Hey guys,
I'm trying to understand what is happening in my cluster, I see the
number of degraded objects increasing, while all OSD's are still up
and running.
Can someone explain what's happening? I would expect the number of
misplaced objects to increase when ceph's balancing algorithm decides
blocks should be on different OSDs, but I would only expect the
degraded objects to increase when OSD's die??
6/15/23 11:31:25 AM[WRN]Health check update: Degraded data redundancy:
809035/219783315 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:31:20 AM[WRN]Health check update: Degraded data redundancy:
809044/219788544 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:31:15 AM[WRN]Health check update: Degraded data redundancy:
809044/219788616 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:31:10 AM[WRN]Health check update: Degraded data redundancy:
808944/219777540 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:31:05 AM[WRN]Health check update: Degraded data redundancy:
808944/219776271 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:31:00 AM[WRN]Health check update: Degraded data redundancy:
808821/219683475 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:30:55 AM[WRN]Health check update: Degraded data redundancy:
808740/219672240 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
6/15/23 11:30:50 AM[WRN]Health check update: Degraded data redundancy:
808667/219645417 objects degraded (0.368%), 6 pgs degraded, 6 pgs
undersized (PG_DEGRADED)
health:
health: HEALTH_WARN
Degraded data redundancy: 810779/220602543 objects
degraded (0.368%), 6 pgs degraded, 6 pgs undersized
services:
mon: 3 daemons, quorum ceph-mon01,ceph-mon02,ceph-mon03 (age 12h)
mgr: ceph-mon01.vzbglj(active, since 12h), standbys: ceph-mon02.qtuntk
mds: 1/1 daemons up, 2 standby
osd: 118 osds: 118 up (since 12h), 118 in (since 23h); 510 remapped pgs
data:
volumes: 1/1 healthy
pools: 5 pools, 1249 pgs
objects: 44.55M objects, 60 TiB
usage: 118 TiB used, 2.0 PiB / 2.1 PiB avail
pgs: 810779/220602543 objects degraded (0.368%)
39586388/220602543 objects misplaced (17.945%)
739 active+clean
406 active+remapped+backfill_wait
98 active+remapped+backfilling
6 active+undersized+degraded+remapped+backfilling
io:
client: 585 KiB/s rd, 22 MiB/s wr, 357 op/s rd, 1.41k op/s wr
recovery: 150 MiB/s, 82 objects/s
Kind regards,
Angelo Hongens
_______________________________________________
ceph-users mailing list -- [email protected]
To unsubscribe send an email to [email protected]
