Commit-ID: e422fcc17185a0cb36e4d0f9b467ca2c597fd6a8
Gitweb: http://git.kernel.org/tip/e422fcc17185a0cb36e4d0f9b467ca2c597fd6a8
Author: Ingo Molnar <mingo@xxxxxxxxxx>
AuthorDate: Wed, 14 Nov 2012 12:18:29 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Thu, 22 Nov 2012 23:06:36 +0100
sched: Implement NUMA scanning backoff
Back off slowly from scanning, up to sysctl_sched_numa_scan_period_max
(1.6 seconds). Scan faster again if we were forced to switch to
another node.
This makes sure that workload in equilibrium don't get scanned as often
as workloads that are still converging.
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
kernel/sched/core.c | 6 ++++++
kernel/sched/fair.c | 8 +++++++-
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index af0602f..ec3cc74 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6024,6 +6024,12 @@ void sched_setnuma(struct task_struct *p, int node, int shared)
if (on_rq)
enqueue_task(rq, p, 0);
task_rq_unlock(rq, p, &flags);
+
+ /*
+ * Reset the scanning period. If the task converges
+ * on this node then we'll back off again:
+ */
+ p->numa_scan_period = sysctl_sched_numa_scan_period_min;
}
#endif /* CONFIG_NUMA_BALANCING */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8f0e6ba..59fea2e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -865,8 +865,10 @@ static void task_numa_placement(struct task_struct *p)
}
}
- if (max_node != p->numa_max_node)
+ if (max_node != p->numa_max_node) {
sched_setnuma(p, max_node, task_numa_shared(p));
+ goto out_backoff;
+ }
p->numa_migrate_seq++;
if (sched_feat(NUMA_SETTLE) &&
@@ -882,7 +884,11 @@ static void task_numa_placement(struct task_struct *p)
if (shared != task_numa_shared(p)) {
sched_setnuma(p, p->numa_max_node, shared);
p->numa_migrate_seq = 0;
+ goto out_backoff;
}
+ return;
+out_backoff:
+ p->numa_scan_period = min(p->numa_scan_period * 2, sysctl_sched_numa_scan_period_max);
}
/*
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|