Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Yafang Shao <laoar.shao@gmail.com>
To:     mingo@redhat.com, peterz@infradead.org, mgorman@suse.de,
        juri.lelli@redhat.com, vincent.guittot@linaro.org,
        dietmar.eggemann@arm.com, rostedt@goodmis.org, bsegall@google.com,
        bristot@redhat.com, achaiken@aurora.tech
Cc:     lkp@intel.com, linux-kernel@vger.kernel.org,
        linux-rt-users@vger.kernel.org, Yafang Shao <laoar.shao@gmail.com>
Subject: [PATCH v3 5/7] sched: introduce task block time in schedstats
Date:   Tue, 24 Aug 2021 11:29:44 +0000
Message-Id: <20210824112946.9324-6-laoar.shao@gmail.com>
In-Reply-To: <20210824112946.9324-1-laoar.shao@gmail.com>
References: <20210824112946.9324-1-laoar.shao@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Alison Chaiken <achaiken@aurora.tech>
---
 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 39c29eae1af9..7888ad8384ba 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -502,6 +502,8 @@ 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 705987aed658..5c6bc3f373f0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -560,10 +560,11 @@ 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));
@@ -995,6 +996,7 @@ 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 b2542f4d3192..21fae41c06f5 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) {
-- 
2.18.2