[RFC PATCH 5/5] sched/events: Introduce task_group load tracking trace event

[Dietmar Eggemann]

The trace event key load is mapped to:

 (1) load : cfs_rq->tg->load_avg

The cfs_rq owned by the task_group is used as the only parameter for the
trace event because it has a reference to the taskgroup and the cpu.
Using the taskgroup as a parameter instead would require the cpu as a
second parameter. A task_group is global and not per-cpu data. The cpu
key only tells on which cpu the value was gathered.

The following list shows examples of the key=value pairs for:

 (1) a task group:

     cpu=1 path=/tg1/tg11/tg111 id=4 load=517

 (2) an autogroup:

     cpu=1 path=/autogroup-10 id=0 load=1050

We don't maintain a load signal for a root task group.

The trace event is only defined if cfs group scheduling support
(CONFIG_FAIR_GROUP_SCHED) is enabled.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
 include/trace/events/sched.h | 31 +++++++++++++++++++++++++++++++
 kernel/sched/fair.c          |  2 ++
 2 files changed, 33 insertions(+)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 647cfaf528fd..3fe0092176f8 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -673,6 +673,37 @@ TRACE_EVENT(sched_load_se,
 		  __entry->cpu, __get_str(path), __entry->id, __entry->comm,
 		  __entry->pid, __entry->load, __entry->util)
 );
+
+/*
+ * Tracepoint for task_group load tracking:
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
+TRACE_EVENT(sched_load_tg,
+
+	TP_PROTO(struct cfs_rq *cfs_rq),
+
+	TP_ARGS(cfs_rq),
+
+	TP_STRUCT__entry(
+		__field(	int,	cpu				)
+		__dynamic_array(char,	path,
+				__trace_sched_path(cfs_rq, NULL, 0)	)
+		__field(	int,	id				)
+		__field(	long,	load				)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cfs_rq->rq->cpu;
+		__trace_sched_path(cfs_rq, __get_dynamic_array(path),
+				   __get_dynamic_array_len(path));
+		__entry->id	= cfs_rq->tg->css.id;
+		__entry->load	= atomic_long_read(&cfs_rq->tg->load_avg);
+	),
+
+	TP_printk("cpu=%d path=%s id=%d load=%ld", __entry->cpu,
+		  __get_str(path), __entry->id, __entry->load)
+);
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 #endif /* CONFIG_SMP */
 #endif /* _TRACE_SCHED_H */
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d1dcb19f5b55..dbe2d5ef8b9e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2997,6 +2997,8 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
 	}
+
+	trace_sched_load_tg(cfs_rq);
 }
 
 /*
-- 
2.11.0