As an example, here's the acting and up set of one of the PG's:
*up: 0: 1131: 1382: 303: 1324: 1055: 576: 1067: 1408: 161acting: 0: 721:
1502: 21474836473: 21474836474: 245: 486: 327: 1578: 103*
So obviously there's a lot of backfilling there... but it seems it's not
making any progress.
Mac Wynkoop, Senior Datacenter Engineer
*NetDepot.com:* Cloud Servers; Delivered
Houston | Atlanta | NYC | Colorado Springs
1-844-25-CLOUD Ext 806
On Wed, Oct 21, 2020 at 2:41 PM Mac Wynkoop <mwynkoop(a)netdepot.com> wrote:
We recently did some work on the Ceph cluster, and a
few disks ended up
offline at the same time. There are now 6 PG's that are stuck in a
"remapped" state, and this is all of their recovery states:
*recovery_state: 0: name: Started/Primary/WaitActingChangeenter_time:
2020-10-21 18:48:02.034430comment: waiting for pg acting set to change1:
name: Startedenter_time: 2020-10-21 18:48:01.752957*
Any ideas?
Mac Wynkoop