From fde7d22e01aa0d252fc5c95fa11f0dac35a4dd59 Mon Sep 17 00:00:00 2001 From: Yuyang Du Date: Tue, 13 Oct 2015 09:18:22 +0800 Subject: sched/fair: Fix overly small weight for interactive group entities Commit: 9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking") led to an overly small weight for interactive group entities. The bad case can be easily reproduced when a number of CPU hogs compete for the CPUs at the same time (thanks to Mike). This is largly because the task group's load average tracking cross CPUs lags behind the real changes. To fix this we accelerate the group share distribution process by using the load.weight of the cfs_rq. This may increase the entire group's share, but we have to do so to protect the (fragile) interactive tasks, especially from CPU hogs. Reported-by: Mike Galbraith Tested-by: Dietmar Eggemann Tested-by: Mike Galbraith Signed-off-by: Yuyang Du Signed-off-by: Peter Zijlstra (Intel) Acked-by: Dietmar Eggemann Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1444699103-20272-1-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sched/fair.c') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6e2e348..bc62c50 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2363,7 +2363,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) */ tg_weight = atomic_long_read(&tg->load_avg); tg_weight -= cfs_rq->tg_load_avg_contrib; - tg_weight += cfs_rq_load_avg(cfs_rq); + tg_weight += cfs_rq->load.weight; return tg_weight; } @@ -2373,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) long tg_weight, load, shares; tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq_load_avg(cfs_rq); + load = cfs_rq->load.weight; shares = (tg->shares * load); if (tg_weight) -- cgit v1.1 From 3e386d56bafbb6d2540b49367444997fc671ea69 Mon Sep 17 00:00:00 2001 From: Yuyang Du Date: Tue, 13 Oct 2015 09:18:23 +0800 Subject: sched/fair: Update task group's load_avg after task migration When cfs_rq has cfs_rq->removed_load_avg set (when a task migrates from this cfs_rq), we need to update its contribution to the group's load_avg. This should not increase tg's update too much, because in most cases, the cfs_rq has already decayed its load_avg. Tested-by: Dietmar Eggemann Signed-off-by: Yuyang Du Signed-off-by: Peter Zijlstra (Intel) Acked-by: Dietmar Eggemann Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1444699103-20272-2-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/sched/fair.c') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bc62c50..9a5e60f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2664,13 +2664,14 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) { - int decayed; struct sched_avg *sa = &cfs_rq->avg; + int decayed, removed = 0; if (atomic_long_read(&cfs_rq->removed_load_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); sa->load_avg = max_t(long, sa->load_avg - r, 0); sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); + removed = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { @@ -2688,7 +2689,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) cfs_rq->load_last_update_time_copy = sa->last_update_time; #endif - return decayed; + return decayed || removed; } /* Update task and its cfs_rq load average */ -- cgit v1.1