lkml.org 
[lkml]   [2011]   [Oct]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: 2.6.32 / RH 6.1 scheduler bloated
Date
Will try this, but I have older kernel version running on the same  
hardware, with the same boot parameters, and showing a more
reasonable 2us wakeup latency. Still high, but coming out of idle can
be slow as you say.
But 10us??

On Oct 9, 2011, at 2:03 AM, Mike Galbraith wrote:

> On Sat, 2011-10-08 at 20:26 -0400, Robert Kubrick wrote:
>> A simple ftrace wakeup test shows 10us latency during the idle-to-run
>> transition:
>
> If you boot nohz=off idle=poll, and measure with cyclictest
> (measure in
> userspace for free), you'll likely see a remarkable difference.
>
> Coming out of idle can be slow, but that has more to do with silicon
> than scheduler bloat (not that bloat doesn't exist mind you). My
> Q6600
> box _sucks_ at getting off it's duff, even intel_idle.max_cstate=1 is
> horrid. E5620 gets moving > order of magnitude more quickly with the
> same kernel/config/params.
>
> -Mike
>



\
 
 \ /
  Last update: 2011-10-09 16:29    [from the cache]
©2003-2011 Jasper Spaans