<html><head><meta http-equiv="Content-Type" content="text/html charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><br class=""><div><blockquote type="cite" class=""><div class="">On Jun 1, 2016, at 1:25 PM, Gandalf Corvotempesta <<a href="mailto:gandalf.corvotempesta@gmail.com" class="">gandalf.corvotempesta@gmail.com</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><p dir="ltr" class="">Il 01 giu 2016 22:06, "Gmail" <<a href="mailto:b.s.mikhael@gmail.com" class="">b.s.mikhael@gmail.com</a>> ha scritto:<br class="">
> stat() on NFS, is just a single stat() from the client to the storage node, then all the storage nodes in the same replica group talk to each other using libgfapi (no FUSE overhead)<br class="">
><br class="">
> conclusion, I’d prefer NFS over FUSE with small files.<br class="">
> drawback, NFS HA is more complicated to setup and maintain than FUSE.<br class=""></p><p dir="ltr" class="">NFS HA with ganesha should be easier than kernel NFS</p><p dir="ltr" class="">Skipping the whole fuse stack should be good also for big files<br class=""></p></div></blockquote>with big files, i don’t notice much difference in performance for NFS over FUSE<br class=""><blockquote type="cite" class=""><div class=""><p dir="ltr" class="">
with nfs replication is made directly by gluster servers with no client involved?<br class=""></p></div></blockquote>correct<br class=""><blockquote type="cite" class=""><p dir="ltr" class="">
In this case would be possibile to split the gluster networks with 10gb used for replication and multiple 1gb bonded for clients.<br class=""></p></blockquote>don’t forget the complication of Ganesha HA setup, pacemaker is pain in the butt.<br class=""><blockquote type="cite" class=""><p dir="ltr" class="">
I can see only advantage for nfs over native gluster</p><p dir="ltr" class="">One question: with no gluster client that always know on which node a single file is located, who is telling nfs where to find the required file? Is nfs totally distributed with no "gateway"/"proxy" or any centralized server? </p>
</blockquote>the NFS client talks to only one NFS server (the one which it mounts), the NFS HA setup is only to failover a virtual IP to another healthy node. so the NFS client will just do 3 minor timeouts then it will do a major timeout, when that happens, the virtual IP failover will be already done.</div><br class=""></body></html>