[PATCH 6/7] RT: Select tasks based on relative affinity

[Gregory Haskins <ghaskins@novell.com>]

In theory, tasks will be most efficient if they are allowed to re-wake to
the CPU that they last ran on due to cache affinity.  Short of that, it is
cheaper to wake up the current CPU.  If neither of those two are options,
than the lowest CPU will do. 

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
---

 kernel/sched.c |   72 +++++++++++++++++++++++++++++++++++++++++---------------
 1 files changed, 53 insertions(+), 19 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 3c71156..b79b968 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1511,6 +1511,15 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
 /* Only try this algorithm three times */
 #define RT_PUSH_MAX_TRIES 3
 
+static int non_rt_cpu(cpumask_t *mask, int cpu)
+{
+	if (!rt_prio(cpu_rq(cpu)->curr_prio) &&
+	    cpu_isset(cpu, *mask))
+		return 1;
+
+	return 0;
+}
+
 /* Will lock the rq it finds */
 static int find_lowest_cpu(cpumask_t *cpu_mask, struct task_struct *task,
 				 struct rq *this_rq)
@@ -1519,32 +1528,57 @@ static int find_lowest_cpu(cpumask_t *cpu_mask, struct task_struct *task,
 	int dst_cpu = -1;
 	int cpu;
 	int tries;
+	int this_cpu = smp_processor_id();
 
 	for (tries = 0; tries < RT_PUSH_MAX_TRIES; tries++) {
+
 		/*
-		 * Scan each rq for the lowest prio.
+		 * We select a CPU in the following priority:
+		 *
+		 *       task_cpu, this_cpu, first_cpu
+		 *
+		 * for efficiency.
+		 *
+		 * - task_cpu preserves cache affinity
+		 * - this_cpu is (presumably) cheaper to preempt
+		 *   (note that sometimes task_cpu and this_cpu
+		 *   are the same).
+		 * - Finally, we will take whatever is available
+		 *   if the first two don't pan out by scanning.
 		 */
-		for_each_cpu_mask(cpu, *cpu_mask) {
-			struct rq *rq = &per_cpu(runqueues, cpu);
-
-			if (cpu == smp_processor_id())
-				continue;
-
-			/* We look for lowest RT prio or non-rt CPU */
-			if (rq->curr_prio >= MAX_RT_PRIO) {
-				lowest_rq = rq;
-				dst_cpu = cpu;
-				break;
-			}
+		if (non_rt_cpu(cpu_mask, task_cpu(task))) {
+			lowest_rq = task_rq(task);	
+			dst_cpu = lowest_rq->cpu;
+		} else if (non_rt_cpu(cpu_mask, this_cpu)) {
+			dst_cpu = this_cpu;
+			lowest_rq = cpu_rq(this_cpu);	
+		} else {
 
-			/* no locking for now */
-			if (rq->curr_prio > task->prio &&
-			    (!lowest_rq || rq->curr_prio < lowest_rq->curr_prio)) {
-				dst_cpu = cpu;
-				lowest_rq = rq;
+			/*
+			 * Scan each rq for the lowest prio.
+			 */
+			for_each_cpu_mask(cpu, *cpu_mask) {
+				struct rq *rq = &per_cpu(runqueues, cpu);
+				
+				if (cpu == this_cpu)
+					continue;
+				
+				/* We look for lowest RT prio or non-rt CPU */
+				if (rq->curr_prio >= MAX_RT_PRIO) {
+					lowest_rq = rq;
+					dst_cpu = cpu;
+					break;
+				}
+				
+				/* no locking for now */
+				if (rq->curr_prio > task->prio &&
+				    (!lowest_rq || rq->curr_prio < lowest_rq->curr_prio)) {
+					dst_cpu = cpu;
+					lowest_rq = rq;
+				}
 			}
 		}
-
+			
 		if (!lowest_rq) {
 			dst_cpu = -1;
 			break;

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/