Hi Nicola, might be https://docs.ceph.com/en/quincy/rados/troubleshooting/troubleshooting-pg/#crush-gives-up-too-soon or https://tracker.ceph.com/issues/57348. Best regards, ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 ________________________________________ From: Nicola Mori <mori@xxxxxxxxxx> Sent: 02 November 2022 18:59:22 To: ceph-users Subject: Missing OSD in up set Dear Ceph users, I have one PG in my cluster that is constantly in active+clean+remapped state. From what I understand there might a problem with the up set: # ceph pg map 3.5e osdmap e23638 pg 3.5e (3.5e) -> up [38,78,55,49,40,39,64,2147483647] acting [38,78,55,49,40,39,64,68] The last OSD of the up set is NONE, and this is the only PG in my cluster with this feature. Since the corresponding OSD in the active set is 68 I tried to put it out of the cluster, but the only result I got is that now the PG is active+undersized+degraded, the up set is still missing one OSD, and no recovery operation for it is ongoing: # ceph pg map 3.5e osdmap e23640 pg 3.5e (3.5e) -> up [38,78,55,49,40,39,64,2147483647] acting [38,78,55,49,40,39,64,2147483647] I found no clue on the web about how to solve this, so I'd need help. Thanks, Nicola _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |