<div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div class="im"><br>
> I have 3 servers with 7 disks each, is it better to use each<br>
> individual disk as brick (several bricks per server). ?Or to have<br>
> them as a raid volume that presents as a single brick per server?<br>
><br>
> I'm setting them up as a replicated volume across all three servers.<br>
<br>
In our environment (several hundred volumes over several servers that had<br>
several bricks) we were told that a lot of our issues stemmed from the<br>
number of bricks per volume. We are now going to a max of 2 bricks local<br>
to each node, using lvm. We are using 2 instead of 1 because we are<br>
separating for replica pairings.<br>
<br>
-greg<br>
<br>
</div>I'm hoping that someone at Gluster will step forward on this one because<br>
this just doesn't sound correct. I have two servers with 8x2TB drives<br>
each and each one is configured as a brick. I have set up replicated<br>
and distributed so server 0/drive 0 is mirrored to server 1/drive 0 ...<br>
That's 8 bricks per server and I'm having no problems. That way if a<br>
drive goes bad, I replace and re-mirror from/to a single drive. If I<br>
use in-server RAID, I either lose space to raid parity (RAID5/RAID5) or<br>
waste a lot of drive space (RAID-10) before I even get to replicate<br>
across the servers. If I used in-server RAID and lost a RAIDset, I<br>
would have to replicate the entire 16TB volume which would take too<br>
long and be a performance hog. I decided to use replicate for<br>
mirroring and then use distribute to act as striping mechanism to<br>
eliminate these two issues. Up for 18 months without any problems, so<br>
I'm pretty happy.<br>
<br>
I've also see people post on this mailing list that had hundreds of<br>
bricks in a single volume, so I'm pretty sure that works. Can someone<br>
clarify that for us?<br><font class="Apple-style-span" color="#888888"><br></font></blockquote><div><br></div><div>Having 10s of bricks on a server should work fine. In Greg's case, the total number of bricks we running into multiple thousands causing processes to run out of ports < 1024.</div>
<div><br></div><div>Avati</div></div>