lkml.org 
[lkml]   [2020]   [Nov]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v3 09/14] cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1
On Thu, Nov 19, 2020 at 09:29:22AM +0000, Quentin Perret wrote:
> On Friday 13 Nov 2020 at 09:37:14 (+0000), Will Deacon wrote:
> > If the scheduler cannot find an allowed CPU for a task,
> > cpuset_cpus_allowed_fallback() will widen the affinity to cpu_possible_mask
> > if cgroup v1 is in use.
> >
> > In preparation for allowing architectures to provide their own fallback
> > mask, just return early if we're not using cgroup v2 and allow
> > select_fallback_rq() to figure out the mask by itself.
> >
> > Cc: Li Zefan <lizefan@huawei.com>
> > Cc: Tejun Heo <tj@kernel.org>
> > Cc: Johannes Weiner <hannes@cmpxchg.org>
> > Signed-off-by: Will Deacon <will@kernel.org>
>
> That makes select_fallback_rq() slightly more expensive if you're using
> cgroup v1, but I don't expect that be really measurable in real-world
> workloads, so:
>
> Reviewed-by: Quentin Perret <qperret@google.com>

Cheers!

Will

\
 
 \ /
  Last update: 2020-11-19 12:08    [W:0.057 / U:0.240 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site