Activity
From 01/21/2014 to 02/19/2014
02/19/2014
- 10:54 PM Revision 1bca9c5c (ceph): v0.77
- 10:14 PM CephFS Bug #6608: samba teuthology dbench failure
- We're still occasional samba test failures, but I haven't diagnosed them carefully enough to know if they're this fai...
- 10:14 PM Revision 40bdcb88 (ceph): osd/,mon/: add (up|acting)_primary to pg_stat_t
- We use pg_stat_t information to determine pg create targeting.
Fixes: #7481
Signed-off-by: Samuel Just <sam.just@ink... - 10:01 PM Revision d78b9b01 (ceph): jenkins: add debugging output to shell script
- When we migrated the Jenkins commands into Git, the exact commands are
no longer visible unless we run with "-x".
Ad... - 09:44 PM Revision c0360077 (ceph): Merge pull request #195 from ceph/wip-7003-wusui
- Add docstrings to the orchestra code. Also fix minor formatting issues
- 09:40 PM Revision 31c27e13 (ceph): Merge pull request #186 from ceph/wip-7369
- Fix #7369: "sed expression must be raw string"
- 09:40 PM Revision e5fe884e (ceph): Merge pull request #186 from ceph/wip-7369
- Fix #7369: "sed expression must be raw string"
- 09:37 PM Revision f3ac7870 (ceph): Fix syntax error in first docstring added.
- 09:34 PM Revision efd59a2a (ceph): Merge pull request #190 from kdreyer-inktank/jenkins
- add jenkins-pull-requests-build script
- 09:26 PM Revision a70e93fc (ceph): Merge pull request #199 from ceph/wip-6540-wusui
- Add docstrings. Fix formatting issues for rgw.py
- 09:26 PM Revision cc3d013e (ceph): Merge pull request #196 from ceph/wip-6541-wusui
- Fix docstrings in radosgw-admin-rest.py
- 09:26 PM Revision 8d85b21c (ceph): Merge pull request #197 from ceph/wip-6535-wusui
- Fix docstrings for task/blktrace.py, peering_speed_test.py, proc_thrashe...
- 09:25 PM Revision f18dcf5b (ceph): Merge pull request #198 from ceph/wip-6539-wusui
- Fix docstrings and minor formatting in task/ssh_keys.py
- 09:23 PM Revision 9f953d42 (ceph): Merge pull request #200 from ceph/wip-6532-wusui
- Fixed task/args.py docstrings.
- 07:23 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
- are you using 3.8 kernel? if you are, please try 3.12 or 3.13
- 01:07 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
- I'm on Ubuntu 13.10 and I've installed the packages distributed with it (ceph-deploy 1.2.3-0ubuntu1 and `ceph` 0.67.4...
- 07:20 PM Revision 10fee0e3 (ceph): Revert "Show hostname instead of IP in errors"
- This reverts commit eafeece243607eef8209eaa8c08eecc7d1098eb1.
I was having problems with my newly-created devstack t... - 07:18 PM Revision 72f260e0 (ceph): Merge pull request #1256 from ceph/wip-librados-ops-and-rvals
- librados c api for object operations and a few bug fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by... - 07:07 PM Revision 0427f615 (ceph): rgw: fix swift range response
- Fixes: #7099
Backport: dumpling
The range response header was broken in swift.
Reported-by: Julien Calvet <julien.ca... - 07:06 PM Revision 2b3e3c83 (ceph): rgw: fix etag in multipart complete
- Fixes: #6830
The etag member variable was not set correctly.
Reported-by: Benjamin Gilbert <bgilbert@backtick.net>
S... - 07:06 PM Revision 859ed33e (ceph): rgw: reset objv tracker on bucket recreation
- Fixes: #6951
If we cannot create a new bucket (as it already existed), we need to
read the old bucket's info. However... - 07:03 PM Revision 53de6412 (ceph): radosgw-admin: don't generate access key if user exists
- Fixes: #6936
We want the user creation operation to be idempotent, so if user already
exists don't generate a new acc... - 06:09 PM Revision d7ab4244 (ceph): v0.67.7
- Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
- 05:56 PM Revision f0bfff11 (ceph): add jenkins-pull-requests-build script
- Move our Jenkins pull requests build script out of Jenkins' database and
into Git so that we can have greater visibil... - 05:40 PM Revision 9e8882e0 (ceph): BackedUpObject::get_xattr() pass function parameter by reference
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:37 PM Revision 53b36898 (ceph): TestRados.cc: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:35 PM Revision 86b08796 (ceph): ErasureCodeBench: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:34 PM Revision 200ebb9b (ceph): ceph_erasure_code.cc: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:32 PM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
- aa110af991e6d637b30d740af46f3dc2168cde01
- 03:19 PM Bug #7482: primary affinity crash in OSDMap on osd
- wip-copyget
- 11:42 AM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
- 05:32 PM Revision e6772c76 (ceph): RGWObjManifest: prefer prefix ++/--operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:30 PM Revision 42e6da7b (ceph): ReplicatedPG: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:26 PM Revision 29c4abd8 (ceph): OSD: use !empty() instead of size() > 0
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:21 PM rgw Bug #7375 (Fix Under Review): s3_user_quota.pl fails
- 05:20 PM rgw Bug #7375: s3_user_quota.pl fails
- This is the same issue as 7374.
- 02:16 PM rgw Bug #7375: s3_user_quota.pl fails
- This appears to be a problem in the 7375 pl script. I am taking it.
- 05:21 PM rgw Bug #7374 (Fix Under Review): s3_multipart_upload.pl fails
- I have pushed a change for this.
- 02:15 PM rgw Bug #7374: s3_multipart_upload.pl fails
- This appears to be two problems in the s3_multipart_upload.pl script.
I am taking this. - 05:17 PM Revision be857274 (ceph): PG: use !empty() instead of size() > 0
- [src/osd/PG.cc:543]: (performance) Possible inefficient checking
for 'actingbackfill' emptiness.
[src/osd/PG.cc:148... - 05:09 PM Revision f23ab4af (ceph): RPCRecPred: use !empty() instead of size() >= 1
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:05 PM Revision 0626df90 (ceph): KeyValueStore: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:03 PM Revision 76c17239 (ceph): KeyValueStore: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:02 PM Revision ede614a7 (ceph): FileStore: use !empty() instead of size()
- [src/os/FileStore.cc:3635]: (performance) Possible inefficient checking
for 'omap_set' emptiness.
Signed-off-by: D... - 04:59 PM Revision eaf66967 (ceph): DBObjectMap: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:57 PM Revision 0bf0ec0f (ceph): OSDMonitor: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:55 PM Revision 31b4107a (ceph): OSDMonitor: use !empty() instead of size() > 0
- [src/mon/OSDMonitor.cc:730]: (performance) Possible inefficient checking
for 'osd_weight' emptiness.
Signed-off-by... - 04:53 PM Revision a1412bdf (ceph): MDCache: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:51 PM Revision 4a48d8ed (ceph): CrushWrapper::is_valid_crush_loc(): pass function parameter by reference
- [src/crush/CrushWrapper.cc:1412]: (performance) Function parameter 'loc'
should be passed by reference.
Signed-off... - 04:07 PM Bug #7423: erasure code: ./rados get retrieves a larger object
- The last call will end with abort()...
- 01:02 PM Bug #7423: erasure code: ./rados get retrieves a larger object
- ...
- 10:24 AM Bug #7423 (In Progress): erasure code: ./rados get retrieves a larger object
- 06:00 AM Bug #7423: erasure code: ./rados get retrieves a larger object
- crashes on master as of today
- 03:41 PM Revision 3f68a5ca (ceph): CrushWrapper: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:38 PM Revision dd71051a (ceph): PGLog.h: prefer prefix ++operator for non-trivial iterator
- [src/osd/PGLog.h:363]: (performance) Prefer prefix ++/-- operators for
non-primitive types.
[src/osd/PGLog.h:375]: ... - 03:24 PM Revision 8488e710 (ceph): Client: remove a std::string::c_str() calls
- [src/client/Client.cc:6821]: (performance) Passing the result of c_str() to a
function that takes std::string as ar... - 03:17 PM Revision 1099e255 (ceph): common/config.cc: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:13 PM Revision c7dfdfdc (ceph): str_map.cc: prefer prefix ++operator for non-trivial iterator
- [src/common/str_map.cc:55]: (performance) Prefer prefix ++/-- operators
for non-primitive types.
Signed-off-by: Da... - 03:10 PM Revision 7da714af (ceph): Client.cc: use !empty() instead of size()
- [src/client/Client.cc:2275]: (performance) Possible inefficient
checking for 'cap_snaps' emptiness.
[src/client/Cli... - 02:40 PM Bug #7471: ec pools copyfrom broken
- wip-copyget
- 02:20 PM Revision fd08b09f (ceph): ceph_argparse.cc: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:15 PM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
- 11:41 AM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
- Mon uses acting[0] to send create messages. More importantly, pg_stat_t does not include acting_primary or up_primar...
- 02:13 PM Revision 1d1392dd (ceph): Monitor: pass function parameter by reference
- [src/mon/Monitor.h:619]: (performance) Function parameter 'param_str_map'
should be passed by reference.
Signed-of... - 02:05 PM Revision ab45d44a (ceph): BarrierContext: prefer prefix ++operator for non-trivial iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision 4adcfa59 (ceph): BarrierContext: reduce scope of 'done' variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:54 PM Revision 19dad031 (ceph): MonClient: pass function parameter by reference
- [src/mon/MonClient.h:412]: (performance) Function parameter 'mon_name'
should be passed by reference.
Changed also... - 01:40 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
- This is already done (CORS).
- 01:34 PM Feature #7484 (New): better wording when authentication fails
- After having a mismatch for the client.admin.keyring in a new host that I needed to get a monitor running I was getti...
- 01:34 PM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
- 01:33 PM rgw Tasks #5121 (Closed): bump up librados version
- Closing this one.
- 01:33 PM rgw Feature #5506 (Resolved): rgw: use Keystone to authenticate S3 requests
- Done by Roald van Loon, commit:a200e184b15a03a4ca382e94caf01efb41cb9db7
- 01:30 PM rgw Bug #6710 (Resolved): radosgw init script does not exit 1 and tell the user if the hostname does ...
- This was fixed, commit:0c610918c4ebd6fc1376027cfe6425cfdcfa0245
- 01:29 PM devops Bug #7483 (Rejected): ceph-deploy should fetch keyrings always
- If keyring files exist in the cwd and they are dated/wrong ceph-deploy will say it has them and will not attempt to r...
- 01:28 PM rgw Feature #5136 (Closed): rgw: revise user stats
- Yeah, I have no idea what this issue is about. Now, considering that user stats have actually been revised for the us...
- 01:26 PM rgw Bug #6733 (Closed): rgw readwrite test fails on next branch
- There's a good chance that this was #7030. Closing.
- 01:24 PM rgw Feature #4365 (Resolved): rgw: allow setting wildcard keystone role
- This was merged long ago, commit:8078e9684e7200db582cab02e0bf5ead557133dd
- 01:05 PM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
- Fix looks fine to me. Can you sign-off it?
- 10:29 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- subusers are only relevant for the swift case, and the regular access-key/secret combination does not apply to them. ...
- 10:21 AM rgw Bug #6936 (Fix Under Review): radosgw-admin allows same user to be created multiple times
- 10:19 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
- So these packages were on the DVD (iso downloaded from https://rhn.redhat.com/rhn/software/channel/downloads/Download...
- 10:11 AM rgw Bug #7099 (Fix Under Review): Strange Comportments with media files
- 09:35 AM rados-java Bug #7479 (Won't Fix): Test failed in rados-dumpling-testing-basic-plana
- Logs are in - qa-proxy.ceph.com/teuthology/teuthology-2014-02-18_19:00:09-rados-dumpling-testing-basic-plana/89421
... - 08:27 AM rgw Bug #6830 (Fix Under Review): S3 CompleteMultipartUploadResult has empty ETag element
- 08:08 AM rgw Bug #6951 (Fix Under Review): rgw: bucket re-create fails when cache is disabled
- 08:06 AM Bug #7451: updatedb will index /var/lib/ceph
- This should also be reported to mlocate upstream (at Fedora) and to Red Hat for RHEL 7.
Here's the upstream update... - 07:53 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
- This was an issue with the osd, fixed by commit:2795339d3632df975486d51e69762f9f567fb43d.
- 06:20 AM Revision 314116e2 (ceph): PG: insert into stray set if !us_up() && !is_acting()
- This is simpler than checking actingbackfill
since it may not yet be filled in.
Fixes: #7470
Signed-off-by: Samuel J... - 06:11 AM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
- crashes, investigating why
- 05:10 AM Revision a33874d0 (ceph): Merge pull request #1257 from ceph/wip-agent
- osd: a few agent fixes
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:09 AM Bug #7445 (Rejected): missing feature bit ( next )
- LD_LIBRARY_PATH was set to /usr/local/bin which contained an old version of the ceph libraries, causing the problem
- 05:05 AM Revision 0af73755 (ceph): osd/ReplicatedPG: strengthen agent_work assertions
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:05 AM Revision a40cd507 (ceph): osd/ReplicatedPG: load older HitSets into memory
- If our evict_mode is non-idle, load older HitSets into memory in the agent
work thread.
Signed-off-by: Sage Weil <sa... - 05:05 AM Revision a5c5d924 (ceph): osd/ReplicatedPG: EOPNOTSUPP on hit_set_get on non-replicated pools
- We need to use the async read stuff for this to work.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:24 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Just a note, bug itself is very unlikely to reproduce in a short times (one crash per 1k VM instances per month or so).
- 03:46 AM Revision 1d907c60 (ceph): OSD: consider up/acting primary for new intervals
- Both acting_up_affected and start_peering_interval need
to consider primary changes as well as acting/up changes.
Fi... - 02:42 AM Revision afbd58ea (ceph): rgw: don't try to read bucket's policy if it doesn't exist
- It's going to fail anyway, just build a default policy.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:35 AM devops Feature #7475 (Rejected): ceph-disk: prepare should be idempotent
- If the target device / directory is already prepared exactly as required, ceph-disk prepare should return true with a...
- 12:43 AM Revision 3ed68eb9 (ceph): rgw: return error if accessing object in non-existent bucket
- Fixes: #7064
Instead of trying to access the object, which is impossible as we don't
even have a proper bucket info. ...
02/18/2014
- 11:43 PM Revision b0dcc798 (ceph): radosgw-admin: gc list --include-all
- A new option to the radosgw-admin gc list command that dumps *all* gc
entries, and not just the expired ones. This is... - 11:38 PM Revision 1ff0eefe (ceph): Merge pull request #1259 from ceph/wip-6677
- rgw: add compatibility for MultipartUpload
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 11:37 PM Revision a2c195d8 (ceph): Merge pull request #1258 from ceph/wip-rgw-gc
- radosgw-admin: gc list --include-all
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 11:07 PM CephFS Bug #6608: samba teuthology dbench failure
- still see the issue ?
- 10:21 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- 04:15 PM Bug #7470: ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- 04:13 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- wip-strays
- 09:49 PM Revision b9e1341f (ceph): rados/thrash: add ec-radosbench workload
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:45 PM Revision 386650d9 (ceph): rados/thrash: add ec workloads
- Adds ec workloads for snaps, small objects, read-write.
copy-from is not yet enabled.
Signed-off-by: Samuel Just <s... - 09:41 PM Revision 82cf9795 (ceph): Merge pull request #1261 from ceph/wip-7463
- ceph_rest_api.py: don't fail if no up OSDs found on startup
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:25 PM Revision 609f4c56 (ceph): Throw a Timeout exception on timeout.
- Signed-off-by: Mike Lundy <mike@fluffypenguin.org>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:19 PM Revision e3715652 (ceph): task/: add ec_pool and append to rados.py
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:19 PM Revision 2718dbc3 (ceph): radosbench: simplify pool creation and add ec_pool support
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:11 PM Revision 3fb6e258 (ceph): test/rgw: manifest unitest
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:11 PM Revision b3ce1889 (ceph): cls/rgw: fix debug output
- print the correct error value
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:11 PM Revision 19754413 (ceph): dencoder: fix for new rgw manifest code
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:11 PM Revision da64bf70 (ceph): rgw: scalable manifest object
- Define a new manifest structure. The idea is that the manifest defines a
set of rules for structuring the object part... - 09:07 PM Revision c5d3bdf7 (ceph): Merge pull request #1214 from ceph/wip-rgw-manifest-2
- Wip rgw manifest 2
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:07 PM Revision db88e7f3 (ceph): ceph_rest_api.py: don't fail if no up OSDs found on startup
- allow find_up_osd() to return None, and have caller check for it
Fixes: #7463
Signed-off-by: Dan Mick <dan.mick@inkt... - 08:34 PM Revision 0dc4309b (ceph): librados: add read to c object operation api
- Do the usual bufferlist to buffer conversion in a callback from the
objecter before the librados user gets called.
S... - 08:34 PM Revision 2543cde7 (ceph): librados: add exec to the c object operations api
- Add two versions: one that allocates a buffer of the appropriate
length for the user, but relies on the user to free ... - 08:34 PM Revision f68b706e (ceph): Objecter: add a way to chain callbacks
- The librados C api needs to do extra things like converting c++ data
structures or setting lengths, but some objecter... - 08:34 PM Revision 242a6c85 (ceph): librados: add read xattr functions for c object operations
- Only implement string xattr comparison by since integer xattr
comparison assumes ceph-encoded integers in little-endi... - 08:34 PM Revision 995fea9a (ceph): librados: add omap object operations to the c api
- Create an iterator type similar to XattrIter for returning results.
It just wraps the std::map to preserve sorting.
... - 08:34 PM Revision bac7bb64 (ceph): librados: bump version number
- This covers the many recent changes leading up to the firefly release,
including the c object operations api.
Signed... - 08:34 PM Revision 7a760337 (ceph): packaging: add test programs for librados c object operations
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 08:34 PM Revision 4b229f71 (ceph): qa: add librados c object operations tests to librados test script
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 08:34 PM Revision e550ad79 (ceph): ReplicatedPG: avoid undefined behavior in xattr comparison
- Reading past the end of a pointer returned by string.data() in c++98
is undefined. While we're fixing this, also allo... - 08:34 PM Revision 77436989 (ceph): ReplicatedPG: don't copy the ops vector into OpContext
- There's no need to copy it, and if we refer to the same vector from
the original MOSDOp, we can modify rvals for indi... - 08:34 PM Revision 1d661ca9 (ceph): ReplicatedPG: set individual osd op rvals
- This takes care of things that can fail before transaction is
executed, like omap comparison. Getting individual rval... - 08:34 PM Revision 18f08cd9 (ceph): ReplicatedPG: clear osd op reply output for writes
- Since the vector of OSDOps used by the reply is the same
as the one processed by do_osd_ops() now, any output data
ne... - 08:34 PM Revision bfbfcd6e (ceph): ReplicatedPG: fix successful write condition
- ctx->modify no longer implies that the operation is a write,
if it ever did. These days op->may_write() is checked re... - 08:34 PM Revision 7a019b38 (ceph): test/librados: remove unused lines and fix return code for cmp guards
- Now that return values are actually set by the osd and client, fix up
the tests that were checking the old behavior.
... - 08:34 PM Revision 9630f2f0 (ceph): test/librados: create general test case classes
- Using a test case allows us to remove a boatload of boilerplate code
in all the tests, and focus them more on what th... - 08:34 PM Revision 8d4a5fd5 (ceph): test/librados: add a connect_cluster() helper
- This mirrors the c++ version, connect_cluster_pp(), and removes the
same code from create_one_pool().
Signed-off-by:... - 08:34 PM Revision d3c6f171 (ceph): test/librados: use connect_cluster_pp() instead of duplicating it
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 08:34 PM Revision c6d8d0ef (ceph): test/librados/cmd: remove unnecessary pool creation
- Several tests here don't use the pool at all.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:34 PM Revision 5497e1cb (ceph): test/librados: use a test case instead of duplicating code everywhere
- These tests don't have any special requirements on their ioctx and
pools, so they can also run much faster by using d... - 08:34 PM Revision ae072ac2 (ceph): test/librados: use standard rados test case for snapshot tests
- Split these into two categories, self-managed and pool snapshots,
since they are mutually exclusive for a single pool... - 08:34 PM Revision 5276e3cc (ceph): test/librados: refactor setup/teardown in tiering tests
- These tests can either use the standard RadosTest, with one pool, or a
new test case with two pools.
The new test ca... - 08:34 PM Revision c61ba410 (ceph): test/librados: add ObjectReadOperation tests
- These will help prevent regressions and demonstrate what should be
expected by the c api.
Signed-off-by: Josh Durgin... - 08:34 PM Revision e255bf58 (ceph): librados: add section docs for object operations
- The doxygen end section of watch notify was accidentally moved when
these were added, so fix that at the same time.
... - 08:34 PM Revision 50ca88a1 (ceph): librados: add some comments about constants in librados.h
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 08:34 PM Revision 7f1f0b55 (ceph): librados: remove constant for CMPXATTR_NOP
- This constant was just added in the public header to match the
operations in rados.h, and was not included in a stabl... - 08:34 PM Revision 4f4121ae (ceph): librados: add global op flags to the c api
- The c++ api did not include these in the sync versions of the calls,
so add a flags argument to the IoCtxImpl functio... - 08:34 PM Revision bc03fbb4 (ceph): librados: add individual op flags for c write operations
- Move flag validation to a static function so it can be shared with the
c++ api. Refer to the new C constants from the... - 08:34 PM Revision 770942aa (ceph): librados: add exec to the c write operations api
- Nothing special needed here, just copying the input buffer and passing
things through. Don't allow output data since ... - 08:34 PM Revision 6094e437 (ceph): librados: add simple atomic read operations to c api
- stat, assert_exists, and set_flags are simple and need no extra
infrastrucutre.
Signed-off-by: Josh Durgin <josh.dur... - 08:34 PM Revision 6503f21a (ceph): Objecter: add a context argument to ObjectOperation::read()
- The c api will need this to be able to set the output buffer length
and potentially copy from bufferlist to buffer.
... - 08:34 PM Revision abca34aa (ceph): Objecter: keep ObjectOperation rval pointers for writes
- Just before sending an op, prepare_mutate_op() is called, creating a
new Op. prepare_read_op() already copied over al... - 08:34 PM Revision 6273ba4a (ceph): test/librados: move test.cc into its own library
- This way it doesn't have to be compiled many times, and it's easier
to add new general functionality to new files wit... - 08:34 PM Revision 393a2021 (ceph): Merge pull request #1227 from ceph/wip-7394
- Improve the OSD and generic monitor timeout mechanisms
Reviewed-by: Sage Weil <sage@inktank.com> - 07:48 PM Bug #7469 (Resolved): ENXIO on ec pool write
- 1d907c60d7628429292917fbabf61d09ef8dfa6f
- 04:15 PM Bug #7469: ENXIO on ec pool write
- 04:12 PM Bug #7469 (Resolved): ENXIO on ec pool write
- testing wip-primary
- 07:45 PM rgw Bug #7374: s3_multipart_upload.pl fails
- Stopping the teuthology run and running the commands manually reveals the following:...
- 06:56 PM Revision 43b5cf97 (ceph): Merge remote-tracking branch 'upstream/wip-ecbackend-for-review'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:40 PM rgw Bug #7064 (Fix Under Review): S3 request to non-existent object in non-existent bucket results in...
- 05:09 PM rbd Bug #6480 (Need More Info): librbd crashed qemu-system-x86_64
- ...and now there's a new similar instance, this time on rhel:...
- 12:54 PM rbd Bug #6480 (Can't reproduce): librbd crashed qemu-system-x86_64
- 04:22 PM Revision 45a782ff (ceph): Merge pull request #1255 from ceph/wip-cache-perf
- osd: add perfcounters for new cache and agent events
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 04:18 PM Bug #7471 (Resolved): ec pools copyfrom broken
- 03:46 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
- Moving to the ceph project since any scrub errors are general rados problems.
- 03:33 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
- Yuri Weinstein wrote:
Logs - qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-master-testing-basic-... - 03:30 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
- There are several of those.
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-maste... - 03:46 PM rgw Feature #6677 (Resolved): rgw: add compatibility for MultipartUpload
- Fixed, commit:5a44e178e4e5503c9edf0da15a6b4ec968d1184d
- 03:10 PM rgw Feature #7467 (Resolved): Make radosgw work with multiple hostnames
- A ceph user has a situation in which they would like to switch to a new hostname for accessing the gateways. At the t...
- 02:47 PM Revision 4c930a0a (ceph): Revert "Capture stderr and include in CommandFailedError"
- This reverts commit d0a434923100dd16548e5f76eaffa5462c4b91d4.
- 02:39 PM rgw Bug #7271 (Fix Under Review): container create via swift doesn't register ACL
- 09:32 AM rgw Bug #7271: container create via swift doesn't register ACL
- 02:30 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
- commit:609f4c56718d8279895b02b8163bbe1976c02bfb
- 02:21 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
- The recently added timeouts for librados should result in a specific exception type in the python bindings.
- 01:18 PM rgw Feature #6339 (Resolved): rgw: compact manifest data
- Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41
- 01:17 PM rgw Feature #6338 (Resolved): rgw: better manifest scaling
- Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41
- 01:07 PM Bug #7463 (Fix Under Review): ceph-rest-api fails to start with no OSDs up
- No reason not to start. This appears to fix it:...
- 11:26 AM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
- ceph-rest-api fails to start id it can find no up OSDs:
osdid = find_up_osd(app)
File "/usr/lib/python2.6/sit... - 12:55 PM rbd Bug #5488 (Need More Info): librbd: deadlock in image refresh
- 12:54 PM Revision c93f14f2 (ceph): filestore_idempotent: filestore -> objectstore path change
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:53 PM rbd Bug #5876 (New): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->n...
- 12:52 PM rbd Bug #7385: Objectcacher setting max object counts too low
- 12:51 PM Revision 150e87a1 (ceph): osd: l_osd_tier_whiteout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision dbec1096 (ceph): osd: l_osd_tier_[dirty|clean]
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision d1a185bd (ceph): osd: l_osd_agent_{wake,skip,flush,evict}
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision 4bee6ff1 (ceph): osd/ReplicatedPG: clean up agent skip debug output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision 4b0a0a10 (ceph): osd: l_osd_copyfrom
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision c45a477e (ceph): osd: l_osd_tier_[try_]flush[_fail]
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision 2d5371dd (ceph): osd: l_osd_tier_evict
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:45 PM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
- This was observed on a 3.11 ubuntu kernel:...
- 12:40 PM rgw Bug #6152 (Resolved): New S3 auth code fails when using response-* query string params to overrid...
- backported in commit:4e47a003bb3adcee690067d4037c248a93023c20 a while ago
- 12:37 PM Feature #7464 (Rejected): Backport appropriate pieces of #7394, #7395
- We put some fixes for OSDs overwhelming the monitor into master; now they need to get backported to Dumpling.
- 12:36 PM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
- Merged into master in commit:393a202198fbe67e7c4456d18c19fdef29305b5e
- 11:02 AM Feature #7149 (Resolved): EC: missing_loc should be maintained until the object is no longer degr...
- 11:01 AM Feature #7149 (Closed): EC: missing_loc should be maintained until the object is no longer degraded
- 11:00 AM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
- 11:00 AM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7366 (Resolved): EC: scrubbing
- 11:01 AM Feature #7366: EC: scrubbing
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
- Not desirable for final design
- 11:00 AM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #6438 (Resolved): EC: implement EC client IO
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #6437 (Resolved): EC: implement ECBackend recovery
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 09:31 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
- Fixed, commit:04b1ae466e280568656f8effb031b01505077c6b
- 09:29 AM rgw Bug #7346 (Pending Backport): An unfound object as part of multi-object delete should return dele...
- A fix was pushed, commit:8ca3d95bf633ea9616852cec74f02285a03071d5.
- 08:54 AM Bug #7451: updatedb will index /var/lib/ceph
- Sage Weil wrote:
> I'm not sure the init script is the place to do it.. maybe the package postinst?
postinst is n... - 04:12 AM Revision 11f288e5 (ceph): Objecter: track primary explicitly to detect changing primaries
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 5e727bfe (ceph): RadosModel: only output if missing header is actually a problem
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 7772014a (ceph): OSD,PG: pass through EC messages
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision ae827cfe (ceph): osd_types: add swap, claim_append to ObjectModDesc
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 258af5eb (ceph): buffer: allow caller to initialize bufferhash state
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 7731a949 (ceph): ObjectStore: add bufferlist/string getattr
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 33c38301 (ceph): osd/ECUtil: add ec encode/decode util helpers
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 45b6c59e (ceph): osd/ECTransaction: add type encapsulating EC transaction
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 792f0a85 (ceph): ECBackend: flesh out ECBackend implementation
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision b90584a8 (ceph): osd/: instantiate the right backend based on pool
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision bc31c4b3 (ceph): ReplicatedPG: add some debugging if waiting_for_commit is non-empty
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision f0b69b38 (ceph): osd/: replace bufferptr with bufferlist for attrs in recovery
- Now we won't have to keep converting back and forth!
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:12 AM Revision 1835c29f (ceph): ReplicatedBackend: factor out be_deep-scrub
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 26745ca8 (ceph): PGBackend/ReplicatedBackend: move the backend agnostic code into PGBack...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 510585b7 (ceph): PGBackend/ReplicatedBackend: factor out logical to ondisk size mapping
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision ca323ff6 (ceph): ReplicatedPG: fix size checking for ECBackend pools
- Allow the backend to adjust the logical object size before
checking against the ondisk size.
Signed-off-by: Samuel J... - 04:12 AM Revision 0661d802 (ceph): PGBackend: make getattrs virtual
- This way, the backend can choose to filter private attrs.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:12 AM Revision e8820ac4 (ceph): src/osd/: add ECBackend stubs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 6cd64a50 (ceph): messages,osd: add EC messages and associated types
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 5db3b2dc (ceph): osd/: extend pg_interval_t to include primary
- Otherwise, we cannot correctly determine up_from/up_thru for
old intervals. Also, we need this information to determ... - 04:12 AM Revision 2d3205ff (ceph): PG: skip CRUSH_ITEM_NONE in acting set in various places
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 5a8c0bb9 (ceph): os/: allow objects with NO_GEN but non-NO_SHARD shard
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 74b8a0c0 (ceph): PG,PGBackend: expose acting and backfill_targets
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision facec765 (ceph): PGBackend: add some additional helpers.
- ECBackend's primary specific logic mostly won't treat the
primary shard specially, so it'll be handy to have primary
... - 04:12 AM Revision 8b33d60f (ceph): PG: allow PGBackend to set criteria for PG up-ness
- ECBackend needs to be able to require that a readable
set of the most recent interval to write be available
in order ... - 04:12 AM Revision 84e2f39c (ceph): PG,ReplicatedPG: Generalize missing_loc for ECBackend
- Prior to EC pools, unfound => missing. Now, unfound (unreadable,
really) is dependent on the PGBackend requirements ... - 04:12 AM Revision 0b180e6a (ceph): PG::discover_all_missing: request a FULLLOG
- Otherwise, we cannot correct for divergent objects in the missing
set.
Signed-off-by: Samuel Just <sam.just@inktank.... - 04:12 AM Revision 41e19453 (ceph): PG: refactor calc_acting to handle pg_shard_t changes
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 285cf772 (ceph): PG: introduce calc_ec_acting
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 109b3c9e (ceph): OSDMap: fill in get_primary_shard
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 904704ac (ceph): OSDMap: handle CRUSH_ITEM_NONE in acting sets
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 9d8be1b0 (ceph): Objecter: handle primary other than acting[0]
- EC pool particularly might have CRUSH_ITEM_NONE as acting[0] which
is not a valid osd.
Signed-off-by: Samuel Just <s... - 04:12 AM Revision 035d6cc2 (ceph): osd/: refer to pg by spg_t and replica by pg_shard_t
- We may have multiple pg shards on the same osd for an
ec pool. Thus, replicas must be referred to by <osd, shard>
an... - 04:11 AM Revision 5d01f88c (ceph): ReplicatedBackend/PGBackend: move objects_* methods into PGBackend
- These also are unchanged in ECBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:11 AM Revision 761f0b1e (ceph): PGBackend: use whoami_shard().shard in rollback*, objects*
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:11 AM Revision 31b7937b (ceph): PGBackend/ReplicatedBackend: move temp handling into PGBackend
- Temp handling is also the same in ReplicatedBackend as in ECBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:11 AM Revision fa980644 (ceph): ReplicatedBackend: excise OSDService*
- This should eventually make it easier to mock out a PGBackend::Listener.
Signed-off-by: Samuel Just <sam.just@inktan... - 04:11 AM Revision 8b46dd1d (ceph): messages/: include shard information in various pg messages
- We can no longer use the messenger source information to determine
the origin of the message since an osd might have ... - 04:11 AM Revision f678aefd (ceph): TestPGLog: remove test with DELETE op with prior_version = eversion_t()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:11 AM Revision 1c93e03f (ceph): osd/: Add a shard parameter to SnapMapper to handle multiple pg shards
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:11 AM Revision f2826fa2 (ceph): src/osd: pass in version to recover to recover_object
- Otherwise we need to do some annoying contortions to
get it out of the missing sets.
Signed-off-by: Samuel Just <sam... - 04:11 AM Revision 44b43df4 (ceph): ObjectStore: use ghobject_t for setattrs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:11 AM Revision 4a259516 (ceph): osd_types: introduce spg_t, pg_shard_t
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:11 AM Revision 8ca875b6 (ceph): PGBackend/ReplicatedBackend: move rollback methods into PGBackend
- These will end up essentially unchanged in ECBackend as it turns out.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:10 AM Revision 09d611d2 (ceph): PGLog::merge_old_entry: simplify the oe.version > ne.version case
- If ne.version < oe.version, the correct answer is to rollback oe.version
if possible regardless of what the entries a... - 12:41 AM Revision 5f8eedf0 (ceph): rados/thrash: test rados against cache pool with agents
- Run rados model against a pool with target_max_objects set so that the
tiering agent is working against us.
Signed-o... - 12:26 AM Revision e6a1122b (ceph): osd: l_osd_tier_promote
- Signed-off-by: Sage Weil <sage@inktank.com>
02/17/2014
- 11:56 PM RADOS Bug #7460 (New): librados: no test for c api's global ops flags
- This could be tested by creating a binary just for testing that enables logging, sets some global op flags, and grepp...
- 11:15 PM Revision 5bc92ece (ceph): Merge pull request #1128 from ceph/wip-dirfrags
- Fixes for mds cluster + directory fragments
- 10:25 PM Revision d116e55f (ceph): PG: just ignore rollbacks on objects we have already failed to rollback
- The relevant changes to missing and/or the filestore will have
already been made.
Signed-off-by: Samuel Just <sam.ju... - 10:25 PM Revision fd9da00e (ceph): ReplicatedPG: take snapset_obc write lock where appropriate
- Otherwise, we might read it for backfill before it's fully created
on a peer.
Signed-off-by: Samuel Just <sam.just@i... - 10:25 PM Revision 0e7b10ac (ceph): PG::remove_snap_mapped_object: use pg_whoami.shard
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 3650da69 (ceph): ErasureCodeJerasure: fill in decoded if all shards are included
- This causes it to match minimum_to_decode.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:24 PM Revision 13a41e14 (ceph): FileStore: permit NULL onreadable callback
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision d8b6d4c1 (ceph): ReplicatedPG: release_op_ctx_locks in all-applied, not all-committed
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision b3b2bab4 (ceph): ReplicatedPG: handle xattr cache on rollback and delete_head
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 17e6ecc8 (ceph): ReplicatedPG: find_object_context debugging: output oi
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision f020ce90 (ceph): ReplicatedPG:: remove_snap_mapped_object already removes the object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 643b6a50 (ceph): ReplicatedPG,osd_types: seperate require_rollback from ec_pool
- It's handy to allow a pool to answer false to ec_pool() and
true to require_rollback() in order to allow a replicated... - 10:24 PM Revision d687ed96 (ceph): ReplicatedPG: take clone write lock as well in make_writeable
- Otherwise, we might start backfilling the clone before the op is
complete.
Signed-off-by: Samuel Just <sam.just@inkt... - 10:24 PM Revision da4652c9 (ceph): ReplicatedPG: release backfill state on_global_recover not peer recover
- There may now be multiple backfill peers.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:24 PM Revision 4c1338f4 (ceph): SimpleMessenger: init_local_connection whenever my_inst changes
- This is necessary to correctly handle messages to self.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:24 PM Revision 211fc4e1 (ceph): librados: add calls to expose required write alignment
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision e0b05085 (ceph): ReplicatedPG: reject unaligned writes on ec pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 541a7e27 (ceph): TestRados: send aligned appends on erasure pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 06ec9bd4 (ceph): ObjectStore: fix OP_COLL_ADD dump output
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 44f5d4de (ceph): ErasureCodeJerasure: fix alignement issues in encode/decode
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:14 PM Revision 093128a8 (ceph): Merge pull request #1139 from ceph/wip-agent
- osd: basic cache tier agent
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:04 PM Revision 749bf40f (ceph): iozone: kill empty suite
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:18 PM Revision 66ffaa65 (ceph): kcephfs, krbd: do not thrash primary-affinity
- Kenrel doesn't yet support it. See #7455
Signed-off-by: Sage Weil <sage@inktank.com> - 09:16 PM Revision 3d0ce693 (ceph): thrashosds: allow primary-affinity thrashing to be disabled
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:07 PM Revision bd8fcd25 (ceph): osd: improve whiteout debug prints
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:07 PM Revision 79976466 (ceph): ReplicatedBackend: print char ack_type as int
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:07 PM Revision 63f5a799 (ceph): osd/ReplicatedPG: make agent skip blocked obcs
- Among other things, this can interfere with an in-flight copy-from and
corrupt the pg stats.
Signed-off-by: Sage Wei... - 07:09 PM Revision 62532fb0 (ceph): Merge pull request #1254 from ceph/wip-barrier
- libcephfs: disable barriers for now
- 07:07 PM Revision a4ca4a73 (ceph): Merge remote-tracking branch 'gh/wip-7212-sage-b'
- We should carefully backport some or all of this.
Backport: emperor, dumpling
Reviewed-by: Joao Eduardo Luis <joao.l... - 06:27 PM Revision a71d829e (ceph): client: disable barrier support
- The boost interval_set class is not available on centos6/rhel6. Until that
dependency is sorted out, fix the build.
... - 06:23 PM Revision 747002c6 (ceph): client: fix barrier interval
- (start, end) not (start, length)
Signed-off-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision d7457f73 (ceph): client/barrier: drop unused active_commit_interval
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:15 PM Revision ce643e00 (ceph): client: don't populate Client::barriers from read accesses
- If the entry doesn't exist, no need to create it.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:28 PM Feature #7459 (Closed): ceph-rest-api: sysvinit and upstart scripts
- enumerate daemon by directory in /var/lib/ceph/rest, using the same structure as the osd, mon, and other daemons.
... - 03:44 PM Bug #7458: osd: stray pg ref on shutdown
- 03:42 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
- ...
- 03:34 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- http://pulpito.ceph.com/teuthology-2014-02-14_23:00:16-rados-master-testing-basic-plana/84322
http://pulpito.ceph.co... - 02:39 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
- 02:15 PM RADOS Feature #7456 (New): osd: agent: measure temperature
- 02:14 PM Feature #7035 (Resolved): cachepool: agent: blocking eviction (when cache pool is 'full')
- 02:14 PM Feature #7033 (Resolved): cachepool: agent: trivial flushing
- 02:14 PM Feature #7034 (Resolved): cachepool: agent: basic eviction
- 02:13 PM Feature #7441 (Fix Under Review): osd: perfcounters for cache events and agent events
- 01:39 PM Bug #7447: osd: copy_from temp objects interact awkwardly with backfill
- Simplest thing seems to be to unconditionally send temp object ops to the backfill targets. Then the final completio...
- 01:37 PM CephFS Bug #7422 (In Progress): client/barrier.h uses boost's interval set library, which is not availab...
- The barrier code has been disabled to fix the build. Matt said he will follow up. http://marc.info/?l=ceph-devel&m=...
- 01:35 PM Bug #6313 (Can't reproduce): dumpling: FAILED assert(latest->is_update()) from recover_primary()
- 01:34 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
- 01:33 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
- reopened #7385
- 01:33 PM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
- This now leaks memory.. presumably stray Object's the cache that never get cleaned up.
Let's just increase the obj... - 01:32 PM rbd Bug #7385: Objectcacher setting max object counts too low
- 01:17 PM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
- when this is complete, be sure to fix ceph-qa-suite.git
- 11:08 AM Bug #7212 (Pending Backport): monitor fails to start
- 10:34 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- The problem is in rgw_user.h:void set_subuser(..) sets 'gen_access = true;'. I can't understand why it's doing that, ...
- 08:44 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
- Pavel Veretennikov wrote:
> * Strange that it worked without permission. Where had it stored the data?
It was onl... - 07:32 AM CephFS Bug #7424: Cannot read from zero-length file
- * Strange that it worked without permission. Where had it stored the data?
- 07:31 AM CephFS Bug #7424: Cannot read from zero-length file
- Yes, the problem resolved after I gave client access to default data pool
rwx pool=data
Strange that it work... - 06:52 AM CephFS Bug #7424: Cannot read from zero-length file
- does client have permission permission to access the data pool? try using admin's keyring to mount the fs.
- 01:19 AM CephFS Bug #7424: Cannot read from zero-length file
- Ubuntu doesn't use SELinux as I know. /selinux lib is empty, only one related selinux package is present - libselinux...
- 06:25 AM Revision a1dbc9ce (ceph): qa/workunits/suites/pjd: use test suite with acl tweak
- Test 45 in xacl/00.t fails on ext4 and cephfs. Just disable it.
Everything else passes.
Signed-off-by: Sage Weil <s... - 05:53 AM Revision c1f42770 (ceph): radosgw-admin: fix object policy read op
- Fixes: #7083
This was broken when we fixed #6940. We use the same function to both
read the bucket policy and the obj... - 05:43 AM devops Feature #7454 (Resolved): ceph-disk: support osd removal / ceph-disk remove
- There should be a *ceph-disk remove* to cleanup an OSD and the associated device / directory. This is not something a...
- 05:35 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
- If you supply rgw_keystone_admin_user and rgw_keystone_admin_password ... instead of supplying "rgw_keystone_admin_to...
- 05:23 AM Revision 623748e5 (ceph): mds: bump the protocol version
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 04:53 AM Revision 2a19a1be (ceph): osd/ReplicatedPG: allow is_degraded_object() to be called outside of ba...
- The agent does this.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:37 AM Revision e5457dfb (ceph): mds: open sessions for rejoin imported caps
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 01:37 AM Revision 6e013cd6 (ceph): mds: properly set COMPLETE flag when merging dirfrags
- don't keep the COMPLETE flag when merging dirfrags during journal
replay, because it's inconvenience to check if the ... - 01:37 AM Revision 0eb311d3 (ceph): mds: fix open undef dirfrags
- Undef inode may contain a undef dirfrag (*). When undef inode is
opened, we should force fragment the undef dirfrag (... - 01:37 AM Revision 305d16f3 (ceph): mds: handle frag mismatch for cache rejoin weak
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 01:37 AM Revision 80799395 (ceph): mds: handle frag mismatch for cache expire
- When sending MDSFragmentNotify to peers, also replicate the new
dirfrags. This guarantees peers get new replica nonce... - 01:37 AM Revision 9a47913d (ceph): mds: improve freeze tree deadlock detection
- Current code uses the start time of freezing tree to detect deadlock.
It is better to check how long the auth pin cou... - 01:37 AM Revision 9df6861b (ceph): mds: freeze dir deadlock detection
- freezing dir and freezing tree have the same deadlock cases.
This patch adds freeze dir deadlock detection, which imi... - 01:37 AM Revision 3dc51dea (ceph): mds: minor cleanup for EFragment and MMDSFragmentNotify
- pass dirfrag_t to their constructors, instead of passing inode_t
and frag_t separately.
Signed-off-by: Yan, Zheng <z... - 01:37 AM Revision 98105b24 (ceph): mds: preserve dir_auth when spliting/merging dirfrags
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 01:37 AM Revision ee7ac6fc (ceph): mds: allow fragmenting subtree dirfrags
- We can't wait until object becomes auth pinnable after freezing a
dirfrag/subtree, because it can cause deadlock. Cur... - 01:37 AM Revision f3666ede (ceph): mds: journal dirfragtree change
- Introduce new flag DIRTYDFT to CDir and EMetaBlob::dirlump, the new
flag indicates the dirfrag is newly fragmented an... - 01:37 AM Revision 4d5ceba5 (ceph): mds: fix 'force dirfrags' during journal replay
- For rename operation, null dentry is first replayed, it detaches
the inode from the FS hierarchy. Then primary dentry... - 01:37 AM Revision 5b1de69a (ceph): mds: force fragment subtree bounds when replaying ESubtreeMap
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 01:37 AM Revision 3b90c785 (ceph): mds: fixes for thrash fragment
- This patch contains 3 changes:
- limit the number of in progress fragmenting processes.
- reduce the probability of s... - 01:37 AM Revision cc77ef2d (ceph): mds: fix scattered wrlock rejoin
- If unstable scatter lock is encountered when handling weak cache
rejoin, don't remove the recovering MDS from the sca... - 01:37 AM Revision 22535340 (ceph): mds: avoid race between cache expire and pushing replicas
- MDentryLink and MMDSFragmentNotify push replica inode/dirfrags
to other MDS. They both are racy because, when the tar... - 01:37 AM Revision 74ef370b (ceph): mds: fix negative rstat assertion
- when gathering rstat for directory inode that is fragmented to
several dirfrags, inode's rstat may temporarily become... - 01:37 AM Revision 21d209d0 (ceph): mds: wake up dentry waiters when handling cache rejoin ack
- Cache rejoin ack message may fragment dirfrag, we should set the
'replay' parameter of adjust_dir_fragments() to fals... - 01:37 AM Revision 9e8dbf9e (ceph): mds: remove failed MDS from export bystanders list
- make sure the importer does not wait for MExportDirNotifyAck from
the failed MDS
Signed-off-by: Yan, Zheng <zheng.z.... - 01:37 AM Revision c54b3cea (ceph): mds: fix slave rename rollback
- use rollback bufferlist to decide if the inode is being exported.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 01:37 AM Revision d0df8413 (ceph): mds: allow acquiring wrlock and remote wrlock at the same time
- Rename may move file from one dirfrag to another dirfrag of the same
directory inode. If two dirfrags belong to diffe... - 01:37 AM Revision 3fb408ee (ceph): mds: introduce nonlocking auth pin
- Add a parameter to Locker::acquire_locks() to enabled nonblocking
auth pin. If nonblocking mode is enabled and an obj... - 01:37 AM Revision 3154ee84 (ceph): mds: acquire locks required by exporting dir
- Start internal MDS request to acquire locks required by exporting dir.
It's more reliable than using Locker::rdlock_t... - 01:37 AM Revision 5faa3134 (ceph): mds: acquire scatter locks when exporting dir
- If auth MDS of the subtree root inode is neither the exporter MDS
nor the importer MDS and it gathers subtree root's ... - 01:37 AM Revision 2c909cda (ceph): mds: revert commit 15a5d37a
- commit 15a5d37a (mds: fix race between scatter gather and dirfrag export)
is incomplete, it doesn't handles the race ... - 01:37 AM Revision 1ff77666 (ceph): mds: introduce fine-grained discover dirfrag wait queue
- Current discover dirfrag code only allows discover one dirfrag at
a time. This can cause deadlock if there are direct... - 01:37 AM Revision b88034ee (ceph): mds: use discover_path to open remote inode
- MDCache::discover_ino() doesn't work well for directories that are
fragmented to several dirfrags. Because MDCache::h... - 01:37 AM Revision ffe71516 (ceph): mds: handle frag mismatch for discover
- When handle discover dirfrag message, choose an approximate frag if
the requested dirfrag doesn't exist. When handlin... - 01:37 AM Revision e0e25658 (ceph): mds: fix MDCache::get_force_dirfrag_bound_set()
- don't force dir fragments according to the subtree bounds in resolve
message. The resolve message was not sent by the... - 01:37 AM Revision 1080fa45 (ceph): mds: fix MDCache::adjust_subtree_after_rename()
- process subtree dirfrags first, then process nested dirfrags. because
the code that processes nested dirfrags treats ... - 01:37 AM Revision ee0ab2b7 (ceph): mds: fix CInode::get_dirfrags_under()
- make the function work when opened dirfrags don't match the
dirfragtree.
Signed-off-by: Yan, Zheng <zheng.z.yan@inte...
02/16/2014
- 10:43 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
- 09:57 PM CephFS Bug #7372: kcephfs: pjd tests fail
- well, as far as i can tell, the pjd tests also fail on ext4 in the same way they do on ceph:...
- 09:46 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
- we missed the backport of commit:b1976dd00f5b29c01791272f63a18250319f2edb
- 09:09 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
- it seems to have been failing for a while, too:
http://pulpito.ceph.com/compare/?branch=dumpling&suite=rgw&count=1... - 08:56 PM Bug #7451 (Resolved): updatedb will index /var/lib/ceph
- See http://git.openvz.org/?p=vzctl;a=commitdiff;h=47334979b9b5340f84d84639b2d77a8a1f0bb7cf for one example of a packa...
- 08:22 PM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- And this bug exists at least as far back as 0.72. I need a fix/workaround asap, to migrate users+subusers between two...
- 08:20 PM rgw Bug #7450 (Resolved): "radosgw-admin key create" ignores specified access key when subuser specified
- If I create to create an explicit accesskey/secret key combo, and specify a subuser, then the access key is not used....
- 04:26 PM Revision 75675bc8 (ceph): Merge pull request #1251 from ceph/wip-7371
- ReplicatedPG: return no data if read size is trimmed to zero
Backport: emperor, dumpling
Reviewed-by: Sage Weil <sag... - 02:36 PM Revision 1dae27c5 (ceph): ReplicatedPG: return no data if read size is trimmed to zero
- OSD should return no data if the read size is trimmed to zero by the
truncate_seq/truncate_size check. We can't rely ... - 08:27 AM Bug #7371 (Pending Backport): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ...
- 06:33 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- 01:39 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- I applied following patch...
- 06:36 AM Revision dcb6d02c (ceph): Merge pull request #1223 from ceph/wip-7395
- Improve OSD subscription handling
Reviewed-by: Sage Weil <sage@inktank.com> - 06:21 AM Revision 8547f43e (ceph): Merge pull request #1234 from dachary/wip-format
- mon: remove format argument from osd crush dump
Reviewed-by: Sage Weil <sage@inktank.com> - 06:20 AM Revision 40450081 (ceph): Merge pull request #1243 from dachary/wip-ceph-disk-dumpling
- ceph-disk: unit tests (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision 905df2e7 (ceph): osd/ReplicatedPG: block requests to cache PGs when they are full
- If we are full and get a write request to a new object, put the op on a
wait list. Wake up when the agent frees up s... - 06:09 AM Revision a8129829 (ceph): osd/ReplicatedPG: simplify agent_choose_mode
- Use a temp variable.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision 0dd1e071 (ceph): osd: schedule agent from a priority queue
- We need to focus agent attention on those PGs that most need it. For
starters, full PGs need immediate attention so ... - 06:09 AM Revision 774125c7 (ceph): osd: set client incarnation for Objecter instance
- Each ceph-osd process's Objecter instance has a sequence
of tid's that start at 1. To ensure these are unique
across... - 06:09 AM Revision c9daf8e5 (ceph): osd/ReplicatedPG: add slop to agent mode selection
- We want to avoid a situation where the agent clicks on and off when the
system hovers around a utilization threshold.... - 06:09 AM Revision e07f987d (ceph): osd/ReplicatedPG: fix evict mode selection for large target
- If the target is > 1.0 for some reason (bad configuration, or high slop
value), and we are not yet full, we should be... - 06:09 AM Revision c2d16d72 (ceph): osd/ReplicatedPG: do not flush or evict hitsets
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision 230aad7b (ceph): osd: clear agent state when PG becomes a replica
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision 90457b17 (ceph): ceph_test_rados_api_tier: fix osd pool set json syntax
- String, not int.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision dd3814f3 (ceph): osd/ReplicatedPG: do not flush|evict degraded objects
- The repop won't work right; we still repair the object before making
any update.
Signed-off-by: Sage Weil <sage@inkt... - 06:09 AM Revision f617eba0 (ceph): osd/ReplicatedPG: do not choke on op-less flush OpContexts (from flush)
- The agent initiates flush ops that don't have an OpRequest associated
with them. Make reply_ctx skip the actual repl... - 06:09 AM Revision 6581ce9c (ceph): osd/ReplicatedPG: ignore starvation potential when taking write lock du...
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision 11e4695a (ceph): osd: add OMAP flag to object_info_t
- Set a flag if we ever set or update OMAP content on an object. This gives
us an easy indicator for the cache agent (... - 06:09 AM Revision 8c7bc2e8 (ceph): osd/ReplicatedPG: do not activate agent unless base pool exists
- Paranoia.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision 7f854211 (ceph): osd/ReplicatedPG: do not flush omap objects to an EC base pool
- The EC pool does not support omap content. If the caching/tiering agent
encounters such an object, just skip it. Us... - 06:09 AM Revision b92c79d2 (ceph): osd/ReplicatedPG: use reply_ctx in a few cases
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision 85e06f9d (ceph): osd/ReplicatedPG: redirect reads instead of promoting when full
- If the cache pool is full, we are processing a read op, and we would
otherwise promote, redirect instead. This lets ... - 06:09 AM Revision 69502123 (ceph): osd/ReplicatedPG: factor clone check out of evict op code
- Move the check for clones into a helper so that we will be able to use in
other places where we need to evict.
Signe... - 06:09 AM Revision 34fcf42c (ceph): osd/HitSet: add HitSetRef
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision 9ac03ef5 (ceph): osd/ReplicatedPG: fix finish_flush
- Make sure we reallocate a pgbackend transaction at the time when we are
initiating new work.
Signed-off-by: Sage Wei... - 06:09 AM Revision a54f8198 (ceph): osd: agent worker thread
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision da9ed08e (ceph): osd/ReplicatedPG: basic flush and evict agent functionality
- This is very basic flush and evict functionality for the tiering agent.
The flush policy is very simple: if we are a... - 06:09 AM Revision 18bc151b (ceph): osd/ReplicatedPG: decay tier agent histograms over time
- Make decisions based on recent observations of object age distributions,
not all time history.
Signed-off-by: Sage W... - 06:09 AM Revision 199bdb1b (ceph): mon: test dirty stats in ceph df detail
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:09 AM Revision a5dabb58 (ceph): histogram: fix histogram::get_position_micro overflow
- Convert the return values to uint64_t
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:09 AM Revision dcf20b9b (ceph): osd: add 'notieragent' flag to OSDMap
- This will pause tiering agent work.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision cb4aa3a7 (ceph): osd: observe 'notieragent' osdmap flag
- Pause/unpause the agent thread accordingly.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision 7bb0aa5a (ceph): osd: only enable tier agent when osd is in active state
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision f6930452 (ceph): osd: add pg_pool_t::get_random_pg_position()
- Return a hash position somewhere inside a given pg.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:09 AM Revision 3bc31272 (ceph): osd/ReplicatedPG: initial agent to random hash position inside pg
- When the agent starts, start at a random offset to ensure we get a more
uniform distribution of attention to all obje... - 06:09 AM Revision bc945248 (ceph): osd: rename test/test_osd_types.cc -> test/osd/types.cc
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision a57052cb (ceph): mon: include dirty stats in 'ceph df detail'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:09 AM Revision fc28a99f (ceph): osd/ReplicatedPG: add on_finish to OpContext
- Add a callback hook for whenever an OpContext completes or cancels. We
are pretty sloppy here about the return value... - 06:08 AM Revision 0988c843 (ceph): osd/osd_types: add cache policy fields to pg_pool_t
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:08 AM Revision 95f25ce0 (ceph): mon/OSDMonitor: allow new pool policy fields to be set
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:08 AM Revision e65c280b (ceph): osd: add pg_pool_t::get_pg_num_divisor
- A PG is not always an equally sized fraction of the total pool size due to
the use of ceph_stable_mod. Add a helper ... - 06:07 AM Revision 8b68ad03 (ceph): histogram: calculate bin position of a value in the histrogram
- Generate a lower and upper bound.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:07 AM Revision 85a82722 (ceph): histogram: rename set -> set_bin
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:07 AM Revision fb4152ae (ceph): histogram: move to common, add unit tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:07 AM Revision 297d54eb (ceph): histogram: add decay
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:38 AM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
- Triggered while running the ceph-deploy suite on next, on debian (http://pulpito.ceph.com/sage-2014-02-15_17:05:48-ce...
- 04:01 AM Revision 63ad9aab (ceph): thrashosds: randomly adjust primary_affinity
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:01 AM Revision dc95aef2 (ceph): ceph.conf: mon osd allow primary affinity = true
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:36 AM Revision 3e7ea33c (ceph): add autotools-generated files to .gitignore
- When running "make check", Automake generates test-suite.log, along with
various *.log and *.trs files in the tree. A... - 12:59 AM Revision af848d4a (ceph): Merge pull request #1176 from ceph/wip-primary-affinity
- osd: primary affinity
Added primary-affinity thrashing to thrashosd.py.
Reviewed-by: Loic Dachary <loic@dachary.org> - 12:49 AM Revision 6d4c1e2b (ceph): Merge pull request #1246 from dachary/wip-7188
- common: ping existing admin socket before unlink
- 12:48 AM Revision f0f1cf4f (ceph): Merge pull request #1249 from dachary/wip-qa-erasure-test
- qa: do not create erasure pools yet
02/15/2014
- 11:53 PM Revision d921d9b3 (ceph): qa: do not create erasure pools yet
- comment out erasure pool related tests when an OSD is involved because
it does not work yet. See http://tracker.ceph.... - 11:05 PM Revision 45600789 (ceph): common: ping existing admin socket before unlink
- When a daemon initializes it tries to create an admin socket and unlinks
any pre-existing file, regardless. If such a... - 10:36 PM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
- 10:19 PM Bug #7188 (Pending Backport): Admin socket files are lost on log rotation calling initctl reload ...
- merged into next. want to wait a bit before backporting.
- 03:13 AM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
- "dumpling backport":https://github.com/ceph/ceph/pull/1248
- 03:11 AM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
- "emperor backport":https://github.com/ceph/ceph/pull/1247
- 02:55 AM Bug #7188 (Fix Under Review): Admin socket files are lost on log rotation calling initctl reload ...
- "work in progress":https://github.com/ceph/ceph/pull/1246
- 06:50 PM Revision f825624f (ceph): osd/OSDMap: add primary_affinity feature bit
- Indicate that we support it. Indicate when an OSDMap requires it.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision c360c604 (ceph): ceph_psim: some futzing to test primary_affinity
- - map to acting
- count first position, primary
Signed-off-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision ba3eef86 (ceph): mon/OSDMonitor: add 'mon osd allow primary affinity' bool option
- By default, disallow adjustment of primary affinity unless the user has
opted in by adjusting their monitor config. ... - 06:50 PM Revision 87be7c15 (ceph): osd/OSDMap: remove bad assert
- You can have an erasure poool with all CRUSH_ITEM_NONE and primary == -1.
acting is not empty.
Signed-off-by: Sage W... - 06:50 PM Revision c673f408 (ceph): osd/OSDMap: include primary affinity in OSDMap::print
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:50 PM Revision 8ecec02f (ceph): osd/OSDMap: apply primary_affinity to mapping
- The behavior is a bit different for replicated and indep/erasure mode.
In the first case, we are rearranging the resu... - 06:48 PM Bug #7447 (Resolved): osd: copy_from temp objects interact awkwardly with backfill
- We decide whether to send the operation based on the object named in the repop, but the temp objects do not get backf...
- 06:37 PM Revision a91d0cbc (ceph): Merge pull request #1245 from ceph/wip-brag
- ceph-brag
Sebastien Han confirms that this is under the default (LGPL2) license, thus:
Signed-off-by: Sage Weil <sa... - 06:25 PM Revision 1d6aceb4 (ceph): upgrade: reorg
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:15 PM Revision 871a5f04 (ceph): ceph.spec: add ceph-brag
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:15 PM Revision 57d70183 (ceph): ceph-brag: add Makefile
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:15 PM Revision 4ea0a25a (ceph): debian: add ceph-brag
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:13 PM Revision fec55a21 (ceph): ceph-disk: unit tests
- src/test/ceph-disk.sh replaces src/test/cli/ceph-disk/data-dir.t
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:08 PM Revision 7e9f03b1 (ceph): Merge pull request #1181 from dachary/wip-7277
- DNM: mon: s/ENOSYS/ENOTSUP/
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Reviewed-by: Sage Weil ... - 06:07 PM CephFS Bug #6791 (Won't Fix): mds assert after startup - CDir::commit error (want > commited version)
- 05:17 PM Revision e485c95f (ceph): Merge branch 'master' of https://github.com/enovance/ceph-brag into wip...
- 05:00 PM Feature #7058 (Resolved): osd primary affinity
- 04:59 PM Revision cf4f7027 (ceph): mon/Elector: bootstrap on timeout
- Currently if an election times out we call a new
election. If we have never joined a quorum, bootstrap
instead. This... - 04:53 PM Revision 0679b11b (ceph): ceph-disk: cannot run unit tests
- Because ceph-disk relies on hardcoded paths. The corresponding test will
be added back when ceph-disk can run from so... - 04:27 PM Bug #7445 (Need More Info): missing feature bit ( next )
- Is it worth investigating the current failure of next on make check ? It will probably go away when master is merged ...
- 04:23 PM Bug #7445: missing feature bit ( next )
- next is missing "osd crush rule create-erasure":https://github.com/ceph/ceph/commits/cb39b1367676215fc244664d83ffb3e2...
- 04:03 PM Bug #7445 (Rejected): missing feature bit ( next )
- On ea6dc997668df98c0a553d677cf22850b476e412 running *test/mon/osd-pool-create.sh* blocks...
- 04:01 PM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
- "revert due to accidental merge of a DNM":https://github.com/ceph/ceph/pull/1249
- 07:52 AM Revision 9dae9993 (ceph): Revert "librbd: remove limit on number of objects in the cache"
- This reverts commit 367cf1bbf86233eb20ff2304e7d6caab77b84fcc.
Removing the limit on objects means we leak memory, si... - 04:27 AM Revision 4595c44b (ceph): mon: tell MonmapMonitor first about winning an election
- It is important in the bootstrap case that the very first paxos round
also codify the contents of the monmap itself i... - 04:27 AM Revision 7bd2104a (ceph): mon: only learn peer addresses when monmap == 0
- It is only safe to dynamically update the address for a peer mon in our
monmap if we are in the midst of the initial ... - 01:28 AM Revision 64ff4ab0 (ceph): Fixed task/args.py docstrings.
- 01:08 AM Revision c631190a (ceph): Add docstrings. Fix formatting issues for rgw.py
- Fix s3tests calls for rgw-logsocket.py.
Fixes: 6540
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 12:54 AM Revision 6db3ae85 (ceph): OSD: create a helper for handling OSDMap subscriptions, and clean them up
- We've had some trouble with not clearing out subscription requests and
overloading the monitors (though only because ... - 12:54 AM Revision 3c76b81f (ceph): OSD: use the osdmap_subscribe helper
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:53 AM Revision 5b9c187c (ceph): monc: new fsub_want_increment( function to make handling subscriptions ...
- Provide a subscription-modifying function which will not decrement
the start version.
Signed-off-by: Greg Farnum <gr...
02/14/2014
- 11:48 PM Revision 6df622b3 (ceph): Fix docstrings and minor formatting in task/ssh_keys.py
- Fixes: 6539
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 11:25 PM Revision 2795339d (ceph): os/FileStore: fix ENOENT error code for getattrs()
- In commit dc0dfb9e01d593afdd430ca776cf4da2c2240a20 the omap xattrs code
moved up a block and r was no longer local to... - 11:13 PM Revision 0af08071 (ceph): Fix docstrings for task/blktrace.py, peering_speed_test.py, proc_thrash...
- recovery_bench.py.
Fixes: 6535
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 10:23 PM Revision c158de23 (ceph): test/filestore/run_seed_to.sh: avoid obsolete --filestore-xattr-use-omap
- This option no longer exists.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 1d4f501a015727a... - 10:20 PM Revision 7d398c2a (ceph): doc/release-notes: v0.67.6
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:57 PM Revision ef97f0cd (ceph): Fix docstrings in radosgw-admin-rest.py
- Fixes: 6541
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 08:59 PM Revision 4015d614 (ceph): Merge pull request #188 from ceph/wip-calamari-onefile
- Add Calamari test tasks, test script
- 08:59 PM Revision 8e2cdbf5 (ceph): Merge pull request #188 from ceph/wip-calamari-onefile
- Add Calamari test tasks, test script
- 08:57 PM Revision e0ed09cf (ceph): Add docstrings to the orchestra code. Also fix minor formatting issues
- (mostly column start locations).
Fixes: 7003
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 07:28 PM Revision a6eee01f (ceph): Review: switch to selecting remotes by roles in the 'normal' way
- This buys us, also, the ability to select remotes by rule, i.e.
"any osd or mon gets calamari-agent installed"
Signe... - 07:28 PM Revision 006428c5 (ceph): Review: refactor packaging routines to common file
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 05:50 PM Revision 67e670b2 (ceph): Merge pull request #192 from ceph/wip-6537-wusui
- Readjust the indentation of mon_clock_skew_check.py and mon_thrash.py.
- 05:50 PM Revision 132f3e8a (ceph): Merge pull request #192 from ceph/wip-6537-wusui
- Readjust the indentation of mon_clock_skew_check.py and mon_thrash.py.
- 05:45 PM Revision e8e7cc22 (ceph): Merge pull request #194 from ceph/wip-6534-wusui
- Add docstrings to internal.py
- 05:45 PM Revision 24363351 (ceph): Merge pull request #194 from ceph/wip-6534-wusui
- Add docstrings to internal.py
- 05:45 PM Revision a3fbb6c5 (ceph): Merge pull request #193 from ceph/wip-6538-wusui
- Add doc strings to Swift tests
- 05:45 PM Revision 4eb14729 (ceph): Merge pull request #193 from ceph/wip-6538-wusui
- Add doc strings to Swift tests
- 05:44 PM Revision af61317a (ceph): Merge pull request #191 from ceph/wip-7002-wusui
- Added some docstrings.
- 05:43 PM Revision 1da78c06 (ceph): Merge pull request #187 from ceph/wip-better-debug
- Debug output improvements
- 05:43 PM Revision ad9aaf8f (ceph): Merge pull request #187 from ceph/wip-better-debug
- Debug output improvements
- 05:27 PM Revision f47062d8 (ceph): Merge pull request #1237 from dachary/wip-hashpspool
- mon: ceph hashpspool false clears the flag
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Reviewed... - 03:45 PM Bug #7188 (In Progress): Admin socket files are lost on log rotation calling initctl reload (ubun...
- Steps to reproduce:...
- 03:25 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
- From a fresh install of "ubuntu 13.04":http://mirrors.ircam.fr/pub/ubuntu/releases/raring/ubuntu-13.04-server-amd64.i...
- 02:37 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
- ceph-osd "installs a sighup handler":https://github.com/ceph/ceph/blob/emperor/src/ceph_osd.cc#L477 which "reopens lo...
- 12:25 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
- Not sure if I can fix it but I'll give it a shot.
- 02:12 PM Feature #7442 (Resolved): mon: health warn on pg "full"
- 02:09 PM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
- 02:04 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
- 01:59 PM RADOS Feature #7440 (New): erasure-code: adapt scrub/repair teuthology tests for EC and add to nightly
- 01:58 PM Feature #7439 (Resolved): EC: adapt unfound teuthology tests and add to nightly for EC
- 01:58 PM Feature #7438 (Resolved): EC: adapt watch/notify stress test for EC and add to nightly
- 01:57 PM Feature #7437 (Resolved): EC: add adapt unittest teuthology task and add to nightly
- 01:42 PM devops Feature #7293: packaging: enable qemu to find librbd on rhev or rhel-osp
- 01:41 PM devops Feature #7436 (Rejected): Build and test RHEL on same subversions.
- 01:39 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
- 01:38 PM devops Feature #5214 (Resolved): Kernel gitbuilders for rpm distros
- Removed requirement for SLES/OpenSuse. Therefore, completed.
- 01:33 PM devops Feature #7046 (Resolved): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
- 01:31 PM rgw Documentation #7434: rgw: doc user/group quota
- John: can you please provide feedback to Yehuda on where he should put the new docs about the user quotas.
- 01:06 PM rgw Documentation #7434 (Resolved): rgw: doc user/group quota
- 01:05 PM rgw Feature #6339: rgw: compact manifest data
- 01:05 PM rgw Feature #6338: rgw: better manifest scaling
- 12:33 PM Revision d8964b2f (ceph): Merge pull request #1235 from ceph/wip-osdmaptool-pool-fix
- wip-osdmaptool-pool-fix
Reviewed-by: Loic Dachary <loic@dachary.org> - 11:53 AM rgw Feature #6513 (In Progress): rgw: dr: Service scripts for meta/data sync agents
- 11:23 AM devops Bug #7427: sha1 does not exist on gitbuilder, install fails
- This happened because the build failed on the rpm gitbuilder. It actually looks like many of the last few master buil...
- 09:13 AM devops Bug #7427 (Resolved): sha1 does not exist on gitbuilder, install fails
- ...
- 11:13 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
- After investigating what was returning this message:...
- 11:05 AM devops Bug #7390 (Resolved): ceph-deploy should remove ceph-release and call yum clean all
- Merged into ceph-deploy master branch 348bf8c
- 07:53 AM devops Bug #7390 (Fix Under Review): ceph-deploy should remove ceph-release and call yum clean all
- Pull request opened https://github.com/ceph/ceph-deploy/pull/163
- 10:24 AM Revision 0ed6a81b (ceph): osdmaptool: add tests for --pool option
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 10:24 AM Revision f98435a4 (ceph): osdmaptool: add --pool option for --test-map-pgs mode to usage()
- --test-map-pgs mode allows to map all pgs from either all pools or just
one pool. Mention it in usage output.
Signe... - 10:24 AM Revision eedbf501 (ceph): osdmaptool: fix --pool option for --test-map-object mode
- Commit 7f1b12f2ef97 ("osdmaptool: add --test-map-pgs mode") broke
--pool for --test-map-object mode. Fix it, and imp... - 09:26 AM devops Bug #7429 (Resolved): fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
- When deploying monitors on fedora 19 VMs, the monitors fail to mkfs due to some segfault. This happens regardless of ...
- 09:04 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
- Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-02-13_12:23:01-rgw-dumpling-master-basic-plana/81039/
<... - 08:20 AM Bug #7406: Seg fault in find_object_context()in recent master rados run
- I don't think snaps should ever be empty.. if it is, there is a bug somewhere that is causing it. On the one hand no...
- 08:10 AM rados-java Bug #7425 (Rejected): Error in run_seed_to_range.sh for rados-dumpling-master-basic-plana
- Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-02-13_12:24:10-rados-dumpling-master-basic-plana/81235/
... - 06:37 AM Revision 68106102 (ceph): Add docstrings to internal.py
- Fixes: 6534
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 06:25 AM CephFS Bug #7424: Cannot read from zero-length file
- do you have selinux enabled
- 02:16 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
- Ubuntu 12.04 LTS 3.8.0-35-generic x64
Ceph 0.72.2-1precise from http://ceph.com/debian-emperor/
cluster b8... - 06:01 AM Revision e44122f0 (ceph): test: fix signed/unsigned warnings in TestCrushWrapper.cc
- Irritatingly, using 0 binds to int and generates warnings
if the thing we're checking is unsigned, so we have to be
e... - 05:11 AM Revision 5c36a5ce (ceph): Add doc strings to Swift tests
- Fixes: 6538
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 05:11 AM Revision f4284b52 (ceph): Add doc strings to Swift tests
- Fixes: 6538
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 04:36 AM Revision 567961b7 (ceph): Readjust the indentation of mon_clock_skew_check.py and mon_thrash.py.
- Added docstrings.
Fixes: 6537
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 04:00 AM Revision 12b79044 (ceph): Review: Rename calamari_testdir/ to calamari/
- 02:04 AM Bug #7423: erasure code: ./rados get retrieves a larger object
- On "ecbackend-8":https://github.com/ceph/ceph/tree/wip-ecbackend-8 it fails in the same way ( the crash does not happ...
- 01:29 AM Bug #7423: erasure code: ./rados get retrieves a larger object
- Loic Dachary wrote:
> While playing with "ECBackend pull request":https://github.com/ceph/ceph/pull/1228
> [...]
>... - 01:28 AM Bug #7423 (Resolved): erasure code: ./rados get retrieves a larger object
- "work in progress":https://github.com/ceph/ceph/pull/1327
Steps to reproduce:... - 01:40 AM Revision bee587c3 (ceph): Added some docstrings.
- Fixes: 7002
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 12:45 AM CephFS Bug #7422 (Resolved): client/barrier.h uses boost's interval set library, which is not available ...
- http://gitbuilder.sepia.ceph.com/gitbuilder-centos6-amd64/log.cgi?log=9cbbc883e225b08b3e31cd2cf6e766688795886b
Thi...
02/13/2014
- 10:27 PM Bug #7420: posix_fallocate failed under CentOS 6.5 when DIO enabled
- posix_allocate in FileJournal::_open_file will call pread to pre-allocate space which will return 22 because unalgine...
- 10:19 PM Bug #7420 (Won't Fix): posix_fallocate failed under CentOS 6.5 when DIO enabled
- under CentOS 6.5, when enable DIO and initialize OSD directory will cause failed:
2014-02-14 05:46:15.591387 7ffff... - 10:23 PM Revision 54e9e3e7 (ceph): fixed yam typos
- 09:20 PM Revision 1a8c4347 (ceph): monc: let users specify a callback when they reopen their monitor session
- Then the callback is triggered when a new session is established, and the
daemon can do whatever it likes. There are ... - 09:20 PM Revision 60da8abe (ceph): monc: set "hunting" to true when we reopen the mon session
- If we don't have a connecton to a monitor, we want to retry to another
monitor regardless of whether it's the first t... - 09:20 PM Revision 794c86fd (ceph): monc: backoff the timeout period when reconnecting
- If the monitors are systematically slowing down, we don't want to spam
them with reconnect attempts every three secon... - 09:20 PM Revision 64cedf6f (ceph): OSD: disable the PGStatsAck timeout when we are reconnecting to a monitor
- Previously, the timeout counter started as soon as we issued the reopen,
but if the reconnect process itself took a w... - 08:20 PM Revision c71f8a60 (ceph): release build 67.6
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 07:41 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
- Recent change is causing 2GB VM KVM processes to consume up to 5GB of memory during heavy write workload. Sage think...
- 06:12 PM Revision de468594 (ceph): added distros
- 06:07 PM Revision 589e2fa4 (ceph): mon: ceph hashpspool false clears the flag
- instead of toggling it.
Signed-off-by: Loic Dachary <loic@dachary.org> - 04:43 PM devops Bug #7417 (Resolved): libleveldb1 missing in debian-testing
- The libleveldb1 package is listed as a dependency for precise/testing (http://ceph.com/debian-testing/dists/precise/m...
- 03:38 PM Bug #7406 (Fix Under Review): Seg fault in find_object_context()in recent master rados run
- Pushed wip-7406
- 03:27 PM Revision 7834535f (ceph): mon: remove format argument from osd crush dump
- The --format argument of the ceph cli is used to send the desired format
argument. The format argument is always part... - 03:00 PM Revision 0ae5e53e (ceph): Merge pull request #1231 from dachary/wip-mon-create-simple
- mon: do not goto reply if a ruleset exists in pending
Reviewed-by: Sage Weil <sage@inktank.com> - 02:59 PM Revision 39e313fc (ceph): Merge pull request #1216 from ceph/wip-null-xattr
- mds: remove xattr when null value is given to setxattr()
Reviewed-by: Sage Weil <sage@inktank.com> - 02:55 PM Revision 1c42a6e3 (ceph): Merge pull request #1232 from ceph/dumpling-7334
- backport ceph-disk improvements to dumpling
http://pulpito.ceph.com/ubuntu-2014-02-12_16:52:33-ceph-deploy-dumpling-... - 02:51 PM Revision 9cbbc883 (ceph): Merge branch 'wip-libcephfs-firefly-rb' of https://github.com/linuxbox2...
- Reviewed-by: Sage Weil <sage@inktank.com>
This went through the fs suite and passed:
http://pulpito.ceph.com/sage-... - 02:50 PM Revision 020e543e (ceph): mon: do not goto reply if a ruleset exists in pending
- If the crush ruleset is found in pending, do not goto reply because it
does not exist yet. Wait for the pending propo... - 02:06 PM Revision 192ed615 (ceph): Merge pull request #1202 from dachary/wip-mon-create-simple
- mon: create simple should goto reply when it exists in pending
Reviewed-By: Christophe Courtaut <christophe.courtaut... - 01:54 PM Revision 0c9c1577 (ceph): mon: osd crush rule create-simple functional tests
- Basic tests and a test that create the conditions where an OSDMap
is pending with a ruleset that is not yet in the OS... - 01:54 PM Revision c248e7cf (ceph): mon: osd crush rule functional tests
- * A set of test for the simplest operations
* A test covering all cases of osd crush rule
Signed-off-by: Loic Dachar... - 01:00 PM Revision f8ec7ae2 (ceph): Merge pull request #1230 from ceph/wip-open-truncate
- mds: properly replay dentry trace for open truncate.
Reviewed-by: Sage Weil <sage@inktank.com> - 11:28 AM devops Bug #7390 (In Progress): ceph-deploy should remove ceph-release and call yum clean all
- 11:27 AM Revision cec18933 (ceph): mon: add missing format argument to crush rule dump
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:27 AM Revision fce4d684 (ceph): mon: add missing format argument to crush dump
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:27 AM Revision 4784a687 (ceph): mon: add ruleset name to crush rule dump
- The crush rule name is made an optional first argument. If not provided, it
defaults to dumping all rules.
Signed-of... - 11:27 AM Revision 7ff27566 (ceph): mon: osd create pool test refactor
- * Use test-helpers.sh instead of duplicating it
* Isolate each test in a separate function for clarity
Signed-off-by... - 11:14 AM Revision 462ad76a (ceph): crush: fix leaks in TestCrushWrapper.cc
- To get a meaningfull valgrind output.
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:14 AM Revision f77e8ea2 (ceph): crush: add CrushWrapper::dump_rules() unit test
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:14 AM Revision dcfeee66 (ceph): crush: add the dump_rule(int ruleset) method
- And implement dump_rules() using dump_rule(). The indentiation and
variable names are intentionaly left as is to not ... - 11:14 AM Revision e5b6eb45 (ceph): crush: cosmetic changes to CrushWrapper::dump_rule()
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:14 AM Revision a7e9a7b6 (ceph): crush: display item name in CrushWrapper::dump_rule()
- When an item name is available used it instead of displaying the number.
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:14 AM Revision 4b687ba6 (ceph): mon: if crush rule create-simple exists return
- And it is consistent with the above. Also use a slightly different
string to allow the caller to differentiate betwee... - 11:14 AM Revision fd13307f (ceph): mon: minor improvement to test-helpers.sh
- * kill -9 daemons to better cope with stuck daemons
* reduce paxos propose interval to speedup tests
* look for erasu... - 10:38 AM rados-java Bug #7413 (Rejected): LibRadosTier.FlushTryFlushRaces failed on rados:basic-wip-agent-testing-bas...
- Logs are in sage-2014-02-12_13:47:37-rados:basic-wip-agent-testing-basic-plana/79327...
- 10:30 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
- 3e473d4237697872498094b41fed19b414f8d3c4
- 10:06 AM Bug #7212 (Fix Under Review): monitor fails to start
- patch bb863b73c45ce5592844c2c72028ef1cfd9647f8 ; pull request: https://github.com/ceph/ceph/pull/1236
- 09:16 AM Revision ee46908b (ceph): Merge pull request #1222 from dachary/wip-pending-osdmap
- mon: control pending OSDMap for testing
Reviewed-by: Joao Eduardo Luis <joao@inktank.com>
Reviewed-by: Greg Farnum <... - 09:14 AM Revision 6ad6b092 (ceph): mon: remove racy tests from osd-pool-create.sh
- Use the admin socket to create the conditions by which a pool creation
is made to wait for the next paxos proposal be... - 08:52 AM Revision 8dea5884 (ceph): mon: add osdmonitor_prepare_command to the admin socket
- It provides a developer path allowing functional tests to modify the
pending OSDMap without triggering a PaxosProposa... - 08:50 AM Revision 07c494bd (ceph): mon: add --mon-advanced-debug-mode
- When this flag is true, the mon is expected to provide functionalities
that are for developer oriented debug purposes... - 08:45 AM Revision 53e92f62 (ceph): mon: split prepare_command in two
- So that it is possible to call prepare_command without a session
established and a cmdmap that has already been parse... - 08:45 AM Revision 5ea156a0 (ceph): mon: Monitor::send_reply gracefully handles no connection
- If req->get_connection() returns a null pointer, drop the reply instead
of crashing the monitor.
Signed-off-by: Loic... - 07:49 AM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
- Merged into ceph dumpling branch with hash 1c42a6e
- 06:48 AM devops Bug #7334: ceph-disk: cannot run partprobe on used devices with EL6
- Created branch dumpling-7334 and got all dumpling ceph-deploy suite tests to pass http://pulpito.ceph.com/ubuntu-2014...
- 04:20 AM Revision d0121197 (ceph): mds: remove xattr when null value is given to setxattr()
- setxattr() should remove xattr if parameter 'value' is NULL. To
distinguish it from the zero-length value case, intro... - 02:40 AM Revision 6e6a3335 (ceph): mds: properly replay dentry trace for open truncate.
- Open request created by ceph_atomic_open() wants dentry trace. But
the corresponding code is missing in Server::do_op... - 02:14 AM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
- Sure, totally agree on the low priority.
- 02:02 AM Revision 9035227e (ceph): doc/release-notes: do not downgrade from v0.67.6
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:55 AM Revision 7533b3b7 (ceph): doc/release-notes: note about dumpling xattr backport
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:42 AM Revision cc1e8449 (ceph): PendingReleaseNotes: note about cephfs backtrace updates
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:37 AM Revision 94828507 (ceph): Merge pull request #1219 from ceph/wip-update-backtrace
- mds: force update backtraces for previously created FS
Reviewed-by: Sage Weil <sage@inktank.com> - 12:52 AM Bug #7409 (Can't reproduce): "make check" doesn't work without --with-radosgw
- It may looks like improper that we can't run "make check" by default configure which lack of "--with-radosgw".
tes...
02/12/2014
- 11:08 PM Revision 2a6ec2db (ceph): added parallel dumping-emperor-next upgrade tests
- 11:01 PM Revision ea6dc997 (ceph): Merge pull request #1225 from ceph/wip-moncap
- osd/OSDCap: mon/MonCap: handle any whitespace (not just space)
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:45 PM Bug #7222 (Won't Fix): init-ceph failed when cluster created by "mkcephfs" and start osd firstly ...
- 10:42 PM Bug #7222: init-ceph failed when cluster created by "mkcephfs" and start osd firstly and
- mkcephfs won't add osd id to osdmap. So if cluster created by mkcephfs, it need to add "osd crush update on start = 0...
- 09:48 PM Revision 3e473d42 (ceph): common,os: Remove filestore_xattr_use_omap option
- Now we operate just like when this was set to true
Fixes: #6143
Signed-off-by: David Zafman <david.zafman@inktank.c... - 09:43 PM Revision c5e12f94 (ceph): add support for absence of PATH
- Note that this commit is actually bisecting the changes from
Loic Dachary that touch ceph-disk only (ad515bf). As tha... - 09:38 PM Revision cee91429 (ceph): osd/OSDMap: add osd_primary_affinity fields, accessors, encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:38 PM Revision 1cc8c258 (ceph): mon/OSDMonitor: add 'osd primary-affinity ...' command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:38 PM Revision e1079382 (ceph): osd/OSDMap: fix _raw_to_up_osds for EC pools
- When filtering down OSDs out of the result set (i.e., raw -> up), we can
shift positions for replicated pools but nee... - 09:38 PM Revision 74951cad (ceph): osd/OSDMap: pass pps value out from _pg_to_osds
- The primary affinity code needs a seed to determine it's pseudo-random
behavior. Pass pps (optionally) out of _pg_to... - 09:37 PM Revision c531d75f (ceph): ceph-disk: make initial journal files 0 bytes
- The ceph-osd will resize journal files up and properly fallocate() them
so that the blocks are preallocated and (hope... - 09:25 PM Revision f0655109 (ceph): Fix flake8 failures
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 09:18 PM Revision af4c142d (ceph): mon/OSDMonitor: fix legacy tunables warning
- Warn on legacy tunables, not on non-optimal tunables. Optimal is a moving
target, but it is really the legacy defaul... - 09:17 PM Revision cff3547c (ceph): use partx for red hat or centos instead of partprobe
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 42900ff9da9f5adcac239a84ebf4d2e407c29699) - 09:17 PM Revision 836ead3e (ceph): alert the user about error messages from partx
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 9bcc42a3e6b08521694b5c0228b2c6ed7b3d312e) - 09:17 PM Revision 6ae96d3c (ceph): ceph-disk: display the command output on OSD creation failure
- The string form of a CalledProcessError instance does not include the
output datamember. Add it to the Error exceptio... - 09:17 PM Revision a33ad6d1 (ceph): ceph-disk: use CalledProcessError.returncode
- CalledProcessError has no errno data member
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commi... - 09:17 PM Revision 3aae5b76 (ceph): ceph-disk: fsid is a known configuration option
- Use get_conf_with_default instead of get_conf because fsid is a known
ceph configuration option. It allows overriding... - 09:17 PM Revision 6ea59a3a (ceph): ceph-disk: implement --mark-init=none
- It is meant to be used when preparing and activating a directory that is
not to be used with init. No file is created... - 09:17 PM Revision c473c65d (ceph): ceph-disk: run ceph-osd when --mark-init=none
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 0fcc081858fae4febbb6a613a93cfbbcedd5a320) - 09:17 PM Revision c4b66bbd (ceph): ceph-disk: create the data directory if it does not exist
- Instead of failing if the OSD data directory does not exist, create
it. Only do so if the data directory is not enfor... - 09:17 PM Revision 79564874 (ceph): ceph-disk: add copyright notice
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 51ee3c04777aaf6b9609dde9bc318b5c66c70787) - 09:17 PM Revision c8b9798a (ceph): ceph-disk: implement --statedir as /var/lib/ceph
- Replace hardcoded /var/lib/ceph with the STATEDIR global variable and
implement the --statedir option to override the... - 09:17 PM Revision 4a7c4e0a (ceph): ceph-disk: implement --sysconfdir as /etc/ceph
- Replace hardcoded /etc/ceph with the SYSCONFDIR global variable and
implement the --sysconfdir option to override the... - 09:17 PM Revision 5ebd7c45 (ceph): ceph-disk: run the right executables from udev
- When run by the udev rules, PATH is not defined. Thus,
ceph-disk-activate relies on its which() function to locate th... - 09:17 PM Revision 0fe2ac47 (ceph): use the new get_command helper in check_call
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 897dfc113fe3b86f3dda53172933bfd4f8089869) - 09:17 PM Revision 2e8496a6 (ceph): ceph-disk: zap needs at least one device
- If given no argument, ceph-disk zap should display the usage instead of
silently doing nothing. Silence can be confus... - 09:17 PM Revision 5df1eaa5 (ceph): ceph-disk: prepare --data-dir must not override files
- ceph-disk does nothing when given a device that is already prepared. If
given a directory that already contains a suc... - 09:17 PM Revision 75bdb543 (ceph): ceph-disk: fix Error() messages formatting
- Mainly using % instead of ,
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit b82ccfbfa786cd... - 09:17 PM Revision 27988cf9 (ceph): ceph-disk: remove noop try:
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit de0050596b5f56863c3486c1cd5e7ffea62e3d00) - 09:17 PM Revision 827edb93 (ceph): ceph-disk: fix activate() indent
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 324804a81c37ff89f2488e2ba106033c0e6e119e) - 09:17 PM Revision d60e952f (ceph): ceph-disk: do not hide main_activate() exceptions
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 55ca7bb2da73f1be1293710a635cfea42abd7682) - 09:17 PM Revision ccf18224 (ceph): ceph-disk: make exception handling terse in main_activate_journal
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 908348b8047e8577ecf9133f2683f91423694416) - 09:17 PM Revision 06bbea18 (ceph): ceph-disk: add --prepend-to-path to control execution
- /usr/bin is hardcoded in front of some ceph programs which makes it
impossible to control where they are located via ... - 09:17 PM Revision deefb3a0 (ceph): ceph-disk: which() uses PATH first
- Instead of relying on a hardcoded set of if paths. Although this has the
potential of changing the location of the bi... - 09:14 PM Revision 83b2cde2 (ceph): Merge pull request #1217 from ceph/wip-7346
- rgw: multi object delete should be idempotent
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:12 PM Revision a0b2c746 (ceph): osd/OSDCap: handle any whitespace (not just space)
- Backport: emperor, dumpling
Signed-off-by: Sage Weil <sage@inktank.com> - 09:10 PM Revision 824dd52b (ceph): mon/MonCap: handle any whitespace (not just space)
- Backport: emperor, dumpling
Reported-by: Dmitry Borodaenko <dborodaenko@mirantis.com>
Signed-off-by: Sage Weil <sage@... - 09:06 PM Revision 8fc9f1b7 (ceph): use the absolute path for executables if found
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit a9334a1c8c6681305e76b361377864d0dd1e3d34) - 09:06 PM Revision a2de2f71 (ceph): remove trailing semicolon
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 43561f791607f5fd6f03d5421e1f30a29fb4194e) - 09:06 PM Revision 2cd22b5d (ceph): replace sgdisk subprocess calls with a helper
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit e19e38012bc4579054f63865e682c8c3a7829c7b) - 09:06 PM Revision e8cc27cc (ceph): Call --mbrtogpt on journal run of sgdisk should the drive require a GPT...
- Signed-off-by: Jonathan Davies <jonathan.davies@canonical.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by:... - 09:05 PM Revision 3942a93f (ceph): ceph-disk: blacklist /dev/fd0
- blkid -s TYPE /dev/fd0 has been verified to hang forever on a
H8DMR-82 supermicro motherboard running
3.8.0-33-gener... - 09:05 PM Revision ccc6b0c5 (ceph): Make fsid comparison case-insensitive
- get_fsid and find_cluster_by_uuid are modified so ceph-disk activate and
ceph-disk activate-all will work if the fsid... - 06:46 PM rgw Bug #7374: s3_multipart_upload.pl fails
- Also, use Amazon::S3 results in the same error message on a hello world perl script.
I got S3 installed via cpan (... - 06:41 PM rgw Bug #7374: s3_multipart_upload.pl fails
- Okay. I think that the Yaml file is okay. There appear to be make issues. The most noticable one is:...
- 06:35 PM Revision dce51969 (ceph): Merge pull request #1224 from kdreyer-inktank/packaging-libdir
- packaging: do not package libdir/ceph recursively
- 06:17 PM Revision 5a6c9508 (ceph): packaging: do not package libdir/ceph recursively
- Package libdir/ceph non-recursively, to avoid duplicates, and
package libdir/ceph/ceph_common.sh explicitly.
Signed-... - 06:10 PM Revision 367cf1bb (ceph): librbd: remove limit on number of objects in the cache
- The number of objects is not a significant indicated of when data
should be written out for rbd. Use the highest poss... - 06:10 PM Revision 4856fc29 (ceph): ObjectCacher: use uint64_t for target and max values
- All the options are uint64_t, but the ObjectCacher was converting them
to int64_t. There's never any reason for these... - 06:10 PM Revision a572aafe (ceph): ObjectCacher: remove max_bytes and max_ob arguments to trim()
- These are never passed, so replace them with the defaults.
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <j... - 06:08 PM Revision 48a71e22 (ceph): librbd: remove limit on number of objects in the cache
- The number of objects is not a significant indicated of when data
should be written out for rbd. Use the highest poss... - 06:08 PM Revision 65e83a34 (ceph): ObjectCacher: use uint64_t for target and max values
- All the options are uint64_t, but the ObjectCacher was converting them
to int64_t. There's never any reason for these... - 06:08 PM Revision 74ea7b2d (ceph): ObjectCacher: remove max_bytes and max_ob arguments to trim()
- These are never passed, so replace them with the defaults.
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <j... - 05:57 PM Bug #7408 (Resolved): filestore xattr use omap = true
- will be in next dumpling point release.
- 05:52 PM Bug #7408: filestore xattr use omap = true
- My code has been backported to Dumpling. So the filestore_xattr_use_omap will be gone from the next Dumpling release.
- 04:08 PM Bug #7408: filestore xattr use omap = true
- Let's see how we (Sage) decide to resolve #7404. I've created a pull request to backport my 6143 change completely. ...
- 02:22 PM Bug #7408: filestore xattr use omap = true
- As I understood Sage what's being done in Dumpling is to flip the default; if so then users still need a warning neve...
- 02:20 PM Bug #7408: filestore xattr use omap = true
- We've generated a couple different tickets about this now that I think are crossing wires, but we're about to backpor...
- 02:14 PM Bug #7408: filestore xattr use omap = true
- David Zafman wrote:
> The change for bug 6143 removed the configuration variable "filestore_xattr_use_omap" The new... - 02:09 PM Bug #7408: filestore xattr use omap = true
- The change for bug 6143 removed the configuration variable "filestore_xattr_use_omap" The new behavior is just like ...
- 01:54 PM Bug #7408 (Resolved): filestore xattr use omap = true
- At the core standup yesterday we talked about a really nasty bug where data loss can occur if filestore xattr use oma...
- 05:54 PM Revision f7cf25f2 (ceph): Merge pull request #1215 from ceph/wip-7385
- Remove the max cached objects restriction for librbd
Reviewed-by: Sage Weil <sage@inktank.com> - 05:29 PM Revision d0a43492 (ceph): Capture stderr and include in CommandFailedError
- Signed-off-by: John Spray <john.spray@inktank.com>
- 05:29 PM Revision 896412f2 (ceph): Remove spurious print
- This was causing junk output like <type 'exceptions.StopIteration'>
Signed-off-by: John Spray <john.spray@inktank.com> - 05:29 PM Revision ca83b7b2 (ceph): Timestamp stdout log output
- Signed-off-by: John Spray <john.spray@inktank.com>
- 05:29 PM Revision ab2a01ff (ceph): Catch a case where we weren't getting tracebacks
- Signed-off-by: John Spray <john.spray@inktank.com>
- 05:29 PM Revision d39dd8cb (ceph): Log correct name of context during errors
- (instead of GeneratorContextManager)
Signed-off-by: John Spray <john.spray@inktank.com> - 05:29 PM Revision d53a5b65 (ceph): Spelling
- Signed-off-by: John Spray <john.spray@inktank.com>
- 04:46 PM Revision 2b9a6bc0 (ceph): Merge pull request #182 from ceph/wip-imports
- Make libvirt import optional (OS X)
- 04:42 PM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
- The original rationale was to keep the existing behavior (not reading a conf file) and use None as a default value to...
- 12:55 PM Bug #7407 (New): Illogical defaults in Python bindings: conffile=None loads no config, conffile='...
- This feels weird:...
- 04:42 PM Revision eafeece2 (ceph): Show hostname instead of IP in errors
- Signed-off-by: John Spray <john.spray@inktank.com>
- 04:25 PM Revision f6afe8cc (ceph): Merge pull request #1199 from ceph/wip-doc-librados-intro
- Wip doc librados intro
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Loic Dachary <loic@dachary.org> - 03:12 PM Revision d728b7ab (ceph): Merge pull request #189 from ceph/wip-6536-wusui
- Add docstrings to s3 related tasks.
- 02:25 PM Fix #7394 (Fix Under Review): OSD: relax monitor ping requirements while connecting
- PR: https://github.com/ceph/ceph/pull/1227
- 01:47 PM devops Bug #7283 (Resolved): centos 6 - gitbuilder mod_ssl broken dependency
- I believe this is fixed now. It appears it installed ok if you just did a yum install mod_ssl but once httpd and http...
- 12:07 PM devops Bug #7283 (In Progress): centos 6 - gitbuilder mod_ssl broken dependency
- I completley missed this issue bieng assigned to me. It looks like a simple issue with the dependency string containi...
- 12:10 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
- I haven't looked at any of the code involved for real, but that sounds like a good plan to me. *thumbs up*
- 11:22 AM CephFS Bug #5382: mds: failed objecter assert on shutdown
- What's happening is that suicide() is getting called from another thread while the dispatch thread is inside _dispatc...
- 12:05 PM devops Bug #7334 (Pending Backport): ceph-disk: cannot run partprobe on used devices with EL6
- Alfredo - please cherry pick to Dumpling
- 11:52 AM Revision 48bcbc75 (ceph): Merge pull request #1221 from dachary/wip-filestore
- tests: fix packaging for s/filestore/objectstore/
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 11:46 AM Revision 840e918f (ceph): tests: fix packaging for s/filestore/objectstore/
- The binaries file name have changed and need to be updated in the
packaging files for deb and rpm. Fix a few leftover... - 11:37 AM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
- On commit 7fe10f1271dd94d4c5014a35c6362a7772dc4508
/a/teuthology-2014-02-09_23:00:13-rados-master-testing-basic-pl... - 11:26 AM Revision b88b2572 (ceph): Merge pull request #1220 from dachary/wip-filestore
- tests: fix objectstore tests
- 11:06 AM Bug #7387: Malformed JSON command output when non-ASCII strings are present
- Yeah -- I don't really want to open that can of worms either, and we'll add some extra hygiene here in Calamari.
B... - 10:52 AM Revision b64f1e39 (ceph): tests: fix objectstore tests
- The objectstore test from 1a588f18ba0e57df64f8a48c1393a4bc65019571 was
missing a few changes.
Signed-off-by: Loic Da... - 10:30 AM Feature #7404: backport default filestore_use_omap and superblock checking to dumpling
- The original change in master removed the filestore_xattr_use_omap variable. I checked current master branch and thi...
- 10:08 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
- 10:26 AM Bug #7345 (Need More Info): LibRadosTier.Evict failed in rados suite
- Deferring this since there are a bunch of other outstanding changes to this code.
- 10:17 AM Bug #7345 (In Progress): LibRadosTier.Evict failed in rados suite
- This hasn't failed in the nightlies since then (although there are other related failures which Sage is looking at), ...
- 09:54 AM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
- 09:52 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
- > > * filestore_xattr_use_omap can be enabled in a running cluster with no known side effects,
>
> We haven't conf... - 09:47 AM RADOS Cleanup #7402 (New): OSD: audit osdmap_subscribe calls to remove forced subscription attempts
- There are a number of places where the OSD subscribes to a map and forces the MonClient to renew its subscription. I ...
- 09:43 AM Bug #5804 (In Progress): mon: binds to 0.0.0.0:6800something port
- The 0.0.0.0 portion of the address is normal. Unless a monitor has a prebuilt monmap supplied at time of creation, al...
- 09:40 AM Fix #7395 (Fix Under Review): OSD: update osdmap subscription proactively instead of when we want...
- PR at https://github.com/ceph/ceph/pull/1223
- 08:06 AM Revision a065e2c0 (ceph): Merge pull request #1212 from ywang19/master
- correct one command line at building packages section
Reviewed-by: Loic Dachary <loic@dachary.org> - 06:24 AM Revision f34eb1b8 (ceph): mds: force update backtraces for previously created FS
- Update inode format version to 10, treat any previously created
inode as no backtrace. When inode with no backtrace i... - 05:17 AM Revision ed0980c9 (ceph): Merge pull request #1168 from yuyuyu101/wip-refactor-objectstore-test
- Rename test/filestore to test/objectstore
Reviewed-by: Sage Weil <sage@inktank.com> - 05:12 AM Revision 7f76e78b (ceph): Merge pull request #1218 from yuyuyu101/wip-misc-fix
- Fix bad dealloctor
Reviewed-by: Sage Weil <sage@inktank.com> - 05:10 AM Revision 7709d19f (ceph): Merge pull request #1211 from ceph/wip-memstore
- memstore: fix touch double-allocation
Reviewed-by: Samuel Just <sam.just@inktank.com> - 04:21 AM Revision cee713ff (ceph): Add docstrings to s3 related tasks.
- Fixes: 6536
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 04:21 AM Revision 7b638766 (ceph): Add docstrings to s3 related tasks.
- Fixes: 6536
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 04:04 AM Revision b5c10bf0 (ceph): Fix bad dealloctor
- Memory allocated by malloc() should be deallocated by free(), not 'delete'
Signed-off-by: Haomai Wang <haomaiwang@gm... - 02:38 AM Revision 33692a2c (ceph): osdmaptool: fix cli test
- Encoding the extra tunable byte threw off the output here.
Signed-off-by: Sage Weil <sage@inktank.com> - 02:38 AM Revision a4b3b786 (ceph): correct one command line at building packages section
- Signed-off-by: Wang, Yaguang <yaguang.wang@intel.com>
- 02:16 AM Revision fed83969 (ceph): tset_bufferlist: fix signed/unsigned comparison
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:54 AM Revision 8ca3d95b (ceph): rgw: multi object delete should be idempotent
- Fixes: #7346
When doing a multi object delete, if an object does not exist then we
should return a success code for t...
02/11/2014
- 11:44 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Josh Durgin wrote:
> Hi Wido,
>
> Attached is a patch to use the timeouts with a libvirt storage pool. I noticed ... - 06:27 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Hi Wido,
Attached is a patch to use the timeouts with a libvirt storage pool. I noticed that libvirt will actually... - 10:42 PM Revision 8533b6ac (ceph): Merge pull request #1185 from ceph/wip-crush
- crush: "vary_r" tunable
Reviewed-by: Loic Dachary <loic@dachary.org> - 10:36 PM Bug #7401 (Resolved): rados bench takes into account second '0' for stddev calculation
- For example:...
- 10:02 PM Revision bf38bfb2 (ceph): rgw: set bucket permissions, cors on swift creation
- Fixes: #7271
Swift bucket creation was ignoring the x-container-read,
x-container-write and the various cors related ... - 09:34 PM Revision e26bb356 (ceph): Add calamari setup/test tasks
- Signed-off-by: Warren Usui <warren.usui@inktank.com>
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 09:28 PM Revision 2682b64c (ceph): doc: Incorporated feed back from Loic and Dan.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:28 PM Revision 0da9621a (ceph): doc: Adds additional terms for use with librados.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:39 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
- To do additional debugging on this problem, I printed out my monmap with:
ceph mon getmap -o zzzz
got latest monm... - 08:15 PM Revision e1a49e53 (ceph): ObjectCacher: remove unused target/max setters
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 08:14 PM Revision 0559d31d (ceph): librbd: remove limit on number of objects in the cache
- The number of objects is not a significant indicated of when data
should be written out for rbd. Use the highest poss... - 08:06 PM Revision db034acf (ceph): ObjectCacher: use uint64_t for target and max values
- All the options are uint64_t, but the ObjectCacher was converting them
to int64_t. There's never any reason for these... - 08:06 PM Revision bf8cf2d6 (ceph): ObjectCacher: remove max_bytes and max_ob arguments to trim()
- These are never passed, so replace them with the defaults.
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <j... - 07:20 PM rgw Bug #7346 (Fix Under Review): An unfound object as part of multi-object delete should return dele...
- 04:48 PM rgw Bug #7346 (In Progress): An unfound object as part of multi-object delete should return deleted i...
- 07:12 PM Revision 525b2d26 (ceph): crush: add firefly tunables baseline test
- This is a user's map that gives different results when the vary_r tunable
is adjusted.
Signed-off-by: Sage Weil <sag... - 07:12 PM Revision e3309bce (ceph): doc/rados/operations/crush: describe new vary_r tunable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:12 PM Revision d136eb4c (ceph): mon: allow firefly crush tunables to be selected
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:11 PM Revision 37f840b4 (ceph): crushtool: new cli tests for the vary-r tunable
- These illustrate the variation in mapping results as the vary_r tunable
is adjusted. Note:
1- For the vary_r=0 case... - 05:44 PM Revision 453d72b2 (ceph): don't use notcmalloc flavor for valgrind
- We now have the suppressions to avoid this. Yay!
Signed-off-by: Sage Weil <sage@inktank.com> - 04:49 PM rgw Bug #7271 (In Progress): container create via swift doesn't register ACL
- 04:48 PM Revision e20a55d9 (ceph): crush: add infrastructure around new chooseleaf_vary_r tunable
- - encoding
- feature bit
- decompile/compile
Signed-off-by: Sage Weil <sage@inktank.com> - 04:48 PM Revision f944ccc2 (ceph): crush: add SET_CHOOSELEAF_VARY_R step
- This lets you adjust the vary_r tunable on a per-rule basis.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:48 PM Revision e88f843c (ceph): crush: add infrastructure around SET_CHOOSELEAF_VARY_R rule step/command
- This will let you vary the vary_r tunable on a per-rule basis.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:41 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
- IMO this is a big can of worms having to do with Ceph itself; I'm willing to bet that *none* of the internal routines...
- 04:32 PM Revision 4889234f (ceph): Merge pull request #1210 from dachary/dumpling
- common: admin socket fallback to json-pretty format (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com> - 04:31 PM Revision 30a346b5 (ceph): Merge pull request #1208 from dachary/emperor
- common: admin socket fallback to json-pretty format (emperor)
Reviewed-by: Sage Weil <sage@inktank.com> - 04:30 PM Revision dd200c92 (ceph): Merge pull request #1207 from dachary/wip-7378
- common: admin socket fallback to json-pretty format
Reviewed-by: Sage Weil <sage@inktank.com> - 03:14 PM Revision c36a6ed4 (ceph): Merge pull request #1198 from dachary/wip-mailmap
- mailmap updates
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 02:45 PM Fix #7395: OSD: update osdmap subscription proactively instead of when we want a new map
- Waiting for the gitbuilders to build the branch so I can run it through thrashing.
- 10:12 AM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
- In most circumstances, the OSD does a one-time subscription for the "next map" from what it has. But in a few places,...
- 01:14 PM rbd Bug #7385 (Fix Under Review): Objectcacher setting max object counts too low
- https://github.com/ceph/ceph/pull/1215
- 06:07 AM rbd Bug #7385: Objectcacher setting max object counts too low
- Does it make sense to be exposing this to librbd/client.cc at all vs just directly setting it via a config option? (o...
- 12:48 PM Bug #6101: ceph-osd crash on corrupted store
- (18:02:26) sage: poelzi: looks reasonable. can you make it log to the cluster log about the error, though? IIRC it ...
- 01:31 AM Bug #6101: ceph-osd crash on corrupted store
- Daniel Poelzleithner wrote:
> We deleted the rados block that was in the stack trace, but deleting it did not solve ... - 12:27 PM Bug #7398 (Resolved): osd: ERANGE from clone
- ubuntu@teuthology:/a/teuthology-2014-02-10_23:01:27-rbd-master-testing-basic-plana/76311...
- 11:33 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
- Florian Haas wrote:
> * filestore_xattr_use_omap can be enabled in a running cluster with no known side effects,
... - 07:25 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
- This issue has caused data corruption in at least one user (Inktank PS is well aware of this).
Since
* https://g... - 09:59 AM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
- Right now, the OSD will time out a monitor after 30 seconds if it fails to ack a PGStats message. But sometimes, the ...
- 09:53 AM Bug #7393 (Duplicate): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whit...
- from new scrub before test teardown.
- 09:41 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
- yay
- 09:41 AM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
- 09:38 AM Revision 9e43f939 (ceph): mailmap: Dmitry Smirnov is with Debian GNU/Linux
- Reviewed-by: Dmitry Smirnov <onlyjob@member.fsf.org>
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:38 AM Revision ac16fd6e (ceph): mailmap: Derek Yarnell is with University of Mississippi
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:37 AM Revision 0869fcb4 (ceph): mailmap: Eric Mourgaya is with Credit Mutuel Arkea
- and name normalization
Reviewed-by: Eric Mourgaya <eric.mourgaya@arkea.com>
Signed-off-by: Loic Dachary <loic@dachar... - 09:18 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
- 12:18 AM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
Line numbers are relative to b9a127e
src/client/Client.cc:113 is not safe
src/osdc/Objecter.cc:2509 i...- 08:41 AM Revision 04e78f89 (ceph): common: admin socket fallback to json-pretty format
- If the format argument to a command sent to the admin socket is not
among the supported formats ( json, json-pretty, ... - 08:36 AM Revision 30a604d2 (ceph): common: admin socket fallback to json-pretty format
- If the format argument to a command sent to the admin socket is not
among the supported formats ( json, json-pretty, ... - 08:21 AM Revision 165e76d4 (ceph): common: admin socket fallback to json-pretty format
- If the format argument to a command sent to the admin socket is not
among the supported formats ( json, json-pretty, ... - 06:36 AM devops Bug #7391 (Resolved): ceph-deploy should pass the verbose flag to ceph-disk
- Any and all output from ceph-disk is useful, no need to be quiet about it because it makes it extremely hard
to debu... - 05:53 AM devops Bug #7390 (Resolved): ceph-deploy should remove ceph-release and call yum clean all
- When uninstalling ceph (or when purging) not removing ceph-release and not calling yum clean all leaves yum in a terr...
- 05:52 AM Revision e98e344d (ceph): client ownership info validation corrected
- 05:44 AM Revision f2f4eb5b (ceph): Updated client code to complete PUT and DELETE requests
- 03:04 AM Revision 69682ad1 (ceph): memstore: fix touch double-allocation
- Reported-by: Allen Samuels <allen.samuels@sandisk.com>
Signed-off-by: Sage Weil <sage@inktank.com> - 01:55 AM Bug #7093: osd: peering can send messages prior to auth
- I would like to add the following comment because I have learned that this is related to an issue we have seen in the...
- 12:25 AM Revision 51957433 (ceph): Merge pull request #184 from ceph/wip-pg-scrub-from-ceph-wusui
- Scrub osds when ceph task finishes
- 12:02 AM Revision f9bad673 (ceph): MonClient: add a timeout on commands for librados
- Just use the conf option directly, since librados is the only caller.
Signed-off-by: Josh Durgin <josh.durgin@inktan... - 12:02 AM Revision 979b4cba (ceph): msg/Pipe: add option to restrict delay injection to specific msg type
- This makes it possible to test timeouts reliably by delaying certain
messages effectively forever, but still being ab... - 12:02 AM Revision dde21dc8 (ceph): librados: check and return on error so timeouts work
- Some functions could not previously return errors, but they had an
int return value, which can now receive ETIMEDOUT.... - 12:02 AM Revision 327ca1a4 (ceph): rados: check return values for commands that can now fail
- A few places were not checking the return values of commands, since
they could not fail before timeouts were added.
... - 12:02 AM Revision e06f8199 (ceph): qa: add script for testing rados client timeout options
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 9e62beb80b6c92a97ec36c0db5ea39e417661... - 12:02 AM Revision 69b1e5e5 (ceph): Objecter: implement mon and osd operation timeouts
- This captures almost all operations from librados other than mon_commands().
Get the values for the timeouts from th...
02/10/2014
- 11:59 PM Cleanup #7388 (Closed): ceph osd find has no format argument
- Although it appears to "handle a format argument":https://github.com/ceph/ceph/blob/v0.76/src/mon/OSDMonitor.cc#L2231...
- 11:54 PM Revision b39f1486 (ceph): librados: add timeout to wait_for_osdmap()
- This is used by several pool operations independent of the objecter,
including rados_ioctx_create() to look up the po... - 11:53 PM Revision 713cef05 (ceph): conf: add options for librados timeouts
- These will be implemented in subsequent patches.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked... - 11:52 PM Revision 576465fa (ceph): Merge pull request #1209 from fghaas/master
- doc: highlight that "raw" is the only useful RBD format for QEMU
- 11:45 PM Revision 6af657bd (ceph): qa: add script for testing rados client timeout options
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 9e62beb80b6c92a97ec36c0db5ea39e417661... - 11:45 PM Revision 21a0b674 (ceph): rados: check return values for commands that can now fail
- A few places were not checking the return values of commands, since
they could not fail before timeouts were added.
... - 11:45 PM Revision 2c42dd26 (ceph): librados: check and return on error so timeouts work
- Some functions could not previously return errors, but they had an
int return value, which can now receive ETIMEDOUT.... - 11:45 PM Revision 28fe564c (ceph): msg/Pipe: add option to restrict delay injection to specific msg type
- This makes it possible to test timeouts reliably by delaying certain
messages effectively forever, but still being ab... - 11:45 PM Revision 1d2ea9ef (ceph): MonClient: add a timeout on commands for librados
- Just use the conf option directly, since librados is the only caller.
Signed-off-by: Josh Durgin <josh.durgin@inktan... - 11:45 PM Revision 30dafacd (ceph): Objecter: implement mon and osd operation timeouts
- This captures almost all operations from librados other than mon_commands().
Get the values for the timeouts from th... - 11:30 PM Revision 9292cc21 (ceph): doc: highlight that "raw" is the only useful RBD format for QEMU
- Explain why people should be using the "raw" image format for RBD
volumes created for use by QEMU: using any other fo... - 11:24 PM Revision 2aa0d758 (ceph): librados: add timeout to wait_for_osdmap()
- This is used by several pool operations independent of the objecter,
including rados_ioctx_create() to look up the po... - 11:21 PM Revision 55d254d5 (ceph): conf: add options for librados timeouts
- These will be implemented in subsequent patches.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked... - 10:12 PM Revision 32aa9fdf (ceph): Merge branch wip-librados-timeout
- Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dachary <loic@dachary.org> - 09:40 PM Revision ad6d412e (ceph): Fix #7369: "sed expression must be raw string"
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 09:09 PM Revision af5d0fcd (ceph): Merge pull request #1205 from ceph/wip-7334
- use `partx` for CentOS/RHEL instead of `partprobe`
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:59 PM Revision 78240c26 (ceph): Merge pull request #1204 from ceph/wip-fsetpipesz-fix
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 08:53 PM Revision d389e617 (ceph): msg/Pipe: add option to restrict delay injection to specific msg type
- This makes it possible to test timeouts reliably by delaying certain
messages effectively forever, but still being ab... - 08:53 PM Revision 8e9459e8 (ceph): librados: check and return on error so timeouts work
- Some functions could not previously return errors, but they had an
int return value, which can now receive ETIMEDOUT.... - 08:53 PM Revision 79c18743 (ceph): rados: check return values for commands that can now fail
- A few places were not checking the return values of commands, since
they could not fail before timeouts were added.
... - 08:53 PM Revision 9e62beb8 (ceph): qa: add script for testing rados client timeout options
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 08:53 PM devops Feature #6020: radosgw-apache opinionated package
- For reference, Gary's WIP branch is here: https://github.com/ceph/ceph/tree/wip-6020
- 08:53 PM Revision 3e1f7bbb (ceph): Objecter: implement mon and osd operation timeouts
- This captures almost all operations from librados other than mon_commands().
Get the values for the timeouts from th... - 08:53 PM Revision 671a76d6 (ceph): MonClient: add a timeout on commands for librados
- Just use the conf option directly, since librados is the only caller.
Signed-off-by: Josh Durgin <josh.durgin@inktan... - 08:09 PM Revision 9bcc42a3 (ceph): alert the user about error messages from partx
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
- 08:09 PM Revision 42900ff9 (ceph): use partx for red hat or centos instead of partprobe
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
- 08:06 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
- > mon_lease_ack_timeout = 10
> mon_accept_timeout = 10
Thanks Sage! After changing the above configuration to 30, t... - 05:57 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
- The (compiled) osdmap attached.
- 09:40 AM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
- can you attach a copy of your osdmap so we can see what the time might be spent on?
in the meantime, you can incre... - 01:24 AM Bug #7376 (Resolved): mon: >10s spent in remove_redundant_pg_temp
- We have a cluster which has 3 monitors, most recently, due to server restart (for both OSDs and Monitors), the cluste...
- 07:49 PM Revision 97617c99 (ceph): Fix broken symlinks.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 06:44 PM Bug #6101: ceph-osd crash on corrupted store
- The patch removes the assert in case the trim event is done an a non existing context.
I think this is save and shou... - 06:19 PM Revision 2c5783cc (ceph): Merge remote-tracking branch 'gh/next'
- 05:49 PM rgw Bug #7374: s3_multipart_upload.pl fails
- I believe that this is a yaml file problem (Same issue as 7375). I am investigating.
- 04:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
- The problem could also be in the packaging
- 04:27 PM rgw Bug #7374: s3_multipart_upload.pl fails
- I've been looking at this. There may be a problem with the script in that a directory is not there that the script e...
- 05:48 PM rgw Bug #7375: s3_user_quota.pl fails
- I believe that the yaml files are not right here. This is probably a ceph-qa-suite problem. I am still investigatin...
- 05:37 PM Revision 450163ec (ceph): configure: don't check for arpa/nameser_compat.h twice
- Nuke redundant check and move the real one into the common
AC_CHECK_HEADERS stanza.
Signed-off-by: Ilya Dryomov <ily... - 05:37 PM Revision a5f479c2 (ceph): configure: fix F_SETPIPE_SZ detection
- Currently CEPH_HAVE_SETPIPE_SZ is not set even if F_SETPIPE_SZ is
available, because AC_COMPILE_IFELSE test program a... - 05:37 PM Revision 69262720 (ceph): common/buffer: fix build breakage for CEPH_HAVE_SETPIPE_SZ
- common/buffer.cc fails to build if CEPH_HAVE_SETPIPE_SZ is defined.
Fix it.
Signed-off-by: Ilya Dryomov <ilya.dryomo... - 05:28 PM Revision ceffee40 (ceph): Make sure osd_scrub_pgs gets called if healthy call fails.
- Fixes: 7198
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 05:14 PM Revision f6bac22d (ceph): Merge pull request #6 from ceph/wip-set-inline
- fs: Fix bad "mds set inline_data" syntax
- 05:11 PM Feature #6507 (Resolved): librados shouldn't block indefinitely when cluster doesn't respond
- merged in commit:32aa9fdf666063e4c5539b5e850f04af37e30b2e to master, backported to dumpling around commit:30dafacd0b5...
- 05:11 PM Revision b2d34313 (ceph): fs: Fix bad "mds set inline_data" syntax
- Signed-off-by: John Spray <john.spray@inktank.com>
- 04:35 PM Revision c1d2a997 (ceph): libcephfs: fix documentation for ceph_readlink
- ceph_readlink() and ceph_ll_readlink() both return the number of bytes
copied on success, which the callers need to g... - 03:52 PM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
- "dumpling backport":https://github.com/ceph/ceph/pull/1210
"emperor backport":https://github.com/ceph/ceph/pull/1208
- 03:12 PM Bug #7378 (Fix Under Review): ceph --format plain --admin-socket mon.asok crashes the mon
- "work in progress":https://github.com/ceph/ceph/pull/1207
- 09:55 AM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
- For what it's worth, it's not a blocker for me. The "plain" format is documented to not being supported and it only h...
- 07:25 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
- Steps to reproduce, from the src dir on todays master:...
- 03:46 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
- Urgh, redmine apparently can't cope with unicode either! Here's what the snipped should look like http://pastebin.co...
- 03:45 PM Bug #7387 (Resolved): Malformed JSON command output when non-ASCII strings are present
Ceph accepts non-ascii input when setting e.g. the name of a pool. Subsequently, when using human-formatted CLI ou...- 03:29 PM rbd Bug #7385: Objectcacher setting max object counts too low
- This is set by librbd or ceph-fuse's Client.cc after creating the objectcacher. There's already a config option for C...
- 03:19 PM rbd Bug #7385 (Resolved): Objectcacher setting max object counts too low
- It appears that the objectcacher is setting max object counts based on the max dirty data size and object size. With...
- 03:24 PM RADOS Documentation #7386 (Won't Fix): librados: document rados_osd_op_timeout and rados_mon_op_timeout...
- These were added in https://github.com/ceph/ceph/pull/1192. They shouldn't be used generally, but are useful for libr...
- 02:04 PM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
- merged into ceph's master branch af5d0fc
- 12:36 PM devops Bug #7334 (Fix Under Review): ceph-disk: cannot run partprobe on used devices with EL6
- pull request opened https://github.com/ceph/ceph/pull/1205
- 01:46 PM Revision dbaf71aa (ceph): mailmap: Moritz Möller is with Bigpoint.com
- Reviewed-by: Moritz Möller <mm@mxs.de>
Signed-off-by: Loic Dachary <loic@dachary.org> - 01:42 PM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
- I change the ceph-disk a little bit:
In mount_active, mount the disk using default mount options, then activate it t... - 11:35 AM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
- After the disk are prepared, udev notices the disk label and this rule calls ceph-disk-activate: https://github.com/c...
- 09:51 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
- ...
- 08:58 AM Tasks #7377 (Resolved): security Certificate is out of date
- 07:49 AM Tasks #7377: security Certificate is out of date
- Greg Farnum wrote:
> I think this should be resolved already, based on an email discussion.
Yes, thats correct. T... - 06:45 AM Tasks #7377: security Certificate is out of date
- I think this should be resolved already, based on an email discussion.
- 01:39 AM Tasks #7377 (Resolved): security Certificate is out of date
- The certificate of https://ceph.com/git/?p=ceph.git;a=blob_plain;f=keys/release.asc is ended yesterday (8-2-2014).
A... - 07:08 AM Revision 4cf2c726 (ceph): Server changes to deploy in a production env
- 1. Added the wsgi entry point app.wsgi
2. Updated client code to mandate the update-metadata to have url to publish a... - 05:32 AM Bug #7367: fail to run mds and mount rbd (v0.76)
- Quick follow Up ;
with 0.76 OSD, MON, MDS: Creating new volume , formatting, mounting leads to normal comportment.
... - 04:53 AM Revision ccd9b5eb (ceph): test_striper: fix warning
- Signed-off-by: Sage Weil <sage@inktank.com>
02/09/2014
- 09:01 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
- http://pulpito.ceph.com/teuthology-2014-02-08_23:02:22-rgw-next-distro-basic-plana/
- 09:01 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
- http://pulpito.ceph.com/teuthology-2014-02-08_23:02:22-rgw-next-distro-basic-plana/
- 08:57 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
- My guess is that this is due to the new ACL code.
http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-08_23:05... - 06:37 PM Revision 39b393d7 (ceph): Merge remote-tracking branch 'gh/wip-7329' into next
- 03:59 PM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
- Hi, I was trying to fix this today. But in my cluster, disk was activated automatically right after ceph-disk-prepare...
- 03:05 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
- ...
- 03:02 PM Bug #7371 (Resolved): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- ubuntu@teuthology:/a/teuthology-2014-02-08_23:05:12-kcephfs-next-testing-basic-plana/73644
tasks:
- chef: null
-... - 10:38 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
- see #7329 for the first two failures.
- 10:38 AM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
- 04:20 AM Revision 575566b1 (ceph): ceph_test_rados_api_tier: try harder to trigger the flush vs try-flush ...
- It seems to be reasonable easy to complete a flush before the next client
request is processed. Crazy...
Same with ... - 12:12 AM Revision 270714d5 (ceph): Merge pull request #1201 from ceph/wip-7370
- crush: fix tries/retries bug that was recently introduced
Reviewed-by: Loic Dachary <loic@dachary.org>
02/08/2014
- 11:58 PM Revision 7fe10f12 (ceph): Merge pull request #1115 from jcsp/tell_cleanup
- Remove some almost-duplicate COMMAND definitions
Reviewed-by: Loic Dachary <loic@dachary.org> - 11:33 PM Revision cf2d71ce (ceph): Merge pull request #1127 from dmsimard/log_links
- Doc: Fix 404 broken links to logging and debug configuration
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Revi... - 09:15 PM Bug #6003: journal Unable to read past sequence 406 ...
- ubuntu@teuthology:/a/sage-2014-02-08_15:50:23-rados:thrash-wip-agent-testing-basic-plana/72854
- 09:14 PM Bug #7329: osd: LibRadosTier.FlushTryFlushRaces failures
- 08:27 PM Revision a8e6c9fb (ceph): crush: add chooseleaf_vary_r tunable
- The current crush_choose_firstn code will re-use the same 'r' value for
the recursive call. That means that if we ar... - 08:24 PM Revision bb44c0d5 (ceph): crushtool: add cli test for off-by-one tries vs retries bug
- See bug #7370. This passes on dumpling and breaks prior to the #7370 fix.
Backport: emperor, dumpling
Signed-off-by... - 08:23 PM Revision f17caba8 (ceph): crush: allow crush rules to set (re)tries counts to 0
- These two fields are misnomers; they are *retry* counts.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:21 PM Revision 795704fd (ceph): crush: fix off-by-one errors in total_tries refactor
- Back in 27f4d1f6bc32c2ed7b2c5080cbd58b14df622607 we refactored the CRUSH
code to allow adjustment of the retry counts... - 08:21 PM Revision ed32c400 (ceph): crushtool: add cli test for off-by-one tries vs retries bug
- See bug #7370. This passes on dumpling and breaks prior to the #7370 fix.
Backport: emperor, dumpling
Signed-off-by... - 04:23 PM Revision 5bc8e9e4 (ceph): Merge remote-tracking branch 'gh/next'
- 04:22 PM Revision 75c55258 (ceph): qa/workunits/rest: use larger max_file_size
- 64k is the min.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:14 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
- "resolved by":https://github.com/ceph/ceph/pull/1201
- 12:20 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
- i broken crush tries behavior when refactoring in commit:27f4d1f6bc32c2ed7b2c5080cbd58b14df622607
- 02:31 PM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
- 471c67828cf98224f89bd8efb28d377f8d745b7a
- 02:30 PM Feature #7366: EC: scrubbing
- 02:30 PM Feature #7361: EC: arrange for chunks to have some padding where we can later add checksums
- 01:56 PM devops Feature #5214: Kernel gitbuilders for rpm distros
- Forgot to update this as it was getting pretty late last night. I got gitbuilders up for:
rhel7beta
rhel6 (6.5)
... - 01:10 PM Revision 17c8a230 (ceph): mailmap: Yan, Zheng name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 01:10 PM Revision a2dae0d7 (ceph): mailmap: Somnath Roy is with SanDisk
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 01:10 PM Revision 5d20c8da (ceph): mailmap: Ray Lv is with Yahoo!
- Reviewed-by: Ray Lv <xiangyulv@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:41 AM Revision 1a588f18 (ceph): Rename test/filestore to test/objectstore
- Now ObjectStore support three backend types, so we need to make each backend
share unit test to avoid duplicate codes... - 06:27 AM Revision 3d656600 (ceph): script to test rgw multi part uploads using s3 interface
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
(cherry picked from commit 5d59dd9cd67834d991b038323bcbc3e8f8612... - 06:22 AM Revision 9506377c (ceph): rgw task for multipart upload script
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:15 AM Revision 5d59dd9c (ceph): script to test rgw multi part uploads using s3 interface
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 04:08 AM CephFS Feature #7352: mds: make classes encode/decode-able
- It's maybe a bit less broad than it sounds (in my mind at least) -- I'm concentrating on the in-rados representations...
- 02:25 AM Subtask #5857 (Resolved): Refactor recovery to use PGBackend methods
- 02:24 AM Subtask #5856 (Resolved): Refactor Backfill to use PGBackend methods
- 01:39 AM Feature #7195: librados: complete C write object operation bindings
- "implementation":https://github.com/ceph/ceph/commit/33717b4f60ce0ba7088164182b99eaf48cf0486f
- 01:10 AM Revision d4e5db58 (ceph): Merge branch 'next' of github.com:ceph/ceph into next
- 01:09 AM Revision 0bac064e (ceph): added script to test rgw user quota
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:07 AM Revision b4a2a2b0 (ceph): s/rgw_user_quota.pl/rgw_user_quota.yaml
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
02/07/2014
- 11:49 PM Revision 8cb3dad5 (ceph): doc: Added Python doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:48 PM Revision 22afd6ca (ceph): doc: Added inline literal tag.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:47 PM Revision aaa2799f (ceph): doc: Adds Python to index and sets maxdepth to 2.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:35 PM Revision 24d89e24 (ceph): task for rgw user quota testing
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 11:34 PM Revision 0f2386a1 (ceph): script to test rgw user quota functionality
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:54 PM Revision 69f29d17 (ceph): Move osd_scrub_pgs call to finally block of ceph main task.
- Fixes: 7198
Signed-off-bye: Warren Usui <warren.usui@inktank.com> - 10:04 PM Revision 935f8b3e (ceph): client/fuse_ll: adapt to new ll_ interface
- This adapts the FUSE client to David Zafman's proposed interface
changes.
(Includes pieces of NFS interface widening... - 10:04 PM Revision e2dc1b6b (ceph): libcephfs: expose new client ll_ interface
- This patch exposes all changes made for interfacing with Ganesha
and layout support and David Zafman's proposed modif... - 10:04 PM Revision acf2e493 (ceph): libcephfs: add ceph_ll_lookup_root()
- Signed-off-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com>
- 10:04 PM Revision 55a20c03 (ceph): libcephfs: add ceph_ll_listxattr
- Signed-off-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com>
- 10:04 PM Revision 77047ee4 (ceph): libcephfs: add an xattr ll test
- Signed-off-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com>
- 10:04 PM Revision afcc7eb4 (ceph): mds: include requested caps (namely, xattrs) on getattr reply
- For xattrs, we only include them in the reply if we are issuing caps on
them. However, in the getattr case, we need ... - 10:04 PM Revision 349b8168 (ceph): client, libcephfs: make readlink sane
- Supply a buffer and copy the data into it. Do not ever expose internal
pointers from libcephfs's own cache.
Signed-... - 10:04 PM Revision c1b07149 (ceph): client: For rebase need to fix ll_readlink() call in Synthetic client
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 10:04 PM Revision 16ae4f84 (ceph): fuse: fix for missing ll_ref on create
- when the 'Inode **outp' argument was added to ll_create(), it was
changed to only take the ll_ref if outp was not NUL... - 10:04 PM Revision dad91b5e (ceph): client: direct read/write methods that bypass cache, cap checks
- These methods were created to implement pNFS data server support,
bypassing cap checks since the pNFS MDS holds a cap... - 10:04 PM Revision 9ad8f571 (ceph): client/SyntheticClient: adapt to new ll_* interface
- (Includes pieces of NFS interface widening by Adam.)
Signed-off-by: Matt Benjamin <matt@linuxbox.com> - 10:04 PM Revision b700768b (ceph): client: expose layout information
- This allows us to construct pNFS layouts and DS filehandles that
match the Ceph clustering, placement, and striping s... - 09:47 PM Revision e08210dd (ceph): client: switch ll_* methods to Inode* arguments
- This commit implements a set of API changes proposed by
"David Zafman" <david.zafman@inktank.com>.
The principle cha... - 08:58 PM Revision 3752660d (ceph): client/Client: make open fhp argument optional
- This is more natural for both FUSE and Ganesha.
Signed-off-by: Matt Benjamin <matt@linuxbox.com> - 08:58 PM Revision 23577c8e (ceph): client/Client: return 1 from readdir cb on full
- This appears to save us a bit of extra work trying to fill up the buffer
further than it can be filled.
Signed-off-b... - 08:55 PM Revision ff046296 (ceph): client: add barrier and types
- This gives us a framework to implement commit operations that are
guaranteed to terminate even if unstable writes com... - 08:54 PM Revision 7f6d755c (ceph): client: whitespace
- Signed-off-by: Matt Benjamin <matt@linuxbox.com>
- 08:50 PM Revision 7f9fdc33 (ceph): osdc/Objecter: whitespace
- Signed-off-by: Matt Benjamin <matt@linuxbox.com>
- 08:48 PM Revision 548ccd9e (ceph): mds/Server: whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Matt Benjamin <matt@linuxbox.com> - 06:21 PM Revision b04ae134 (ceph): Merge pull request #1197 from ceph/wip-osdmap-primary
- osd/OSDMap: populate *primary when pool dne
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:38 PM Revision 3a5fa876 (ceph): osd/OSDMap: populate *primary when pool dne
- This fixes a valgrind error from OSD::handle_osd_map where primary is not
initialized and is compared after the call ... - 05:26 PM Revision 4cca38ca (ceph): Merge pull request #1173 from ceph/wip-7109
- Fix #7109: Prevent removal of default data pool
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:43 PM Revision 5b7e2b22 (ceph): rgw: initialize variable before call
- Need to initialize the truncated variable, as we sometimes ignore error
response (e.g., with ENOENT), and in such cas... - 04:43 PM Revision ebe505b9 (ceph): Merge pull request #1191 from ceph/wip-rgw-vg
- rgw: initialize variable before call
Revewed-by: Sage Weil <sage@inktank.com> - 04:10 PM Revision ed438aaa (ceph): Merge pull request #1194 from dachary/wip-erasure-code-directory
- erasure code directory
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 03:56 PM Bug #7368 (Can't reproduce): ceph osd repair * blocks after some minutes and prevent other ceph p...
- Hello,
this is a follow up of http://tracker.ceph.com/issues/7367
An unfortunate update To 0.75 endend with lots ... - 03:46 PM CephFS Feature #7352: mds: make classes encode/decode-able
- This is...remarkably broad. Do we have an order of priorities or anything? :)
- 03:45 PM CephFS Fix #7109 (Resolved): disallow removing the first data pool
- Merged into master in commit:4cca38c
- 03:39 PM Bug #7367: fail to run mds and mount rbd (v0.76)
- Hello, all & thanks to loic for taking the time to make a bugreport.
The problem occured on one of my cluster, th... - 02:19 PM Bug #7367: fail to run mds and mount rbd (v0.76)
- Is this a CephFS or an RBD bug report?
(Perhaps it should be two different ones. :p) - 02:16 PM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
- ...
- 03:12 PM Revision 0e9adf73 (ceph): Merge pull request #1178 from ceph/wip-osdmaptool
- osdmaptool: add --test-map-pgs mode
Reviewed-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Loic Dachary <loic@... - 03:10 PM Revision b98eaa5c (ceph): osdmaptool: test --import/export-crush
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:10 PM Revision 45d31f09 (ceph): osdmaptool: tests for --test-map-pgs
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:10 PM Revision 362825c4 (ceph): osdmaptool: fix cli tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:10 PM Revision 7c310368 (ceph): osdmaptool: s/simple.t/missing-argument.t/
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:10 PM Revision 7f1b12f2 (ceph): osdmaptool: add --test-map-pgs mode
- This command will map all pgs from all pools (or just one pool) to osds
and summarize the placement and calculate the... - 03:10 PM Revision 9caaef71 (ceph): osdmaptool: allow a completely random placement
- This useful for comparison purposes and sanity-checking the results.
Signed-off-by: Sage Weil <sage@inktank.com> - 02:11 PM Revision bb6d3f81 (ceph): rest/test.py: use larger max_file_size for mds set test
- Current min is 64k.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:40 PM Revision f584de57 (ceph): With functionality test cases. Test it using 'python setup.py test'
- 01:26 PM Feature #7366 (Resolved): EC: scrubbing
- Fill in the ECBackend methods for shallow and deep scrubbing
- 11:41 AM Revision 302fc924 (ceph): mon: s/ENOSYS/ENOTSUP/
- On Linux ENOTSUP is remapped
/usr/include/x86_64-linux-gnu/bits/errno.h
/* Linux has no ENOTSUP error code. */
... - 10:25 AM Revision e1e6c458 (ceph): Completed model and controller code
- 1. GET, PUT and DELETE request are added
2. Removed public folder as it will never be used - 09:59 AM Bug #6101: ceph-osd crash on corrupted store
- We deleted the rados block that was in the stack trace, but deleting it did not solve the problem.
The node still cr... - 09:31 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
- Is it actually that much work to enable? We'll want it in the future and it'll be easier if it's set up using the cor...
- 09:24 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
- Greg Farnum wrote:
> Unless you've already done so, the agent will also need to be recast the same way. We might as ... - 09:15 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
- Unless you've already done so, the agent will also need to be recast the same way. We might as well make this work pr...
- 09:13 AM devops Bug #7334 (In Progress): ceph-disk: cannot run partprobe on used devices with EL6
- 04:57 AM Subtask #7363 (Rejected): erasure code: reduce the chunk size to a minimum
- make sure the jerasure cauchy technique does not oversize chunks, see "related mail thread":http://www.spinics.net/li...
- 04:23 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
- "pulpito report":http://pulpito.ceph.com/teuthology-2014-02-05_23:00:49-rados-master-testing-basic-plana/69541/
"cor... - 04:07 AM Feature #7266: erasure code : implement locality (was pyramid)
- "primary affinity":https://github.com/ceph/ceph/pull/1176
- 03:13 AM Revision 42a64e19 (ceph): Revert test case of "mon: OSDMonitor: do not allow changing an erasure-...
- This reverts part of commit c8c4cc6e81816069886af6bff968712993554759.
Fixes: #7355
Signed-off-by: David Zafman <dav... - 12:54 AM Revision 0aa25b17 (ceph): Some suggested changes, both errors and rewordings
- Python and C code examples tweaked a bit
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:48 AM rgw Bug #6621 (Resolved): quota: the max-size and max-objects value when zero
- 12:29 AM rgw Bug #6621 (In Progress): quota: the max-size and max-objects value when zero
02/06/2014
- 09:32 PM Fix #6483: osd: does not fill in OSDOp::rval member
- Running this through the rados suite. It's in wip-librados-op-rvals, which is on top of https://github.com/ceph/ceph/...
- 09:32 PM Fix #6483 (Fix Under Review): osd: does not fill in OSDOp::rval member
- https://github.com/ceph/ceph/pull/1195
- 09:31 PM Feature #7194 (Fix Under Review): librados: omap in the c api
- https://github.com/ceph/ceph/pull/1195
- 09:31 PM Feature #7193 (Fix Under Review): librados: object operation bindings for reads
- https://github.com/ceph/ceph/pull/1195
- 09:31 PM Bug #7250 (Fix Under Review): osd: string xattr comparison can have undefined behavior
- https://github.com/ceph/ceph/pull/1195
- 09:30 PM Feature #7195 (Fix Under Review): librados: complete C write object operation bindings
- https://github.com/ceph/ceph/pull/1195
- 07:53 PM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
- 07:52 PM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
- nvm
- 07:18 PM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
- 42a64e19b7a06c1b3e0fd40e2d9c572103e3e426
- 03:07 PM Bug #7355 (In Progress): assert(0) in_make_pg() because EC getting enabled
- 11:49 AM Bug #7355: assert(0) in_make_pg() because EC getting enabled
- 2014-02-06T01:24:45.644 INFO:teuthology.task.workunit.client.0.err:[10.214.133.32]: + ceph osd pool delete fuggg fugg...
- 11:45 AM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
- 07:18 PM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
- "Work in progress":https://github.com/ceph/ceph/pull/1267
Once OSDs can handle Erasure Coding we should add back t... - 04:10 PM rados-java Bug #7359: [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-plana suite
- Same issue was reported in ceph project - BUG #7354
- 03:52 PM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-05_23:00:49-rados-master-testing-basic-plana/69709...
- 01:38 PM Subtask #7358 (Rejected): erasure code : plugin upgrade documentation
- when a plugin is upgraded and its behavior changes, it must be renamed. That is until there is a more sophisticated p...
- 01:36 PM Subtask #7292 (Rejected): erasure code: plugin backward compatibility
- For Firefly it is enough to document. If a new backward compatible plugin is introduced in Giant, it will need to hav...
- 09:36 AM Subtask #7292: erasure code: plugin backward compatibility
- Or maybe a increasing version and mandatory backward compatibility is all we need and compatset is overkill
- 05:50 AM Subtask #7292 (Need More Info): erasure code: plugin backward compatibility
- Is there a better way to prepare an upgrade path without over engineering it ?
- 02:18 AM Subtask #7292: erasure code: plugin backward compatibility
- "work in progress":https://github.com/ceph/ceph/pull/1193
- 01:45 AM Subtask #7292 (In Progress): erasure code: plugin backward compatibility
- 12:45 PM devops Bug #7356 (Rejected): Kill all while loops that will never end....
- Ok maybe with the one exception of one of mine that is for VPS creation... If the host machine is down then it will j...
- 12:36 PM Revision 30fd0c55 (ceph): Intial version of the server code.
- 1. Database modelling is done
2. PUT request is completed - 11:49 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
- Hi,
I am seeing the same issue on my clusters with 3 monitors. I am running:
ceph --version
ceph version 0.7... - 11:45 AM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure
During master run and a also my branch which has a backfill fix we have seen the following test case failures:
L...- 11:12 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
- Duplicate of #7336. Already fixed on next.
- 10:34 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-05_23:02:36-rgw-master-testing-basic-plana/69941/
... - 10:31 AM Bug #7350: osd: scrub does not detect recently touched and then renamed backend files
- Thanks Sage -- I can confirm that the issue does not appear when echo'ing directly into the file. So evidently it was...
- 09:40 AM Bug #7350: osd: scrub does not detect recently touched and then renamed backend files
- the problem is that vi is renaming the file and we cache recently opened files. use echo asdf >> file or similar to ...
- 04:18 AM Bug #7350 (Won't Fix): osd: scrub does not detect recently touched and then renamed backend files
- This is on Dumpling (0.67.5-1precise).
Steps to reproduce:
> Create a single-byte RADOS object and read it back... - 10:28 AM Revision fc963acf (ceph): erasure-code: move test files to a dedicated directory
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:28 AM Revision 7baa62f6 (ceph): erasure-code: move source files to a dedicated directory
- The src/erasure-code directory contains the erasure-code plugin system
and the jerasure plugin. It is moved out of OS... - 09:57 AM Feature #6507 (Fix Under Review): librados shouldn't block indefinitely when cluster doesn't resp...
- https://github.com/ceph/ceph/pull/1192
- 07:48 AM Documentation #6465: admin/build-doc should have some kind of build check for broken links
- No updates here, assigning back to John since this looks like a problem with the build.
The one change added to th... - 07:00 AM CephFS Feature #7352: mds: make classes encode/decode-able
- working on this at https://github.com/ceph/ceph/tree/wip-mds-dencoder
- 06:57 AM CephFS Feature #7352 (In Progress): mds: make classes encode/decode-able
- 06:55 AM CephFS Feature #7352 (Resolved): mds: make classes encode/decode-able
- 06:54 AM CephFS Feature #7319 (In Progress): qa: multimds, no failure
- 01:41 AM Feature #7238 (In Progress): erasure code : implement LRC plugin
- refactoring to not introduce new API functions as it turns out to be more complicated
- 01:38 AM Subtask #7307 (Rejected): erasure-code: chunk_size must not be architecture dependant
- Alignment is calculated using "LARGEST_VECTOR_WORDSIZE":https://github.com/ceph/ceph/blob/4c4e1d0d470beba7690d1c0e39b...
- 01:06 AM Subtask #7158 (Resolved): EC: flesh out how the ceph tool should be used to manage ec pools and c...
- http://tracker.ceph.com/issues/7146 was created and implemented. There does not seem to be a need for more tools.
... - 12:38 AM Revision 471c6782 (ceph): Merge pull request #1188 from dachary/wip-7339
- DNM: define pg_pool_t::stripe_width and set from erasure-code plugin on erasure pool creation
Reviewed-by: Samuel Ju...
02/05/2014
- 11:47 PM Revision 5cc99fec (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
- 11:46 PM Revision f0bc87a3 (ceph): created upgrades:dumpling-next suite to test parallel upgrades
- and partial upgrades.
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> - 11:26 PM Revision 5422c41d (ceph): s/rgw_tests.sh/s3_bucket_quota.pl
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 11:20 PM Revision 330612dc (ceph): schedule_suite: be slightly more verbose
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:19 PM Revision 9ecf3467 (ceph): rgw: initialize variable before call
- Need to initialize the truncated variable, as we sometimes ignore error
response (e.g., with ENOENT), and in such cas... - 09:15 PM Revision 81e3c621 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
- 09:04 PM Revision 3d435310 (ceph): Merge pull request #1190 from ceph/wip-snaptest-next
- qa/workunits/snaps: New allow_new_snaps syntax
- 09:00 PM Revision ce0e3bd1 (ceph): qa/workunits/snaps: New allow_new_snaps syntax
- These were probably just obscuring other failures.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: John Spr... - 07:46 PM Revision 0d2cbe64 (ceph): Merge pull request #185 from ceph/wip-7342
- Enable killing runs that haven't even started yet
- 07:44 PM Revision 22b0057f (ceph): mon: test osd pool create pg_pool_t::stripe_width behavior
- * Check that the default from the configuration options is found in the
output of osd dump
* Check that specifying ... - 07:43 PM Revision 7759473e (ceph): Enable killing runs that haven't even started yet
- This requires passing --machine-type.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 07:40 PM Revision dfc90cf3 (ceph): mon: osd pool create sets pg_pool_t::stripe_width
- It does nothing if the pool is replicated. Otherwise it uses
osd_pool_erasure_code_stripe_width as the desired stripe... - 07:40 PM Revision 33b8ad81 (ceph): common: add osd_pool_erasure_code_stripe_width
- and document it.
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:33 PM Revision 798b56a6 (ceph): unittests: update osdmaptools with stripe_width
- stripe_width 0 now shows on every osd dump.
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:31 PM Revision 11c11ba9 (ceph): mon: add erasure-code pg_pool_t::stripe_width
- Contains the actual stripe size used by erasure coded pools. It is
initialized to zero by default and has to be expli... - 07:26 PM Revision c2bd8464 (ceph): valgrind: fix msync suppression
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:19 PM Revision b0f37078 (ceph): Merge pull request #1187 from ceph/port/fixes
- portability fixes
Reviewed-by: Sage Weil <sage@inktank.com> - 04:59 PM Feature #7347 (New): Per CRUSH type mon_osd_down_out_interval
- Ability to have different mon_osd_down_out_interval values for different CRUSH types.
For example, you could set:
... - 04:42 PM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
- 12:09 PM Subtask #7339 (Fix Under Review): erasure code: add stripe width to pg_pool_t
- "work in progress":https://github.com/ceph/ceph/pull/1188
- 01:39 AM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
- * add *erasure_code_stripe_width* to config_opts.h
* on *osd pool create*, set the pg_pool_t::stripe_width to be get... - 04:37 PM Revision 994bdeaf (ceph): os/kvstore: trivial portability fixes
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:37 PM Revision 6fda45b1 (ceph): os/kvstore: remove used var
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:37 PM Revision 922e5cf8 (ceph): osd: fix type mismatch warning
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:35 PM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
- Upon trying to issue a multiple delete operation on a bucket that contains an unfound object, we return:
@<?xml ve... - 04:27 PM Revision 377a8458 (ceph): common: simpler erasure code technique
- Change the default technique from Cauchy to ReedSolomon. Although it is
less efficient the alignment constraints are ... - 03:44 PM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
- This func does two things: either returns in in-memory structure, or generates the right archived hitset that spans t...
- 03:20 PM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
- No pattern has emerged, except that it happened twice in rapid succession after a long period of not happening (weeks...
- 08:28 AM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
- Hi Nathaniel,
What kind of workload are you running? Have you noticed any pattern
wrt when it occurs, what might... - 03:15 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
- Logs are in - http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-04_23:00:02-rados-next-distro-basic-plana/68114
... - 11:51 AM Feature #7344: osd: add additional heartbeat on cluster interface
- If we have to do heartbeating over the exact same connection we send our other traffic on, is there any advantage to ...
- 11:24 AM Feature #7344 (Resolved): osd: add additional heartbeat on cluster interface
- A user had a switch configuration problem (no jumbo frames) that prevented progress on the cluster interface but allo...
- 11:46 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- 11:18 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
As unsigned values CEPH_SNAPDIR (snapdir) > CEPH_NOSNAP (head). The code wants to collapse both into a single last...- 10:20 AM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- 11:20 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
- logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-04_23:00:02-rados-next-distro-basic-plana/68416/te...
- 09:30 AM devops Bug #6595 (Resolved): Hardcoded install path in ceph-disk
- All subprocess calls in ceph-disk will use a PATH helper to find the correct executables regardless if $PATH is set o...
- 09:28 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
- Pull request https://github.com/ceph/ceph-deploy/pull/160
Merged into master with hash b50345e - 09:26 AM devops Bug #7276 (Resolved): ceph-deploy: -n arg is ignored
- Merged into ceph-deploy's master branch with hash c036cbd
- 08:37 AM devops Bug #7276 (Fix Under Review): ceph-deploy: -n arg is ignored
- pull request opened https://github.com/ceph/ceph-deploy/pull/162
- 07:18 AM devops Bug #7276 (In Progress): ceph-deploy: -n arg is ignored
- Ah good catch. That does absolutely nothing. Will have to remove that.
- 07:27 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- > Locking in RADOS is strictly voluntary; making it a mandatory thing would require keeping global knowledge about wh...
- 07:18 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- Locking in RADOS is strictly voluntary; making it a mandatory thing would require keeping global knowledge about whic...
- 01:03 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- Dan Mick wrote:
> Another way to state this: rbd images are defined such that if an object doesn't exist within the ... - 05:33 AM Revision eb18c0a8 (ceph): Merge pull request #1183 from ceph/wip-7336
- rgw: fix rgw_read_user_buckets() use of max param
Reviewed-by: Sage Weil <sage@inktank.com> - 01:45 AM Feature #7340 (Duplicate): rados.py does not expose object locking
- Commit d8415663b62edb812d087cba40b03b933e3e4556 exposed @rados_lock_exclusive()@, @rados_lock_shared()@, @rados_unloc...
02/04/2014
- 09:04 PM Revision decfe7c2 (ceph): increase mon verbosity in logs
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 09:04 PM Revision a07db3ca (ceph): increase mon verbosity for all ceph-deploy tasks
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 06:37 PM Revision 04b1ae46 (ceph): rgw: fix rgw_read_user_buckets() use of max param
- Fixes: #7336
The rgw_read_user_buckets() treated the max param as the max number of
entries to request in a single o... - 06:10 PM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- Another way to state this: rbd images are defined such that if an object doesn't exist within the defined size of the...
- 11:20 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- There's a big difference between what happens if the objects get zapped versus rendered unreadable — if unreadable, t...
- 10:54 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- OK. Now the recent rgw/xattr bug has shown that it is possible for a Ceph application to mess up objects so badly tha...
- 10:29 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- Just the first; as you say, it's how we do TRIM and that implementation is very common behavior among storage systems.
- 10:25 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- > Nonexistent objects are *defined* as zeros in RBD.
Erm, OK. I take it that this is also how TRIM/DISCARD is imp... - 10:14 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- Nonexistent objects are *defined* as zeros in RBD. We'd have to distinguish between deliberately nonexistent and lost...
- 10:10 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- Greg Farnum wrote:
> At present this is expected behavior. In order to raise an error we would need to know that the... - 09:42 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
- At present this is expected behavior. In order to raise an error we would need to know that the object was supposed t...
- 09:32 AM Bug #7335 (Won't Fix): librbd does not raise "Object Not Found", instead returning NUL bytes
- Test case attached. @test_remove_object@ fails. Prose description:
* Create RBD image
* Remove RADOS object belon... - 05:18 PM Revision 12f4688a (ceph): Merge pull request #1182 from ceph/wip-mds-cluster
- mds: avoid sending duplicated discovers during recovery
Reviewed-by: Sage Weil <sage@inktank.com> - 04:34 PM Revision 105eac4f (ceph): Merge pull request #1177 from dachary/wip-erasure-code-command
- erasure code command
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 04:17 PM Revision fdeb18e2 (ceph): mon: MDSMonitor: Forbid removal of first data pool
- Because inodes from other pools now store their backtrace
on the first/default data pool, it is special and may not
b... - 04:14 PM Revision c7d265a9 (ceph): mon: OSDMonitor: Refuse to delete CephFS pools
- To avoid confusing CephFS, don't permit deletion
of pools which are in use as the metadata pool
or any of the data po... - 02:58 PM Revision e80b084f (ceph): erasure-code: add ceph_erasure_code debug command
- It loads a designated erasure-code plugin and calls its
methods. It is convenient to figure out and tune the number o... - 01:43 PM Revision 68e6dada (ceph): mds: avoid sending duplicated discovers during recovery
- If MDS just entered the rejoin state, it should not kick discovers
because the discovers were just sent. Similarly, i... - 01:17 PM Revision bec12096 (ceph): erasure-code: benchmark moves to a dedicated directory
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 12:27 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
- 12:08 <@sage> alram joao wido: on issue 5804 i'm guessing ssh access and debugging is the trick,
altho... - 12:13 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
- really think that log message would go a long way toward helping.
- 11:58 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
- I'm able to reproduce this fairly consistently on the Ceph VM Wido is mentioning.
Any information/debug settings t... - 12:00 PM Bug #6685 (Fix Under Review): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present ...
- 11:21 AM Revision 0d6095ce (ceph): Merge pull request #1180 from dachary/wip-7313
- mon: check cluster features before rule create-erasure
Reviewed-by: Sage Weil <sage@inktank.com> - 10:48 AM rgw Bug #7336 (Fix Under Review): rgw: limit on list buckets broken
- 10:22 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
- The limit param that is used in swift when listing buckets does not work correctly on latest master.
- 10:48 AM Revision ad8c6660 (ceph): mon: check cluster features before rule create-erasure
- Encapsulate the logic used when creating an erasure coded pool into the
check_cluster_features helper.
check_cluster... - 10:38 AM Revision c40e4d4f (ceph): Merge pull request #1144 from dachary/wip-7146
- osd crush rule create-erasure
gitbuilder is green/yellow for wip-7146
Reviewed-By: Christophe Courtaut <christophe.... - 10:28 AM Subtask #7277: EC: on erasure pool creation, size needs to be fixed to K+M, size must not subsequ...
- resolved with https://github.com/dachary/ceph/commit/c8c4cc6e81816069886af6bff968712993554759 and later amended by ht...
- 03:11 AM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
- 09:22 AM Revision c8c4cc6e (ceph): mon: OSDMonitor: do not allow changing an erasure-coded pool's size
- Fixes: 7277
Reviewed-by: Loic Dachary <loic@dachary.org>
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 08:46 AM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
- commit:42900ff9da9f5adcac239a84ebf4d2e407c29699
https://bugzilla.redhat.com/show_bug.cgi?id=614357.
After ceph-... - 07:16 AM Revision fdc967d8 (ceph): pybind: cosmetic changes to tests
- * untabify
* re-indent
* 2014 to copyright notice
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
S... - 07:16 AM Revision 3370973f (ceph): pybind: osd crush rule create-erasure tests
- Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:16 AM Revision 5f9f300a (ceph): unittests: reduce paxos propose interval to increase speed
- The MONs are stressed more often and there is less aggregation of the
pending requests. But the unit tests are only m... - 07:16 AM Revision 5bb4ca4d (ceph): vstart: load erasure code plugins from sources
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:16 AM Revision 9cb2215e (ceph): mon: osd-pool-create shows logs on error
- extracting the logs would otherwise require a modification of the test
file to not clobber the directory containing t... - 07:16 AM Revision 0ca7ed80 (ceph): mon: osd-pool-create test initialization
- * reduce the paxos propose interval speed up tests
* load erasure code plugins from sources
Reviewed-By: Christophe ... - 07:16 AM Revision d8d747d7 (ceph): mon: osd-pool-create test must kill -9
- If a MON is stuck, kill -15 won't be enough and the test will hang
forever.
Reviewed-By: Christophe Courtaut <christ... - 07:16 AM Revision d40841cb (ceph): mon: osd-pool-create test enforce -e
- Use
! grep foo || exit 1
instead of
grep foo && exit 1
so that all commands have a successful exit code. Ot... - 07:16 AM Revision 59ba03b3 (ceph): mon: test erasure code pool creation
- * The sequence now is a) create ruleset, b) create pool.
* Check that not specifying the ruleset when an erasure code... - 07:16 AM Revision 428c75e1 (ceph): mon: osd-pool-create test EAGAIN when pending
- Test that if the ruleset is found in the pending paxos proposal, the
pool creation will try again.
Reviewed-By: Chri... - 07:16 AM Revision 7b15cb1b (ceph): mon: osd-pool-create test no longer use hardcoded ruleset
- For erasure-code the ruleset must be specified instead of relying on an
hardcoded value. Adapt the test to this for t... - 07:06 AM Revision 6caac92c (ceph): mon: pool creation helper for size
- The size of the replicated pools are by default set to
osd_pool_default_size but it may vary depending on the pool ty... - 07:06 AM Revision 61c45fe0 (ceph): mon: pool create helper for crush ruleset
- The crush ruleset of the replicated pools are by default set to
osd_pool_default_crush_replicated_ruleset but it may ... - 07:06 AM Revision caefb8a2 (ceph): mon: erasure code plugin loader helper
- The get_erasure_code helper loads the erasure code plugin found in the
erasure-code-plugin string of the properties a... - 07:06 AM Revision 8259e51d (ceph): mon: compute the size of erasure-coded pools
- It is K+M ( data chunks + coding chunks ) as returned by the
get_chunk_count() method of the erasure code plugin.
ht... - 07:06 AM Revision 1acc73bb (ceph): mon: compute the ruleset of erasure-coded pools
- The default ruleset of an erasure coded pool may depend on the
parameters used to configure it. In the case of a pyra... - 07:06 AM Revision cb39b136 (ceph): mon: osd crush rule create-erasure
- Delegates the creation of the rule to the erasure code plugin associated
with the specified pool.
Reviewed-By: Chris... - 07:06 AM Revision ad09023e (ceph): pybind: fix tests that do not fail as expected
- A missing argument make the test fail indeed, but the intended test is
to demonstrate something else ( either charact... - 07:06 AM Revision 2dca7371 (ceph): erasure-code: the plugin is in a convenience library
- So that it can be used by mon without linking with libosd
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmai... - 07:06 AM Revision 6ca9b246 (ceph): erasure-code: add crush ruleset creation API
- Because only the erasure code plugin knows enough to create a ruleset
that is best suited for a given set of paramete... - 07:06 AM Revision f019c906 (ceph): erasure-code: implement example create_ruleset
- And the associated unit tests.
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Signed-off-by: Loic ... - 07:06 AM Revision 02869f8d (ceph): erasure-code: implement ErasureCodeJerasure::create_ruleset
- It is based on CrushWrapper::add_simple_ruleset, using a "default" root
and "host" failure domain by default. They ca... - 07:06 AM Revision cc66c6a0 (ceph): erasure-code: test ErasureCodeJerasure::create_ruleset
- Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:06 AM Revision 0cac2025 (ceph): mon: helper for pool properties parsing
- Add the prepare_pool_properties to convert the properties vector into a
properties map suitable for either initializi... - 07:06 AM Revision 9d766cab (ceph): mon: no default ruleset except for replicated pools
- Remove the hardcoded default ruleset for erasure coded pools and only
keep it for replicated pools. Move the logic up... - 07:02 AM CephFS Feature #7319: qa: multimds, no failure
- Enable the marginal suite multi-mds tests.
- 06:59 AM CephFS Feature #7316: improve mds state dumps (memory usage, completeness)
- https://wiki.ceph.com/Planning/Sideboard/mds%3A_dumpability
- 06:52 AM CephFS Feature #7333 (In Progress): client: evaluate multiple O_APPEND writers
- This needs done for kclient and libcephfs. Extending the size of the file is potentially racy with updates to inode's...
- 06:50 AM CephFS Fix #7109 (Fix Under Review): disallow removing the first data pool
- https://github.com/ceph/ceph/pull/1173
- 06:20 AM Revision a8fcffb9 (ceph): Merge remote-tracking branch 'gh/next'
- 06:18 AM Revision 2bcc6006 (ceph): Implement the rest of the checks for automatic pg scrubbing.
- osd_scrub_pgs now:
1.) Insures that all pgs are clean and active.
2.) Performs the scrub of all OSDs.
3.) Waits until... - 05:55 AM Revision e47e49d2 (ceph): doc/release-notes: v0.77 draft notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:50 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
- ...
- 05:40 AM Revision 2c504ea1 (ceph): doc/release-notes: v0.76
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:22 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Florian Haas wrote:
> Wido den Hollander wrote:
> > Florian Haas wrote:
> > > Just for clarification: when you say... - 05:02 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Wido den Hollander wrote:
> Florian Haas wrote:
> > Just for clarification: when you say "it" blocked forever, are ... - 02:34 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Florian Haas wrote:
> Wido den Hollander wrote:
> > > * Did you only test with an RBD storage *pool*, or do you als... - 05:12 AM Revision 60ca6f69 (ceph): client: fix warnings
- client/Client.cc: In member function 'int Client::_read(Fh*, int64_t, uint64_t, ceph::bufferlist*)':
warning: client/... - 04:26 AM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- Josh Durgin wrote:
> Wido den Hollander wrote:
> > Josh Durgin wrote:
> > > It makes sense to add as an option for... - 03:37 AM Revision 9b2b2c28 (ceph): misc.py: helper roles_to_remotes for generic use
- roles_to_remotes will take a config key, 'roles' by default,
and search cluster.remotes for those roles, returning a ... - 03:22 AM Subtask #7313 (Resolved): erasure-code: rule create-erasure requires CEPH_FEATURE_CRUSH_V2
- "pull request":https://github.com/ceph/ceph/pull/1180
- 03:00 AM Subtask #7146 (Resolved): implement osd crush rule create-erasure
- 03:00 AM Revision 1829d2c9 (ceph): librados: add timeout to wait_for_osdmap()
- This is used by several pool operations independent of the objecter,
including rados_ioctx_create() to look up the po... - 02:57 AM Revision 0dcceff1 (ceph): conf: add options for librados timeouts
- These will be implemented in subsequent patches.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 01:50 AM Revision eb9ffd5a (ceph): mon: use 'mds set inline_data ...' for enable/disable of inline data
- This makes the management interface a bit more consistent.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:50 AM Revision 8e30db8f (ceph): rest: add a few rest api tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:50 AM Revision a23a2c8f (ceph): os/KeyValueStore: fix warning
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:50 AM Revision 408b0c8e (ceph): mon: fix 'mds set allow_new_snaps'
- We had already added this as a flag (set/unset) when I generalized the
'mds set_max_mds' to be 'ceph mds set <var> <v... - 01:48 AM Revision 3e56cc08 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
- 12:37 AM Revision 33338c5c (ceph): Merge pull request #1179 from dachary/wip-force-proposal
- mon: do not force proposal when no osds
Backport: emperor, dumpling
Reviewed-by: Sage Weil <sage@inktank.com> - 12:25 AM Revision e5ed1b29 (ceph): mon: do not force proposal when no osds
- If there are no OSDs, there is no need to propose to paxos. It does not
hurt on a production cluster but it matters w...
02/03/2014
- 11:06 PM Revision 9f4edb61 (ceph): Merge pull request #1151 from ceph/wip-performance-configs
- Performance improvements and config options
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Josh Durgin <jo... - 10:39 PM Revision f9b9f524 (ceph): Merge branch 'next'
- 09:14 PM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
- sage-2014-02-03_16:41:22-rados:basic-wip-agent-testing-basic-plana/64994...
- 08:03 PM Feature #6507 (In Progress): librados shouldn't block indefinitely when cluster doesn't respond
- Wido den Hollander wrote:
> Josh Durgin wrote:
> > It makes sense to add as an option for librados users like the l... - 12:45 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- Josh Durgin wrote:
> It makes sense to add as an option for librados users like the libvirt storage pool. The defaul... - 12:37 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- didn't mean to change these
- 12:21 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- It makes sense to add as an option for librados users like the libvirt storage pool. The default is blocking for thin...
- 02:41 AM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- Dan Mick wrote:
> 1) I solved this in the python bindings with a separate timer thread, which is always possible in ... - 06:26 PM Revision 3b990136 (ceph): v0.76
- 06:26 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I just wanted to inform you that since 0.7, I don't have to patch and recompile ceph-mds to get it to start every upd...
- 05:22 PM CephFS Bug #5250 (Can't reproduce): ceph-mds 0.61.2 aborts on start
- 06:07 PM Bug #7328 (Resolved): osd: reweight-by-utilization ended up with stuck remapped pgs
- Running ceph osd reweight-by-utilization resulted in stuck pgs....
- 05:30 PM rbd Bug #7327 (Resolved): Assertion failure in rbd_object_request_destroy()
- Running Debian kernel 3.12.6 (debian package linux-image-3.12-1-amd64_3.12.6-2_amd64) inside a Xen DomU, we occasiona...
- 05:28 PM CephFS Bug #6623 (Resolved): mds: update backtraces on existing clusters
- 05:27 PM CephFS Feature #1448 (Resolved): test hadoop on sepia
- 05:25 PM CephFS Bug #4489 (Can't reproduce): ceph fs hangs on file stat
- 05:25 PM CephFS Bug #5485 (Can't reproduce): failed cifs mount
- 05:23 PM CephFS Bug #4685 (Can't reproduce): BUG: unable to handle kernel NULL pointer dereference at
- 05:20 PM CephFS Bug #5753 (Duplicate): ceph-fuse: segfault when getting back a traceless rename op
- 05:19 PM CephFS Bug #6394 (Resolved): teuthology: bad dereference in mds thrasher
- 05:18 PM CephFS Bug #4909 (Can't reproduce): mds: stalled/stuck directory (standby)
- 05:02 PM Revision c301ec68 (ceph): client: use 64-bit value in sync read eof logic
- The file size can jump to a value that is very much larger than our current
position (for example, it could be a disk... - 05:02 PM Revision f2684c93 (ceph): client: use 64-bit value in sync read eof logic
- The file size can jump to a value that is very much larger than our current
position (for example, it could be a disk... - 05:01 PM CephFS Feature #3863: implement a tool to lookup inode numbers without holding their path
- 05:01 PM CephFS Feature #3863 (Resolved): implement a tool to lookup inode numbers without holding their path
- 05:00 PM CephFS Feature #1693 (Resolved): libcephfs: Support TRIM (hole punching)
- 04:59 PM CephFS Feature #3867 (Resolved): optionally do not use an anchor table
- 04:58 PM CephFS Cleanup #2177 (Resolved): mds: play nicely with omap
- 04:58 PM CephFS Feature #7326 (New): qa: fix flock tests
- 04:57 PM CephFS Feature #7325 (New): mds: tool to examine (later, manipulate) dirfrag objects
- 04:57 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
- 04:56 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
- 04:55 PM CephFS Feature #7322 (New): qa: inline data + thrashing
- 04:55 PM CephFS Feature #7321 (Duplicate): qa: multimds thrasher
- 04:54 PM CephFS Feature #7320 (Fix Under Review): qa: thrash directory fragmentation
- Define killpoints for directory fragmentation. Create tests as in https://github.com/ceph/ceph/pull/28004
- 04:54 PM CephFS Feature #7319 (Resolved): qa: multimds, no failure
- 04:54 PM CephFS Feature #7318 (Duplicate): qa: ceph-fuse + sync mode
- 04:54 PM Revision 7ff2b541 (ceph): client: use 64-bit value in sync read eof logic
- The file size can jump to a value that is very much larger than our current
position (for example, it could be a disk... - 04:53 PM CephFS Feature #7317 (Resolved): mds: behave with fs fills (e.g., allow deletion)
- 04:53 PM CephFS Feature #7316 (New): improve mds state dumps (memory usage, completeness)
- 04:52 PM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
- 04:40 PM Cleanup #7314 (In Progress): remove dead code from OSDMonitor::should_propose
- "located here":https://github.com/ceph/ceph/blob/v0.75/src/mon/OSDMonitor.cc#L763
- 02:47 PM Subtask #7313 (Resolved): erasure-code: rule create-erasure requires CEPH_FEATURE_CRUSH_V2
- before asking the erasure-code plugin to create the rule, check if CEPH_FEATURE_CRUSH_V2 is supported by all daemons
- 12:59 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Wido den Hollander wrote:
> > * Did you only test with an RBD storage *pool*, or do you also have *domains* running ... - 12:46 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Florian Haas wrote:
> Thanks Wido. As explained in the original description we went off 1.1.1 here due to a SIGABRT ... - 10:55 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Thanks Wido. As explained in the original description we went off 1.1.1 here due to a SIGABRT bug.
Two questions:
... - 06:00 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- So I've played around with this today and I can't fully reproduce it.
I have a machine running with libvirt 1.1.1-... - 01:48 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Florian Haas wrote:
> Right, but why should the qemu process stall if all the MONs are available, and only a few RBD... - 01:42 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Right, but why should the qemu process stall if all the MONs are available, and only a few RBDs are shot? (if they ar...
- 12:56 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- I'm going to try to figure this out, I'm setting up a test env right now.
I think it's libvirt which can't handle ... - 12:32 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- With Wido having confirmed that the issue exists, I'm bumping the severity to critical.
Wido, if you could offer y... - 11:26 AM Bug #7178 (Resolved): sample.ceph.conf needs update
- commit:e268e9562dd0831fe40702e56bfbdf8f6cb80b1a
- 09:45 AM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
- Work-in-progress kmod packaging here: https://github.com/kdreyer-inktank/ceph-kmod-rpm
Originally I'd planned to b... - 08:32 AM devops Bug #7312 (Resolved): ERROR: Running exception handlers
- Failed in:
teuthology-2014-01-31_19:35:02-upgrade:small-next-testing-basic-vps/61907
logs in http://qa-proxy.ceph... - 07:37 AM devops Bug #7311 (Closed): GPG/packaging failures
- apt complained throughout the install process...
- 07:25 AM rbd Bug #7310 (Can't reproduce): rbd snap unprotect test failing
- ...
- 06:51 AM CephFS Bug #5411 (Resolved): teuthology: bad object dereference
- 05:21 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Greg Farnum wrote:
> Which op threads and filestore threads are you talking about? The splitting happens whenever th... - 01:16 AM Revision 021d94ca (ceph): fs/basic: test with inline data
- Signed-off-by: Sage Weil <sage@inktank.com>
02/02/2014
- 05:40 PM Revision e4ff4720 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/mon/OSDMonitor.cc
src/osd/OSDMap.h - 05:19 PM Feature #7058 (Fix Under Review): osd primary affinity
- 05:18 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
- 05:16 PM Revision 29eac1d1 (ceph): Merge remote-tracking branch 'gh/wip-inline'
- Passed fs suite, sage-2014-02-01_22:18:10-fs-wip-inline-testing-basic-plana,
modulo a snap test error in the suite.
... - 07:53 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Hey Wido,
thanks for responding to this, and doubly for doing so on a weekend. Much appreciated.
> I'm aware of... - 06:30 AM Subtask #7307 (Rejected): erasure-code: chunk_size must not be architecture dependant
- The "get_chunk_size() method":https://github.com/ceph/ceph/blob/4c4e1d0d470beba7690d1c0e39bfd1146a25f465/src/osd/Eras...
- 06:05 AM Revision be3ea71c (ceph): valgrind: another tcmalloc suppression
- With this I can run a simple job with a normal build (not
notcmalloc) and valgrind does not complain. Fingers crosse... - 05:51 AM Subtask #7146 (Fix Under Review): implement osd crush rule create-erasure
- "work in progress":https://github.com/ceph/ceph/pull/1144
- 05:42 AM Subtask #7277 (In Progress): EC: on erasure pool creation, size needs to be fixed to K+M, size mu...
- "setting the size of the pool":https://github.com/ceph/ceph/pull/1144#issuecomment-33899812
- 05:00 AM Revision 9c3a4d8a (ceph): Merge pull request #1165 from mo22/client_fuse_multithreading
- client: ceph-fuse use fuse_session_loop_mt to allow multithreaded operat...
Reviewed-by: Sage Weil <sage@inktank.com>
02/01/2014
- 10:57 PM Feature #7288: Deep-scrub throttle
- Yes but if you have one scrub per OSD and you have a replication of 3. It could be easily happen that one OSD has 3 o...
- 09:01 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
- ubuntu@teuthology:/a/teuthology-2014-01-31_23:00:01-rados-master-testing-basic-plana/62166
- 02:22 PM Bug #7178: sample.ceph.conf needs update
- Fully merged by Josh Durgin -- thanks.
This bug can be closed now (I have no rights to do that). - 11:40 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- I'm aware of this. It's not only with RBD though, the same happens with libvirt when you use NFS and a export is dead...
- 05:58 AM Revision 2f85b8c8 (ceph): doc: Incorporated feedback.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:33 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- I'm sorry to say, all my data is considered lost right now. I like Ceph architecture very much but cannot use due to ...
01/31/2014
- 11:54 PM Revision 27b5f2b8 (ceph): common/shared_cache.hpp: avoid list::size()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:54 PM Revision ee48c871 (ceph): common/shared_cache.hpp: compact to a single lookup where possible
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:54 PM Revision 03f7f771 (ceph): Throttler: optionally disable use of perfcounters
- These can be expensive enough that we want to disable them. We're already
mostly set up for it to be optional, so jus... - 11:54 PM Revision 98ae0592 (ceph): Throttle: Turn off throttle based on max bytes
- If max throttle bytes is 0, throttle should not be doing anything.
This check is introduced in the beginning of each ... - 11:54 PM Revision 8e194888 (ceph): TrackedOp: optionally disable the actual tracking operations
- To avoid op contention on global locks, optionally disable the
op tracking. Create an "osd_op_tracker" config to cont... - 11:54 PM Revision 5fde828d (ceph): cmp.h: boost tuple comparison is replaced by regular comparison
- Profiler was showing this boost tuple comparison is expensive.
So, it is replaced by regular comparison.
Signed-off-... - 11:54 PM Revision 684e5c45 (ceph): Pipe, cephx: Message signing under config option
- The config option was present earlier but the option is checked
not in the beginning, so, it was doing some stuff. No... - 11:29 PM Revision e8717163 (ceph): Scrub osds when ceph task finishes
- Fixes: 7198
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 10:32 PM Revision 183deb89 (ceph): osd: do not send peering messages during init
- Do not send any peering messages while we are still working our way
through init().
Fixes: #7093
Signed-off-by: Sage... - 10:20 PM Revision b717e11b (ceph): Merge pull request #1174 from alram/master
- doc: rgw: el6 documentation fixes
- 09:55 PM Revision ee4cfda1 (ceph): doc: rgw: el6 documentation fixes
- - fix a couple of typo for repo configuration and service restart
- the ceph package must be installed on RPM distro ... - 09:41 PM Revision c1bc7fcc (ceph): Merge pull request #180 from ceph/wip-7278
- install.py: look for 'local' in config directly, don't warn if not found
- 09:41 PM Revision 8213ebbd (ceph): Merge pull request #183 from ceph/wip-enhance
- Wip enhance
- 09:30 PM Revision a321b6e7 (ceph): README.rst: describe new pp object and unlock_on_failure option.
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 09:12 PM Revision 915cb5d4 (ceph): Merge pull request #181 from ceph/wip-thrash-exception
- Fix MDS wait when get_mds_status returns None
- 09:07 PM Revision 1845a5ab (ceph): interactive.py: add handy "pp" for prettyprinting at the prompt
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 09:07 PM Revision 77ec4311 (ceph): internal.py: add global config key 'unlock_on_failure'
- When testing new tasks, it's a drag to have to keep manually unlocking
the targets. Default behavior is to keep them... - 08:53 PM Revision b80e5102 (ceph): Make libvirt import optional (OS X)
- 08:49 PM Revision aaf9b51c (ceph): Fix MDS wait when get_mds_status returns None
- 08:35 PM Revision dffe6019 (ceph): Merge pull request #1162 from ceph/wip-5997
- Fixes: #5997
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:08 PM Feature #7288: Deep-scrub throttle
- As it is we have config value osd_max_scrubs which defaults to 1. This should cause each OSD to only scrub a single ...
- 12:13 PM Feature #7288 (Resolved): Deep-scrub throttle
- Currently, it appears many PGs are allowed to enter a deep-scrubbing state. Due to the more intensive nature of a dee...
- 07:00 PM Revision 37447e75 (ceph): osd: Add scrub_supported() backend interface
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:00 PM Revision f9128e89 (ceph): osd: Move PG::_scan_list() to backend as ReplicatedBackend::be_scan_list()
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:00 PM Revision 34eb549c (ceph): osd: Move the rest of scrubbing routines to the backend
- Move enum scrub_error_type to osd_types.h
Move PG::_compare_scrub_objects to ReplicatedBackend::be_compare_scrub_obje... - 07:00 PM Revision e1bfed52 (ceph): common: buffer::ptr::cmp() is a const function
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:00 PM Revision ce1ea619 (ceph): osd: Change be_scan_list() arg to const
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:00 PM Revision 48fbccec (ceph): osd: Change some be_compare_scrub_objects() args to const
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 03:57 PM Revision 560f5f1f (ceph): OSDMap: fix deepish_copy_from
- Start with a shallow copy!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d0f13f54146694a197... - 03:57 PM Revision d5080799 (ceph): OSDMonitor: use deepish_copy_from for remove_down_pg_temp
- This is a backport of 368852f6c0a884b8fdc80a5cd6f9ab72e814d412.
Make a deep copy of the OSDMap to avoid clobbering t... - 03:57 PM Revision 61914d82 (ceph): OSDMap: deepish_copy_from()
- Make a deep(ish) copy of another OSDMap. Unfortunatley we can't make the
compiler-generated copy operator/constructo... - 03:19 PM Revision 802692ed (ceph): os/KeyValueStore: fix warning
- ./os/KeyValueStore.h: In member function ‘std::string KeyValueStore::strip_object_key(uint64_t)’:
warning: ./os/KeyVa... - 03:09 PM Bug #7093 (Pending Backport): osd: peering can send messages prior to auth
- Backported this to dumpling in commit:183deb899bc6b1b7b2a1ec639425e45786e56b01
Do we also want to backport it to e... - 03:00 PM Revision f8316f1a (ceph): Merge branch 'wip-inline' of git://github.com/kylinstorage/ceph
- Conflicts:
src/include/ceph_features.h - 02:39 PM Documentation #6547: should document magic data/journal partition types
- No, thanks, fixed
- 02:34 PM Documentation #6547: should document magic data/journal partition types
- hmm, is this meant to be in the calamari product?
- 02:13 PM devops Feature #7293 (Resolved): packaging: enable qemu to find librbd on rhev or rhel-osp
- qemu-kvm-rhev will dynamically load librbd if /usr/lib64/qemu/librbd.so.1 exists.
The librbd package needs to add ... - 02:02 PM Subtask #7292 (Rejected): erasure code: plugin backward compatibility
- The goal is to allow Giant to install upgraded backward compatible erasure-code plugins so that pools created with Fi...
- 02:01 PM Feature #7291 (New): EC: add mechanism for mon to detect and whitelist EC plugins which are globa...
- Otherwise, we might end up with a situation where the mon believes an EC plugin is usable and creates such a pool, bu...
- 01:58 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
- 01:57 PM Feature #7034: cachepool: agent: basic eviction
- 01:56 PM Feature #7033: cachepool: agent: trivial flushing
- 01:53 PM Fix #7215 (Resolved): mon: prevent old monitors which do not support new encodings from joining t...
- This is merged (and so are some fixes around it), just didn't get the automated tests debugged but they can go elsewh...
- 01:27 PM devops Feature #6882 (Resolved): downburst: list available distro/versions
- This is done in branch wip-list-distros which was merged a while ago.
- 01:24 PM devops Feature #7047 (In Progress): rhel7: build process for rbd.ko, ceph.ko kernel modules
- 01:24 PM devops Feature #7046 (In Progress): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
- 01:22 PM devops Feature #7094 (Resolved): f20 gitbuilder
- 01:22 PM devops Fix #7095 (Resolved): fix f19 gitbuilder
- 01:08 PM rgw Feature #6338: rgw: better manifest scaling
- Currently a gateway object includes in the manifest a list of all the rados objects that it uses. Every time we acces...
- 12:54 PM rgw Feature #6338 (In Progress): rgw: better manifest scaling
- 12:54 PM rgw Feature #6339 (In Progress): rgw: compact manifest data
- 12:32 PM Subtask #5861 (Resolved): Refactor scrub to use PGBackend methods
- dffe6019c3698ca1661c94984df9629241c3e1ef
- 12:31 PM Feature #5997 (Resolved): EC: [link] Refactor scrub to use PGBackend methods
- dffe6019c3698ca1661c94984df9629241c3e1ef
- 10:37 AM Feature #7287 (New): Make units of measurement constant and definable in ceph commands
- From the customer:
It would be great if it were possible to lock the units for ceph reporting
ceph -w /ceph -s ... - 10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
- 10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
- While ReplicatedBackend always calls log_operation from within the call to log_operation, this won't be true of ECBac...
- 10:28 AM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
- This is necessary because though with ReplicatedBackend, log_operation will be called from within the submit_transact...
- 10:22 AM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
- 10:12 AM Bug #7256: ceph osd crashed at ReplicatedPG::trim_object on next
- maybe dup of #6101 ?
- 09:59 AM devops Bug #7283 (Resolved): centos 6 - gitbuilder mod_ssl broken dependency
- From the doc, I'm using http://gitbuilder.ceph.com/apache2-rpm-centos6-x86_64-basic/ref/master to install httpd on th...
- 09:49 AM CephFS Fix #7109: disallow removing the first data pool
- https://github.com/ceph/ceph/pull/1173
- 09:47 AM rbd Bug #7282 (Resolved): Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connect...
- This isn't fully confirmed yet, because we haven't found a reliable way to reproduce. In short, it seems that if you ...
- 07:49 AM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
- > "2014-01-31 05:32:26.722560 osd.5 10.214.131.11:6810/5928 5 : [ERR] 3.12 3
> tried to pull 1518ccf2/plana1... - 07:47 AM Revision c489e440 (ceph): install.py: look for 'local' in config directly, don't warn if not found
- Fixes: #7278
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 05:01 AM Revision 3a53d6de (ceph): Merge pull request #1171 from ceph/wip-osdmap-features
- mon: encode full osdmap with same feature bits as the incremental
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:47 AM rbd Bug #7076 (Resolved): rbd: check for watchers before removing an image
- 12:04 AM Revision abcc17bf (ceph): Merge pull request #1169 from dachary/wip-ceph-disk
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
01/30/2014
- 11:40 PM Revision 36658157 (ceph): Merge remote-tracking branch 'origin/next'
- Conflicts:
src/test/ceph-disk.sh - 11:13 PM Revision 0389f1d6 (ceph): mon/OSDMonitor: encode full OSDMap with same feature bits as the Increm...
- Each monitor is independently encoding the full OSDMap and storing it in
its local store. Sometime this happens when... - 11:09 PM Revision b9208b47 (ceph): OSDMap: note encoding features in Incremental encoding
- The monitor will need to know what features the incremental was encoded
with so that it can encode the OSDMap using t... - 09:10 PM Revision ab649919 (ceph): Merge pull request #1170 from ceph/wip-pybind-enverr
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:04 PM Revision e4dd1bea (ceph): pybind: improve EnvironmentError output
- Follow 70c7c9e600c5 ("pybind/rados.py: improve error output") and
improve EnvironmentError output for librbd and libc... - 08:54 PM Revision de771ddd (ceph): Update README.rst to reflect changes in libvirt
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:17 PM Revision 754ddb16 (ceph): rgw: fix build on centos
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 08:15 PM Revision d11d1880 (ceph): Merge pull request #1145 from dachary/wip-mailmap
- mailmap: organization affiliations
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 08:13 PM Revision a28f1fa2 (ceph): mailmap: Christian Marie affiliation
- and name normalization
Reviewed-by: Christian Marie <pingu@anchor.net.au>
Signed-off-by: Loic Dachary <loic@dachary.... - 08:13 PM Revision 79563e19 (ceph): mailmap: Jonathan Dieter affiliation
- Reviewed-by: Jonathan Dieter <jdieter@lesbg.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:13 PM Revision 49842db1 (ceph): mailmap: Alan Somers affiliation
- Reviewed-by: Alan Somers <asomers@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:13 PM Revision f9132e0a (ceph): mailmap: John Spray is with Inktank
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:13 PM Revision 74d5bf50 (ceph): mailmap: Simon Leinen is with SWITCH
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:13 PM Revision 93a62d73 (ceph): mailmap: Ma Jianpeng affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:13 PM Revision b0fe2a94 (ceph): mailmap: Andras Elso affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:13 PM Revision 5b5bc0bc (ceph): mailmap: anonymous contributions are unaffiliated
- there only are a few of them
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:13 PM Revision 3a1a8c3e (ceph): mailmap: Laurent Barbe affiliation
- Reviewed-by: Laurent Barbe <laurent@ksperis.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:13 PM Revision 16284230 (ceph): mailmap: Rutger ter Borg affiliation
- Reviewed-by: Rutger ter Borg <rutger@terborg.net>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:13 PM Revision aa7fc3bb (ceph): mailmap: Dan Chai is unaffiliated
- and name normalization
Reviewed-by: Dan Chai <tengweicai@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:12 PM Revision cb9792ee (ceph): mailmap: Kai Zhang affiliation
- Reviewed-by: Kai Zhang <zakir.exe@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:12 PM Revision 0dbf44ff (ceph): mailmap: Kun Huang affiliation
- As found at https://github.com/pyKun
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:12 PM Revision 47a5122e (ceph): mailmap: Huang Jun is unaffiliated
- and name normalization
Reviewed-by: Huang Jun <hjwsm1989@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:12 PM Revision f7b000e5 (ceph): mailmap: Adam Twardowski affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:12 PM Revision c8c103b7 (ceph): mailmap: Xihui He affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:12 PM Revision b5d22eb8 (ceph): mailmap: Thomas Bechtold affiliation
- and canonical name. Also fix the name "Deutsche Telekom"
Reviewed-by: Thomas Bechtold <t.bechtold@telekom.de>
Signed... - 08:12 PM Revision 30f4969f (ceph): mailmap: Ron Allred name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:11 PM Revision 3f5e4f52 (ceph): ceph-disk: larger timeout in the test script
- Otherwise slow machines may timeout just because they are slow and not
because the process is blocked by an actual pr... - 07:11 PM Revision ad515bfe (ceph): ceph-disk: support and test the absence of PATH
- Although this is not exactly the context in which ceph-disk is run when
invoked by udev, it makes sure there is at le... - 07:01 PM Revision d70efe98 (ceph): FileStore: avoid leveldb check for xattr when possible
- Maintain an internal xattr called "spill_out" that indicates whether we
(may) have xattrs stored in omap. If attribu... - 06:52 PM Revision 7b179119 (ceph): Merge pull request #1159 from ceph/wip-rbd-rm-watchers
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:45 PM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
- 05:19 PM Revision 15c0dd02 (ceph): Merge remote-tracking branch 'gh/next'
- 05:13 PM Revision 6d1daeae (ceph): unittest_striper: fix warning
- In file included from test/test_striper.cc:1:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::AssertionRe... - 04:13 PM devops Bug #7276 (Resolved): ceph-deploy: -n arg is ignored
- Originally noticed this after running ceph-deploy -n --overwrite-conf config push host1 host2 host3
I also tried ins... - 03:42 PM Revision 83db8b04 (ceph): Merge pull request #1167 from mourgaya/master
- doc: cls moved to subdirectory
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 02:26 PM Revision f9071a77 (ceph): doc: cls moved to subdirectory
- Signed-off-by: Eric Mourgaya <eric.mourgaya@gmail.com>
- 12:47 PM Revision 0a553cfa (ceph): rbd: check for watchers before trimming an image on 'rbd rm'
- Check for watchers before trimming image data to try to avoid getting
into the following situation:
- user does 'r... - 12:47 PM Revision 4ebc32f3 (ceph): rbd: don't forget to call close_image() if remove_child() fails
- close_image() among other things unregisters a watcher that's been
registered by open_image(). Even though it'll tim... - 12:47 PM Revision e78f7564 (ceph): run-rbd-tests: run remove_with_watcher test
- Bug #2533 has been fixed for a while now, start running
remove_with_watcher test.
Signed-off-by: Ilya Dryomov <ilya.... - 11:48 AM Revision dcbe872e (ceph): pybind: work around find_library() not searching LD_LIBRARY_PATH
- Commit b28b64a0b6db ("pybind: use find_library for libcephfs and
librbd") switched us to find_library(), but this fun... - 11:06 AM devops Bug #7263 (Resolved): ceph-deploy should not use color formatting in non-tty sessions
- Merged into ceph-deploy's master branch 2fcf4bc
- 08:17 AM devops Bug #7263 (Fix Under Review): ceph-deploy should not use color formatting in non-tty sessions
- Pull request opened https://github.com/ceph/ceph-deploy/pull/157
- 10:53 AM Feature #7059 (Resolved): filestore: avoid leveldb check for xattr when possible
- 10:38 AM Feature #5997: EC: [link] Refactor scrub to use PGBackend methods
- 10:33 AM rgw Bug #7099: Strange Comportments with media files
- I'm not saying that it's not. I'm trying to figure out what the gateway does that makes the client behave like that.
- 10:31 AM rgw Bug #7099: Strange Comportments with media files
- Yehuda,
It's a general problem on all range request. I have reproduced it on multiple installations ...
It's ... - 10:16 AM rbd Feature #7272 (Duplicate): rbd: import performance
- Currently the rbd import appears to be single threaded which means the import process is being written to a single di...
- 09:55 AM rgw Bug #7271 (Resolved): container create via swift doesn't register ACL
- Hi,
when creating a container thanks the Swift API (PUT /{version}/{account}/{container}), X-Container-Read seems ... - 09:31 AM RADOS Feature #7270 (New): /usr/bin/ceph: notify user when privs are insufficient
- It should be pretty straightforward to significantly enhance this user experience:...
- 09:16 AM Bug #7258 (Resolved): ceph-disk: many calls do not work if command is not in PATH
- 05:25 AM Revision 47dcddc7 (ceph): Corrected the sample output in README.md
- 05:22 AM Revision 90067778 (ceph): 1. Updated README.md with sample output
- 2. Remove 'osd_hosts' entry from json and added that information as part of sys_info
3. In the 'num_components' entry... - 12:20 AM Revision 70c7c9e6 (ceph): pybind/rados.py: improve error output
- Fixes: 7264
When failing to load librados, output the exception.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 12:17 AM Revision 1a1f53d2 (ceph): Merge pull request #1163 from ceph/wip-7264
- pybind/rados.py: improve error output
Reviewed-by: Dan Mick <dan.mick@inktank.com>
01/29/2014
- 11:50 PM RADOS Feature #7267 (New): erasure code: take advantage of locality for recovery
- Only select the chunks with the "closest ancestor":https://github.com/ceph/ceph/blob/v0.75/src/crush/CrushWrapper.h#L...
- 11:44 PM Feature #7266 (Resolved): erasure code : implement locality (was pyramid)
- "June 2014 Giant / Hammer summit":http://pad.ceph.com/p/GH-locally-repairable-code
- 10:14 PM Revision 456c727e (ceph): doc: Removed extraneous character from path.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:44 PM Feature #6960 (Closed): DBObjectMap: refactor interface
- 05:45 PM Bug #6101: ceph-osd crash on corrupted store
- The initial problem was thought to be related to snapshots, therefore they cleaned all snapshots on the cluster but t...
- 05:15 PM Bug #6101: ceph-osd crash on corrupted store
- find_object_context() in trim_object returned -ENOENT.
But I couldn't track down why, optimized builds were drivin... - 03:50 PM Bug #6101: ceph-osd crash on corrupted store
- The nodes use xfs, so I don't think that the original assumption that filesystem corruption may be the cause is the o...
- 03:40 PM Bug #6101: ceph-osd crash on corrupted store
- Today I had contact with a cluster that suffers the same problem.
ceph version 0.67.5 (a60ac9194718083a4b6a225fc17... - 04:30 PM Revision f32bfa5a (ceph): ceph_test_object_map: fix build
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:53 PM Documentation #7265 (Closed): OpenStack <=> RBD docs should specify that config stanzas should be...
- At:
http://ceph.com/docs/master/rbd/rbd-openstack/
Under "Configure OpenStack to use Ceph", it should be mentione... - 03:25 PM Revision 3a39f363 (ceph): Merge pull request #1156 from ceph/wip-ceph-disk
- ceph-disk: run the right executables from udev
- 03:22 PM Revision 75da9f10 (ceph): Merge pull request #1148 from ceph/wip-7215-quorum-features
- Add monitor quorum features
Reviewed-by: Sage Weil <sage@inktank.com> - 02:59 PM Revision a4d1927b (ceph): Merge remote-tracking branch 'gh/next'
- 02:40 PM Revision 5476b4b6 (ceph): keyvaluestore: name to keyvaluetore-dev for now
- This helps warn the user that the ondisk format may be subject to change.
Signed-off-by: Sage Weil <sage@inktank.com> - 02:38 PM Revision e1349df4 (ceph): Merge pull request #1158 from yuyuyu101/keyvaluestore-dev
- Keyvaluestore Support
Reviewed-by: Sage Weil <sage@inktank.com> - 02:20 PM Feature #7247: EC: distinguish is_missing from is_readable
- 01:58 PM Bug #7264 (Resolved): rados.py: exception catching when librados load fails hides error
- A developer had built a library set that had an unresolved-symbol problem; rados.py, and thus the ceph cli, failed wi...
- 01:50 PM Revision cfdfb98a (ceph): Make ObjectStore unit tests shared with KeyValueStore
- Via gtest's value-parameterized feature, let the successors of
ObjectStore share the same unit tests.
Signed-off-by:... - 01:50 PM Revision 972d4b24 (ceph): Add KeyValueStore implementation
- KeyValueStore is another ObjectStore implementation with FileStore. It
uses KV store wrapper(StripObjectMap) which in... - 01:32 PM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
- 01:32 PM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
- 12:54 PM devops Bug #7263 (Resolved): ceph-deploy should not use color formatting in non-tty sessions
- Hopefully this would mean that teuthology logs would not be filled with ANSI escape codes trying to represent
colors... - 12:33 PM Bug #7262 (Resolved): ceph-disk-activate: custom mount options aren't handled correctly for non-d...
- Mount options are initially read from the hardcoded ceph.conf:
https://github.com/ceph/ceph/blob/d7b0c7faafd37e4ae... - 11:16 AM Revision 03da035f (ceph): docs: Typo in CloudStack user creation
- 10:43 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- No, clean server right now means there is nothing except gentoo stage3 installation.
- 07:55 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- are you reusing a previous store, from a previously problematic cluster?
- 10:08 AM Revision f0f4b8df (ceph): docs: Improve CloudStack documentation.
- Add a section about creating a CephX user for CloudStack.
- 09:46 AM Revision 8fb366f0 (ceph): Add a new KV wrapper GenericObjectMap
- Now we already have DBObjectMap which implement ObjectMap and other
interfaces, and ObjectMap.h implied that ObjectMa... - 09:20 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Which op threads and filestore threads are you talking about? The splitting happens whenever the filestore actually d...
- 07:44 AM Bug #7259: ceph mon crash in master branch
- Tamil, I suspect this is related to #7215, which should have been fixed by https://github.com/ceph/ceph/pull/1148 (wh...
- 07:12 AM Feature #6173 (Resolved): Add LevelDB support to ceph cluster backend store
- 07:12 AM Bug #6950 (Resolved): refactor OSD awareness of FileStore to make the ObjectStore backend configu...
- 06:15 AM rbd Bug #7076 (Fix Under Review): rbd: check for watchers before removing an image
- wip-rbd-rm-watchers; https://github.com/ceph/ceph/pull/1159
- 05:08 AM Revision b31c0f03 (ceph): civetweb: fix warning
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:54 AM Revision 3a1fb174 (ceph): OSDMap: fix deepish_copy_from
- Start with a shallow copy!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d0f13f54146694a197... - 04:54 AM Revision 26ad5ded (ceph): OSDMap: fix deepish_copy_from
- Start with a shallow copy!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d0f13f54146694a197... - 04:08 AM Revision 1e85bc99 (ceph): cls_user: init cls_user_list_buckets_op fields
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision fd260c99 (ceph): cls_user: init cls_user_stats fields in ctor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:46 AM Revision d0f13f54 (ceph): OSDMap: fix deepish_copy_from
- Start with a shallow copy!
Signed-off-by: Sage Weil <sage@inktank.com> - 01:27 AM Revision d7b0c7fa (ceph): ceph-disk: run the right executables from udev
- When run by the udev rules, PATH is not defined. Thus,
ceph-disk-activate relies on its which() function to locate th...
01/28/2014
- 11:47 PM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi,
I had this error on a 3.10.27 kernel. The fix is included in this kernel, right ?... - 11:26 PM Bug #7260 (Can't reproduce): rados api test LibRadosList.ListObjectsNS failed
- logs: ubuntu@teuthology:/a/teuthology-2014-01-25_19:40:02-upgrade:parallel-master-testing-basic-plana/53137...
- 11:15 PM Bug #7259 (Resolved): ceph mon crash in master branch
- logs: ubuntu@teuthology:/a/teuthology-2014-01-25_19:40:02-upgrade:parallel-master-testing-basic-plana/53135...
- 10:13 PM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- I've reproduced bug on clean server:
1. Download ceph-0.72.2.tar.gz and unpack
2. Install snappy-1.1.0
3. Instal... - 10:00 PM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- I've opened ssh for you:
<redacted>
When you logged in you can ssh to those three servers:
ssh root@10.0.0.1... - 10:52 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- My steps are:
1. Install ceph-0.72.2 to three servers.
2. Created some RBD images.
3. Run qemu-kvm on them.
4. ... - 09:48 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- Unfortunately I've been unable to reproduce this locally.
Can you provide a list of the steps you took in order to... - 09:43 PM Revision f01bd8a9 (ceph): rgw: fix listing of multipart upload parts
- Fixes: #7169
There are two issues here. One is that we may return more entries than
we should (as specified by max_p... - 09:14 PM Revision 152c2c41 (ceph): Merge pull request #1155 from ceph/wip-7190
- OSD: don't assume we have the pool in handle_pg_create
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:13 PM Revision ccfe243d (ceph): Merge pull request #1154 from ceph/wip-7169-2
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:06 PM Revision 6b657992 (ceph): rgw: initialize RGWUserAdminOpState::system_specified
- Fixes: #6829
Backport: dumpling, emperor
We didn't init this member variable, which might cause that when
modifying u... - 09:05 PM Revision 318e208a (ceph): OSD: don't assume we have the pool in handle_pg_create
- The pool may have been removed since the creation message
was sent. Previously, role would end up as -1 and this
pat... - 09:04 PM Revision cc3956ad (ceph): fix indentation level for task
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 1397d29963b2135998ccaaa9a89c83e0bb9... - 09:04 PM Revision bdafbc0c (ceph): make sure we are using a dict
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit fe4c97dc4f5f893df526f8694d4b9fafb06... - 08:53 PM Revision 585e0e7e (ceph): rgw: Fix CORS allow-headers validation
- This fix is needed because Ceph presently validates CORS headers in a
case-sensitive manner. Keeps a local cache of l... - 08:52 PM Revision da2267a8 (ceph): rgw: Clarify naming of case-change functions
- It is not clear that the lowercase_http_attr & uppercase_http_attr
functions replace dashes with underscores. Rename ... - 08:36 PM Revision fdea76ef (ceph): rgw: Look at correct header about headers for CORS
- The CORS standard dictates that preflight requests are made with the
Access-Control-Request-Headers header containing... - 08:28 PM Revision a5739e39 (ceph): rgw: fix reading bucket policy in RGWBucket::get_policy()
- Fixes: 6940
Backport: dumpling, emperor
We changed the way we keep the bucket policy, and we shouldn't try to
access... - 08:24 PM Revision ba792cdc (ceph): rgw: handle racing object puts when object doesn't exist
- If the object didn't exist before and now we have multiple puts coming
in concurrently, we need to make sure that we ... - 08:24 PM Revision 1e2984ac (ceph): rgw: don't return -ENOENT in put_obj_meta()
- Fixes: #7168
An object put may race with the same object's delete. In this case just
ignore the error, same behavior... - 08:23 PM Revision 5f1eea2c (ceph): rgw: Use correct secret key for POST authn
- The POST authentication by signature validation looked up a user based
on the access key, then used the first secret ... - 08:18 PM Revision 2a737d84 (ceph): leveldb: add leveldb_* options
- The osd_leveldb_* and mon_leveldb_* are now deprecated. If they are
still used, they override these values.
Signed-... - 08:16 PM Revision 11cf9bbb (ceph): rgw: fix multipart min part size
- As part of the fix for wip-7169 it turned out that we removed
min_part_size. Looking back, the original implementatio... - 08:14 PM Revision 12ba8a3a (ceph): Add a virtual interface init, open, create_and_open to KeyValueDB
- This will provide an opportunity to set leveldb_* settings in the next
patch.
Signed-off-by: Haomai Wang <haomaiwang... - 07:59 PM Revision 2e7bd83f (ceph): rgw: fix multipart upload listing
- Fixes: #7169
A separate fix has been created for dumpling.
Previously we read the entire list of parts, disregardin... - 07:20 PM Revision d294d736 (ceph): osd: OSDMonitor: ignore pgtemps from removed pool
- There's a window in-between receiving an MOSDPGTemp message from an OSD
and actually handling it that may lead to the... - 07:20 PM Revision 14e933eb (ceph): osd: OSDMonitor: ignore pgtemps from removed pool
- There's a window in-between receiving an MOSDPGTemp message from an OSD
and actually handling it that may lead to the... - 07:19 PM Revision f1b53093 (ceph): osd: OSDMonitor: ignore pgtemps from removed pool
- There's a window in-between receiving an MOSDPGTemp message from an OSD
and actually handling it that may lead to the... - 07:18 PM Revision da2da48b (ceph): Merge pull request #1153 from ceph/wip-7116-joao
- osd: OSDMonitor: ignore pgtemps from removed pool
Reviewed-by: Sage Weil <sage@inktank.com> - 07:10 PM Revision 9e357ed5 (ceph): OSDMonitor: use deepish_copy_from for remove_down_pg_temp
- This is a backport of 368852f6c0a884b8fdc80a5cd6f9ab72e814d412.
Make a deep copy of the OSDMap to avoid clobbering t... - 07:10 PM Revision 0fa0c016 (ceph): OSDMap: deepish_copy_from()
- Make a deep(ish) copy of another OSDMap. Unfortunatley we can't make the
compiler-generated copy operator/constructo... - 07:08 PM Revision 3672fc49 (ceph): OSDMonitor: use deepish_copy_from for remove_down_pg_temp
- This is a backport of 368852f6c0a884b8fdc80a5cd6f9ab72e814d412.
Make a deep copy of the OSDMap to avoid clobbering t... - 07:08 PM Revision e6fef68e (ceph): OSDMap: deepish_copy_from()
- Make a deep(ish) copy of another OSDMap. Unfortunatley we can't make the
compiler-generated copy operator/constructo... - 06:46 PM Revision 75d68a34 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
- 06:31 PM Revision a42e4fb1 (ceph): osdc/Striper: test zero-length add_partial_result
- If we add a partial result that is 0-length, we used to hit an assert in
buffer::list::splice(). Add a unit test to ... - 06:31 PM Revision 5c2a64c6 (ceph): buffer: make 0-length splice() a no-op
- This was causing a problem in the Striper, but fixing it here will avoid
corner cases all over the tree. Note that w... - 06:30 PM Revision 2528186c (ceph): buffer: make 0-length splice() a no-op
- This was causing a problem in the Striper, but fixing it here will avoid
corner cases all over the tree. Note that w... - 06:30 PM Revision fe9539e1 (ceph): osdc/Striper: test zero-length add_partial_result
- If we add a partial result that is 0-length, we used to hit an assert in
buffer::list::splice(). Add a unit test to ... - 06:26 PM Revision ff5abfbd (ceph): buffer: make 0-length splice() a no-op
- This was causing a problem in the Striper, but fixing it here will avoid
corner cases all over the tree. Note that w... - 06:25 PM Revision 86c3c5a5 (ceph): test/Makefile.am: update test_cls_rgw* rules
- Need to link with libcls_user_client.a
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:25 PM Revision 26ace1ef (ceph): test_rgw_admin_opstate: get it compiled
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:24 PM Bug #7258 (Resolved): ceph-disk: many calls do not work if command is not in PATH
- When called from udev, PATH is not set, so ceph-disk must be able to locate the correct executables. This causes ceph...
- 06:10 PM Revision 3447825b (ceph): Merge pull request #1137 from ceph/wip-7060
- fix #7060 mon scrub problem due to osdmap copying
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:09 PM Revision 28c7388d (ceph): osdc/Striper: test zero-length add_partial_result
- If we add a partial result that is 0-length, we used to hit an assert in
buffer::list::splice(). Add a unit test to ... - 05:40 PM Revision 9c67226d (ceph): rgw: fix get_obj() with zero sized obj
- Now that even zero sized objs have manifest a
test had to be modified.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.c... - 05:40 PM Revision e146934e (ceph): rgw/rgw_rados.cc: use empty() instead of checking for size() > 0
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 22e0dbbd0e6b6a0fc3b49018d0a5d91ce54... - 05:38 PM Revision 70b03824 (ceph): rgw/rgw_rados.cc: use empty() instead of checking for size() > 0
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 22e0dbbd0e6b6a0fc3b49018d0a5d91ce54... - 05:38 PM Revision 8fb15edf (ceph): rgw: fix get_obj() with zero sized obj
- Now that even zero sized objs have manifest a
test had to be modified.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.c... - 05:22 PM Revision f513f66f (ceph): osd: OSDMonitor: ignore pgtemps from removed pool
- There's a window in-between receiving an MOSDPGTemp message from an OSD
and actually handling it that may lead to the... - 05:05 PM Bug #7256 (Duplicate): ceph osd crashed at ReplicatedPG::trim_object on next
- logs: ubuntu@teuthology:/a/teuthology-2014-01-28_00:05:42-upgrade:parallel-next-testing-basic-plana/55891...
- 04:05 PM Revision 81d1405a (ceph): Attempt to fix #7241
- This involves moving everything in build_ceph_cluster() inside the try:
block, so if an exception fails the cleanup i... - 03:54 PM Revision 427bf93c (ceph): Fix PEP-8 linter complaints
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 03:08 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Another change I would suggest is to add some logs before and after folder splitting so that it is easier to check wh...
- 03:06 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Greg Farnum wrote:
> Well, we already only do folder split/merge when creating or removing objects,
Oh right, it ch... - 01:38 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Well, we already only do folder split/merge when creating or removing objects, which isn't going to happen on a read....
- 01:31 PM rgw Feature #6678: rgw: reject writes to secondary zones
- I created a branch wip-6678-dumpling, but it'll need to get some testing before cherry-picking wasn't clean.
- 01:29 PM rgw Bug #7169 (Resolved): rgw: list multipart parts broken (> 1000 parts)
- dumpling commit:f01bd8a94adc4ce8e7131f74282de5b434a7316a
master commit:ccfe243db5749e3d9406dc1f4d2f768d00f8715e - 01:05 PM Bug #7190 (Resolved): osd/OSD.cc: 2338: FAILED assert(oldmap->have_pg_pool(pgid.pool()))
- 318e208ab6cf2262d5b9954efb11bd3e1fafac32
- 12:30 PM Bug #7190: osd/OSD.cc: 2338: FAILED assert(oldmap->have_pg_pool(pgid.pool()))
- vector<int> up, acting;
- osdmap->pg_to_up_acting_osds(on, up, acting);
+ int up_primary, acting_primary... - 12:56 PM rgw Support #6784 (Closed): integration of radosgw and keystone
- 12:56 PM rgw Support #6785 (Closed): integration of radosgw and keystone
- Sorry for not responding to this one, it's best if such usability issues go to the ceph-users mailing list first. I'm...
- 12:54 PM rgw Bug #6709 (Can't reproduce): rgw upgrade test fails during readwrite
- There's a good chance that this one is #7030, closing it for now.
- 12:53 PM rgw Bug #6829 (Resolved): rgw: missing RGWUserAdminOpState::system_specified initialization
- This was merged long ago, commit:890bd5b3a8d7987fec7887915987a462998096d5. Cherry-picked into dumpling at commit:6b65...
- 12:47 PM rgw Fix #7043 (Resolved): RGW CORS fixes for Access-Control-Request-Headers
- 3 related commits landed dumpling at commit:fdea76ef6f7d7c4ee89c30d430f5495072023957, commit:da2267a87e37afa28385e915...
- 12:12 PM rgw Bug #6940 (Resolved): rgw: reading bucket policy through bucket restful api fails
- backporte to dumpling, commit:da5739e3903f8c30c8168199413818922b4a29bad
- 12:11 PM rgw Bug #7183 (Resolved): RGW CORS POST fix for subusers and cleanups
- Relevant commit backported to dumpling at commit:5f1eea2ccf1ee4296530fc754bfd5dfc1571cd62.
- 12:09 PM rgw Bug #7168 (Resolved): 404 Errors When save immediately follows a delete
- Fix landed dumpling at commit:1e2984ac4a4ed0508e1b5efc8b69ae4da0cac824, and commit:ba792cdc8d0c006e260e6a02a33ca1491b...
- 11:10 AM Bug #7116 (Resolved): mon: pg_temp left behind if pool deleted while pg_temp exist
- 09:14 AM Bug #7116 (Fix Under Review): mon: pg_temp left behind if pool deleted while pg_temp exist
- wip-7116-joao ; https://github.com/ceph/ceph/pull/1153
Haven't been able to reproduce using David's test for well ... - 11:00 AM Bug #7060 (Resolved): mon: osdmap scrub crc mismatch
- 09:24 AM rgw Bug #6919 (Resolved): rgw: copy of some zero sized objects failure
- fixed at bobtail, commit:8fb15edf79757a24f3c788553d4befcd587a680a
cuttlefish, commit:9c67226dfc9f78663975d864bb0badd... - 09:07 AM rgw Bug #7099: Strange Comportments with media files
- It seems to me that the client is hanging up because it's getting something it didn't expect. It's really hard to kno...
- 08:38 AM rgw Bug #7054 (Resolved): rgw: replace mongoose with civetweb
- 08:38 AM rgw Bug #7054 (Won't Fix): rgw: replace mongoose with civetweb
- 05:14 AM Revision 4c98d676 (ceph): Merge pull request #175 from ceph/wip-tcmalloc
- valgrind: ignore tcmalloc uninitialized memory
- 04:50 AM RADOS Fix #6250: OSD: handle ENODEV on reads
- Have you got any target version to fix this issue? Thank you!
- 02:14 AM Revision b1351280 (ceph): Merge pull request #1105 from ceph/wip-7168
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 01:13 AM Revision 3c77c4c5 (ceph): OSDMap: use deepish_copy_from in remove_redundant_temporaries
- Better not to open-code it. We do a bit of extra work here, but it's worth
it.
Signed-off-by: Sage Weil <sage@inkta... - 12:31 AM Revision 1408a69b (ceph): correct user name
01/27/2014
- 11:40 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- > That I find to be a pretty unlikely problem — random balances aren't going to result in that happening very often....
- 09:43 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Guang Yang wrote:
> After checking the fix, I think there is another potential improvement over the splitting, that ... - 10:57 PM Revision 120b3fbf (ceph): Merge pull request #1080 from onlyjob/master
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 10:17 PM Revision bd54b984 (ceph): OSDMap: deepish_copy_from()
- Make a deep(ish) copy of another OSDMap. Unfortunatley we can't make the
compiler-generated copy operator/constructo... - 10:17 PM Revision 368852f6 (ceph): OSDMap: fix damaging input osdmap from remove_down_temps
- The default copy constructor copies shared_ptrs do vectors that are then
modified by apply_incremental, which means t... - 09:52 PM Revision 7da08ae2 (ceph): packaging: apply udev hack rule to RHEL
- In the RPM spec file there is a test to deploy the uuid hack udev rules
for older udev operating systems. This includ... - 09:51 PM Revision 9801718e (ceph): packaging: apply udev hack rule to RHEL
- In the RPM spec file there is a test to deploy the uuid hack udev rules
for older udev operating systems. This includ... - 09:50 PM Revision 9e523984 (ceph): packaging: apply udev hack rule to RHEL
- In the RPM spec file there is a test to deploy the uuid hack udev rules
for older udev operating systems. This includ... - 09:49 PM Revision 536306df (ceph): Merge pull request #1149 from kdreyer-inktank/wip-7245-redhat-udev
- packaging: apply udev hack rule to RHEL
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Derek Yarnell <derek@... - 07:32 PM Revision 64a0b4fa (ceph): packaging: apply udev hack rule to RHEL
- In the RPM spec file there is a test to deploy the uuid hack udev rules
for older udev operating systems. This includ... - 07:29 PM Revision cacdfd91 (ceph): Merge branch 'wip-user-quota-2'
- Conflicts:
src/common/config_opts.h
src/rgw/rgw_common.h
src/rgw/rgw_json_enc.cc
src/rgw/rgw_quota.cc
src/rgw/rg... - 06:28 PM Revision e424d78c (ceph): Be more verbose about log file locations
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:14 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
- I've pushed the cherry-picked commit to a new branch "rhel7": https://github.com/ceph/ceph-client/tree/rhel7 . As the...
- 06:04 PM rgw Bug #7168 (Pending Backport): 404 Errors When save immediately follows a delete
- commit:86c15480fc3e33b9a3b84d0af68d8398fc732bae
- 04:57 PM Bug #7250 (Resolved): osd: string xattr comparison can have undefined behavior
- It's using the non-nul-terminated string.data() method with strcmp(), resulting in undefined behavior in c++98.
- 04:56 PM Feature #5995: EC: [link] Getinfo should use PGBackend methods to determine when peering can cont...
- 01:51 PM Feature #5995 (In Progress): EC: [link] Getinfo should use PGBackend methods to determine when pe...
- 04:51 PM Bug #7249 (Resolved): osd: int xattr comparison is endian-dependent
- The xattr is loaded off disk and interpreted without decoding it. librados also has no interface to set such a value,...
- 02:29 PM Bug #7245: RedHat udev 95-osd-rules file
- I checked the 0.75 RPMs to look further into this. http://ceph.com/rpm-testing/rhel6/x86_64/ceph-0.75-0.el6.x86_64.rp...
- 02:22 PM Bug #7245: RedHat udev 95-osd-rules file
- Thanks again, yes we have rebuilt the packages with some changes that didn't land in emperor yet so this is how it bi...
- 01:42 PM Bug #7245: RedHat udev 95-osd-rules file
- to clarify: i think the reason this hasn't caused problems yet is because our el6 packages have been built on centos ...
- 01:42 PM Bug #7245 (Resolved): RedHat udev 95-osd-rules file
- 11:28 AM Bug #7245 (Fix Under Review): RedHat udev 95-osd-rules file
- Proposed here: https://github.com/ceph/ceph/pull/1149
Derek I listed you as the author of the Git commit in order ... - 11:13 AM Bug #7245: RedHat udev 95-osd-rules file
- I agree, I didn't know if CentOS provided this connivence macro or not so I didn't want to assume.
- 11:10 AM Bug #7245 (In Progress): RedHat udev 95-osd-rules file
- 11:08 AM Bug #7245: RedHat udev 95-osd-rules file
- Thanks for tracking this down. CentOS's redhat-rpm-config package defines a %{rhel} macro, so I'm thinking we should ...
- 10:57 AM Bug #7245 (Resolved): RedHat udev 95-osd-rules file
- In the RPM spec file there is a test to deploy the uuid hack udev rules for older udev operating systems. This inclu...
- 02:01 PM Bug #7248 (Resolved): osd: bench set max size
- Occasionally, an OSD bench with default values will cause a crash of the process for that OSD. This crash can be rel...
- 01:51 PM Feature #6438: EC: implement EC client IO
- 01:51 PM Feature #6437: EC: implement ECBackend recovery
- 01:51 PM Feature #5999: EC: [link] OSD internals must work in terms of cpg_t
- 01:50 PM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
- 01:47 PM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
- 11:16 AM rgw Feature #6870: rgw: user level quota: new user objclass
- User quota was merged at commit:cacdfd9165d32652bf82d3400c15485a89824a3d
- 11:15 AM rgw Feature #6870 (Resolved): rgw: user level quota: new user objclass
- 11:15 AM rgw Feature #6874 (Resolved): rgw: user level quota: rest api
- 11:15 AM rgw Feature #6873 (Resolved): rgw: user level quota: radosgw-admin interface
- 11:15 AM rgw Feature #6872 (Resolved): rgw: user level quota: async update of bucket info in user objclass
- 11:15 AM rgw Feature #6871 (Resolved): rgw: user level quota: core functionality
- 09:43 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- I'm sorry to say that but there isn't. There are nothing related to ceph in /var/log.
- 08:14 AM Bug #7216 (Need More Info): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- Is there a full log for this monitor, as well as for the other 2 monitors?
- 09:27 AM Bug #7060: mon: osdmap scrub crc mismatch
- Greg - please take a look at wip-7060.
- 07:25 AM Revision 40a69391 (ceph): client: Fallocate inline data path
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:25 AM Revision 81c4f54e (ceph): client: Make inline size tunable
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:25 AM Revision e3c4c4cd (ceph): mds: Add inline switch
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:25 AM Revision ddbaa5c2 (ceph): mds: Shutdown old mds when inline enable
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:25 AM Revision b99e9d3b (ceph): mds: Handle client compatibility
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:25 AM Revision 9265d76a (ceph): client: Avoid uninline empty inline data
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 1280d99e (ceph): mds: Push inline data to client in inodestat
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 45c2ab45 (ceph): mds: Receive updated inline data from client
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision be3db0b8 (ceph): client: Add inline fields to Inode
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 3c05e809 (ceph): client: Receive inline data pushed from mds
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 165ddb9a (ceph): client: Push inline data to mds by send cap
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 4a5c0990 (ceph): client: Add inline data migration helper
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision a0cb5242 (ceph): client: Read inline data path
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 47e6a782 (ceph): client: Write inline data path
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision ac5c9dd3 (ceph): ceph: Add inline fields to MClientCaps
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 0f00f07d (ceph): osdc: Add write method with truncate parameters
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 3aa7f0bc (ceph): mds: Add inline fields to Capability
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision cf63f7e6 (ceph): mds: Push inline data to client in cap message
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 07:24 AM Revision 7af7a5e1 (ceph): ceph: Add inline fields to InodeStat
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 06:50 AM Revision eff9f022 (ceph): If 'ceph osd metadata' isn't working, inform the user about it via stderr
01/26/2014
- 08:14 PM Revision 715586fe (ceph): Merge pull request #1143 from dachary/wip-vstart-disk-usage
- unittests: fail early when low on disk
Reviewed-by: Sage Weil <sage@inktank.com> - 01:25 PM Revision c1c1aa91 (ceph): Merge pull request #1003 from dachary/wip-handle-forward-unittest
- mon: test for MForward messages
Reviewed-by: Joao Eduardo Luis <joao@inktank.com> - 12:40 PM Revision d9a689d6 (ceph): mon: shell test helpers to run MONs from sources
- The intent is to make it more convenient to reproduce a specific mon
behavior and observe the result by grepping the ... - 12:40 PM Revision fffbfc94 (ceph): mon: test for MForward messages
- Creates two mons, send a mon command to the peon and check that the
command is forwarded to the leader.
Add a test t... - 12:32 PM Revision c06eca24 (ceph): unittests: fail early when low on disk
- Scripts from qa that are run as unittests via test/vstart_wrapper.sh may
fail because the partition on which it runs ... - 11:34 AM devops Feature #7239: ceph-deploy: install cephfs java bindings
- Oh, neither is libcephfs. Maybe this doesn't make since yet.
- 11:31 AM devops Feature #7239 (Closed): ceph-deploy: install cephfs java bindings
- ceph-deploy doesn't install cephfs java bindings, which makes hadoop deployment a pain if ceph is originally deployed...
- 09:53 AM Subtask #7146: implement osd crush rule create-erasure
- "work in progress":https://github.com/ceph/ceph/pull/1144
- 12:54 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- I see Guang's concern is that the all threads within a thread pool might be working on splitting, as most of the fold...
- 12:34 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Greg Farnum wrote:
> Hmm, the problem with that is:
> 1) people are really bad at estimating how much stuff they're...
01/25/2014
- 03:16 PM Subtask #6064: erasure code : convenience functions to code / decode
- Removing from parent as it seems this is not going to be needed for a first implementation. Keeping it because it may...
- 03:14 PM Subtask #6434 (Rejected): review and test PGBackend
- It looks like I'm not going to do this.
- 03:10 PM Subtask #6478: ErasureCode : XOR plugin
- Part of the initial implementation had an efficient XOR erasure code part that could be turned into a plugin to be us...
- 03:07 PM Feature #7238 (Fix Under Review): erasure code : implement LRC plugin
- "work in progress":https://github.com/ceph/ceph/pull/1142
- 02:56 PM Feature #7238 (Resolved): erasure code : implement LRC plugin
- "ready for review":https://github.com/ceph/ceph/pull/1921
previous draft implementations "1":https://github.com/ce... - 07:45 AM Bug #7186: ceph-rest-api: /tell/<osdid-or-pgid>/query doesn't work
- Good point, I must have missed that. Can we close this bug ?
- 03:37 AM Bug #7237 (Closed): replaced osd is silently prevented from joining the cluster
- The disk holding one of my OSDs died. After replacing the disk and creating a new osd fs on it, the osd would start...
01/24/2014
- 11:33 PM Revision 9413a519 (ceph): rgw: simplify a code path
- remove some duplicate code.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:25 PM Revision 1b0567b0 (ceph): radosgw-admin: add usage for user stats [--sync-stats]
- add missing usage
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:11 PM Revision 97edd2fc (ceph): doc: Switched logging to true. Now required for sync agent.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:09 PM Bug #7222: init-ceph failed when cluster created by "mkcephfs" and start osd firstly and
- Yes, ceph-disk can do it.
But if use "mkcephfs", it may failed. Maybe it better to do more things in "mkcephfs" side - 09:34 AM Bug #7222: init-ceph failed when cluster created by "mkcephfs" and start osd firstly and
- when is the osd not in the osdmap? this is normally done by ceph-disk activate...
we somewhat deliberately error ... - 12:26 AM Bug #7222 (Won't Fix): init-ceph failed when cluster created by "mkcephfs" and start osd firstly ...
- When the OSD is not in OSDMap and run "init-ceph" to start, it will report error when execute "ceph osd crush create-...
- 11:07 PM Revision 92cabd41 (ceph): rgw: new restful api for retrieving user quota info
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:07 PM Revision 8a69ac89 (ceph): rgw: implement restful set user quota request
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:07 PM Revision e5dc8d65 (ceph): rgw, cls_user: handle error cases related to response decoding
- Certain operations weren't handling errors in decode, add some missing
logic.
Signed-off-by: Yehuda Sadeh <yehuda@in... - 11:07 PM Revision 9a55fa1c (ceph): cls_user: add generate_test_instances() implementation
- to all the encoded/decoded stuff
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:07 PM Revision 0f7b3c72 (ceph): rgw: quota thread for full user stats sync
- Get user stats up to date periodically. Add configurables for different
periods, whether we update idle users.
Make s... - 08:33 PM Revision f8e4af2d (ceph): OSDMonitor: do not allow creation of EC pools if the quorum can't handl...
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:33 PM Revision 41796c07 (ceph): Monitor: add a function to get the required quorum features from the lo...
- We will use this to avoid deferring to people who can't read our store.
Signed-off-by: Greg Farnum <greg@inktank.com> - 08:33 PM Revision 687b570b (ceph): Elector: ignore messages from mons without required feature capabilities
- We maintain a list of required_features which the other monitor's features
must supply. This starts out at 0 and is i... - 08:33 PM Revision 3d4a6739 (ceph): Elector: send an OP_NAK MMonElection to old peers who support it
- Only new monitors support receiving OP_NAK from a peer without crashing, but
when we add new required features in the... - 08:33 PM Revision 51ffede3 (ceph): mon: do not use CEPH_FEATURES_ALL for things that touch the disk
- We want to encode with our quorum_features instead. Remaining uses of
CEPH_FEATURES_ALL are:
1) when the Elector is s... - 08:33 PM Revision e79e1d28 (ceph): Monitor: introduce a function that translates quorum features into disk...
- After an election, we call apply_quorum_to_compatset_features(). It translates
from the quorum features into monitor ... - 06:28 PM Revision 7545177a (ceph): rgw, cls_user: fix bucket creation
- There's a single op to create and update the user bucket info, however,
the cases differ a bit, as we only need to gu... - 06:28 PM Revision 6f34df45 (ceph): rgw: sync bucket stats thread
- a new thread that periodically sync stats of recently modified buckets.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.... - 06:28 PM Revision 2f9a93d3 (ceph): rgw: round bytes to the next 4k for quota use
- Be more consistent as we round it like this in the objclass, so we need
the accounting to match.
Signed-off-by: Yehu... - 06:28 PM Revision 0b7968cd (ceph): cls_user: header cleanup
- put stats under a new struct
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision a68b52af (ceph): cls_user: keep time info about stats update
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision ba395128 (ceph): cls_user: op to keep track of sync completion time
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 5976bfcc (ceph): radosgw-admin: update stats sync completion
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision d9920439 (ceph): radosgw-admin: dump header when requested for user stats
- header also contains sync timestamps, so we should dump it.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision a6fae689 (ceph): rgw: more rgw_quota fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 12f5801b (ceph): rgw: configure user quota also through region map
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision c59a98e0 (ceph): rgw: more quota fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 45b22293 (ceph): rgw: user quota should rely on cached info
- user quota should rely on cached info if it says that we're at the
limit, since backend info might not be up to date.... - 06:28 PM Revision c1c40df1 (ceph): rgw: implement quota handlers for user stats
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision a854d893 (ceph): rgw: some fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 15c01895 (ceph): radosgw-admin: user quota interface
- also add needed functionality in RGWUser
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision cfb9553c (ceph): rgw: enable user quota
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 04b5a711 (ceph): rgw: some quota fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 4aee3fa2 (ceph): rgw: rename RGWBucketStats to RGWStorageStats
- make it more generic, will be reused for user's stats.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision 92a87b3d (ceph): rgw: refactor quota cache
- bucket quota cache is going to be reused, add a new abstract layer.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision 364f7c54 (ceph): rgw: move some code around, no actual changes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision c13634e8 (ceph): rgw: extend infrastructure to handle user stats read
- Some helper functions that return data in required format for quota, add
async functions.
Signed-off-by: Yehuda Sade... - 06:28 PM Revision eef7ba48 (ceph): rgw, radosgw-admin, cls/user: retrieve user stats
- add a new op to retrieve user header, new radosgw-admin command to stat
user.
Signed-off-by: Yehuda Sadeh <yehuda@in... - 06:28 PM Revision c8793fba (ceph): cls/user: some fixes + handle old buckets case
- If a bucket was created prior to the new accounting, we can't substract
the old values, as the header stats didn't ac... - 06:28 PM Revision cbe1da85 (ceph): radosgw-admin: bucket stats --sync-stats [--bucket=...]
- Sync user stats, either for a single buckets, or for all user's buckets.
Signed-off-by: Yehuda Sadeh <yehuda@inktank... - 06:28 PM Revision 5612ded3 (ceph): rgw: pass bucket owner all around
- User quota operations require that we know who the actual user we do the
operation on is. Pass that info when creatin... - 06:28 PM Revision 23aa65f6 (ceph): rgw: replace user bucket listing with objclass call
- instead of directly accessing the omap operation
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision c7b4d008 (ceph): rgw: move bucket add / remove to new user objclass
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:28 PM Revision 438aea7f (ceph): cls/user: accounting functionality
- Keep user total accounting in omap header, handle add/dec functionality.
Signed-off-by: Yehuda Sadeh <yehuda@inktank... - 06:28 PM Revision edcf9fed (ceph): cls/user: a new op to retrieve user header
- user header holds user total stats
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:28 PM Revision 248c4aef (ceph): rgw: new user objclass
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:56 PM Revision a200fa96 (ceph): removed roles from task file
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 05:13 PM devops Tasks #7230 (Resolved): Rebuild sync-agent packages for dumpling repo
- Would like to see some fixes make their way into the dumpling repo sometime soon.
- 04:57 PM rgw Bug #7229 (Resolved): sync-agent logging breaks after logrotate
- Josh fixed in commit:cabc3a6a2da1d437f766003600e7fd524a96f7d2
- 04:47 PM rgw Bug #7229 (Resolved): sync-agent logging breaks after logrotate
- sync-agent should continue logging to the specified log after a logrotate. As of now, it appears to continue running ...
- 04:31 PM Revision 5756f7c4 (ceph): Merge pull request #1102 from ceph/wip-rgw-civetweb-2
- Wip rgw civetweb 2
Reviewed-by: Sage Weil <sage@inktank.com> - 04:19 PM Revision 50722a7d (ceph): Symlink worker logs into job archive dir
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 03:57 PM rgw Feature #6678 (In Progress): rgw: reject writes to secondary zones
- Please consider this for a backport to dumpling.
- 03:53 PM Bug #7218: Displaying wrong number of pools with ceph -s after removeing a pool
- The experiment I did yesterday still shows the inconsistency. I was just looking at the output, in PGMap::print_summ...
- 03:41 PM Revision b90570f3 (ceph): Fix 404 broken links to logging and debug configuration
- Signed-off-by: David Moreau Simard <dmsimard@iweb.com>
- 03:28 PM rgw Bug #7169 (Fix Under Review): rgw: list multipart parts broken (> 1000 parts)
- Pushed two different fixes, one for wip-7169, second one for wip-7169-dumpling. The dumpling one only fixes the speci...
- 03:13 PM Bug #7207 (Resolved): Lock contention at filestore I/O (FileStore::lfn_open) during filestore fol...
- This is in master in commit:55ab35ba9c1b3a1c4fc0abe5539c6bc320409371. It passed a full rados suite run.
Apparently... - 09:50 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Hmm, the problem with that is:
1) people are really bad at estimating how much stuff they're going to put into a sto... - 02:45 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Thanks for looking at this!
In terms of folder splitting, I am wondering if people are interested in an alternativ... - 02:58 PM Bug #7190: osd/OSD.cc: 2338: FAILED assert(oldmap->have_pg_pool(pgid.pool()))
- Saw this several times in a suite testing a filestore change as well:
http://qa-proxy.ceph.com/teuthology/gregf-20... - 01:54 PM Revision 60da6e0c (ceph): Merge pull request #177 from ceph/wip-7213
- use create-initial for deploying monitors
- 01:46 PM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- i got a complete log with osd=20 and filestore=20
- 12:35 PM rgw Feature #7228 (New): Get RadosGW Federated config and Keystone working nicely
- With the currently documented method of Keystone integration, it's not clear if Keystone will function properly with ...
- 11:41 AM Bug #7060 (Fix Under Review): mon: osdmap scrub crc mismatch
- 11:08 AM devops Bug #7227: ceph-create-keys upstart script fails
- This is emperor stable on Ubuntu 12.04
- 11:04 AM devops Bug #7227 (Can't reproduce): ceph-create-keys upstart script fails
- I've been trying to debug this problem that shows up when using ceph-deploy, and have found some pretty weird behavio...
- 09:47 AM Fix #7215: mon: prevent old monitors which do not support new encodings from joining the cluster
- Nifty, thanks Tamil! That should let me cover a bunch of it.
- 08:37 AM Fix #7215: mon: prevent old monitors which do not support new encodings from joining the cluster
- Greg, we have some tests in the upgrade:parallel suite [ceph-qa-suite/suites/upgrade/parallel/stress-split] to do thi...
- 09:34 AM Revision 4553e6af (ceph): Fix trailing space
- Fix trailing space and indentation.
- 06:43 AM Revision 28af392b (ceph): Merge pull request #1116 from jcsp/doc_toofull
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:36 AM Revision e23513fb (ceph): Merge pull request #1135 from ceph/use-ceph-sharedptr
- libc++: convert tr1 uses
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:15 AM Revision 7bed2d6f (ceph): called sysinfo.append(meta) in get_sysinfo within the while loop
- 06:08 AM Revision ef3fe7b6 (ceph): Updated README with How-to-use instructions
- 04:35 AM Revision faae5b94 (ceph): libc++: convert tr1 uses
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 01:11 AM Revision ea026c6c (ceph): doc: Added domain pool, and changed zone configs to use domain tool so ...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:11 AM Revision 0303f0f1 (ceph): doc: Change zone domain to include "domain" so it is clear.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:21 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
- Also i think i need to add that it was clean install of 0.72.2 version. No updates, no movements.
- 12:03 AM Revision 95e63ac6 (ceph): doc: Added space between {Query_String} and [E=HTTP ... to solve for 50...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
01/23/2014
- 11:44 PM Revision 9a7643bb (ceph): Merge pull request #1134 from ceph/wip-backend-uninit-use
- ReplicatedBackend: fix uninitialized use warning/bug
Reviewed-by: Samuel Just <sam.just@inktank.com> - 11:40 PM Revision 6f6b1eea (ceph): ReplicatedBackend: fix uninitialized use warning/bug
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:32 PM Revision df4df46d (ceph): Monitor: use a single static accessor for getting CompatSet features of...
- This way we don't need to maintain two working code paths.
Signed-off-by: Greg Farnum <greg@inktank.com> - 10:27 PM Revision 69150536 (ceph): doc: Adding more information on style and usage for documenting Ceph.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:41 PM Revision cf250a8f (ceph): use create-initial for deploying monitors
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 09:34 PM Revision 2216afdf (ceph): doc: Fixed omission of a comma in zone configuration.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:48 PM Revision 55ab35ba (ceph): FileStore: perform LFNIndex lookup without holding fdcache lock
- Fixes: #7207
Signed-off-by: Samuel Just <sam.just@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 08:47 PM Revision 689f983e (ceph): Merge remote-tracking branch 'origin/next'
- 07:00 PM Revision 1560cc01 (ceph): mongoose: git rm src/mongoose
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:22 PM Revision 102c83a3 (ceph): Merge pull request #1132 from ceph/wip-erasure-rule
- osd/OSDMap: do not create erasure rule by default
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Loic Dach... - 05:41 PM Revision 3f20a41f (ceph): civetweb: update submodule
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:41 PM Revision d26e7665 (ceph): civetweb: fix module uri
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:41 PM Revision 287ea5ca (ceph): rgw: modify the civetweb rule
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:41 PM Revision 1a2bed1e (ceph): civetweb: add include to makefile
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:41 PM Revision bd089b12 (ceph): civetweb: md5.inl -> md5.h
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:40 PM Revision f2f74754 (ceph): rgw: switch mongoose to civetweb
- Fixes: #7054
mongoose is now GPL, using the civetweb fork instead.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 05:27 PM Revision d8bafaeb (ceph): Merge pull request #1131 from ceph/use-unordered-map
- osd: use ceph:: scoped hash_map
Reviewed-by: Sage Weil <sage@inktank.com> - 05:16 PM Revision 08fa34d9 (ceph): osd/OSDMap: do not create erasure rule by default
- If we do, we will require the v2 feature bit from clients.
We could only include feature bits for rules that are act... - 03:48 PM Bug #7218: Displaying wrong number of pools with ceph -s after removeing a pool
- Where are you looking?
I'm assuming that since this is PGMap output, the OSDs haven't all finished deleting the po... - 03:29 PM Bug #7218: Displaying wrong number of pools with ceph -s after removeing a pool
- I looked, and this is reporting a hash_map .size(); I'll bet .size() isn't an accurate count of currently-defined key...
- 03:19 PM Bug #7218 (Resolved): Displaying wrong number of pools with ceph -s after removeing a pool
- $ceph osd lspools
0 pool0,1 pool1,2 pool2,3 pool3,
ceph osd pool delete pool0 pool0 --yes-i-really-really-mean-it
... - 03:27 PM Fix #7215: mon: prevent old monitors which do not support new encodings from joining the cluster
- wip-7215-quorum-features
Going to have to do some manual testing; not sure if there's any feasible automated testing... - 02:46 PM Fix #7215 (Resolved): mon: prevent old monitors which do not support new encodings from joining t...
- When we added our new osdmap encoding, we changed the on-disk encoding of the map. If old monitors join up, they won'...
- 03:20 PM Revision 6f8541c8 (ceph): osd: use ceph:: scoped hash_map
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 03:12 PM Revision dea7534b (ceph): Merge pull request #1130 from ceph/wip-cuttlefish-backport-6620
- mds: MDSMap: adjust buffer size for uint64 values with more than 5 chars
- 03:12 PM Revision 5817078b (ceph): Merge pull request #1129 from ceph/wip-dumpling-backport-6620
- mds: MDSMap: adjust buffer size for uint64 values with more than 5 chars
- 03:08 PM Revision 47dcdb32 (ceph): rados/thrash: add cache + snaps workload
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:52 PM Documentation #3839 (Resolved): SSD crushmap example will not compile
- 02:51 PM Bug #7216 (Can't reproduce): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- Greetings.
Today i have restarted my cluster and got all tree monitors not starting. Whole output is attached but ... - 01:55 PM rgw Feature #7214 (Rejected): radosgw-agent should work with older versions of python-requests
- precise packages 0.8.2-1, yet radosgw-agent needs >= 1.2.1 to work (not packaged in ubuntu until saucy).
- 12:33 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- As he noted, there's already a patch that gets rid of this lock over the affected area (although it also needs the im...
- 10:14 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- 3849ce2fa428dcfab57d6a7fdde1870f1448a33f I think
- 11:39 AM Revision 0c7e035a (ceph): mds: MDSMap: adjust buffer size for uint64 values with more than 5 chars
- Fixes: #6620
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 0e8182edd850f061421... - 11:36 AM Revision abf64417 (ceph): mds: MDSMap: adjust buffer size for uint64 values with more than 5 chars
- Fixes: #6620
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 0e8182edd850f061421... - 10:58 AM Bug #7212 (Resolved): monitor fails to start
- Some teuthology/ceph-deploy tests are failing for the ceph master branch because some monitors are
not coming up:
... - 09:26 AM Bug #6620 (Resolved): mon: MDSMonitor/MDSMap: 'ceph report' leads to segfault on MDSMap::dump_info
- This has been backported to both cuttlefish and dumpling.
- 03:31 AM Bug #6620: mon: MDSMonitor/MDSMap: 'ceph report' leads to segfault on MDSMap::dump_info
- wip-dumpling-backport-6620 , pr 1129
wip-cuttlefish-backport-6620, pr 1130 - 03:05 AM Bug #6620: mon: MDSMonitor/MDSMap: 'ceph report' leads to segfault on MDSMap::dump_info
- bump
- 08:27 AM Revision 645dd31c (ceph): Merge pull request #1064 from ceph/port/libc++
- support libc++
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:47 AM Bug #7211 (Duplicate): Mon: does not validate snapshot removal commands
- #7210. Stupid redmine ticket creation.
- 07:44 AM Bug #7211 (Duplicate): Mon: does not validate snapshot removal commands
- See thread "[ceph-users] failed to open snapshot after 'rados cppool '" at e.g. http://www.spinics.net/lists/ceph-use...
- 07:42 AM Bug #7210 (Resolved): mon: does not validate snapshot removal commands
- See thread "[ceph-users] failed to open snapshot after 'rados cppool '" at e.g. http://www.spinics.net/lists/ceph-use...
- 07:26 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- +1 of the previous question!
I get the impression from comment #6 that this would be easy to fix. Any chance that... - 06:55 AM Revision 289a400a (ceph): Corrected ownership info which was presented as string, added stub code...
01/22/2014
- 10:52 PM Revision 2b0f8cbf (ceph): Merge branch 'wip-client-io-final'
- Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com> - 10:39 PM Revision 167f8523 (ceph): RadosModel: RollBack dirties the object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 7e3ccfef (ceph): ReplicatedPG: take ReplicatedPGRef in BlessedContext
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 96d4a0c2 (ceph): PG::calc_acting: consider newest_update_osd when choosing backfill peers
- We must include newest_update_osd->second.log_tail when considering backfill
peers because in GetLog we will request ... - 10:39 PM Revision e73a9f7b (ceph): ReplicatedPG: make STARTSYNC a noop
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 4fc4573f (ceph): PG: drop messages from down peers
- This overlaps with the existing old_peering_msg() mechanism
except in one case: pulls from a replica not in the actin... - 10:39 PM Revision ecbdeb19 (ceph): PGBackend: clarify rollback_stash name and method comments
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 0bba79b7 (ceph): ReplicatedPG: support async reads on ec pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision a382ab82 (ceph): ReplicatedPG: requeue in_progress_async_reads on_change
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision b3c2ef2d (ceph): ReplicatedPG: make COPY_GET async read friendly
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision f2384412 (ceph): ReplicatedPG: EOPNOTSUPP on ec_pool if there are omaps in the COPY_GET
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision eb8f66d5 (ceph): ReplicatedPG: handle removing the old object in finish_copy_op
- do_osd_ops will need to either copy the old version out of the
way or simply delete it depending on mod_desc. Thus, ... - 10:39 PM Revision e8a08ffa (ceph): ReplicatedPG::finish_copyfrom: check new_obs.exists, not obs.exists
- If the transaction previously created the object, the stat update
will have already happened.
Signed-off-by: Samuel ... - 10:39 PM Revision 7c9425c3 (ceph): ReplicatedPG: fill in mod_desc in finish_copyfrom
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 9fd7a800 (ceph): ReplicatedPG: use append for write and writefull
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 183f41c0 (ceph): ReplicatedPG: fill in mod_desc for hitset repops
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 9273177a (ceph): ReplicatedPG::_process_copy_chunk: use append
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision d0eda792 (ceph): common/hobject: print shard as unsigned, not as char
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision ca37d08e (ceph): ReplicatedPG::trim_object: remove unused int r; declaration
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 6e74123c (ceph): RadosModel: undirty with update_object_undirty
- Otherwise it doesn't behave properly with snapshots since
update_object_version doesn't add another snapshot entry.
... - 10:39 PM Revision 155b4b06 (ceph): PGBackend,ReplicatedBackend: add support for rolling back log entries
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision ecae37c3 (ceph): osd/: introduce xattr caching for ec pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision c98cb1ce (ceph): ReplicatedPG: Fill in rollback info for log events
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 25eced59 (ceph): PGLog: create interface allowing interface user to cleanup/rollback
- We need to be able to allow the PGLog interface user to provide
logic for rolling back and trimming log entries. To ... - 10:39 PM Revision 347d968a (ceph): PGLog: we cannot rollback past a recovered object entry
- We don't recover the older versions, so we can't do a rollback.
In general, this is ok since we had enough copies to ... - 10:39 PM Revision a3e4a844 (ceph): PGLog,PG: reset can_rollback_to when we get a log entry without a trans...
- We cannot rollback past an entry which we didn't actually
apply locally.
Signed-off-by: Samuel Just <sam.just@inktan... - 10:39 PM Revision 66bc91cf (ceph): ObjectStore: _collection_move_rename needs to increment ops
- Bugfix.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:39 PM Revision 2fe5e1f2 (ceph): osd/: add sync/async read methods to PGBackend
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 3ef6282c (ceph): ReplicatedPG: use pgbackend->objects_read_sync() as appropriate
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 647e75ae (ceph): src/: add CEPH_OSD_OP_READ_SYNC
- EC pools won't support SYNC reads. This means that TMAP and friends
along with reads from an object class will not b... - 10:39 PM Revision c60185c0 (ceph): PGBackend: add PGTransaction
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision bf9390f3 (ceph): hobject_t/ReplicatedPG: tempness is now an hobject thing
- PGBackend implmentations will have complete control over the temp
collection. Rather than specifying the collection ... - 10:39 PM Revision 5732f0c9 (ceph): ReplicatedBackend: implement RPGTransaction
- RPGTransaction is essentially a wrapped ObjectStore::Transaction.
The coll_t argument is elided, tempness is instead ... - 10:39 PM Revision 09717e6d (ceph): PG/ReplicatedPG: move snap map management into append_log
- Both the replica and the primary should use the same append_log
mechanism to update the snap map.
Signed-off-by: Sam... - 10:39 PM Revision 26b804f2 (ceph): ReplicatedPG: split out op_applied_replica
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 1a4694fd (ceph): ReplicatedPG: factor out should_send_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision c58c8990 (ceph): PGBackend: allow queue_transaction to specify an op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 53c26bc3 (ceph): osd/: move client op handling into ReplicatedBackend
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision a7a6a2f1 (ceph): osd_types: ObjectModDesc
- Contains information needed to roll back a pg_log_entry_t.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:39 PM Revision 63f64de1 (ceph): osd_types: add ObjectModDesc into pg_log_entry_t
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 05289745 (ceph): osd_types: add a can_rollback_to line to pg_log_t
- This allows us to determine how far back the log can be rolled.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:39 PM Revision 1b5992b0 (ceph): FileStore::lfn_link: handle link within a collection
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 1b0335ed (ceph): common: add option to disable filestore sharded object check
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 03c5344f (ceph): PGLog: allow for empty pg log in update_range if log_tail == eversion_t()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 8494aa84 (ceph): src/test/osd: remove tmap test
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 69ad880e (ceph): test/osd/Object: create encoders for ContDesc
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 7fe22da2 (ceph): test/osd: restructure Object/RadosModel in prep for append
- Attribute handling no longer has special support in ContentsGenerator.
The most recent operation information is now s... - 10:39 PM Revision ca91fb4c (ceph): test/osd: adapt RadosModel to not do omap ops on ec_pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision d0933eef (ceph): test/osd: add append support to WriteOp
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 0885880b (ceph): test/osd/TestRados.cc: skip 0 weight ops
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 4d56e3c8 (ceph): test/osd/: verify length of buffer returned in read
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision d3c8e85a (ceph): ReplicatedBackend: update the collection_list mechanisms to skip stashe...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:39 PM Revision 393a035b (ceph): OSDMonitor: add debug_fake_ec_pool
- This flag will cause ReplicatedPG to act as though the
pool were actually an EC pool in that operations will
be restr... - 10:39 PM Revision 6d05fa23 (ceph): PG: prefer older last_update for ec_pool
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:38 PM Revision a1ee1ee7 (ceph): PGLog::rewind_divergent_log: we can rewind to tail, fix assert
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:38 PM Revision c03d027c (ceph): hobject: admit that gen_t is actually version_t
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:38 PM Revision 518774dc (ceph): ObjectStore: improve name of the queue_transaction which cleans up the ...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:38 PM Revision 06f7a98a (ceph): ReplicatedBackend.h: don't need to be active for pushes
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:38 PM Revision b7d100b6 (ceph): FileStore::_collection_move_rename: remove source before closing guard
- Fixes a bug in _collection_move_rename replays.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:38 PM Revision 1f9457c5 (ceph): ReplicatedBackend: remove pushing entry for each object as it completes
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:38 PM Revision a2006507 (ceph): PGLog: don't move up log.tail
- Moving up log.tail unnecessarily risks backfilling
a replica after a split. Also, it disrupts the
property that repl... - 09:44 PM Revision d6b592c0 (ceph): Merge pull request #1079 from ceph/wip-tier-bits
- osd: a few tiering fixes
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:10 PM Bug #7208 (Resolved): CEPH_FEATURE_CRUSH_V2 feature mismatch
- In attempting to test kernel rbd with 0.74-553-g54d51d8-1saucy on kernel 3.11, I'm seeing:
feature set mismatch, m... - 07:39 PM Bug #7207 (Resolved): Lock contention at filestore I/O (FileStore::lfn_open) during filestore fol...
- There is a lock contention happening at filestore I/O (FileStore::lfn_open, https://github.com/guangyy/ceph/blob/mast...
- 06:48 PM CephFS Bug #7206: Ceph MDS Hang on hadoop workloads
- just enable admin socket (without enabling client debug and mds debug). When the hang occurs, dump client request and...
- 06:18 PM CephFS Bug #7206: Ceph MDS Hang on hadoop workloads
- Greg Farnum already knows this, but for reference
I spent a large part of today with debug logging on to try to ca... - 02:01 PM CephFS Bug #7206: Ceph MDS Hang on hadoop workloads
- That should be enough to either diagnose it or realize we need to reproduce it locally.
- 01:58 PM CephFS Bug #7206: Ceph MDS Hang on hadoop workloads
- Greg Farnum wrote:
> This could be an issue with time sync on the nodes; check your clock drift. (That's the only is... - 01:26 PM CephFS Bug #7206: Ceph MDS Hang on hadoop workloads
- This could be an issue with time sync on the nodes; check your clock drift. (That's the only issue I know of that we'...
- 12:30 PM CephFS Bug #7206 (Can't reproduce): Ceph MDS Hang on hadoop workloads
- With blatant disregard for posted advice about the stability of ceph-fs, I attempted to use it for testing out some h...
- 05:40 PM Revision 022e531b (ceph): added roles for bucket quota tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 04:33 PM Tasks #6185: expand upgrade tests to be able to test downgrade
- I don't think we want to do this until we decide that supporting downgrade is a worthwhile investment.
- 04:33 PM RADOS Feature #6436: erasure-code: Downgrade testing
- We don't support daemon downgrade in general, so let's not try and make that a requirement for testing here!
- 04:20 PM Revision 8eaef414 (ceph): Merge pull request #1126 from ceph/wip-osdmapenc-fix
- MOSDMap: reencode maps if target doesn't have OSDMAP_ENC
Reviewed-by: Sage Weil <sage@inktank.com> - 03:41 PM Bug #7186: ceph-rest-api: /tell/<osdid-or-pgid>/query doesn't work
- The help information is a little confusing here, "query" only works for placement group while "version" only works fo...
- 03:34 PM Revision 8060afd7 (ceph): MOSDMap: reencode maps if target doesn't have OSDMAP_ENC
- Reencode both full and incremental maps if target doesn't know how to
decode OSDMAP_ENC maps (CEPH_FEATURE_OSDMAP_ENC... - 02:44 PM Feature #5996 (Resolved): EC: [link] PG::calc_acting and friends should always choose the shortes...
- 02:44 PM Feature #5990 (Resolved): EC: [link] Factor out the ReplciatedPG object replication and client wr...
- 02:44 PM Feature #6832 (Resolved): EC: Adapt pg log to include information necessary for rollback
- 02:44 PM Feature #6831 (Resolved): EC: Adapt ReplicatedPG read path to handle async reads
- 12:50 PM Bug #7185: ceph-rest-api inconsistent routing with show_human_help
- /tell is a command itself:...
- 12:26 PM Revision 9792500a (ceph): doc: add-or-rm-mons.rst: better explanation on number of monitors
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:39 AM RADOS Feature #7205 (New): erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
- Or, re-express using async read/sync read.
- 09:45 AM Revision 9eac5e37 (ceph): Added update_metadata, clear_metadata, and usage description code
- 09:38 AM Bug #7203 (Can't reproduce): osd/ReplicatedPG.cc: 9551: FAILED assert(r >= 0) in scan_range
- on next:...
- 09:36 AM Subtask #7158: EC: flesh out how the ceph tool should be used to manage ec pools and create sub t...
- i think pool creation is all there. the create-pyramid rule we can treat separately, i think!
but... should we ha... - 02:46 AM Subtask #7158: EC: flesh out how the ceph tool should be used to manage ec pools and create sub t...
- Loic pointed out that there's already support to create pools via the ceph tool
https://github.com/ceph/ceph/blob/... - 09:32 AM rgw Bug #7169 (In Progress): rgw: list multipart parts broken (> 1000 parts)
- 09:31 AM Bug #7184 (Resolved): osd: scrub complains about num_objects_dirty for old pools
- 03:08 AM Revision e4abe40c (ceph): added roles to rest yaml
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 02:51 AM Revision dcca4137 (ceph): added perl script for rgw bucket quota tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 02:50 AM Revision 28c75f81 (ceph): removing rgw_tests.sh
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
(cherry picked from commit 54caa0192b02b03549fe4ca5d062495e6e429... - 02:44 AM Revision 54caa019 (ceph): removing rgw_tests.sh
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 02:35 AM Revision 98c78736 (ceph): modified rgw suite for bucket quota tests
- Signed-off-by: tamil <tamil@tamil-VirtualBox.(none)>
- 01:50 AM Revision 4550fb5f (ceph): Merge branch 'master' of github.com:ceph/ceph
- 01:50 AM Revision 8b8ede7a (ceph): modified the port to 7280 in the script instead of the default 80
- Signed-off-by: tamil <tamil@tamil-VirtualBox.(none)>
- 01:30 AM Revision 81ff12ec (ceph): Merge pull request #1124 from ceph/wip-cache-mode-fix
- mon/MonCommands: 'invalidate+forward' -> 'forward'
Reviewed-by: Sage Weil <sage@inktank.com>
01/21/2014
- 11:56 PM Revision 850b4f42 (ceph): script for rgw bucket quota testing
- Signed-off-by: tamil <tamil@tamil-VirtualBox.(none)>
- 10:27 PM Revision 339bed1b (ceph): mon/MonCommands: 'invalidate+forward' -> 'forward'
- Commit 4e439857a694 introduced invalidate+forward cache mode, commit
81279e3bb6e0 renamed it to forward, but missed t... - 10:18 PM Revision b88c8eae (ceph): doc: Added Documenting Ceph (draft) document.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:18 PM Revision 90aea596 (ceph): doc: Added documenting Ceph to the toc tree.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:05 PM devops Feature #6986 (In Progress): Build packages containing RBD and CephFS kernel modules for installa...
- I'm building against kernel-3.10.0-54.0.1.el7.x86_64, and I get the following error when using df5f7b6abd0dacf6fa60ac...
- 12:39 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
- 08:16 PM Revision 9fa8d2d1 (ceph): mon/MDSMonitor: do not generate mdsmaps from already-laggy mds
- There is one path where a mds that is not sending its beacon (e.g.,
because it is not running at all) will lead to pr... - 08:16 PM Revision e8298515 (ceph): mon/MDSMonitor: do not generate mdsmaps from already-laggy mds
- There is one path where a mds that is not sending its beacon (e.g.,
because it is not running at all) will lead to pr... - 08:12 PM Revision 3d88dfff (ceph): mon/MDSMonitor: do not generate mdsmaps from already-laggy mds
- There is one path where a mds that is not sending its beacon (e.g.,
because it is not running at all) will lead to pr... - 08:04 PM Revision 291407bc (ceph): Merge pull request #1123 from ceph/wip-stray-mdsmaps
- mon/MDSMonitor: do not generate mdsmaps from already-laggy mds
Reviewed-by: Greg Farnum <greg@inktank.com> - 07:51 PM Revision ed2decb1 (ceph): doc: Fixed end string from '' to `` to stop warnings. Enforced 80 char ...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:29 PM Revision 584c2dd6 (ceph): mon/MDSMonitor: do not generate mdsmaps from already-laggy mds
- There is one path where a mds that is not sending its beacon (e.g.,
because it is not running at all) will lead to pr... - 06:34 PM Revision cd217ec0 (ceph): Merge pull request #1119 from ceph/wip-7184
- osd: ignore num_objects_dirty for old pools
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 03:44 PM devops Bug #7157: ceph-disk list fails in encrypted disk setup
- I'm having this problem, with a fresh install of Ubuntu 12.04 and the latest (as of yesterday) Ceph release (ceph ver...
- 03:40 PM Revision 4c968534 (ceph): packaging: ship libdir/ceph
- Automake puts ceph_common.sh into libdir/ceph, but the Red Hat packaging
was not capturing this file.
Add the libdir... - 01:41 PM Feature #5999 (In Progress): EC: [link] OSD internals must work in terms of cpg_t
- 01:38 PM Feature #6437 (In Progress): EC: implement ECBackend recovery
- 01:37 PM Feature #7167 (Resolved): Add op_process_latency in perf counters
- 01:31 PM Feature #5990 (Fix Under Review): EC: [link] Factor out the ReplciatedPG object replication and c...
- 01:28 PM Feature #6832 (Fix Under Review): EC: Adapt pg log to include information necessary for rollback
- 01:28 PM Feature #6831 (Fix Under Review): EC: Adapt ReplicatedPG read path to handle async reads
- 01:27 PM Feature #5996 (Fix Under Review): EC: [link] PG::calc_acting and friends should always choose the...
- 01:27 PM Feature #6438 (Fix Under Review): EC: implement EC client IO
- 12:39 PM devops Feature #7047: rhel7: build process for rbd.ko, ceph.ko kernel modules
- 12:39 PM devops Feature #7046: rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
- 12:20 PM Feature #7196 (New): qa: test encoding semantics, not just being able to decode/encode different ...
- I have a branch with at least slightly better detection by comparing the json dumps. Need to generate new object corp...
- 12:16 PM Feature #7195 (Resolved): librados: complete C write object operation bindings
- They're missing individual return values, exec, omap (covered by #7194), and possibly a few other features from the c...
- 12:14 PM Feature #7194 (Resolved): librados: omap in the c api
- It doesn't exist, but should. Add it to the read/write object operations bindings.
- 12:13 PM Feature #7193 (Resolved): librados: object operation bindings for reads
- Writes were added recently. It would be useful to have these available for binding to other languages.
- 11:50 AM Revision 6bee1885 (ceph): Docs: Add backfill_toofull to list of PG states
- Signed-off-by: John Spray <john.spray@inktank.com>
- 11:21 AM devops Documentation #2974 (Resolved): doc: update chef docs for mon key distribution
- 10:57 AM Revision 199e614b (ceph): Initial version of the source code. Statistics extraction is done
- 09:45 AM Feature #7192 (Resolved): An easier-to-process health report
Currently, the "ceph health" is great for human consumption, but a bit awkward to feed into a monitoring app, becau...- 05:34 AM Revision 7a2d7f13 (ceph): Merge pull request #1120 from xylv/wip-op-process-latency-squashed
- osd: Add op_process_latency in perf counter
Reviewed-by: Sage Weil <sage@inktank.com> - 03:11 AM Revision 78150bd9 (ceph): osd: Add op_process_latency in perf counter
- Fixes: #7167
Signed-off-by: Ray Lv <xiangyulv@gmail.com>
Also available in: Atom