[Linux-cluster] GFS RG size (and tuning)
Jos Vos
jos at xos.nl
Tue Oct 30 07:27:34 UTC 2007
On Mon, Oct 29, 2007 at 08:53:10PM -0400, Glen Dosey wrote:
> We have several 3.3TB and larger filesystems on GFS1. I found that using
> the larger RG helps with performance. Increasing the statfs_slots seemed
> to help with df time and similar tasks as well. We have a filesystem
> with smaller RG's and I don't think the difference is worth moving the
> data around. If there is some other reason to make changes then I will
> increase the RG size. The statfs_slots can be increased on the fly and
> you should hopefully see an improvement.
Unfortunately, no. We see dramatic performace, df's may take 10+ minutes,
and above approx. 100 Mbit/sec total network traffic (mostly read from
GFS disks) the performance goes up and down, sometiems back to 5 Mbit/sec etc.
I have statfs_slots now set to 128, or should that be bigger?
We created now one fs with larger RG's and at least df works better, but
I fear we also have to do the other patches.
--
-- Jos Vos <jos at xos.nl>
-- X/OS Experts in Open Systems BV | Phone: +31 20 6938364
-- Amsterdam, The Netherlands | Fax: +31 20 6948204
More information about the Linux-cluster
mailing list