sched: Make struct sched_statistics independent of fair sched class
If we want to use the schedstats facility to trace other sched classes, we
should make it independent of fair sched class. The struct sched_statistics
is the schedular statistics of a task_struct or a task_group. So we can
move it into struct task_struct and struct task_group to achieve the goal.
After the patch, schestats are orgnized as follows,
struct task_struct {
...
struct sched_entity se;
struct sched_rt_entity rt;
struct sched_dl_entity dl;
...
struct sched_statistics stats;
...
};
Regarding the task group, schedstats is only supported for fair group
sched, and a new struct sched_entity_stats is introduced, suggested by
Peter -
struct sched_entity_stats {
struct sched_entity se;
struct sched_statistics stats;
} __no_randomize_layout;
Then with the se in a task_group, we can easily get the stats.
The sched_statistics members may be frequently modified when schedstats is
enabled, in order to avoid impacting on random data which may in the same
cacheline with them, the struct sched_statistics is defined as cacheline
aligned.
As this patch changes the core struct of scheduler, so I verified the
performance it may impact on the scheduler with 'perf bench sched
pipe', suggested by Mel. Below is the result, in which all the values
are in usecs/op.
Before After
kernel.sched_schedstats=0 5.2~5.4 5.2~5.4
kernel.sched_schedstats=1 5.3~5.5 5.3~5.5
[These data is a little difference with the earlier version, that is
because my old test machine is destroyed so I have to use a new
different test machine.]
Almost no impact on the sched performance.
No functional change.
[lkp@intel.com: reported build failure in earlier version]
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20210905143547.4668-3-laoar.shao@gmail.com
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ccb604a..a1741e0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3489,11 +3489,11 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
#ifdef CONFIG_SMP
if (cpu == rq->cpu) {
__schedstat_inc(rq->ttwu_local);
- __schedstat_inc(p->se.statistics.nr_wakeups_local);
+ __schedstat_inc(p->stats.nr_wakeups_local);
} else {
struct sched_domain *sd;
- __schedstat_inc(p->se.statistics.nr_wakeups_remote);
+ __schedstat_inc(p->stats.nr_wakeups_remote);
rcu_read_lock();
for_each_domain(rq->cpu, sd) {
if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
@@ -3505,14 +3505,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
}
if (wake_flags & WF_MIGRATED)
- __schedstat_inc(p->se.statistics.nr_wakeups_migrate);
+ __schedstat_inc(p->stats.nr_wakeups_migrate);
#endif /* CONFIG_SMP */
__schedstat_inc(rq->ttwu_count);
- __schedstat_inc(p->se.statistics.nr_wakeups);
+ __schedstat_inc(p->stats.nr_wakeups);
if (wake_flags & WF_SYNC)
- __schedstat_inc(p->se.statistics.nr_wakeups_sync);
+ __schedstat_inc(p->stats.nr_wakeups_sync);
}
/*
@@ -4196,7 +4196,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
#ifdef CONFIG_SCHEDSTATS
/* Even if schedstat is disabled, there should not be garbage */
- memset(&p->se.statistics, 0, sizeof(p->se.statistics));
+ memset(&p->stats, 0, sizeof(p->stats));
#endif
RB_CLEAR_NODE(&p->dl.rb_node);
@@ -9553,9 +9553,9 @@ void normalize_rt_tasks(void)
continue;
p->se.exec_start = 0;
- schedstat_set(p->se.statistics.wait_start, 0);
- schedstat_set(p->se.statistics.sleep_start, 0);
- schedstat_set(p->se.statistics.block_start, 0);
+ schedstat_set(p->stats.wait_start, 0);
+ schedstat_set(p->stats.sleep_start, 0);
+ schedstat_set(p->stats.block_start, 0);
if (!dl_task(p) && !rt_task(p)) {
/*
@@ -10397,11 +10397,14 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
if (schedstat_enabled() && tg != &root_task_group) {
+ struct sched_statistics *stats;
u64 ws = 0;
int i;
- for_each_possible_cpu(i)
- ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+ for_each_possible_cpu(i) {
+ stats = __schedstats_from_se(tg->se[i]);
+ ws += schedstat_val(stats->wait_sum);
+ }
seq_printf(sf, "wait_sum %llu\n", ws);
}