summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
* 0.94.1.1v0.94.1.1Jenkins2015-04-272-1/+7
|
* init-radosgw: run RGW as rootKen Dreyer2015-04-242-2/+2
| | | | | | | | | | | | | | | The ceph-radosgw service fails to start if the httpd package is not installed. This is because the init.d file attempts to start the RGW process with the "apache" UID. If a user is running civetweb, there is no reason for the httpd or apache2 package to be present on the system. Switch the init scripts to use "root" as is done on Ubuntu. http://tracker.ceph.com/issues/11453 Refs: #11453 Reported-by: Vickey Singh <vickey.singh22693@gmail.com> Signed-off-by: Ken Dreyer <kdreyer@redhat.com> (cherry picked from commit 47339c5ac352d305e68a58f3d744c3ce0fd3a2ac)
* rgw: remove meta file after deleting bucketOrit Wasserman2015-04-162-0/+40
| | | | | | | | | | The meta file is deleted only if the bucket meta data is not synced Signed-off-by: Orit Wasserman <owasserm@redhat.com> Fixes: #11149 Backport: hammer, firefly (cherry picked from commit dfdc7afb59cc8e32cf8bff55faa09076c853de06)
* Move ceph-dencoder build to clientBoris Ranto2015-04-162-24/+24
| | | | | | | The patch simply moves the ceph-dencoder build from server part of the Makefiles to client part of the Makefiles. Signed-off-by: Boris Ranto <branto@redhat.com>
* Rework mds/Makefile.am to support a dencoder client buildBoris Ranto2015-04-163-67/+79
| | | | | | | | The patch adds all the mds sources to DENCODER_SOURCES to allow a dencoder client build. The patch also splits the Makefile.am file to better accomodate the change. Signed-off-by: Boris Ranto <branto@redhat.com>
* rgw/Makefile.am: Populate DENCODER_SOURCES properlyBoris Ranto2015-04-161-8/+9
| | | | | | | | Dencoder is built if ENABLE_CLIENT is set. However, the rgw/Makefile.am populated DENCODER_SOURCES only if WITH_RADOSGW was set. The patch fixes this and populates DENCODER_SOURES if ENABLE_CLIENT is set. Signed-off-by: Boris Ranto <branto@redhat.com>
* Dencoder should never be built with tcmallocBoris Ranto2015-04-161-0/+5
| | | | | | | The patch adds disabled perfglue stubs to DENCODER sources in order to avoid tcmalloc-enabled ceph-dencoder builds. Signed-off-by: Boris Ranto <branto@redhat.com>
* 0.94.1v0.94.1Jenkins2015-04-102-1/+7
|
* Merge pull request #4328 from dachary/wip-11364-hammerLoic Dachary2015-04-101-1/+2
|\ | | | | | | | | | | v4 bucket feature detection Reviewed-by: Sage Weil <sage@redhat.com>
| * crush: fix has_v4_buckets()Sage Weil2015-04-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | alg, not type! This bug made us incorrectly think we were using v4 features when user type 5 was being used. That's currently 'rack' with recent crush maps, but was other types for clusters that were created with older versions. This is clearly problematic as it will lock out non-hammer clients incorrectly, breaking deployments on upgrade. Fixes: #11364 Backport: hammer Signed-off-by: Sage Weil <sage@redhat.com> (cherry picked from commit 38b35ab9d17eb84ac178c4cd3ebcf2ec0f66d8b6)
| * crush: fix dump of has_v4_bucketsSage Weil2015-04-101-0/+1
|/ | | | | | Backport: hammer Signed-off-by: Sage Weil <sage@redhat.com> (cherry picked from commit d6e23413017fb8f5d7f18d74e993ceeedb82d8bc)
* crush/mapper: fix divide-by-0 in straw2Sage Weil2015-04-091-19/+29
| | | | | | | | | | | If the item weight is 0 we don't want to divide; instead draw a minimal value. Fixes: #11357 Reported-by: Yann Dupont <yd@objoo.org> Tested-by: Yann Dupont <yd@objoo.org> Signed-off-by: Sage Weil <sage@redhat.com> (cherry picked from commit 64d1e900ec4f5831972ec80e8d0129604669f5bb)
* osd: fix negative degraded objects during backfillingGuang Yang2015-04-091-2/+4
| | | | | | | | | | When there is deleting requests during backfilling, the reported number of degraded objects could be negative, as the primary's num_objects is the latest (locally) but the number for replicas might not reflect the deletings. A simple fix is to ignore the negative subtracted value. Signed-off-by: Guang Yang <yguang@yahoo-inc.com> (cherry picked from commit 14d7e36d3c978844da73d0e1c8a3a1ec863bac15)
* 0.94v0.94Jenkins2015-04-072-1/+7
|
* debian: remove lttng checking from rulesJosh Durgin2015-04-061-6/+0
| | | | | | | | | | This can be done better in a separate script, which puts these in CEPH_EXTRA_CONFIGURE_ARGS. In particular, this lets us enable lttng for gitbuilder builds, but not release builds. Fixes: #11333 Signed-off-by: Josh Durgin <jdurgin@redhat.com> (cherry picked from commit a294daff0bb69a7e0951f98c9497ccb22e91e705)
* Merge pull request #4246 from ceph/wip-11113-hammerSage Weil2015-04-061-1/+7
|\ | | | | librbd: snap_remove should ignore -ENOENT errors
| * librbd: snap_remove should ignore -ENOENT errorsJason Dillaman2015-04-011-1/+4
| | | | | | | | | | | | | | | | | | | | If the attempt to deregister the snapshot from the parent image fails with -ENOENT, ignore the error as it is safe to assume that the child is not associated with the parent. Fixes: #11113 Signed-off-by: Jason Dillaman <dillaman@redhat.com> (cherry picked from commit cf8094942ccdba831e03e5a79451cfa5d78a135f)
| * librbd: get_parent_info should protect against invalid parentJason Dillaman2015-04-011-0/+3
| | | | | | | | | | | | | | | | get_parent_info should return -ENOENT if the image does not have an associated parent image. Signed-off-by: Jason Dillaman <dillaman@redhat.com> (cherry picked from commit 21afd0ef8e1fb81c5ace5fd403513c542e2413e3)
* | Merge pull request #4250 from athanatos/wip-11265Sage Weil2015-04-061-1/+17
|\ \ | | | | | | | | | | | | ECTransaction: write out the hinfo key on touch as well Reviewed-by: Sage Weil <sage@redhat.com>
| * | ECTransaction: write out the hinfo key on touch as wellSamuel Just2015-03-311-1/+17
| | | | | | | | | | | | | | | | | | | | | | | | This way, even empty objects have the hinfo key written. That way, touch and touch->append->truncate end up with the same state. Fixes: 11265 Signed-off-by: Samuel Just <sjust@redhat.com>
* | | Merge pull request #4251 from athanatos/wip-11284Sage Weil2015-04-061-9/+10
|\ \ \ | | | | | | | | | | | | | | | | ReplicatedPG::promote_object: do not create obc if not promoting Reviewed-by: Sage Weil <sage@redhat.com>
| * | | ReplicatedPG::promote_object: do not create obc if not promotingSamuel Just2015-03-311-9/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Otherwise, we can leave an incorrect cached obc around. Introduced: 65bb4df599541cd2e0f195b905f24f529e255c00 Fixes: 11284 Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | Merge pull request #4167 from dzafman/wip-11184Samuel Just2015-04-016-6/+176
|\ \ \ \ | |_|_|/ |/| | | | | | | | | | | Fix 11184 by filtering the log Reviewed-by: Samuel Just <sjust@redhat.com>
| * | | test: Add testing for PGLog::filter_log()David Zafman2015-03-271-0/+111
| | | | | | | | | | | | | | | | | | | | | | | | Indirectly tests pg_log_t::filter_log() Signed-off-by: David Zafman <dzafman@redhat.com>
| * | | osd: Create a filter_log for PGLogDavid Zafman2015-03-272-0/+13
| | | | | | | | | | | | | | | | | | | | | | | | This could be tested as a way to test pg_log_t::filter_log() Signed-off-by: David Zafman <dzafman@redhat.com>
| * | | ceph-objectstore-tool, osd: Filter the pg_log_t for objects no longer in pgDavid Zafman2015-03-273-1/+47
| | | | | | | | | | | | | | | | | | | | | | | | Fixes: #11184 Signed-off-by: David Zafman <dzafman@redhat.com>
| * | | ceph-objectstore-tool: Fix message and make it debug only to stderrDavid Zafman2015-03-261-1/+2
| | | | | | | | | | | | | | | | Signed-off-by: David Zafman <dzafman@redhat.com>
| * | | ceph-objectstore-tool: Remove bogus comment and eliminate a debug messageDavid Zafman2015-03-261-4/+3
| | | | | | | | | | | | | | | | Signed-off-by: David Zafman <dzafman@redhat.com>
* | | | Merge pull request #4230 from athanatos/wip-11244Samuel Just2015-03-311-0/+11
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | ReplicatedPG::cancel_pull: requeue waiters as well Reviewed-by: Sage Weil <sage@redhat.com>
| * | | | ReplicatedPG::cancel_pull: requeue waiters as wellSamuel Just2015-03-311-0/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we are in recovery_wait, we might not recover that object as part of recover_primary for some time. Worse, if we are waiting on a backfill which is blocked waiting on a copy_from on the missing object in question, it can become a dead lock. Fixes: 11244 Backport: firefly Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | | Merge pull request #4219 from liewegas/wip-scrub-mtimeSamuel Just2015-03-312-7/+5
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | osd: do not update mtime when recording digest Reviewed-by: Samuel Just <sjust@redhat.com>
| * | | | | osd: drop unused utime_t now arg to issue_repopSage Weil2015-03-302-7/+4
| | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Sage Weil <sage@redhat.com>
| * | | | | osd: do not update mtime when recording digestJianpeng Ma2015-03-301-0/+1
| | |_|/ / | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The user mtime and local_mtime are normally set in finish_ctx based on the value of ctx->mtime; clear that to avoid this update. Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> [Sage: simplified] Signed-off-by: Sage Weil <sage@redhat.com>
* | | | | Merge pull request #4229 from athanatos/wip-scrub-hitsetsSage Weil2015-03-311-0/+8
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | ReplicatedPG: don't write hitset while scrubbing, update scrub_cstat Reviewed-by: Sage Weil <sage@redhat.com>
| * | | | | ReplicatedPG: don't write hitset while scrubbing, update scrub_cstatSamuel Just2015-03-311-0/+8
| | |_|_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes: 11263 Fixes: 11262 Backport: firefly Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | | Merge pull request #4228 from athanatos/wip-11280Sage Weil2015-03-312-5/+12
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | Wip 11280 Reviewed-by: Sage Weil <sage@redhat.com>
| * | | | | ReplicatedPG: in do_op, requeue op if we requeue waiters in agent_choose_modeSamuel Just2015-03-312-4/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current op might be ordered after a waiter. Fixes: 11280 Backport: firefly Signed-off-by: Samuel Just <sjust@redhat.com>
| * | | | | ReplicatedPG: requeue waiting_for_active before waiting_for_cache_not_fullSamuel Just2015-03-311-1/+1
| | |/ / / | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The waiting_for_cache_not_full waiters must be dequeued first. Fixes: 11267 Backport: firefly Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | | Merge pull request #4207 from ceph/wip-11177Samuel Just2015-03-314-20/+29
|\ \ \ \ \ | |/ / / / |/| | | | | | | | | | | | | | common: fix logging default channel to be 'cluster' not 'default' (11177) Reviewed-by: Samuel Just <sjust@redhat.com>
| * | | | common: send cluster log messages to 'cluster' channel by defaultSage Weil2015-03-274-20/+29
| |/ / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The CLOG_CHANNEL_DEFAULT constant was being abused for two purposes: - the default channel to log messages to - the name of the config option key in the key/value pair string that is used for the default option, e.g. "default=true foo=false bar=false" Fix this by making the config option key CLOG_CONFIG_DEFAULT_KEY and replacing throughout, and changing CLOG_CHANNEL_DEFAULT to "cluster" (as it should be and has been historically). Fixes: #11177 Signed-off-by: Sage Weil <sage@redhat.com>
* | | | Merge pull request #4131 from t-miyamae/wip-mshec-documentation-h2Loic Dachary2015-03-304-8/+141
|\ \ \ \ | |/ / / |/| | | | | | | | | | | | | | | erasure code: add shec's documentation / change default layout Reviewed-by: Loic Dachary <ldachary@redhat.com>
| * | | erasure code: add shec's documentation / change default layoutTakeshi Miyamae2015-03-224-8/+141
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Takeshi Miyamae <miyamae.takeshi@jp.fujitsu.com> (cherry picked from commit cd708e216f8655eb91184e68fb6ef58949630101)
* | | | Merge pull request #4194 from athanatos/wip-11199Sage Weil2015-03-271-1/+2
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | ReplicatedPG: trim backfill intervals based on peer's last_backfill_star... Reviewed-by: Sage Weil <sage@redhat.com>
| * | | | ReplicatedPG: trim backfill intervals based on peer's last_backfill_startedSamuel Just2015-03-241-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Otherwise, we fail to trim the peer's last_backfill_started and get bug 11199. 1) osd 4 backfills up to 31bccdb2/mira01213209-286/head (henceforth: foo) 2) Interval change happens 3) osd 0 now finds itself backfilling to 4 (lb=foo) and osd.5 (lb=b6670ba2/mira01213209-160/snapdir//1, henceforth: bar) 4) recover_backfill causes both 4 and 5 to scan forward, so 4 has an interval starting at foo, 5 has an interval starting at bar. 5) Once those have come back, recover_backfill attempts to trim off the last_backfill_started, but 4's interval starts after that, so foo remains in osd 4's interval (this is the bug) 7) We serve a copyfrom on foo (sent to 4 as well). 8) We eventually get to foo in the backfilling. Normally, they would have the same version, but of course we don't update osd.4's interval from the log since it should not have received writes in that interval. Thus, we end up trying to recover foo on osd.4 anyway. 9) But, an interval change happens between removing foo from osd.4 and completing the recovery, leaving osd.4 without foo, but with lb >= foo Fixes: #11199 Backport: firefly Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | | Merge pull request #4195 from athanatos/wip-11197Sage Weil2015-03-271-6/+5
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | PG: set/clear CREATING in Primary state entry/exit Reviewed-by: Sage Weil <sage@redhat.com>
| * | | | | PG: set/clear CREATING in Primary state entry/exitSamuel Just2015-03-251-6/+5
| | |_|_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previously, we did not actually set it when we got a pg creation message from the mon. It would actually get set on the first start_peering_interval after that point. If we don't get that far, but do send a stat update to the mon, we can end up with 11197. Instead, let's just set it and clear it upon entry into and exit from the Primary state. Fixes: 11197 Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | | Merge pull request #4196 from athanatos/wip-move-codeKefu Chai2015-03-273-1638/+1623
|\ \ \ \ \ | |_|_|_|/ |/| | | | | | | | | | | | | | osd: Wip move code Reviewed-by: Kefu Chai <kchai@redhat.com>
| * | | | osd/: Move ReplicatedBackend methods into ReplicatedBackend.ccSamuel Just2015-03-262-1626/+1623
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Samuel Just <sjust@redhat.com>
| * | | | ReplicatedPG: remove unused C_OnPushCommitSamuel Just2015-03-262-12/+0
|/ / / / | | | | | | | | | | | | Signed-off-by: Samuel Just <sjust@redhat.com>
* | | | Merge pull request #4128 from dzafman/wip-11139-hammerSamuel Just2015-03-251-2/+5
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | ceph-objectstore-tool: Use exit status 11 for incompatible import attemp... Reviewed-by: Samuel Just <sjust@redhat.com>
View Lorry Controller Status