Merge branches 'sched/rt' and 'sched/urgent' into sched/core

[linux-2.6-omap-h63xx.git] / kernel / sched_fair.c

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a7e50ba185ac0a843ac16604e13a721ca8e4cb8e..bc1563e7a248d421932f60ce0e4ebabd68a59145 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1309,16 +1309,63 @@ out:
 }
 #endif /* CONFIG_SMP */
 
-static unsigned long wakeup_gran(struct sched_entity *se)
+/*
+ * Adaptive granularity
+ *
+ * se->avg_wakeup gives the average time a task runs until it does a wakeup,
+ * with the limit of wakeup_gran -- when it never does a wakeup.
+ *
+ * So the smaller avg_wakeup is the faster we want this task to preempt,
+ * but we don't want to treat the preemptee unfairly and therefore allow it
+ * to run for at least the amount of time we'd like to run.
+ *
+ * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
+ *
+ * NOTE: we use *nr_running to scale with load, this nicely matches the
+ *       degrading latency on load.
+ */
+static unsigned long
+adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
+{
+       u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+       u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
+       u64 gran = 0;
+
+       if (this_run < expected_wakeup)
+               gran = expected_wakeup - this_run;
+
+       return min_t(s64, gran, sysctl_sched_wakeup_granularity);
+}
+
+static unsigned long
+wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 {
        unsigned long gran = sysctl_sched_wakeup_granularity;
 
+       if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
+               gran = adaptive_gran(curr, se);
+
        /*
-        * More easily preempt - nice tasks, while not making it harder for
-        * + nice tasks.
+        * Since its curr running now, convert the gran from real-time
+        * to virtual-time in his units.
         */
-       if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD)
-               gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+       if (sched_feat(ASYM_GRAN)) {
+               /*
+                * By using 'se' instead of 'curr' we penalize light tasks, so
+                * they get preempted easier. That is, if 'se' < 'curr' then
+                * the resulting gran will be larger, therefore penalizing the
+                * lighter, if otoh 'se' > 'curr' then the resulting gran will
+                * be smaller, again penalizing the lighter task.
+                *
+                * This is especially important for buddies when the leftmost
+                * task is higher priority than the buddy.
+                */
+               if (unlikely(se->load.weight != NICE_0_LOAD))
+                       gran = calc_delta_fair(gran, se);
+       } else {
+               if (unlikely(curr->load.weight != NICE_0_LOAD))
+                       gran = calc_delta_fair(gran, curr);
+       }
 
        return gran;
 }
@@ -1345,7 +1392,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
        if (vdiff <= 0)
                return -1;
 
-       gran = wakeup_gran(curr);
+       gran = wakeup_gran(curr, se);
        if (vdiff > gran)
                return 1;