forge/linux-pinenote
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
linux-pinenote/tools/perf/perf.h
Andrew Vagin 3e76ac78b0 perf record: Add ability to record event period 
The problem is that when SAMPLE_PERIOD is not set, the kernel generates
a number of samples in proportion to an event's period. Number of these
samples may be too big and the kernel throttles all samples above a
defined limit.

E.g.: I want to trace when a process sleeps. I created a process which
sleeps for 1ms and for 4ms.  perf got 100 events in both cases.

swapper 0 [000] 1141.371830: sched_stat_sleep: comm=foo pid=1801 delay=1386750 [ns]
swapper 0 [000] 1141.369444: sched_stat_sleep: comm=foo pid=1801 delay=4499585 [ns]

In the first case a kernel want to send 4499585 events and in the second
case it wants to send 1386750 events.  perf-reports shows that process
sleeps in both places equal time.

Instead of this we can get only one sample with an attribute period. As
result we have less data transferring between kernel and user-space and
we avoid throttling of samples.

The patch "events: Don't divide events if it has field period" added a
kernel part of this functionality.

Acked-by: Arun Sharma <asharma@fb.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: devel@openvz.org
Link: http://lkml.kernel.org/r/1324391565-1369947-1-git-send-email-avagin@openvz.org
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-12-20 12:50:09 -02:00

212 lines
5 KiB
C
Raw Blame History

#ifndef _PERF_PERF_H
#define _PERF_PERF_H
struct winsize;
void get_term_dimensions(struct winsize *ws);
#if defined(__i386__)
#include "../../arch/x86/include/asm/unistd.h"
#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
#define CPUINFO_PROC "model name"
#endif
#if defined(__x86_64__)
#include "../../arch/x86/include/asm/unistd.h"
#define rmb() asm volatile("lfence" ::: "memory")
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
#define CPUINFO_PROC "model name"
#endif
#ifdef __powerpc__
#include "../../arch/powerpc/include/asm/unistd.h"
#define rmb() asm volatile ("sync" ::: "memory")
#define cpu_relax() asm volatile ("" ::: "memory");
#define CPUINFO_PROC "cpu"
#endif
#ifdef __s390__
#include "../../arch/s390/include/asm/unistd.h"
#define rmb() asm volatile("bcr 15,0" ::: "memory")
#define cpu_relax() asm volatile("" ::: "memory");
#endif
#ifdef __sh__
#include "../../arch/sh/include/asm/unistd.h"
#if defined(__SH4A__) || defined(__SH5__)
# define rmb() asm volatile("synco" ::: "memory")
#else
# define rmb() asm volatile("" ::: "memory")
#endif
#define cpu_relax() asm volatile("" ::: "memory")
#define CPUINFO_PROC "cpu type"
#endif
#ifdef __hppa__
#include "../../arch/parisc/include/asm/unistd.h"
#define rmb() asm volatile("" ::: "memory")
#define cpu_relax() asm volatile("" ::: "memory");
#define CPUINFO_PROC "cpu"
#endif
#ifdef __sparc__
#include "../../arch/sparc/include/asm/unistd.h"
#define rmb() asm volatile("":::"memory")
#define cpu_relax() asm volatile("":::"memory")
#define CPUINFO_PROC "cpu"
#endif
#ifdef __alpha__
#include "../../arch/alpha/include/asm/unistd.h"
#define rmb() asm volatile("mb" ::: "memory")
#define cpu_relax() asm volatile("" ::: "memory")
#define CPUINFO_PROC "cpu model"
#endif
#ifdef __ia64__
#include "../../arch/ia64/include/asm/unistd.h"
#define rmb() asm volatile ("mf" ::: "memory")
#define cpu_relax() asm volatile ("hint @pause" ::: "memory")
#define CPUINFO_PROC "model name"
#endif
#ifdef __arm__
#include "../../arch/arm/include/asm/unistd.h"
/*
* Use the __kuser_memory_barrier helper in the CPU helper page. See
* arch/arm/kernel/entry-armv.S in the kernel source for details.
*/
#define rmb() ((void(*)(void))0xffff0fa0)()
#define cpu_relax() asm volatile("":::"memory")
#define CPUINFO_PROC "Processor"
#endif
#ifdef __mips__
#include "../../arch/mips/include/asm/unistd.h"
#define rmb() asm volatile( \
".set mips2\n\t" \
"sync\n\t" \
".set mips0" \
: /* no output */ \
: /* no input */ \
: "memory")
#define cpu_relax() asm volatile("" ::: "memory")
#define CPUINFO_PROC "cpu model"
#endif
#include <time.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/syscall.h>
#include "../../include/linux/perf_event.h"
#include "util/types.h"
#include <stdbool.h>
struct perf_mmap {
void *base;
int mask;
unsigned int prev;
};
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{
struct perf_event_mmap_page *pc = mm->base;
int head = pc->data_head;
rmb();
return head;
}
static inline void perf_mmap__write_tail(struct perf_mmap *md,
unsigned long tail)
{
struct perf_event_mmap_page *pc = md->base;
/*
* ensure all reads are done before we write the tail out.
*/
/* mb(); */
pc->data_tail = tail;
}
/*
* prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
* counters in the current task.
*/
#define PR_TASK_PERF_EVENTS_DISABLE 31
#define PR_TASK_PERF_EVENTS_ENABLE 32
#ifndef NSEC_PER_SEC
# define NSEC_PER_SEC 1000000000ULL
#endif
static inline unsigned long long rdclock(void)
{
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
/*
* Pick up some kernel type conventions:
*/
#define __user
#define asmlinkage
#define unlikely(x) __builtin_expect(!!(x), 0)
#define min(x, y) ({ \
typeof(x) _min1 = (x); \
typeof(y) _min2 = (y); \
(void) (&_min1 == &_min2); \
_min1 < _min2 ? _min1 : _min2; })
static inline int
sys_perf_event_open(struct perf_event_attr *attr,
pid_t pid, int cpu, int group_fd,
unsigned long flags)
{
attr->size = sizeof(*attr);
return syscall(__NR_perf_event_open, attr, pid, cpu,
group_fd, flags);
}
#define MAX_COUNTERS 256
#define MAX_NR_CPUS 256
struct ip_callchain {
u64 nr;
u64 ips[0];
};
extern bool perf_host, perf_guest;
extern const char perf_version_string[];
void pthread__unblock_sigwinch(void);
struct perf_record_opts {
pid_t target_pid;
pid_t target_tid;
bool call_graph;
bool group;
bool inherit_stat;
bool no_delay;
bool no_inherit;
bool no_samples;
bool pipe_output;
bool raw_samples;
bool sample_address;
bool sample_time;
bool sample_id_all_avail;
bool system_wide;
bool period;
unsigned int freq;
unsigned int mmap_pages;
unsigned int user_freq;
u64 default_interval;
u64 user_interval;
const char *cpu_list;
};
#endif
Reference in a new issue View git blame Copy permalink