linux/tools/perf/bench/mem-memcpy.c

424 lines
10 KiB
C
Raw Normal View History

/*
* mem-memcpy.c
*
* Simple memcpy() and memset() benchmarks
*
* Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*/
#include "../perf.h"
#include "../util/util.h"
#include "../util/parse-options.h"
#include "../util/header.h"
#include "../util/cloexec.h"
#include "bench.h"
#include "mem-memcpy-arch.h"
#include "mem-memset-arch.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#include <errno.h>
#define K 1024
static const char *length_str = "1MB";
perf bench: Default to all routines in 'perf bench mem' So few people know that the --routine option to 'perf bench memcpy/memset' exists, and would not know that it's capable of testing the kernel's memcpy/memset implementations. Furthermore, 'perf bench mem all' will not run all routines: vega:~> perf bench mem all # Running mem/memcpy benchmark... Routine default (Default memcpy() provided by glibc) # Copying 1MB Bytes ... 894.454383 MB/Sec 3.844734 GB/Sec (with prefault) # Running mem/memset benchmark... Routine default (Default memset() provided by glibc) # Copying 1MB Bytes ... 1.220703 GB/Sec 9.042245 GB/Sec (with prefault) Because misleadingly the 'all' refers to 'all sub-benchmarks', not 'all sub-benchmarks and routines'. Fix all this by making the memcpy/memset routine to default to 'all', which results in all the benchmarks being run: triton:~> perf bench mem all # Running mem/memcpy benchmark... Routine default (Default memcpy() provided by glibc) # Copying 1MB Bytes ... 1.448906 GB/Sec 4.957170 GB/Sec (with prefault) Routine x86-64-unrolled (unrolled memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB Bytes ... 1.614153 GB/Sec 4.379204 GB/Sec (with prefault) Routine x86-64-movsq (movsq-based memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB Bytes ... 1.570036 GB/Sec 4.264465 GB/Sec (with prefault) Routine x86-64-movsb (movsb-based memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB Bytes ... 1.788576 GB/Sec 6.554111 GB/Sec (with prefault) # Running mem/memset benchmark... Routine default (Default memset() provided by glibc) # Copying 1MB Bytes ... 2.082223 GB/Sec 9.126752 GB/Sec (with prefault) Routine x86-64-unrolled (unrolled memset() in arch/x86/lib/memset_64.S) # Copying 1MB Bytes ... 5.710892 GB/Sec 8.346688 GB/Sec (with prefault) Routine x86-64-stosq (movsq-based memset() in arch/x86/lib/memset_64.S) # Copying 1MB Bytes ... 9.765625 GB/Sec 12.520032 GB/Sec (with prefault) Routine x86-64-stosb (movsb-based memset() in arch/x86/lib/memset_64.S) # Copying 1MB Bytes ... 9.668936 GB/Sec 12.682630 GB/Sec (with prefault) Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1445241870-24854-3-git-send-email-mingo@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-19 08:04:18 +00:00
static const char *routine = "all";
static int iterations = 1;
static bool use_cycle;
static int cycle_fd;
static bool only_prefault;
static bool no_prefault;
static const struct option options[] = {
OPT_STRING('l', "length", &length_str, "1MB",
"Specify length of memory to copy. "
"Available units: B, KB, MB, GB and TB (upper and lower)"),
perf bench: Default to all routines in 'perf bench mem' So few people know that the --routine option to 'perf bench memcpy/memset' exists, and would not know that it's capable of testing the kernel's memcpy/memset implementations. Furthermore, 'perf bench mem all' will not run all routines: vega:~> perf bench mem all # Running mem/memcpy benchmark... Routine default (Default memcpy() provided by glibc) # Copying 1MB Bytes ... 894.454383 MB/Sec 3.844734 GB/Sec (with prefault) # Running mem/memset benchmark... Routine default (Default memset() provided by glibc) # Copying 1MB Bytes ... 1.220703 GB/Sec 9.042245 GB/Sec (with prefault) Because misleadingly the 'all' refers to 'all sub-benchmarks', not 'all sub-benchmarks and routines'. Fix all this by making the memcpy/memset routine to default to 'all', which results in all the benchmarks being run: triton:~> perf bench mem all # Running mem/memcpy benchmark... Routine default (Default memcpy() provided by glibc) # Copying 1MB Bytes ... 1.448906 GB/Sec 4.957170 GB/Sec (with prefault) Routine x86-64-unrolled (unrolled memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB Bytes ... 1.614153 GB/Sec 4.379204 GB/Sec (with prefault) Routine x86-64-movsq (movsq-based memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB Bytes ... 1.570036 GB/Sec 4.264465 GB/Sec (with prefault) Routine x86-64-movsb (movsb-based memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB Bytes ... 1.788576 GB/Sec 6.554111 GB/Sec (with prefault) # Running mem/memset benchmark... Routine default (Default memset() provided by glibc) # Copying 1MB Bytes ... 2.082223 GB/Sec 9.126752 GB/Sec (with prefault) Routine x86-64-unrolled (unrolled memset() in arch/x86/lib/memset_64.S) # Copying 1MB Bytes ... 5.710892 GB/Sec 8.346688 GB/Sec (with prefault) Routine x86-64-stosq (movsq-based memset() in arch/x86/lib/memset_64.S) # Copying 1MB Bytes ... 9.765625 GB/Sec 12.520032 GB/Sec (with prefault) Routine x86-64-stosb (movsb-based memset() in arch/x86/lib/memset_64.S) # Copying 1MB Bytes ... 9.668936 GB/Sec 12.682630 GB/Sec (with prefault) Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1445241870-24854-3-git-send-email-mingo@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-19 08:04:18 +00:00
OPT_STRING('r', "routine", &routine, "all",
"Specify routine to copy, \"all\" runs all available routines"),
OPT_INTEGER('i', "iterations", &iterations,
"repeat memcpy() invocation this number of times"),
OPT_BOOLEAN('c', "cycle", &use_cycle,
"Use cycles event instead of gettimeofday() for measuring"),
OPT_BOOLEAN('o', "only-prefault", &only_prefault,
"Show only the result with page faults before memcpy()"),
OPT_BOOLEAN('n', "no-prefault", &no_prefault,
"Show only the result without page faults before memcpy()"),
OPT_END()
};
typedef void *(*memcpy_t)(void *, const void *, size_t);
typedef void *(*memset_t)(void *, int, size_t);
struct routine {
const char *name;
const char *desc;
union {
memcpy_t memcpy;
memset_t memset;
} fn;
};
struct routine memcpy_routines[] = {
{ .name = "default",
.desc = "Default memcpy() provided by glibc",
.fn.memcpy = memcpy },
#ifdef HAVE_ARCH_X86_64_SUPPORT
# define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn},
# include "mem-memcpy-x86-64-asm-def.h"
# undef MEMCPY_FN
#endif
{ NULL, }
};
static const char * const bench_mem_memcpy_usage[] = {
"perf bench mem memcpy <options>",
NULL
};
static struct perf_event_attr cycle_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES
};
static void init_cycle(void)
{
cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, perf_event_open_cloexec_flag());
if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
else
BUG_ON(cycle_fd < 0);
}
static u64 get_cycle(void)
{
int ret;
u64 clk;
ret = read(cycle_fd, &clk, sizeof(u64));
BUG_ON(ret != sizeof(u64));
return clk;
}
static double timeval2double(struct timeval *ts)
{
return (double)ts->tv_sec + (double)ts->tv_usec / (double)1000000;
}
#define print_bps(x) do { \
if (x < K) \
printf(" %14lf B/Sec", x); \
else if (x < K * K) \
printf(" %14lfd KB/Sec", x / K); \
else if (x < K * K * K) \
printf(" %14lf MB/Sec", x / K / K); \
else \
printf(" %14lf GB/Sec", x / K / K / K); \
} while (0)
struct bench_mem_info {
const struct routine *routines;
u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault);
double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault);
const char *const *usage;
};
static void __bench_mem_routine(struct bench_mem_info *info, int r_idx, size_t len, double totallen)
{
const struct routine *r = &info->routines[r_idx];
double result_bps[2];
u64 result_cycle[2];
int prefault = no_prefault ? 0 : 1;
result_cycle[0] = result_cycle[1] = 0ULL;
result_bps[0] = result_bps[1] = 0.0;
printf("Routine %s (%s)\n", r->name, r->desc);
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Copying %s Bytes ...\n\n", length_str);
if (!only_prefault && prefault) {
/* Show both results: */
if (use_cycle) {
result_cycle[0] = info->do_cycle(r, len, false);
result_cycle[1] = info->do_cycle(r, len, true);
} else {
result_bps[0] = info->do_gettimeofday(r, len, false);
result_bps[1] = info->do_gettimeofday(r, len, true);
}
} else {
if (use_cycle)
result_cycle[prefault] = info->do_cycle(r, len, only_prefault);
else
result_bps[prefault] = info->do_gettimeofday(r, len, only_prefault);
}
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
if (!only_prefault && prefault) {
if (use_cycle) {
printf(" %14lf Cycle/Byte\n",
(double)result_cycle[0]
/ totallen);
printf(" %14lf Cycle/Byte (with prefault)\n",
(double)result_cycle[1]
/ totallen);
} else {
print_bps(result_bps[0]);
printf("\n");
print_bps(result_bps[1]);
printf(" (with prefault)\n");
}
} else {
if (use_cycle) {
printf(" %14lf Cycle/Byte",
(double)result_cycle[prefault]
/ totallen);
} else
print_bps(result_bps[prefault]);
printf("%s\n", only_prefault ? " (with prefault)" : "");
}
break;
case BENCH_FORMAT_SIMPLE:
if (!only_prefault && prefault) {
if (use_cycle) {
printf("%lf %lf\n",
(double)result_cycle[0] / totallen,
(double)result_cycle[1] / totallen);
} else {
printf("%lf %lf\n",
result_bps[0], result_bps[1]);
}
} else {
if (use_cycle) {
printf("%lf\n", (double)result_cycle[prefault]
/ totallen);
} else
printf("%lf\n", result_bps[prefault]);
}
break;
default:
/* Reaching this means there's some disaster: */
die("unknown format: %d\n", bench_format);
break;
}
}
static int bench_mem_common(int argc, const char **argv,
const char *prefix __maybe_unused,
struct bench_mem_info *info)
{
int i;
size_t len;
double totallen;
argc = parse_options(argc, argv, options, info->usage, 0);
if (no_prefault && only_prefault) {
fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
return 1;
}
if (use_cycle)
init_cycle();
len = (size_t)perf_atoll((char *)length_str);
totallen = (double)len * iterations;
if ((s64)len <= 0) {
fprintf(stderr, "Invalid length:%s\n", length_str);
return 1;
}
/* Same as without specifying either of prefault and no-prefault: */
if (only_prefault && no_prefault)
only_prefault = no_prefault = false;
if (!strncmp(routine, "all", 3)) {
for (i = 0; info->routines[i].name; i++)
__bench_mem_routine(info, i, len, totallen);
return 0;
}
for (i = 0; info->routines[i].name; i++) {
if (!strcmp(info->routines[i].name, routine))
break;
}
if (!info->routines[i].name) {
printf("Unknown routine:%s\n", routine);
printf("Available routines...\n");
for (i = 0; info->routines[i].name; i++) {
printf("\t%s ... %s\n",
info->routines[i].name, info->routines[i].desc);
}
return 1;
}
__bench_mem_routine(info, i, len, totallen);
return 0;
}
static void memcpy_alloc_mem(void **dst, void **src, size_t length)
{
*dst = zalloc(length);
if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
*src = zalloc(length);
if (!*src)
die("memory allocation failed - maybe length is too large?\n");
/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
memset(*src, 0, length);
}
static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *src = NULL, *dst = NULL;
memcpy_t fn = r->fn.memcpy;
int i;
memcpy_alloc_mem(&dst, &src, len);
if (prefault)
fn(dst, src, len);
cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
cycle_end = get_cycle();
free(src);
free(dst);
return cycle_end - cycle_start;
}
static double do_memcpy_gettimeofday(const struct routine *r, size_t len, bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
memcpy_t fn = r->fn.memcpy;
void *src = NULL, *dst = NULL;
int i;
memcpy_alloc_mem(&dst, &src, len);
if (prefault)
fn(dst, src, len);
BUG_ON(gettimeofday(&tv_start, NULL));
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
free(src);
free(dst);
return (double)(((double)len * iterations) / timeval2double(&tv_diff));
}
int bench_mem_memcpy(int argc, const char **argv,
const char *prefix __maybe_unused)
{
struct bench_mem_info info = {
.routines = memcpy_routines,
.do_cycle = do_memcpy_cycle,
.do_gettimeofday = do_memcpy_gettimeofday,
.usage = bench_mem_memcpy_usage,
};
return bench_mem_common(argc, argv, prefix, &info);
}
static void memset_alloc_mem(void **dst, size_t length)
{
*dst = zalloc(length);
if (!*dst)
die("memory allocation failed - maybe length is too large?\n");
}
static u64 do_memset_cycle(const struct routine *r, size_t len, bool prefault)
{
u64 cycle_start = 0ULL, cycle_end = 0ULL;
memset_t fn = r->fn.memset;
void *dst = NULL;
int i;
memset_alloc_mem(&dst, len);
if (prefault)
fn(dst, -1, len);
cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
cycle_end = get_cycle();
free(dst);
return cycle_end - cycle_start;
}
static double do_memset_gettimeofday(const struct routine *r, size_t len,
bool prefault)
{
struct timeval tv_start, tv_end, tv_diff;
memset_t fn = r->fn.memset;
void *dst = NULL;
int i;
memset_alloc_mem(&dst, len);
if (prefault)
fn(dst, -1, len);
BUG_ON(gettimeofday(&tv_start, NULL));
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
BUG_ON(gettimeofday(&tv_end, NULL));
timersub(&tv_end, &tv_start, &tv_diff);
free(dst);
return (double)(((double)len * iterations) / timeval2double(&tv_diff));
}
static const char * const bench_mem_memset_usage[] = {
"perf bench mem memset <options>",
NULL
};
static const struct routine memset_routines[] = {
{ .name = "default",
.desc = "Default memset() provided by glibc",
.fn.memset = memset },
#ifdef HAVE_ARCH_X86_64_SUPPORT
# define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn },
# include "mem-memset-x86-64-asm-def.h"
# undef MEMSET_FN
#endif
{ NULL, }
};
int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct bench_mem_info info = {
.routines = memset_routines,
.do_cycle = do_memset_cycle,
.do_gettimeofday = do_memset_gettimeofday,
.usage = bench_mem_memset_usage,
};
return bench_mem_common(argc, argv, prefix, &info);
}