Messages in this thread | | | Subject | Re: [PATCH v4] sched: fix wrong rq's runnable_avg update with rt tasks | From | Steven Rostedt <> | Date | Tue, 09 Apr 2013 09:16:08 -0400 |
| |
On Tue, 2013-04-09 at 14:18 +0200, Vincent Guittot wrote: > On 9 April 2013 10:55, Peter Zijlstra <peterz@infradead.org> wrote: > > On Thu, 2013-04-04 at 16:15 +0200, Vincent Guittot wrote: > >> Changes since V2: > >> - remove useless definition for UP platform > >> - rebased on top of Steven Rostedt's patches : > >> https://lkml.org/lkml/2013/2/12/558 > > > > So what's the status of those patches? I still worry about the extra > > context switch overhead for the high-frequency idle scenario. > > I don't know. I have seen a pulled answer from Ingo but can't find the > commits in the tip tree. > > Steve, have you got more info about the status of your patches ? >
Yeah, I asked Ingo to revert it due to Peter's concerns. I was able to get the latencies I needed without that patch set. That made it not so urgent.
Can you rebase your patches doing something similar? That is, still use the pre/post_schedule_idle() calls, but don't base it off of my patch set.
Thanks,
-- Steve
| |