On Wed, 2005-02-09 at 14:02 -0500, Devin Bougie wrote:
> Hi All,
> 
> We have been struggling with what appears to be a bug in RH kernels.  
> This results in local disk I/O blocking all NFS I/O (and, as we show, 
> subsequent local I/O).  This appears easy to reproduce:
> ----
I just tried this set of steps.
Cluster, running SL 3.03,  kernel 2.4.21-27.0.1ELsmp on client and
server.

The server is a Sunfire V40z - four Opteron. 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.