Hi,
> Den ons 3 juli 2019 kl 09:01 skrev Luk <skidoo@xxxxxxx>:
> Hello,
> I have strange problem with scrubbing.
> When scrubbing starts on PG which belong to default.rgw.buckets.index
> pool, I can see that this OSD is very busy (see attachment), and starts showing many
> slow request, after the scrubbing of this PG stops, slow requests
> stops immediately.
> [root@stor-b02 /var/lib/ceph/osd/ceph-118/current]# du -sh 20.2_*
> 636K 20.2_head
> 0 20.2_TEMP
> [root@stor-b02 /var/lib/ceph/osd/ceph-118/current]# ls -1 -R 20.2_head | wc -l
> 4125
> [root@stor-b02 /var/lib/ceph/osd/ceph-118/current]#
> I think that pool might contain tons of metadata entries and
> non-obvious data for which it takes a while to process.
> But I see similar things on my rgw pools also during scrubs. :-(
this pool is that 'big' :
[root@ceph-mon-01 ~]# rados df | grep -e index -e WR
POOL_NAME USED OBJECTS CLONES COPIES MISSING_ON_PRIMARY UNFOUND DEGRADED RD_OPS RD WR_OPS WR
default.rgw.buckets.index 0B 31763 0 95289 0 0 0 147679875 3.88TiB 8014040021 0B
[root@ceph-mon-01 ~]# ceph df | grep -e index -e N
NAME ID USED %USED MAX AVAIL OBJECTS
default.rgw.buckets.index 20 0B 0 37.0TiB 31763
[root@ceph-mon-01 ~]#
I don't think it should have such big problem during scrubing...
--
Regards
Lukasz
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
