AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

tracing: Have hwlat trace migrate across tracing_cpumask CPUs

Browse Source 
Instead of having the hwlat detector thread stay on one CPU, have it migrate
across all the CPUs specified by tracing_cpumask. If the user modifies the
thread's CPU affinity, the migration will stop until the next instance that
the tracer is instantiated. The migration happens at the end of each window
(period).

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
This commit is contained in:
Steven Rostedt (Red Hat) 2016-07-15 15:48:56 -04:00 committed by Steven Rostedt
parent c850ed38db
commit 0330f7aa8e
2 changed files with 61 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Documentation/trace/hwlat_detector.txt
View File

@ -69,5 +69,11 @@ in /sys/kernel/tracing:
tracing_threshold - minimum latency value to be considered (usecs)
tracing_max_latency - maximum hardware latency actually observed (usecs)
tracing_cpumask - the CPUs to move the hwlat thread across
hwlat_detector/width - specified amount of time to spin within window (usecs)
hwlat_detector/window - amount of time between (width) runs (usecs)
The hwlat detector's kernel thread will migrate across each CPU specified in
tracing_cpumask between each window. To limit the migration, either modify
tracing_cpumask, or modify the hwlat kernel thread (named [hwlatd]) CPU
affinity directly, and the migration will stop.

55
kernel/trace/trace_hwlat.c
View File

@ -42,6 +42,7 @@
#include <linux/kthread.h>
#include <linux/tracefs.h>
#include <linux/uaccess.h>
#include <linux/cpumask.h>
#include <linux/delay.h>
#include "trace.h"
@ -211,6 +212,57 @@ static int get_sample(void)
return ret;
}
static struct cpumask save_cpumask;
static bool disable_migrate;
static void move_to_next_cpu(void)
{
static struct cpumask *current_mask;
int next_cpu;
if (disable_migrate)
return;
/* Just pick the first CPU on first iteration */
if (!current_mask) {
current_mask = &save_cpumask;
get_online_cpus();
cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
put_online_cpus();
next_cpu = cpumask_first(current_mask);
goto set_affinity;
}
/*
* If for some reason the user modifies the CPU affinity
* of this thread, than stop migrating for the duration
* of the current test.
*/
if (!cpumask_equal(current_mask, &current->cpus_allowed))
goto disable;
get_online_cpus();
cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
next_cpu = cpumask_next(smp_processor_id(), current_mask);
put_online_cpus();
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(current_mask);
set_affinity:
if (next_cpu >= nr_cpu_ids) /* Shouldn't happen! */
goto disable;
cpumask_clear(current_mask);
cpumask_set_cpu(next_cpu, current_mask);
sched_setaffinity(0, current_mask);
return;
disable:
disable_migrate = true;
}
/*
* kthread_fn - The CPU time sampling/hardware latency detection kernel thread
*
@ -230,6 +282,8 @@ static int kthread_fn(void *data)
while (!kthread_should_stop()) {
move_to_next_cpu();
local_irq_disable();
get_sample();
local_irq_enable();
@ -473,6 +527,7 @@ static int hwlat_tracer_init(struct trace_array *tr)
hwlat_trace = tr;
disable_migrate = false;
hwlat_data.count = 0;
tr->max_latency = 0;
save_tracing_thresh = tracing_thresh;