[PATCH 6/7] numa,sched: normalize faults_from stats and weigh by CPU use

[riel]

From: Rik van Riel <riel@xxxxxxxxxx>

The tracepoint has made it abundantly clear that the naive
implementation of the faults_from code has issues.

Specifically, the garbage collector in some workloads will
access orders of magnitudes more memory than the threads
that do all the active work. This resulted in the node with
the garbage collector being marked the only active node in
the group.

This issue is avoided if we weigh the statistics by CPU use
of each task in the numa group, instead of by how many faults
each thread has occurred.

To achieve this, we normalize the number of faults to the
fraction of faults that occurred on each node, and then
multiply that fraction by the fraction of CPU time the
task has used since the last time task_numa_placement was
invoked.

This way the nodes in the active node mask will be the ones
where the tasks from the numa group are most actively running,
and the influence of eg. the garbage collector and other
do-little threads is properly minimized.

Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Chegu Vinod <chegu_vinod@xxxxxx>
Signed-off-by: Rik van Riel <riel@xxxxxxxxxx>
---
 include/linux/sched.h |  2 ++
 kernel/sched/core.c   |  2 ++
 kernel/sched/fair.c   | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0af6c1a..52de567 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1471,6 +1471,8 @@ struct task_struct {
 	int numa_preferred_nid;
 	unsigned long numa_migrate_retry;
 	u64 node_stamp;			/* migration stamp  */
+	u64 last_task_numa_placement;
+	u64 last_sum_exec_runtime;
 	struct callback_head numa_work;
 
 	struct list_head numa_entry;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f45fd5..9a0908a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1758,6 +1758,8 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
 	p->numa_faults_buffer = NULL;
+	p->last_task_numa_placement = 0;
+	p->last_sum_exec_runtime = 0;
 
 	INIT_LIST_HEAD(&p->numa_entry);
 	p->numa_group = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8e0a53a..0d395a0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1422,11 +1422,41 @@ static void update_task_scan_period(struct task_struct *p,
 	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 }
 
+/*
+ * Get the fraction of time the task has been running since the last
+ * NUMA placement cycle. The scheduler keeps similar statistics, but
+ * decays those on a 32ms period, which is orders of magnitude off
+ * from the dozens-of-seconds NUMA balancing period. Use the scheduler
+ * stats only if the task is so new there are no NUMA statistics yet.
+ */
+static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
+{
+	u64 runtime, delta, now;
+	/* Use the start of this time slice to avoid calculations. */
+	now = p->se.exec_start;
+	runtime = p->se.sum_exec_runtime;
+
+	if (p->last_task_numa_placement) {
+		delta = runtime - p->last_sum_exec_runtime;
+		*period = now - p->last_task_numa_placement;
+	} else {
+		delta = p->se.avg.runnable_avg_sum;
+		*period = p->se.avg.runnable_avg_period;
+	}
+
+	p->last_sum_exec_runtime = runtime;
+	p->last_task_numa_placement = now;
+
+	return delta;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1, max_group_nid = -1;
 	unsigned long max_faults = 0, max_group_faults = 0;
 	unsigned long fault_types[2] = { 0, 0 };
+	unsigned long total_faults;
+	u64 runtime, period;
 	spinlock_t *group_lock = NULL;
 
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1435,6 +1465,10 @@ static void task_numa_placement(struct task_struct *p)
 	p->numa_scan_seq = seq;
 	p->numa_scan_period_max = task_scan_max(p);
 
+	total_faults = p->numa_faults_locality[0] +
+		       p->numa_faults_locality[1] + 1;
+	runtime = numa_get_avg_runtime(p, &period);
+
 	/* If the task is part of a group prevent parallel updates to group stats */
 	if (p->numa_group) {
 		group_lock = &p->numa_group->lock;
@@ -1447,7 +1481,7 @@ static void task_numa_placement(struct task_struct *p)
 		int priv, i;
 
 		for (priv = 0; priv < 2; priv++) {
-			long diff, f_diff;
+			long diff, f_diff, f_weight;
 
 			i = task_faults_idx(nid, priv);
 			diff = -p->numa_faults[i];
@@ -1459,8 +1493,18 @@ static void task_numa_placement(struct task_struct *p)
 			fault_types[priv] += p->numa_faults_buffer[i];
 			p->numa_faults_buffer[i] = 0;
 
+			/*
+			 * Normalize the faults_from, so all tasks in a group
+			 * count according to CPU use, instead of by the raw
+			 * number of faults. Tasks with little runtime have
+			 * little over-all impact on throughput, and thus their
+			 * faults are less important.
+			 */
+			f_weight = (1024 * runtime *
+				   p->numa_faults_from_buffer[i]) /
+				   (total_faults * period + 1);
 			p->numa_faults_from[i] >>= 1;
-			p->numa_faults_from[i] += p->numa_faults_from_buffer[i];
+			p->numa_faults_from[i] += f_weight;
 			p->numa_faults_from_buffer[i] = 0;
 
 			faults += p->numa_faults[i];
-- 
1.8.4.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/