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 <[email protected]> wrote:
>
> But they would only reveal inconsistent PGs during deep-scrub.
_______________________________________________
ceph-users mailing list -- [email protected]
To unsubscribe send an email to [email protected]
