<div dir="ltr">Hello,<div><br></div><div>what do you mean by "true" clustering ?</div><div>We can do a Windows Failover cluster (1 virtual ip, 1 virtual name), but this mean using a shared storage like SAN.</div><div><br></div><div>Then it depends on your network topology. If you have multiple geographical sites / datacenter, then DFS-R behave a lot better than Gluster in replicated mode. Users won't notice any latency, </div><div>At the price that replication is async.</div><div><br></div></div><div class="gmail_extra"><br clear="all"><div><div class="gmail_signature">Cordialement,<br>Mathieu CHATEAU<br><a href="http://www.lotp.fr" target="_blank">http://www.lotp.fr</a></div></div>
<br><div class="gmail_quote">2015-08-10 7:26 GMT+02:00 Ira Cooper <span dir="ltr"><<a href="mailto:ira@redhat.com" target="_blank">ira@redhat.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">Mathieu Chateau <<a href="mailto:mathieu.chateau@lotp.fr">mathieu.chateau@lotp.fr</a>> writes:<br>
<br>
> I do have DFS-R in production, that replaced sometimes netapp ones.<br>
> But no similar workload as my current GFS.<br>
><br>
> In active/active, the most common issue is file changed on both side (no<br>
> global lock)<br>
> Will users access same content from linux & windows ?<br>
<br>
</span>If you want to go active/active. I'd recommend Samba + CTDB + Gluster.<br>
<br>
You want true clustering, and a system that can handle the locking etc.<br>
<br>
I'd layer normal DFS to do "namespace" control, and to help with<br>
handling failover, or just use round robin DNS.<br>
<br>
Thanks,<br>
<br>
-Ira<br>
</blockquote></div><br></div>