[ceph-users] Re: Reef: RGW Multisite object fetch limits

2024-05-31 Thread Jayanth Reddy
Correct. Nagle's algorithm has been disabled on RGWs and LBs but not seeing any significant difference, and also looks like RGWs don't support HTTP/2. In addition to this, we're also being affected by [1]. [1] https://tracker.ceph.com/issues/64999 Regards, Jayanth On Thu, May 16, 2024 at 2:40 PM

[ceph-users] Re: rgw mgr module not shipped? (in reef at least)

2024-05-31 Thread kefu chai
On Fri, May 31, 2024 at 10:56 PM Matthew Vernon wrote: > Hi, > Hi Matthew, > > As far as I can tell, the rgw mgr module is not shipped in the published > reef Debian packages (nor, I suspect, the ubuntu ones, but I've not > actually checked). > > Is there a reason why it couldn't just be added

[ceph-users] rgw mgr module not shipped? (in reef at least)

2024-05-31 Thread Matthew Vernon
Hi, As far as I can tell, the rgw mgr module is not shipped in the published reef Debian packages (nor, I suspect, the ubuntu ones, but I've not actually checked). Is there a reason why it couldn't just be added to ceph-mgr-modules-core ? That contains quite a large number of modules already

[ceph-users] Re: How to create custom container that exposes a listening port?

2024-05-31 Thread Robert Sander
On 5/31/24 16:07, Robert Sander wrote: extra_container_args:   - "--publish 8080/tcp" Never mind, in the custom container service specification it's "args", not "extra_container_args". Regards -- Robert Sander Heinlein Consulting GmbH Schwedter Str. 8/9b, 10119 Berlin https://www.heinlein

[ceph-users] How to create custom container that exposes a listening port?

2024-05-31 Thread Robert Sander
Hi, with the custom container service it is possible to deploy other services with the cephadm orchestrator: https://docs.ceph.com/en/reef/cephadm/services/custom-container/ The application inside the container wants to listen to a port (say 8080/tcp). How do I tell podman to publish this port?

[ceph-users] Re: unknown PGs after adding hosts in different subtree

2024-05-31 Thread Eugen Block
Hi, after more testing and investigating I created a tracker issue: https://tracker.ceph.com/issues/66310 My current theory for the inactive/unkown PGs is that the MGR gets overloaded with mon messages. The default for mgr_mon_messages is only 128, the mgr service has taken over more roles