sched: reintroduce cache-hot affinity

[powerpc.git] / kernel / sched_fair.c

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f819f94..a17b785 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -25,14 +25,12 @@
  * (default: 20ms, units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
- * 'timeslice length' - timeslices in CFS are of variable length.
- * (to see the precise effective timeslice length of your workload,
- *  run vmstat and monitor the context-switches field)
+ * 'timeslice length' - timeslices in CFS are of variable length
+ * and have no persistent notion like in traditional, time-slice
+ * based scheduling concepts.
  *
- * On SMP systems the value of this is multiplied by the log2 of the
- * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
- * systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
- * Targeted preemption latency for CPU-bound tasks:
+ * (to see the precise effective timeslice length of your workload,
+ *  run vmstat and monitor the context-switches (cs) field)
  */
 const_debug unsigned int sysctl_sched_latency = 20000000ULL;
 
@@ -76,6 +74,8 @@ const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
  */
 const_debug unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
 
+const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -381,15 +381,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
        se->exec_start = rq_of(cfs_rq)->clock;
 }
 
-/*
- * We are descheduling a task - update its stats:
- */
-static inline void
-update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-       se->exec_start = 0;
-}
-
 /**************************************************
  * Scheduling class queueing methods:
  */
@@ -611,8 +602,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
        if (prev->on_rq)
                update_curr(cfs_rq);
 
-       update_stats_curr_end(cfs_rq, prev);
-
        check_spread(cfs_rq, prev);
        if (prev->on_rq) {
                update_stats_wait_start(cfs_rq, prev);
@@ -830,6 +819,12 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
                resched_task(curr);
                return;
        }
+       /*
+        * Batch tasks do not preempt (their preemption is driven by
+        * the tick):
+        */
+       if (unlikely(p->policy == SCHED_BATCH))
+               return;
 
        if (sched_feat(WAKEUP_PREEMPT)) {
                while (!is_same_group(se, pse)) {