From 46a87b3851f0d6eb05e6d83d5c5a30df0eca8f76 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Tue, 10 Mar 2020 18:01:13 -0700 Subject: sched/core: Distribute tasks within affinity masks Currently, when updating the affinity of tasks via either cpusets.cpus, or, sched_setaffinity(); tasks not currently running within the newly specified mask will be arbitrarily assigned to the first CPU within the mask. This (particularly in the case that we are restricting masks) can result in many tasks being assigned to the first CPUs of their new masks. This: 1) Can induce scheduling delays while the load-balancer has a chance to spread them between their new CPUs. 2) Can antogonize a poor load-balancer behavior where it has a difficult time recognizing that a cross-socket imbalance has been forced by an affinity mask. This change adds a new cpumask interface to allow iterated calls to distribute within the intersection of the provided masks. The cases that this mainly affects are: - modifying cpuset.cpus - when tasks join a cpuset - when modifying a task's affinity via sched_setaffinity(2) Signed-off-by: Paul Turner Signed-off-by: Josh Don Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Qais Yousef Tested-by: Qais Yousef Link: https://lkml.kernel.org/r/20200311010113.136465-1-joshdon@google.com --- include/linux/cpumask.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d5cc88514aee..f0d895d6ac39 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -194,6 +194,11 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) return 0; } +static inline int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) { + return cpumask_next_and(-1, src1p, src2p); +} + #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ @@ -245,6 +250,8 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); unsigned int cpumask_local_spread(unsigned int i, int node); +int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p); /** * for_each_cpu - iterate over every cpu in a mask -- cgit v1.2.3