[tip: sched/core] sched: Introduce task block time in schedstats

From: tip-bot2 for Yafang Shao
Date: Tue Oct 05 2021 - 10:13:14 EST


The following commit has been merged into the sched/core branch of tip:

Commit-ID: 847fc0cd0664fcb2a08ac66df6b85935361ec454
Gitweb: https://git.kernel.org/tip/847fc0cd0664fcb2a08ac66df6b85935361ec454
Author: Yafang Shao <laoar.shao@xxxxxxxxx>
AuthorDate: Sun, 05 Sep 2021 14:35:43
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 05 Oct 2021 15:51:48 +02:00

sched: Introduce task block time in schedstats

Currently in schedstats we have sum_sleep_runtime and iowait_sum, but
there's no metric to show how long the task is in D state. Once a task in
D state, it means the task is blocked in the kernel, for example the
task may be waiting for a mutex. The D state is more frequent than
iowait, and it is more critital than S state. So it is worth to add a
metric to measure it.

Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20210905143547.4668-5-laoar.shao@xxxxxxxxx
---
include/linux/sched.h | 2 ++
kernel/sched/debug.c | 6 ++++--
kernel/sched/stats.c | 1 +
3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2bc4c72..193e16e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -503,6 +503,8 @@ struct sched_statistics {

u64 block_start;
u64 block_max;
+ s64 sum_block_runtime;
+
u64 exec_max;
u64 slice_max;

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 76fd38e..26fac5e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -540,10 +540,11 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
(long long)(p->nvcsw + p->nivcsw),
p->prio);

- SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+ SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld",
SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
SPLIT_NS(p->se.sum_exec_runtime),
- SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)));
+ SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
+ SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));

#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
@@ -977,6 +978,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
u64 avg_atom, avg_per_cpu;

PN_SCHEDSTAT(sum_sleep_runtime);
+ PN_SCHEDSTAT(sum_block_runtime);
PN_SCHEDSTAT(wait_start);
PN_SCHEDSTAT(sleep_start);
PN_SCHEDSTAT(block_start);
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index fad781c..07dde29 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -82,6 +82,7 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,

__schedstat_set(stats->block_start, 0);
__schedstat_add(stats->sum_sleep_runtime, delta);
+ __schedstat_add(stats->sum_block_runtime, delta);

if (p) {
if (p->in_iowait) {