Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1282264

[PATCH v2 1/3] sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats()

From Waiman Long <Waiman.Long@hpe.com>
Newsgroups linux.kernel
Subject [PATCH v2 1/3] sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats()
Date 2015-12-02 19:50 +0100
Message-ID <qBkDv-2x9-7@gated-at.bofh.it> (permalink)
References <qBkDv-2x9-3@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

Part of the responsibility of the update_sg_lb_stats() function is to
update the idle_cpus statistical counter in struct sg_lb_stats. This
check is done by calling idle_cpu(). The idle_cpu() function, in
turn, checks a number of fields within the run queue structure such
as rq->curr and rq->nr_running.

With the current layout of the run queue structure, rq->curr and
rq->nr_running are in separate cachelines. The rq->curr variable is
checked first followed by nr_running. As nr_running is also accessed
by update_sg_lb_stats() earlier, it makes no sense to load another
cacheline when nr_running is not 0 as idle_cpu() will always return
false in this case.

This patch eliminates this redundant cacheline load by checking the
cached nr_running before calling idle_cpu().

Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
---
 kernel/sched/fair.c |   10 +++++++---
 1 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f04fda8..8f1eccc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6302,7 +6302,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			bool *overload)
 {
 	unsigned long load;
-	int i;
+	int i, nr_running;
 
 	memset(sgs, 0, sizeof(*sgs));
 
@@ -6319,7 +6319,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->group_util += cpu_util(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
-		if (rq->nr_running > 1)
+		nr_running = rq->nr_running;
+		if (nr_running > 1)
 			*overload = true;
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -6327,7 +6328,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->nr_preferred_running += rq->nr_preferred_running;
 #endif
 		sgs->sum_weighted_load += weighted_cpuload(i);
-		if (idle_cpu(i))
+		/*
+		 * No need to call idle_cpu() if nr_running is not 0
+		 */
+		if (!nr_running && idle_cpu(i))
 			sgs->idle_cpus++;
 	}
 
-- 
1.7.1

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

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v2 0/3] sched/fair: Reduce contention on tg's load_avg Waiman Long <Waiman.Long@hpe.com> - 2015-12-02 19:50 +0100
  [PATCH v2 1/3] sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats() Waiman Long <Waiman.Long@hpe.com> - 2015-12-02 19:50 +0100
  [PATCH v2 3/3] sched/fair: Disable tg load_avg update for root_task_group Waiman Long <Waiman.Long@hpe.com> - 2015-12-02 19:50 +0100
    Re: [PATCH v2 3/3] sched/fair: Disable tg load_avg update for root_task_group bsegall@google.com - 2015-12-02 21:00 +0100
    [tip:sched/core] sched/fair:   Disable the task group load_avg update for the root_task_group tip-bot for Waiman Long <tipbot@zytor.com> - 2015-12-04 13:00 +0100
  [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline Waiman Long <Waiman.Long@hpe.com> - 2015-12-02 19:50 +0100
    Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline bsegall@google.com - 2015-12-02 21:10 +0100
      Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline Waiman Long <waiman.long@hpe.com> - 2015-12-03 20:30 +0100
        Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline bsegall@google.com - 2015-12-03 20:50 +0100
    Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own  cacheline Mike Galbraith <umgwanakikbuti@gmail.com> - 2015-12-03 05:40 +0100
      Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline Waiman Long <waiman.long@hpe.com> - 2015-12-03 20:40 +0100
        Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own  cacheline Mike Galbraith <umgwanakikbuti@gmail.com> - 2015-12-04 03:10 +0100
          Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline Waiman Long <waiman.long@hpe.com> - 2015-12-04 21:20 +0100
    Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own  cacheline Peter Zijlstra <peterz@infradead.org> - 2015-12-03 12:00 +0100
      Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline Waiman Long <waiman.long@hpe.com> - 2015-12-03 20:40 +0100
    Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own  cacheline Peter Zijlstra <peterz@infradead.org> - 2015-12-03 12:20 +0100
      Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline bsegall@google.com - 2015-12-03 19:10 +0100
        Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own  cacheline Peter Zijlstra <peterz@infradead.org> - 2015-12-03 19:20 +0100
          Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline bsegall@google.com - 2015-12-03 19:30 +0100
      Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own cacheline Waiman Long <waiman.long@hpe.com> - 2015-12-03 21:00 +0100
        Re: [PATCH v2 2/3] sched/fair: Move hot load_avg into its own  cacheline Peter Zijlstra <peterz@infradead.org> - 2015-12-03 21:10 +0100
    [tip:sched/core] sched/fair: Move the cache-hot 'load_avg'   variable into its own cacheline tip-bot for Waiman Long <tipbot@zytor.com> - 2015-12-04 13:00 +0100

csiph-web