Amudhan, Have you looked at the logs and did you try enabling debug to see why the OSDs are marked down? There should be some reason right? Just focus on the MON and take one node/OSD by enabling debug to see what is happening. https://docs.ceph.com/en/latest/cephadm/operations/. Thanks, Suresh On Sat, Aug 14, 2021, 9:53 AM Amudhan P <amudhan83@xxxxxxxxx> wrote: > Hi, > I am stuck with ceph cluster with multiple PG errors due to multiple OSD > was stopped and starting OSD's manually again didn't help. OSD service > stops again there is no issue with HDD for sure but for some reason, OSD > stops. > > I am using running ceph version 15.2.5 on podman container. > > How do I recover these pg failures? > > can someone help me to recover this or where to look further? > > pgs: 0.360% pgs not active > 124186/5082364 objects degraded (2.443%) > 29899/5082364 objects misplaced (0.588%) > 670 active+clean > 69 active+undersized+remapped > 26 active+undersized+degraded+remapped+backfill_wait > 16 active+undersized+remapped+backfill_wait > 15 active+undersized+degraded+remapped > 13 active+clean+remapped > 9 active+recovery_wait+degraded > 4 active+remapped+backfill_wait > 3 stale+down > 3 active+undersized+remapped+inconsistent > 2 active+recovery_wait+degraded+remapped > 1 active+recovering+degraded+remapped > 1 active+clean+remapped+inconsistent > 1 active+recovering+degraded > _______________________________________________ > ceph-users mailing list -- ceph-users@xxxxxxx > To unsubscribe send an email to ceph-users-leave@xxxxxxx > _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |