The patch titled
sched: protect calculation of max_pull from integer wrap
has been removed from the -mm tree. Its filename is
sched-protect-calculation-of-max_pull-from-integer-wrap.patch
This patch was dropped because it was folded into sched-implement-smpnice.patch
------------------------------------------------------
Subject: sched: protect calculation of max_pull from integer wrap
From: Peter Williams <pwil3058@xxxxxxxxxxxxxx>
Problem:
As the comment above the calculation of max_pull in the function states,
there is a need to ensure that negative results of the subtractions do
not wrap around to large numbers. This has not been implemented for the
(max_load - busiest_load_per_task) expression and the possible
consequences are for undesirable movement of tasks from one group to
another group. E.g. consider a numa system with two nodes, each
node containing four processors. If there are two processes in node-0
and with node-1 being completely idle, one of those processes will be
moved to node-1 whereas the desired behavior is to retain those two
processes in node-0.
Fix:
Make sure that max_load is greater than busiest_load_per_task before
making the calculation. If it isn't max_pull will be zero and we skip
directly to out_balanced.
Signed-off-by: Peter Williams <pwil3058@xxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
kernel/sched.c | 2 ++
1 file changed, 2 insertions(+)
diff -puN kernel/sched.c~sched-protect-calculation-of-max_pull-from-integer-wrap kernel/sched.c
--- devel/kernel/sched.c~sched-protect-calculation-of-max_pull-from-integer-wrap 2006-06-09 15:18:10.000000000 -0700
+++ devel-akpm/kernel/sched.c 2006-06-09 15:18:10.000000000 -0700
@@ -2171,6 +2171,8 @@ find_busiest_group(struct sched_domain *
* by pulling tasks to us. Be careful of negative numbers as they'll
* appear as very large values with unsigned longs.
*/
+ if (max_load <= busiest_load_per_task)
+ goto out_balanced;
/* Don't want to pull so many tasks that a group would go idle */
max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
_
Patches currently in -mm which might be from pwil3058@xxxxxxxxxxxxxx are
origin.patch
sched-implement-smpnice.patch
sched-protect-calculation-of-max_pull-from-integer-wrap.patch
sched-store-weighted-load-on-up.patch
sched-prevent-high-load-weight-tasks-suppressing-balancing.patch
sched-improve-stability-of-smpnice-load-balancing.patch
sched-improve-smpnice-load-balancing-when-load-per-task.patch
sched-modify-move_tasks-to-improve-load-balancing-outcomes.patch
sched-avoid-unnecessarily-moving-highest-priority-task-move_tasks.patch
sched-avoid-unnecessarily-moving-highest-priority-task-move_tasks-fix-2.patch
sched-uninline-task_rq_lock.patch
sched-add-above-background-load-function.patch
pi-futex-scheduler-support-for-pi.patch
pi-futex-rt-mutex-tester-fix.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
