That problem seems to have cleared up. We are in the middle of a massive rebalancing effort for a 700 OSD, 10PB cluster that is wildly out of whack (because it got too full) and see lots of strange numbers reported occasionally. ________________________________ From: Eugen Block <eblock@xxxxxx> Sent: Thursday, August 25, 2022 2:56 PM To: Wyll Ingersoll <wyllys.ingersoll@xxxxxxxxxxxxxx> Cc: ceph-users@xxxxxxx <ceph-users@xxxxxxx> Subject: Re: backfillfull osd - but it is only at 68% capacity Hi, I’ve seen this many times in older clusters, mostly Nautilus (can’t say much about Octopus or later). Apparently the root cause hasn’t been fixed yet, but it should resolve after the recovery has finished. Zitat von Wyll Ingersoll <wyllys.ingersoll@xxxxxxxxxxxxxx>: > My cluster (ceph pacific) is complaining about one of the OSD being > backfillfull: > > [WRN] OSD_BACKFILLFULL: 1 backfillfull osd(s) > > osd.31 is backfill full > > backfillfull ratios: > > full_ratio 0.95 > > backfillfull_ratio 0.9 > > nearfull_ratio 0.85 > > ceph osd df shows: > > 31 hdd 5.55899 1.00000 5.6 TiB 3.8 TiB 3.7 TiB 411 MiB > 6.7 GiB 1.8 TiB 68.13 0.92 83 up > > So, why does the cluster think that osd.31 is backfillfull if its > only at 68% capacity? > > > _______________________________________________ > 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
 |