<html><body><div style="font-family: garamond,new york,times,serif; font-size: 12pt; color: #000000"><div><br></div><div><br></div><hr id="zwchr"><blockquote style="border-left:2px solid #1010FF;margin-left:5px;padding-left:5px;color:#000;font-weight:normal;font-style:normal;text-decoration:none;font-family:Helvetica,Arial,sans-serif;font-size:12pt;"><b>From: </b>"Alan Hodgson" <ahodgson@simkin.ca><br><b>To: </b>gluster-users@gluster.org<br><b>Sent: </b>Wednesday, October 28, 2015 11:22:24 PM<br><b>Subject: </b>[Gluster-users] New user, couple of questions (sharding+discard, arbiters, shutting down nodes)<br><div><br></div>I have a couple of 2-node clusters I'm hoping to move from drbd+ocfs2 to <br>glusterfs. I've been testing with 3.7.4 and I have a few questions.<br><div><br></div>1) I gather that 2-node replicas have quorum issues, and if you disable <br>quorum, then they have split-brain issues. Do split-brains happen even if the <br>network link is very reliable - I have point-to-point 10Gbit, and the only <br>clients will be the brick servers? If so would it make more sense to make this <br>a 4-node cluster and use arbiter volumes?<br><div><br></div>2) Sharding looks pretty good, as the volumes will be used exclusively for <br>large VM backing images. I've been testing with 1GB shard sizes and <br>performance seems good. It seems that sharded volumes don't support discard, <br>though (ie. fstrim within VM guests). Is there a timeline on when that might <br>be implemented?. Discard seems to work right on non-sharded volumes, but then <br>heal times seem like they'll be an issue.</blockquote><div><br></div><div>Thanks for the feedback, Alan.</div><div><br></div><div>So 3.7.6 release is just two days away, and therefore it will not be possible to get discard implementation</div><div>in by then. You can expect it to be available for 3.7.7 though (which would be end of Nov).</div><div>Meanwhile, you can track its progress at <a href="https://bugzilla.redhat.com/show_bug.cgi?id=1261841,">https://bugzilla.redhat.com/show_bug.cgi?id=1261841</a>. <br></div><div><br></div><div>-Krutika<br></div><div><br></div><blockquote style="border-left:2px solid #1010FF;margin-left:5px;padding-left:5px;color:#000;font-weight:normal;font-style:normal;text-decoration:none;font-family:Helvetica,Arial,sans-serif;font-size:12pt;"><br><div><br></div>3) Is there operational documentation for maintenance procedures, like how to <br>properly shut down nodes in a way that won't impact clients? What I got from <br>a recent mailing list post suggests something like:<br><div><br></div>killall glusterfs <br>killall glusterfsd <br>systemctl stop glusterd <br><div><br></div>That seems to work in testing, the client VM's stay responsive. Is it safe?<br><div><br></div>Thanks in advance for any advice.<br>_______________________________________________<br>Gluster-users mailing list<br>Gluster-users@gluster.org<br>http://www.gluster.org/mailman/listinfo/gluster-users<br></blockquote><div><br></div></div></body></html>