[RFC][PATCH 25/26] sched, numa: Only migrate long-running entities

[Peter Zijlstra]

It doesn't make much sense to memory migrate short running things.

Suggested-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
---
 kernel/sched/numa.c |   43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
--- a/kernel/sched/numa.c
+++ b/kernel/sched/numa.c
@@ -15,6 +15,8 @@ struct numa_ops {
 	void		(*mem_migrate)(struct numa_entity *ne, int node);
 	void		(*cpu_migrate)(struct numa_entity *ne, int node);
 
+	u64		(*cpu_runtime)(struct numa_entity *ne);
+
 	bool		(*tryget)(struct numa_entity *ne);
 	void		(*put)(struct numa_entity *ne);
 };
@@ -196,6 +198,21 @@ static void process_mem_migrate(struct n
 	lazy_migrate_process(ne_mm(ne), node);
 }
 
+static u64 process_cpu_runtime(struct numa_entity *ne)
+{
+	struct task_struct *p, *t;
+	u64 runtime = 0;
+
+	rcu_read_lock();
+	t = p = ne_owner(ne);
+	if (p) do {
+		runtime += t->se.sum_exec_runtime; // @#$#@ 32bit
+	} while ((t = next_thread(t)) != p);
+	rcu_read_unlock();
+
+	return runtime;
+}
+
 static bool process_tryget(struct numa_entity *ne)
 {
 	/*
@@ -219,6 +236,8 @@ static const struct numa_ops process_num
 	.mem_migrate	= process_mem_migrate,
 	.cpu_migrate	= process_cpu_migrate,
 
+	.cpu_runtime	= process_cpu_runtime,
+
 	.tryget		= process_tryget,
 	.put		= process_put,
 };
@@ -616,6 +635,14 @@ static bool can_move_ne(struct numa_enti
 	 * XXX: consider mems_allowed, stinking cpusets has mems_allowed
 	 * per task and it can actually differ over a whole process, la-la-la.
 	 */
+
+	/*
+	 * Don't bother migrating memory if there's less than 1 second
+	 * of runtime on the tasks.
+	 */
+	if (ne->nops->cpu_runtime(ne) < NSEC_PER_SEC)
+		return false;
+
 	return true;
 }
 
@@ -1000,6 +1027,20 @@ static void numa_group_cpu_migrate(struc
 	rcu_read_unlock();
 }
 
+static u64 numa_group_cpu_runtime(struct numa_entity *ne)
+{
+	struct numa_group *ng = ne_ng(ne);
+	struct task_struct *p;
+	u64 runtime = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(p, &ng->tasks, ng_entry)
+		runtime += p->se.sum_exec_runtime; // @#$# 32bit
+	rcu_read_unlock();
+
+	return runtime;
+}
+
 static bool numa_group_tryget(struct numa_entity *ne)
 {
 	/*
@@ -1020,6 +1061,8 @@ static const struct numa_ops numa_group_
 	.mem_migrate	= numa_group_mem_migrate,
 	.cpu_migrate	= numa_group_cpu_migrate,
 
+	.cpu_runtime	= numa_group_cpu_runtime,
+
 	.tryget		= numa_group_tryget,
 	.put		= numa_group_put,
 };


--
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/