<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
On 11/08/2016 10:53 PM, Gandalf Corvotempesta wrote:<br>
<blockquote
cite="mid:CAJH6TXjMpufJeQ=9NAwYCZLaUMtFb79z2FTK-xvkz=4XOEO-fg@mail.gmail.com"
type="cite">
<p dir="ltr">Il 09 nov 2016 1:23 AM, "Joe Julian" <<a
moz-do-not-send="true" href="mailto:joe@julianfamily.org">joe@julianfamily.org</a>>
ha scritto:<br>
><br>
> Replicas are defined in the order bricks are listed in the
volume create command. So gluster volume create myvol replica 2
server1:/data/brick1 server2:/data/brick1 server3:/data/brick1
server4:/data/brick1 will replicate between server1 and server2
and replicate between server3 and server4.<br>
><br>
> See also <a moz-do-not-send="true"
href="https://joejulian.name/blog/how-to-expand-glusterfs-replicated-clusters-by-one-server/">https://joejulian.name/blog/how-to-expand-glusterfs-replicated-clusters-by-one-server/</a><br>
></p>
<p dir="ltr">i really hope this could be automated in newer
gluster versions<br>
There is almost no sense to make a replica on the same server so
gluster<br>
should automatically move bricks to preserve data consistency
when adding servers.</p>
<p dir="ltr">Ceph does this by moving objects around and you don't
have to add servers in a multiple of replica</p>
</blockquote>
<br>
Yes, and ceph has a metadata server to manage this, which breaks
horribly if you have a cascading failure where your sas expanders
start dropping drives when the throughput reaches the max bandwidth
(not that I've <i>ever</i> had that problem... <sigh>). The
final straw in that failure scenario is that the database could
never converge between all the monitors as the objects were moving
around and eventually all 5 monitors ran out of database space -
losing the object map and all the data.<br>
<br>
I'm not blaming ceph for that failure, but just pointing out that
gluster's lack of a metadata server is part of its design philosophy
which serves a specific engineering requirement that ceph does not
fulfill. Luckily, we have both tools to use where they're each most
appropriate.<br>
<br>
<blockquote
cite="mid:CAJH6TXjMpufJeQ=9NAwYCZLaUMtFb79z2FTK-xvkz=4XOEO-fg@mail.gmail.com"
type="cite">
<p dir="ltr">the rebalance command could be used to rebalance
newly added bricks by preserving replicas in a proper state </p>
</blockquote>
<br>
</body>
</html>