https://tracker.ceph.com/https://tracker.ceph.com/favicon.ico2019-11-13T22:32:04ZCeph RADOS - Bug #42503: There are a lot of OSD downturns on this node. After PG is redistributed, a PG member may cannot be selected.https://tracker.ceph.com/issues/42503?journal_id=1515262019-11-13T22:32:04ZGreg Farnumgfarnum@redhat.com
<ul><li><strong>Status</strong> changed from <i>New</i> to <i>Closed</i></li></ul><p>Yes, sometimes CRUSH selection fails when you have a very small number of choices compared to the number of required selections. Nuking half the OSDs in a host will make this an essentially impossible scenario to handle.</p>
<p>Even if CRUSH could select a node, this in general won't work because if your cluster is anywhere near full, losing half a node will mean you don't have the storage space available to correctly rebalance, since you have to be able to store a full copy of all the data on every host.</p>