On Wed, Nov 18, 2020 at 05:06:32PM +0100, Vincent Guittot wrote:
> > > which would return how much margin remains available before not
> > > allowing the imbalance
> > >
> >
> > Easier to just make it a bool as the available margin is not relevant
> > (yet).
>
> That's my point, preparing future
On Tue, 17 Nov 2020 at 18:28, Mel Gorman wrote:
>
> On Tue, Nov 17, 2020 at 04:53:10PM +0100, Vincent Guittot wrote:
> > On Tue, 17 Nov 2020 at 16:17, Mel Gorman
> > wrote:
> > >
> > > On Tue, Nov 17, 2020 at 03:31:19PM +0100, Vincent Guittot wrote:
> > > > On Tue, 17 Nov 2020 at 15:18, Peter
On Tue, Nov 17, 2020 at 04:53:10PM +0100, Vincent Guittot wrote:
> On Tue, 17 Nov 2020 at 16:17, Mel Gorman wrote:
> >
> > On Tue, Nov 17, 2020 at 03:31:19PM +0100, Vincent Guittot wrote:
> > > On Tue, 17 Nov 2020 at 15:18, Peter Zijlstra wrote:
> > > >
> > > > On Tue, Nov 17, 2020 at 01:42:22PM
On Tue, 17 Nov 2020 at 16:17, Mel Gorman wrote:
>
> On Tue, Nov 17, 2020 at 03:31:19PM +0100, Vincent Guittot wrote:
> > On Tue, 17 Nov 2020 at 15:18, Peter Zijlstra wrote:
> > >
> > > On Tue, Nov 17, 2020 at 01:42:22PM +, Mel Gorman wrote:
> > > > - if
On Tue, Nov 17, 2020 at 03:31:19PM +0100, Vincent Guittot wrote:
> On Tue, 17 Nov 2020 at 15:18, Peter Zijlstra wrote:
> >
> > On Tue, Nov 17, 2020 at 01:42:22PM +, Mel Gorman wrote:
> > > - if (local_sgs.idle_cpus)
> > > + if (local_sgs.idle_cpus >=
On Tue, 17 Nov 2020 at 15:18, Peter Zijlstra wrote:
>
> On Tue, Nov 17, 2020 at 01:42:22PM +, Mel Gorman wrote:
> > - if (local_sgs.idle_cpus)
> > + if (local_sgs.idle_cpus >= (sd->span_weight >> 2))
> > return NULL;
>
> Is
On Tue, Nov 17, 2020 at 01:42:22PM +, Mel Gorman wrote:
> - if (local_sgs.idle_cpus)
> + if (local_sgs.idle_cpus >= (sd->span_weight >> 2))
> return NULL;
Is that the same 25% ?
At fork time currently, a local node can be allowed to fill completely
and allow the periodic load balancer to fix the problem. This can
be problematic in cases where a task creates lots of threads that
idle until woken as part of a worker poll causing a memory bandwidth
problem.
This patch tries
8 matches
Mail list logo