Preliminary testing results for 2.4.10

Bob Matthews (bmatthews@redhat.com)
Mon, 24 Sep 2001 18:17:44 -0400

Arjan van de Ven wrote:
>
> Hi.
>
> In the Red Hat testlab, Bob Matthews has run the stress-test part of our
> normal "release signoff tests" on 2.4.10pre11 to evaluate the new VM for
> stability.

I've just finished a quick test cycle with 2.4.10. Here are the results
we observed:

There are two tests running, both with HIMEM set to 64G.

machine test1: 2xPIII, 2G RAM/4G Swap. Appears to be in a memory
related deadlock. All test related processes save one are in D state.
Vmstat indicates no swapping activity. Top says both processors are
~95% idle. The exception is the TTCP test, which has a very small
memory footprint and is running normally.

machine test4: 4xPIII, 1G/2G. Appears to be running normally, but top
indicates frequent stalls with CPU idle times shooting up to 90% on all
processors for brief, but recurring periods.

No processes have been killed by OOM at this point.

-- 
Bob Matthews
Red Hat, Inc.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/