Re: Proper kernel irq time accounting -v4

From: Venkatesh Pallipadi
Date: Tue Oct 12 2010 - 15:00:37 EST


On Mon, Oct 4, 2010 at 5:03 PM, Venkatesh Pallipadi <venki@xxxxxxxxxx> wrote:
> Previous versions:
> -v0: http://lkml.indiana.edu/hypermail//linux/kernel/1005.3/00411.html
>     lkml subject - "Finer granularity and task/cgroup irq time accounting"
>
> -v1: http://lkml.indiana.edu/hypermail//linux/kernel/1007.2/00987.html
>     lkml subject - "Finer granularity and task/cgroup irq time accounting"
>
> -v2: http://lkml.indiana.edu/hypermail//linux/kernel/1009.2/00488.html
>     lkml subject - "Proper kernel irq time accounting"
>
> -v3: http://lkml.indiana.edu/hypermail//linux/kernel/1009.3/02482.html
>     lkml subject - "Proper kernel irq time accounting -v3"
>
>
> Change from -v3:
> - Switch to using sched_clock_cpu instead of sched_clock in
>  account_system_vtime. This needed tick_check_idle to be called early in
>  irq_enter.
> - Do not account softirq time in ksoftirqd context. We want ksoftirqd to
>  continue having sched exec_runtime.
> - Add a boot option to disable tsc based irq accounting in x86.
> - Remove the patch that exported irq times in /proc/interrupts and
>  /proc/softirqs. I am relooking at other options to export that and
>  will have a replacement patch soon.
>
>

Peter,

If the patchset looks sane can you push this along to tip please.

Thanks,
Venki
--
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/