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
CC: Qais Yousef
CC: Ingo Molnar
CC: Peter Zijlstra
CC: Vincent Guittot
CC: Steven Rostedt
CC: linux-kernel@vger.kernel.org
---
V2: Fix use of tracepoint in header from Steven. Pass rq* and use
helper to get nr_running field, from Qais.
include/linux/sched.h| 1 +
include/trace/events/sched.h | 4
kernel/sched/core.c | 13 +
kernel/sched/fair.c | 8 ++--
kernel/sched/pelt.c | 2 --
kernel/sched/sched.h | 10 ++
6 files changed, 30 insertions(+), 8 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4418f5cb8324..5f114faf2247 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2015,6 +2015,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq
*rq);
const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_nr_running(struct rq *rq);
const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index ed168b0e2c53..8c72f9113694 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -634,6 +634,10 @@ DECLARE_TRACE(sched_overutilized_tp,
TP_PROTO(struct root_domain *rd, bool overutilized),
TP_ARGS(rd, overutilized));
+DECLARE_TRACE(sched_update_nr_running_tp,
+ TP_PROTO(struct rq *rq, int change),
+ TP_ARGS(rq, change));
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9a2fbf98fd6f..0d35d7c4c330 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,6 +6,10 @@
*
* Copyright (C) 1991-2002 Linus Torvalds
*/
+#define CREATE_TRACE_POINTS
+#include
+#undef CREATE_TRACE_POINTS
+
#include "sched.h"
#include
@@ -21,9 +25,6 @@
#include "pelt.h"
-#define CREATE_TRACE_POINTS
-#include
-
/*
* Export tracepoints that act as a bare tracehook (ie: have no trace event
* associated with them) to allow external modules to probe them.
@@ -34,6 +35,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -7970,4 +7972,7 @@ const u32 sched_prio_to_wmult[40] = {
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+trace_sched_update_nr_running_tp(rq, count);
+}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index da3e5b54715b..2e2f3f68e318 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,8 +22,6 @@
*/
#include "sched.h"
-#include
-
/*
* Targeted preemption latency for CPU-bound tasks:
*
@@ -11293,3 +11291,9 @@ const struct cpumask *sched_trace_rd_span(struct
root_domain *rd)
#endif
}
EXPORT_SYMBOL_GPL(sched_trace_rd_span);
+
+int sched_trace_rq_nr_running(struct rq *rq)
+{
+return rq ? rq->nr_running : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index b647d04d9c8b..bb69a0ae8d6c 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -28,8 +28,6 @@
#include "sched.h"
#include "pelt.h"
-#include
-
/*
* Approximate:
* val * y^n,where y^32 ~= 0.5 (~1 scheduling period)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index db3a57675ccf..e621eaa44474 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -75,6 +75,8 @@
#include "cpupri.h"
#include "cpudeadline.h"
+#include
+
#ifdef CONFIG_SCHED_DEBUG
# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
#else
@@ -96,6 +98,7 @@ 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
