On Sun, Jul 28, 2013 at 8:58 AM, Marcus Bointon <marcus at synchromedia.co.uk>wrote: > On 28 Jul 2013, at 17:31, Anand Avati <anand.avati at gmail.com> wrote: > > Mounting NFS export from localhost is a recipe for disaster for many other > reasons (including deadlocks under heavy IO). > > > Docs? I'm only doing it because it's the only workable solution I've found > for gluster at all. > Gluster native client performance is too bad, and pointing it non-local > servers implies anti-redundancy (someone else mentioned the same problem > for the same reason on here just recently) and is worse than not using > gluster at all. > If you have a better solution, I'm all ears. > > What is your typical workload, and what kind of tests did you compare native client perf against NFS perf? Avati > it stops gluster before unmounting volumes. This causes the NFS client to > hang waiting for a response from the gluster server (which will never > happen because it's stopped), blocking the reboot, leaving the server > hanging indefinitely. The only way out seems to be to power-cycle the > server. > >> >> How is this supposed to work? Is there some way of scheduling unmounts >> before killing gluster? >> > > Not sure about this - should the init.d shutdown script be de-prioritized > for your runlevel? But then, we are talking about a use case which is > highly non-recommended. > > > I've not experimented with init scripts yet, but I think the unmounts are > done by /etc/init.d/umountfs. > > Marcus > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20130728/8985c257/attachment.html>
