Activity
From 04/26/2018 to 05/25/2018
05/25/2018
- 10:25 PM Bug #23614 (Fix Under Review): local_reserver double-reservation of backfilled pg
- Explanation of the problem and resolution included in the pull request.
https://github.com/ceph/ceph/pull/22255 - 10:06 PM Bug #24219 (Pending Backport): osd: InProgressOp freed by on_change(); in-flight op may use-after...
- 09:25 PM Bug #24304 (Fix Under Review): MgrStatMonitor decode crash on 12.2.4->12.2.5 upgrade
- This is due to the fast-path decoding for object_stat_sum_t not being updated in the backport. Fix: https://github.co...
- 04:22 PM Bug #24304 (Closed): MgrStatMonitor decode crash on 12.2.4->12.2.5 upgrade
- This appears to be specific to a downstream build, closing.
- 12:29 PM Bug #24304 (Resolved): MgrStatMonitor decode crash on 12.2.4->12.2.5 upgrade
- ...
- 03:08 PM Backport #24297 (Resolved): mimic: RocksDB compression is not supported at least on Debian.
- 11:03 AM Backport #24297 (Resolved): mimic: RocksDB compression is not supported at least on Debian.
- https://github.com/ceph/ceph/pull/22183
- 03:06 PM Bug #24023: Segfault on OSD in 12.2.5
- ALso posted this in bug http://tracker.ceph.com/issues/23352
Hi Brad, we had one too just now, core dump and log:
... - 08:04 AM Bug #24023: Segfault on OSD in 12.2.5
- hi,
i've noticed similar/same segfault on my deployment. random segfaults on random osds appears under load or wit... - 03:05 PM Bug #23352: osd: segfaults under normal operation
- Hi Brad, we had one too just now, core dump and log:
https://drive.google.com/open?id=1t1jfjqwjhUUBzWjxamos3Hr7ghj... - 07:54 AM Bug #23352: osd: segfaults under normal operation
- Thanks Beom-Seok,
I've set up a centos environment to debug those cores along with the Xenial ones. I will update ... - 03:11 AM Bug #23352: osd: segfaults under normal operation
- Today two osd crashes.
coredump at:
https://drive.google.com/open?id=1rXtW0riZMBwP5OqrJ7QdRIOAsKFr-kYw
https://d... - 02:10 PM Bug #23965: FAIL: s3tests.functional.test_s3.test_multipart_upload_resend_part with ec cache pools
- https://github.com/ceph/ceph/pull/22126 merged to remove failures from rgw suite. moving to rados project
- 12:28 PM Backport #24259 (Resolved): mimic: crush device class: Monitor Crash when moving Bucket into Defa...
- 11:03 AM Backport #24294 (Resolved): mimic: control-c on ceph cli leads to segv
- https://github.com/ceph/ceph/pull/22225
- 11:03 AM Backport #24293 (Resolved): jewel: mon: slow op on log message
- https://github.com/ceph/ceph/pull/22431
- 11:03 AM Backport #24292 (Resolved): mimic: common: JSON output from rados bench write has typo in max_lat...
- https://github.com/ceph/ceph/pull/22406
- 11:03 AM Backport #24291 (Resolved): jewel: common: JSON output from rados bench write has typo in max_lat...
- https://github.com/ceph/ceph/pull/22407
- 11:03 AM Backport #24290 (Resolved): luminous: common: JSON output from rados bench write has typo in max_...
- https://github.com/ceph/ceph/pull/22391
- 03:47 AM Bug #24045 (Resolved): Eviction still raced with scrub due to preemption
- 03:47 AM Bug #22881 (Resolved): scrub interaction with HEAD boundaries and snapmapper repair is broken
- 03:46 AM Backport #24016 (Resolved): luminous: scrub interaction with HEAD boundaries and snapmapper repai...
- 03:43 AM Backport #23863 (Resolved): luminous: scrub interaction with HEAD boundaries and clones is broken
- 03:39 AM Backport #24153 (Resolved): luminous: Eviction still raced with scrub due to preemption
- 03:38 AM Bug #23267 (Resolved): scrub errors not cleared on replicas can cause inconsistent pg state when ...
- 03:37 AM Backport #23486 (Resolved): jewel: scrub errors not cleared on replicas can cause inconsistent pg...
- 03:30 AM Bug #23811: RADOS stat slow for some objects on same OSD
- ...
05/24/2018
- 08:41 PM Bug #23267: scrub errors not cleared on replicas can cause inconsistent pg state when replica tak...
- merged https://github.com/ceph/ceph/pull/21194
- 08:38 PM Backport #23316: jewel: pool create cmd's expected_num_objects is not correctly interpreted
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22050
merged - 08:38 PM Backport #23316: jewel: pool create cmd's expected_num_objects is not correctly interpreted
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22050
merged - 08:37 PM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- merged https://github.com/ceph/ceph/pull/22188
- 08:36 PM Bug #23769: osd/EC: slow/hung ops in multimds suite test
- jewel backport PR https://github.com/ceph/ceph/pull/22189 merged
- 06:07 PM Bug #24192: cluster [ERR] Corruption detected: object 2:f59d1934:::smithi14913526-5822:head is mi...
- ...
- 06:05 PM Bug #24199 (Pending Backport): common: JSON output from rados bench write has typo in max_latency...
- 06:03 PM Bug #24162 (Pending Backport): control-c on ceph cli leads to segv
- mimic backport https://github.com/ceph/ceph/pull/22225
- 05:59 PM Bug #23879: test_mon_osdmap_prune.sh fails
- /a/sage-2018-05-23_14:50:29-rados-wip-sage2-testing-2018-05-22-1410-distro-basic-smithi/2576533
- 03:40 PM Feature #24232: Add new command ceph mon status
- added a card to the backlog: https://trello.com/c/PTgwBpmx
- 01:27 PM Feature #24232: Add new command ceph mon status
- Sorry for the confusion, I did not check that we have ceph osd stat and ceph mon stat has the same purpose. I wanted ...
- 10:55 AM Feature #24232: Add new command ceph mon status
- copy/pasting from the PR opened to address this issue (https://github.com/ceph/ceph/pull/22202):...
- 01:44 PM Bug #24037 (Resolved): osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_nod...
- 01:42 PM Bug #24145: osdmap decode error in rados/standalone/*
- ...
- 01:39 PM Bug #17257: ceph_test_rados_api_lock fails LibRadosLockPP.LockExclusiveDurPP
- ...
- 12:08 PM Backport #24279 (In Progress): luminous: RocksDB compression is not supported at least on Debian.
- 12:08 PM Backport #24279 (Resolved): luminous: RocksDB compression is not supported at least on Debian.
- https://github.com/ceph/ceph/pull/22215
- 09:48 AM Bug #24025 (Pending Backport): RocksDB compression is not supported at least on Debian.
- 09:43 AM Bug #24025: RocksDB compression is not supported at least on Debian.
- tested...
- 08:22 AM Bug #23352: osd: segfaults under normal operation
- Hi Alex,
I notice there are several more coredumps attached to the related bug reports. Are they all separate cras... - 03:07 AM Bug #24264: ssd-primary crush rule not working as intended
- Sorry, here's my updated rule instead of the one in the document.
rule ssd-primary {
id 2
type r... - 03:05 AM Bug #24264 (Closed): ssd-primary crush rule not working as intended
- I've set up the rule according to the doc, but some of the PGs are still being assigned to the same host though my fa...
05/23/2018
- 09:36 PM Bug #23787 (Rejected): luminous: "osd-scrub-repair.sh'" failures in rados
- This is an incompatibility between the OSD version 64ffa817000d59d91379f7335439845930f58530 (luminous) and the versio...
- 06:40 PM Bug #22920 (Resolved): filestore journal replay does not guard omap operations
- 06:40 PM Backport #22934 (Resolved): luminous: filestore journal replay does not guard omap operations
- 06:35 PM Bug #23878 (Resolved): assert on pg upmap
- 06:34 PM Backport #23925 (Resolved): luminous: assert on pg upmap
- 06:32 PM Backport #24259 (Resolved): mimic: crush device class: Monitor Crash when moving Bucket into Defa...
- https://github.com/ceph/ceph/pull/22169
- 06:32 PM Backport #24258 (Resolved): luminous: crush device class: Monitor Crash when moving Bucket into D...
- https://github.com/ceph/ceph/pull/22381
- 06:32 PM Backport #24244 (New): jewel: osd/EC: slow/hung ops in multimds suite test
- 05:09 PM Backport #24244 (Resolved): jewel: osd/EC: slow/hung ops in multimds suite test
- https://github.com/ceph/ceph/pull/22189
partial backport for mdsmonitor - 06:31 PM Backport #24256 (Resolved): mimic: osd: Assertion `!node_algorithms::inited(this->priv_value_tra...
- https://github.com/ceph/ceph/pull/22160
- 06:31 PM Backport #24246 (Resolved): mimic: Manager daemon y is unresponsive during teuthology cluster tea...
- https://github.com/ceph/ceph/pull/22333
- 06:31 PM Backport #24245 (Resolved): luminous: Manager daemon y is unresponsive during teuthology cluster ...
- https://github.com/ceph/ceph/pull/22331
- 04:27 PM Bug #23352: osd: segfaults under normal operation
- Sage, I had tried to do this, but we don't know when these crashes would happen, just that they will occur. Random t...
- 04:10 PM Bug #23352 (Need More Info): osd: segfaults under normal operation
- Alex, how reproducible is this for you? Could you reproduce with debug timer = 20?
- 04:21 PM Backport #24058 (In Progress): jewel: Deleting a pool with active notify linger ops can result in...
- https://github.com/ceph/ceph/pull/22188
- 04:15 PM Bug #24243 (Resolved): osd: pg hard limit too easy to hit
- The default ratio of 2x mon_max_pg_per_osd is easy to hit for clusters that have differently weighted disks (e.g. 1 a...
- 03:27 PM Bug #24025: RocksDB compression is not supported at least on Debian.
- mimic: https://github.com/ceph/ceph/pull/22183
- 03:25 PM Bug #24025 (Fix Under Review): RocksDB compression is not supported at least on Debian.
- https://github.com/ceph/ceph/pull/22181
- 02:53 PM Bug #24025: RocksDB compression is not supported at least on Debian.
- because we fail to pass -DWITH_SNAPPY etc to cmake while building rocksdb. this bug also impacts rpm package. i can h...
- 01:51 PM Bug #24229 (Triaged): Libradosstriper successfully removes nonexistent objects instead of returni...
- 11:57 AM Bug #24242 (New): tcmalloc::ThreadCache::ReleaseToCentralCache on rhel (w/ centos packages)
- ...
- 11:43 AM Bug #24222 (Pending Backport): Manager daemon y is unresponsive during teuthology cluster teardown
- 08:41 AM Bug #23145: OSD crashes during recovery of EC pg
- osd in last peering stage will call pg_log.roll_forward(at last of PG::activate), is there possible the entry rollbf...
- 06:52 AM Bug #23386 (Pending Backport): crush device class: Monitor Crash when moving Bucket into Default ...
- https://github.com/ceph/ceph/pull/22169
- 01:21 AM Bug #24037 (Pending Backport): osd: Assertion `!node_algorithms::inited(this->priv_value_traits(...
05/22/2018
- 09:55 PM Bug #24222 (Fix Under Review): Manager daemon y is unresponsive during teuthology cluster teardown
- https://github.com/ceph/ceph/pull/22158
- 02:20 AM Bug #24222 (Resolved): Manager daemon y is unresponsive during teuthology cluster teardown
- ...
- 08:47 PM Feature #24232 (Fix Under Review): Add new command ceph mon status
- Add new command ceph mon status
For more information please check - https://tracker.ceph.com/issues/24217
Changed... - 08:32 PM Bug #23965: FAIL: s3tests.functional.test_s3.test_multipart_upload_resend_part with ec cache pools
- Josh Durgin wrote:
> Casey, could you or someone else familiar with rgw look through the logs for this and identify ... - 03:19 PM Bug #23965: FAIL: s3tests.functional.test_s3.test_multipart_upload_resend_part with ec cache pools
- Casey, could you or someone else familiar with rgw look through the logs for this and identify the relevant OSD reque...
- 07:17 PM Feature #24231 (New): librbd/libcephfs/librgw should ignore rados_mon/osd_op_timeouts options (re...
- librbd/libcephfs/librgw should ignore rados_mon/osd_op_timeouts options
https://bugzilla.redhat.com/show_bug.cgi?id=... - 04:09 PM Bug #24025 (In Progress): RocksDB compression is not supported at least on Debian.
- ...
- 03:48 PM Bug #24037 (Fix Under Review): osd: Assertion `!node_algorithms::inited(this->priv_value_traits(...
- https://github.com/ceph/ceph/pull/22156
- 02:35 PM Bug #24229 (Triaged): Libradosstriper successfully removes nonexistent objects instead of returni...
- libradosstriper remove() call on nonexistent objects returns zero instead of ENOENT.
Tested on luminous 12.2.5-1xe... - 11:35 AM Feature #24099: osd: Improve workflow when creating OSD on raw block device if there was bluestor...
> Point out that it found existing data on the OSD, and possibly suggest using `ceph-volume lvm zap` if that's what...- 10:51 AM Bug #24199 (Fix Under Review): common: JSON output from rados bench write has typo in max_latency...
- 07:00 AM Bug #23371: OSDs flaps when cluster network is made down
- we have not observed this behavior in kraken.
when ever the Cluster interface is made down, few OSDs which goes do... - 03:55 AM Bug #23352: osd: segfaults under normal operation
- OSD log attached
- 03:15 AM Bug #23352: osd: segfaults under normal operation
- It's an internal comment for others looking at this - though if you (Alex) have an osd log to go with the 'MMgrReport...
- 02:59 AM Bug #23352: osd: segfaults under normal operation
- Josh, is this something I can extract from the OSD node for you, or is this an internal comment?
- 01:10 AM Bug #23352: osd: segfaults under normal operation
- I put the core file from comment #14 and binaries from 12.2.5 in senta02:/slow/jdurgin/ceph/bugs/tracker_23352/2018-0...
- 03:49 AM Backport #24059 (In Progress): luminous: Deleting a pool with active notify linger ops can result...
- https://github.com/ceph/ceph/pull/22143
05/21/2018
- 10:04 PM Bug #24219: osd: InProgressOp freed by on_change(); in-flight op may use-after-free in op_commit()
- /a/teuthology-2018-05-21_20:00:50-powercycle-mimic-distro-basic-smithi/2563192
powercycle/osd/{clusters/3osd-1per-... - 09:40 PM Bug #24219 (Fix Under Review): osd: InProgressOp freed by on_change(); in-flight op may use-after...
- https://github.com/ceph/ceph/pull/22133
- 09:28 PM Bug #24219 (Resolved): osd: InProgressOp freed by on_change(); in-flight op may use-after-free in...
- ...
- 07:29 PM Bug #22330 (Need More Info): ec: src/common/interval_map.h: 161: FAILED assert(len > 0)
- need to capture some logs...
- 07:15 PM Bug #23031: FAILED assert(!parent->get_log().get_missing().is_missing(soid))
- I hit this issue a couple of times while trying to reproduce #23614...
- 06:36 PM Backport #24200 (Resolved): mimic: PrimaryLogPG::try_flush_mark_clean mixplaced ctx release
- 08:48 AM Backport #24200 (Resolved): mimic: PrimaryLogPG::try_flush_mark_clean mixplaced ctx release
- 06:24 PM Bug #23386 (Fix Under Review): crush device class: Monitor Crash when moving Bucket into Default ...
- https://github.com/ceph/ceph/pull/22127
- 05:14 PM Bug #23386: crush device class: Monitor Crash when moving Bucket into Default root
- reproduces on luminous with...
- 01:52 PM Bug #23386: crush device class: Monitor Crash when moving Bucket into Default root
- I suspect the recent pr https://github.com/ceph/ceph/pull/22091 fixed this, but figuring out how to reproduce to be s...
- 05:59 PM Bug #23965 (Fix Under Review): FAIL: s3tests.functional.test_s3.test_multipart_upload_resend_part...
- https://github.com/ceph/ceph/pull/22126 removes ec-cache pools from the rgw suite
- 04:55 PM Bug #22656: scrub mismatch on bytes (cache pools)
- http://qa-proxy.ceph.com/teuthology/dzafman-2018-05-18_11:33:31-rados-wip-zafman-testing-mimic-distro-basic-smithi/25...
- 04:21 PM Backport #22934: luminous: filestore journal replay does not guard omap operations
- Victor Denisov wrote:
> https://github.com/ceph/ceph/pull/21547
merged - 04:13 PM Backport #23925: luminous: assert on pg upmap
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21818
merged - 04:01 PM Backport #24213 (In Progress): mimic: Module 'balancer' has failed: could not find bucket -14
- 03:59 PM Backport #24213 (Resolved): mimic: Module 'balancer' has failed: could not find bucket -14
- https://github.com/ceph/ceph/pull/22120
- 03:59 PM Backport #24216 (Resolved): luminous: "process (unknown)" in ceph logs
- https://github.com/ceph/ceph/pull/22290
- 03:59 PM Backport #24215 (Resolved): mimic: "process (unknown)" in ceph logs
- https://github.com/ceph/ceph/pull/22311
- 03:59 PM Backport #24214 (Resolved): luminous: Module 'balancer' has failed: could not find bucket -14
- https://github.com/ceph/ceph/pull/22308
- 03:03 PM Bug #23585 (Triaged): osd: safe_timer segfault
- 02:17 PM Bug #21142: OSD crashes when loading pgs with "FAILED assert(interval.last > last)"
- We are experiencing this too. Majority of the OSDs went down. We tried removing the intervals. It works on some OSDs ...
- 01:44 PM Bug #24167: Module 'balancer' has failed: could not find bucket -14
- mimic backport: https://github.com/ceph/ceph/pull/22120
- 01:42 PM Bug #24167 (Pending Backport): Module 'balancer' has failed: could not find bucket -14
- 01:00 PM Bug #23431: OSD Segmentation fault in thread_name:safe_timer
- Hi.
We have the same issue: ... - 12:07 PM Bug #24123 (Pending Backport): "process (unknown)" in ceph logs
- 09:50 AM Backport #24048 (In Progress): luminous: pg-upmap cannot balance in some case
- https://github.com/ceph/ceph/pull/22115
- 09:43 AM Bug #24199: common: JSON output from rados bench write has typo in max_latency key
- PR: https://github.com/ceph/ceph/pull/22112
- 06:23 AM Bug #24199 (Resolved): common: JSON output from rados bench write has typo in max_latency key
- The JSON output from `rados bench write --format json/json-pretty` has a typo in the `max_latency` key.
It contains ... - 08:48 AM Backport #24204 (Resolved): mimic: LibRadosMiscPool.PoolCreationRace segv
- https://github.com/ceph/ceph/pull/22291
- 08:43 AM Bug #24174: PrimaryLogPG::try_flush_mark_clean mixplaced ctx release
- mimic: https://github.com/ceph/ceph/pull/22113
- 08:41 AM Bug #24174 (Pending Backport): PrimaryLogPG::try_flush_mark_clean mixplaced ctx release
- 07:11 AM Bug #24076 (Duplicate): rados/test.sh fails in "bin/ceph_test_rados_api_misc --gtest_filter=*Pool...
- 06:24 AM Backport #24198 (In Progress): luminous: mon: slow op on log message
- 06:23 AM Backport #24198 (Resolved): luminous: mon: slow op on log message
- https://github.com/ceph/ceph/pull/22109
- 06:20 AM Backport #24195 (Resolved): mimic: mon: slow op on log message
- 02:51 AM Bug #20924: osd: leaked Session on osd.7
- osd.4
/a/sage-2018-05-20_18:11:15-rados-wip-sage3-testing-2018-05-20-1031-distro-basic-smithi/2558319
rados/ver... - 02:24 AM Bug #24150 (Pending Backport): LibRadosMiscPool.PoolCreationRace segv
05/20/2018
- 06:58 PM Bug #18239 (Duplicate): nan in ceph osd df again
- 10:32 AM Bug #24023: Segfault on OSD in 12.2.5
- Alexander M wrote:
> Alex Gorbachev wrote:
> > This continues to happen every day, usually during scrub
>
> I've... - 10:30 AM Bug #24023: Segfault on OSD in 12.2.5
- Alex Gorbachev wrote:
> This continues to happen every day, usually during scrub
I've faced with the same issue
... - 09:45 AM Backport #24195 (In Progress): mimic: mon: slow op on log message
- https://github.com/ceph/ceph/pull/22104
- 09:42 AM Backport #24195 (Resolved): mimic: mon: slow op on log message
- 09:40 AM Bug #24180 (Pending Backport): mon: slow op on log message
05/19/2018
- 07:04 PM Bug #24192 (Duplicate): cluster [ERR] Corruption detected: object 2:f59d1934:::smithi14913526-582...
davidz@teuthology:/a/dzafman-2018-05-18_11:36:58-rados-wip-zafman-testing-distro-basic-smithi/2549009...
05/18/2018
- 08:45 PM Bug #24180: mon: slow op on log message
- https://github.com/ceph/ceph/pull/22098
- 08:44 PM Bug #24180 (Fix Under Review): mon: slow op on log message
- https://github.com/ceph/ceph/pull/22098
- 08:41 PM Bug #24180 (Resolved): mon: slow op on log message
- ...
- 08:37 PM Bug #20924: osd: leaked Session on osd.7
- osd.7
/a/sage-2018-05-18_16:20:24-rados-wip-sage-testing-2018-05-18-0817-distro-basic-smithi/2548324
rados/veri... - 02:26 PM Bug #20924: osd: leaked Session on osd.7
- osd.7
/a/sage-2018-05-18_13:08:19-rados-wip-sage2-testing-2018-05-17-0701-distro-basic-smithi/2546923
rados/ver... - 08:16 PM Backport #24149 (Resolved): mimic: Eviction still raced with scrub due to preemption
- 07:24 PM Bug #24162 (Fix Under Review): control-c on ceph cli leads to segv
- hacky workaround: https://github.com/ceph/ceph/pull/22093
- 07:18 PM Bug #24162: control-c on ceph cli leads to segv
- ...
- 07:09 PM Bug #24037: osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_node_ptr(value...
- related?...
- 01:26 PM Bug #24037 (In Progress): osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_...
- 01:15 PM Bug #24037: osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_node_ptr(value...
- Scenario I can see after static analysis:
1. An instance of `TrackedOp` in `STATE_LIVE` is being dereferenced - th... - 06:59 PM Bug #23352: osd: segfaults under normal operation
- The latest ones look like this, below.
Crash dump at https://drive.google.com/open?id=12v95-TCHlkrBZ16ni5UkhYkXRt... - 06:41 PM Bug #23352: osd: segfaults under normal operation
- For some reason we are also seeing more of these happening, simultaneous failures and recoveries are occurring during...
- 02:36 AM Bug #23352: osd: segfaults under normal operation
- I run into this issue with 12.2.5, it affects cluster stability heavily.
- 06:12 PM Bug #24167 (Fix Under Review): Module 'balancer' has failed: could not find bucket -14
- https://github.com/ceph/ceph/pull/22091
- 05:02 PM Feature #24176 (Resolved): osd: add command to drop OSD cache
- Idea here is to basically make it possible for performance testing on the same data set in RADOS without restarting t...
- 04:24 PM Feature #22420 (Resolved): Add support for obtaining a list of available compression options
- 04:04 PM Bug #23487 (Resolved): There is no 'ceph osd pool get erasure allow_ec_overwrites' command
- 04:04 PM Backport #23668 (Resolved): luminous: There is no 'ceph osd pool get erasure allow_ec_overwrites'...
- 04:03 PM Bug #23664 (Resolved): cache-try-flush hits wrlock, busy loops
- 04:03 PM Backport #23914 (Resolved): luminous: cache-try-flush hits wrlock, busy loops
- 04:02 PM Bug #23860 (Resolved): luminous->master: luminous crashes with AllReplicasRecovered in Started/Pr...
- 04:02 PM Backport #23988 (Resolved): luminous: luminous->master: luminous crashes with AllReplicasRecovere...
- 04:02 PM Bug #23980 (Resolved): UninitCondition in PG::RecoveryState::Incomplete::react(PG::AdvMap const&)
- 04:01 PM Backport #24015 (Resolved): luminous: UninitCondition in PG::RecoveryState::Incomplete::react(PG:...
- 02:30 PM Backport #24135 (Resolved): mimic: Add support for obtaining a list of available compression options
- 02:25 PM Bug #24174: PrimaryLogPG::try_flush_mark_clean mixplaced ctx release
- https://github.com/ceph/ceph/pull/22084
- 02:24 PM Bug #24174 (Resolved): PrimaryLogPG::try_flush_mark_clean mixplaced ctx release
- ...
05/17/2018
- 10:22 PM Bug #24167: Module 'balancer' has failed: could not find bucket -14
- It looks like we also don't create weight-sets for new buckets. And if you create buckets and move things into them ...
- 09:58 PM Bug #24167 (Resolved): Module 'balancer' has failed: could not find bucket -14
- crushmap may contain choose_args for deleted buckets...
- 05:39 PM Bug #23965: FAIL: s3tests.functional.test_s3.test_multipart_upload_resend_part with ec cache pools
- 03:52 PM Bug #23763 (Resolved): upgrade: bad pg num and stale health status in mixed lumnious/mimic cluster
- 03:52 PM Backport #23808 (Resolved): luminous: upgrade: bad pg num and stale health status in mixed lumnio...
- 03:42 PM Backport #23808: luminous: upgrade: bad pg num and stale health status in mixed lumnious/mimic cl...
- Kefu Chai wrote:
> https://github.com/ceph/ceph/pull/21556
merged - 03:45 PM Bug #24162 (Resolved): control-c on ceph cli leads to segv
- ...
- 03:43 PM Backport #23668: luminous: There is no 'ceph osd pool get erasure allow_ec_overwrites' command
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21378
merged - 03:42 PM Backport #23914: luminous: cache-try-flush hits wrlock, busy loops
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21764
merged - 03:41 PM Backport #23988: luminous: luminous->master: luminous crashes with AllReplicasRecovered in Starte...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21964
merged - 03:40 PM Backport #23988: luminous: luminous->master: luminous crashes with AllReplicasRecovered in Starte...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21964
merged - 03:38 PM Backport #24015: luminous: UninitCondition in PG::RecoveryState::Incomplete::react(PG::AdvMap con...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21993
merged - 01:55 PM Backport #23786 (Resolved): luminous: "utilities/env_librados.cc:175:33: error: unused parameter ...
- 01:55 PM Bug #22330: ec: src/common/interval_map.h: 161: FAILED assert(len > 0)
- 01:50 PM Bug #23145: OSD crashes during recovery of EC pg
- Peter Woodman wrote:
> Each OSD is on its own host- these are small arm64 machines. Unfortunately i've already tried... - 11:49 AM Bug #24159 (Duplicate): Monitor down when large store data needs to compact triggered by ceph tel...
- 10:38 AM Bug #24159 (Duplicate): Monitor down when large store data needs to compact triggered by ceph tel...
- I have met a monitor problem with capacity too large in our production environment.
This logical volume for monito... - 10:38 AM Bug #24160 (Resolved): Monitor down when large store data needs to compact triggered by ceph tell...
- I have met a monitor problem with capacity too large in our production environment.
This logical volume for monito... - 09:04 AM Bug #23598 (Duplicate): hammer->jewel: ceph_test_rados crashes during radosbench task in jewel ra...
- #23290 does not contain any of the PR mentioned above. so it's not a regression.
- 08:33 AM Backport #24153 (In Progress): luminous: Eviction still raced with scrub due to preemption
- 08:33 AM Backport #24149 (In Progress): mimic: Eviction still raced with scrub due to preemption
- 08:33 AM Backport #24149 (New): mimic: Eviction still raced with scrub due to preemption
- 08:27 AM Bug #23962 (Resolved): ceph_daemon.py format_dimless units list index out of range
- 08:26 AM Bug #24000 (Resolved): mon: snap delete on deleted pool returns 0 without proper payload
- 08:25 AM Bug #23899 (Resolved): run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentation fault
- 07:37 AM Backport #23316 (In Progress): jewel: pool create cmd's expected_num_objects is not correctly int...
05/16/2018
- 10:29 PM Backport #24153: luminous: Eviction still raced with scrub due to preemption
- I'm pulling in these pull requests also on top of existing pull request (not yet merged) https://github.com/ceph/ceph...
- 10:26 PM Backport #24153 (Resolved): luminous: Eviction still raced with scrub due to preemption
- https://github.com/ceph/ceph/pull/22044
- 08:52 PM Bug #24150 (Fix Under Review): LibRadosMiscPool.PoolCreationRace segv
- https://github.com/ceph/ceph/pull/22042
- 08:51 PM Bug #24150 (Resolved): LibRadosMiscPool.PoolCreationRace segv
- ...
- 08:36 PM Backport #24149 (Resolved): mimic: Eviction still raced with scrub due to preemption
- https://github.com/ceph/ceph/pull/22041
- 08:28 PM Bug #24045 (Pending Backport): Eviction still raced with scrub due to preemption
- 07:31 PM Bug #24148: Segmentation fault out of ObcLockManager::get_lock_type()
- The pg 3.3 involved here was never scrubbed, so unrelated to my changes.
- 07:16 PM Bug #24148 (Duplicate): Segmentation fault out of ObcLockManager::get_lock_type()
teuthology:/a/dzafman-2018-05-16_09:57:45-rados:thrash-wip-zafman-testing-distro-basic-smithi/2539708
remote/smi...- 06:53 PM Bug #22354: v12.2.2 unable to create bluestore osd using ceph-disk
- kobi ginon wrote:
> Note: i still believe there is a relation to rocksdb somehow and the clearing of disk's forces t... - 03:52 PM Backport #24027 (Resolved): mimic: ceph_daemon.py format_dimless units list index out of range
- 03:51 PM Backport #24103 (Resolved): mimic: mon: snap delete on deleted pool returns 0 without proper payload
- 03:50 PM Backport #24104 (Resolved): mimic: run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentatio...
- 03:49 PM Bug #24145 (Duplicate): osdmap decode error in rados/standalone/*
- ...
- 12:03 PM Feature #24099: osd: Improve workflow when creating OSD on raw block device if there was bluestor...
- This is not a ceph-volume issue, the description of this issue doesn't point to a ceph-volume operation, but rather, ...
05/15/2018
- 10:58 PM Bug #23145: OSD crashes during recovery of EC pg
- Each OSD is on its own host- these are small arm64 machines. Unfortunately i've already tried stopping osd6, it just ...
- 10:37 PM Bug #23145: OSD crashes during recovery of EC pg
- Hmm, it's possible that if you stop osd.6 that this PG will be able to peer with the remaining OSDs... want to give i...
- 10:34 PM Bug #23145: OSD crashes during recovery of EC pg
- Peter Woodman wrote:
> For the record, I discovered recently that a number of OSDs were operating with write caching... - 10:33 PM Bug #23145: OSD crashes during recovery of EC pg
- Hmm, I think the problem comes before that. This is problematic:...
- 10:20 PM Bug #23145: OSD crashes during recovery of EC pg
- For the record, I discovered recently that a number of OSDs were operating with write caching enabled, and because th...
- 10:15 PM Bug #23145: OSD crashes during recovery of EC pg
- This code appears to be the culprit, at least in this case:...
- 02:48 PM Bug #24023: Segfault on OSD in 12.2.5
- This continues to happen every day, usually during scrub
- 01:15 PM Backport #24135 (In Progress): mimic: Add support for obtaining a list of available compression o...
- 01:13 PM Backport #24135 (Resolved): mimic: Add support for obtaining a list of available compression options
- https://github.com/ceph/ceph/pull/22004
- 12:29 PM Feature #22448 (Resolved): Visibility for snap trim queue length
- Already merged to master, luminous and jewel.
- 12:28 PM Backport #22449 (Resolved): jewel: Visibility for snap trim queue length
- 10:44 AM Bug #23767: "ceph ping mon" doesn't work
- Confirmed on my cluster (13.0.2-1969-g49365c7).
- 10:37 AM Fix #24126: ceph osd purge command error message improvement
- How are you seeing that ugly logfile style output? When I try it, it looks like this:...
- 10:32 AM Feature #24127: "osd purge" should print more helpful message when daemon is up
- This is completely reasonable as a general point, but not really actionable as a tracker ticket -- we aren't ever goi...
- 10:31 AM Bug #23937: FAILED assert(info.history.same_interval_since != 0)
- I can't post using ceph-post-file, so I uploaded file here https://eocloud.eu:8080/swift/v1/rwadolowski/ceph-osd.33.l...
- 06:31 AM Bug #24007: rados.connect get a segmentation fault
- John Spray wrote:
> Is there a backtrace or any other message from the crash?
there are many different backtraces. - 03:15 AM Backport #24015 (In Progress): luminous: UninitCondition in PG::RecoveryState::Incomplete::react(...
- https://github.com/ceph/ceph/pull/21993
05/14/2018
- 09:59 PM Bug #23145: OSD crashes during recovery of EC pg
- happy to see action on this ticket. for the record, i still have the data for this pg.
- 09:38 PM Bug #22837 (Resolved): discover_all_missing() not always called during activating
- 09:36 PM Bug #23576 (Can't reproduce): osd: active+clean+inconsistent pg will not scrub or repair
- 06:12 PM Bug #23576: osd: active+clean+inconsistent pg will not scrub or repair
- Sorry for the lack of updates, there were no messages of any sort in the logs when attempting to deep scrub or repair...
- 04:26 PM Bug #23576: osd: active+clean+inconsistent pg will not scrub or repair
- No, I never had that message in any of our logs. After a month the PGs ran their own deep-scrub again and I was able...
- 09:29 PM Bug #22354: v12.2.2 unable to create bluestore osd using ceph-disk
- Hi again
indeed your method also works
in my simple test i just cleared 2 GB out of the disk
before zap setting ... - 08:45 PM Bug #22354: v12.2.2 unable to create bluestore osd using ceph-disk
- Hi Jon , thanks a lot for the reply
i'm fighting with issue for a day now, and i have a very strange observation
... - 08:01 PM Bug #22354: v12.2.2 unable to create bluestore osd using ceph-disk
- I think I ran into the same thing last week reusing an OSD disk. I did a dd of /dev/zero to the disk for ~10-15 minu...
- 02:38 AM Bug #22354: v12.2.2 unable to create bluestore osd using ceph-disk
- Hi all
i m using the following version ceph-12.2.2-0.el7.x86_64.
it seem's that even with dd of 100MB or 110MB
i s... - 07:22 PM Feature #24127 (New): "osd purge" should print more helpful message when daemon is up
- Compilers like GCC and clang are sometimes able to make suggestions when a user makes certain
common mistakes for wh... - 07:19 PM Fix #24126 (New): ceph osd purge command error message improvement
- In response to the command "ceph osd purge 1 --yes-i-really-mean-it", we
get:
2018-05-10 15:18:03.444 7f29c0ae2700... - 06:54 PM Bug #24123 (Fix Under Review): "process (unknown)" in ceph logs
- PR: https://github.com/ceph/ceph/pull/21985
- 06:47 PM Bug #24123 (Resolved): "process (unknown)" in ceph logs
- get_process_name from libcommon was broken when cleaning up headers (95fc248). As a result we don't log process name ...
- 02:44 PM Bug #24007: rados.connect get a segmentation fault
- Is there a backtrace or any other message from the crash?
- 10:42 AM Bug #24077 (Resolved): test_pool_create_fail (tasks.mgr.dashboard.test_pool.PoolTest) fails
- 08:05 AM Backport #23912 (In Progress): luminous: mon: High MON cpu usage when cluster is changing
- 06:52 AM Backport #23912: luminous: mon: High MON cpu usage when cluster is changing
- -http://tracker.ceph.com/issues/23912-
https://github.com/ceph/ceph/pull/21968 - 04:20 AM Backport #23988 (In Progress): luminous: luminous->master: luminous crashes with AllReplicasRecov...
- https://github.com/ceph/ceph/pull/21964
05/12/2018
- 05:25 PM Bug #24022: "ceph tell osd.x bench" writes resulting JSON to stderr instead of stdout.
- https://github.com/ceph/ceph/pull/21960
- 11:36 AM Bug #24022: "ceph tell osd.x bench" writes resulting JSON to stderr instead of stdout.
- https://github.com/ceph/ceph/pull/21957
- 11:16 AM Bug #24022: "ceph tell osd.x bench" writes resulting JSON to stderr instead of stdout.
- Марк i am leaving this ticket open. will close it once
> But, I found the same bug about stdou/stderr for "debug ... - 11:13 AM Bug #24022 (Resolved): "ceph tell osd.x bench" writes resulting JSON to stderr instead of stdout.
- 12:20 PM Backport #24104 (In Progress): mimic: run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmenta...
- 12:20 PM Backport #24104 (Resolved): mimic: run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentatio...
- https://github.com/ceph/ceph/pull/21959
- 12:16 PM Backport #24103 (In Progress): mimic: mon: snap delete on deleted pool returns 0 without proper p...
- 12:14 PM Backport #24103 (Resolved): mimic: mon: snap delete on deleted pool returns 0 without proper payload
- https://github.com/ceph/ceph/pull/21958
- 11:24 AM Bug #23899 (Pending Backport): run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentation fault
- https://github.com/ceph/ceph/pull/21950
- 11:11 AM Bug #23899 (Resolved): run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentation fault
- 11:22 AM Bug #24000 (Pending Backport): mon: snap delete on deleted pool returns 0 without proper payload
05/11/2018
- 08:06 PM Bug #23195 (Resolved): Read operations segfaulting multiple OSDs
- 08:06 PM Backport #23850 (Resolved): luminous: Read operations segfaulting multiple OSDs
- 04:28 PM Backport #23850: luminous: Read operations segfaulting multiple OSDs
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21911
merged - 03:44 PM Feature #24099: osd: Improve workflow when creating OSD on raw block device if there was bluestor...
- Another related issue I found is that zapping requires root, even when the user executing it already has write permis...
- 03:32 PM Feature #24099 (New): osd: Improve workflow when creating OSD on raw block device if there was bl...
- On Ceph Luminous, when creating a new bluestore OSD on a block device...
- 02:16 PM Bug #24077 (Fix Under Review): test_pool_create_fail (tasks.mgr.dashboard.test_pool.PoolTest) fails
- Josh, it's not a mon crash. mon was just not happy with this command, please see @handle_bad_get()@ in @cmd_getval(Ce...
- 06:54 AM Bug #24094: some objects are lost after one of osd in cache-tier is broken
- New findings:
For the object: s3://B6-2017-12-22-10-25-42/timecost.txt, which index is .dir.0089274c-7a8b-4e66-83d... - 04:33 AM Bug #24094 (New): some objects are lost after one of osd in cache-tier is broken
- I have a small cluster to setup, some configs:
* 9 machines
* 9*2 4T SSD as cache tier(size == 1)
* 9*14 8T HDD as... - 04:39 AM Bug #23899 (Fix Under Review): run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentation fault
- https://github.com/ceph/ceph/pull/21691
- 03:20 AM Backport #23986 (In Progress): luminous: recursive lock of objecter session::lock on cancel
- https://github.com/ceph/ceph/pull/21939
05/10/2018
- 11:40 PM Bug #24077: test_pool_create_fail (tasks.mgr.dashboard.test_pool.PoolTest) fails
- Looks to have caused a monitor crash:...
- 09:13 AM Bug #24077 (Resolved): test_pool_create_fail (tasks.mgr.dashboard.test_pool.PoolTest) fails
- ...
- 08:25 PM Bug #24037: osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_node_ptr(value...
- Here's another that looks related:...
- 04:33 PM Bug #24041 (Resolved): ceph-disk log is written to /var/run/ceph
- 03:44 PM Bug #24041: ceph-disk log is written to /var/run/ceph
- https://github.com/ceph/ceph/pull/21870
merged - 04:33 PM Backport #24042 (Resolved): luminous: ceph-disk log is written to /var/run/ceph
- 04:29 PM Backport #24083 (Resolved): luminous: rados: not all exceptions accept keyargs
- https://github.com/ceph/ceph/pull/22979
- 03:11 PM Bug #20924: osd: leaked Session on osd.7
- osd.3
/a//yuriw-2018-05-09_22:08:37-rados-mimic-distro-basic-smithi/2511364/remote/smithi118/log/valgrind/osd.3.lo... - 02:08 PM Bug #23492: Abort in OSDMap::decode() during qa/standalone/erasure-code/test-erasure-eio.sh
- i saw a similar abort, except that it came from OSD::init() during qa/standalone/scrub/osd-scrub-repair.sh:...
- 12:43 PM Bug #24023: Segfault on OSD in 12.2.5
- This is happening on a regular basis, 1-2 per day
- 12:29 PM Bug #24078 (New): spdk crash during librados shutdown
- I use spdk_tgt from spdk project:
1. rbd create foo --size 1000
2. python /home/sample/build_pool/agent/repo/test/j... - 10:56 AM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- forward-port for master: https://github.com/ceph/ceph/pull/21831
- 09:34 AM Bug #24033 (Pending Backport): rados: not all exceptions accept keyargs
- 08:48 AM Bug #24076 (Fix Under Review): rados/test.sh fails in "bin/ceph_test_rados_api_misc --gtest_filte...
- https://github.com/ceph/ceph/pull/21927
- 08:45 AM Bug #24076: rados/test.sh fails in "bin/ceph_test_rados_api_misc --gtest_filter=*PoolCreationRace*"
- the test of LibRadosMiscPool.PoolCreationRace creates a ctx for poolrac2.%d before creating it, and sends a bunch of ...
- 08:36 AM Bug #24076 (Duplicate): rados/test.sh fails in "bin/ceph_test_rados_api_misc --gtest_filter=*Pool...
- it's a regression introduced by https://github.com/ceph/ceph/pull/21609
http://pulpito.ceph.com/kchai-2018-05-09_1... - 01:28 AM Bug #23119: MD5-checksum of the snapshot for rbd image in Ceph(as OpenStack-Glance backend Storag...
- Jason Dillaman wrote:
> Moving to RADOS since it sounds like it's an issue of corruption on your cache tier.
I re...
05/09/2018
- 09:24 PM Bug #23937: FAILED assert(info.history.same_interval_since != 0)
- The pg is waiting for state from osd.33 - can you use ceph-post-file to upload the full log from the crash?
You mi... - 09:11 PM Bug #24000: mon: snap delete on deleted pool returns 0 without proper payload
- 09:11 PM Bug #24006: ceph-osd --mkfs has nondeterministic output
- Sounds like we need to flush the log before exiting in ceph-osd.
- 09:08 PM Bug #23879: test_mon_osdmap_prune.sh fails
- Sounds like we need to block for trimming sometimes when there's a constant propose workload.
- 09:02 PM Bug #24037: osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_node_ptr(value...
- Sounds like a use-after-free of some sort, unrelated to other crashes we've seen.
- 08:48 PM Bug #24057: cbt fails to copy results to the archive dir
- This seems to be an issue with cbt not being able to copy output files to its archive dir, and hence we don't find th...
- 12:00 PM Bug #24057: cbt fails to copy results to the archive dir
- Neha, mind taking a look? i've run into this failure couple times.
- 11:59 AM Bug #24057 (Rejected): cbt fails to copy results to the archive dir
- /a/kchai-2018-05-08_12:15:21-rados-wip-kefu-testing2-2018-05-08-1834-distro-basic-mira/2501280...
- 06:44 PM Backport #24068 (Resolved): luminous: osd sends op_reply out of order
- https://github.com/ceph/ceph/pull/23137
- 06:38 PM Bug #23827 (Pending Backport): osd sends op_reply out of order
- 04:45 PM Bug #23827 (Fix Under Review): osd sends op_reply out of order
- The cause for this issue is that we are not tracking enough dup ops for this test, which does multiple writes to the ...
- 04:01 PM Backport #24059 (Resolved): luminous: Deleting a pool with active notify linger ops can result in...
- https://github.com/ceph/ceph/pull/22143
- 04:01 PM Backport #24058 (Resolved): jewel: Deleting a pool with active notify linger ops can result in se...
- https://github.com/ceph/ceph/pull/22188
- 02:21 PM Bug #24022 (Fix Under Review): "ceph tell osd.x bench" writes resulting JSON to stderr instead of...
- I tend to agree: https://github.com/ceph/ceph/pull/21905
- 02:09 PM Backport #24026 (Resolved): mimic: pg-upmap cannot balance in some case
- 12:11 PM Bug #23966 (Pending Backport): Deleting a pool with active notify linger ops can result in seg fault
- 08:05 AM Bug #23851 (Resolved): OSD crashes on empty snapset
- 08:05 AM Backport #23852 (Resolved): luminous: OSD crashes on empty snapset
05/08/2018
- 11:09 PM Support #22531: OSD flapping under repair/scrub after recieve inconsistent PG LFNIndex.cc: 439: F...
- For the record...
I was also suffering this problem on a pg repair. That was because I was following the procedure... - 11:05 PM Backport #23852: luminous: OSD crashes on empty snapset
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21638
merged - 09:37 PM Bug #23909 (Resolved): snaps missing in mapper, should be: 188,18f,191,195,197,198,199,19d,19e,1a...
- 08:56 PM Backport #24048 (Resolved): luminous: pg-upmap cannot balance in some case
- https://github.com/ceph/ceph/pull/22115
- 05:08 PM Bug #20876: BADAUTHORIZER on mgr, hung ceph tell mon.*
- Triggered on Luminous 12.2.5 again.
Mon quorum worked as expected, after all monitors restart, not healed. all pgs... - 04:53 PM Bug #24045 (Resolved): Eviction still raced with scrub due to preemption
We put code in cache tier eviction to check the scrub range, but that isn't sufficient. During scrub preemption re...- 06:58 AM Backport #23850 (In Progress): luminous: Read operations segfaulting multiple OSDs
- -https://github.com/ceph/ceph/pull/21873-
- 06:48 AM Bug #23402: objecter: does not resend op on split interval
- we also met this problem with osd_debug_op_order=true, that result "out of order" assert
- 04:30 AM Backport #24042 (In Progress): luminous: ceph-disk log is written to /var/run/ceph
- 04:30 AM Backport #24042 (Resolved): luminous: ceph-disk log is written to /var/run/ceph
- https://github.com/ceph/ceph/pull/21870
- 04:28 AM Bug #24041: ceph-disk log is written to /var/run/ceph
- https://github.com/ceph/ceph/pull/18375
- 04:28 AM Bug #24041 (Resolved): ceph-disk log is written to /var/run/ceph
- it should go to /var/log/ceph
05/07/2018
- 08:38 PM Bug #24037 (Resolved): osd: Assertion `!node_algorithms::inited(this->priv_value_traits().to_nod...
- ...
- 07:24 PM Bug #23909: snaps missing in mapper, should be: 188,18f,191,195,197,198,199,19d,19e,1a1,1a3 was r...
Nevermind. I see you branch was still on ci repo.
$ git branch --contains c20a95b0b9f4082dcebb339135683b91fe39e...- 07:18 PM Bug #23909 (Need More Info): snaps missing in mapper, should be: 188,18f,191,195,197,198,199,19d,...
Does your branch include c20a95b0b9f4082dcebb339135683b91fe39ec0a? The change I made was needed to make that fix w...- 05:25 PM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- Alternative Mimic fix: https://github.com/ceph/ceph/pull/21859
- 02:55 PM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- will reset the member variables of C_notify_Finish in its dtor for debugging, to see if it has been destroyed or not ...
- 07:43 AM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- the test still fails with the fixes above: /a/kchai-2018-05-06_15:50:41-rados-wip-kefu-testing-2018-05-06-2204-distro...
- 03:34 PM Bug #24033 (Fix Under Review): rados: not all exceptions accept keyargs
- 01:19 PM Bug #24033: rados: not all exceptions accept keyargs
- https://github.com/ceph/ceph/pull/21853
- 12:55 PM Bug #24033 (Resolved): rados: not all exceptions accept keyargs
- The method make_ex() in rados.pyx raises exceptions irrespective of the fact whether an exception can or cannot handl...
- 02:15 AM Backport #23925 (In Progress): luminous: assert on pg upmap
- 12:05 AM Bug #24023: Segfault on OSD in 12.2.5
- Another one occurred today on a different OSD:
2018-05-06 19:48:33.636221 7f0f55922700 -1 *** Caught signal (Segme...
05/06/2018
- 09:01 AM Backport #23925: luminous: assert on pg upmap
- https://github.com/ceph/ceph/pull/21818
- 08:57 AM Bug #23921 (Pending Backport): pg-upmap cannot balance in some case
- 03:35 AM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- mimic: https://github.com/ceph/ceph/pull/21834
- 03:32 AM Backport #24027 (In Progress): mimic: ceph_daemon.py format_dimless units list index out of range
- 03:30 AM Backport #24027 (Resolved): mimic: ceph_daemon.py format_dimless units list index out of range
- https://github.com/ceph/ceph/pull/21836
- 03:29 AM Bug #23962 (Pending Backport): ceph_daemon.py format_dimless units list index out of range
- 03:28 AM Backport #24026 (In Progress): mimic: pg-upmap cannot balance in some case
- 03:27 AM Backport #24026 (Resolved): mimic: pg-upmap cannot balance in some case
- https://github.com/ceph/ceph/pull/21835
- 03:24 AM Bug #23627 (Resolved): Error EACCES: problem getting command descriptions from mgr.None from 'cep...
05/05/2018
- 08:32 PM Bug #24025: RocksDB compression is not supported at least on Debian.
- I use:
deb https://download.ceph.com/debian-luminous/ stretch main
Ceph 12.2.5 and Debian 9. - 08:31 PM Bug #24025 (Resolved): RocksDB compression is not supported at least on Debian.
- ...
- 04:20 PM Bug #23909: snaps missing in mapper, should be: 188,18f,191,195,197,198,199,19d,19e,1a1,1a3 was r...
- http://pulpito.ceph.com/kchai-2018-05-05_14:56:43-rados-wip-kefu-testing-2018-05-05-1912-distro-basic-smithi/
<pre... - 01:47 PM Backport #23904 (Resolved): luminous: Deleting a pool with active watch/notify linger ops can res...
- 11:55 AM Bug #24023 (Duplicate): Segfault on OSD in 12.2.5
- 2018-05-05 06:33:42.383231 7f83289a4700 -1 *** Caught signal (Segmentation fault) **
in thread 7f83289a4700 thread_... - 11:23 AM Bug #24022: "ceph tell osd.x bench" writes resulting JSON to stderr instead of stdout.
- Maybe not only this command, but also some others.
- 11:23 AM Bug #24022 (Resolved): "ceph tell osd.x bench" writes resulting JSON to stderr instead of stdout.
- 11:05 AM Bug #23627: Error EACCES: problem getting command descriptions from mgr.None from 'ceph tell mgr'
- https://github.com/ceph/ceph/pull/21832
- 10:57 AM Bug #23966: Deleting a pool with active notify linger ops can result in seg fault
- master: https://github.com/ceph/ceph/pull/21831
- 08:57 AM Bug #21977 (Resolved): null map from OSDService::get_map in advance_pg
- 08:57 AM Backport #23870 (Resolved): luminous: null map from OSDService::get_map in advance_pg
- 08:56 AM Backport #24016: luminous: scrub interaction with HEAD boundaries and snapmapper repair is broken
- Quoting David Zafman, PR to backport is:
https://github.com/ceph/ceph/pull/21546
Backport the entire pull reque...
05/04/2018
- 07:01 PM Backport #23784 (Resolved): luminous: osd: Warn about objects with too many omap entries
- 05:13 PM Backport #23784: luminous: osd: Warn about objects with too many omap entries
- Vikhyat Umrao wrote:
> https://github.com/ceph/ceph/pull/21518
merged - 06:22 PM Bug #24000: mon: snap delete on deleted pool returns 0 without proper payload
- Jason put a client-side handler in, but we should change the monitor as well so that we don't break older clients (or...
- 05:16 PM Backport #23904: luminous: Deleting a pool with active watch/notify linger ops can result in seg ...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21752
merged - 05:14 PM Backport #23870: luminous: null map from OSDService::get_map in advance_pg
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21737
merged - 03:20 PM Backport #24016 (Resolved): luminous: scrub interaction with HEAD boundaries and snapmapper repai...
- Included in
https://github.com/ceph/ceph/pull/22044 - 03:19 PM Backport #24015 (Resolved): luminous: UninitCondition in PG::RecoveryState::Incomplete::react(PG:...
- https://github.com/ceph/ceph/pull/21993
- 02:30 PM Bug #23921 (Fix Under Review): pg-upmap cannot balance in some case
- 02:30 PM Bug #23921: pg-upmap cannot balance in some case
- https://github.com/ceph/ceph/pull/21815
- 08:29 AM Bug #24007 (New): rados.connect get a segmentation fault
- if i try to use librados in this follow way, i will get a segmentation fault.
!http://img0.ph.126.net/ekMbDVzMROb-o_... - 04:04 AM Feature #22420 (Fix Under Review): Add support for obtaining a list of available compression options
- https://github.com/ceph/ceph/pull/21809
- 01:47 AM Bug #24006 (New): ceph-osd --mkfs has nondeterministic output
- On 12.2.3, my `ceph-osd` has nondeterministic output. I'm running it s root.
Sometimes it prints "created object s... - 12:46 AM Bug #22881: scrub interaction with HEAD boundaries and snapmapper repair is broken
- https://github.com/ceph/ceph/pull/21546
Backport the entire pull request which also fixes http://tracker.ceph.com/... - 12:43 AM Bug #22881 (Pending Backport): scrub interaction with HEAD boundaries and snapmapper repair is br...
- 12:45 AM Bug #23909 (Resolved): snaps missing in mapper, should be: 188,18f,191,195,197,198,199,19d,19e,1a...
- Included in https://github.com/ceph/ceph/pull/21546
05/03/2018
- 10:30 PM Bug #23980 (Pending Backport): UninitCondition in PG::RecoveryState::Incomplete::react(PG::AdvMap...
- 01:45 PM Bug #23980 (Fix Under Review): UninitCondition in PG::RecoveryState::Incomplete::react(PG::AdvMap...
- https://github.com/ceph/ceph/pull/21798
- 01:03 AM Bug #23980 (Resolved): UninitCondition in PG::RecoveryState::Incomplete::react(PG::AdvMap const&)
- ...
- 08:56 PM Bug #23576: osd: active+clean+inconsistent pg will not scrub or repair
- Are there messages "not scheduling scrubs due to active recovery" in the logs on any of the primary OSDs? That messa...
- 08:40 PM Bug #23576: osd: active+clean+inconsistent pg will not scrub or repair
- Ran into something similar this past week. ( active+clean+inconsistent) where forced scrubs would not run. The foll...
- 07:27 PM Bug #24000 (Fix Under Review): mon: snap delete on deleted pool returns 0 without proper payload
- *PR*: https://github.com/ceph/ceph/pull/21804
- 07:21 PM Bug #24000 (Resolved): mon: snap delete on deleted pool returns 0 without proper payload
- It can lead to an abort in the client application since an empty reply w/o an error code is constructed in the monito...
- 03:44 PM Documentation #23999 (Resolved): osd_recovery_priority is not documented (but osd_recovery_op_pri...
- Please document osd_recovery_priority and how it differs from osd_recovery_op_priority.
- 02:48 PM Bug #23961 (Duplicate): valgrind reports UninitCondition in osd PG::RecoveryState::Incomplete::re...
- 02:18 PM Backport #23998 (Resolved): luminous: osd/EC: slow/hung ops in multimds suite test
- https://github.com/ceph/ceph/pull/24393
- 02:08 PM Backport #23915 (Resolved): luminous: monitors crashing ./include/interval_set.h: 355: FAILED ass...
- 01:51 PM Backport #23915: luminous: monitors crashing ./include/interval_set.h: 355: FAILED assert(0) (jew...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21717
merged - 01:40 PM Bug #23769 (Pending Backport): osd/EC: slow/hung ops in multimds suite test
- 11:58 AM Feature #22420 (New): Add support for obtaining a list of available compression options
- i am reopening this ticket. as the plugin registry is empty before any of the supported compressor plugin is created ...
- 11:27 AM Bug #23937: FAILED assert(info.history.same_interval_since != 0)
- I didn't import or export any pgs, that was working osd in the cluster.
Is it possible that the restart of the osd ... - 10:28 AM Backport #23988 (Resolved): luminous: luminous->master: luminous crashes with AllReplicasRecovere...
- https://github.com/ceph/ceph/pull/21964
- 10:27 AM Backport #23986 (Resolved): luminous: recursive lock of objecter session::lock on cancel
- https://github.com/ceph/ceph/pull/21939
- 05:21 AM Bug #22220: osd/ReplicatedPG.h:1667:14: internal compiler error: in force_type_die, at dwarf2out....
- https://access.redhat.com/errata/RHBA-2018:1293
- 01:37 AM Bug #23119: MD5-checksum of the snapshot for rbd image in Ceph(as OpenStack-Glance backend Storag...
- Jason Dillaman wrote:
> Moving to RADOS since it sounds like it's an issue of corruption on your cache tier.
How ... - 01:00 AM Bug #22656: scrub mismatch on bytes (cache pools)
- /a/sage-2018-05-02_22:22:16-rados-wip-sage3-testing-2018-05-02-1448-distro-basic-smithi/2468046
description: rados... - 12:20 AM Feature #23979 (Resolved): Limit pg log length during recovery/backfill so that we don't run out ...
This means if there's another failure, we'll need to restart backfill or go from recovery to backfill, but that's b...
05/02/2018
- 09:02 PM Bug #23937: FAILED assert(info.history.same_interval_since != 0)
- Did you import or export any PGs? The on-disk pg info from comment #2 indicates the pg doesn't exist on osd.33 yet.
... - 08:53 PM Bug #23961: valgrind reports UninitCondition in osd PG::RecoveryState::Incomplete::react(PG::AdvM...
- What PRs were in the test branch that hit this? Did any of them change the PG class or related structures?
- 12:23 PM Bug #23961: valgrind reports UninitCondition in osd PG::RecoveryState::Incomplete::react(PG::AdvM...
- rerunning this test with another branch did not reproduce this issue.
http://pulpito.ceph.com/kchai-2018-05-02_11:... - 01:50 AM Bug #23961 (Duplicate): valgrind reports UninitCondition in osd PG::RecoveryState::Incomplete::re...
- ...
- 08:48 PM Bug #23830: rados/standalone/erasure-code.yaml gets 160 byte pgmeta object
- The pg meta object is supposed to be empty since many versions ago. IIRC sage suggested this may be from a race that ...
- 08:42 PM Bug #23860 (Pending Backport): luminous->master: luminous crashes with AllReplicasRecovered in St...
- 08:40 PM Bug #23942 (Duplicate): test_mon_osdmap_prune.sh failures
- 07:50 PM Bug #23769 (Fix Under Review): osd/EC: slow/hung ops in multimds suite test
- https://github.com/ceph/ceph/pull/21684
- 05:26 PM Bug #23966 (Fix Under Review): Deleting a pool with active notify linger ops can result in seg fault
- *PR*: https://github.com/ceph/ceph/pull/21786
- 04:00 PM Bug #23966 (In Progress): Deleting a pool with active notify linger ops can result in seg fault
- 03:51 PM Bug #23966 (Resolved): Deleting a pool with active notify linger ops can result in seg fault
- It's possible that if a notification is sent while a pool is being deleted, the Objecter will fail the Op w/ -ENOENT ...
- 02:50 PM Bug #23965 (New): FAIL: s3tests.functional.test_s3.test_multipart_upload_resend_part with ec cach...
- teuthology run with debug-ms 1 at http://pulpito.ceph.com/joshd-2018-05-01_18:40:57-rgw-master-distro-basic-smithi/
- 01:42 PM Bug #22330: ec: src/common/interval_map.h: 161: FAILED assert(len > 0)
- http://pulpito.ceph.com/pdonnell-2018-05-01_20:58:18-multimds-wip-pdonnell-testing-20180501.191840-testing-basic-smit...
- 11:47 AM Bug #23119: MD5-checksum of the snapshot for rbd image in Ceph(as OpenStack-Glance backend Storag...
- Moving to RADOS since it sounds like it's an issue of corruption on your cache tier.
- 02:41 AM Bug #23119: MD5-checksum of the snapshot for rbd image in Ceph(as OpenStack-Glance backend Storag...
- More discovery:
The snapshot exported from cache tier(rep_glance pool) is an all-zero file (viewed by "od xxx.snap... - 11:40 AM Bug #21142: OSD crashes when loading pgs with "FAILED assert(interval.last > last)"
- We frequently experience this with 12.2.3 running Ceph in a Kubernetes cluster, cf. https://github.com/ceph/ceph-cont...
- 11:32 AM Bug #23952: "ceph -f json osd pool ls detail" has missing pool namd and pool id
- Sorry, pool_name is here. Only pool id is missing.
- 10:11 AM Bug #23952: "ceph -f json osd pool ls detail" has missing pool namd and pool id
- Are you sure you're not getting pool name? I'm getting a pool_name field when I try this, and it appears to have bee...
- 11:04 AM Backport #23924 (In Progress): luminous: LibRadosAio.PoolQuotaPP failed
- https://github.com/ceph/ceph/pull/21778
- 06:53 AM Bug #23386: crush device class: Monitor Crash when moving Bucket into Default root
- Any update? Mentioned workaround is not good idea for us.
- 06:42 AM Bug #23949 (Resolved): osd: "failed to encode map e19 with expected crc" in cluster log "
- 05:22 AM Bug #23962 (Fix Under Review): ceph_daemon.py format_dimless units list index out of range
- https://github.com/ceph/ceph/pull/21765
- 04:02 AM Bug #23962: ceph_daemon.py format_dimless units list index out of range
- sorry, the actual max magnitude is EB level instead of ZB.
- 03:48 AM Bug #23962 (Resolved): ceph_daemon.py format_dimless units list index out of range
- The largest order of magnitude of original list max only to the PB level,however the ceph cluster Objecter actv metri...
- 03:31 AM Backport #23914 (In Progress): luminous: cache-try-flush hits wrlock, busy loops
- https://github.com/ceph/ceph/pull/21764
05/01/2018
- 06:31 PM Bug #23827: osd sends op_reply out of order
- For object 10000000004.00000004 osd_op_reply for 102425 is received before 93353....
- 05:52 PM Bug #23949 (Fix Under Review): osd: "failed to encode map e19 with expected crc" in cluster log "
- https://github.com/ceph/ceph/pull/21756
- 03:53 PM Bug #23949: osd: "failed to encode map e19 with expected crc" in cluster log "
- /a/sage-2018-05-01_15:25:33-fs-master-distro-basic-smithi/2462491
reproduces on master - 03:09 PM Bug #23949 (In Progress): osd: "failed to encode map e19 with expected crc" in cluster log "
- 03:09 PM Bug #23949: osd: "failed to encode map e19 with expected crc" in cluster log "
- ...
- 02:17 PM Bug #23949: osd: "failed to encode map e19 with expected crc" in cluster log "
- More from master: http://pulpito.ceph.com/pdonnell-2018-05-01_03:21:36-fs-master-testing-basic-smithi/
- 05:26 PM Bug #23940 (Pending Backport): recursive lock of objecter session::lock on cancel
- 02:39 PM Bug #22354: v12.2.2 unable to create bluestore osd using ceph-disk
- The problem of left-over OSD data still persists when the partition table has been removed before "ceph-disk zap" is ...
- 12:42 PM Backport #23905 (In Progress): jewel: Deleting a pool with active watch/notify linger ops can res...
- https://github.com/ceph/ceph/pull/21754
- 11:36 AM Backport #23904 (In Progress): luminous: Deleting a pool with active watch/notify linger ops can ...
- https://github.com/ceph/ceph/pull/21752
- 07:01 AM Bug #23952 (New): "ceph -f json osd pool ls detail" has missing pool namd and pool id
- `ceph osd pool ls detail` shows information about pool id and pool name, but with '-f json' this information disappears.
04/30/2018
- 11:10 PM Bug #23949 (Resolved): osd: "failed to encode map e19 with expected crc" in cluster log "
- http://pulpito.ceph.com/pdonnell-2018-04-30_21:17:21-fs-wip-pdonnell-testing-20180430.193008-testing-basic-smithi/245...
- 05:46 PM Bug #23860: luminous->master: luminous crashes with AllReplicasRecovered in Started/Primary/Activ...
- 05:25 PM Bug #23386: crush device class: Monitor Crash when moving Bucket into Default root
- http://lists.ceph.com/pipermail/ceph-users-ceph.com/2018-March/025569.html
Paul Emmerich wrote:
> looks like it fai... - 12:28 PM Bug #23386: crush device class: Monitor Crash when moving Bucket into Default root
- (Pulling backtrace into the ticket)
- 03:57 PM Bug #23937: FAILED assert(info.history.same_interval_since != 0)
- This pg has 0 value in same_interval_since. I checked this with following output:
https://paste.fedoraproject.org/pa... - 01:12 PM Bug #23937: FAILED assert(info.history.same_interval_since != 0)
- I found a little more...
- 03:48 PM Bug #23942 (Duplicate): test_mon_osdmap_prune.sh failures
- ...
- 02:55 PM Bug #23922 (Resolved): ENOMEM from ceph_test_rados and ceph_test_cls_rbd (hammer client)
- 01:44 PM Bug #23922 (Fix Under Review): ENOMEM from ceph_test_rados and ceph_test_cls_rbd (hammer client)
- https://github.com/ceph/ceph/pull/21739
- 01:32 PM Bug #23922: ENOMEM from ceph_test_rados and ceph_test_cls_rbd (hammer client)
- ...
- 01:06 PM Bug #23922: ENOMEM from ceph_test_rados and ceph_test_cls_rbd (hammer client)
- failed to reproduce this issue locally.
adding... - 11:00 AM Bug #23922: ENOMEM from ceph_test_rados and ceph_test_cls_rbd (hammer client)
- http://pulpito.ceph.com/kchai-2018-04-30_00:59:17-rados-wip-kefu-testing-2018-04-29-1248-distro-basic-smithi/2454246/
- 02:53 PM Bug #23940 (Fix Under Review): recursive lock of objecter session::lock on cancel
- https://github.com/ceph/ceph/pull/21742
- 02:30 PM Bug #23940 (Resolved): recursive lock of objecter session::lock on cancel
- ...
- 12:30 PM Backport #23870 (In Progress): luminous: null map from OSDService::get_map in advance_pg
- https://github.com/ceph/ceph/pull/21737
04/29/2018
- 11:46 PM Bug #23937 (New): FAILED assert(info.history.same_interval_since != 0)
- Two of our osds hit these assert and now they are down....
- 10:23 AM Bug #22354 (Resolved): v12.2.2 unable to create bluestore osd using ceph-disk
- 10:23 AM Backport #23103 (Resolved): luminous: v12.2.2 unable to create bluestore osd using ceph-disk
- 10:22 AM Bug #22082 (Resolved): Various odd clog messages for mons
- 10:21 AM Backport #22167 (Resolved): luminous: Various odd clog messages for mons
- 10:21 AM Bug #22090 (Resolved): cluster [ERR] Unhandled exception from module 'balancer' while running on ...
- 10:20 AM Backport #22164 (Resolved): luminous: cluster [ERR] Unhandled exception from module 'balancer' wh...
- 10:20 AM Bug #21993 (Resolved): "ceph osd create" is not idempotent
- 10:20 AM Backport #22019 (Resolved): luminous: "ceph osd create" is not idempotent
- 10:19 AM Bug #21203 (Resolved): build_initial_pg_history doesn't update up/acting/etc
- 10:19 AM Backport #21236 (Resolved): luminous: build_initial_pg_history doesn't update up/acting/etc
- 07:07 AM Bug #21206 (Resolved): thrashosds read error injection doesn't take live_osds into account
- 07:07 AM Backport #21235 (Resolved): luminous: thrashosds read error injection doesn't take live_osds into...
- 06:22 AM Backport #23915 (In Progress): luminous: monitors crashing ./include/interval_set.h: 355: FAILED ...
- 05:44 AM Backport #22934: luminous: filestore journal replay does not guard omap operations
- https://github.com/ceph/ceph/pull/21547
04/28/2018
- 10:32 PM Backport #23915: luminous: monitors crashing ./include/interval_set.h: 355: FAILED assert(0) (jew...
- https://github.com/ceph/ceph/pull/21717
- 07:11 PM Backport #23926 (Rejected): luminous: disable bluestore cache caused a rocksdb error
- 07:11 PM Backport #23925 (Resolved): luminous: assert on pg upmap
- https://github.com/ceph/ceph/pull/21818
- 07:11 PM Backport #23924 (Resolved): luminous: LibRadosAio.PoolQuotaPP failed
- https://github.com/ceph/ceph/pull/21778
- 06:19 PM Bug #23816 (Pending Backport): disable bluestore cache caused a rocksdb error
- 06:17 PM Bug #23878 (Pending Backport): assert on pg upmap
- 06:17 PM Bug #23916 (Pending Backport): LibRadosAio.PoolQuotaPP failed
- 06:16 PM Bug #23922 (Resolved): ENOMEM from ceph_test_rados and ceph_test_cls_rbd (hammer client)
- ...
- 04:23 AM Bug #23921: pg-upmap cannot balance in some case
- But if i unlink all osds from 'root default / host huangjun', every thing works ok....
- 04:04 AM Bug #23921 (Resolved): pg-upmap cannot balance in some case
- I have a cluster with 21 osds, cluster topology is...
04/27/2018
- 10:38 PM Bug #23916 (Fix Under Review): LibRadosAio.PoolQuotaPP failed
- https://github.com/ceph/ceph/pull/21709
- 09:22 PM Bug #23916 (Resolved): LibRadosAio.PoolQuotaPP failed
- http://qa-proxy.ceph.com/teuthology/yuriw-2018-04-27_16:52:05-rados-wip-yuri-testing-2018-04-27-1519-distro-basic-smi...
- 10:27 PM Bug #23917 (Duplicate): LibRadosAio.PoolQuotaPP failure
- 10:24 PM Bug #23917 (Duplicate): LibRadosAio.PoolQuotaPP failure
- ...
- 08:07 PM Backport #23915 (Resolved): luminous: monitors crashing ./include/interval_set.h: 355: FAILED ass...
- https://github.com/ceph/ceph/pull/21717
- 08:06 PM Backport #23914 (Resolved): luminous: cache-try-flush hits wrlock, busy loops
- https://github.com/ceph/ceph/pull/21764
- 08:01 PM Bug #23860 (Fix Under Review): luminous->master: luminous crashes with AllReplicasRecovered in St...
- https://github.com/ceph/ceph/pull/21706
- 07:30 PM Bug #18746 (Pending Backport): monitors crashing ./include/interval_set.h: 355: FAILED assert(0) ...
- 07:28 PM Bug #23664 (Pending Backport): cache-try-flush hits wrlock, busy loops
- 07:28 PM Bug #21165 (Can't reproduce): 2 pgs stuck in unknown during thrashing
- 07:27 PM Bug #23788 (Duplicate): luminous->mimic: EIO (crc mismatch) on copy-get from ec pool
- I think this was a dup of #23871
- 07:24 PM Backport #23912 (Resolved): luminous: mon: High MON cpu usage when cluster is changing
- https://github.com/ceph/ceph/pull/21968
- 07:17 PM Bug #23911: ceph:luminous: osd out/down when setup with ubuntu/bluestore
- The zap run in this is definitely not zero'ing the first block based on log output...
- 06:49 PM Bug #23911: ceph:luminous: osd out/down when setup with ubuntu/bluestore
- we clean more than 100m but i think its from the end
https://github.com/ceph/ceph/blob/luminous/src/ceph-disk/ceph... - 06:25 PM Bug #23911: ceph:luminous: osd out/down when setup with ubuntu/bluestore
- Thanks alfredo
It shows that zap is not working now, I think we should fix the ceph-disk zap to properly clean the... - 06:07 PM Bug #23911: ceph:luminous: osd out/down when setup with ubuntu/bluestore
- Looking at the logs for the OSD that failed:...
- 05:48 PM Bug #23911: ceph:luminous: osd out/down when setup with ubuntu/bluestore
- seen in both 14.04, 16.04 and centos for bluestore option only
14.04:
http://qa-proxy.ceph.com/teuthology/teuth... - 05:45 PM Bug #23911 (Won't Fix - EOL): ceph:luminous: osd out/down when setup with ubuntu/bluestore
- this could be a systemd issue or more,
a) setup cluster using ceph-deploy
b) use ceph-disk/bluestore option for ... - 05:26 PM Bug #22624: filestore: 3180: FAILED assert(0 == "unexpected error"): error (2) No such file or di...
- Moving this back to RADOS as it seems the new consensus is that it's a RADOS bug.
- 06:46 AM Bug #22624: filestore: 3180: FAILED assert(0 == "unexpected error"): error (2) No such file or di...
- From message: "error (2) No such file or directory not handled on operation 0x55e1ce80443c (21888.1.0, or op 0, count...
- 04:38 PM Bug #23893 (Resolved): jewel clients fail to decode mimic osdmap
- it was a bug in wip-osdmap-encode, fixed before merge
- 04:14 PM Bug #23713 (Pending Backport): High MON cpu usage when cluster is changing
- 03:01 PM Bug #23909 (Resolved): snaps missing in mapper, should be: 188,18f,191,195,197,198,199,19d,19e,1a...
New code for tracker #22881 in pull request https://github.com/ceph/ceph/pull/21546 no calls _scan_snaps() on each ...- 01:23 PM Bug #23627 (Fix Under Review): Error EACCES: problem getting command descriptions from mgr.None f...
- https://github.com/ceph/ceph/pull/21698
- 01:16 PM Bug #23627: Error EACCES: problem getting command descriptions from mgr.None from 'ceph tell mgr'
- ...
- 12:22 PM Bug #23627: Error EACCES: problem getting command descriptions from mgr.None from 'ceph tell mgr'
- /a//kchai-2018-04-27_07:23:02-rados-wip-kefu-testing-2018-04-27-0902-distro-basic-smithi/2444194
- 10:43 AM Backport #23905 (Resolved): jewel: Deleting a pool with active watch/notify linger ops can result...
- https://github.com/ceph/ceph/pull/21754
- 10:42 AM Backport #23904 (Resolved): luminous: Deleting a pool with active watch/notify linger ops can res...
- https://github.com/ceph/ceph/pull/21752
- 10:39 AM Backport #23850 (New): luminous: Read operations segfaulting multiple OSDs
- Status can change to "In Progress" when the PR is open and URL of PR is mentioned in a comment.
- 06:29 AM Backport #23850 (In Progress): luminous: Read operations segfaulting multiple OSDs
- 10:17 AM Bug #23899: run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentation fault
- root cause is sometimes output.read_fd() could return 0 length data.
ret = output.read_fd(smartctl.get_stdout(), 1... - 10:15 AM Bug #23899 (Resolved): run cmd 'ceph daemon osd.0 smart' cause osd daemon Segmentation fault
2018-04-27 09:44:51.572 7fb787a05700 -1 osd.0 57 smartctl output is:
2018-04-27 09:44:51.576 7fb787a05700 -1 *** C...- 09:00 AM Bug #23879: test_mon_osdmap_prune.sh fails
- ...
- 01:34 AM Bug #23878: assert on pg upmap
- This pr #21670 passed tests failed before in my local cluster, needs qa
- 12:55 AM Bug #23872 (Pending Backport): Deleting a pool with active watch/notify linger ops can result in ...
04/26/2018
- 11:27 PM Bug #23492: Abort in OSDMap::decode() during qa/standalone/erasure-code/test-erasure-eio.sh
Seen again:
http://qa-proxy.ceph.com/teuthology/dzafman-2018-04-26_10:04:07-rados-wip-zafman-testing-distro-basi...- 10:33 PM Bug #23893 (Resolved): jewel clients fail to decode mimic osdmap
- http://pulpito.ceph.com/sage-2018-04-26_19:17:57-rados:thrash-old-clients-wip-sage-testing-2018-04-26-1251-distro-bas...
- 10:22 PM Bug #23871 (Resolved): luminous->mimic: missing primary copy of xxx, wil try copies on 3, then fu...
- 10:20 PM Bug #23892 (Can't reproduce): luminous->mimic: mon segv in ~MonOpRequest from OpHistoryServiceThread
- ...
- 05:06 PM Bug #23785 (Resolved): "test_prometheus (tasks.mgr.test_module_selftest.TestModuleSelftest) ... E...
- test is passing now
- 02:23 PM Bug #23769 (In Progress): osd/EC: slow/hung ops in multimds suite test
- 01:55 PM Bug #23878 (Fix Under Review): assert on pg upmap
- https://github.com/ceph/ceph/pull/21670
- 01:55 PM Bug #23878: assert on pg upmap
- 09:52 AM Bug #23878: assert on pg upmap
- I’ll prepare a patch soon
- 06:44 AM Bug #23878: assert on pg upmap
- And then if i do pg-upmap operation....
- 05:35 AM Bug #23878: assert on pg upmap
- After pick the pr https://github.com/ceph/ceph/pull/21325
It works fine.
But i have some question:
the upmap items... - 04:31 AM Bug #23878 (Resolved): assert on pg upmap
- I use the follow script to test upmap...
- 10:09 AM Backport #23863 (In Progress): luminous: scrub interaction with HEAD boundaries and clones is broken
- 09:16 AM Backport #23863: luminous: scrub interaction with HEAD boundaries and clones is broken
- https://github.com/ceph/ceph/pull/21665
- 07:46 AM Bug #23879 (Can't reproduce): test_mon_osdmap_prune.sh fails
- ...
- 02:46 AM Bug #20798: LibRadosLockECPP.LockExclusiveDurPP gets EEXIST
- /kchai-2018-04-26_00:52:32-rados-wip-kefu-testing-2018-04-25-2253-distro-basic-smithi/2439501/
- 12:02 AM Bug #20924: osd: leaked Session on osd.7
- osd.3 here:
http://pulpito.ceph.com/yuriw-2018-04-23_23:19:23-rados-wip-yuri-testing-2018-04-23-1502-distro-basic-...
Also available in: Atom