linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Paul Turner <pjt@google.com>
To: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Bharata B Rao <bharata@linux.vnet.ibm.com>,
	Dhaval Giani <dhaval.giani@gmail.com>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>,
	Srivatsa Vaddagiri <vatsa@in.ibm.com>,
	Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>,
	Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>,
	Ingo Molnar <mingo@elte.hu>, Pavel Emelyanov <xemul@openvz.org>
Subject: [patch 02/16] sched: hierarchical task accounting for SCHED_OTHER
Date: Tue, 21 Jun 2011 00:16:51 -0700	[thread overview]
Message-ID: <20110621071659.904847383@google.com> (raw)
In-Reply-To: 20110621071649.862846205@google.com

[-- Attachment #1: sched-bwc-account_nr_running.patch --]
[-- Type: text/plain, Size: 4530 bytes --]

Introduce hierarchical task accounting for the group scheduling case in CFS, as
well as promoting the responsibility for maintaining rq->nr_running to the
scheduling classes.

The primary motivation for this is that with scheduling classes supporting
bandwidth throttling it is possible for entities participating in throttled
sub-trees to not have root visible changes in rq->nr_running across activate
and de-activate operations.  This in turn leads to incorrect idle and 
weight-per-task load balance decisions.

This also allows us to make a small fixlet to the fastpath in pick_next_task()
under group scheduling.

Note: this issue also exists with the existing sched_rt throttling mechanism.
This patch does not address that.

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>

---
 kernel/sched.c          |    6 ++----
 kernel/sched_fair.c     |   10 ++++++++--
 kernel/sched_rt.c       |    5 ++++-
 kernel/sched_stoptask.c |    2 ++
 4 files changed, 16 insertions(+), 7 deletions(-)

Index: tip/kernel/sched.c
===================================================================
--- tip.orig/kernel/sched.c
+++ tip/kernel/sched.c
@@ -308,7 +308,7 @@ struct task_group root_task_group;
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight load;
-	unsigned long nr_running;
+	unsigned long nr_running, h_nr_running;
 
 	u64 exec_clock;
 	u64 min_vruntime;
@@ -1830,7 +1830,6 @@ static void activate_task(struct rq *rq,
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
-	inc_nr_running(rq);
 }
 
 /*
@@ -1842,7 +1841,6 @@ static void deactivate_task(struct rq *r
 		rq->nr_uninterruptible++;
 
 	dequeue_task(rq, p, flags);
-	dec_nr_running(rq);
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -4194,7 +4192,7 @@ pick_next_task(struct rq *rq)
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(rq->nr_running == rq->cfs.nr_running)) {
+	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq);
 		if (likely(p))
 			return p;
Index: tip/kernel/sched_fair.c
===================================================================
--- tip.orig/kernel/sched_fair.c
+++ tip/kernel/sched_fair.c
@@ -1332,16 +1332,19 @@ enqueue_task_fair(struct rq *rq, struct 
 			break;
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);
+		cfs_rq->h_nr_running++;
 		flags = ENQUEUE_WAKEUP;
 	}
 
 	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		cfs_rq = cfs_rq_of(se);
+		cfs_rq->h_nr_running++;
 
 		update_cfs_load(cfs_rq, 0);
 		update_cfs_shares(cfs_rq);
 	}
 
+	inc_nr_running(rq);
 	hrtick_update(rq);
 }
 
@@ -1361,6 +1364,7 @@ static void dequeue_task_fair(struct rq 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
+		cfs_rq->h_nr_running--;
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
@@ -1379,12 +1383,14 @@ static void dequeue_task_fair(struct rq 
 	}
 
 	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		cfs_rq = cfs_rq_of(se);
+		cfs_rq->h_nr_running--;
 
 		update_cfs_load(cfs_rq, 0);
 		update_cfs_shares(cfs_rq);
 	}
 
+	dec_nr_running(rq);
 	hrtick_update(rq);
 }
 
Index: tip/kernel/sched_rt.c
===================================================================
--- tip.orig/kernel/sched_rt.c
+++ tip/kernel/sched_rt.c
@@ -949,6 +949,8 @@ enqueue_task_rt(struct rq *rq, struct ta
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
+
+	inc_nr_running(rq);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -959,6 +961,8 @@ static void dequeue_task_rt(struct rq *r
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
+
+	dec_nr_running(rq);
 }
 
 /*
@@ -1851,4 +1855,3 @@ static void print_rt_stats(struct seq_fi
 	rcu_read_unlock();
 }
 #endif /* CONFIG_SCHED_DEBUG */
-
Index: tip/kernel/sched_stoptask.c
===================================================================
--- tip.orig/kernel/sched_stoptask.c
+++ tip/kernel/sched_stoptask.c
@@ -34,11 +34,13 @@ static struct task_struct *pick_next_tas
 static void
 enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
+	inc_nr_running(rq);
 }
 
 static void
 dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
+	dec_nr_running(rq);
 }
 
 static void yield_task_stop(struct rq *rq)



  parent reply	other threads:[~2011-06-21  7:27 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-21  7:16 [patch 00/16] CFS Bandwidth Control v7 Paul Turner
2011-06-21  7:16 ` [patch 01/16] sched: (fixlet) dont update shares twice on on_rq parent Paul Turner
2011-06-21  7:16 ` Paul Turner [this message]
2011-06-21  7:16 ` [patch 03/16] sched: introduce primitives to account for CFS bandwidth tracking Paul Turner
2011-06-22 10:52   ` Peter Zijlstra
2011-07-06 21:38     ` Paul Turner
2011-07-07 11:32       ` Peter Zijlstra
2011-06-21  7:16 ` [patch 04/16] sched: validate CFS quota hierarchies Paul Turner
2011-06-22  5:43   ` Bharata B Rao
2011-06-22  6:57     ` Paul Turner
2011-06-22  9:38   ` Hidetoshi Seto
2011-06-21  7:16 ` [patch 05/16] sched: accumulate per-cfs_rq cpu usage and charge against bandwidth Paul Turner
2011-06-21  7:16 ` [patch 06/16] sched: add a timer to handle CFS bandwidth refresh Paul Turner
2011-06-22  9:38   ` Hidetoshi Seto
2011-06-21  7:16 ` [patch 07/16] sched: expire invalid runtime Paul Turner
2011-06-22  9:38   ` Hidetoshi Seto
2011-06-22 15:47   ` Peter Zijlstra
2011-06-28  4:42     ` Paul Turner
2011-06-29  2:29       ` Paul Turner
2011-06-21  7:16 ` [patch 08/16] sched: throttle cfs_rq entities which exceed their local runtime Paul Turner
2011-06-22  7:11   ` Bharata B Rao
2011-06-22 16:07   ` Peter Zijlstra
2011-06-22 16:54     ` Paul Turner
2011-06-21  7:16 ` [patch 09/16] sched: unthrottle cfs_rq(s) who ran out of quota at period refresh Paul Turner
2011-06-22 17:29   ` Peter Zijlstra
2011-06-28  4:40     ` Paul Turner
2011-06-28  9:11       ` Peter Zijlstra
2011-06-29  3:37         ` Paul Turner
2011-06-21  7:16 ` [patch 10/16] sched: throttle entities exceeding their allowed bandwidth Paul Turner
2011-06-22  9:39   ` Hidetoshi Seto
2011-06-21  7:17 ` [patch 11/16] sched: allow for positional tg_tree walks Paul Turner
2011-06-21  7:17 ` [patch 12/16] sched: prevent interactions with throttled entities Paul Turner
2011-06-22 21:34   ` Peter Zijlstra
2011-06-28  4:43     ` Paul Turner
2011-06-23 11:49   ` Peter Zijlstra
2011-06-28  4:38     ` Paul Turner
2011-06-21  7:17 ` [patch 13/16] sched: migrate throttled tasks on HOTPLUG Paul Turner
2011-06-21  7:17 ` [patch 14/16] sched: add exports tracking cfs bandwidth control statistics Paul Turner
2011-06-21  7:17 ` [patch 15/16] sched: return unused runtime on voluntary sleep Paul Turner
2011-06-21  7:33   ` Paul Turner
2011-06-22  9:39   ` Hidetoshi Seto
2011-06-23 15:26   ` Peter Zijlstra
2011-06-28  1:42     ` Paul Turner
2011-06-28 10:01       ` Peter Zijlstra
2011-06-28 18:45         ` Paul Turner
2011-06-21  7:17 ` [patch 16/16] sched: add documentation for bandwidth control Paul Turner
2011-06-21 10:30   ` Hidetoshi Seto
2011-06-21 19:46     ` Paul Turner
2011-06-22 10:05 ` [patch 00/16] CFS Bandwidth Control v7 Hidetoshi Seto
2011-06-23 12:06   ` Peter Zijlstra
2011-06-23 12:43     ` Ingo Molnar
2011-06-24  5:11       ` Hidetoshi Seto
2011-06-26 10:35         ` Ingo Molnar
2011-06-29  4:05           ` Hu Tao
2011-07-01 12:28             ` Ingo Molnar
2011-07-05  3:58               ` Hu Tao
2011-07-05  8:50                 ` Ingo Molnar
2011-07-05  8:52                   ` Ingo Molnar
2011-07-07  3:53                     ` Hu Tao

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=20110621071659.904847383@google.com \
    --to=pjt@google.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=bharata@linux.vnet.ibm.com \
    --cc=dhaval.giani@gmail.com \
    --cc=kamalesh@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=seto.hidetoshi@jp.fujitsu.com \
    --cc=svaidy@linux.vnet.ibm.com \
    --cc=vatsa@in.ibm.com \
    --cc=xemul@openvz.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).