linux-kernel - [PATCH v4 5/5] sched/fair: Track peak per-entity utilization

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: <1472640739-8778-6-git-send-email-morten.rasmussen@arm.com>
Date:   Wed, 31 Aug 2016 11:52:19 +0100
From:   Morten Rasmussen <morten.rasmussen@....com>
To:     peterz@...radead.org, mingo@...hat.com
Cc:     dietmar.eggemann@....com, yuyang.du@...el.com,
        vincent.guittot@...aro.org, mgalbraith@...e.de,
        sgurrappadi@...dia.com, freedom.tan@...iatek.com,
        keita.kobayashi.ym@...esas.com, linux-kernel@...r.kernel.org,
        Morten Rasmussen <morten.rasmussen@....com>
Subject: [PATCH v4 5/5] sched/fair: Track peak per-entity utilization

When using PELT (per-entity load tracking) utilization to place tasks at
wake-up using the decayed utilization (due to sleep) leads to
under-estimation of true utilization of the task. This could mean
putting the task on a cpu with less available capacity than is actually
needed. This issue can be mitigated by using 'peak' utilization instead
of the decayed utilization for placement decisions, e.g. at task
wake-up.

The 'peak' utilization metric, util_peak, tracks util_avg when the task
is running and retains its previous value while the task is
blocked/waiting on the rq. It is instantly updated to track util_avg
again as soon as the task running again.

cc: Ingo Molnar <mingo@...hat.com>
cc: Peter Zijlstra <peterz@...radead.org>

Signed-off-by: Morten Rasmussen <morten.rasmussen@....com>
---
 include/linux/sched.h |  2 +-
 kernel/sched/fair.c   | 23 ++++++++++++++---------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d75024053e9b..fff4e4b6e654 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1282,7 +1282,7 @@ struct load_weight {
 struct sched_avg {
 	u64 last_update_time, load_sum;
 	u32 util_sum, period_contrib;
-	unsigned long load_avg, util_avg;
+	unsigned long load_avg, util_avg, util_peak;
 };
 
 #ifdef CONFIG_SCHEDSTATS
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 68d8b40c546b..27534e36555b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -692,6 +692,7 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 * At this point, util_avg won't be used in select_task_rq_fair anyway
 	 */
 	sa->util_avg = 0;
+	sa->util_peak = 0;
 	sa->util_sum = 0;
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
@@ -743,6 +744,7 @@ void post_init_entity_util_avg(struct sched_entity *se)
 		} else {
 			sa->util_avg = cap;
 		}
+		sa->util_peak = sa->util_avg;
 		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
 
@@ -2804,6 +2806,9 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
 	}
 
+	if (running || sa->util_avg > sa->util_peak)
+		sa->util_peak = sa->util_avg;
+
 	return decayed;
 }
 
@@ -5184,7 +5189,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	return 1;
 }
 
-static inline int task_util(struct task_struct *p);
+static inline int task_util_peak(struct task_struct *p);
 static int cpu_util_wake(int cpu, struct task_struct *p);
 
 static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
@@ -5267,14 +5272,14 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 	/*
 	 * The cross-over point between using spare capacity or least load
 	 * is too conservative for high utilization tasks on partially
-	 * utilized systems if we require spare_capacity > task_util(p),
+	 * utilized systems if we require spare_capacity > task_util_peak(p),
 	 * so we allow for some task stuffing by using
-	 * spare_capacity > task_util(p)/2.
+	 * spare_capacity > task_util_peak(p)/2.
 	 */
-	if (this_spare > task_util(p) / 2 &&
+	if (this_spare > task_util_peak(p) / 2 &&
 	    imbalance*this_spare > 100*most_spare)
 		return NULL;
-	else if (most_spare > task_util(p) / 2)
+	else if (most_spare > task_util_peak(p) / 2)
 		return most_spare_sg;
 
 	if (!idlest || 100*this_load < imbalance*min_load)
@@ -5432,9 +5437,9 @@ static int cpu_util(int cpu)
 	return (util >= capacity) ? capacity : util;
 }
 
-static inline int task_util(struct task_struct *p)
+static inline int task_util_peak(struct task_struct *p)
 {
-	return p->se.avg.util_avg;
+	return p->se.avg.util_peak;
 }
 
 /*
@@ -5450,7 +5455,7 @@ static int cpu_util_wake(int cpu, struct task_struct *p)
 		return cpu_util(cpu);
 
 	capacity = capacity_orig_of(cpu);
-	util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0);
+	util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util_peak(p), 0);
 
 	return (util >= capacity) ? capacity : util;
 }
@@ -5476,7 +5481,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 	/* Bring task utilization in sync with prev_cpu */
 	sync_entity_load_avg(&p->se);
 
-	return min_cap * 1024 < task_util(p) * capacity_margin;
+	return min_cap * 1024 < task_util_peak(p) * capacity_margin;
 }
 
 /*
-- 
1.9.1