@@ -502,6 +502,8 @@ struct sched_statistics {
u64 block_start;
u64 block_max;
+ s64 sum_block_runtime;
+
u64 exec_max;
u64 slice_max;
@@ -534,10 +534,11 @@ 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));
@@ -968,6 +969,7 @@ 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);
@@ -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) {
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(-)