Robin,
Thank you very much for your quick response. It was really helpful.
The issue has been successfully resolved.
The RC:
podman (by default) allows 2048 threads, while (for some reason) Ceph had
8K thread pool size for RGWs. Changing this parameter helps bring the
cluster to a normal state.
On Sat, Feb 10, 2024 at 10:05:02AM -0500, Vladimir Sigunov wrote:
> Hello Community!
> I would appreciate any help/suggestions with the massive RGWs outage we are
> facing.
> The cluster's overall status is acceptable (HEALTH_WARN because of some pgs
> not scrubbed in time), and the cluster is
Hello Community!
I would appreciate any help/suggestions with the massive RGWs outage we are
facing.
The cluster's overall status is acceptable (HEALTH_WARN because of some pgs
not scrubbed in time), and the cluster is operational.
However, all RGWs fail to start with a core dump.
The only issue I
Oh really? That seems rather trivial but alright. :-D
Zitat von Gary Molenkamp :
Just wanted to follow up on this to say that it is now working.
After reviewing the configuration of the new host many times, I did
a hard restart of the active mrg container.
The command to add the new host