I think you dont have enough hosts for your ec pool crush rule.
if your failure domain is host, then you need at least ten hosts.
On Wed, Oct 24, 2018 at 9:39 PM Brady Deetz <bde...@gmail.com> wrote:
>
> My cluster (v12.2.8) is currently recovering and I noticed this odd OSD ID in
> ceph health detail:
> "2147483647"
>
> [ceph-admin@admin libr-cluster]$ ceph health detail | grep 2147483647
> pg 50.c3 is stuck undersized for 148638.689866, current state
> active+recovery_wait+undersized+degraded+remapped, last acting
> [275,282,330,25,154,98,239,2147483647,75,49]
> pg 50.d4 is stuck undersized for 148638.649657, current state
> active+recovery_wait+undersized+degraded+remapped, last acting
> [239,275,307,49,184,25,281,2147483647,283,378]
> pg 50.10b is stuck undersized for 148638.666901, current state
> active+undersized+degraded+remapped+backfill_wait, last acting
> [131,192,283,308,169,258,2147483647,75,306,25]
> pg 50.110 is stuck undersized for 148638.684818, current state
> active+recovery_wait+undersized+degraded+remapped, last acting
> [169,377,2147483647,2,274,47,306,192,131,283]
> pg 50.116 is stuck undersized for 148638.703043, current state
> active+recovery_wait+undersized+degraded+remapped, last acting
> [99,283,168,47,71,400,2147483647,108,239,2]
> pg 50.121 is stuck undersized for 148638.700838, current state
> active+undersized+degraded+remapped+backfill_wait, last acting
> [71,2,75,307,286,73,168,2147483647,376,25]
> pg 50.12a is stuck undersized for 145362.808035, current state
> active+undersized+degraded+remapped+backfill_wait, last acting
> [71,378,169,2147483647,192,308,131,108,239,97]
>
>
> [ceph-admin@admin libr-cluster]$ ceph osd metadata 2147483647
> Error ENOENT: osd.2147483647 does not exist
>
> Is this expected? If not, what should I do?
> _______________________________________________
> ceph-users mailing list
> ceph-users@lists.ceph.com
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
