On 11/10/21 16:32, Christoph Adomeit wrote:
Thanks Stefan,
i played with bluefs_buffered_io but i think the impact is not great since the nvmes are so fast.
I think buffered IO on increased cpu load while buffered io off increase nvme load. Problem was with both settings.
I am not sure if require-osd-release was run. What do you think ceph osd require-osd-release pacific will do and is there a risk when running the command that the cluster might become unavailable ?
It's part of the upgrade. You *SHOULD* set this when all daemons have
been upgraded, see [1], and [2] when not using cephadm.
From the docs:
"Complete the upgrade by disallowing pre-Pacific OSDs and enabling all
new Pacific-only functionality"
I think all osds are running 16.2.6 anyway and so it would not change anything if i set the force to run Pacific ?
You need to make sure before running that command:
ceph osd versions
and or "ceph versions" to see if all daemons are running 16.2.6.
Not sure where you have upgraded from, but _DO NOT_ convert any OMAP on
the OSDs. See the danger note in [3].
Gr. Stefan
[1]: https://docs.ceph.com/en/latest/releases/pacific/
[2]:
https://docs.ceph.com/en/latest/releases/pacific/#upgrading-non-cephadm-clusters
[3]: https://docs.ceph.com/en/latest/releases/pacific/#v16-2-6-pacific
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
