linux-kernel - [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1404144343-18720-9-git-send-email-vincent.guittot@linaro.org>
Date:	Mon, 30 Jun 2014 18:05:39 +0200
From:	Vincent Guittot <vincent.guittot@...aro.org>
To:	peterz@...radead.org, mingo@...nel.org,
	linux-kernel@...r.kernel.org, linux@....linux.org.uk,
	linux-arm-kernel@...ts.infradead.org
Cc:	preeti@...ux.vnet.ibm.com, Morten.Rasmussen@....com, efault@....de,
	nicolas.pitre@...aro.org, linaro-kernel@...ts.linaro.org,
	daniel.lezcano@...aro.org, dietmar.eggemann@....com,
	Vincent Guittot <vincent.guittot@...aro.org>
Subject: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity

If the CPU is used for handling lot of IRQs, trig a load balance to check if
it's worth moving its tasks on another CPU that has more capacity.

As a sidenote, this will note generate more spurious ilb because we already
trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that
has a task, we will trig the ilb once for migrating the task.

The nohz_kick_needed function has been cleaned up a bit while adding the new
test

Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
---
 kernel/sched/fair.c | 58 +++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 17 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a23c938..742ad88 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5944,6 +5944,14 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 			return true;
 	}
 
+	/*
+	 * The group capacity is reduced probably because of activity from other
+	 * sched class or interrupts which use part of the available capacity
+	 */
+	if ((sg->sgc->capacity_orig * 100) > (sgs->group_capacity *
+				env->sd->imbalance_pct))
+		return true;
+
 	return false;
 }
 
@@ -6421,13 +6429,24 @@ static int need_active_balance(struct lb_env *env)
 	struct sched_domain *sd = env->sd;
 
 	if (env->idle == CPU_NEWLY_IDLE) {
+		int src_cpu = env->src_cpu;
 
 		/*
 		 * ASYM_PACKING needs to force migrate tasks from busy but
 		 * higher numbered CPUs in order to pack all tasks in the
 		 * lowest numbered CPUs.
 		 */
-		if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu)
+		if ((sd->flags & SD_ASYM_PACKING) && src_cpu > env->dst_cpu)
+			return 1;
+
+		/*
+		 * If the CPUs share their cache and the src_cpu's capacity is
+		 * reduced because of other sched_class or IRQs, we trig an
+		 * active balance to move the task
+		 */
+		if ((sd->flags & SD_SHARE_PKG_RESOURCES)
+		 && ((capacity_orig_of(src_cpu) * 100) > (capacity_of(src_cpu) *
+							sd->imbalance_pct)))
 			return 1;
 	}
 
@@ -6529,6 +6548,8 @@ redo:
 
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
+	env.src_cpu = busiest->cpu;
+
 	ld_moved = 0;
 	if (busiest->nr_running > 1) {
 		/*
@@ -6538,7 +6559,6 @@ redo:
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.src_cpu   = busiest->cpu;
 		env.src_rq    = busiest;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
@@ -7233,9 +7253,10 @@ static inline int nohz_kick_needed(struct rq *rq)
 	struct sched_domain *sd;
 	struct sched_group_capacity *sgc;
 	int nr_busy, cpu = rq->cpu;
+	bool kick = false;
 
 	if (unlikely(rq->idle_balance))
-		return 0;
+		return false;
 
        /*
 	* We may be recently in ticked or tickless idle mode. At the first
@@ -7249,38 +7270,41 @@ static inline int nohz_kick_needed(struct rq *rq)
 	 * balancing.
 	 */
 	if (likely(!atomic_read(&nohz.nr_cpus)))
-		return 0;
+		return false;
 
 	if (time_before(now, nohz.next_balance))
-		return 0;
+		return false;
 
 	if (rq->nr_running >= 2)
-		goto need_kick;
+		return true;
 
 	rcu_read_lock();
 	sd = rcu_dereference(per_cpu(sd_busy, cpu));
-
 	if (sd) {
 		sgc = sd->groups->sgc;
 		nr_busy = atomic_read(&sgc->nr_busy_cpus);
 
-		if (nr_busy > 1)
-			goto need_kick_unlock;
+		if (nr_busy > 1) {
+			kick = true;
+			goto unlock;
+		}
+
+		if ((rq->cfs.h_nr_running >= 1)
+		 && ((rq->cpu_capacity * sd->imbalance_pct) <
+					(rq->cpu_capacity_orig * 100))) {
+			kick = true;
+			goto unlock;
+		}
 	}
 
 	sd = rcu_dereference(per_cpu(sd_asym, cpu));
-
 	if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
 				  sched_domain_span(sd)) < cpu))
-		goto need_kick_unlock;
+		kick = true;
 
+unlock:
 	rcu_read_unlock();
-	return 0;
-
-need_kick_unlock:
-	rcu_read_unlock();
-need_kick:
-	return 1;
+	return kick;
 }
 #else
 static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/