Re: [RFC PATCH] check_preempt_tick should not compare vruntime withwall time

From: Ingo Molnar
Date: Mon Sep 13 2010 - 14:20:20 EST



* Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx> wrote:

> 2.0GHz Pentium M
>
> * wakeup-latency.c (SIGEV_THREAD) with make -j10
>
> - Mainline 2.6.35.2 kernel
>
> maximum latency: 45762.1 µs
> average latency: 7348.6 µs
> missed timer events: 0
>
> - check_preempt fix
>
> maximum latency: 39858.9 µs
> average latency: 7728.1 µs
> missed timer events: 0

Note that the check_preempt fix, as i mentioned it in the previous mail,
has no effect on this workload - so any effect you see is pure noise.

> - With only Peter's smaller min_gran (shown below):
>
> maximum latency: 29100.6 µs
> average latency: 6684.1 µs
> missed timer events: 0

That's the real improvement.

> - check_preempt fix + Peter's smaller min_gran:
> maximum latency: 20433.0 µs
> average latency: 5112.5 µs
> missed timer events: 0

Again, pure noise effect.

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