[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <tip-5f3e60fb2a0e05cdaf9b59acb0bb249bb1e96362@git.kernel.org>
Date: Mon, 3 Aug 2009 13:22:03 GMT
From: tip-bot for Peter Zijlstra <a.p.zijlstra@...llo.nl>
To: linux-tip-commits@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
arjan@...ux.intel.com, a.p.zijlstra@...llo.nl, fweisbec@...il.com,
rostedt@...dmis.org, tglx@...utronix.de, mingo@...e.hu
Subject: [tip:sched/core] sched: Add wait, sleep and iowait accounting tracepoints
Commit-ID: 5f3e60fb2a0e05cdaf9b59acb0bb249bb1e96362
Gitweb: http://git.kernel.org/tip/5f3e60fb2a0e05cdaf9b59acb0bb249bb1e96362
Author: Peter Zijlstra <a.p.zijlstra@...llo.nl>
AuthorDate: Thu, 23 Jul 2009 20:13:26 +0200
Committer: Ingo Molnar <mingo@...e.hu>
CommitDate: Mon, 3 Aug 2009 14:35:37 +0200
sched: Add wait, sleep and iowait accounting tracepoints
Add 3 schedstat tracepoints to help account for wait-time,
sleep-time and iowait-time.
They can also be used as a perf-counter source to profile tasks
on these clocks.
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Frederic Weisbecker <fweisbec@...il.com>
Cc: Arjan van de Ven <arjan@...ux.intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
include/trace/events/sched.h | 95 ++++++++++++++++++++++++++++++++++++++++++
kernel/sched_fair.c | 10 ++++-
2 files changed, 104 insertions(+), 1 deletions(-)
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8949bb7..a4c369e 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -340,6 +340,101 @@ TRACE_EVENT(sched_signal_send,
__entry->sig, __entry->comm, __entry->pid)
);
+/*
+ * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
+ * adding sched_stat support to SCHED_FIFO/RR would be welcome.
+ */
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+TRACE_EVENT(sched_stat_wait,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d wait: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+TRACE_EVENT(sched_stat_sleep,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d sleep: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+TRACE_EVENT(sched_stat_iowait,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d iowait: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 471fa28..0e4d6c5 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -546,6 +546,11 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
schedstat_set(se->wait_sum, se->wait_sum +
rq_of(cfs_rq)->clock - se->wait_start);
schedstat_set(se->wait_start, 0);
+
+ if (entity_is_task(se)) {
+ trace_sched_stat_wait(task_of(se),
+ rq_of(cfs_rq)->clock - se->wait_start);
+ }
}
static inline void
@@ -636,8 +641,10 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
- if (tsk)
+ if (tsk) {
account_scheduler_latency(tsk, delta >> 10, 1);
+ trace_sched_stat_sleep(tsk, delta);
+ }
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
@@ -655,6 +662,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
if (tsk->in_iowait) {
se->iowait_sum += delta;
se->iowait_count++;
+ trace_sched_stat_iowait(tsk, delta);
}
/*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists