lkml.org 
[lkml]   [2012]   [Nov]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 28/33] sched: Use the best-buddy 'ideal cpu' in balancing decisions
Date
Now that we have a notion of (one of the) best CPUs we interrelate
with in terms of memory usage, use that information to improve
can_migrate_task() balancing decisions: allow the migration to
occur even if we locally cache-hot, if we are on another node
and want to migrate towards our best buddy's node.

( Note that this is not hard affinity - if imbalance persists long
enough then the scheduler will eventually balance tasks anyway,
to maximize CPU utilization. )

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/fair.c | 35 ++++++++++++++++++++++++++++++++---
kernel/sched/features.h | 2 ++
2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 67f7fd2..24a5588 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -840,6 +840,14 @@ static void task_numa_migrate(struct task_struct *p, int next_cpu)
p->numa_migrate_seq = 0;
}

+static int task_ideal_cpu(struct task_struct *p)
+{
+ if (!sched_feat(IDEAL_CPU))
+ return -1;
+
+ return p->ideal_cpu;
+}
+
/*
* Called for every full scan - here we consider switching to a new
* shared buddy, if the one we found during this scan is good enough:
@@ -1028,7 +1036,7 @@ out_hit:
* but don't stop the discovery of process level sharing
* either:
*/
- if (this_task->mm == last_task->mm)
+ if (sched_feat(IDEAL_CPU_THREAD_BIAS) && this_task->mm == last_task->mm)
pages *= 2;

this_task->shared_buddy_faults_curr += pages;
@@ -1189,6 +1197,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
}
#else /* !CONFIG_NUMA_BALANCING: */
#ifdef CONFIG_SMP
+static inline int task_ideal_cpu(struct task_struct *p) { return -1; }
static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) { }
#endif
static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) { }
@@ -4064,6 +4073,7 @@ struct lb_env {
static void move_task(struct task_struct *p, struct lb_env *env)
{
deactivate_task(env->src_rq, p, 0);
+
set_task_cpu(p, env->dst_cpu);
activate_task(env->dst_rq, p, 0);
check_preempt_curr(env->dst_rq, p, 0);
@@ -4242,15 +4252,17 @@ static bool can_migrate_numa_task(struct task_struct *p, struct lb_env *env)
*
* LBF_NUMA_RUN -- numa only, only allow improvement
* LBF_NUMA_SHARED -- shared only
+ * LBF_NUMA_IDEAL -- ideal only
*
* LBF_KEEP_SHARED -- do not touch shared tasks
*/

/* a numa run can only move numa tasks about to improve things */
if (env->flags & LBF_NUMA_RUN) {
- if (task_numa_shared(p) < 0)
+ if (task_numa_shared(p) < 0 && task_ideal_cpu(p) < 0)
return false;
- /* can only pull shared tasks */
+
+ /* If we are only allowed to pull shared tasks: */
if ((env->flags & LBF_NUMA_SHARED) && !task_numa_shared(p))
return false;
} else {
@@ -4307,6 +4319,23 @@ static int can_migrate_task(struct task_struct *p, struct lb_env *env)
if (!can_migrate_running_task(p, env))
return false;

+#ifdef CONFIG_NUMA_BALANCING
+ /* If we are only allowed to pull ideal tasks: */
+ if ((task_ideal_cpu(p) >= 0) && (p->shared_buddy_faults > 1000)) {
+ int ideal_node;
+ int dst_node;
+
+ BUG_ON(env->dst_cpu < 0);
+
+ ideal_node = cpu_to_node(p->ideal_cpu);
+ dst_node = cpu_to_node(env->dst_cpu);
+
+ if (ideal_node == dst_node)
+ return true;
+ return false;
+ }
+#endif
+
if (env->sd->flags & SD_NUMA)
return can_migrate_numa_task(p, env);

diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index b75a10d..737d2c8 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -66,6 +66,8 @@ SCHED_FEAT(TTWU_QUEUE, true)
SCHED_FEAT(FORCE_SD_OVERLAP, false)
SCHED_FEAT(RT_RUNTIME_SHARE, true)
SCHED_FEAT(LB_MIN, false)
+SCHED_FEAT(IDEAL_CPU, true)
+SCHED_FEAT(IDEAL_CPU_THREAD_BIAS, false)

#ifdef CONFIG_NUMA_BALANCING
/* Do the working set probing faults: */
--
1.7.11.7


\
 
 \ /
  Last update: 2012-11-24 20:21    [W:0.357 / U:8.700 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site