Activity
From 08/27/2017 to 09/25/2017
09/25/2017
- 09:21 PM Backport #21544 (Resolved): luminous: mon osd feature checks for osdmap flags and require-osd-rel...
- https://github.com/ceph/ceph/pull/18364
- 09:21 PM Backport #21543 (Resolved): luminous: bluestore fsck took 224.778802 seconds to complete which ca...
- https://github.com/ceph/ceph/pull/18362
- 05:37 PM Bug #21532: osd: Abort in thread_name:tp_osd_tp
- ...although even a slow disk shouldn't be long enough for the the heartbeat to time out. :/
- 05:36 PM Bug #21532: osd: Abort in thread_name:tp_osd_tp
- It looks like a zilli threads are blocked at...
- 05:25 PM Bug #21532 (Need More Info): osd: Abort in thread_name:tp_osd_tp
- [10:22:39] <@sage> it looks like everyone is waiting for log flush.. which is deep in snprintf in the core. can't te...
- 05:23 PM Bug #21532: osd: Abort in thread_name:tp_osd_tp
- The log ends 14 minutes prior to the signal, which I imagine is related to #21507....
- 03:47 AM Bug #21532 (Need More Info): osd: Abort in thread_name:tp_osd_tp
- ...
- 02:19 AM Bug #21471 (Pending Backport): mon osd feature checks for osdmap flags and require-osd-release fa...
- 02:15 AM Bug #21474 (Pending Backport): bluestore fsck took 224.778802 seconds to complete which caused "t...
- 02:13 AM Bug #21511 (Resolved): rados/standalone/scrub.yaml: can't decode 'snapset' attr buffer::malformed...
09/23/2017
- 04:39 PM Bug #21470: Ceph OSDs crashing in BlueStore::queue_transactions() using EC after applying fix
- With a similar but slightly different setup, this same crash happened to me.
Installed via ceph-deploy install --r... - 10:15 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- @Daniel,
Yes.no OSD running on xfs shows the problem in question. I think one of different between the db based o... - 02:25 AM Bug #21382: Erasure code recovery should send additional reads if necessary
- https://github.com/ceph/ceph/pull/17920
- 02:25 AM Bug #21382 (Fix Under Review): Erasure code recovery should send additional reads if necessary
09/22/2017
- 09:49 PM Bug #21511 (Fix Under Review): rados/standalone/scrub.yaml: can't decode 'snapset' attr buffer::m...
- https://github.com/ceph/ceph/pull/17927
- 06:00 PM Bug #21511 (Resolved): rados/standalone/scrub.yaml: can't decode 'snapset' attr buffer::malformed...
- ...
- 09:04 PM Bug #21408 (Resolved): osd: "fsck error: free extent 0x2000~2000 intersects allocated blocks"
- 08:43 PM Bug #21218: thrash-eio + bluestore (hangs with unfound objects or read_log_and_missing assert)
- @Sage,
Pls, would you have the reproducer for this, so I could give it a try and check it out in my environment? ... - 05:51 PM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- @Wei,
Yes, the log file shows the same error with 12.2.0 build running on. I agree with @Josh and you, it seems t... - 02:45 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- @Sage @Daniel Huang and I use the same cluster. We use xfs insteads of bluefs for some osds in our cluster, the issue...
- 01:54 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- Sage Weil wrote:
> Can you please upgrade to 12.2.0 (or better yet, latest luminous branch), and then run fsck and a... - 12:51 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- Daniel Oliveira wrote:
> @Wei,
>
> Please, would you mind describing a bit more your environment? Also, how ofte... - 11:36 AM Bug #20871 (Resolved): core dump when bluefs's mkdir returns -EEXIST
- 03:31 AM Bug #20759: mon: valgrind detects a few leaks
- /kchai-2017-09-21_06:22:45-rados-wip-kefu-testing-2017-09-21-1013-distro-basic-mira/1654844/remote/mira038/log/valgri...
- 03:13 AM Bug #21474: bluestore fsck took 224.778802 seconds to complete which caused "timed out waiting fo...
- ...
- 03:06 AM Bug #21474 (Fix Under Review): bluestore fsck took 224.778802 seconds to complete which caused "t...
- https://github.com/ceph/ceph/pull/17902
09/21/2017
- 11:00 PM Bug #21382 (In Progress): Erasure code recovery should send additional reads if necessary
- 09:50 PM Bug #21470: Ceph OSDs crashing in BlueStore::queue_transactions() using EC after applying fix
- Done. Took less than an hour and happened on two OSDs. Uploaded one of them:
ceph-post-file: 6e0ed6ab-1528-428d-aa... - 08:26 PM Bug #21470 (Need More Info): Ceph OSDs crashing in BlueStore::queue_transactions() using EC after...
- Okay, thanks for confirmation that the #21171 fix is applied. can you reproduce with debug bluestore = 20, and then ...
- 08:25 PM Bug #21475 (Duplicate): 12.2.0 bluestore - OSD down/crash " internal heartbeat not healthy, dropp...
- 08:08 PM Bug #20416: "FAILED assert(osdmap->test_flag((1<<15)))" (sortbitwise) on upgraded cluster
- Got a report of this happening in downstream Red Hat packages at https://bugzilla.redhat.com/show_bug.cgi?id=1494238
... - 08:02 PM Bug #21496 (Fix Under Review): doc: Manually editing a CRUSH map, Word 'type' missing.
- http://docs.ceph.com/docs/master/rados/operations/crush-map-edits/
In the section "CRUSH map rules", in the overvi... - 07:59 PM Bug #21303 (Need More Info): rocksdb get a error: "Compaction error: Corruption: block checksum m...
- Can you please upgrade to 12.2.0 (or better yet, latest luminous branch), and then run fsck and attach the output?
... - 04:59 PM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- @Wei,
Please, would you mind describing a bit more your environment? Also, how often does it happen? Can we repro... - 06:11 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- This issue can reproduce in our cluster, we are willing to give more information if you need.
- 07:36 PM Bug #20653 (Can't reproduce): bluestore: aios don't complete on very large writes on xenial
- I'm going to assume this was #21171
- 06:48 PM Bug #21417: buffer_anon leak during deep scrub (on otherwise idle osd)
- definitely happens from an ec pool.
- 04:03 PM Bug #21410 (Resolved): pg_upmap_items can duplicate an item
- 02:45 PM Bug #21410 (Pending Backport): pg_upmap_items can duplicate an item
- 04:02 PM Bug #21495 (New): src/osd/OSD.cc: 346: FAILED assert(piter != rev_pending_splits.end())
- ...
- 04:07 AM Backport #21465 (In Progress): luminous: OSD metadata 'backend_filestore_dev_node' is "unknown" e...
- 04:05 AM Backport #21438 (In Progress): luminous: Daemons(OSD, Mon...) exit abnormally at injectargs command
- 04:03 AM Backport #21343 (In Progress): luminous: DNS SRV default service name not used anymore
- 04:01 AM Backport #21307 (In Progress): luminous: Client client.admin marked osd.2 out, after it was down ...
09/20/2017
- 08:37 PM Bug #21428: luminous: osd: does not request latest map from mon
- Fix:
* master https://github.com/ceph/ceph/pull/17828
* luminous https://github.com/ceph/ceph/pull/17829 - 03:15 PM Bug #21428 (Resolved): luminous: osd: does not request latest map from mon
- 05:17 AM Bug #21428 (In Progress): luminous: osd: does not request latest map from mon
- fixing bug in the patch
- 04:39 PM Bug #21408 (Fix Under Review): osd: "fsck error: free extent 0x2000~2000 intersects allocated blo...
- https://github.com/ceph/ceph/pull/17845
- 04:03 PM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- potentially a bug in bluefs
- 03:53 PM Bug #21407: backoff causes out of order op
- 03:46 PM Bug #20924: osd: leaked Session on osd.7
- /a/yuriw-2017-09-19_19:54:13-rados-wip-yuri-testing3-2017-09-19-1710-distro-basic-smithi/1648800
osd.7 again! weird - 03:01 PM Bug #21474: bluestore fsck took 224.778802 seconds to complete which caused "timed out waiting fo...
- cool. will update the test.
- 12:14 PM Bug #21474: bluestore fsck took 224.778802 seconds to complete which caused "timed out waiting fo...
- Sigh.. yeah. I can't decide if we should stop doing these fsck's entirely, or reduce the debug level just for fsck, ...
- 05:30 AM Bug #21474: bluestore fsck took 224.778802 seconds to complete which caused "timed out waiting fo...
- Sage, if you believe that it's normal for bluestore to take around 4 minutes to complete a deep fsck. i will prolong ...
- 05:28 AM Bug #21474 (Resolved): bluestore fsck took 224.778802 seconds to complete which caused "timed out...
- /a/kchai-2017-09-19_14:50:44-rados-wip-kefu-testing-2017-09-19-1954-distro-basic-mira/1648644...
- 11:19 AM Bug #21475: 12.2.0 bluestore - OSD down/crash " internal heartbeat not healthy, dropping ping req...
- Seems, its a duplicate of this tracker http://tracker.ceph.com/issues/21180 . Please verify..
- 11:18 AM Bug #21475 (Duplicate): 12.2.0 bluestore - OSD down/crash " internal heartbeat not healthy, dropp...
- ~~~
2017-09-18 14:51:59.895746 7f1e744e0700 0 log_channel(cluster) log [WRN] : slow request 60.068824 seconds old... - 10:25 AM Bug #21471 (In Progress): mon osd feature checks for osdmap flags and require-osd-release fail if...
- https://github.com/ceph/ceph/pull/17831
- 02:29 AM Bug #21471 (Resolved): mon osd feature checks for osdmap flags and require-osd-release fail if 0 ...
- the various checks test get_up_osd_features() but that returns 0 if no osds are up.
needs to be fixed in luminous ... - 02:19 AM Bug #21470: Ceph OSDs crashing in BlueStore::queue_transactions() using EC after applying fix
- Oh, forgot to add that I've tried the workarounds on the related issues. Adding this to my ceph.conf makes no differe...
- 02:16 AM Bug #21470 (Resolved): Ceph OSDs crashing in BlueStore::queue_transactions() using EC after apply...
- This is a copy of http://tracker.ceph.com/issues/21314, which was marked as resolved. It's not resolved after applyin...
09/19/2017
- 11:46 PM Bug #21428 (Resolved): luminous: osd: does not request latest map from mon
- backport was https://github.com/ceph/ceph/pull/17796
- 07:24 AM Bug #21428 (Fix Under Review): luminous: osd: does not request latest map from mon
- https://github.com/ceph/ceph/pull/17795
- 02:02 AM Bug #21428 (In Progress): luminous: osd: does not request latest map from mon
- 12:16 AM Bug #21428: luminous: osd: does not request latest map from mon
- I think this is from the fast_dispatch refactor in luminous, and the latest test timing just happened to show it.
- 12:12 AM Bug #21428 (Resolved): luminous: osd: does not request latest map from mon
- On the current luminous branch, a couple tests saw slow requests > 1 hour due to ops waiting for maps.
One is /a/y... - 08:25 PM Backport #21465 (Resolved): luminous: OSD metadata 'backend_filestore_dev_node' is "unknown" even...
- https://github.com/ceph/ceph/pull/17865
- 06:01 PM Bug #20944 (Pending Backport): OSD metadata 'backend_filestore_dev_node' is "unknown" even for si...
- 11:36 AM Backport #21438 (Resolved): luminous: Daemons(OSD, Mon...) exit abnormally at injectargs command
- https://github.com/ceph/ceph/pull/17864
- 08:20 AM Bug #21287: 1 PG down, OSD fails with "FAILED assert(i->prior_version == last || i->is_error())"
- I had to delete affected pool to reclaim occupied space so I am unable to verify any fixes
- 03:31 AM Bug #21174: OSD crash: 903: FAILED assert(objiter->second->version > last_divergent_update)
- duplicate issue: http://tracker.ceph.com/issues/16279
09/18/2017
- 08:57 PM Bug #19790 (Resolved): rados ls on pool with no access returns no error
- 08:57 PM Backport #20723 (Resolved): jewel: rados ls on pool with no access returns no error
- 02:45 PM Bug #20909: Error ETIMEDOUT: crush test failed with -110: timed out during smoke test (5 seconds)
- with https://github.com/ceph/ceph/pull/17179, we also met this error:
mon.b@0(leader).osd e15 tester.test_with_fork... - 02:53 AM Bug #21171: bluestore: aio submission deadlock
- Since my issue (http://tracker.ceph.com/issues/21314) was marked as a dupe of this and I haven't received a response ...
- 01:42 AM Bug #21417 (Resolved): buffer_anon leak during deep scrub (on otherwise idle osd)
- observed gobs of ram (11gb rss) and most of it buffer_anon (~8gb) on a basically idle cluster with replication, ec, a...
09/16/2017
- 05:59 PM Bug #21409 (Resolved): per-pool full flags set incorrectly?
- 05:46 AM Bug #21409 (Fix Under Review): per-pool full flags set incorrectly?
- https://github.com/ceph/ceph/pull/17763
09/15/2017
- 09:54 PM Bug #21408 (In Progress): osd: "fsck error: free extent 0x2000~2000 intersects allocated blocks"
- 07:50 PM Bug #21408 (Resolved): osd: "fsck error: free extent 0x2000~2000 intersects allocated blocks"
- Run: http://pulpito.ceph.com/teuthology-2017-09-15_17:30:33-upgrade:luminous-x-master-distro-basic-smithi/
Jobs: man... - 08:57 PM Bug #21410 (Fix Under Review): pg_upmap_items can duplicate an item
- https://github.com/ceph/ceph/pull/17760
- 08:43 PM Bug #21410 (Resolved): pg_upmap_items can duplicate an item
- ...
- 08:34 PM Bug #21309 (Resolved): mon/OSDMonitor: deleting pool while pgs are being created leads to assert(...
- 08:34 PM Backport #21341 (Resolved): luminous: mon/OSDMonitor: deleting pool while pgs are being created l...
- 08:32 PM Bug #21409 (Resolved): per-pool full flags set incorrectly?
- http://pulpito.ceph.com/sage-2017-09-15_15:50:19-rados-wip-sage-testing2-2017-09-14-1256-distro-basic-smithi/1635852
... - 08:28 PM Bug #21407: backoff causes out of order op
- https://github.com/ceph/ceph/pull/17759
- 07:44 PM Bug #21407: backoff causes out of order op
- problem seems to be that we are requeueing waiting_for_peered before we are actually peered. that happens from on_fl...
- 07:19 PM Bug #21407 (Resolved): backoff causes out of order op
- - receive op a and b...
- 11:53 AM Bug #21365 (Pending Backport): Daemons(OSD, Mon...) exit abnormally at injectargs command
- https://github.com/ceph/ceph/pull/17664
- 08:11 AM Bug #21388: inconsistent pg but repair does nothing reporting head data_digest != data_digest fro...
- We did an scp of the OSD object file then a rados put and deep-scrub got it back to OK.
Thanks for your quick answer!
09/14/2017
- 10:20 PM Bug #21388: inconsistent pg but repair does nothing reporting head data_digest != data_digest fro...
- I forgot the mention that on get you have to prevent the code from checking the digest by doing reads that are smalle...
- 10:18 PM Bug #21388: inconsistent pg but repair does nothing reporting head data_digest != data_digest fro...
After the deep-scrub, "rados get" give us some errors:
# rados list-inconsistent-obj 58.6c1 --format=json-pretty...- 03:35 PM Bug #21388: inconsistent pg but repair does nothing reporting head data_digest != data_digest fro...
Doing the following should produce list-inconsistent-obj information:
$ ceph pg deep-scrub 58.6c1
(Wait for scr...- 01:37 PM Bug #21388 (Duplicate): inconsistent pg but repair does nothing reporting head data_digest != dat...
- ceph pg repair is currently not fixing three "inconsistent" objects
on one of our pg on a replica 3 pool.
For al... - 10:18 PM Backport #21117 (In Progress): jewel: osd: osd_scrub_during_recovery only considers primary, not ...
- This requires merge resolution which I've begun looking at.
- 12:25 PM Bug #20924: osd: leaked Session on osd.7
- /a/sage-2017-09-13_13:31:57-rados-wip-sage-testing-2017-09-12-1750-distro-basic-smithi/1627916
is it just me or is... - 12:22 PM Bug #21218: thrash-eio + bluestore (hangs with unfound objects or read_log_and_missing assert)
- another run, eio injection led to a read_log_and_missing assert:...
- 12:15 PM Bug #21387 (Can't reproduce): mark_unfound_lost hangs
- ...
- 10:51 AM Bug #21354: Possible bug in interval_set.intersect_of()
- great, i was searching this ticket in "My Page" on tracker =D
- 09:29 AM Backport #21374 (In Progress): luminous: incorrect erasure-code space in command ceph df
- 09:22 AM Documentation #21386: rados: manpage missing import/export
- Also there seem to be hidden secret options like '--workers', nowhere to be found (not even in rados --help) but acce...
- 09:17 AM Documentation #21386 (New): rados: manpage missing import/export
- IMPORT AND EXPORT
export [filename]
Serialize pool contents to a file or standard out.
import [--dry-...
09/13/2017
- 11:59 PM Bug #21382 (Resolved): Erasure code recovery should send additional reads if necessary
We don't send additional reads when recovery experiences errors on some of the shards. For recovery we send k read...- 09:54 PM Backport #17445: jewel: list-snap cache tier missing promotion logic (was: rbd cli segfault when ...
- https://github.com/ceph/ceph/pull/17707
09/12/2017
- 06:59 PM Feature #21084 (Fix Under Review): auth: add osd auth caps based on pool metadata
- https://github.com/ceph/ceph/pull/17678
- 05:19 PM Bug #20981: ./run_seed_to_range.sh errored out
- I'm lowering the priority because it appears to me to be a test code issue. The test doesn't detect the failure it i...
- 02:17 PM Backport #21374 (Resolved): luminous: incorrect erasure-code space in command ceph df
- https://github.com/ceph/ceph/pull/17724
- 01:44 PM Bug #21243 (Pending Backport): incorrect erasure-code space in command ceph df
- 12:32 PM Bug #21243 (Resolved): incorrect erasure-code space in command ceph df
- 12:31 PM Bug #21258 (Closed): "ceph df"'s MAX AVAIL is not correct
- 11:04 AM Bug #21354 (Closed): Possible bug in interval_set.intersect_of()
- Closing, as the real reason for the issue was a git-merge that went wrong, leaving extra "insert(start, en-start);" c...
- 04:21 AM Bug #21354: Possible bug in interval_set.intersect_of()
- I have tried to reproduce this problem myself, but I got the same results with and without the intersection_size_asym...
- 07:01 AM Feature #21366: tools/ceph-objectstore-tool: split filestore directories offline to target hash l...
- https://github.com/ceph/ceph/pull/17666
- 07:00 AM Feature #21366 (Resolved): tools/ceph-objectstore-tool: split filestore directories offline to ta...
- Currently ceph-objectstore-tool can only split dirs that already meet the usual object number criteria. It won't redu...
- 06:21 AM Bug #21338 (Fix Under Review): There is a big risk in function bufferlist::claim_prepend()
- https://github.com/ceph/ceph/pull/17661
- 04:13 AM Bug #21365 (Resolved): Daemons(OSD, Mon...) exit abnormally at injectargs command
- Use tell injectargs command to adjust log level of osd, get the following error:...
09/11/2017
- 11:16 PM Bug #20981: ./run_seed_to_range.sh errored out
This bug was filed because the ceph_test_filestore_idempotent_sequence wasn't completing the _exit() in _inject_fai...- 03:44 PM Bug #21354 (Closed): Possible bug in interval_set.intersect_of()
- I've been working on different kind of optimization of pg_pool_t::build_removed_snaps (that gets rid of intersect int...
- 09:39 AM Backport #21341 (In Progress): luminous: mon/OSDMonitor: deleting pool while pgs are being create...
- 09:37 AM Backport #21341 (Resolved): luminous: mon/OSDMonitor: deleting pool while pgs are being created l...
- https://github.com/ceph/ceph/pull/17634
- 09:38 AM Backport #21343 (Resolved): luminous: DNS SRV default service name not used anymore
- https://github.com/ceph/ceph/pull/17863
- 08:17 AM Bug #21338 (Resolved): There is a big risk in function bufferlist::claim_prepend()
- Recently i found a design flaw in the study of the bufferlist. There is a big risk if we call buffer::list::claim_pre...
- 08:10 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- [root@ceph241 hw]# ceph-bluestore-tool --path /var/lib/ceph/osd/ceph-1 fsck
action fsck
2017-09-11 15:37:35.698119 ... - 04:06 AM Bug #18749: OSD: allow EC PGs to do recovery below min_size
- https://github.com/ceph/ceph/pull/17619
Greg Farnum, would you mind taking a look?
09/10/2017
- 07:17 PM Bug #21309 (Pending Backport): mon/OSDMonitor: deleting pool while pgs are being created leads to...
- 07:15 PM Bug #20924: osd: leaked Session on osd.7
- /a/sage-2017-09-10_02:50:18-rados-wip-sage-testing-2017-09-08-1434-distro-basic-smithi/1615133
- 06:58 PM Bug #21180 (Resolved): Bluestore throttler causes down OSD
- Pretty sure this was #21171, fixed merged to master and luminous, will be in 12.2.1.
- 06:57 PM Bug #21246 (Resolved): bluestore: hang while replaying deferred ios from journal
- Pretty sure this was #21171. Fix is merged to master and luminous branch, will be in v12.2.1.
- 06:57 PM Backport #21325 (Resolved): luminous: bluestore: aio submission deadlock
- 06:57 PM Bug #21171 (Resolved): bluestore: aio submission deadlock
- 12:41 AM Bug #21331: pg recovery priority inversion
- ...
09/09/2017
- 08:38 PM Bug #21314: Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- I also tried the workaround in http://tracker.ceph.com/issues/21180 by adding these to ceph.conf but no luck:
<pre... - 07:19 PM Bug #21314: Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- After a few crashes the OSDs become permanently lost, consistently displaying errors like this upon startup:...
- 05:31 PM Bug #21314: Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- I've applied the changes in the Git pull request referenced in that issue and the issue still persists:...
- 05:51 AM Bug #21314: Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- Hmm, I found another log file and came across this:...
- 07:42 PM Bug #21331: pg recovery priority inversion
- Actually, this isn't quite right.
The real problem is that the *primary* has an ancient last_complete, because it ... - 06:53 PM Bug #21331: pg recovery priority inversion
- it looks lke peer_last_commit_ondisk for osd.26 isn't getting updated since it is not in acting (it's backfill target...
- 06:21 PM Bug #21331 (Resolved): pg recovery priority inversion
- ...
- 08:45 AM Bug #21303: rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- the gdb info maybe helpful.It return null when rocsdb read metadata from the sst file
(gdb) n
rocksdb::ReadBlockC... - 04:08 AM Bug #21204 (Pending Backport): DNS SRV default service name not used anymore
09/08/2017
- 08:21 PM Backport #21325 (In Progress): luminous: bluestore: aio submission deadlock
- 08:20 PM Backport #21325 (Resolved): luminous: bluestore: aio submission deadlock
- https://github.com/ceph/ceph/pull/17601
- 08:18 PM Bug #21314: Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- There are no log entries regarding failed heartbeat checks on the failing OSDs, only on the other OSDs witnessing the...
- 07:37 PM Bug #21314 (Duplicate): Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- It is hard to tell because the lines preceding the snippet are missing, but I'm pretty sure this is a dup of #21171, ...
- 06:22 PM Bug #21314: Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- ...
- 03:44 PM Bug #21314 (Duplicate): Ceph OSDs crashing in BlueStore::queue_transactions() using EC
- Log is attached. 3 of my 4 OSDs have crashed in a similar manner at different times. I'm running Ceph on a single nod...
- 06:37 PM Bug #21250 (Resolved): os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnode.extents.empty())
- 06:36 PM Backport #21276 (Resolved): luminous: os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnod...
- 03:48 PM Backport #21276: luminous: os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnode.extents.e...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/17562
merged - 05:51 PM Bug #21123 (Resolved): osd/PrimaryLogPG: sparse read won't trigger repair correctly
- 05:50 PM Bug #21162 (Resolved): 'osd crush rule rename' not idempotent
- 05:50 PM Bug #21207 (Resolved): bluestore: asyn cdeferred_try_submit deadlock
- 05:13 PM Bug #19605 (Resolved): OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_queue.front() == repop)
- 05:12 PM Bug #20888 (Resolved): "Health check update" log spam
- 03:57 PM Backport #21133 (Resolved): luminous: osd/PrimaryLogPG: sparse read won't trigger repair correctly
- 03:56 PM Backport #21234 (Resolved): luminous: bluestore: asyn cdeferred_try_submit deadlock
- 03:56 PM Backport #21182 (Resolved): luminous: 'osd crush rule rename' not idempotent
- 03:41 PM Bug #20370: leaked MOSDOp via PrimaryLogPG::_copy_some and PrimaryLogPG::do_proxy_write
- /a/yuriw-2017-09-07_19:30:56-rados-wip-yuri-testing4-2017-09-07-1811-distro-basic-smithi/1607597
- 02:42 PM Backport #21308: jewel: pre-luminous: aio_read returns erroneous data when rados_osd_op_timeout i...
- Nathan, thanks for creating this ticket!
- 08:16 AM Backport #21308 (In Progress): jewel: pre-luminous: aio_read returns erroneous data when rados_os...
- 08:15 AM Backport #21308 (Resolved): jewel: pre-luminous: aio_read returns erroneous data when rados_osd_o...
- https://github.com/ceph/ceph/pull/17594
- 02:26 PM Backport #21242 (Resolved): luminous: OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_queue...
- 02:25 PM Backport #21240 (Resolved): luminous: "Health check update" log spam
- 02:24 PM Backport #21238 (Resolved): luminous: test_health_warnings.sh can fail
- 12:20 PM Bug #21293 (Resolved): bluestore: spanning blob doesn't match expected ref_map
- 12:18 PM Bug #21171 (Pending Backport): bluestore: aio submission deadlock
- https://github.com/ceph/ceph/pull/17601 is teh backport
- 12:05 PM Bug #21309 (Fix Under Review): mon/OSDMonitor: deleting pool while pgs are being created leads to...
- https://github.com/ceph/ceph/pull/17600
- 11:56 AM Bug #21309 (In Progress): mon/OSDMonitor: deleting pool while pgs are being created leads to asse...
- 11:55 AM Bug #21309 (Resolved): mon/OSDMonitor: deleting pool while pgs are being created leads to assert(...
- ceph version 13.0.0-429-gbc5fe2e (bc5fe2e9099dbb560c2153d3ac85f38b46593a77) mimic (dev)
Easily reproducible on a v... - 08:14 AM Backport #21307 (Resolved): luminous: Client client.admin marked osd.2 out, after it was down for...
- https://github.com/ceph/ceph/pull/17862
- 08:14 AM Bug #20616 (Pending Backport): pre-luminous: aio_read returns erroneous data when rados_osd_op_ti...
- Fixed in Infernalis by https://github.com/ceph/ceph/commit/64bca33ae76646879e6801c45e6d91852e488f8b
Needs backport... - 07:32 AM Bug #20616 (Fix Under Review): pre-luminous: aio_read returns erroneous data when rados_osd_op_ti...
- this only happens if "rados_osd_op_timeout > 0", where the rx_buffer optimization is disabled, due to #9582. in that ...
- 06:04 AM Bug #21303 (Resolved): rocksdb get a error: "Compaction error: Corruption: block checksum mismatch"
- ceph --version
ceph version 12.1.0.5 (27f32562975c5fd3b785a124c818599c677b3f67) luminous (dev)
osd log:
2017-09-...
09/07/2017
- 09:23 PM Bug #21249 (Pending Backport): Client client.admin marked osd.2 out, after it was down for 150462...
- 08:47 PM Bug #21171: bluestore: aio submission deadlock
- There wsa also an aio submission bug that dropped ios on the floor. it was consistently reproducible with...
- 06:42 PM Bug #20910 (In Progress): spurious MON_DOWN, apparently slow/laggy mon
- Ok, this is still happening.. and it correlated with (1) bluestore and (2) bluestore fsck on mount, which spews an un...
- 01:57 AM Bug #20910: spurious MON_DOWN, apparently slow/laggy mon
- *master PR for backport*: https://github.com/ceph/ceph/pull/17505
- 01:29 PM Bug #21293: bluestore: spanning blob doesn't match expected ref_map
- ...
- 01:29 PM Bug #21293 (Fix Under Review): bluestore: spanning blob doesn't match expected ref_map
- https://github.com/ceph/ceph/pull/17569
- 01:11 PM Bug #21293 (Resolved): bluestore: spanning blob doesn't match expected ref_map
- ...
- 01:02 PM Backport #21283 (In Progress): luminous: spurious MON_DOWN, apparently slow/laggy mon
- 07:36 AM Backport #21283 (Resolved): luminous: spurious MON_DOWN, apparently slow/laggy mon
- https://github.com/ceph/ceph/pull/17564
- 01:00 PM Backport #21276 (In Progress): luminous: os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->f...
- 07:35 AM Backport #21276 (Resolved): luminous: os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnod...
- https://github.com/ceph/ceph/pull/17562
- 10:49 AM Bug #20616: pre-luminous: aio_read returns erroneous data when rados_osd_op_timeout is set but no...
- i am able to reproduce this issue with the last jewel, but not master.
reverting 126d0b30e990519b8f845f99ba893fdcd... - 09:01 AM Bug #21287: 1 PG down, OSD fails with "FAILED assert(i->prior_version == last || i->is_error())"
- btw down pg is 1.1735.
Starting OSD 381 crashes 65, 133 and 118. Stoping 65 enables to start remaining OSDs, start... - 08:14 AM Bug #21287 (Duplicate): 1 PG down, OSD fails with "FAILED assert(i->prior_version == last || i->i...
- One PG went down for me during large rebalance (I added racks to OSD placement, almost all data had to be shuffled). ...
- 08:16 AM Bug #21180: Bluestore throttler causes down OSD
- pool used for this workload is blocked by down PG (#21287), but I'll try to replicate on same cluster with newly crea...
- 05:27 AM Bug #21204 (Fix Under Review): DNS SRV default service name not used anymore
- https://github.com/ceph/ceph/pull/17539
- 02:44 AM Bug #21258: "ceph df"'s MAX AVAIL is not correct
- Josh Durgin wrote:
> What is your crushmap and device sizes? It looks like you may have different roots, hence diffe... - 01:31 AM Bug #21262: cephfs ec data pool, many osds marked down
- yes. the log not only about one issue.totally issue like blow:
1. slow request, osd marked down, osd op suicide ca...
09/06/2017
- 09:03 PM Bug #20910 (Pending Backport): spurious MON_DOWN, apparently slow/laggy mon
- 09:02 PM Bug #20910 (Resolved): spurious MON_DOWN, apparently slow/laggy mon
- the problem is that bluestore logs so freaking much at debug bluestore = 30 that the mon gets all laggy.
- 08:52 PM Bug #21250 (Pending Backport): os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnode.exten...
- 05:03 PM Bug #21249 (Fix Under Review): Client client.admin marked osd.2 out, after it was down for 150462...
- https://github.com/ceph/ceph/pull/17525
- 04:35 PM Bug #21262 (Need More Info): cephfs ec data pool, many osds marked down
- 03:44 PM Bug #21262: cephfs ec data pool, many osds marked down
- You're hitting a variety of issues there - some suggesting on-disk corruption, the unexpected error indicating a like...
- 02:26 PM Bug #21262: cephfs ec data pool, many osds marked down
- relationed error
ceph-osd.22.log:/home/jenkins-build/build/workspace/ceph-build/ARCH/x86_64/AVAILABLE_ARCH/x86_64/AV... - 02:16 PM Bug #21262 (Need More Info): cephfs ec data pool, many osds marked down
- cephfs ec data pool, many osds marked down
slow request and get flow blocked, deal op blocked and etc.
- 04:34 PM Bug #21180 (Need More Info): Bluestore throttler causes down OSD
- 04:34 PM Bug #21180: Bluestore throttler causes down OSD
- Can you try setting bluestore_deferred_throttle_bytes = 0 along with bluestore_throttle_bytes = 0 and see if that res...
- 04:32 PM Bug #21246: bluestore: hang while replaying deferred ios from journal
- This looks like it might be the same as #21171, or one of the related bugs I am currently working on. As soon as I h...
- 03:18 PM Bug #21258 (Fix Under Review): "ceph df"'s MAX AVAIL is not correct
- Ah I see your PR now: https://github.com/ceph/ceph/pull/17513
- 03:16 PM Bug #21258: "ceph df"'s MAX AVAIL is not correct
- What is your crushmap and device sizes? It looks like you may have different roots, hence different space available i...
- 03:45 AM Bug #21258 (Closed): "ceph df"'s MAX AVAIL is not correct
- ...
- 03:18 PM Bug #21263: when disk error happens, osd reports assertion failure without any error information
- Will fix it in this PR:
https://github.com/ceph/ceph/pull/17522 - 02:38 PM Bug #21263 (Resolved): when disk error happens, osd reports assertion failure without any error i...
- I used fio+librbd to test one osd(bluestore), which built in an NVME SSD. After I plug-out this SSD, osd reports asse...
- 11:40 AM Bug #21143: bad RESETSESSION between OSDs?
- @yuri, this PR is not merged. or i misunderstand your comment here?
- 07:44 AM Bug #21243: incorrect erasure-code space in command ceph df
- https://github.com/ceph/ceph/pull/17513
- 05:56 AM Feature #21198: Monitors don't handle incomplete network splits
- the same case:
https://marc.info/?l=ceph-devel&w=2&r=1&s=ceph-mon+leader+election+problem&q=b
09/05/2017
- 08:49 PM Bug #20041 (Resolved): ceph-osd: PGs getting stuck in scrub state, stalling RBD
- 08:49 PM Backport #20780 (Resolved): jewel: ceph-osd: PGs getting stuck in scrub state, stalling RBD
- 08:47 PM Bug #20464 (Resolved): cache tier osd memory high memory consumption
- 08:47 PM Backport #20511 (Resolved): jewel: cache tier osd memory high memory consumption
- 08:46 PM Bug #20375 (Resolved): osd: omap threadpool heartbeat is only reset every 100 values
- 08:46 PM Backport #20492 (Resolved): jewel: osd: omap threadpool heartbeat is only reset every 100 values
- 07:02 PM Bug #21250 (Fix Under Review): os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnode.exten...
- https://github.com/ceph/ceph/pull/17503
- 06:53 PM Bug #21250: os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnode.extents.empty())
- looks like two concurrent threads trying to compact_log_async:...
- 06:51 PM Bug #21250 (Resolved): os/bluestore/BlueFS.cc: 1255: FAILED assert(!log_file->fnode.extents.empty())
- ...
- 04:49 PM Bug #21249 (Resolved): Client client.admin marked osd.2 out, after it was down for 1504627577 sec...
- ...
- 03:30 PM Bug #20843 (Resolved): assert(i->prior_version == last) when a MODIFY entry follows an ERROR entry
- 03:30 PM Backport #20930 (Rejected): kraken: assert(i->prior_version == last) when a MODIFY entry follows ...
- Kraken is EOL.
- 03:30 PM Backport #20722 (Rejected): kraken: rados ls on pool with no access returns no error
- Kraken is EOL.
- 03:29 PM Backport #20493 (Rejected): kraken: osd: omap threadpool heartbeat is only reset every 100 values
- Kraken is EOL.
- 03:21 PM Backport #21242 (In Progress): luminous: OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_qu...
- 09:10 AM Backport #21242 (Resolved): luminous: OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_queue...
- https://github.com/ceph/ceph/pull/17501
- 03:20 PM Backport #21240 (In Progress): luminous: "Health check update" log spam
- 09:09 AM Backport #21240 (Resolved): luminous: "Health check update" log spam
- https://github.com/ceph/ceph/pull/17500
- 03:18 PM Backport #21238 (In Progress): luminous: test_health_warnings.sh can fail
- 09:09 AM Backport #21238 (Resolved): luminous: test_health_warnings.sh can fail
- https://github.com/ceph/ceph/pull/17498
- 03:15 PM Backport #21236 (In Progress): luminous: build_initial_pg_history doesn't update up/acting/etc
- 09:09 AM Backport #21236 (Resolved): luminous: build_initial_pg_history doesn't update up/acting/etc
- https://github.com/ceph/ceph/pull/17496
https://github.com/ceph/ceph/pull/17622 - 03:13 PM Backport #21235 (In Progress): luminous: thrashosds read error injection doesn't take live_osds i...
- 09:09 AM Backport #21235 (Resolved): luminous: thrashosds read error injection doesn't take live_osds into...
- https://github.com/ceph/ceph/pull/17495
- 03:12 PM Backport #21234 (In Progress): luminous: bluestore: asyn cdeferred_try_submit deadlock
- 09:09 AM Backport #21234 (Resolved): luminous: bluestore: asyn cdeferred_try_submit deadlock
- https://github.com/ceph/ceph/pull/17494
- 01:02 PM Bug #21243: incorrect erasure-code space in command ceph df
- not only ISA plugin, It's common problem....
- 01:00 PM Bug #21243: incorrect erasure-code space in command ceph df
- ...
- 11:09 AM Bug #21243 (Resolved): incorrect erasure-code space in command ceph df
ceph osd erasure-code-profile set ISA plugin=isa k=2 m=2 crush-failure-domain=host crush-device-c...- 12:56 PM Bug #21246 (Resolved): bluestore: hang while replaying deferred ios from journal
- Running ceph-osd-11.2.0-0.el7.x86_64 from ceph-stable's CentOS repository, I hit the following problem. The cluster (...
- 10:22 AM Bug #21180: Bluestore throttler causes down OSD
- just an update - sometimes even with bluestore_throttle_bytes set to 0 I get down OSDs, but it is much more rare and ...
- 09:51 AM Backport #21182 (In Progress): luminous: 'osd crush rule rename' not idempotent
- 09:39 AM Backport #21133 (In Progress): luminous: osd/PrimaryLogPG: sparse read won't trigger repair corre...
- 09:38 AM Backport #21132 (Resolved): luminous: qa/standalone/scrub/osd-scrub-repair.sh timeout
- 09:09 AM Backport #21239 (Resolved): jewel: test_health_warnings.sh can fail
- https://github.com/ceph/ceph/pull/20289
09/04/2017
- 08:36 PM Bug #20785 (Resolved): osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools().count(pgid.pool...
- 01:43 PM Bug #20785: osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools().count(pgid.pool()))
- thanks Joao, i am commenting on https://github.com/ceph/ceph/pull/17191 so it references https://github.com/ceph/ceph...
- 12:57 PM Bug #20785: osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools().count(pgid.pool()))
- doh. I missed the needs-backport tag on the pr :(
- 12:14 PM Bug #20785: osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools().count(pgid.pool()))
- Joao, I changed status to "Pending Backport" but the PR is also has the "needs-backport" label, which is perhaps enou...
- 12:13 PM Bug #20785 (Pending Backport): osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools().count(p...
- 11:19 AM Bug #20785: osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools().count(pgid.pool()))
- I may be wrong, but it looks like the commit fixing this is only present in current master. I was under the impressio...
- 04:15 PM Bug #21227 (New): [osd]default mkfs.xfs option may make some problem
- the default mkfs.xfs osd with -i size 2048
xfs=[
# xfs insists on not overwriting previous fs; even if... - 10:39 AM Bug #21171: bluestore: aio submission deadlock
- Sage, is there an identifiable behavior when this happens? Do the osds die, or is IO simply forever blocked?
- 09:33 AM Backport #20781 (Rejected): kraken: ceph-osd: PGs getting stuck in scrub state, stalling RBD
- Kraken is EOL.
- 06:46 AM Bug #21207 (Pending Backport): bluestore: asyn cdeferred_try_submit deadlock
09/02/2017
- 06:36 PM Bug #20888 (Pending Backport): "Health check update" log spam
- 06:35 PM Bug #21206 (Pending Backport): thrashosds read error injection doesn't take live_osds into account
- 06:34 PM Bug #21203 (Pending Backport): build_initial_pg_history doesn't update up/acting/etc
- 04:15 AM Bug #21174: OSD crash: 903: FAILED assert(objiter->second->version > last_divergent_update)
- I've got exactly the same problem with kernel client. But fuse client seems fine with ec pool on cephfs
- 01:04 AM Bug #20981: ./run_seed_to_range.sh errored out
- one more here http://qa-proxy.ceph.com/teuthology/yuriw-2017-09-01_23:34:11-rados-wip-yuri-testing-2017-08-31-2109-di...
09/01/2017
- 09:25 PM Bug #21218 (Resolved): thrash-eio + bluestore (hangs with unfound objects or read_log_and_missing...
- ...
- 02:02 PM Bug #21203: build_initial_pg_history doesn't update up/acting/etc
- https://github.com/ceph/ceph/pull/17423
- 01:30 PM Backport #20512 (Rejected): kraken: cache tier osd memory high memory consumption
- Kraken is EOL.
- 06:53 AM Bug #21211: 12.2.0,cephfs(meta replica 2, data ec 2+1),ceph-osd coredump
- 12.2.0
create cephfs
meta pool: model : replica 2
data pool: model : ec 2+1
ceph-osd coredump after r... - 06:49 AM Bug #21211 (Need More Info): 12.2.0,cephfs(meta replica 2, data ec 2+1),ceph-osd coredump
- ceph version 12.2.0 (32ce2a3ae5239ee33d6150705cdb24d43bab910c) luminous (rc)
1: (()+0xa23b21) [0x7fe4a148bb21]
2...
08/31/2017
- 09:38 PM Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- Hi
My institute has a large cluster running Kraken 11.2.1-0 and using EC 8+3 and believe we have run into this bug... - 08:45 PM Bug #21121 (Pending Backport): test_health_warnings.sh can fail
- 08:44 PM Bug #21207 (Fix Under Review): bluestore: asyn cdeferred_try_submit deadlock
- https://github.com/ceph/ceph/pull/17409
- 08:39 PM Bug #21207 (Resolved): bluestore: asyn cdeferred_try_submit deadlock
- In deferred_aio_finish we may need to requeue pending deferred via a finisher. Currently we reuse finishers[0], but ...
- 06:56 PM Bug #21206 (Fix Under Review): thrashosds read error injection doesn't take live_osds into account
- https://github.com/ceph/ceph/pull/17406
- 06:54 PM Bug #21206 (Resolved): thrashosds read error injection doesn't take live_osds into account
- ...
- 04:31 PM Bug #20981: ./run_seed_to_range.sh errored out
- David, the first dead job to appear was http://pulpito.ceph.com/smithfarm-2017-08-21_19:38:42-rados-wip-jewel-backpor...
- 03:21 AM Bug #20981: ./run_seed_to_range.sh errored out
- Are we sure it isn't http://tracker.ceph.com/issues/20613#note-24 ? Because the dead runs here http://pulpito.ceph.c...
- 03:14 AM Bug #20981: ./run_seed_to_range.sh errored out
- I looked at https://github.com/ceph/ceph/pull/15050 and don't see anything that would cause this issue.
- 04:11 PM Bug #21204 (Resolved): DNS SRV default service name not used anymore
- Hi,
I am in the process of upgrading from Kraken to Luminous.
I am using DNS SRV records to lookup MON servers.
... - 01:56 PM Bug #19605 (Pending Backport): OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_queue.front(...
- 01:52 PM Bug #21203 (Resolved): build_initial_pg_history doesn't update up/acting/etc
- The loop doesn't update up/acting/etc values, which means the result is incorrect when there are multiple intervals s...
- 11:00 AM Bug #20933: All mon nodes down when i use ceph-disk prepare a new osd.
- I think I've hit the similar issue. Occured with 12.1.2 when tried to add host / osd (ceph-deploy osd prepare --dmcry...
- 09:27 AM Feature #21198 (New): Monitors don't handle incomplete network splits
- the network between monitors(the minimum rank and the maximum rank) disconnect, the node of the maximum rank always k...
- 03:30 AM Bug #21194 (New): mon clock skew test is fragile
- The original observed problem is that it failed to detect clock skew in run /a/sage-2017-08-27_02:16:57-rados-wip-sa...
08/30/2017
- 06:10 PM Bug #20981: ./run_seed_to_range.sh errored out
- My money is on https://github.com/ceph/ceph/pull/15050
- 06:07 PM Bug #20981: ./run_seed_to_range.sh errored out
- David, the jewel failure started occurring in the integration branch that included the following PRs: http://tracker....
- 04:56 PM Bug #20981: ./run_seed_to_range.sh errored out
- I reverted https://github.com/ceph/ceph/pull/15947 to see if that would fix it and it did NOT.
- 03:57 PM Backport #21182 (Resolved): luminous: 'osd crush rule rename' not idempotent
- https://github.com/ceph/ceph/pull/17481
- 03:28 PM Bug #21180 (Resolved): Bluestore throttler causes down OSD
- Writing large amount of data to EC RBD pool via NBD causes down OSDs, PGs and drop in traffic due to unhealthy cluste...
- 02:12 PM Bug #21174: OSD crash: 903: FAILED assert(objiter->second->version > last_divergent_update)
- To clarify then: I have not tested this with a replicated cephfs data pool. Only tested with ec data pool as per my 4...
- 01:19 PM Bug #21174: OSD crash: 903: FAILED assert(objiter->second->version > last_divergent_update)
- Martin: just to confirm, you were seeing this crash while you had EC pools involved, and when you do not have any EC ...
- 11:25 AM Bug #21174: OSD crash: 903: FAILED assert(objiter->second->version > last_divergent_update)
- ...
- 06:12 AM Bug #21174 (Rejected): OSD crash: 903: FAILED assert(objiter->second->version > last_divergent_up...
- I've setup a cephfs erasure coded pool on a small cluster consisting of 5 bluestore OSDs.
The pools were created as ... - 01:33 PM Bug #20871 (Fix Under Review): core dump when bluefs's mkdir returns -EEXIST
- 01:33 PM Bug #20871: core dump when bluefs's mkdir returns -EEXIST
- https://github.com/ceph/ceph/pull/17357
08/29/2017
- 09:43 PM Bug #21171 (Fix Under Review): bluestore: aio submission deadlock
- https://github.com/ceph/ceph/pull/17352
- 02:47 PM Bug #21171 (Resolved): bluestore: aio submission deadlock
- - thread a holds deferred_submit_lock, blocks on aio submission (queue is full)
- thread b holds deferred_lock, bloc... - 08:58 PM Bug #21162 (Pending Backport): 'osd crush rule rename' not idempotent
- 10:46 AM Bug #21162 (Fix Under Review): 'osd crush rule rename' not idempotent
- https://github.com/ceph/ceph/pull/17329
- 07:38 PM Documentation #20486 (Resolved): Document how to use bluestore compression
- 04:11 PM Bug #21143: bad RESETSESSION between OSDs?
- Haomai Wang wrote:
> https://github.com/ceph/ceph/pull/16009
>
> this pr gives a brief about reason. it's really ... - 03:08 PM Bug #21092: OSD sporadically starts reading at 100% of ssd bandwidth
- Seems that is side effect of too small value for bluestore_cache_size.
We set it to 50M to reduce osd memory consump... - 07:36 AM Bug #20981: ./run_seed_to_range.sh errored out
- This is occurring in the current jewel branch now too:
https://github.com/ceph/ceph/pull/17317#issuecomment-325580432 - 07:06 AM Backport #16239 (Resolved): 'ceph tell osd.0 flush_pg_stats' fails in rados qa run
- h3. description...
- 03:00 AM Bug #21165 (Can't reproduce): 2 pgs stuck in unknown during thrashing
- ...
08/28/2017
- 10:20 PM Bug #21162 (Resolved): 'osd crush rule rename' not idempotent
- ...
- 06:15 PM Backport #21150: jewel: tests: btrfs copy_clone returns errno 95 (Operation not supported)
- Is this causing job failures? I'm having trouble finding anything indicating this would be fatal without an actual I...
- 08:06 AM Backport #21150 (Resolved): jewel: tests: btrfs copy_clone returns errno 95 (Operation not suppor...
- https://github.com/ceph/ceph/pull/18165
- 01:55 AM Bug #21016 (Resolved): CRUSH crash on bad memory handling
- 01:54 AM Backport #21106 (Resolved): luminous: CRUSH crash on bad memory handling
- https://github.com/ceph/ceph/pull/17214
08/27/2017
- 05:59 PM Bug #21147 (Resolved): Manager daemon x is unresponsive. No standby daemons available
- /a/sage-2017-08-26_20:38:41-rados-luminous-distro-basic-smithi/1567938
The last time I looked this appeared to be ... - 04:04 PM Bug #20924: osd: leaked Session on osd.7
- /a/sage-2017-08-26_20:38:41-rados-luminous-distro-basic-smithi/1568055
- 04:30 AM Bug #21143: bad RESETSESSION between OSDs?
- https://github.com/ceph/ceph/pull/16009
this pr gives a brief about reason. it's really rare, so I don't do it imm... - 02:16 AM Backport #21076 (Resolved): luminous: osd/osd_types.cc: 3574: FAILED assert(lastmap->get_pools()....
- 02:15 AM Backport #21095 (Resolved): osd: leak from osd/PGBackend.cc:136 PGBackend::handle_recovery_delete()
Also available in: Atom