Subject: | |
From: | |
Reply To: | |
Date: | Fri, 11 Feb 2005 14:51:21 -0500 |
Content-Type: | text/plain |
Parts/Attachments: |
|
|
Thanks for giving it a try, John. I've got a couple questions that I'm
sure you can help clarify.
On Feb 10, 2005, at 10:31 AM, John Hearns wrote:
> I just tried this set of steps.
> Cluster, running SL 3.03, kernel 2.4.21-27.0.1ELsmp on client and
> server.
What do you mean by "Cluster?" (are you using RH Cluster Suite, a
clustered file system, ...)
> The server is a Sunfire V40z - four Opteron.
Are you running the kernel in 32 or 64-bit mode?
Are you using the kernel and nfs-utils binary rpms, or did you compile
anything from source?
Thanks,
Devin
> The clients are a mix of
> V20s and V40s.
> I did tests on a V40, running as root.
>
>
> Step 5, client touching a file on the NFS share when the I/O is
> running,
> seems to take a mean of about 5 seconds.
>
> Step 6 times are unaffected - no time increase.
>
--------------------
Devin Bougie
Laboratory for Elementary-Particle Physics
Computer Group
[log in to unmask]
(607) 254-8353
|
|
|