[tip:sched/numa] sched/numa: Only migrate long-running entities

[tip:sched/numa] sched/numa: Only migrate long-running entities

[tip-bot for Peter Zijlstra]

Commit-ID:  28a5d43566d3c72a75eb07051833901eec6e2602
Gitweb:     http://git.kernel.org/tip/28a5d43566d3c72a75eb07051833901eec6e2602
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Fri, 9 Mar 2012 11:52:14 +0100
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 18 May 2012 08:16:24 +0200

sched/numa: Only migrate long-running entities

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

Suggested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Paul Turner <pjt@google.com>
Cc: Dan Smith <danms@us.ibm.com>
Cc: Bharata B Rao <bharata.rao@gmail.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-yhxhkcnevwerp7qzejirdmgv@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/numa.c |   27 +++++++++++++++++++++++++++
 1 files changed, 27 insertions(+), 0 deletions(-)

diff --git a/kernel/sched/numa.c b/kernel/sched/numa.c
index 6088165..7712744 100644
--- a/kernel/sched/numa.c
+++ b/kernel/sched/numa.c
@@ -27,6 +27,8 @@ 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);
 };
@@ -208,6 +210,21 @@ static void process_mem_migrate(struct numa_entity *ne, int node)
 	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)
 {
 	/*
@@ -231,6 +248,8 @@ static const struct numa_ops process_numa_ops = {
 	.mem_migrate	= process_mem_migrate,
 	.cpu_migrate	= process_cpu_migrate,
 
+	.cpu_runtime	= process_cpu_runtime,
+
 	.tryget		= process_tryget,
 	.put		= process_put,
 };
@@ -611,6 +630,14 @@ static bool can_move_ne(struct numa_entity *ne)
 	 * 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;
 }