sched: Add a tracepoint to track rq->nr_running

Add a bare tracepoint trace_sched_update_nr_running_tp which tracks
->nr_running CPU's rq. This is used to accurately trace this data and
provide a visualization of scheduler imbalances in, for example, the
form of a heat map.  The tracepoint is accessed by loading an external
kernel module. An example module (forked from Qais' module and including
the pelt related tracepoints) can be found at:

  https://github.com/auldp/tracepoints-helpers.git

A script to turn the trace-cmd report output into a heatmap plot can be
found at:

  https://github.com/jirvoz/plot-nr-running

The tracepoints are added to add_nr_running() and sub_nr_running() which
are in kernel/sched/sched.h. In order to avoid CREATE_TRACE_POINTS in
the header a wrapper call is used and the trace/events/sched.h include
is moved before sched.h in kernel/sched/core.

Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200629192303.GC120228@lorien.usersys.redhat.com

1 files changed, 10 insertions, 0 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1432f608061..65b72e0487bf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -76,6 +76,8 @@
 #include "cpupri.h"
 #include "cpudeadline.h"
 
+#include <trace/events/sched.h>
+
 #ifdef CONFIG_SCHED_DEBUG
 # define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
@@ -97,6 +99,7 @@ extern atomic_long_t calc_load_tasks;
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
+extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -1973,6 +1976,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 	unsigned prev_nr = rq->nr_running;
 
 	rq->nr_running = prev_nr + count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
 
 #ifdef CONFIG_SMP
 	if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1987,6 +1993,10 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
+
 	/* Check if we still need preemption */
 	sched_update_tick_dependency(rq);
 }