Just a not, we have seen a pretty significant increase in speed from
this latest 2.03 release. Doing a test read over afr we are seeing
speeds between 200-320 mB a second. (over infiniband, ib-verbs)
This is with direct IO disabled too. Oddly putting performance
translators on the clients made no difference.
We cued up 10 servers to read a single file simultaneously and got about
~30-50 mB a sec from each client, totaling up to ~400 mB a sec on a
single file (read from 2 servers, by 10 servers).
We are really happy with these numbers for a virtual cluster so, most
single drives won't read at those speeds.
Thanks!
-Mic
Hiren Joshi wrote:
-----Original Message-----
From: Stephan von Krawczynski [mailto:[email protected]]
Sent: 09 July 2009 13:50
To: Hiren Joshi
Cc: Liam Slusser; [email protected]
Subject: Re: [Gluster-users] GlusterFS Preformance
On Thu, 9 Jul 2009 09:33:59 +0100
"Hiren Joshi" <[email protected]> wrote:
-----Original Message-----
From: Stephan von Krawczynski [mailto:[email protected]]
Sent: 09 July 2009 09:08
To: Liam Slusser
Cc: Hiren Joshi; [email protected]
Subject: Re: [Gluster-users] GlusterFS Preformance
On Wed, 8 Jul 2009 10:05:58 -0700
Liam Slusser <[email protected]> wrote:
You have to remember that when you are writing with NFS
you're writing to
one node, where as your gluster setup below is copying the
same data to two
nodes; so you're doubling the bandwidth. Dont expect nfs
like performance
on writing with multiple storage bricks. However read
performance should be
quite good.
liam
Do you think this problem can be solved by using 2 storage
bricks on two
different network cards on the client?
I'd be surprised if the bottleneck here was the network.
I'm testing on
a xen network but I've only been given one eth per slice.
Do you mean your clients and servers are virtual XEN
installations (on the
same physical box) ?
They are on different boxes and using different disks (don't ask), this
seemed like a good way to evaluate as I setup an NFS server using the
same equipment to get relative timings. The plan is to roll it out onto
new physical boxes in a month or 2....
Regards,
Stephan
_______________________________________________
Gluster-users mailing list
[email protected]
http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
--
_______________________________________________
Gluster-users mailing list
[email protected]
http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
