From: Peng Wang Date: Fri, 13 Dec 2019 03:45:40 +0000 (+0800) Subject: schied/fair: Skip calculating @contrib without load X-Git-Tag: v5.6-rc1~167^2~25 X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=commitdiff_plain;h=d040e0734fb3dedfe24c3d94f5a32b4812eca610;p=linux.git schied/fair: Skip calculating @contrib without load Because of the: if (!load) runnable = running = 0; clause in ___update_load_sum(), all the actual users of @contrib in accumulate_sum(): if (load) sa->load_sum += load * contrib; if (runnable) sa->runnable_load_sum += runnable * contrib; if (running) sa->util_sum += contrib << SCHED_CAPACITY_SHIFT; don't happen, and therefore we don't care what @contrib actually is and calculating it is pointless. If we count the times when @load equals zero and not as below: if (load) { load_is_not_zero_count++; contrib = __accumulate_pelt_segments(periods, 1024 - sa->period_contrib,delta); } else load_is_zero_count++; As we can see, load_is_zero_count is much bigger than load_is_zero_count, and the gap is gradually widening: load_is_zero_count: 6016044 times load_is_not_zero_count: 244316 times 19:50:43 up 1 min, 1 user, load average: 0.09, 0.06, 0.02 load_is_zero_count: 7956168 times load_is_not_zero_count: 261472 times 19:51:42 up 2 min, 1 user, load average: 0.03, 0.05, 0.01 load_is_zero_count: 10199896 times load_is_not_zero_count: 278364 times 19:52:51 up 3 min, 1 user, load average: 0.06, 0.05, 0.01 load_is_zero_count: 14333700 times load_is_not_zero_count: 318424 times 19:54:53 up 5 min, 1 user, load average: 0.01, 0.03, 0.00 Perhaps we can gain some performance advantage by saving these unnecessary calculation. Signed-off-by: Peng Wang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot < vincent.guittot@linaro.org> Link: https://lkml.kernel.org/r/1576208740-35609-1-git-send-email-rocking@linux.alibaba.com --- diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index a96db50d40e0..bd006b79b360 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -129,8 +129,20 @@ accumulate_sum(u64 delta, struct sched_avg *sa, * Step 2 */ delta %= 1024; - contrib = __accumulate_pelt_segments(periods, - 1024 - sa->period_contrib, delta); + if (load) { + /* + * This relies on the: + * + * if (!load) + * runnable = running = 0; + * + * clause from ___update_load_sum(); this results in + * the below usage of @contrib to dissapear entirely, + * so no point in calculating it. + */ + contrib = __accumulate_pelt_segments(periods, + 1024 - sa->period_contrib, delta); + } } sa->period_contrib = delta; @@ -205,7 +217,9 @@ ___update_load_sum(u64 now, struct sched_avg *sa, * This means that weight will be 0 but not running for a sched_entity * but also for a cfs_rq if the latter becomes idle. As an example, * this happens during idle_balance() which calls - * update_blocked_averages() + * update_blocked_averages(). + * + * Also see the comment in accumulate_sum(). */ if (!load) runnable = running = 0;