Thanks, I will put this in and see how things go.<br clear="all"><br>Dan<br>
<br><br><div class="gmail_quote">On Mon, Mar 9, 2009 at 9:49 PM, Krishna Srinivas <span dir="ltr"><<a href="mailto:krishna@zresearch.com">krishna@zresearch.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Dan,<br>
<br>
I think ping timeout value is not large enough for you, can you put<br>
"option ping-timeout 50" in client volumes and see if you still get<br>
the error? It is presently 10 secs, if it works fine for you we will<br>
increase the default value in the code.<br>
<br>
Thanks<br>
Krishna<br>
<div><div></div><div class="h5"><br>
On Tue, Mar 10, 2009 at 11:04 AM, Dan Parsons <<a href="mailto:dparsons@nyip.net">dparsons@nyip.net</a>> wrote:<br>
> I just received this error message using rc4:<br>
> 2009-03-09 21:58:16 E [client-protocol.c:505:client_ping_timer_expired]<br>
> distfs03-stripe: ping timer expired! bailing transport<br>
> 2009-03-09 21:58:16 N [client-protocol.c:6607:notify] distfs03-stripe:<br>
> disconnected<br>
> It happened a total of 7 times across my 33 client nodes. It doesn't seem to<br>
> be related to any particular client, but the errors did happen mostly<br>
> (though not always) on the unify-ns server. The gluster servers are under<br>
> pretty heavy network utilization, however it doesn't seem to be near the<br>
> link capacity and in any case, i/o should just block if it's slow to<br>
> respond, correct? Fortunately, gluster is automatically reconnecting after<br>
> the error. I don't remember seeing this in rc2. The only corresponding<br>
> errors in the server logs are simply showing the client disconnecting. I've<br>
> also ruled out any interconnect faults.<br>
> Any suggestions? My configs are below.<br>
> Dan<br>
><br>
> CLIENT CONFIG:<br>
> volume unify-switch-ns<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.51<br>
> option remote-subvolume posix-unify-switch-ns<br>
> end-volume<br>
> #volume distfs01-ns-readahead<br>
> # type performance/read-ahead<br>
> # option page-size 1MB<br>
> # option page-count 8<br>
> # subvolumes distfs01-ns-brick<br>
> #end-volume<br>
> #volume unify-switch-ns<br>
> # type performance/write-behind<br>
> # option block-size 1MB<br>
> # option cache-size 3MB<br>
> # subvolumes distfs01-ns-readahead<br>
> #end-volume<br>
> volume distfs01-unify<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.51<br>
> option remote-subvolume posix-unify<br>
> end-volume<br>
> volume distfs02-unify<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.52<br>
> option remote-subvolume posix-unify<br>
> end-volume<br>
> volume distfs03-unify<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.53<br>
> option remote-subvolume posix-unify<br>
> end-volume<br>
> volume distfs04-unify<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.54<br>
> option remote-subvolume posix-unify<br>
> end-volume<br>
> volume distfs01-stripe<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.51<br>
> option remote-subvolume posix-stripe<br>
> end-volume<br>
> volume distfs02-stripe<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.52<br>
> option remote-subvolume posix-stripe<br>
> end-volume<br>
> volume distfs03-stripe<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.53<br>
> option remote-subvolume posix-stripe<br>
> end-volume<br>
> volume distfs04-stripe<br>
> type protocol/client<br>
> option transport-type tcp<br>
> option remote-host 10.8.101.54<br>
> option remote-subvolume posix-stripe<br>
> end-volume<br>
> volume stripe0<br>
> type cluster/stripe<br>
> option block-size *.jar,*.pin:1MB,*:2MB<br>
> subvolumes distfs01-stripe distfs02-stripe distfs03-stripe distfs04-stripe<br>
> end-volume<br>
> volume dht0<br>
> type cluster/dht<br>
> # option lookup-unhashed yes<br>
> subvolumes distfs01-unify distfs02-unify distfs03-unify distfs04-unify<br>
> end-volume<br>
> volume unify<br>
> type cluster/unify<br>
> option namespace unify-switch-ns<br>
> option self-heal off<br>
> option scheduler switch<br>
> # send *.phr/psq/pnd etc to stripe0, send the rest to hash<br>
> # extensions have to be *.foo* and not simply *.foo or rsync's tmp file<br>
> naming will prevent files from being matched<br>
> option scheduler.switch.case<br>
> *.phr*:stripe0;*.psq*:stripe0;*.pnd*:stripe0;*.psd*:stripe0;*.pin*:stripe0;*.nsi*:stripe0;*.nin*:stripe0;*.nsd*:stripe0;*.nhr*:stripe0;*.nsq*:stripe0;*.tar*:stripe0;*.tar.gz*:stripe0;*.jar*:stripe0;*.img*:stripe0;*.perf*:stripe0;*.tgz*:stripe0;*.fasta*:stripe0;*.huge*:stripe0<br>
> subvolumes stripe0 dht0<br>
> end-volume<br>
> volume ioc<br>
> type performance/io-cache<br>
> subvolumes unify<br>
> option cache-size 3000MB<br>
> option cache-timeout 3600<br>
> end-volume<br>
> volume filter<br>
> type features/filter<br>
> option fixed-uid 0<br>
> option fixed-gid 900<br>
> subvolumes ioc<br>
> end-volume<br>
><br>
><br>
><br>
> SERVER CONFIG:<br>
> volume posix-unify-brick<br>
> type storage/posix<br>
> option directory /distfs-storage-space/glusterfs/unify<br>
> # the below line is here to make the output of 'df' accurate, as both<br>
> volumes are served from the same local drive<br>
> option export-statfs-size off<br>
> end-volume<br>
> volume posix-stripe-brick<br>
> type storage/posix<br>
> option directory /distfs-storage-space/glusterfs/stripe<br>
> end-volume<br>
> volume posix-unify-switch-ns-brick<br>
> type storage/posix<br>
> option directory /distfs-storage-space/glusterfs/unify-switch-ns<br>
> end-volume<br>
> volume posix-unify<br>
> type performance/io-threads<br>
> option thread-count 4<br>
> subvolumes posix-unify-brick<br>
> end-volume<br>
> volume posix-stripe<br>
> type performance/io-threads<br>
> option thread-count 4<br>
> subvolumes posix-stripe-brick<br>
> end-volume<br>
> volume posix-unify-switch-ns<br>
> type performance/io-threads<br>
> option thread-count 2<br>
> subvolumes posix-unify-switch-ns-brick<br>
> end-volume<br>
> volume server<br>
> type protocol/server<br>
> option transport-type tcp<br>
> option auth.addr.posix-unify.allow 10.8.101.*,10.8.15.50<br>
> option auth.addr.posix-stripe.allow 10.8.101.*,10.8.15.50<br>
> option auth.addr.posix-unify-switch-ns.allow 10.8.101.*,10.8.15.50<br>
> subvolumes posix-unify posix-stripe posix-unify-switch-ns<br>
> end-volume<br>
><br>
</div></div>> _______________________________________________<br>
> Gluster-devel mailing list<br>
> <a href="mailto:Gluster-devel@nongnu.org">Gluster-devel@nongnu.org</a><br>
> <a href="http://lists.nongnu.org/mailman/listinfo/gluster-devel" target="_blank">http://lists.nongnu.org/mailman/listinfo/gluster-devel</a><br>
><br>
><br>
</blockquote></div><br>