Hi,
We have been rebalacing our cluster (CRUSH policy change for cephfs
metadata pool). The rebalancing is done ... but now there are PG
deep-scrubs going on (mostly on the pool that got almost completely
backfilled). We have had the no-(deep)-scrub flags active ... but that
does not prevent new (deep-)scrubs from happening. Also disabling them
completely on the specific pool did not help ... The oldest deep-scrub
was from the 14th of december ...
Is there logic coded somewhere that a PG that got backfilled needs to be
deep-scrubbed after that? I remember this was a thing on filestore (to
check integrity) ... should not be needed anymore with bluestore, right
(CRC checking)?
All this on Mimic 13.2.8
Thanks,
Stefan
P.s. I updated
https://tracker.ceph.com/issues/11202
--
| BIT BV
https://www.bit.nl/ Kamer van Koophandel 09090351
| GPG: 0xD14839C6 +31 318 648 688 / info(a)bit.nl