On 03/18/2014 11:58 AM, Jeff Darcy wrote:
On Tue, Mar 18, 2014 at 1:42 PM, Greg Waite
I've been playing around with a 2x2 distributed replicated setup with
replicating group 1 having a different brick size than replicating group 2.
I've been running into "out of disk" errors when the smaller replicating
pair disks fill up. I know of the minimum free disk feature which should
prevent this issue. My question is, are there features that allow gluster
to
smartly use different brick sizes so extra space on larger bricks do not go
unused?
It looks like different sized bricks will be a core feature in 3.6
(coming soon).
Correct. In fact, a lot of the logic already exists and is even in the tree.
http://review.gluster.org/#/c/3573/
The trick now is to get that logic integrated into the place where
rebalance calculates the new layout. Until then, you could try running
that script, but I should warn you that it hasn't been looked at for over a
year so you should try it out on a small test volume first to make sure
it's still doing the right thing(s). I'll be glad to help with that.
Another thing you can do is to divide your larger bricks in two - or three,
or whatever's necessary to even things out. This means more ports, more
glusterfsd processes, quite possibly some performance loss as those contend
with one another, but it's something you can do *right now* that's pretty
easy and bullet-proof.
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users
Thanks for the input!
Sorry to go off topic, my gluster experience extends to only my cobbled
together test bed, but how would I go about implementing that? If this
is currently being tested ill be happy to take part in testing it!
--
Greg Waite
System Administrator
Computing Group, JILA
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users
