Hi,

On Wed, Jan 30, 2008 at 02:57:16AM -0800, Paul E. McKenney wrote:
=2E.....
quoted text
> > Yes, I used "$ cyclictest -n -t1 -p80 -i1000" to measure the latency. So
> > far, I have not done other tests. Any recommendation?
> > As no-rt load I used "while ls; do ls /bin; done" in one telnet window
> > and "while ./hackbench 10; do ./calibrator 400 32M cali; sleep 30; done"
> > in another. But already "while ls; do ls /bin; done" is enough to
> > trigger the high latencies quickly. Note also, that I work on a root
> > files-ystem mounted via NFS resulting in a lot of network traffic and
> > utilization.
>=20
> I have to ask...
>=20
> Did you see large latencies when -not- running on NFS?
>=20

I cannot speak for Wolfgang but I myself did not get extraordinary high
latencies running tests on system booted from flash. Neither I could produce
high latencies on nfs booted system. If my non-rt workload doesn't do heavy
filesystem/network accesses. i.E. running only hackbench. Hence we were
wondering if the problem is caused by rcu's in network layer or nfs
implementation.

regards
Luotao Fu
--=20
   Dipl.-Ing. Luotao Fu | Phone: +49-5121-206917-3
Pengutronix - Linux Solutions for Science and Industry
Entwicklungszentrum Nord     http://www.pengutronix.de