[Linux-cluster] gfs performance

[Leonardo Rodrigues de Mello]

create one ramdevice, export it using gnbd and format using gfs. 
measure the performance localy using gfs, and over the network.
you will teste gfs with the highest "disk" performance you can, so you
can see if the bootleneck is in your disks or in gfs.


cya
On Seg, 2006-01-30 at 18:00 +0100, Jure Pečar wrote:
> On Mon, 30 Jan 2006 09:17:38 -0600
> gabe at msi.umn.edu (Gabe Turner) wrote:
> 
> > The DS4100, provided your's has two controllers, should have about 512MB of
> > RAID cache total. 
> 
> Yes.
> 
> > If this is the LSI/Engenio-based SATA storage I'm
> > thinking of, you should be able to turn on write cache on the controllers
> > via the management interface while the unit is live in order to see if it
> > makes much of a difference. 
> 
> I checked again, it's on for both volumes.
> 
> Any other ideas?
> 
> I'm thinking of trying the same test with ocfs2. If it gives me similiar
> numbers, then the bottleneck is underlying hardware, else it must be gfs.
> 
> 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
URL: <http://listman.redhat.com/archives/linux-cluster/attachments/20060130/b96b5f4a/attachment.sig>