lkml.org 
[lkml]   [2021]   [Jan]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] sched/eas: Don't update misfit status if the task is pinned
On 01/19/21 15:35, Quentin Perret wrote:
> On Tuesday 19 Jan 2021 at 12:07:55 (+0000), Qais Yousef wrote:
> > If the task is pinned to a cpu, setting the misfit status means that
> > we'll unnecessarily continuously attempt to migrate the task but fail.
> >
> > This continuous failure will cause the balance_interval to increase to
> > a high value, and eventually cause unnecessary significant delays in
> > balancing the system when real imbalance happens.
> >
> > Caught while testing uclamp where rt-app calibration loop was pinned to
> > cpu 0, shortly after which we spawn another task with high util_clamp
> > value. The task was failing to migrate after over 40ms of runtime due to
> > balance_interval unnecessary expanded to a very high value from the
> > calibration loop.
> >
> > Not done here, but it could be useful to extend the check for pinning to
> > verify that the affinity of the task has a cpu that fits. We could end
> > up in a similar situation otherwise.
>
> Do you mean failing the sched_setaffinity syscall if e.g. the task
> has a min clamp that is higher than the capacity of the CPUs to which it
> will be pinned? If so, I'm not sure if we really want that.

No. In Android for instance, I'm worried a background task affined to little
cores that has a utilization > capacity_of(little) will trigger the same
problem. It'll be affined to more than just 1 cpu, but none of the little cpus
will actually fit.

Makes sense?

> But this patch makes sense on its own for sure, so:
>
> Reviewed-by: Quentin Perret <qperret@google.com>

Thanks

--
Qais Yousef

\
 
 \ /
  Last update: 2021-01-19 17:46    [W:0.147 / U:0.892 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site