Hi Gregory,
Sorry for the delay getting back.
There was no activity at all on those 3 pools. Activity on the fourth
pool was under 1 Mbps of writes.
I think I waited several hours, but I can't recall exactly. One hour at
least is for sure.
Thanks
Eneko
On 11/12/14 19:32, Gregory Farnum wr
Was there any activity against your cluster when you reduced the size
from 3 -> 2? I think maybe it was just taking time to percolate
through the system if nothing else was going on. When you reduced them
to size 1 then data needed to be deleted so everything woke up and
started processing.
-Greg
Hi all,
I fixed the issue with the following commands:
# ceph osd pool set data size 1
(wait some seconds for clean+active state of +64pgs)
# ceph osd pool set data size 2
# ceph osd pool set metadata size 1
(wait some seconds for clean+active state of +64pgs)
# ceph osd pool set metadata size 2