I found some logs says osd.91 is down. I think that should be same for osd.9
I am not sure what will cause the OSD process treated by peers as down.
2018-01-30 06:39:33.767747 7f2402ef9700 1 mon.ubuntuser8@0(leader).log
v424396 check_sub sending message to client.164108 10.1.248.8:0/3388257888
wi
I really not sure why monitor mark the OSD to down state
"Monitor daemon marked osd.9 down, but it is still running"
2018-01-30 16:07 GMT+08:00 blackpiglet J. :
> Guys,
>
> We had set up a five nodes Ceph cluster. Four are OSD servers and the
> other one is MON and MGR.
> Recently, during RGW s
Guys,
We had set up a five nodes Ceph cluster. Four are OSD servers and the other
one is MON and MGR.
Recently, during RGW stability test, RGW default
pool: default.rgw.buckets.data is accidentally written full. As a result,
RGW is stuck. We don't know the exact steps to recover, then we deleted a
