[PATCH 2/2] tracing, sched: Add a new tracepoint for sleeptime

From: Arun Sharma
Date: Tue Dec 20 2011 - 13:09:29 EST


If CONFIG_SCHEDSTATS is defined, the kernel maintains
information about how long the task was sleeping or
in the case of iowait, blocking in the kernel before
getting woken up.

Note: this information is only provided for sched_fair.
Other scheduling classes may choose to provide this in
the future.

Note: the delay includes the time spent on the runqueue
as well.

Signed-off-by: Arun Sharma <asharma@xxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxx>
Cc: Andrew Vagin <avagin@xxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
---
include/trace/events/sched.h | 48 ++++++++++++++++++++++++++++++++++++++++++
kernel/sched/core.c | 1 +
2 files changed, 49 insertions(+), 0 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 959ff18..5189220 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -363,6 +363,54 @@ TRACE_EVENT(sched_stat_runtime,
(unsigned long long)__entry->vruntime)
);

+#ifdef CREATE_TRACE_POINTS
+static inline u64 trace_get_sleeptime(struct task_struct *tsk)
+{
+#ifdef CONFIG_SCHEDSTATS
+ u64 block, sleep;
+
+ block = tsk->se.statistics.block_start;
+ sleep = tsk->se.statistics.sleep_start;
+
+ return block ? block : sleep ? sleep : 0;
+#else
+ return 0;
+#endif
+}
+#endif
+
+/*
+ * Tracepoint for accounting sleeptime (time the task is sleeping
+ * or waiting for I/O).
+ */
+TRACE_EVENT(sched_stat_sleeptime,
+
+ TP_PROTO(struct task_struct *tsk, u64 now),
+
+ TP_ARGS(tsk, now),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, sleeptime )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->sleeptime = trace_get_sleeptime(tsk);
+ __entry->sleeptime = __entry->sleeptime ?
+ now - __entry->sleeptime : 0;
+ )
+ TP_perf_assign(
+ __perf_count(__entry->sleeptime);
+ ),
+
+ TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->sleeptime)
+);
+
/*
* Tracepoint for showing priority inheritance modifying a tasks
* priority.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ca8fd44..172e6ee 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1899,6 +1899,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
local_irq_enable();
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
finish_lock_switch(rq, prev);
+ trace_sched_stat_sleeptime(current, rq->clock);

fire_sched_in_preempt_notifiers(current);
if (mm)
--
1.7.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/