Patchwork [Precise,SRU] sched: Fix migration thread runtime bogosity

login
register
mail settings
Submitter Tim Gardner
Date Sept. 28, 2012, 7:44 p.m.
Message ID <1348861458-50485-1-git-send-email-tim.gardner@canonical.com>
Download mbox | patch
Permalink /patch/187893/
State New
Headers show

Comments

Tim Gardner - Sept. 28, 2012, 7:44 p.m.
From: Mike Galbraith <mgalbraith@suse.de>

BugLink: http://bugs.launchpad.net/bugs/1057593

Make stop scheduler class do the same accounting as other classes,

Migration threads can be caught in the act while doing exec balancing,
leading to the below due to use of unmaintained ->se.exec_start.  The
load that triggered this particular instance was an apparently out of
control heavily threaded application that does system monitoring in
what equated to an exec bomb, with one of the VERY frequently migrated
tasks being ps.

%CPU   PID USER     CMD
99.3    45 root     [migration/10]
97.7    53 root     [migration/12]
97.0    57 root     [migration/13]
90.1    49 root     [migration/11]
89.6    65 root     [migration/15]
88.7    17 root     [migration/3]
80.4    37 root     [migration/8]
78.1    41 root     [migration/9]
44.2    13 root     [migration/2]

Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1344051854.6739.19.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
(back ported from commit 8f6189684eb4e85e6c593cd710693f09c944450a)

Signed-off-by: Chris J Arges <chris.j.arges@canonical.com>
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>
---
 kernel/sched_stoptask.c |   22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)
Herton Ronaldo Krzesinski - Sept. 28, 2012, 8:46 p.m.

Chris J Arges - Oct. 1, 2012, 5:49 p.m.
On 09/28/2012 03:46 PM, Herton Ronaldo Krzesinski wrote:
> 
I don't believe I'm allowed to ACK this since I'm the one who backported
the patch. Has anybody else had a chance to look at this?
Thanks,
--chris j arges
Tim Gardner - Oct. 1, 2012, 7:01 p.m.

Patch

diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 8b44e7f..85e9da2 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -25,8 +25,10 @@  static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->on_rq)
+	if (stop && stop->on_rq) {
+		stop->se.exec_start = rq->clock_task;
 		return stop;
+	}
 
 	return NULL;
 }
@@ -50,6 +52,21 @@  static void yield_task_stop(struct rq *rq)
 
 static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 {
+	struct task_struct *curr = rq->curr;
+	u64 delta_exec;
+
+	delta_exec = rq->clock_task - curr->se.exec_start;
+	if (unlikely((s64)delta_exec < 0))
+		delta_exec = 0;
+
+	schedstat_set(curr->se.statistics.exec_max,
+			max(curr->se.statistics.exec_max, delta_exec));
+
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
+	curr->se.exec_start = rq->clock_task;
+	cpuacct_charge(curr, delta_exec);
 }
 
 static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
@@ -58,6 +75,9 @@  static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
 
 static void set_curr_task_stop(struct rq *rq)
 {
+	struct task_struct *stop = rq->stop;
+
+	stop->se.exec_start = rq->clock_task;
 }
 
 static void switched_to_stop(struct rq *rq, struct task_struct *p)