sched/numa: Remove numa_has_capacity()

task_numa_find_cpu() helps to find the CPU to swap/move the task to.
It's guarded by numa_has_capacity(). However node not having capacity
shouldn't deter a task swapping if it helps NUMA placement.

Further load_too_imbalanced(), which evaluates possibilities of move/swap,
provides similar checks as numa_has_capacity.

Hence remove numa_has_capacity() to enhance possibilities of task
swapping even if load is imbalanced.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25657.9     25804.1     0.569
1     74435       73413       -1.37

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rik van Riel <riel@surriel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-13-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 3 insertions, 33 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7b4eddec3ccc..3bcf0e864613 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1456,7 +1456,6 @@ struct numa_stats {
 	unsigned long compute_capacity;
 
 	unsigned int nr_running;
-	int has_free_capacity;
 };
 
 /*
@@ -1483,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	 * the @ns structure is NULL'ed and task_numa_compare() will
 	 * not find this node attractive.
 	 *
-	 * We'll either bail at !has_free_capacity, or we'll detect a huge
-	 * imbalance and bail there.
+	 * We'll detect a huge imbalance and bail there.
 	 */
 	if (!cpus)
 		return;
@@ -1495,7 +1493,6 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 
 	capacity = min_t(unsigned, capacity,
 		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
-	ns->has_free_capacity = (ns->nr_running < capacity);
 }
 
 struct task_numa_env {
@@ -1698,31 +1695,6 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 	}
 }
 
-/* Only move tasks to a NUMA node less busy than the current node. */
-static bool numa_has_capacity(struct task_numa_env *env)
-{
-	struct numa_stats *src = &env->src_stats;
-	struct numa_stats *dst = &env->dst_stats;
-
-	if (src->has_free_capacity && !dst->has_free_capacity)
-		return false;
-
-	/*
-	 * Only consider a task move if the source has a higher load
-	 * than the destination, corrected for CPU capacity on each node.
-	 *
-	 *      src->load                dst->load
-	 * --------------------- vs ---------------------
-	 * src->compute_capacity    dst->compute_capacity
-	 */
-	if (src->load * dst->compute_capacity * env->imbalance_pct >
-
-	    dst->load * src->compute_capacity * 100)
-		return true;
-
-	return false;
-}
-
 static int task_numa_migrate(struct task_struct *p)
 {
 	struct task_numa_env env = {
@@ -1777,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p)
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
-	if (numa_has_capacity(&env))
-		task_numa_find_cpu(&env, taskimp, groupimp);
+	task_numa_find_cpu(&env, taskimp, groupimp);
 
 	/*
 	 * Look at other nodes in these cases:
@@ -1808,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p)
 			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
-			if (numa_has_capacity(&env))
-				task_numa_find_cpu(&env, taskimp, groupimp);
+			task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}