sched: keep total / count stats in addition to the max for

Right now, the linux kernel (with scheduler statistics enabled) keeps track
of the maximum time a process is waiting to be scheduled. While the maximum
is a very useful metric, tracking average and total is equally useful
(at least for latencytop) to figure out the accumulated effect of scheduler
delays. The accumulated effect is important to judge the performance impact
of scheduler tuning/behavior.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 734f6d8f6ed547469be04211d72d2e97669739ae..df5b24ee80b307044bb5292404d1fc41686c8a6d 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -895,6 +895,8 @@ struct sched_entity {
 #ifdef CONFIG_SCHEDSTATS
        u64                     wait_start;
        u64                     wait_max;
+       u64                     wait_count;
+       u64                     wait_sum;
 
        u64                     sleep_start;
        u64                     sleep_max;

diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9e5de098d47129207f81f90aac51602dc1eb0d34..4b5e24cf2f4a98387c849d8461b85a8a9c79aa55 100644 (file)
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -300,6 +300,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
        PN(se.exec_max);
        PN(se.slice_max);
        PN(se.wait_max);
+       PN(se.wait_sum);
+       P(se.wait_count);
        P(sched_info.bkl_count);
        P(se.nr_migrations);
        P(se.nr_migrations_cold);
@@ -367,6 +369,8 @@ void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
        p->se.wait_max                          = 0;
+       p->se.wait_sum                          = 0;
+       p->se.wait_count                        = 0;
        p->se.sleep_max                         = 0;
        p->se.sum_sleep_runtime                 = 0;
        p->se.block_max                         = 0;

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 45ff4e9411e0b3fd4071e997adf0ee70791b0cb5..72e25c7a3a186dc9830c206662dca4ad7d5892cb 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -385,6 +385,9 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
        schedstat_set(se->wait_max, max(se->wait_max,
                        rq_of(cfs_rq)->clock - se->wait_start));
+       schedstat_set(se->wait_count, se->wait_count + 1);
+       schedstat_set(se->wait_sum, se->wait_sum +
+                       rq_of(cfs_rq)->clock - se->wait_start);
        schedstat_set(se->wait_start, 0);
 }