sched/numa: Select a preferred node with the most numa hinting faults

This patch selects a preferred node for a task to run on based on the
NUMA hinting faults. This information is later used to migrate tasks
towards the node during balancing.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-21-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a810e95bca2b88b40dd883aa87ee7ccc67e0ebe7..b1fc75e7187b55455720731ad46a67802aaecdf6 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1344,6 +1344,7 @@ struct task_struct {
        struct callback_head numa_work;
 
        unsigned long *numa_faults;
+       int numa_preferred_nid;
 #endif /* CONFIG_NUMA_BALANCING */
 
        struct rcu_head rcu;

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6808d35fd7edc5cce13f67e8971620e6eabc6425..d15cd70f85b5231628bd6ef8d551939384218c4e 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1633,6 +1633,7 @@ static void __sched_fork(struct task_struct *p)
        p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
        p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
        p->numa_scan_period = sysctl_numa_balancing_scan_delay;
+       p->numa_preferred_nid = -1;
        p->numa_work.next = &p->numa_work;
        p->numa_faults = NULL;
 #endif /* CONFIG_NUMA_BALANCING */

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0bb3e0aa110b21ea664a9c0a0f6224185c34fcd5..9efd34f63e8196c9ab56baa9fc3cdbf0e5185047 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -879,7 +879,8 @@ static unsigned int task_scan_max(struct task_struct *p)
 
 static void task_numa_placement(struct task_struct *p)
 {
-       int seq;
+       int seq, nid, max_nid = -1;
+       unsigned long max_faults = 0;
 
        if (!p->mm)     /* for example, ksmd faulting in a user's mm */
                return;
@@ -889,7 +890,19 @@ static void task_numa_placement(struct task_struct *p)
        p->numa_scan_seq = seq;
        p->numa_scan_period_max = task_scan_max(p);
 
-       /* FIXME: Scheduling placement policy hints go here */
+       /* Find the node with the highest number of faults */
+       for_each_online_node(nid) {
+               unsigned long faults = p->numa_faults[nid];
+               p->numa_faults[nid] >>= 1;
+               if (faults > max_faults) {
+                       max_faults = faults;
+                       max_nid = nid;
+               }
+       }
+
+       /* Update the tasks preferred node if necessary */
+       if (max_faults && max_nid != p->numa_preferred_nid)
+               p->numa_preferred_nid = max_nid;
 }
 
 /*