Wouldn't be better a configuration named (map|unmap)_timeout? Cause we are talking about a map/unmap of a RBD device, not a mount/unmount of a file system.
On Fri, May 8, 2015 at 10:04 AM, Ilya Dryomov <idryo...@gmail.com> wrote: > On Fri, May 8, 2015 at 3:59 PM, Ilya Dryomov <idryo...@gmail.com> wrote: > > On Fri, May 8, 2015 at 1:18 PM, Vandeir Eduardo > > <vandeir.edua...@gmail.com> wrote: > >> This causes an annoying problem with rbd resource agent in pacemaker. > In a > >> situation where pacemaker needs to stop a rbd resource agent on a node > where > >> there is no network connection, the rbd unmap command hangs. This > causes the > >> resource agent stop command to timeout and the node is fenced. > >> > >> On Thu, May 7, 2015 at 4:37 PM, Ilya Dryomov <idryo...@gmail.com> > wrote: > >>> > >>> On Thu, May 7, 2015 at 10:20 PM, Vandeir Eduardo > >>> <vandeir.edua...@gmail.com> wrote: > >>> > Hi, > >>> > > >>> > when issuing rbd unmap command when there is no network connection > with > >>> > mons > >>> > and osds, the command hangs. Isn't there a option to force unmap > even on > >>> > this situation? > >>> > >>> No, but you can Ctrl-C the unmap command and that should do it. In the > >>> dmesg you'll see something like > >>> > >>> rbd: unable to tear down watch request > >>> > >>> and you may have to wait for the cluster to timeout the watch. > > > > We can probably add a --force to rbd unmap. That would require > extending our > > sysfs interface but I don't see any obstacles. Sage? > > On a second thought, we can timeout our wait for a reply to a watch > teardown request with a configurable timeout (mount_timeout). We might > still need --force for more in the future, but for this particular > problem the timeout is a better solution I think. I'll take care of > it. > > Thanks, > > Ilya >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
