Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-18 Thread Mel Gorman
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

Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-18 Thread Vincent Guittot
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

Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-17 Thread Mel Gorman
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

Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-17 Thread Vincent Guittot
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

Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-17 Thread Mel Gorman
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 >=

Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-17 Thread Vincent Guittot
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

Re: [PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-17 Thread Peter Zijlstra
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% ?

[PATCH 3/3] sched/numa: Limit the amount of imbalance that can exist at fork time

2020-11-17 Thread Mel Gorman
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