1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
|
/*
*
* 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 <subcmd/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>
#include <linux/time64.h>
#define DATASIZE 100
static bool use_pipes = false;
static unsigned int nr_loops = 100;
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)
{
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[<
|