Re: [PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg()

From	Steve Muckle <steve.muckle@linaro.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg()
Date	2016-03-31 03:50 +0200
Message-ID	<rizUe-5Lv-15@gated-at.bofh.it> (permalink)
References	(1 earlier) <rhImS-1aq-17@gated-at.bofh.it> <rhImS-1aq-15@gated-at.bofh.it> <rhLb3-36F-13@gated-at.bofh.it> <rhLb3-36F-11@gated-at.bofh.it> <riu89-1FR-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On 03/30/2016 12:35 PM, Peter Zijlstra wrote:
> On Mon, Mar 28, 2016 at 12:38:26PM -0700, Steve Muckle wrote:
>> Without covering all the paths where CFS utilization changes it's
>> possible to have to wait up to a tick to act on some changes, since the
>> tick is the only guaranteed regularly-occurring instance of the hook.
>> That's an unacceptable amount of latency IMO...
> 
> Note that even with your patches that might still be the case. Remote
> wakeups might not happen on the destination CPU at all, so it might not
> be until the next tick (which always happens locally) that we'll
> 'observe' the utilization change brought with the wakeups.
> 
> We could force all the remote wakeups to IPI the destination CPU, but
> that comes at a significant performance cost.

What about only IPI'ing the destination when the utilization change is
known to require a higher CPU frequency?

Thread

[PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg() Steve Muckle <steve.muckle@linaro.org> - 2016-03-22 01:30 +0100
  Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Steve Muckle <steve.muckle@linaro.org> - 2016-03-28 18:40 +0200
    Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Steve Muckle <steve.muckle@linaro.org> - 2016-03-28 21:40 +0200
      Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Peter Zijlstra <peterz@infradead.org> - 2016-03-30 21:40 +0200
        Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Steve Muckle <steve.muckle@linaro.org> - 2016-03-31 03:50 +0200
          Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Peter Zijlstra <peterz@infradead.org> - 2016-03-31 09:40 +0200
            Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Steve Muckle <steve.muckle@linaro.org> - 2016-03-31 23:30 +0200
              Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Peter Zijlstra <peterz@infradead.org> - 2016-04-01 11:30 +0200
        Re: [PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg() Vincent Guittot <vincent.guittot@linaro.org> - 2016-03-31 11:30 +0200
          Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Peter Zijlstra <peterz@infradead.org> - 2016-03-31 11:40 +0200
            Re: [PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg() Vincent Guittot <vincent.guittot@linaro.org> - 2016-03-31 12:00 +0200
              Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Peter Zijlstra <peterz@infradead.org> - 2016-03-31 12:50 +0200
                Re: [PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg() Vincent Guittot <vincent.guittot@linaro.org> - 2016-03-31 14:20 +0200
                Re: [PATCH 1/2] sched/fair: move cpufreq hook to  update_cfs_rq_load_avg() Peter Zijlstra <peterz@infradead.org> - 2016-03-31 14:40 +0200
                Re: [PATCH 1/2] sched/fair: move cpufreq hook to update_cfs_rq_load_avg() Vincent Guittot <vincent.guittot@linaro.org> - 2016-03-31 15:00 +0200

csiph-web