From 7dd4912594daf769a46744848b05bd5bc6d62469 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 24 Jun 2016 15:53:54 +0200 Subject: [PATCH] sched/fair: Fix effective_load() to consistently use smoothed load Starting with the following commit: fde7d22e01aa ("sched/fair: Fix overly small weight for interactive group entities") calc_tg_weight() doesn't compute the right value as expected by effective_load(). The difference is in the 'correction' term. In order to ensure \Sum rw_j >= rw_i we cannot use tg->load_avg directly, since that might be lagging a correction on the current cfs_rq->avg.load_avg value. Therefore we use tg->load_avg - cfs_rq->tg_load_avg_contrib + cfs_rq->avg.load_avg. Now, per the referenced commit, calc_tg_weight() doesn't use cfs_rq->avg.load_avg, as is later used in @w, but uses cfs_rq->load.weight instead. So stop using calc_tg_weight() and do it explicitly. The effects of this bug are wake_affine() making randomly poor choices in cgroup-intense workloads. Signed-off-by: Peter Zijlstra (Intel) Cc: # v4.3+ Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: fde7d22e01aa ("sched/fair: Fix overly small weight for interactive group entities") Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bdcbeea90c95..cc48bef40cca 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se) } } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); -static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else void init_entity_runnable_average(struct sched_entity *se) { @@ -4946,19 +4944,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; for_each_sched_entity(se) { - long w, W; + struct cfs_rq *cfs_rq = se->my_q; + long W, w = cfs_rq_load_avg(cfs_rq); - tg = se->my_q->tg; + tg = cfs_rq->tg; /* * W = @wg + \Sum rw_j */ - W = wg + calc_tg_weight(tg, se->my_q); + W = wg + atomic_long_read(&tg->load_avg); + + /* Ensure \Sum rw_j >= rw_i */ + W -= cfs_rq->tg_load_avg_contrib; + W += w; /* * w = rw_i + @wl */ - w = cfs_rq_load_avg(se->my_q) + wl; + w += wl; /* * wl = S * s'_i; see (2) -- GitLab