We really don't know what the cluster state was. I assume by removing
the fifth host you removed the fullest OSD(s). But again, we only get
a few bits of information, so it's still basically guessing.
What exactly do you mean by "so I thought to run pool repair"? What
exactly did you do?
Zitat von Devender Singh <devender@xxxxxxxxxx>:
Hello Eugen
Thanks for your reply.
ceph osd set nodeep-scrub is not stopping if repairs are running.
Reapir started another set for deepscrub+repair which is not
controlled using this command.
When I started my cluster utilization as 74% and when it finished
now my cluster is showing 43%(surprising figure, does a repair can
shuffle that much? Even my osd’s where between 60-83%) utilized.
Before starting repair I increased pool pg’s manually from 1024 to
2048 but my pool only came down to 84%, so I thought to run pool
repair..
During the repair and high utilization my cluster was crying and
giving SLOW OSD Communication from osd.x to osd.y and many number of
times.
Not sure what was it, how utilization came that much down, If repair
can change thing this much then it should have command to
pause/unpause too.
Regards
Dev
On Jan 25, 2025, at 1:15 AM, Eugen Block <eblock@xxxxxx> wrote:
But they would only reveal inconsistent PGs during deep-scrub.
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
