Hi Marc,
Thanks for participating. At first I thought this is an incorrect report and maybe I need
to upgrade to for a bugfix.
But I couldn’t find a such a report and I asked here.
When people shared experiences it appears there may be two causes. Unbalanced OSDs or
Storage Amplification.
As far as I understand, this is most likely to be storage amplification. Unbalancing seems
to less relevant since this is a fresh cluster. Or I might be misinterpreting ceph osd df.
https://pastebin.ubuntu.com/p/ZmQZsGYpr7/
<https://pastebin.ubuntu.com/p/7C9zpXYntR/>
So I am trying to figure out the best way to change bluestore_min_alloc_size_hdd. And also
I think pool compression can be a quick solution for the future data writes, but I am not
%100 sure. Any idea is more than welcome.
On 28 Jan 2021, at 12:29, Marc Roos
<Marc(a)f1-outsourcing.eu> wrote:
Hi George,
Sorry for asking maybe I skipped an email. But what eventually caused the
'incorrect' report on available storage.