diff --git a/include/linux/sched.h b/include/linux/sched.h index e209ae0e7a8a..9c96ef2f7e68 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1111,6 +1111,8 @@ struct sched_entity { u64 wait_max; u64 wait_count; u64 wait_sum; + u64 iowait_count; + u64 iowait_sum; u64 sleep_start; u64 sleep_max; @@ -1231,6 +1233,8 @@ struct task_struct { unsigned did_exec:1; unsigned in_execve:1; /* Tell the LSMs that the process is doing an * execve */ + unsigned in_iowait:1; + /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; diff --git a/kernel/sched.c b/kernel/sched.c index 6244d24cafc1..38d05a89e0f2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6754,7 +6754,9 @@ void __sched io_schedule(void) delayacct_blkio_start(); atomic_inc(&rq->nr_iowait); + current->in_iowait = 1; schedule(); + current->in_iowait = 0; atomic_dec(&rq->nr_iowait); delayacct_blkio_end(); } @@ -6767,7 +6769,9 @@ long __sched io_schedule_timeout(long timeout) delayacct_blkio_start(); atomic_inc(&rq->nr_iowait); + current->in_iowait = 1; ret = schedule_timeout(timeout); + current->in_iowait = 0; atomic_dec(&rq->nr_iowait); delayacct_blkio_end(); return ret; diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 70c7e0b79946..5ddbd0891267 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -409,6 +409,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.wait_max); PN(se.wait_sum); P(se.wait_count); + PN(se.iowait_sum); + P(se.iowait_count); P(sched_info.bkl_count); P(se.nr_migrations); P(se.nr_migrations_cold); @@ -479,6 +481,8 @@ void proc_sched_set_task(struct task_struct *p) p->se.wait_max = 0; p->se.wait_sum = 0; p->se.wait_count = 0; + p->se.iowait_sum = 0; + p->se.iowait_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 342000b31ad6..471fa281f5e0 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -652,6 +652,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->sum_sleep_runtime += delta; if (tsk) { + if (tsk->in_iowait) { + se->iowait_sum += delta; + se->iowait_count++; + } + /* * Blocking time is in units of nanosecs, so shift by * 20 to get a milliseconds-range estimation of the