Hi,
On 22.03.19 17:14, Robert Sander wrote:
> we created a bunch of new OSDs on three new nodes this morning. Now,
> after roughly 6 hours they still are empty and the cluster did not
> rebalance any objects resp. placement groups to them.
A new data point in this story emerged today as we had t
Hi,
we created a bunch of new OSDs on three new nodes this morning. Now,
after roughly 6 hours they still are empty and the cluster did not
rebalance any objects resp. placement groups to them.
The crush rule is the simple one, selecting destination OSDs on
different hosts. All OSDs are up and in
