From: Ingo Molnar <mingo@kernel.org>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
Paul Turner <pjt@google.com>,
Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
Christoph Lameter <cl@linux.com>, Rik van Riel <riel@redhat.com>,
Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Thomas Gleixner <tglx@linutronix.de>,
Johannes Weiner <hannes@cmpxchg.org>,
Hugh Dickins <hughd@google.com>
Subject: [PATCH 08/10] sched: Converge NUMA migrations
Date: Fri, 30 Nov 2012 20:58:39 +0100 [thread overview]
Message-ID: <1354305521-11583-9-git-send-email-mingo@kernel.org> (raw)
In-Reply-To: <1354305521-11583-1-git-send-email-mingo@kernel.org>
Consolidate the various convergence models and add a new one: when
a strongly converged NUMA task migrates, prefer to migrate it in
the direction of its preferred node.
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
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 | 59 +++++++++++++++++++++++++++++++++++--------------
kernel/sched/features.h | 3 ++-
2 files changed, 44 insertions(+), 18 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1f6104a..10cbfa3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4750,6 +4750,35 @@ done:
return target;
}
+static bool numa_allow_migration(struct task_struct *p, int prev_cpu, int new_cpu)
+{
+#ifdef CONFIG_NUMA_BALANCING
+ if (sched_feat(NUMA_CONVERGE_MIGRATIONS)) {
+ /* Help in the direction of expected convergence: */
+ if (p->convergence_node >= 0 && (cpu_to_node(new_cpu) != p->convergence_node))
+ return false;
+
+ return true;
+ }
+
+ if (sched_feat(NUMA_BALANCE_ALL)) {
+ if (task_numa_shared(p) >= 0)
+ return false;
+
+ return true;
+ }
+
+ if (sched_feat(NUMA_BALANCE_INTERNODE)) {
+ if (task_numa_shared(p) >= 0) {
+ if (cpu_to_node(prev_cpu) != cpu_to_node(new_cpu))
+ return false;
+ }
+ }
+#endif
+ return true;
+}
+
+
/*
* sched_balance_self: balance the current task (running on cpu) in domains
* that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
@@ -4766,7 +4795,8 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
- int prev_cpu = task_cpu(p);
+ int prev0_cpu = task_cpu(p);
+ int prev_cpu = prev0_cpu;
int new_cpu = cpu;
int want_affine = 0;
int sync = wake_flags & WF_SYNC;
@@ -4775,10 +4805,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
return prev_cpu;
#ifdef CONFIG_NUMA_BALANCING
- /* We do NUMA balancing elsewhere: */
- if (sched_feat(NUMA_BALANCE_ALL) && task_numa_shared(p) >= 0)
- return prev_cpu;
-
if (sched_feat(WAKE_ON_IDEAL_CPU) && p->ideal_cpu >= 0)
return p->ideal_cpu;
#endif
@@ -4857,8 +4883,8 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
unlock:
rcu_read_unlock();
- if (sched_feat(NUMA_BALANCE_INTERNODE) && task_numa_shared(p) >= 0 && (cpu_to_node(prev_cpu) != cpu_to_node(new_cpu)))
- return prev_cpu;
+ if (!numa_allow_migration(p, prev0_cpu, new_cpu))
+ return prev0_cpu;
return new_cpu;
}
@@ -5401,8 +5427,11 @@ static bool can_migrate_running_task(struct task_struct *p, struct lb_env *env)
static int can_migrate_task(struct task_struct *p, struct lb_env *env)
{
/* We do NUMA balancing elsewhere: */
- if (sched_feat(NUMA_BALANCE_ALL) && task_numa_shared(p) > 0 && env->failed <= env->sd->cache_nice_tries)
- return false;
+
+ if (env->failed <= env->sd->cache_nice_tries) {
+ if (!numa_allow_migration(p, env->src_rq->cpu, env->dst_cpu))
+ return false;
+ }
if (!can_migrate_pinned_task(p, env))
return false;
@@ -5461,10 +5490,7 @@ static int move_one_task(struct lb_env *env)
if (!can_migrate_task(p, env))
continue;
- if (sched_feat(NUMA_BALANCE_ALL) && task_numa_shared(p) >= 0)
- continue;
-
- if (sched_feat(NUMA_BALANCE_INTERNODE) && task_numa_shared(p) >= 0 && (cpu_to_node(env->src_rq->cpu) != cpu_to_node(env->dst_cpu)))
+ if (!numa_allow_migration(p, env->src_rq->cpu, env->dst_cpu))
continue;
move_task(p, env);
@@ -5527,10 +5553,7 @@ static int move_tasks(struct lb_env *env)
if (!can_migrate_task(p, env))
goto next;
- if (sched_feat(NUMA_BALANCE_ALL) && task_numa_shared(p) >= 0)
- continue;
-
- if (sched_feat(NUMA_BALANCE_INTERNODE) && task_numa_shared(p) >= 0 && (cpu_to_node(env->src_rq->cpu) != cpu_to_node(env->dst_cpu)))
+ if (!numa_allow_migration(p, env->src_rq->cpu, env->dst_cpu))
goto next;
move_task(p, env);
@@ -6520,8 +6543,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.iteration = 0,
};
+#ifdef CONFIG_NUMA_BALANCING
if (sched_feat(NUMA_BALANCE_ALL))
return 1;
+#endif
cpumask_copy(cpus, cpu_active_mask);
max_lb_iterations = cpumask_weight(env.dst_grpmask);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index fd9db0b..9075faf 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -76,9 +76,10 @@ SCHED_FEAT(WAKE_ON_IDEAL_CPU, false)
/* Do the working set probing faults: */
SCHED_FEAT(NUMA, true)
SCHED_FEAT(NUMA_BALANCE_ALL, false)
-SCHED_FEAT(NUMA_BALANCE_INTERNODE, false)
+SCHED_FEAT(NUMA_BALANCE_INTERNODE, false)
SCHED_FEAT(NUMA_LB, false)
SCHED_FEAT(NUMA_GROUP_LB_COMPRESS, true)
SCHED_FEAT(NUMA_GROUP_LB_SPREAD, true)
SCHED_FEAT(MIGRATE_FAULT_STATS, false)
+SCHED_FEAT(NUMA_CONVERGE_MIGRATIONS, true)
#endif
--
1.7.11.7
next prev parent reply other threads:[~2012-11-30 19:59 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-30 19:58 [PATCH 00/10] Latest numa/core release, v18 Ingo Molnar
2012-11-30 19:58 ` [PATCH 01/10] sched: Add "task flipping" support Ingo Molnar
2012-11-30 19:58 ` [PATCH 02/10] sched: Move the NUMA placement logic to a worklet Ingo Molnar
2012-11-30 19:58 ` [PATCH 03/10] numa, mempolicy: Improve CONFIG_NUMA_BALANCING=y OOM behavior Ingo Molnar
2012-11-30 19:58 ` [PATCH 04/10] mm, numa: Turn 4K pte NUMA faults into effective hugepage ones Ingo Molnar
2012-11-30 19:58 ` [PATCH 05/10] sched: Introduce directed NUMA convergence Ingo Molnar
2012-11-30 19:58 ` [PATCH 06/10] sched: Remove statistical NUMA scheduling Ingo Molnar
2012-11-30 19:58 ` [PATCH 07/10] sched: Track quality and strength of convergence Ingo Molnar
2012-11-30 19:58 ` Ingo Molnar [this message]
2012-11-30 19:58 ` [PATCH 09/10] sched: Add convergence strength based adaptive NUMA page fault rate Ingo Molnar
2012-11-30 19:58 ` [PATCH 10/10] sched: Refine the 'shared tasks' memory interleaving logic Ingo Molnar
2012-11-30 20:37 ` [PATCH 00/10] Latest numa/core release, v18 Linus Torvalds
2012-12-01 9:49 ` [RFC PATCH] mm/migration: Don't lock anon vmas in rmap_walk_anon() Ingo Molnar
2012-12-01 12:26 ` [RFC PATCH] mm/migration: Remove anon vma locking from try_to_unmap() use Ingo Molnar
2012-12-01 18:38 ` Linus Torvalds
2012-12-01 18:41 ` Ingo Molnar
2012-12-01 18:50 ` Linus Torvalds
2012-12-01 20:10 ` [PATCH 1/2] mm/rmap: Convert the struct anon_vma::mutex to an rwsem Ingo Molnar
2012-12-01 20:19 ` Rik van Riel
2012-12-02 15:10 ` Ingo Molnar
2012-12-03 13:59 ` Mel Gorman
2012-12-01 20:15 ` [PATCH 2/2] mm/migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable Ingo Molnar
2012-12-01 20:33 ` Rik van Riel
2012-12-02 15:12 ` [PATCH 2/2, v2] " Ingo Molnar
2012-12-02 17:53 ` Rik van Riel
2012-12-04 14:42 ` Michel Lespinasse
2012-12-05 2:59 ` Michel Lespinasse
2012-12-03 14:17 ` [PATCH 2/2] " Mel Gorman
2012-12-04 14:37 ` Michel Lespinasse
2012-12-04 18:17 ` Mel Gorman
2012-12-01 18:55 ` [RFC PATCH] mm/migration: Remove anon vma locking from try_to_unmap() use Rik van Riel
2012-12-01 16:19 ` [RFC PATCH] mm/migration: Don't lock anon vmas in rmap_walk_anon() Rik van Riel
2012-12-01 17:55 ` Linus Torvalds
2012-12-01 18:30 ` Ingo Molnar
2012-12-03 13:41 ` [PATCH 00/10] Latest numa/core release, v18 Mel Gorman
2012-12-04 17:30 ` Thomas Gleixner
2012-12-03 10:43 ` Mel Gorman
2012-12-03 11:32 ` Mel Gorman
2012-12-04 22:49 ` Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1354305521-11583-9-git-send-email-mingo@kernel.org \
--to=mingo@kernel.org \
--cc=Lee.Schermerhorn@hp.com \
--cc=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=pjt@google.com \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).