Can you give me a little pointer on how and where to do the verbose logging? I am really interested in discovery why I am getting the large osdmap message. Maybe it is because of the snapshot being created? -----Original Message----- From: Ilya Dryomov [mailto:idryomov@xxxxxxxxx] Cc: paul.emmerich; ceph-users Subject: Re: "session established", "io error", "session lost, hunting for new mon" solution/fix On Fri, Jul 12, 2019 at 5:38 PM Marc Roos <M.Roos@xxxxxxxxxxxxxxxxx> wrote: > > > Thanks Ilya for explaining. Am I correct to understand from the > link[0] mentioned in the issue, that because eg. I have an unhealthy > state for some time (1 pg on a insignificant pool) I have larger > osdmaps, triggering this issue? Or is just random bad luck? (Just a > bit curious why I have this issue) > > [0] > https://www.mail-archive.com/ceph-users@xxxxxxxxxxxxxx/msg51522.html I'm not sure. I wouldn't expect one unhealthy PG to trigger a large osdmap message. Only verbose logs can tell. Thanks, Ilya _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |