Re: [PATCH v6 2/2] Output stall data in debugfs

[Alex Neronskiy]

On Thu, Aug 11, 2011 at 2:17 PM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Thu, 2011-08-11 at 13:31 -0700, Alex Neronskiy wrote:
>>
>> > I mean, we're at the point where a PREEMPT=y kernel has a pretty decent
>> > latency and the PREEMPT_RT kernels live at ~30us. So wth are you
>> > measuring?
>> Well, not all kernels have PREEMPT. Chromebook kernels don't, for example.
>
> Can one infer from that statement that the purpose is trying to measure
> non preempt latency? Why not use the tracer build for that purpose?
>
> Still the watchdog ticks at 1s intervals or so, anything that takes that
> long, even on voluntary preemption kernels is quite insane.
I think Don grasped the sentiment well about a month ago when he
commented on the first version of the patch, so I'll just resend his
words:
On Wed, Jul 13, 2011 at 6:43 AM, Don Zickus <dzickus@xxxxxxxxxx> wrote:
> I like the idea of this patch.  It definitely helps with better statistics
> when trying to set the appropriate values for a soft/hard lockup as
> opposed to pulling numbers from the air.
--
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/