmake: set ARM_CRC_FLAGS from the CRC test rather than ARM_NEON_FLAGS
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:28 AM Revision 3fdccc9e (ceph): Set ARM_CRC_FLAGS from the CRC test rather than ARM_NEON_FLAGS
- Fixes: http://tracker.ceph.com/issues/17250
Signed-off-by: Dan Mick <dan.mick@redhat.com> - 03:12 AM Revision 3be403cc (ceph): Client: optimization param type of make_request
- Signed-off-by: gongchuang <gong.chuang@zte.com.cn>
- 02:56 AM Revision a0ffe7a0 (ceph): Merge pull request #10302 from stiopaa1/msg_asyncconn_addConstToMemFun
- msg/AsyncConnection: add const to mem functions
Reviewed-by: Haomai Wang <haomai@xsky.com> - 02:56 AM Revision 7979a210 (ceph): Merge pull request #10114 from stiopaa1/msg_asyncmess_get_proto_version...
- msg/AsyncMessenger: add const to function
Reviewed-by: Haomai Wang <haomai@xsky.com> - 02:55 AM Revision 1b163c80 (ceph): Merge pull request #11015 from tchaikov/wip-optional-py3
- cmake: make py3 a nice-to-have
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
Reviewed-by: Josh Durgin <jdurgin@... - 01:48 AM Revision 4b94d7fe (ceph): Merge branch 'rgwfs-fix-rgw-lookup' of https://github.com/cmgitdream/ce...
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 01:34 AM Revision 15ab4309 (ceph): rbd: move nbd test workload to separate client host from OSDs
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
09/08/2016
- 11:02 PM CephFS Feature #17249 (Resolved): cephfs tool for finding files that use named PGs
- Sometimes when a data pool is damaged, it is useful to work out which files are affected.
http://lists.ceph.com/pi... - 08:43 PM Revision 06d36f74 (ceph): mailmap: Sirisha Guduru affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 43ec6a41 (ceph): mailmap: Daniel Oliveira affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 977dd2ec (ceph): mailmap: Jan Fajerski affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 6f370df0 (ceph): mailmap: Dirk Mueller affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision cf973bbf (ceph): mailmap: Casey Bodley name normalization
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 51895550 (ceph): mailmap: Zhang Zezhu name normalization
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 652cc32c (ceph): mailmap: Jason Dillaman name normalization
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 7f5201a9 (ceph): mailmap: Shinobu Kinjo name normalization and affiliation (reverts a pr...
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision bcbfaccc (ceph): mailmap: Jeff Layton name normalization
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 78628ca3 (ceph): mailmap: Vladislav Odintsov affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision a9ddc7ef (ceph): mailmap: Michel Normand affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision ca767ca2 (ceph): mailmap: Ren Huanwen name normalization
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 141af375 (ceph): mailmap: MinSheng Lin affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision f4821e63 (ceph): mailmap: lan de affiliation and name normalization
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 8f68074b (ceph): mailmap: Weibing Zhang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision c2e71aa1 (ceph): mailmap: Hong Zhangoole name normalization and affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision 0986f1dd (ceph): mailmap: Ryne Li affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:43 PM Revision aa40a73d (ceph): mailmap: Chengwei Yang affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:17 PM Revision 5cb85003 (ceph): osd/PGBackend.h: move structs to .cc file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 08:10 PM Revision 3671d065 (ceph): osd/OSD.cc: remove unneeded searching of map
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 08:09 PM Revision 3d9e698b (ceph): client/barrier: move C_Block_Sync class to .cc
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:58 PM Revision aebfad68 (ceph): msg/AsyncMessenger: add const to function
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:56 PM Revision 85d0d359 (ceph): msg/AsyncMessenger: remove unused function
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:22 PM Revision 9a395049 (ceph): msg/AsyncConnection: add const to mem functions
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:12 PM Revision 2731a209 (ceph): Merge pull request #11003 from ceph/wip-cmake
- cmake: include(SIMDExt) in src/CMakeLists.txt
- 06:39 PM Revision 7123227f (ceph): Merge pull request #11023 from liewegas/wip-bluefs-extent-append
- os/bluestore/BlueFS: only extend extent on same bdev
- 06:29 PM Revision 0e530870 (ceph): os/bluestore/BlueFS: only extend extent on same bdev
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:26 PM Revision a3050182 (ceph): Merge pull request #10822 from Yan-waller/yj-wip-rgwfile-0823
- rgw_file: fix return value signedness (rgw_readdir)
verified: f23 - 05:35 PM Bug #17248 (Duplicate): Reduce deep scrub impact on normal operations
If there are lot of clones this can cause scrub to degrade performance.- 04:55 PM Revision de7cbf42 (ceph): make assert noop without debug macro
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 04:47 PM Revision 25b5a898 (ceph): Merge pull request #10321 from stiopaa1/async_EventSelect_addoverride
- msg/EventSelect.h: add override to virtual funct
Reviewed-by: Haomai Wang <haomai@xsky.com> - 04:47 PM Revision ea6e38c3 (ceph): Merge pull request #10318 from stiopaa1/async_eventkqueue_addOverride
- msg/EventKqueue.h: add override to virtual func
Reviewed-by: Haomai Wang <haomai@xsky.com> - 04:47 PM Revision 8aa5a565 (ceph): Merge pull request #10314 from stiopaa1/async_eventpoll_addOverride
- msg/EventPoll.h: add override to virtual functions
Reviewed-by: Haomai Wang <haomai@xsky.com> - 04:13 PM Revision a39db3d9 (ceph): Merge pull request #10882 from stiopaa1/rgw_rgw_coroutine_moveWaitConte...
- rgw/rgw_coroutine: move WaitContext to .cc file
verified: f23 - 03:51 PM rbd Bug #16921: rbd-nbd IO hang
- Spurious read request from kernel via rbd-nbd that raced with the resize resulted in the cache not being able to inva...
- 03:44 PM rgw Backport #16794 (New): jewel: multisite bucket sync doesn't retry objects that it fails to fetch
- the missing commit had already been backported. i cherry-picked the commits cleanly here: https://github.com/ceph/cep...
- 03:23 PM Revision f82b5936 (ceph): rgw: back off bucket sync on failures, don't store marker
- Fixes: http://tracker.ceph.com/issues/16742
If we fail on any single entry in bucket, skip updating the marker track... - 03:23 PM Revision bce19a39 (ceph): rgw: collect() stops if error encoutered
- and returns true if needed to be called again
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from co... - 03:23 PM Revision aa369817 (ceph): rgw: fix marker tracker completion handling
- Was not tracking high markers correctly. Could only work if there was a single
hole in the completion range. Just kee... - 03:23 PM Revision cefd6f51 (ceph): rgw: fix collection of object sync errors
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit aacc31f72cef6f151459e4a0543850edeeaf1938) - 03:14 PM Revision ccd7cd17 (ceph): Merge pull request #10929 from atheism/rgw-lc-fix-typo
- rgw: fix typo of "minite" to "minute" in rgw_lc.cc
verified: f23 - 02:13 PM Revision a61dc2a1 (ceph): tasks/scrub_test: use fuse path (do not assume filestore!)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:10 PM Revision c934402a (ceph): Merge pull request #11010 from liewegas/wip-bluefs-compaction-race
- os/bluestore/BlueFS: do not start racing async compaction
Reviewed-by: Varada Kari <varada.kari@sandisk.com> - 02:07 PM Revision fd1bf4aa (ceph): Merge pull request #11013 from xiexingguo/xxg-wip-fix-cmake-check
- build: drop dryrun of autogen.sh from run-cmake-check.sh script
- 02:03 PM Revision 73e4d2d0 (ceph): Merge pull request #11012 from majianpeng/bluefs-buffered-io
- os/bluestore/BlueFS: For logs of rocksdb & bluefs only use directio.
Reviewed-by: Sage Weil <sage@redhat.com> - 02:02 PM Revision 718d6c2a (ceph): Merge pull request #11009 from liewegas/wip-bluestore-keys
- os/bluestore: make onode keys more efficient (and sort correctly)
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:00 PM rbd Backport #17241 (In Progress): jewel: "*** Caught signal" in krbd
- 01:59 PM rbd Backport #17241 (Resolved): jewel: "*** Caught signal" in krbd
- https://github.com/ceph/ceph/pull/11018
- 02:00 PM CephFS Backport #17246 (Resolved): jewel: Log path as well as ino when detecting metadata damage
- https://github.com/ceph/ceph/pull/11418
- 01:59 PM Backport #17245 (Resolved): jewel: tests: scsi_debug fails /dev/disk/by-partuuid
- https://github.com/ceph/ceph/pull/11411
- 01:59 PM CephFS Backport #17244 (Resolved): jewel: Failure in snaptest-git-ceph.sh
- https://github.com/ceph/ceph/pull/11419
- 01:59 PM rbd Backport #17243 (Resolved): jewel: Deadlock in several librbd teuthology test cases
- https://github.com/ceph/ceph/pull/12890
- 01:59 PM rbd Backport #17242 (Resolved): jewel: ImageWatcher: double unwatch of failed watch handle
- 01:57 PM rbd Bug #17223 (Pending Backport): "*** Caught signal" in krbd
- 01:57 PM rbd Bug #17223: "*** Caught signal" in krbd
- https://github.com/ceph/ceph/pull/9517
https://github.com/ceph/ceph/pull/9080
https://github.com/ceph/ceph/pull/9123 - 01:55 PM CephFS Bug #17240: inode_permission error with kclient when running client IO with recovery operations.
- Cluster state at the time:-
ceph -s
cluster ee17af9f-24f1-425e-abd3-d2289102dec1
health HEALTH_ERR
... - 01:49 PM CephFS Bug #17240 (Closed): inode_permission error with kclient when running client IO with recovery ope...
- Steps to reproduce:-
1) With client io running make few osds down and out of the cluster
2) Bring up the osds to ... - 01:52 PM devops Bug #17103: make python3 optional on RHEL 7
- the change on cmake side is posted at https://github.com/ceph/ceph/pull/11015.
- 01:49 PM Revision 7d7a9848 (ceph): cmake: make py3 a nice-to-have
- python3 is not a hard requirement to build ceph, so make it optional.
add an option named "WITH_PYTHON3" which accept... - 01:35 PM Revision 2313079c (ceph): Merge pull request #11017 from ifed01/wip-bluestore-cleanup
- os/bluestore: remove some copy-pastes
Reviewed-by: Sage Weil <sage@redhat.com> - 01:35 PM Revision a192c786 (ceph): tasks: add rebuild_mondb
- * tasks/rebuild_mondb.py: this task
1. removes all store.db on all monitors
2. rebuild the store.db for the first... - 01:22 PM Revision ccd9b5ea (ceph): os/bluestore: remove some copy-pastes
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 01:17 PM Revision d1ab24b0 (ceph): Merge pull request #11011 from liewegas/wip-bluestore-inline-bl
- os/bluestore: fix a few memory utilization leaks and wasters
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 12:49 PM Revision b8a530e3 (ceph): mds: Set mds_snap_max_uid to 4294967294
- Since kernel version 2.6 the Linux kernel supports 32-bit integers
and thus the limit is no longer 65536.
By setting... - 12:47 PM rgw Bug #17239 (Resolved): radosgw-admin period update reverts deleted zonegroup
- start the radosgw without any multisite configuration (default zonegroup and zone will be created)
create a realm , ... - 11:40 AM Revision 7d1d689a (ceph): os/bluestore/BlueFS: For logs of rocksdb & bluefs only use directio.
- Now it use bluefs_buffered_io to control whether use buffer or directio
when write. But in fact for logs of rocksdb &... - 11:30 AM rgw Bug #17164: Orphan data gets leaked on Bucket deletion
- I have submitted a fix for review to fix this problem.
https://github.com/ceph/ceph/pull/10920
- 10:32 AM CephFS Bug #17172 (Pending Backport): Failure in snaptest-git-ceph.sh
- 09:30 AM Revision 88996fb8 (ceph): Merge pull request #10957 from ukernel/wip-17172
- client: properly set inode number of created inode in replay request
Reviewed-by: John Spray <john.spray@redhat.com> - 09:29 AM Revision ab320c97 (ceph): suites/fs: pin java test to ubuntu
- Workaround for #16640
Signed-off-by: John Spray <john.spray@redhat.com> - 09:15 AM Revision b1f417f2 (ceph): Merge pull request #9936 from onyb/wip-ceph-disk-py3
- ceph-disk: Compatibility fixes for Python 3
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Kefu Chai <kc... - 06:14 AM Revision a776f5a6 (ceph): build: drop dryrun of autogen.sh from run-cmake-check.sh script
- Introduced by https://github.com/ceph/ceph/pull/11007.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:57 AM CephFS Bug #17231: CephFS : IOs get terminated while reading/writing on larger files
- the slow requests seem like caused by "dirty page writeback"
09/07/2016
- 10:55 PM Revision 693528d2 (ceph): ceph_detect_init: Add support for Alpine
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 10:52 PM Revision 5fb666c0 (ceph): ceph_detect_init/__init__.py: Define alpine as a supported distro when ...
- Python does not define alpine as a supported dist.
https://hg.python.org/cpython/file/default/Lib/platform.py#l268
... - 10:49 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- >hdparm is not installed, maybe this should be a package dependancy?
It is for rpm based installations.... - 10:32 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- These log views are consistent.
$ md5sum *
8b850c41d84c013d95be15ea10682f05 07_09_16_osd_15.txt
8b850c41d84c013... - 08:45 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi,
I was not running fstrim explicitly it seems 16.04 comes with the below cron.weekly:
root@ceph-osd1:~# cat ... - 05:13 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Note that I edited the last comment.
- 05:00 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Actually Sean,
I changed my mind. If you get the chance to grab the following output from each OSD it may provide ... - 04:32 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi Sean,
Following up for your issue specifically.
>I found that fstrim gets called then the OSD's start to fla... - 03:58 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- This looks normal.
https://github.com/badone/ceph/blob/master/src/os/ObjectStore.cc#L88-L115
No recommendations... - 03:41 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi Brad...
Thanks for all the help. Unfortunately, I do not have further logs. Based on my experience, I do feel t... - 02:39 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Goncalo,
The earliest entry in the log related to the divergent object is this.
{
... - 02:34 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Just an additional comment on the 'pg repair' behaviour.
I confirm what Brad reported in
http://tracker.ceph.co... - 01:10 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi Brad, Guys...
The outputs of ceph-objecstore-tool for each osd involved in the inconsistent pg are available i... - 10:14 PM Revision 265730aa (ceph): os/FuseStore: only flush if dirty
- No need to rewrite the object unless it was changed.
This partially fixes truncate.
Signed-off-by: Sage Weil <sage@... - 10:14 PM Revision b6870a61 (ceph): qa/workunits/objectstore: fix test_fuse.sh
- We switched from @ to # a while back.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:07 PM CephFS Bug #16983 (Resolved): mds: handle_client_open failing on open
- Randy privately confirmed https://github.com/ceph/ceph/pull/8778 resolves his problem. Closing.
- 08:46 PM Revision 662136f7 (ceph): os/bluestore: do not waste memory on cached encoded blobs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:45 PM Revision 9035883c (ceph): buffer: implement buffer::list::reserve(n)
- Make sure we have N bytes of append_buffer reserved. On
a new or cleared list, this allocates exactly that much
runwa... - 08:18 PM CephFS Feature #16973 (Pending Backport): Log path as well as ino when detecting metadata damage
- 02:43 PM CephFS Feature #16973: Log path as well as ino when detecting metadata damage
- Marking for backport because although it's not a bugfix, it's a supportability thing.
- 08:16 PM CephFS Bug #17236 (Resolved): MDS goes damaged on blacklist (failed to read JournalPointer: -108 ((108) ...
http://qa-proxy.ceph.com/teuthology/teuthology-2016-09-05_17:25:02-kcephfs-master-testing-basic-mira/401388/
OSD...- 07:58 PM Revision 9cd042a5 (ceph): os/bluestore/BlueFS: fix Dir memory leak
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:29 PM Revision dbe23c94 (ceph): os/bluestore/BlueFS: do not start racing async compaction
- Compaction is triggred from sync_metadata. If one compaction is
in progress and another thread also calls sync_metad... - 07:26 PM Revision 0ac8ab9d (ceph): os/bluestore: remove faulted debug hackery
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:26 PM Revision b39df47f (ceph): os/bluestore: bits for unit tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:26 PM Revision b9227e3f (ceph): unittest_bluestore_types: resurrect blob and extent_map unit tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:30 PM Revision b53f405e (ceph): os/bluestore: small put_ref cleanup
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:01 PM Documentation #17234: OS reccomendations - jewel updates
- > This page -could be- is missing platform testing data for the Jewel release(s) along with kernel versions.
- 05:57 PM Documentation #17234 (Closed): OS reccomendations - jewel updates
- http://docs.ceph.com/docs/jewel/start/os-recommendations/
This page could be is missing platform testing data for ... - 06:00 PM Revision f8abb628 (ceph): Merge pull request #10978 from chhabaramesh/extent_alloc
- os/bluestore: Hint based allocation in bitmap Allocator
Reviewed-by: Sage Weil <sage@redhat.com> - 05:59 PM Documentation #17235 (Closed): os reccomendations - Xenial 16.04 LTS
- http://docs.ceph.com/docs/jewel/start/os-recommendations/
This page could be improved by included platform testing... - 05:43 PM rbd Bug #16921: rbd-nbd IO hang
- 2016-09-07 17:15:50.931644 7f59527fc700 -1 librbd::AioCompletion: 0x7f5938000cc0 fail: (22) Invalid argument
2016-09... - 02:55 PM rbd Bug #16921: rbd-nbd IO hang
- ...
- 05:28 PM rgw Bug #17052: unittest_http_manager times out
- this is a unit test to detect a bug in old versions of libcurl (pre-7.32), so that's what causes the deadlock here. w...
- 05:04 PM rgw Bug #17052: unittest_http_manager times out
- @Casey could you take a look at this?
- 05:07 PM rgw Backport #16448 (Resolved): hammer: default quota fixes
- 05:06 PM Revision 8f66abd0 (ceph): Merge pull request #10839 from oritwas/hammer-default-quota
- Hammer default quota
Reviewed-by: Daniel Gryniewicz <dang@redhat.com> - 05:06 PM Revision 45084488 (ceph): Merge pull request #11007 from liewegas/wip-autotools-must-die
- remove autotools
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Ali Maredia <amaredia@redhat.com>
Revie... - 05:00 PM Revision 55c8143b (ceph): os/bluestore: drop unnecessary separator between fields
- We have fixed length/order for integer fields and use !
to terminate string fields, so there is no need to use
any ex... - 05:00 PM Revision df17cc9b (ceph): os/bluestore: fix key+name sort wonkiness
- We want to unconditoinally start with the name or key, *then* do < > or =
(and if not =, a trailing name).
Signed-of... - 05:00 PM Revision ef12b513 (ceph): os/bluestore: encode shard id in single byte
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:00 PM Revision 420150d9 (ceph): os/bluestore: don't dirty onode if its size is already at desired offset
- for truncate operation.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 05:00 PM Revision 18c348de (ceph): os/bluestore: remove never reachable asserts
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 04:48 PM Bug #17100 (Pending Backport): tests: scsi_debug fails /dev/disk/by-partuuid
- 04:41 PM Revision b0d1f865 (ceph): buffer: clear append_buffer on clear()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:41 PM Revision c953d27f (ceph): os/bluestore: tunable prealloc size for ExtentMap inline_bl
- Otherwise we eat 4KB for every Onode.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:41 PM Revision bc0de8bc (ceph): Merge pull request #11008 from liewegas/wip-libaio
- test/objectstore/CMakeLists.txt: fix libaio conditional
- 04:40 PM Revision 578668f1 (ceph): test/objectstore/CMakeLists.txt: fix libaio conditional
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:34 PM Bug #17114: tests: ceph-disk-test.py requires vps
- This is different from #17100
- 03:50 PM Revision fba798dc (ceph): remove autotools
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:36 PM Revision 68cf9d82 (ceph): Merge pull request #10963 from liewegas/wip-bluestore-sharded-extent-map
- os/bluestore: shard extent map
Reviewed-by: Allen Samuels <allen.samuels@sandisk.com> - 03:26 PM Revision 3fb6c5c1 (ceph): os/bluestore: instrument transaction count
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:26 PM Revision f69af0b8 (ceph): os/bluestore: instrument onode reshard events
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:26 PM Revision 2d8a145d (ceph): os/bluestore: dump some stats after fsck
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:26 PM Revision fad3d998 (ceph): os/bluestore: assert shared blob cache cleared on split
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:26 PM Revision 7f35725f (ceph): os/bluestore: optimize compress_extent_map
- Only examine the range we just wrote to (and to the left
and right).
Signed-off-by: Sage Weil <sage@redhat.com> - 03:26 PM Revision 6e251cfd (ceph): os/bluestore: fix fsck used_block bitmap
- This has to be block_size bits because min_alloc_size
can vary over mounts.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:26 PM Revision dcc58c9b (ceph): os/bluestore: use block_size for allocator unit
- We need to handle objects written during previous mounts
that may have had a smaller min_alloc_size. Use
block_size,... - 03:26 PM Revision 2df9aa8e (ceph): os/bluestore: make blob_t unused helpers use logical length
- These were taking min_alloc_size, but this can change
across mounts; better to use the logical blob length
instead (t... - 03:26 PM Revision e152e97c (ceph): os/bluestore: instrument big/small writes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:26 PM Revision 4fbb1efd (ceph): os/bluestore: shard extent map
- Rewrote much of the persistence of onode metadata. The
highlights:
- extents and blobs stored together (the blob w... - 03:26 PM Revision ec58b21a (ceph): os/bluestore: make nid and blobid allocation less racy
- We could bump the _max value for a TransContext in it's
prepare state, have it wait for a long time on IO, and
let an... - 03:19 PM Revision b307a643 (ceph): Merge pull request #10973 from wjwithagen/wip-wjw-freebsd-cmake-excludes-2
- cmake: FreeBSD specific excludes in CMakeLists.txt
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:05 PM Revision 2eed1ef1 (ceph): hint in extent_alloc code
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 03:05 PM Revision 89afb56f (ceph): remove wrap argument and handle in wrappers
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 03:05 PM Revision 3c06717a (ceph): Hint argument in alloc_blocks + test case changes
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 02:43 PM Revision 65940220 (ceph): Merge pull request #10996 from jcsp/wip-16973
- mds: log path with CDir damage messages
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:23 PM Revision 4fe06e95 (ceph): Merge pull request #10928 from stiopaa1/rbd_mirror_imagesyncthrottler
- rbd_mirror/ImageSynceThrottler: move struct to .cc
Reviewed-by: Sage Weil <sage@redhat.com> - 02:20 PM Revision e2a75328 (ceph): Merge pull request #10947 from atheism/radosgw-admin-help
- rgw: right parenthesis is missing in radosgw-admin help message on caps
Reviewed-by: Sage Weil <sage@redhat.com> - 02:18 PM Revision b2af4411 (ceph): Merge pull request #10954 from stiopaa1/rgw_rgwrados_removeUnneededClas...
- rgw/rgw_rados.h: remove unneeded class C_Tick
Reviewed-by: Sage Weil <sage@redhat.com> - 02:16 PM Revision 77948303 (ceph): Merge pull request #10967 from stiopaa1/osd_replicatedbackend_moveClasses
- osd/ReplicatedBackend: move classes to cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 02:15 PM Revision 2a5255fc (ceph): Merge pull request #10971 from stiopaa1/osd_replicatedpg_moveContextCla...
- osd/ReplicatedPG: move classes to .cc file
Reviewed-by: Sage Weil <sage@redhat.com> - 02:13 PM Revision 5e7e22bc (ceph): Merge pull request #10979 from wjwithagen/wip-wjw-cephtool-test
- qa/workunits/cephtool/test.sh: fix omission of ceph-command
- 02:13 PM Revision 04405b6c (ceph): Merge pull request #10988 from jazeltq/fix-compile-error
- autogen: Fix rocksdb error when make dist
- 02:02 PM Revision 439cd5e1 (ceph): mds: log path with CDir damage messages
- Previously you just got the inode number, which
wasn't terribly useful for e.g. a missing fragment
object, as you cou... - 01:56 PM CephFS Bug #17231: CephFS : IOs get terminated while reading/writing on larger files
- I don't have any idea what this test does, but your pasted bit includes as output:
> 17:22:57.411 Do you maybe hav... - 11:59 AM CephFS Bug #17231: CephFS : IOs get terminated while reading/writing on larger files
- Yes I ran it on multiple clients, but each client had been mounted with different sub-directories(each with 6 files-1...
- 11:07 AM CephFS Bug #17231: CephFS : IOs get terminated while reading/writing on larger files
- I see several clients in your MDS log. How are the operations in your test split between clients?
It is possible ... - 10:54 AM CephFS Bug #17231 (Resolved): CephFS : IOs get terminated while reading/writing on larger files
- CephFs Environment:
1 MDS node
1 Ceph Kernel Filesystem, Ubuntu 14.04 LTS, kernel version 4.4.0-36-generic
Test ... - 01:48 PM Revision 0f0c16bf (ceph): Merge pull request #10930 from atheism/rgw-lc-fix-sleep-time
- rgw/rgw_lc.cc: fix sleep time according to the error message
- 01:10 PM Revision f337a072 (ceph): krbd: don't segfault if images are unmapped concurrently
- "rbd map c" can die from a NULL dereference on any of this_pool,
this_image or this_snap in wait_for_udev_add():
... - 01:10 PM Revision 2399d4ae (ceph): qa: rbd/simple_big.sh: drop extraneous sudo
- Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
(cherry picked from commit 6643f4d9723e5d9c5195680ac9abb9915ef42a56) - 01:09 PM Revision 472cb29c (ceph): qa: rbd/concurrent.sh: suppress rbd map output
- rbd_map_image() echoes the id of the image and is used in command
substitution:
id=$(rbd_map_image "${image}")
... - 01:09 PM Revision 667d42aa (ceph): qa: rbd: don't modprobe, chown sysfs files or udevadm settle
- This is a followup to 38a572011dbb ("qa: rbd/map-snapshot-io.sh: don't
chown sysfs files") for the rest of the workun... - 01:09 PM Revision 866c3e59 (ceph): qa: rbd/map-snapshot-io.sh: don't chown sysfs files
- /sys/bus/rbd/add_single_major is used if present, so chown'ing
/sys/bus/rbd/add doesn't help. Use sudo on rbd map in... - 11:58 AM Revision 20fc0fec (ceph): cmake: include(SIMDExt) in src/CMakeLists.txt
- as we need to check HAVE_ARMV8_CRC in src/CMakeLists.txt.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 11:52 AM Revision 86f6522d (ceph): mds: trim null dentries proactively
- Instead of leaving null dentries (e.g. left
behind from unlinks) in the cache until they
fall out of the LRU, activel... - 10:48 AM Revision 628d3969 (ceph): crush: make counting of choose_tries consistent
- When we alloc choose map (for crushtool checking), we need to
alloc the tries instead of retries.
Fixes: http://... - 10:48 AM CephFS Feature #17230 (Resolved): ceph_volume_client: py3 compatible
- Manila drivers and their CIs are encouraged to be py3 compatible. Manila's cephfs_native driver uses ceph_volume_clie...
- 10:47 AM RADOS Bug #17229 (In Progress): crushtool will using the out of bound space when testing with "--show-c...
- PR: https://github.com/ceph/ceph/pull/10993
- 10:46 AM RADOS Bug #17229 (Resolved): crushtool will using the out of bound space when testing with "--show-choo...
when we testing the crush rule which could not be mapped successfully under our `choose_total_tries`
it seems to...- 10:44 AM Revision 8ecd55ca (ceph): src/tools/CMakeLists.txt: conditionaly build ceph-client-debug
- - Honor WITH_LIBCEPHFS
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl> - 10:44 AM Revision 2e9809ae (ceph): src/test/objectstore/CMakeLists.txt: conditionaly build tests
- - Honor WITH_AIO tests that depend on bluestore parts
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl> - 10:44 AM Revision 1ce0e75c (ceph): src/pybind/CMakeLists.txt: conditionaly build cython tools
- - honor the WITH_RBD and WITH_LIBCEPHFS flags
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl> - 10:43 AM Revision c7c07da5 (ceph): src/CMakeLists.txt: exclude parts not buildable on FreeBSD
- - FreeBSD does not have keyutils or any kernel type security store
So using secret.c is not really relevant here
... - 09:52 AM Revision 42bf1d0a (ceph): Makfile: Fix rocksdb error when make dist
- Rocksdb delete some files, so we should change another way
to get rocksdb's files.
Currently, if we do not run confi... - 08:32 AM Bug #17228 (Can't reproduce): Hammer OSD memory use very high (EL6)
- We have a small 160TB Ceph cluster used only as a test s3 storage repository for media content.
Problem
Since upg... - 06:53 AM Revision 3942ac4d (ceph): Merge pull request #10972 from wjwithagen/wip-wjw-cmake-resolv
- CmakeLists.txt: use LIB_RESOLV instead of resolv.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:34 AM Bug #15350 (Duplicate): ceph-disk failed on centos in ceph-disk-jewel-distro-basic-mira
- 06:33 AM Bug #15350: ceph-disk failed on centos in ceph-disk-jewel-distro-basic-mira
- The ceph-disk suite must be run on VPS
- 03:36 AM CephFS Bug #17212: Unable to remove symlink / fill_inode badness on ffff88025f049f88
- the mds bugs are fixed by https://github.com/ceph/ceph/pull/8778/commits. they will be included in next jewel release...
- 02:50 AM Revision c2a5e703 (ceph): Merge pull request #10378 from trociny/wip-14738
- librbd: optionally unregister "laggy" journal clients
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:49 AM rbd Bug #17227 (Resolved): exclusive_lock::AcquireRequest doesn't handle -ERESTART on image::RefreshR...
- http://qa-proxy.ceph.com/teuthology/jdillaman-2016-09-06_13:37:26-rbd-wip-jd-testing---basic-smithi/402468/teuthology...
- 02:17 AM Bug #17226: Osd assert failed after large amount of write
- My config:
[global]
auth_service_required = cephx
auth_client_required = cephx
auth_cluster_required = cephx
f... - 02:15 AM Bug #17226 (Rejected): Osd assert failed after large amount of write
- I have a cluster of 120 OSDs, and after the test, 3 OSDs assert failed.
The log is attached. - 12:04 AM Revision a46a18fe (ceph): crush/CrushCompiler.cc:884
- bug fix: index out of range
Signed-off-by: xu biao <xubiao.codeyz@gmail.com>
09/06/2016
- 09:58 PM Revision 025bbc62 (ceph): ceph_test_objectstore: add SyntheticMatrixSharding
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:58 PM Revision 933a1da6 (ceph): ceph_test_objectstore: occasional umount/fsck/mount
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:58 PM Revision 58030cc0 (ceph): ceph_test_objectstore: test shards for longer
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:47 PM Revision ebf289a6 (ceph): Merge pull request #10870 from ceph/wip_build_cls_rbd
- cmake: add dependency from ceph_smalliobenchrbd to cls libraries
Reviewed-by: Jason Dillaman <jdillama@redhat.com>
R... - 08:44 PM rbd Bug #17223 (In Progress): "*** Caught signal" in krbd
- 05:44 PM rbd Bug #17223: "*** Caught signal" in krbd
- Most of the coredumps here are probably #16030 material. Need to backport that fix to jewel.
- 04:32 PM rbd Bug #17223 (Resolved): "*** Caught signal" in krbd
- This is jewel 10.2.3 release
Run: http://pulpito.front.sepia.ceph.com/yuriw-2016-09-05_15:56:10-krbd-master-testin... - 08:35 PM Revision eb3abfcd (ceph): Merge pull request #1153 from ceph/wip-manager-construct
- tasks/ceph: construct CephManager earlier
- 08:20 PM Revision 40df120b (ceph): Merge pull request #10912 from stiopaa1/journal_journaltimer_moveCRemov...
- journal: move JournalTrimmer::C_RemoveSet struct
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:17 PM Linux kernel client Bug #17222 (Resolved): "rbd: map failed: (5) Input/output error" in krbd run
- 08:13 PM Linux kernel client Bug #17222 (Fix Under Review): "rbd: map failed: (5) Input/output error" in krbd run
- https://github.com/ceph/ceph-qa-suite/pull/1167
- 05:39 PM Linux kernel client Bug #17222: "rbd: map failed: (5) Input/output error" in krbd run
- Needs a backport to jewel ceph-qa-suite branch.
- 04:31 PM Linux kernel client Bug #17222 (Resolved): "rbd: map failed: (5) Input/output error" in krbd run
- This is jewel 10.2.3 release
Run: http://pulpito.front.sepia.ceph.com/yuriw-2016-09-05_15:56:10-krbd-master-testin... - 08:16 PM Revision aa1600ec (ceph): Merge pull request #1167 from ceph/wip-17222-jewel
- Backport krbd/unmap fixes
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 07:26 PM Revision 4411d34e (ceph): Merge pull request #1109 from batrick/fs-fuse_default_permissions
- fs: fuse_default_permissions = 0 for kernel build test
Reviewed-by: John Spray <john.spray@redhat.com> - 07:13 PM Revision 33e241e7 (ceph): Add dependencies from ceph_smalliobenchrbd on cls_rbd, cls_journal,
- and cls_lock.
Signed-off-by: J. Eric Ivancich <ivancich@redhat.com> - 07:12 PM Bug #17209 (Rejected): build: ceph/src/librados/librados.cc:47:30: fatal error: tracing/librados....
- 09:22 AM Bug #17209: build: ceph/src/librados/librados.cc:47:30: fatal error: tracing/librados.h: No such ...
- Please close this INVALID bug. One have not the permission to close a bug he created?
- 06:55 PM rgw Bug #16695: radosgw Consumes too much CPU time to synchronize metadata or data between multisite
- new pr: https://github.com/ceph/ceph/pull/10998
- 06:46 PM rgw Bug #13817 (In Progress): RGW does not send HTTP header
- 06:38 PM rgw Bug #17163 (In Progress): Rados object leak
- Folks, could you retest with (at earliest) the latest Hammer version (there have been multiple leak fixes)?
- 06:35 PM rgw Bug #17164 (In Progress): Orphan data gets leaked on Bucket deletion
- 06:32 PM rgw Bug #17159: system user can't copy objects using put method and rgwx-source-zone parameter
- Can you folks add logs and reproducing URL (optionally sanitized)?
- 06:25 PM rgw Bug #16727: s3tests-test-readwrite failed in rados run
- The second log doesn't return 403/forbidden (so looks like different issue)?
- 06:22 PM rgw Bug #17203 (Resolved): rgw: remove EEXIST error msg for ZoneCreate
- 06:20 PM rgw Bug #14208 (Need More Info): rgw: 500 returned on Put Bucket ACL (ECANCELLED/-125)
- Assigning myself. I think we need more context to guide in reproducing (or a reproducer?).
- 06:11 PM rgw Bug #14081 (In Progress): The radosgw-agent cannot unlock, and error code is 404
- 06:08 PM rgw Bug #16828 (Need More Info): radosgw swift interface put object response 500 error?
- 06:02 PM rgw Bug #16854 (In Progress): the usage log record date is 16 hours later than the real operate time...
- 06:02 PM rgw Bug #16408 (In Progress): Creating Bucket failed and can't be deleted.
- 06:00 PM rgw Bug #17111 (In Progress): ERROR: got unexpected error when trying to read object: -2
- 06:00 PM rgw Bug #17186 (In Progress): radosgw keystonev3 token revocation error
- 05:59 PM Revision c97079f3 (ceph): krbd/unmap: put client.0 on a separate remote
- Otherwise a pre-single-major kernel override is a headache,
particularly with non-standard yaml configs.
Signed-off-... - 05:59 PM Revision f507bf42 (ceph): krbd/unmap: override client.0 only
- The unmap test uses one remote, so the end result is the same.
However, overriding the most specific role is nicer an... - 05:59 PM Revision 45116a87 (ceph): krbd/unmap: set tunables to bobtail
- Kernel 3.13, which is used in pre-single-major.yaml test, doesn't
support firefly tunables (default in jewel, up from... - 05:59 PM Revision e7436548 (ceph): krbd/unmap: assert that pre-single-major kernel is installed
- Similarly to how single-major-off.yaml and single-major-on.yaml check
the value of /sys/module/rbd/parameters/single_... - 04:42 PM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- Thank you, Nathan.
Nathan Cutler wrote:
> So, just drop ceph-devel from packages.yaml and you'll be good.
- 04:24 PM Linux kernel client Bug #17221 (Resolved): "Failures: xfs/001 generic/275 generic/225 generic/079" in krbd
- This is jewel 10.2.3 release
Run: http://pulpito.front.sepia.ceph.com/yuriw-2016-09-05_15:56:10-krbd-master-testin... - 04:07 PM CephFS Bug #17105: multimds: allow_multimds not required when max_mds is set in ceph.conf at startup
- Backport: https://github.com/ceph/ceph/pull/10997
- 01:43 PM CephFS Bug #17105 (Pending Backport): multimds: allow_multimds not required when max_mds is set in ceph....
- 04:02 PM Feature #17220 (Resolved): ceph-objectstore-tool: ability to perform filestore splits offline
- See https://github.com/ceph/ceph/pull/10776 for details. This issue is for tracking backports.
- 03:42 PM CephFS Support #17171: Ceph-fuse client hangs on unmount
- Hmm, so if that's resproducible then it sounds like we could reproduce it by killing an MDS, invoking umount, seeing ...
- 02:48 PM CephFS Support #17171: Ceph-fuse client hangs on unmount
- Actually when it becomes responsive - unmount is still hanging and only `kill -9` helps.
- 01:45 PM CephFS Support #17171: Ceph-fuse client hangs on unmount
- To be clear, you're saying that while the server cluster is unresponsive, ceph-fuse hangs on unmount? That is expect...
- 12:59 PM CephFS Support #17171: Ceph-fuse client hangs on unmount
- Actually after several checks it seems like ceph is actually not responding from time to time due to very high load/d...
- 03:39 PM Revision 2676a567 (ceph): Merge pull request #1163 from ceph/wip-kfsx-exclusive-lock
- krbd: enable exclusive-lock feature
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:39 PM Revision 4b000c9f (ceph): Merge pull request #10984 from ceph/wip-kfsx-exclusive-lock
- test/librbd/fsx: enable exclusive-lock feature in krbd mode
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:23 PM Bug #13937: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- We are seeing this on Jewel versions 10.2.2 with RGW data pool on EC (8+3) jerasure with failure domain set to host.
... - 03:23 PM rbd Bug #17219 (Resolved): rbd-nbd: disallow mapping images >2TB in size
- The nbd kernel driver uses a hard-coded 512 byte sector size, resulting in a 2TB block size limit for nbd devices.
- 03:10 PM Revision da9b0e7c (ceph): Merge pull request #10964 from liewegas/wip-bluefs-compaction
- os/bluestore/BlueFS: fix async compaction logging bug
- 02:12 PM Revision 3a036c79 (ceph): Merge pull request #10966 from liewegas/wip-bluefs-runway
- os/bluestore/BlueFS: factor unflushed log into runway calculation
Reviewed-by: Varada Kari <varada.kari@sandisk.com>... - 02:11 PM Revision e6a39aeb (ceph): Merge pull request #10970 from xiexingguo/xxg-wip-honour-alloweio-flag
- os/bluestore: honour allow-eio flag; use global compressor if possible
Reviewed-by: Sage Weil <sage@redhat.com> - 01:49 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- I also collected the data for PG 5.15b
root@ceph-osd3:~# ceph-objectstore-tool --op list --pgid 5.15b --data-path ... - 01:22 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- The below shows a quick diff:
[root@korn ceph]# ll
total 732
-rw-r--r--. 1 root root 239490 Sep 6 14:18 osd17_l... - 01:16 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi,
Not sure if you need the list-omap from the other osd's in scope of that PG but here is is in case:
root@ce... - 11:42 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi,
Interestingly the 'network' issue that I think caused the problem to start with happened again at the same tim... - 12:57 PM Revision 4ccd9949 (ceph): Merge pull request #1160 from ceph/wip-no-btrfs
- suites: switch filesystem tests from btrfs to xfs
- 12:38 PM rbd Bug #17210 (Pending Backport): ImageWatcher: double unwatch of failed watch handle
- 12:38 PM Revision 9a955364 (ceph): Merge pull request #10974 from dillaman/wip-17210
- librbd: potential double-unwatch of watch handle upon error
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 12:29 PM Revision f0134a3d (ceph): tasks/cephfs: test recovery of partial auth update
- ... in ceph_volume_client.
Signed-off-by: Ramana Raja <rraja@redhat.com>
Update test_volume_client.py - 12:22 PM CephFS Bug #17216: ceph_volume_client: recovery of partial auth update is broken
- The reproducer https://github.com/ceph/ceph-qa-suite/pull/1166
- 11:55 AM CephFS Bug #17216 (Resolved): ceph_volume_client: recovery of partial auth update is broken
- I run into the following traceback when the volume_client tries
to recover from partial auth update,
Connecting t... - 12:17 PM CephFS Feature #16973 (Fix Under Review): Log path as well as ino when detecting metadata damage
- https://github.com/ceph/ceph/pull/10996
- 12:07 PM Revision bd3645fb (ceph): mds: s/used_ions/used_inos/
- Signed-off-by: John Spray <john.spray@redhat.com>
- 11:51 AM Revision 9fda6d1c (ceph): Merge pull request #10774 from renhwztetecs/renhw-wip-cephfs-python-umount
- libcephfs: add unmount function in cephfs.pyx
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Ramana Ra... - 11:50 AM Revision 4a3085bc (ceph): Merge pull request #10914 from batrick/mds-no-maxmds
- mds: remove max_mds config option
Reviewed-by: John Spray <john.spray@redhat.com> - 11:48 AM CephFS Bug #17212: Unable to remove symlink / fill_inode badness on ffff88025f049f88
- The complete log file has been uploaded with ceph-post-file under id cd309feb-70b3-4291-b32f-8c559ecd3866
The prob... - 09:41 AM CephFS Bug #17212: Unable to remove symlink / fill_inode badness on ffff88025f049f88
- The SessionMap crash will be related to the "client.4031546 does not advance its oldest_client_tid" message, as with ...
- 09:40 AM CephFS Bug #17212: Unable to remove symlink / fill_inode badness on ffff88025f049f88
- Please can we have the MDS log from the Locker::check_inode_max_size crash?
Is that happening with both the kernel... - 11:04 AM Revision 0358fc09 (ceph): Merge pull request #10922 from ceph/wip-jlayton-statx
- First pile of statx patches
- 11:03 AM Revision a995ddde (ceph): Merge pull request #1164 from SUSE/wip-fix-make-rpm-jewel
- buildpackages: backport make-rpm.sh improvements
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:51 AM Bug #16157 (Resolved): "grep -c 'load_pgs. skipping PG'" fails in suites/rados/singleton-nomsgr/a...
- 09:54 AM Bug #16157 (Fix Under Review): "grep -c 'load_pgs. skipping PG'" fails in suites/rados/singleton-...
- https://github.com/ceph/ceph-qa-suite/pull/1165
- 08:53 AM Bug #16157: "grep -c 'load_pgs. skipping PG'" fails in suites/rados/singleton-nomsgr/all/11429.yaml
- "load_pgs. skipping PG" is in v0.80.0 (69eaad7f8308f21573c604f121956e64679a52a7).
- 10:22 AM Revision b7652e43 (ceph): Merge pull request #1165 from tchaikov/wip-16157
- rados/singleton-nomsgr/all/11429: wait until clean before checking log
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:01 AM Revision 3091fa3b (ceph): test/cephfs: add mount&&unmount test
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 09:56 AM Revision a053ce09 (ceph): tasks/ceph_manager: allow ObjectStoreTool to not revive OSD after done ...
- rebuild_mondb task is not able to offer OSD with any monitor alive. so
self.manager.revive_osd() will always timeout ... - 09:50 AM Revision 3ad90bfb (ceph): rados/singleton-nomsgr/all/11429: wait until clean before checking log
- to make sure that load_pgs() is finished before checking its output
Fixes: http://tracker.ceph.com/issues/16157
Sign... - 09:08 AM Revision 949af79b (ceph): rgw: fix failed to create bucket if a non-master zonegroup has a single...
- If a non-master zonegroup has a single zone, the metadata sync thread not running and
the non-master zonegroup can't ... - 08:32 AM rgw Bug #17215 (Resolved): Unable to suspend a user that is part of a tenant
- I am creating users with a tenant, e.g. "DB0370$mark".
When I try to suspend this user, that succeeds when the use... - 07:24 AM Revision db2b0d8b (ceph): buildpackages/common.sh: use install-deps.sh from jewel
- Significant changes took place between jewel and kraken. This commit ensures
that we use the jewel install-deps.sh to... - 07:23 AM Revision 76fd4623 (ceph): buildpackages/make-rpm.sh: install lsb_release dependencies
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 07:15 AM Revision 00f8378d (ceph): buildpackages/make-rpm.sh: adjust Source0 spec file line on SUSE
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
(cherry picked from commit 67de197ce51613922a9015b554be98b5a7b4c9be) - 07:15 AM Revision 20747172 (ceph): buildpackages: use unadulterated make-dist
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
(cherry picked from commit 29671063f9d2562c4e430ea12ce7e61ddf276f9e) - 07:15 AM Revision 4eee9f58 (ceph): buildpackages: make make-{deb,rpm}.sh aware of cmake
- Fixes: http://tracker.ceph.com/issues/16819
Signed-off-by: Ricardo Dias <rdias@suse.com>
Signed-off-by: Nathan Cutler... - 07:14 AM Revision 4c198241 (ceph): buildpackages/make-rpm.sh: use /etc/os-release
- The lsb_release binary is deprecated and requires installation of packages.
The /etc/os-release file is guaranteed t... - 06:15 AM devops Bug #17214 (Can't reproduce): SUSE build fails when cephfs_java is turned on
- Master build fails with:...
- 02:02 AM rbd Backport #16952 (In Progress): hammer: ceph 10.2.2 rbd status on image format 2 returns "(2) No s...
- 01:06 AM CephFS Bug #16842: mds: replacement MDS crashes on InoTable release
- @John Spray
add an complete MDS(cephfs103) log, and set debug_mds = 30/30
Also available in: Atom