From: vincent.guittot@linaro.org (Vincent Guittot)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 08/14] sched: trig ILB on an idle buddy
Date: Thu, 25 Apr 2013 19:23:24 +0200 [thread overview]
Message-ID: <1366910611-20048-9-git-send-email-vincent.guittot@linaro.org> (raw)
In-Reply-To: <1366910611-20048-1-git-send-email-vincent.guittot@linaro.org>
If the buddy CPU is not full and currently idle, we trigger an Idle Load
Balance to give it the opportunity to pull more tasks.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
kernel/sched/fair.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 874f330..954adfd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5776,6 +5776,26 @@ end:
clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
}
+static int check_nohz_buddy(int cpu)
+{
+ int buddy = per_cpu(sd_pack_buddy, cpu);
+
+ if (sysctl_sched_packing_mode != SCHED_PACKING_FULL)
+ return false;
+
+ /* No pack buddy for this CPU */
+ if (buddy == -1)
+ return false;
+
+ if (is_buddy_full(buddy))
+ return false;
+
+ if (cpumask_test_cpu(buddy, nohz.idle_cpus_mask))
+ return true;
+
+ return false;
+}
+
/*
* Current heuristic for kicking the idle load balancer in the presence
* of an idle cpu is the system.
@@ -5813,6 +5833,10 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
if (rq->nr_running >= 2)
goto need_kick;
+ /* the buddy is idle and not busy so we can pack */
+ if (check_nohz_buddy(cpu))
+ goto need_kick;
+
rcu_read_lock();
for_each_domain(cpu, sd) {
struct sched_group *sg = sd->groups;
--
1.7.9.5
next prev parent reply other threads:[~2013-04-25 17:23 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-25 17:23 [RFC PATCH v4 00/14] sched: packing small tasks Vincent Guittot
2013-04-25 17:23 ` [PATCH 01/14] Revert "sched: Introduce temporary FAIR_GROUP_SCHED dependency for load-tracking" Vincent Guittot
2013-04-25 17:23 ` [PATCH 02/14] sched: add a new SD_SHARE_POWERDOMAIN flag for sched_domain Vincent Guittot
2013-04-25 17:23 ` [PATCH 03/14] sched: pack small tasks Vincent Guittot
2013-04-26 12:30 ` Peter Zijlstra
2013-04-26 13:16 ` Vincent Guittot
2013-04-26 12:38 ` Peter Zijlstra
2013-04-26 13:38 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 04/14] sched: pack the idle load balance Vincent Guittot
2013-04-26 12:49 ` Peter Zijlstra
2013-04-26 13:47 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 05/14] ARM: sched: clear SD_SHARE_POWERDOMAIN Vincent Guittot
2013-04-25 17:23 ` [PATCH 06/14] sched: add a knob to choose the packing level Vincent Guittot
2013-04-25 17:23 ` [PATCH 07/14] sched: agressively pack at wake/fork/exec Vincent Guittot
2013-04-26 13:08 ` Peter Zijlstra
2013-04-26 14:23 ` Vincent Guittot
2013-04-25 17:23 ` Vincent Guittot [this message]
2013-04-26 13:15 ` [PATCH 08/14] sched: trig ILB on an idle buddy Peter Zijlstra
2013-04-26 14:52 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 09/14] sched: evaluate the activity level of the system Vincent Guittot
2013-05-22 16:50 ` Morten Rasmussen
2013-05-23 8:11 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 10/14] sched: update the buddy CPU Vincent Guittot
2013-04-28 8:20 ` Francesco Lavra
2013-04-29 7:32 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 11/14] sched: filter task pull request Vincent Guittot
2013-04-26 10:00 ` Vincent Guittot
2013-05-22 15:56 ` Morten Rasmussen
2013-05-22 16:03 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 12/14] sched: create a new field with available capacity Vincent Guittot
2013-04-25 17:23 ` [PATCH 13/14] sched: update the cpu_power Vincent Guittot
2013-05-22 15:46 ` Morten Rasmussen
2013-05-22 15:58 ` Vincent Guittot
2013-04-25 17:23 ` [PATCH 14/14] sched: force migration on buddy CPU Vincent Guittot
2013-04-26 12:08 ` [RFC PATCH v4 00/14] sched: packing small tasks Vincent Guittot
2013-04-26 15:00 ` Arjan van de Ven
2013-04-26 15:40 ` Vincent Guittot
2013-04-26 15:46 ` Arjan van de Ven
2013-04-26 15:56 ` Vincent Guittot
2013-05-02 9:12 ` Vincent Guittot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1366910611-20048-9-git-send-email-vincent.guittot@linaro.org \
--to=vincent.guittot@linaro.org \
--cc=linux-arm-kernel@lists.infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).