Ceph

12/03/2019

03:40 PM RADOS Bug #43106 (New): crash in build_incremental_map_msg

Since upgrading from 13.2.6 to 13.2.7 we get this around once per 10 minutes on a cluster with 500 out of 1500 OSDs u...

03:27 PM RADOS Bug #38330: osd/OSD.cc: 1515: abort() in Service::build_incremental_map_msg

https://tracker.ceph.com/issues/38282 was backported to mimic in 13.2.7.
Does this need a backport also ?
(we ha...

11/14/2019

04:44 PM RADOS Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster

I think this is when this started:...

03:46 PM RADOS Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster

I may have found more about what's causing this.
I have a cluster with ~1600 uncleaned maps. ...

10:05 AM RADOS Bug #42810 (New): ceph config rm does not revert debug_mon to default

When we increase the debug_mon level to 10, then rm the setting, the effective log level is stuck at 10 in the ceph-m...

10/17/2019

10:21 AM RADOS Bug #42347: nautilus assert during osd shutdown: FAILED ceph_assert((sharded_in_flight_list.back(...

coredump and log file @ ceph-post-file: a0fcd877-46da-4491-9e58-5ae117cfb92b

09:09 AM RADOS Bug #42347 (New): nautilus assert during osd shutdown: FAILED ceph_assert((sharded_in_flight_list...

Looks like #38377, but that is already fixed in nautilus.
We see this occasionally during OSD shutdown:...

09/23/2019

02:27 PM RADOS Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster

Still ongoing here, with mimic too. On one 13.2.6 cluster we have this, for example:...

09/19/2019

03:42 PM fs Bug #41935: ceph mdss keep on crashing

Looks like the backport of https://tracker.ceph.com/issues/39987 to nautilus was incomplete, it's missing https://git...

09/11/2019

07:56 AM bluestore Bug #38745: spillover that doesn't make sense

@Igor, @Rafal: please ignore. I was confused about the configuration of this cluster. It indeed has 26GB rocksdb's, s...