kernel_optimize_test/tools/perf/bench/sched-messaging.c

332 lines
7.0 KiB
C
Raw Normal View History

/*
*
perf bench: Add "all" pseudo subsystem and "all" pseudo suite This patch adds a new "all" pseudo subsystem and an "all" pseudo suite. These are for testing all subsystem and its all suite, or all suite of one subsystem. (This patch also contains a few trivial comment fixes for bench/* and output style fixes. I judged that there are no necessity to make them into individual patch.) Example of use: | % ./perf bench sched all # Test all suites of sched subsystem | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.414 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 10.999 [sec] | | 10.999317 usecs/op | 90914 ops/sec | | % ./perf bench all # Test all suites of all subsystems | # Running sched/messaging benchmark... | # 20 sender and receiver processes per group | # 10 groups == 400 processes run | | Total time: 0.420 [sec] | | # Running sched/pipe benchmark... | # Extecuted 1000000 pipe operations between two tasks | | Total time: 11.741 [sec] | | 11.741346 usecs/op | 85169 ops/sec | | # Running mem/memcpy benchmark... | # Copying 1MB Bytes from 0x7ff33e920010 to 0x7ff3401ae010 ... | | 808.407437 MB/Sec Signed-off-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1260691319-4683-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-13 16:01:59 +08:00
* sched-messaging.c
*
* messaging: Benchmark for scheduler and IPC mechanisms
*
* Based on hackbench by Rusty Russell <rusty@rustcorp.com.au>
* Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*
*/
#include "../perf.h"
#include "../util/util.h"
#include "../util/parse-options.h"
#include "../builtin.h"
#include "bench.h"
/* Test groups of 20 processes spraying to 20 receivers */
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/wait.h>
#include <sys/time.h>
#include <poll.h>
#include <limits.h>
#include <err.h>
#define DATASIZE 100
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool use_pipes = false;
static unsigned int nr_loops = 100;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool thread_mode = false;
static unsigned int num_groups = 10;
struct sender_context {
unsigned int num_fds;
int ready_out;
int wakefd;
int out_fds[0];
};
struct receiver_context {
unsigned int num_packets;
int in_fds[2];
int ready_out;
int wakefd;
};
static void fdpair(int fds[2])
{
if (use_pipes) {
if (pipe(fds) == 0)
return;
} else {
if (socketpair(AF_UNIX, SOCK_STREAM, 0, fds) == 0)
return;
}
err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()");
}
/* Block until we're ready to go */
static void ready(int ready_out, int wakefd)
{
char dummy;
struct pollfd pollfd = { .fd = wakefd, .events = POLLIN };
/* Tell them we're ready. */
if (write(ready_out, &dummy, 1) != 1)
err(EXIT_FAILURE, "CLIENT: ready write");
/* Wait for "GO" signal */
if (poll(&pollfd, 1, -1) != 1)
err(EXIT_FAILURE, "poll");
}
/* Sender sprays nr_loops messages down each file descriptor */
static void *sender(struct sender_context *ctx)
{
char data[DATASIZE];
unsigned int i, j;
ready(ctx->ready_out, ctx->wakefd);
/* Now pump to every receiver. */
for (i = 0; i < nr_loops; i++) {
for (j = 0; j < ctx->num_fds; j++) {
int ret, done = 0;
again:
ret = write(ctx->out_fds[j], data + done,
sizeof(data)-done);
if (ret < 0)
err(EXIT_FAILURE, "SENDER: write");
done += ret;
if (done < DATASIZE)
goto again;
}
}
return NULL;
}
/* One receiver per fd */
static void *receiver(struct receiver_context* ctx)
{
unsigned int i;
if (!thread_mode)
close(ctx->in_fds[1]);
/* Wait for start... */
ready(ctx->ready_out, ctx->wakefd);
/* Receive them all */
for (i = 0; i < ctx->num_packets; i++) {
char data[DATASIZE];
int ret, done = 0;
again:
ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
if (ret < 0)
err(EXIT_FAILURE, "SERVER: read");
done += ret;
if (done < DATASIZE)
goto again;
}
return NULL;
}
static pthread_t create_worker(void *ctx, void *(*func)(void *))
{
pthread_attr_t attr;
pthread_t childid;
int ret;
if (!thread_mode) {
/* process mode */
/* Fork the receiver. */
switch (fork()) {
case -1:
err(EXIT_FAILURE, "fork()");
break;
case 0:
(*func) (ctx);
exit(0);
break;
default:
break;
}
return (pthread_t)0;
}
if (pthread_attr_init(&attr) != 0)
err(EXIT_FAILURE, "pthread_attr_init:");
#ifndef __ia64__
if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
err(EXIT_FAILURE, "pthread_attr_setstacksize");
#endif
ret = pthread_create(&childid, &attr, func, ctx);
if (ret != 0)
err(EXIT_FAILURE, "pthread_create failed");
return childid;
}
static void reap_worker(pthread_t id)
{
int proc_status;
void *thread_status;
if (!thread_mode) {
/* process mode */
wait(&proc_status);
if (!WIFEXITED(proc_status))
exit(1);
} else {
pthread_join(id, &thread_status);
}
}
/* One group of senders and receivers */
static unsigned int group(pthread_t *pth,
unsigned int num_fds,
int ready_out,
int wakefd)
{
unsigned int i;
struct sender_context *snd_ctx = malloc(sizeof(struct sender_context)
+ num_fds * sizeof(int));
if (!snd_ctx)
err(EXIT_FAILURE, "malloc()");
for (i = 0; i < num_fds; i++) {
int fds[2];
struct receiver_context *ctx = malloc(sizeof(*ctx));
if (!ctx)
err(EXIT_FAILURE, "malloc()");
/* Create the pipe between client and server */
fdpair(fds);
ctx->num_packets = num_fds * nr_loops;
ctx->in_fds[0] = fds[0];
ctx->in_fds[1] = fds[1];
ctx->ready_out = ready_out;
ctx->wakefd = wakefd;
pth[i] = create_worker(ctx, (void *)receiver);
snd_ctx->out_fds[i] = fds[1];
if (!thread_mode)
close(fds[0]);
}
/* Now we have all the fds, fork the senders */
for (i = 0; i < num_fds; i++) {
snd_ctx->ready_out = ready_out;
snd_ctx->wakefd = wakefd;
snd_ctx->num_fds = num_fds;
pth[num_fds+i] = create_worker(snd_ctx, (void *)sender);
}
/* Close the fds we have left */
if (!thread_mode)
for (i = 0; i < num_fds; i++)
close(snd_ctx->out_fds[i]);
/* Return number of children to reap */
return num_fds * 2;
}
static const struct option options[] = {
OPT_BOOLEAN('p', "pipe", &use_pipes,
"Use pipe() instead of socketpair()"),
OPT_BOOLEAN('t', "thread", &thread_mode,
"Be multi thread instead of multi process"),
OPT_UINTEGER('g', "group", &num_groups, "Specify number of groups"),
OPT_UINTEGER('l', "nr_loops", &nr_loops, "Specify the number of loops to run (default: 100)"),
OPT_END()
};
static const char * const bench_sched_message_usage[] = {
"perf bench sched messaging <options>",
NULL
};
int bench_sched_messaging(int argc, const char **argv,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
const char *prefix __maybe_unused)
{
unsigned int i, total_children;
struct timeval start, stop, diff;
unsigned int num_fds = 20;
int readyfds[2], wakefds[2];
char dummy;
pthread_t *pth_tab;
argc = parse_options(argc, argv, options,
bench_sched_message_usage, 0);
pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
if (!pth_tab)
err(EXIT_FAILURE, "main:malloc()");
fdpair(readyfds);
fdpair(wakefds);
total_children = 0;
for (i = 0; i < num_groups; i++)
total_children += group(pth_tab+total_children, num_fds,
readyfds[1], wakefds[0]);
/* Wait for everyone to be ready */
for (i = 0; i < total_children; i++)
if (read(readyfds[0], &dummy, 1) != 1)
err(EXIT_FAILURE, "Reading for readyfds");
gettimeofday(&start, NULL);
/* Kick them off */
if (write(wakefds[1], &dummy, 1) != 1)
err(EXIT_FAILURE, "Writing to start them");
/* Reap them all */
for (i = 0; i < total_children; i++)
reap_worker(pth_tab[i]);
gettimeofday(&stop, NULL);
timersub(&stop, &start, &diff);
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
printf("# %d sender and receiver %s per group\n",
num_fds, thread_mode ? "threads" : "processes");
printf("# %d groups == %d %s run\n\n",
num_groups, num_groups * 2 * num_fds,
thread_mode ? "threads" : "processes");
printf(" %14s: %lu.%03lu [sec]\n", "Total time",
diff.tv_sec,
(unsigned long) (diff.tv_usec/1000));
break;
case BENCH_FORMAT_SIMPLE:
printf("%lu.%03lu\n", diff.tv_sec,
(unsigned long) (diff.tv_usec/1000));
break;
default:
/* reaching here is something disaster */
fprintf(stderr, "Unknown format:%d\n", bench_format);
exit(1);
break;
}
free(pth_tab);
return 0;
}