Activity
From 12/24/2018 to 01/22/2019
01/22/2019
- 05:07 PM Bug #37264: scrub warning check incorrectly uses mon scrub interval
- 05:06 PM Bug #19753 (Resolved): Deny reservation if expected backfill size would put us over backfill_full...
- 05:06 PM Bug #24801 (Resolved): PG num_bytes becomes huge
- 04:02 PM Backport #37984 (Resolved): mimic: cli: dump osd-fsid as part of osd find <id>
- 03:35 PM Backport #37984: mimic: cli: dump osd-fsid as part of osd find <id>
- https://github.com/ceph/ceph/pull/26035
- 04:02 PM Backport #37985 (Resolved): luminous: cli: dump osd-fsid as part of osd find <id>
- 03:35 PM Backport #37985: luminous: cli: dump osd-fsid as part of osd find <id>
- https://github.com/ceph/ceph/pull/26036
- 03:55 PM Backport #37993 (In Progress): luminous: ec pool lost data due to snap clone
- 03:50 PM Backport #37992 (In Progress): mimic: ec pool lost data due to snap clone
- 03:47 PM Bug #37980: luminous: osd memery use very high,and missmatch between res and heap stats
- Hi,
Often times this kind of thing is related to transparent huge pages. There definitely seems to be different k... - 02:16 PM Bug #37980: luminous: osd memery use very high,and missmatch between res and heap stats
- > ceph 12.2.1
Are you really running that version, 12.2.1 ? - 03:38 AM Bug #37980: luminous: osd memery use very high,and missmatch between res and heap stats
- I am using bluestore, and my client is rbd with ec datapool.
The cluster is running on Centos 7.0.1406, tcmalloc ver... - 02:54 PM Backport #37995 (In Progress): luminous: Change osd_objectstore default to bluestore
- 02:52 PM Backport #37994 (In Progress): mimic: Change osd_objectstore default to bluestore
- 12:58 PM Backport #37903 (Resolved): luminous: osd: pg log hard limit can cause crash during upgrade
- 12:40 PM Bug #36515 (Resolved): config options: 'services' field is empty for many config options
- 09:38 AM Bug #38000 (Duplicate): The osd shutdown procedure accesses the memory that has been released
- https://tracker.ceph.com/issues/37975
- 03:54 AM Bug #38000: The osd shutdown procedure accesses the memory that has been released
- int OSD::shutdown()
{
store->umount();
delete store; // The cache is destroyed
store = 0;
...
... - 03:52 AM Bug #38000 (Duplicate): The osd shutdown procedure accesses the memory that has been released
- [Switching to thread 2 (Thread 0x7f7314cc8700 (LWP 32025))]
#0 0x00007f73395a842d in __lll_lock_wait () from /lib64... - 09:24 AM Bug #37871: Ceph cannot connect to any monitors if one of them has a DNS resolution problem
- In practical terms, what's the difference between not being able to connect because the host name cannot be resolved,...
- 03:32 AM Bug #37871: Ceph cannot connect to any monitors if one of them has a DNS resolution problem
- i think the unresolvable address(es) is more of a configuration issue. and we should not ignore this. it's quite diff...
01/21/2019
- 10:19 PM Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster
- Sounds like Dan's is behaving as expected, but if there's any more info about Bryan's let us know.
- 11:58 AM Bug #37980: luminous: osd memery use very high,and missmatch between res and heap stats
- And what OS are you using?
- 11:56 AM Bug #37980: luminous: osd memery use very high,and missmatch between res and heap stats
- Are you using FileStore or BlueStore?
- 03:36 AM Bug #37980 (New): luminous: osd memery use very high,and missmatch between res and heap stats
- ceph 12.2.1
3 nodes, 30 osds per node
ec pool:4+2
After running for 2 months,we find some osds memery use very h... - 10:36 AM Backport #37904 (In Progress): mimic: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in Pr...
- 10:05 AM Backport #37905 (In Progress): luminous: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in...
- 09:16 AM Backport #37995 (Rejected): luminous: Change osd_objectstore default to bluestore
- https://github.com/ceph/ceph/pull/26076
- 09:16 AM Backport #37994 (Rejected): mimic: Change osd_objectstore default to bluestore
- https://github.com/ceph/ceph/pull/26075
- 09:15 AM Backport #37993 (Resolved): luminous: ec pool lost data due to snap clone
- https://github.com/ceph/ceph/pull/26078
- 09:15 AM Backport #37992 (Resolved): mimic: ec pool lost data due to snap clone
- https://github.com/ceph/ceph/pull/26077
- 09:14 AM Backport #37985 (Resolved): luminous: cli: dump osd-fsid as part of osd find <id>
- https://github.com/ceph/ceph/pull/26036
- 09:13 AM Backport #37984 (Resolved): mimic: cli: dump osd-fsid as part of osd find <id>
- 02:22 AM Bug #37978 (Duplicate): osd killed by kernel for Segmentation fault
- My env is:
[root@gz-ceph-52-204 ceph]# cat /etc/redhat-release
CentOS Linux release 7.2.1511 (Core)
[root@gz-ceph-...
01/20/2019
- 06:31 AM Bug #37975 (Fix Under Review): assert failure in OSDService::shutdown()
- 05:27 AM Bug #37975: assert failure in OSDService::shutdown()
- the return value was 22, as the mutex being acquired was destroyed already.
- 05:12 AM Bug #37975 (Resolved): assert failure in OSDService::shutdown()
- ...
- 02:38 AM Bug #37593 (Pending Backport): ec pool lost data due to snap clone
01/19/2019
- 04:23 PM Backport #37972 (In Progress): luminous: FreeBSD/Linux integration - monitor map with wrong sa_fa...
- 04:22 PM Backport #37972: luminous: FreeBSD/Linux integration - monitor map with wrong sa_family
- PR: https://github.com/ceph/ceph/pull/26042
- 04:06 PM Backport #37972: luminous: FreeBSD/Linux integration - monitor map with wrong sa_family
- Need to backport https://github.com/ceph/ceph/pull/17615/commits/9099ca599de5238cde917f1e1f933247392de03e
- 04:05 PM Backport #37972 (Resolved): luminous: FreeBSD/Linux integration - monitor map with wrong sa_family
- https://github.com/ceph/ceph/pull/26042
- 09:23 AM Backport #37438 (Resolved): luminous: crushtool: add --reclassify operation to convert legacy cru...
- 02:07 AM Bug #37969 (Can't reproduce): ENOENT on setattrs
- ...
01/18/2019
- 11:04 PM Bug #23145: OSD crashes during recovery of EC pg
- I've generated a log for this at https://www.dropbox.com/s/8zoos5hhvakcpc4/ceph-osd.3.log?dl=0
haven't been able t... - 10:43 PM Bug #37968 (Resolved): maybe_remove_pg_upmaps incorrectly cancels valid pending upmaps
- It appears that OSDMap::maybe_remove_pg_upmaps's sanity checks are overzealous. With some crush rules it is possible ...
- 09:56 PM Backport #37438: luminous: crushtool: add --reclassify operation to convert legacy crush maps to ...
- Mykola Golub wrote:
> https://github.com/ceph/ceph/pull/25307
merged - 08:38 PM Backport #37903: luminous: osd: pg log hard limit can cause crash during upgrade
- Neha Ojha wrote:
> https://github.com/ceph/ceph/pull/25949
merged - 07:22 PM Backport #37903: luminous: osd: pg log hard limit can cause crash during upgrade
- https://github.com/ceph/ceph/pull/25949
- 01:11 PM Backport #37903 (Need More Info): luminous: osd: pg log hard limit can cause crash during upgrade
- Marking "Need More Info" just to make sure backporting team doesn't take it by accident.
- 07:44 PM Bug #37966 (Resolved): cli: dump osd-fsid as part of osd find <id>
- https://github.com/ceph/ceph/pull/26015
- 05:32 PM Bug #37965 (Can't reproduce): rados/upgrade test fails
- recent regression. looking at /a/sage-2019-01-18_06:11:36-rados-wip-sage-testing-2019-01-17-2111-distro-basic-smithi...
- 02:37 PM Bug #24676 (Pending Backport): FreeBSD/Linux integration - monitor map with wrong sa_family
- Richard, i don't think 9099ca5 was ever backported to luminous. if you want to get it fixed sooner in luminous. proba...
- 01:26 PM Bug #36515: config options: 'services' field is empty for many config options
- I think with https://github.com/ceph/ceph/pull/25456 the issue can be resolved. I'm not allowed to do it myself.
- 01:11 PM Backport #37902 (Need More Info): mimic: osd: pg log hard limit can cause crash during upgrade
- Marking "Need More Info" just to make sure backporting team doesn't take it by accident.
- 03:29 AM Bug #19753: Deny reservation if expected backfill size would put us over backfill_full_ratio
- 12:51 AM Bug #36494 (Pending Backport): Change osd_objectstore default to bluestore
01/17/2019
- 03:43 PM Bug #37910: segv during crc of incoming message front
- Putting on shelf in the sake of msgr V2.
Runs on wip-bug-37910 with **client** failures:
* http://pulpito.ceph.co... - 11:41 AM Bug #36741 (Resolved): debian: packaging need to reflect move of /etc/bash_completion.d/radosgw-a...
- 11:40 AM Backport #37274 (Resolved): luminous: debian: packaging need to reflect move of /etc/bash_complet...
01/16/2019
- 02:40 PM Bug #37910: segv during crc of incoming message front
- Hmm, interesting. The same thread 0x7f6ea2dad700 is handling two instances of AsyncConnection: 0x5615360ef000
and th... - 10:32 AM Backport #37806 (Resolved): luminous: OSD logs are not logging slow requests
- 10:15 AM Feature #37935 (Resolved): Add clear-data-digest command to objectstore tool
- There may be a situation where data digest in object info is
inconsistent with that computed from object data, then ... - 12:42 AM Bug #37930 (New): osd/PrimaryLogPG.cc: 11997: FAILED ceph_assert(object_c ontexts.empty())
- @2019-01-15T11:29:05.078 INFO:tasks.ceph.osd.1.smithi055.stderr:2019-01-15 11:29:05.069 7f35017d1700 -1 osd.1 pg_epoc...
01/15/2019
- 09:37 PM Bug #37910: segv during crc of incoming message front
- ...
- 08:34 PM Bug #37910: segv during crc of incoming message front
- ...
- 05:18 PM Bug #37919: osd/ECBackend.cc: 1547: FAILED ceph_assert(!(*m).is_missing(hoid))
- Looks like we are testing with leveldb here, not sure that matters for the purpose of this bug, but we could get rid ...
- 01:14 PM Bug #37919 (Resolved): osd/ECBackend.cc: 1547: FAILED ceph_assert(!(*m).is_missing(hoid))
- ...
- 03:52 PM Bug #36163 (Resolved): mon osdmap cash too small during upgrade to mimic
- 03:51 PM Backport #36506 (Resolved): luminous: mon osdmap cash too small during upgrade to mimic
- 03:35 PM Backport #37343 (Resolved): luminous: Prioritize user specified scrubs
- 03:34 PM Backport #37697 (Resolved): luminous: osd_memory_target: failed assert when options mismatch
- 02:40 PM Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster
- Hrm.. actually, after enabling debug_paxos=10 on the mon leader, I see that there's a hysteresis between 500 and 750:...
- 02:12 PM Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster
- I just updated a cluster from v12.2.8 to 12.2.10.
At the beginning we had:
"oldest_map": 281368,
"newes... - 01:56 PM Bug #22597 (Resolved): "sudo chown -R ceph:ceph /var/lib/ceph/osd/ceph-0'" fails in upgrade test
- 01:56 PM Backport #37288 (Resolved): mimic: "sudo chown -R ceph:ceph /var/lib/ceph/osd/ceph-0'" fails in u...
- 09:14 AM Bug #24531: Mimic MONs have slow/long running ops
- I've seen this on a 13.2.2 cluster after restarting OSDs
- 06:55 AM Backport #37904: mimic: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV1::repl...
- https://github.com/ceph/ceph/pull/25958
- 06:06 AM Documentation #24924 (Resolved): doc: typo in crush-map docs
- 04:07 AM Documentation #24924: doc: typo in crush-map docs
- Don't care one way or another. Go ahead if you want.
- 03:52 AM Documentation #24924: doc: typo in crush-map docs
- Hi Michael,
Thank you for reporting this typo. I opened a PR to correct. Is it ok if I
credit you for this repo... - 05:54 AM Backport #37905: luminous: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV1::r...
- https://github.com/ceph/ceph/pull/25956
01/14/2019
- 11:49 PM Bug #37915 (Can't reproduce): osd: Segmentation fault in OpRequest::_unregistered
- ...
- 03:06 PM Bug #37911 (Can't reproduce): osd dequeue misorder
- ...
- 01:25 PM Bug #37910 (Resolved): segv during crc of incoming message front
- ...
- 01:21 PM Feature #36474 (Resolved): Add support for osd_delete_sleep configuration value
- 01:21 PM Backport #36729 (Resolved): mimic: Add support for osd_delete_sleep configuration value
- 10:43 AM Backport #37905 (Resolved): luminous: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in Pr...
- https://github.com/ceph/ceph/pull/25956
- 10:43 AM Backport #37904 (Resolved): mimic: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in Proto...
- https://github.com/ceph/ceph/pull/25958
- 10:42 AM Backport #37903 (Resolved): luminous: osd: pg log hard limit can cause crash during upgrade
- https://github.com/ceph/ceph/pull/25949
- 10:42 AM Backport #37902 (Resolved): mimic: osd: pg log hard limit can cause crash during upgrade
- https://github.com/ceph/ceph/pull/26206
01/13/2019
- 03:46 AM Bug #37886: Adding back the IOPS line for client and recovery IO in cluster logs
- I did some search in the code and testing with vstart cluster and we need to bring back this commit.
https://github... - 03:37 AM Bug #37886 (Resolved): Adding back the IOPS line for client and recovery IO in cluster logs
- In luminous cluster logs, client and recovery IOPS log lines were removed it used to help a lot in RCA. These logs we...
- 01:50 AM Bug #37795 (Resolved): luminous: "'hello_world_cpp' failed" in rados
01/12/2019
- 10:06 PM Bug #37795: luminous: "'hello_world_cpp' failed" in rados
- Brad Hubbard wrote:
> https://github.com/ceph/ceph/pull/25829
merged - 04:26 PM Bug #37868 (Resolved): qa/standalone/mon/mon-handle-forward.sh failure
- 11:41 AM Bug #37868 (Fix Under Review): qa/standalone/mon/mon-handle-forward.sh failure
- https://github.com/ceph/ceph/pull/25902
- 11:11 AM Bug #21592: LibRadosCWriteOps.CmpExt got 0 instead of -4095-1
- /a/sage-2019-01-11_13:08:30-rados-wip-sage-testing-2019-01-10-1950-distro-basic-smithi/3447059
01/11/2019
- 06:34 PM Bug #36686: osd: pg log hard limit can cause crash during upgrade
- Nathan, can you please help generate backport tracker tickets for this?
- 04:17 PM Bug #37875 (Duplicate): osdmaps aren't being cleaned up automatically on healthy cluster
- After doing an expansion from ~1,500 OSDs to ~1,900 OSDs on a Luminous 12.2.8 cluster using FileStore, I've noticed t...
- 01:40 PM Backport #37806: luminous: OSD logs are not logging slow requests
- https://github.com/ceph/ceph/pull/25824 merged
- 11:39 AM Bug #37871 (New): Ceph cannot connect to any monitors if one of them has a DNS resolution problem
- My ceph cluster is configured with this:...
01/10/2019
- 10:45 PM Bug #37868 (Resolved): qa/standalone/mon/mon-handle-forward.sh failure
- /a/sage-2019-01-10_15:03:47-rados-wip-sage-testing-2019-01-10-0709-distro-basic-smithi/3442655...
- 10:29 PM Bug #37807 (Resolved): osd: valgrind catches InvalidRead
- 09:34 PM Feature #36737: Allow multi instances of "make tests" on the same machine
- @Kefu FYI
- 06:03 PM Backport #37274: luminous: debian: packaging need to reflect move of /etc/bash_completion.d/rados...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/24997
merged - 04:21 AM Bug #36686: osd: pg log hard limit can cause crash during upgrade
- https://github.com/ceph/ceph/pull/25816
https://github.com/ceph/ceph/pull/25887 - 12:47 AM Cleanup #37852 (New): qa/suites/rados/thrash: review coverage
01/09/2019
- 10:29 PM Bug #37786: test fails in mon/crush_ops.sh
- This does look weird to me as well; we should investigate. I can't offhand think of any way for a bug like that to im...
- 10:29 PM Bug #37777 (Closed): OSD dies on assert triggered by a spicific other OSD joining the cluster
- 10:25 PM Bug #37788 (Closed): ceph osd process run out of memory
- Unfortunately there are a number of known issues with tcmalloc and hugepages. I don't think I've seen it this bad bef...
- 10:21 PM Bug #37808: osd: osdmap cache weak_refs assert during shutdown
- Apparently these are popping up again so we should try and track them down, but note that since https://github.com/ce...
- 10:12 PM Bug #23879: test_mon_osdmap_prune.sh fails
- We aren't hitting this in recent rados runs anymore
- 10:05 PM Bug #37797 (Resolved): radosbench tests hit ENOSPC
- https://github.com/ceph/ceph/pull/25801
- 09:41 PM Bug #36686 (Pending Backport): osd: pg log hard limit can cause crash during upgrade
- 09:07 PM Bug #25182: Upmaps forgotten after restarting OSDs
- After upgrading to 13.2.4 this problem went away. I believe this was the change which made it happen:
https://git... - 03:21 PM Bug #37844 (New): OSD medium errors do not generate warning or error
- Hi,
I've been seeing inconsistent pgs for a few times past weeks... - 01:36 PM Bug #37671 (Resolved): race between split and pg create
- 12:46 PM Bug #37840 (New): FAILED assert(0 == "we got a bad state machine event") after upgrade from 13.2....
- Running a 3 node cluster, no issues on two of the hosts, but one of the hosts has osds crashing like this:
--- beg... - 05:59 AM Bug #37807: osd: valgrind catches InvalidRead
- 05:13 AM Backport #37821 (In Progress): mimic: ceph-objectstore-tool export from luminous, import to maste...
- 04:25 AM Backport #37833 (In Progress): luminous: FAILED assert(is_up(osd)) in OSDMap::get_inst(int)
- 04:22 AM Backport #37832 (In Progress): mimic: FAILED assert(is_up(osd)) in OSDMap::get_inst(int)
- 04:14 AM Backport #37815 (In Progress): luminous: workunits/rados/test_health_warnings.sh fails with <9 os...
- 04:11 AM Backport #37814 (In Progress): mimic: workunits/rados/test_health_warnings.sh fails with <9 osds ...
01/08/2019
- 10:32 PM Bug #37795 (In Progress): luminous: "'hello_world_cpp' failed" in rados
- 05:44 AM Bug #37795 (Fix Under Review): luminous: "'hello_world_cpp' failed" in rados
- https://github.com/ceph/ceph/pull/25829
- 12:23 AM Bug #37795: luminous: "'hello_world_cpp' failed" in rados
- Frustratingly difficult to track down...
As suspected "make" in the examples/librados directory has not worked for... - 07:05 PM Bug #36497 (Pending Backport): FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV...
- 01:07 PM Bug #36497: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV1::replace()
- ...
- 04:43 PM Bug #20000: osd assert in shared_cache.hpp: 107: FAILED assert(weak_refs.empty())
- i see a zillion of these in this run
http://pulpito.ceph.com/teuthology-2019-01-05_03:09:02-powercycle-master-dist... - 04:28 PM Backport #37833 (Resolved): luminous: FAILED assert(is_up(osd)) in OSDMap::get_inst(int)
- https://github.com/ceph/ceph/pull/25853
- 04:28 PM Backport #37832 (Resolved): mimic: FAILED assert(is_up(osd)) in OSDMap::get_inst(int)
- https://github.com/ceph/ceph/pull/25852
- 04:26 PM Backport #37821 (Resolved): mimic: ceph-objectstore-tool export from luminous, import to master c...
- https://github.com/ceph/ceph/pull/25856
- 04:25 PM Backport #37815 (Resolved): luminous: workunits/rados/test_health_warnings.sh fails with <9 osds ...
- https://github.com/ceph/ceph/pull/25851
- 04:25 PM Backport #37814 (Resolved): mimic: workunits/rados/test_health_warnings.sh fails with <9 osds down
- https://github.com/ceph/ceph/pull/25850
- 04:22 PM Backport #37690 (In Progress): luminous: ceph-objectstore-tool: Add HashInfo to object dump output
- 04:21 PM Backport #37689 (In Progress): mimic: ceph-objectstore-tool: Add HashInfo to object dump output
- 08:30 AM Bug #6297: ceph osd tell * will break when FD limit reached, messenger should close pipes as nece...
- Patrick Donnelly wrote:
> I suspect this isn't a problem anymore with systemd units allowing us to specify a larger ... - 02:39 AM Bug #37807 (Fix Under Review): osd: valgrind catches InvalidRead
- https://github.com/ceph/ceph/pull/25827
- 02:21 AM Bug #37807 (Resolved): osd: valgrind catches InvalidRead
- ...
- 02:25 AM Bug #37808 (New): osd: osdmap cache weak_refs assert during shutdown
- ...
01/07/2019
- 11:55 PM Backport #36434 (In Progress): luminous: monstore tool rebuild does not generate creating_pgs
- https://github.com/ceph/ceph/pull/25825
- 11:09 PM Backport #37806 (Fix Under Review): luminous: OSD logs are not logging slow requests
- 11:05 PM Backport #37806 (Resolved): luminous: OSD logs are not logging slow requests
- https://github.com/ceph/ceph/pull/25824
- 10:40 PM Fix #5756: ceph: tell {osd,mon}.* hugely slower than cuttlefish
- I think this one can be closed?
- 10:36 PM Bug #6297 (Rejected): ceph osd tell * will break when FD limit reached, messenger should close pi...
- I suspect this isn't a problem anymore with systemd units allowing us to specify a larger number of file descriptors.
- 10:17 PM Bug #37777: OSD dies on assert triggered by a spicific other OSD joining the cluster
- For the record: I can no longer reproduce this crash. I fixed the crashes on osd.27 yesterday by
1. taking down t... - 10:10 PM Bug #37720 (Resolved): Ceph-osd is halt when enable SPDK
- 10:09 PM Bug #37747: slow requests are being show on Luminous version while using bluestore , and cluster ...
- I've moved this into the RADOS tracker for now, but you will probably get more useful help on the ceph-users mailing ...
- 09:31 PM Bug #36497 (Fix Under Review): FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV...
- https://github.com/ceph/ceph/pull/25823
- 08:06 PM Bug #37803 (Duplicate): osd/PGLog.cc: 170: FAILED assert(trim_to <= info.last_complete)
- 01:19 PM Bug #37803 (Duplicate): osd/PGLog.cc: 170: FAILED assert(trim_to <= info.last_complete)
- ...
- 06:01 PM Bug #36686 (Fix Under Review): osd: pg log hard limit can cause crash during upgrade
- 04:08 PM Bug #37804 (Closed): "monmaptool: too many arguments" in perf siute
- Run: http://pulpito.ceph.com/teuthology-2019-01-04_03:57:03-perf-basic-master-distro-basic-smithi/
Jobs: all
Logs: ... - 09:26 AM Bug #37795: luminous: "'hello_world_cpp' failed" in rados
- https://github.com/ceph/ceph/pull/24538 was merged only a couple of months ago so I suspect this has never run succes...
01/06/2019
- 02:45 PM Bug #37798 (Can't reproduce): ceph-objectstore-tool crash from finisher
- ...
- 02:42 PM Bug #37797 (Resolved): radosbench tests hit ENOSPC
- ...
01/04/2019
- 10:51 PM Backport #36506: luminous: mon osdmap cash too small during upgrade to mimic
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25021
merged - 10:49 PM Backport #37343: luminous: Prioritize user specified scrubs
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25514
merged - 10:48 PM Backport #37697: luminous: osd_memory_target: failed assert when options mismatch
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25604
merged - 10:21 PM Bug #37795: luminous: "'hello_world_cpp' failed" in rados
- That's on luminous....
- 10:18 PM Bug #37795 (Resolved): luminous: "'hello_world_cpp' failed" in rados
- Run: http://pulpito.ceph.com/yuriw-2019-01-03_21:34:40-rados-wip-yuri3-testing-2019-01-03-1654-luminous-distro-basic-...
- 09:30 PM Bug #21143 (Duplicate): bad RESETSESSION between OSDs?
- dup of #36612 i think
- 09:29 PM Bug #20439 (Resolved): PG never finishes getting created
- I'm going to guess this reoccurance was actually #37775
- 09:25 PM Bug #37671 (Fix Under Review): race between split and pg create
- https://github.com/ceph/ceph/pull/25795
- 09:21 PM Bug #37671: race between split and pg create
- ah, it's a double-split, 1.3 -> 1.b -> 1.1b...
- 09:10 PM Bug #37671: race between split and pg create
- 1.b and 1.1b existed in the osd
1.3 was imported at an old epoch prior to it splitting into 1.b and 1.1b. - 09:07 AM Bug #36497 (In Progress): FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV1::re...
- 08:58 AM Bug #37788: ceph osd process run out of memory
- sorry about the layout of the post, I am not sure why the text become the picture.
- 08:37 AM Bug #37788 (Closed): ceph osd process run out of memory
- Hello everyone,
We test ceph 13.2.2 in our server using rbd service, we find the osd process restart in runtime ... - 05:09 AM Bug #37786: test fails in mon/crush_ops.sh
- ...
- 03:09 AM Bug #37786 (Can't reproduce): test fails in mon/crush_ops.sh
- ...
- 02:37 AM Bug #37542 (Resolved): nvme partitions aren't mapped back to device
01/03/2019
- 11:14 PM Bug #36497: FAILED ceph_assert(can_write == WriteStatus::NOWRITE) in ProtocolV1::replace()
- /a/sage-2019-01-02_20:26:30-fs-wip-sage-testing-2019-01-02-1155-distro-basic-smithi/3416049
incoming connection...... - 04:21 PM Backport #37288: mimic: "sudo chown -R ceph:ceph /var/lib/ceph/osd/ceph-0'" fails in upgrade test
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25227
merged - 04:11 PM Backport #36729: mimic: Add support for osd_delete_sleep configuration value
- David Zafman wrote:
> https://github.com/ceph/ceph/pull/25507
merged
01/02/2019
- 10:28 PM Bug #36498 (Duplicate): failed to recover before timeout expired due to pg stuck in creating+peering
- We fixed at least one bug with PGs not getting marked as created correctly, so I'm closing this one.
- 10:27 PM Bug #37752 (Duplicate): pool stuck with 'creating' flag set
- 10:03 PM Bug #37752: pool stuck with 'creating' flag set
- Is this a dupe of http://tracker.ceph.com/issues/37775 ?
- 10:21 PM Bug #37764 (Resolved): doc: Fix Create a Cluster url in Running Multiple Clusters
- 10:17 PM Bug #37768 (Duplicate): mon gets stuck op for failing OSDs
- 10:09 PM Bug #37665 (Pending Backport): ceph-objectstore-tool export from luminous, import to master clear...
- 06:45 PM Bug #37393: mimic: osd-backfill-stats.sh fails in rados/standalone/osd.yaml
- /a/yuriw-2018-12-18_16:36:24-rados-wip-yuri-testing-2018-12-13-1649-mimic-distro-basic-smithi/3374258/
- 10:42 AM Bug #37775 (Pending Backport): some pg_created messages not sent to mon
01/01/2019
- 08:31 PM Bug #23145: OSD crashes during recovery of EC pg
- Peter Woodman wrote:
> This time:
> [...]
>
> I'll see what I can do re. debug osd logs.
That is to say, I'm ... - 07:45 PM Bug #23145: OSD crashes during recovery of EC pg
- This time:...
- 07:42 PM Bug #23145: OSD crashes during recovery of EC pg
- Hey, I've hit this once again- this time, though, the disk write cache was disabled, so the back-in-time explanation ...
- 04:04 PM Bug #37776 (Pending Backport): workunits/rados/test_health_warnings.sh fails with <9 osds down
- 03:49 PM Bug #37751 (Resolved): handle_conf_change crash in osd
- 03:12 PM Bug #21557: osd.6 found snap mapper error on pg 2.0 oid 2:0e781f33:::smithi14431805-379 ... :187 ...
- /a/sage-2019-01-01_04:27:00-rados-wip-sage-testing-2018-12-31-1546-distro-basic-smithi/3410885...
- 03:04 PM Bug #20798: LibRadosLockECPP.LockExclusiveDurPP gets EEXIST
- I'm guessing this is teh same......
- 02:59 PM Bug #18749: OSD: allow EC PGs to do recovery below min_size
- /a/sage-2019-01-01_04:27:00-rados-wip-sage-testing-2018-12-31-1546-distro-basic-smithi/3410708
- 04:30 AM Bug #37511 (Resolved): merge target placeholder may get wrong PastIntervals from source
- 04:30 AM Bug #37774 (Resolved): bad op 7
- 02:24 AM Bug #37777 (Closed): OSD dies on assert triggered by a spicific other OSD joining the cluster
- Short description: In a cluster with 44 OSDs, osd.8 will allways assert and die if osd.7 is part of or joins the clus...
12/31/2018
- 05:18 PM Bug #37776 (Fix Under Review): workunits/rados/test_health_warnings.sh fails with <9 osds down
- https://github.com/ceph/ceph/pull/25732
- 05:17 PM Bug #37776 (Resolved): workunits/rados/test_health_warnings.sh fails with <9 osds down
- ...
- 05:05 PM Bug #37775 (Fix Under Review): some pg_created messages not sent to mon
- https://github.com/ceph/ceph/pull/25731
- 04:43 PM Bug #37775: some pg_created messages not sent to mon
- how about,
- if pool CREATING flag is sent, we queue a 'created' message when the pg peers
- osd tracks pending cre... - 04:38 PM Bug #37775 (Resolved): some pg_created messages not sent to mon
- mon doesn't get pg_created for two pgs. CREATING flag is never removed, job fails with a final scrub timeout
/a/s... - 04:56 PM Bug #24601 (Pending Backport): FAILED assert(is_up(osd)) in OSDMap::get_inst(int)
- 03:10 PM Bug #37774 (Fix Under Review): bad op 7
- https://github.com/ceph/ceph/pull/25730
- 02:55 PM Bug #37774: bad op 7
- i am inclined to revert this change unless we guard it with a feature bit.
- 02:53 PM Bug #37774: bad op 7
- osd w/o https://github.com/ceph/ceph/pull/22385 does not understand this op.
- 02:50 PM Bug #37774 (Resolved): bad op 7
- ...
- 01:58 PM Bug #37766 (Fix Under Review): rados_shutdown hang forever in ~objecter()
- https://github.com/ceph/ceph/pull/25714
12/30/2018
- 04:10 PM Bug #37772 (New): unittest_seastar_messenger fails with debug build
- ...
- 02:09 PM Bug #37751: handle_conf_change crash in osd
- we started to guard @handle_conf_change()@ since aad318abc9a680d68aab96b051fb7457c8f7feac.
- 02:06 PM Bug #37751 (Fix Under Review): handle_conf_change crash in osd
- https://github.com/ceph/ceph/pull/25726
12/29/2018
- 04:30 PM Backport #37690 (Need More Info): luminous: ceph-objectstore-tool: Add HashInfo to object dump ou...
- While backporting changes related to tracker 37597, found the following compilation errors :
/home/jenkins-build/b... - 02:19 PM Backport #37689 (Need More Info): mimic: ceph-objectstore-tool: Add HashInfo to object dump output
- While backporting changes related to tracker 37597, getting cbegin not found compilation error :
/home/jenkins-bui...
12/28/2018
- 06:23 PM Backport #37690 (In Progress): luminous: ceph-objectstore-tool: Add HashInfo to object dump output
- 06:17 PM Backport #37689 (In Progress): mimic: ceph-objectstore-tool: Add HashInfo to object dump output
- 03:25 PM Bug #24531: Mimic MONs have slow/long running ops
- I just hit this on a 13.2.1 single-host cluster with 1 mon and 8 OSDs. The log is basically identical to the one Wido...
12/27/2018
- 06:54 PM Bug #37768 (Duplicate): mon gets stuck op for failing OSDs
- @6 slow ops, oldest one blocked for 736706 sec, mon.rofl has slow ops@
I have several slow monitor ops that were t... - 11:16 AM Bug #37747: slow requests are being show on Luminous version while using bluestore , and cluster ...
- Well we do not see any traffic related to this bug , so just updating to reflect current trials
1. we did tried to e... - 08:41 AM Bug #37766 (Resolved): rados_shutdown hang forever in ~objecter()
- we use tbd todo some test over, and shutdown our client, then it hang for a long time, and did't go on ever.
it lo...
12/26/2018
- 05:57 AM Bug #37764 (Fix Under Review): doc: Fix Create a Cluster url in Running Multiple Clusters
- 05:48 AM Bug #37764 (Resolved): doc: Fix Create a Cluster url in Running Multiple Clusters
- http://docs.ceph.com/docs/master/rados/configuration/common/#running-multiple-clusters
- 05:13 AM Feature #36737: Allow multi instances of "make tests" on the same machine
- partial fix: https://github.com/ceph/ceph/pull/25704
we also need to move the venv directories to "./build".
12/24/2018
- 02:25 PM Bug #37752 (Duplicate): pool stuck with 'creating' flag set
- ...
- 02:19 PM Bug #37751 (Resolved): handle_conf_change crash in osd
- ...
- 10:33 AM Bug #37747 (New): slow requests are being show on Luminous version while using bluestore , and cl...
- Hi
we are seeing a regression in luminous blue store compared to filestore jewels version
while the capacity of the...
Also available in: Atom