This was commented on recently on ceph-users, but I’ll explain the scenario.
If the single kernel needs to flush rbd blocks to reclaim memory and the OSD process needs memory to handle the flushes, you end up deadlocked. If you run the rbd client in a VM with dedicated memory allocation from the point of view of the host kernel, this won’t happen. David Zafman Senior Developer http://www.inktank.com http://www.redhat.com On Jun 12, 2014, at 6:33 PM, lists+c...@deksai.com wrote: > I remember reading somewhere that the kernel ceph clients (rbd/fs) could > not run on the same host as the OSD. I tried finding where I saw that, > and could only come up with some irc chat logs. > > The issue stated there is that there can be some kind of deadlock. Is > this true, and if so, would you have to run a totally different kernel > in a vm, or would some form of namespacing be enough to avoid it? > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com