<div dir="ltr">James,<div><br></div><div style>vrrp works fine, but from what I understand of the Gluster FUSE mount process is that it will read the whole of the rrdns response and keep trying to get the volfile from the others if the first server fails to respond.</div>
<div style><br></div><div style>--</div><div style>Adam</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, May 10, 2013 at 5:53 PM, James <span dir="ltr"><<a href="mailto:purpleidea@gmail.com" target="_blank">purpleidea@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im">On Fri, May 10, 2013 at 6:45 PM, Adam Tygart <<a href="mailto:mozes@k-state.edu">mozes@k-state.edu</a>> wrote:<br>
> Randy,<br>
><br>
> On my compute cluster we use round-robin dns (for HA of the volume<br>
> definition) and mount the GlusterFS volume via the FUSE (native) client. All<br>
> of the I/O would go directly to the nodes, rather than through an<br>
> intermediary (NFS) server.<br>
</div>I've mentioned this once before, but in my opinion, using something<br>
like vrrp (eg: keepalived) is better than using rr-dns. Also it's<br>
cooler.<br>
<span class="HOEnZb"><font color="#888888"><br>
James<br>
</font></span><div class="HOEnZb"><div class="h5"><br>
><br>
> --<br>
> Adam Tygart<br>
> Beocat Sysadmin<br>
> <a href="http://www.beocat.cis.ksu.edu" target="_blank">www.beocat.cis.ksu.edu</a><br>
><br>
><br>
> On Fri, May 10, 2013 at 5:38 PM, Bradley, Randy <<a href="mailto:Randy.Bradley@ars.usda.gov">Randy.Bradley@ars.usda.gov</a>><br>
> wrote:<br>
>><br>
>><br>
>> I've got a 24 node compute cluster. Each node has one extra terabyte<br>
>> drive. It seemed reasonable to install Gluster on each of the compute nodes<br>
>> and the head node. I created a volume from the head node:<br>
>><br>
>> gluster volume create gv1 rep 2 transport tcp compute000:/export/brick1<br>
>> compute001:/export/brick1 compute002:/export/brick1<br>
>> compute003:/export/brick1 compute004:/export/brick1<br>
>> compute005:/export/brick1 compute006:/export/brick1<br>
>> compute007:/export/brick1 compute008:/export/brick1<br>
>> compute009:/export/brick1 compute010:/export/brick1<br>
>> compute011:/export/brick1 compute012:/export/brick1<br>
>> compute013:/export/brick1 compute014:/export/brick1<br>
>> compute015:/export/brick1 compute016:/export/brick1<br>
>> compute017:/export/brick1 compute018:/export/brick1<br>
>> compute019:/export/brick1 compute020:/export/brick1<br>
>> compute021:/export/brick1 compute022:/export/brick1<br>
>> compute023:/export/brick1<br>
>><br>
>> And then I mounted the volume on the head node. So far, so good. Apx. 10<br>
>> TB available.<br>
>><br>
>> Now I would like each compute node to be able to access files on this<br>
>> volume. Would this be done by NFS mount from the head node to the compute<br>
>> nodes or is there a better way?<br>
>><br>
>><br>
>> Thanks,<br>
>><br>
>> Randy<br>
>><br>
>><br>
>><br>
>><br>
>> This electronic message contains information generated by the USDA solely<br>
>> for the intended recipients. Any unauthorized interception of this message<br>
>> or the use or disclosure of the information it contains may violate the law<br>
>> and subject the violator to civil or criminal penalties. If you believe you<br>
>> have received this message in error, please notify the sender and delete the<br>
>> email immediately.<br>
>><br>
>> _______________________________________________<br>
>> Gluster-users mailing list<br>
>> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
>> <a href="http://supercolony.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://supercolony.gluster.org/mailman/listinfo/gluster-users</a><br>
><br>
><br>
><br>
> _______________________________________________<br>
> Gluster-users mailing list<br>
> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
> <a href="http://supercolony.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://supercolony.gluster.org/mailman/listinfo/gluster-users</a><br>
</div></div></blockquote></div><br></div>