Dear Ceph users,
I'm setting up a cluster, at the moment I have 56 OSDs for a total
available space of 109 TiB, and an erasure coded pool with a total
occupancy of just 90 GB. The autoscale mode for the pool is set to "on",
but I still have just 32 PGs. As far as I understand (admittedly not
that much, I'm a Ceph beginner) the rule of thumb says that 100 PGs per
OSD is the reference, so I would expect that the autoscaler should
increase the PGs count, but that's not the case.
If my expectation is correct then I can't understand whether it's a
config issue, and eventually which config options should I tweak, or
it's expected behavior since e.g. the occupancy is very low and thus PG
are not scaled up.
Any help/hint is really appreciated.
Thanks in advance,
Nicola
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
