From c8987ae5af793a73e2c0d6ce804d8ff454ea377c Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sun, 21 Mar 2021 11:14:32 +1300 Subject: [PATCH] sched/fair: Optimize test_idle_cores() for !SMT update_idle_core() is only done for the case of sched_smt_present. but test_idle_cores() is done for all machines even those without SMT. This can contribute to up 8%+ hackbench performance loss on a machine like kunpeng 920 which has no SMT. This patch removes the redundant test_idle_cores() for !SMT machines. Hackbench is ran with -g {2..14}, for each g it is ran 10 times to get an average. $ numactl -N 0 hackbench -p -T -l 20000 -g $1 The below is the result of hackbench w/ and w/o this patch: g= 2 4 6 8 10 12 14 w/o: 1.8151 3.8499 5.5142 7.2491 9.0340 10.7345 12.0929 w/ : 1.8428 3.7436 5.4501 6.9522 8.2882 9.9535 11.3367 +4.1% +8.3% +7.3% +6.3% Signed-off-by: Barry Song Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Acked-by: Mel Gorman Link: https://lkml.kernel.org/r/20210320221432.924-1-song.bao.hua@hisilicon.com --- kernel/sched/fair.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6aad028..aaa0dfa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6038,9 +6038,11 @@ static inline bool test_idle_cores(int cpu, bool def) { struct sched_domain_shared *sds; - sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - if (sds) - return READ_ONCE(sds->has_idle_cores); + if (static_branch_likely(&sched_smt_present)) { + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) + return READ_ONCE(sds->has_idle_cores); + } return def; } -- 2.7.4