linux-kernel - [tip: sched/core] sched/fair: Take into account runnable

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: <158255763115.28353.13296779966078754559.tip-bot2@tip-bot2>
Date:   Mon, 24 Feb 2020 15:20:31 -0000
From:   "tip-bot2 for Vincent Guittot" <tip-bot2@...utronix.de>
To:     linux-tip-commits@...r.kernel.org
Cc:     Vincent Guittot <vincent.guittot@...aro.org>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Ingo Molnar <mingo@...nel.org>,
        "Dietmar Eggemann" <dietmar.eggemann@....com>,
        Peter Zijlstra <a.p.zijlstra@...llo.nl>,
        Juri Lelli <juri.lelli@...hat.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Valentin Schneider <valentin.schneider@....com>,
        Phil Auld <pauld@...hat.com>, Hillf Danton <hdanton@...a.com>,
        x86 <x86@...nel.org>, LKML <linux-kernel@...r.kernel.org>
Subject: [tip: sched/core] sched/fair: Take into account runnable_avg to
 classify group

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     070f5e860ee2bf588c99ef7b4c202451faa48236
Gitweb:        https://git.kernel.org/tip/070f5e860ee2bf588c99ef7b4c202451faa48236
Author:        Vincent Guittot <vincent.guittot@...aro.org>
AuthorDate:    Mon, 24 Feb 2020 09:52:19 
Committer:     Ingo Molnar <mingo@...nel.org>
CommitterDate: Mon, 24 Feb 2020 11:36:37 +01:00

sched/fair: Take into account runnable_avg to classify group

Take into account the new runnable_avg signal to classify a group and to
mitigate the volatility of util_avg in face of intensive migration or
new task with random utilization.

Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
Signed-off-by: Ingo Molnar <mingo@...nel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@....com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Juri Lelli <juri.lelli@...hat.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Valentin Schneider <valentin.schneider@....com>
Cc: Phil Auld <pauld@...hat.com>
Cc: Hillf Danton <hdanton@...a.com>
Link: https://lore.kernel.org/r/20200224095223.13361-10-mgorman@techsingularity.net
---
 kernel/sched/fair.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 49b36d6..87521ac 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5469,6 +5469,24 @@ static unsigned long cpu_runnable(struct rq *rq)
 	return cfs_rq_runnable_avg(&rq->cfs);
 }
 
+static unsigned long cpu_runnable_without(struct rq *rq, struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq;
+	unsigned int runnable;
+
+	/* Task has no contribution or is new */
+	if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return cpu_runnable(rq);
+
+	cfs_rq = &rq->cfs;
+	runnable = READ_ONCE(cfs_rq->avg.runnable_avg);
+
+	/* Discount task's runnable from CPU's runnable */
+	lsub_positive(&runnable, p->se.avg.runnable_avg);
+
+	return runnable;
+}
+
 static unsigned long capacity_of(int cpu)
 {
 	return cpu_rq(cpu)->cpu_capacity;
@@ -7752,7 +7770,8 @@ struct sg_lb_stats {
 	unsigned long avg_load; /*Avg load across the CPUs of the group */
 	unsigned long group_load; /* Total load over the CPUs of the group */
 	unsigned long group_capacity;
-	unsigned long group_util; /* Total utilization of the group */
+	unsigned long group_util; /* Total utilization over the CPUs of the group */
+	unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
 	unsigned int sum_nr_running; /* Nr of tasks running in the group */
 	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
 	unsigned int idle_cpus;
@@ -7973,6 +7992,10 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 	if (sgs->sum_nr_running < sgs->group_weight)
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return false;
+
 	if ((sgs->group_capacity * 100) >
 			(sgs->group_util * imbalance_pct))
 		return true;
@@ -7998,6 +8021,10 @@ group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 			(sgs->group_util * imbalance_pct))
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return true;
+
 	return false;
 }
 
@@ -8092,6 +8119,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		sgs->group_load += cpu_load(rq);
 		sgs->group_util += cpu_util(i);
+		sgs->group_runnable += cpu_runnable(rq);
 		sgs->sum_h_nr_running += rq->cfs.h_nr_running;
 
 		nr_running = rq->nr_running;
@@ -8367,6 +8395,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 		sgs->group_load += cpu_load_without(rq, p);
 		sgs->group_util += cpu_util_without(i, p);
+		sgs->group_runnable += cpu_runnable_without(rq, p);
 		local = task_running_on_cpu(i, p);
 		sgs->sum_h_nr_running += rq->cfs.h_nr_running - local;