<div dir="ltr">Hi.<br><br><div class="gmail_quote"><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">It's got similar speeds compared to gluster for a few nodes but depends on fiberchannel or some other shared block storage system for redundancy. We immediately discarded it in favor of gluster for this reason. It was also significantly more difficult to get running as it was a kernel patch.<br>
</blockquote><div><br>Are you sure about that? <br><br><br>From Lustre wiki (<a href="http://wiki.lustre.org/index.php?title=Lustre_FAQ">http://wiki.lustre.org/index.php?title=Lustre_FAQ</a>)<br><blockquote style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;" class="gmail_quote">
<h3>Are fibrechannel switches necessary? How does HA shared storage work?</h3><p>Typically, fibrechannel switches are not necessary. Multi-port
shared storage for failover is normally configured to be shared between
two server nodes on a FC-AL. Shared SCSI and future shared SATA devices
will also work.
</p><p>Backend storage is expected to be cache-coherent between
multiple channels reaching the devices. Servers in an OSS failover pair
are normally both active in the file system, and can be configured to
take over partitions for each other in the case of a failure. MDS
failover pairs can also both be active, but only if they serve multiple
separate file systems.
</p></blockquote>
<br>As far a I understand, Lustre is designed with the approach most cluster file systems (except GlusterFS of course :) ), meaning you have master servers that responsible for storage and retrieval of the data, and storage nodes, which do actualy storage.<br>
<br>Regards.<br></div></div></div>