sched debug: check spread

debug feature: check how well we schedule within a reasonable
vruntime 'spread' range. (note that CPU overload can increase
the spread, so this is not a hard condition, but normal loads
should be within the spread.)

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

3 files changed, 22 insertions, 0 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index fe1165b226a1..213294fdcd0f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -250,6 +250,9 @@ struct cfs_rq {
          * It is set to NULL otherwise (i.e when none are currently running).
          */
         struct sched_entity *curr;
+
+        unsigned long nr_spread_over;
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
         struct rq *rq;  /* cpu runqueue to which this cfs_rq is attached */
 
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index b24f17de19e3..4659c90c3418 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -140,6 +140,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
         SEQ_printf(m, "  .%-30s: %ld\n", "bkl_cnt",
                         rq->bkl_cnt);
 #endif
+        SEQ_printf(m, "  .%-30s: %ld\n", "nr_spread_over",
+                        cfs_rq->nr_spread_over);
 }
 
 static void print_cpu(struct seq_file *m, int cpu)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 87acc5cedd2d..8ea4c9b3e411 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -447,6 +447,19 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 #endif
 }
 
+static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+#ifdef CONFIG_SCHED_DEBUG
+        s64 d = se->vruntime - cfs_rq->min_vruntime;
+
+        if (d < 0)
+                d = -d;
+
+        if (d > 3*sysctl_sched_latency)
+                schedstat_inc(cfs_rq, nr_spread_over);
+#endif
+}
+
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
@@ -494,6 +507,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
         }
 
         update_stats_enqueue(cfs_rq, se);
+        check_spread(cfs_rq, se);
         if (se != cfs_rq->curr)
                 __enqueue_entity(cfs_rq, se);
         account_entity_enqueue(cfs_rq, se);
@@ -587,6 +601,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 
         update_stats_curr_end(cfs_rq, prev);
 
+        check_spread(cfs_rq, prev);
         if (prev->on_rq) {
                 update_stats_wait_start(cfs_rq, prev);
                 /* Put 'current' back into the tree. */
@@ -996,6 +1011,8 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
         }
 
         update_stats_enqueue(cfs_rq, se);
+        check_spread(cfs_rq, se);
+        check_spread(cfs_rq, curr);
         __enqueue_entity(cfs_rq, se);
         account_entity_enqueue(cfs_rq, se);
         resched_task(rq->curr);