Hi all,
my cluster is in WARN state because apparently there are some pgs
unfound. I think that I reached this situation because the metadata
pool, this pool was in default root but without any use because I don't
use cephfs, I only use rbd for VMs. I don't have OSDs in the default
root, they are assigned to different roots depending on its disk type.
My pools have specific crush rules to use the different roots. Again,
all my pools, but not the metadata pool, it was assigned to the default
root.
With this situation I got problems in one OSD (I had to reset it from
scratch) and when I restored the situation I got some pgs unfound
because they where in the faulty OSD and belonged to the metadata pool
with size 1. Because I didn't care of any data in the metadata pool I
created the unfounds pgs again with "ceph pg force_create_pg 1.25".
Finally I set a crush rule to the metadata pool to change its location
and the pgs were created.
But now, the cluster is showing 29 unfound pgs, but without saying what pgs.
How can I recover from this situation? Can I remove metadata pool and
recreate it again?
# ceph status
cluster 72a4a18b-ec5c-454d-9135-04362c97c307
health HEALTH_WARN
recovery 29/2748828 unfound (0.001%)
monmap e13: 5 mons at
{mon1=172.16.64.12:6789/0,mon2=172.16.64.13:6789/0,mon3=172.16.64.16:6789/0,mon4=172.16.64.30:6789/0,mon4=172.16.64.31:6789/0}
election epoch 99672, quorum 0,1,2,3,4 mon1,mon2,mon2,mon3,mon4
mdsmap e35323: 0/0/1 up
osdmap e49648: 38 osds: 38 up, 38 in
pgmap v76150847: 3065 pgs, 21 pools, 10654 GB data, 2684 kobjects
31111 GB used, 25423 GB / 56534 GB avail
29/2748828 unfound (0.001%)
3063 active+clean
2 active+clean+scrubbing
client io 4431 kB/s rd, 15897 kB/s wr, 2385 op/s
# ceph health detail
HEALTH_WARN recovery 29/2748829 unfound (0.001%)
recovery 29/2748829 unfound (0.001%)
My cluster runs hammer 0.94.9
5 Servers with 7 OSDs each on Ubuntu 14.04
5 monitor servers.
Thanks and Best regards,
Xabier
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
