From 6708491b7c6316c238caee90bb1ea0639e37ac23 Mon Sep 17 00:00:00 2001
From: Phil Auld <pauld@redhat.com>
Date: Mon, 29 Jun 2020 15:23:03 -0400
Subject: [PATCH] sched: Add a tracepoint to track rq->nr_running
References: bnc#1155798 (CPU scheduler functional and performance backports)
Patch-mainline: v5.9-rc1
Git-commit: 9d246053a69196c7c27068870e9b4b66ac536f68
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
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
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 01c98186c004..47c65e91873d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2008,6 +2008,7 @@ 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 bffd758a119c..29a526a795d0 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -638,6 +638,10 @@ DECLARE_TRACE(sched_util_est_se_tp,
TP_PROTO(struct sched_entity *se),
TP_ARGS(se));
+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 077045de3aaa..a995ef4344ad 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 <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
#include "sched.h"
#include <linux/nospec.h>
@@ -20,9 +24,6 @@
#include "pelt.h"
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-
/*
* Export tracepoints that act as a bare tracehook (ie: have no trace event
* associated with them) to allow external modules to probe them.
@@ -35,6 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -7724,4 +7726,7 @@ 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 47209c44f064..1e9c3decdfa6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,8 +22,6 @@
*/
#include "sched.h"
-#include <trace/events/sched.h>
-
/*
* Targeted preemption latency for CPU-bound tasks:
*
@@ -11244,3 +11242,9 @@ 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 94e188324000..c02dd0478c09 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -28,8 +28,6 @@
#include "sched.h"
#include "pelt.h"
-#include <trace/events/sched.h>
-
/*
* 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 eecb3e77a4c8..7c942c91da7d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -75,6 +75,8 @@
#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
@@ -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 count);
/*
* Helpers for converting nanosecond timing to jiffy resolution
*/
@@ -1931,6 +1934,9 @@ 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) {
@@ -1945,6 +1951,10 @@ 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);
}