Hi,
I am using ceph version 15.2.7 in 4 node cluster my OSD's is
continuously stopping and even if I start again it stops after some time. I
couldn't find anything from the log.
I have set norecover and nobackfil as soon as I unset norecover OSD starts
to fail.
cluster:
id: b6437922-3edf-11eb-adc2-0cc47a5ec98a
health: HEALTH_ERR
1/6307061 objects unfound (0.000%)
noout,nobackfill,norebalance,norecover,noscrub,nodeep-scrub
flag(s) set
19 osds down
62477 scrub errors
Reduced data availability: 75 pgs inactive, 12 pgs down, 57 pgs
peering, 90 pgs stale
Possible data damage: 1 pg recovery_unfound, 7 pgs inconsistent
Degraded data redundancy: 3090660/12617416 objects degraded
(24.495%), 394 pgs degraded, 399 pgs undersized
5 pgs not deep-scrubbed in time
127 daemons have recently crashed
data:
pools: 4 pools, 833 pgs
objects: 6.31M objects, 23 TiB
usage: 47 TiB used, 244 TiB / 291 TiB avail
pgs: 9.004% pgs not active
3090660/12617416 objects degraded (24.495%)
315034/12617416 objects misplaced (2.497%)
1/6307061 objects unfound (0.000%)
368 active+undersized+degraded
299 active+clean
56 stale+peering
24 stale+active+clean
15 active+recovery_wait
12 active+undersized+remapped
11 active+undersized+degraded+remapped+backfill_wait
11 down
7 active+recovery_wait+degraded
7 active+clean+remapped
5 active+clean+remapped+inconsistent
5 stale+activating+undersized
4 active+recovering+degraded
2 stale+active+recovery_wait+degraded
1 active+recovery_unfound+undersized+degraded+remapped
1 stale+remapped+peering
1 stale+activating
1 stale+down
1 active+remapped+backfill_wait
1 active+undersized+remapped+inconsistent
1
active+undersized+degraded+remapped+inconsistent+backfill_wait
what needs to be done to recover this?
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
