<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<div class="moz-cite-prefix">On 11/06/2017 9:23 PM, Atin Mukherjee
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CAGkR8FOSDRkXTKuyAGChHty6ZoCjUuFk76_k7WGnPsarvF=JDw@mail.gmail.com">Until
and unless server side quorum is not enabled that's not correct.
I/O path should be active even though management plane is down. We
can still get this done by one node after another with out
bringing down all glusterd instances at one go but just wanted to
ensure the workaround is safe and clean.</blockquote>
<p>Not quite sure of your wording here but I <br>
</p>
<ul>
<li>brought down all glusterd with "systemctl stop
glusterfs-server.service" on each node</li>
<li>rm
/var/lib/glusterd/peers/de673495-8cb2-4328-ba00-0419357c03d7 on
each node</li>
<li>systemctl start glusterfs-server.service" on each node</li>
</ul>
<p><br>
</p>
<p>Several hundred shards needed to be healed after that, but all
done now with no split-brain. And:</p>
<blockquote>
<p><tt>root@vng:~# gluster peer status</tt><tt><br>
</tt><tt>Number of Peers: 2</tt><tt><br>
</tt><tt><br>
</tt><tt>Hostname: vnh.proxmox.softlog</tt><tt><br>
</tt><tt>Uuid: 9eb54c33-7f79-4a75-bc2b-67111bf3eae7</tt><tt><br>
</tt><tt>State: Peer in Cluster (Connected)</tt><tt><br>
</tt><tt><br>
</tt><tt>Hostname: vnb.proxmox.softlog</tt><tt><br>
</tt><tt>Uuid: 43a1bf8c-3e69-4581-8e16-f2e1462cfc36</tt><tt><br>
</tt><tt>State: Peer in Cluster (Connected)</tt></p>
</blockquote>
<p><br>
</p>
<p>Which is good. Not in a position to test quorum by rebooting a
node right now though :) but I'm going to assume its all good,
probably test next weekend.<br>
</p>
<p>Thanks for all the help, much appreciated.<br>
</p>
<pre class="moz-signature" cols="72">--
Lindsay Mathieson</pre>
</body>
</html>