mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 19:29:37 +00:00
![Mel Gorman](/assets/img/avatar_default.png)
schedstats is very useful during debugging and performance tuning but it incurs overhead to calculate the stats. As such, even though it can be disabled at build time, it is often enabled as the information is useful. This patch adds a kernel command-line and sysctl tunable to enable or disable schedstats on demand (when it's built in). It is disabled by default as someone who knows they need it can also learn to enable it when necessary. The benefits are dependent on how scheduler-intensive the workload is. If it is then the patch reduces the number of cycles spent calculating the stats with a small benefit from reducing the cache footprint of the scheduler. These measurements were taken from a 48-core 2-socket machine with Xeon(R) E5-2670 v3 cpus although they were also tested on a single socket machine 8-core machine with Intel i7-3770 processors. netperf-tcp 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v3r1 Hmean 64 560.45 ( 0.00%) 575.98 ( 2.77%) Hmean 128 766.66 ( 0.00%) 795.79 ( 3.80%) Hmean 256 950.51 ( 0.00%) 981.50 ( 3.26%) Hmean 1024 1433.25 ( 0.00%) 1466.51 ( 2.32%) Hmean 2048 2810.54 ( 0.00%) 2879.75 ( 2.46%) Hmean 3312 4618.18 ( 0.00%) 4682.09 ( 1.38%) Hmean 4096 5306.42 ( 0.00%) 5346.39 ( 0.75%) Hmean 8192 10581.44 ( 0.00%) 10698.15 ( 1.10%) Hmean 16384 18857.70 ( 0.00%) 18937.61 ( 0.42%) Small gains here, UDP_STREAM showed nothing intresting and neither did the TCP_RR tests. The gains on the 8-core machine were very similar. tbench4 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v3r1 Hmean mb/sec-1 500.85 ( 0.00%) 522.43 ( 4.31%) Hmean mb/sec-2 984.66 ( 0.00%) 1018.19 ( 3.41%) Hmean mb/sec-4 1827.91 ( 0.00%) 1847.78 ( 1.09%) Hmean mb/sec-8 3561.36 ( 0.00%) 3611.28 ( 1.40%) Hmean mb/sec-16 5824.52 ( 0.00%) 5929.03 ( 1.79%) Hmean mb/sec-32 10943.10 ( 0.00%) 10802.83 ( -1.28%) Hmean mb/sec-64 15950.81 ( 0.00%) 16211.31 ( 1.63%) Hmean mb/sec-128 15302.17 ( 0.00%) 15445.11 ( 0.93%) Hmean mb/sec-256 14866.18 ( 0.00%) 15088.73 ( 1.50%) Hmean mb/sec-512 15223.31 ( 0.00%) 15373.69 ( 0.99%) Hmean mb/sec-1024 14574.25 ( 0.00%) 14598.02 ( 0.16%) Hmean mb/sec-2048 13569.02 ( 0.00%) 13733.86 ( 1.21%) Hmean mb/sec-3072 12865.98 ( 0.00%) 13209.23 ( 2.67%) Small gains of 2-4% at low thread counts and otherwise flat. The gains on the 8-core machine were slightly different tbench4 on 8-core i7-3770 single socket machine Hmean mb/sec-1 442.59 ( 0.00%) 448.73 ( 1.39%) Hmean mb/sec-2 796.68 ( 0.00%) 794.39 ( -0.29%) Hmean mb/sec-4 1322.52 ( 0.00%) 1343.66 ( 1.60%) Hmean mb/sec-8 2611.65 ( 0.00%) 2694.86 ( 3.19%) Hmean mb/sec-16 2537.07 ( 0.00%) 2609.34 ( 2.85%) Hmean mb/sec-32 2506.02 ( 0.00%) 2578.18 ( 2.88%) Hmean mb/sec-64 2511.06 ( 0.00%) 2569.16 ( 2.31%) Hmean mb/sec-128 2313.38 ( 0.00%) 2395.50 ( 3.55%) Hmean mb/sec-256 2110.04 ( 0.00%) 2177.45 ( 3.19%) Hmean mb/sec-512 2072.51 ( 0.00%) 2053.97 ( -0.89%) In constract, this shows a relatively steady 2-3% gain at higher thread counts. Due to the nature of the patch and the type of workload, it's not a surprise that the result will depend on the CPU used. hackbench-pipes 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v3r1 Amean 1 0.0637 ( 0.00%) 0.0660 ( -3.59%) Amean 4 0.1229 ( 0.00%) 0.1181 ( 3.84%) Amean 7 0.1921 ( 0.00%) 0.1911 ( 0.52%) Amean 12 0.3117 ( 0.00%) 0.2923 ( 6.23%) Amean 21 0.4050 ( 0.00%) 0.3899 ( 3.74%) Amean 30 0.4586 ( 0.00%) 0.4433 ( 3.33%) Amean 48 0.5910 ( 0.00%) 0.5694 ( 3.65%) Amean 79 0.8663 ( 0.00%) 0.8626 ( 0.43%) Amean 110 1.1543 ( 0.00%) 1.1517 ( 0.22%) Amean 141 1.4457 ( 0.00%) 1.4290 ( 1.16%) Amean 172 1.7090 ( 0.00%) 1.6924 ( 0.97%) Amean 192 1.9126 ( 0.00%) 1.9089 ( 0.19%) Some small gains and losses and while the variance data is not included, it's close to the noise. The UMA machine did not show anything particularly different pipetest 4.5.0-rc1 4.5.0-rc1 vanilla nostats-v2r2 Min Time 4.13 ( 0.00%) 3.99 ( 3.39%) 1st-qrtle Time 4.38 ( 0.00%) 4.27 ( 2.51%) 2nd-qrtle Time 4.46 ( 0.00%) 4.39 ( 1.57%) 3rd-qrtle Time 4.56 ( 0.00%) 4.51 ( 1.10%) Max-90% Time 4.67 ( 0.00%) 4.60 ( 1.50%) Max-93% Time 4.71 ( 0.00%) 4.65 ( 1.27%) Max-95% Time 4.74 ( 0.00%) 4.71 ( 0.63%) Max-99% Time 4.88 ( 0.00%) 4.79 ( 1.84%) Max Time 4.93 ( 0.00%) 4.83 ( 2.03%) Mean Time 4.48 ( 0.00%) 4.39 ( 1.91%) Best99%Mean Time 4.47 ( 0.00%) 4.39 ( 1.91%) Best95%Mean Time 4.46 ( 0.00%) 4.38 ( 1.93%) Best90%Mean Time 4.45 ( 0.00%) 4.36 ( 1.98%) Best50%Mean Time 4.36 ( 0.00%) 4.25 ( 2.49%) Best10%Mean Time 4.23 ( 0.00%) 4.10 ( 3.13%) Best5%Mean Time 4.19 ( 0.00%) 4.06 ( 3.20%) Best1%Mean Time 4.13 ( 0.00%) 4.00 ( 3.39%) Small improvement and similar gains were seen on the UMA machine. The gain is small but it stands to reason that doing less work in the scheduler is a good thing. The downside is that the lack of schedstats and tracepoints may be surprising to experts doing performance analysis until they find the existence of the schedstats= parameter or schedstats sysctl. It will be automatically activated for latencytop and sleep profiling to alleviate the problem. For tracepoints, there is a simple warning as it's not safe to activate schedstats in the context when it's known the tracepoint may be wanted but is unavailable. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <mgalbraith@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1454663316-22048-1-git-send-email-mgorman@techsingularity.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
304 lines
7.8 KiB
C
304 lines
7.8 KiB
C
/*
|
|
* latencytop.c: Latency display infrastructure
|
|
*
|
|
* (C) Copyright 2008 Intel Corporation
|
|
* Author: Arjan van de Ven <arjan@linux.intel.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; version 2
|
|
* of the License.
|
|
*/
|
|
|
|
/*
|
|
* CONFIG_LATENCYTOP enables a kernel latency tracking infrastructure that is
|
|
* used by the "latencytop" userspace tool. The latency that is tracked is not
|
|
* the 'traditional' interrupt latency (which is primarily caused by something
|
|
* else consuming CPU), but instead, it is the latency an application encounters
|
|
* because the kernel sleeps on its behalf for various reasons.
|
|
*
|
|
* This code tracks 2 levels of statistics:
|
|
* 1) System level latency
|
|
* 2) Per process latency
|
|
*
|
|
* The latency is stored in fixed sized data structures in an accumulated form;
|
|
* if the "same" latency cause is hit twice, this will be tracked as one entry
|
|
* in the data structure. Both the count, total accumulated latency and maximum
|
|
* latency are tracked in this data structure. When the fixed size structure is
|
|
* full, no new causes are tracked until the buffer is flushed by writing to
|
|
* the /proc file; the userspace tool does this on a regular basis.
|
|
*
|
|
* A latency cause is identified by a stringified backtrace at the point that
|
|
* the scheduler gets invoked. The userland tool will use this string to
|
|
* identify the cause of the latency in human readable form.
|
|
*
|
|
* The information is exported via /proc/latency_stats and /proc/<pid>/latency.
|
|
* These files look like this:
|
|
*
|
|
* Latency Top version : v0.1
|
|
* 70 59433 4897 i915_irq_wait drm_ioctl vfs_ioctl do_vfs_ioctl sys_ioctl
|
|
* | | | |
|
|
* | | | +----> the stringified backtrace
|
|
* | | +---------> The maximum latency for this entry in microseconds
|
|
* | +--------------> The accumulated latency for this entry (microseconds)
|
|
* +-------------------> The number of times this entry is hit
|
|
*
|
|
* (note: the average latency is the accumulated latency divided by the number
|
|
* of times)
|
|
*/
|
|
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/latencytop.h>
|
|
#include <linux/export.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/list.h>
|
|
#include <linux/stacktrace.h>
|
|
|
|
static DEFINE_RAW_SPINLOCK(latency_lock);
|
|
|
|
#define MAXLR 128
|
|
static struct latency_record latency_record[MAXLR];
|
|
|
|
int latencytop_enabled;
|
|
|
|
void clear_all_latency_tracing(struct task_struct *p)
|
|
{
|
|
unsigned long flags;
|
|
|
|
if (!latencytop_enabled)
|
|
return;
|
|
|
|
raw_spin_lock_irqsave(&latency_lock, flags);
|
|
memset(&p->latency_record, 0, sizeof(p->latency_record));
|
|
p->latency_record_count = 0;
|
|
raw_spin_unlock_irqrestore(&latency_lock, flags);
|
|
}
|
|
|
|
static void clear_global_latency_tracing(void)
|
|
{
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&latency_lock, flags);
|
|
memset(&latency_record, 0, sizeof(latency_record));
|
|
raw_spin_unlock_irqrestore(&latency_lock, flags);
|
|
}
|
|
|
|
static void __sched
|
|
account_global_scheduler_latency(struct task_struct *tsk,
|
|
struct latency_record *lat)
|
|
{
|
|
int firstnonnull = MAXLR + 1;
|
|
int i;
|
|
|
|
if (!latencytop_enabled)
|
|
return;
|
|
|
|
/* skip kernel threads for now */
|
|
if (!tsk->mm)
|
|
return;
|
|
|
|
for (i = 0; i < MAXLR; i++) {
|
|
int q, same = 1;
|
|
|
|
/* Nothing stored: */
|
|
if (!latency_record[i].backtrace[0]) {
|
|
if (firstnonnull > i)
|
|
firstnonnull = i;
|
|
continue;
|
|
}
|
|
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
|
|
unsigned long record = lat->backtrace[q];
|
|
|
|
if (latency_record[i].backtrace[q] != record) {
|
|
same = 0;
|
|
break;
|
|
}
|
|
|
|
/* 0 and ULONG_MAX entries mean end of backtrace: */
|
|
if (record == 0 || record == ULONG_MAX)
|
|
break;
|
|
}
|
|
if (same) {
|
|
latency_record[i].count++;
|
|
latency_record[i].time += lat->time;
|
|
if (lat->time > latency_record[i].max)
|
|
latency_record[i].max = lat->time;
|
|
return;
|
|
}
|
|
}
|
|
|
|
i = firstnonnull;
|
|
if (i >= MAXLR - 1)
|
|
return;
|
|
|
|
/* Allocted a new one: */
|
|
memcpy(&latency_record[i], lat, sizeof(struct latency_record));
|
|
}
|
|
|
|
/*
|
|
* Iterator to store a backtrace into a latency record entry
|
|
*/
|
|
static inline void store_stacktrace(struct task_struct *tsk,
|
|
struct latency_record *lat)
|
|
{
|
|
struct stack_trace trace;
|
|
|
|
memset(&trace, 0, sizeof(trace));
|
|
trace.max_entries = LT_BACKTRACEDEPTH;
|
|
trace.entries = &lat->backtrace[0];
|
|
save_stack_trace_tsk(tsk, &trace);
|
|
}
|
|
|
|
/**
|
|
* __account_scheduler_latency - record an occurred latency
|
|
* @tsk - the task struct of the task hitting the latency
|
|
* @usecs - the duration of the latency in microseconds
|
|
* @inter - 1 if the sleep was interruptible, 0 if uninterruptible
|
|
*
|
|
* This function is the main entry point for recording latency entries
|
|
* as called by the scheduler.
|
|
*
|
|
* This function has a few special cases to deal with normal 'non-latency'
|
|
* sleeps: specifically, interruptible sleep longer than 5 msec is skipped
|
|
* since this usually is caused by waiting for events via select() and co.
|
|
*
|
|
* Negative latencies (caused by time going backwards) are also explicitly
|
|
* skipped.
|
|
*/
|
|
void __sched
|
|
__account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
|
|
{
|
|
unsigned long flags;
|
|
int i, q;
|
|
struct latency_record lat;
|
|
|
|
/* Long interruptible waits are generally user requested... */
|
|
if (inter && usecs > 5000)
|
|
return;
|
|
|
|
/* Negative sleeps are time going backwards */
|
|
/* Zero-time sleeps are non-interesting */
|
|
if (usecs <= 0)
|
|
return;
|
|
|
|
memset(&lat, 0, sizeof(lat));
|
|
lat.count = 1;
|
|
lat.time = usecs;
|
|
lat.max = usecs;
|
|
store_stacktrace(tsk, &lat);
|
|
|
|
raw_spin_lock_irqsave(&latency_lock, flags);
|
|
|
|
account_global_scheduler_latency(tsk, &lat);
|
|
|
|
for (i = 0; i < tsk->latency_record_count; i++) {
|
|
struct latency_record *mylat;
|
|
int same = 1;
|
|
|
|
mylat = &tsk->latency_record[i];
|
|
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
|
|
unsigned long record = lat.backtrace[q];
|
|
|
|
if (mylat->backtrace[q] != record) {
|
|
same = 0;
|
|
break;
|
|
}
|
|
|
|
/* 0 and ULONG_MAX entries mean end of backtrace: */
|
|
if (record == 0 || record == ULONG_MAX)
|
|
break;
|
|
}
|
|
if (same) {
|
|
mylat->count++;
|
|
mylat->time += lat.time;
|
|
if (lat.time > mylat->max)
|
|
mylat->max = lat.time;
|
|
goto out_unlock;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* short term hack; if we're > 32 we stop; future we recycle:
|
|
*/
|
|
if (tsk->latency_record_count >= LT_SAVECOUNT)
|
|
goto out_unlock;
|
|
|
|
/* Allocated a new one: */
|
|
i = tsk->latency_record_count++;
|
|
memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record));
|
|
|
|
out_unlock:
|
|
raw_spin_unlock_irqrestore(&latency_lock, flags);
|
|
}
|
|
|
|
static int lstats_show(struct seq_file *m, void *v)
|
|
{
|
|
int i;
|
|
|
|
seq_puts(m, "Latency Top version : v0.1\n");
|
|
|
|
for (i = 0; i < MAXLR; i++) {
|
|
struct latency_record *lr = &latency_record[i];
|
|
|
|
if (lr->backtrace[0]) {
|
|
int q;
|
|
seq_printf(m, "%i %lu %lu",
|
|
lr->count, lr->time, lr->max);
|
|
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
|
|
unsigned long bt = lr->backtrace[q];
|
|
if (!bt)
|
|
break;
|
|
if (bt == ULONG_MAX)
|
|
break;
|
|
seq_printf(m, " %ps", (void *)bt);
|
|
}
|
|
seq_puts(m, "\n");
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static ssize_t
|
|
lstats_write(struct file *file, const char __user *buf, size_t count,
|
|
loff_t *offs)
|
|
{
|
|
clear_global_latency_tracing();
|
|
|
|
return count;
|
|
}
|
|
|
|
static int lstats_open(struct inode *inode, struct file *filp)
|
|
{
|
|
return single_open(filp, lstats_show, NULL);
|
|
}
|
|
|
|
static const struct file_operations lstats_fops = {
|
|
.open = lstats_open,
|
|
.read = seq_read,
|
|
.write = lstats_write,
|
|
.llseek = seq_lseek,
|
|
.release = single_release,
|
|
};
|
|
|
|
static int __init init_lstats_procfs(void)
|
|
{
|
|
proc_create("latency_stats", 0644, NULL, &lstats_fops);
|
|
return 0;
|
|
}
|
|
|
|
int sysctl_latencytop(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp, loff_t *ppos)
|
|
{
|
|
int err;
|
|
|
|
err = proc_dointvec(table, write, buffer, lenp, ppos);
|
|
if (latencytop_enabled)
|
|
force_schedstat_enabled();
|
|
|
|
return err;
|
|
}
|
|
device_initcall(init_lstats_procfs);
|