On Thu, 2010-06-17 at 21:16 -0700, Gregory P. Smith wrote:
> diff --git a/client/tests/tsc/src/checktsc.c
> b/client/tests/tsc/src/checktsc.c
> index f7fc879..74290ff 100644
> --- a/client/tests/tsc/src/checktsc.c
> +++ b/client/tests/tsc/src/checktsc.c
> @@ -218,6 +218,12 @@ tsc_delta(int cpu_a, int cpu_b)
> wait_for_state(&slave, DONE);
> t1 = rdtsc();
>
> + /* Ignore roundtrips bigger than 2 * treshold,
> as one of the threads
> + * that reads TSC is likely out of the CPU in
> this case */
> + if ((t1 - t0) > 2 * threshold)
> + continue;
> +
> +
> if ((t1 - t0) < (best_t1 - best_t0)) {
> best_t0 = t0;
> best_t1 = t1;
> diff --git a/client/tests/tsc/tsc.py b/client/tests/tsc/tsc.py
> index ef3c960..2bac609 100644
>
> FWIW, we are seeing new failures of TSC test due to this change on
> hardware and kernels where it did not fail in the past.
Ok, we can revert it, but better look into this more carefully. Michael,
Glauber, any ideas here?
_______________________________________________
Autotest mailing list
[email protected]
http://test.kernel.org/cgi-bin/mailman/listinfo/autotest
