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
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2018 Davidlohr Bueso.
*
* Benchmark the various operations allowed for epoll_ctl(2).
* The idea is to concurrently stress a single epoll instance
*/
#ifdef HAVE_EVENTFD_SUPPORT
/* For the CLR_() macros */
#include <string.h>
#include <pthread.h>
#include <errno.h>
#include <inttypes.h>
#include <signal.h>
#include <stdlib.h>
#include <unistd.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/epoll.h>
#include <sys/eventfd.h>
#include <perf/cpumap.h>
#include "../util/mutex.h"
#include "../util/stat.h"
#include <subcmd/parse-options.h>
#include "bench.h"
#include <err.h>
#define printinfo(fmt, arg...) \
do { if (__verbose) printf(fmt, ## arg); } while (0)
static unsigned int nthreads = 0;
static unsigned int nsecs = 8;
static bool done, __verbose, randomize;
/*
* epoll related shared variables.
*/
/* Maximum number of nesting allowed inside epoll sets */
#define EPOLL_MAXNESTS 4
enum {
OP_EPOLL_ADD,
OP_EPOLL_MOD,
OP_EPOLL_DEL,
EPOLL_NR_OPS,
};
static int epollfd;
static int *epollfdp;
static bool noaffinity;
static unsigned int nested = 0;
/* amount of fds to monitor, per thread */
static unsigned int nfds = 64;
static struct mutex thread_lock;
static unsigned int threads_starting;
static struct stats all_stats[EPOLL_NR_OPS];
static struct cond thread_parent, thread_worker;
struct worker {
int tid;
pthread_t thread;
unsigned long ops[EPOLL_NR_OPS];
int *fdmap;
};
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
OPT_UINTEGER('f', "nfds", &nfds, "Specify amount of file descriptors to monitor for each thread"),
OPT_BOOLEAN( 'n', "noaffinity", &noaffinity, "Disables CPU affinity"),
OPT_UINTEGER( 'N', "nested", &nested, "Nesting level epoll hierarchy (default is 0, no nesting)"),
OPT_BOOLEAN( 'R', "randomize", &randomize, "Perform random operations on random fds"),
OPT_BOOLEAN( 'v', "verbose", &__verbose, "Verbose mode"),
OPT_END()
};
static const char * const bench_epoll_ctl_usage[] = {
"perf bench epoll ctl <options>",
NULL
};
static void toggle_done(int sig __maybe_unused,
siginfo_t *info __maybe_unused,
void *uc __maybe_unused)
{
/* inform all threads that we're done for the day */
done = true;
gettimeofday(&bench__end, NULL);
timersub(&bench__end, &bench__start, &bench__runtime);
}
static void nest_epollfd(void)
{
unsigned int i;
struct epoll_event ev;
if (nested > EPOLL_MAXNESTS)
nested = EPOLL_MAXNESTS;
printinfo("Nesting level(s): %d\n", nested);
epollfdp = calloc(nested, sizeof(int));
if (!epollfdp)
err(EXIT_FAILURE, "calloc");
for (i = 0; i < nested; i++) {
epollfdp[i] = epoll_create(1);
if (epollfd < 0)
err(EXIT_FAILURE, "epoll_create");
}
ev.events = EPOLLHUP; /* anything */
ev.data.u64 = i; /* any number */
for (i = nested - 1; i; i--) {
if (epoll_ctl(epollfdp[i - 1], EPOLL_CTL_ADD,
epollfdp[i], &ev) < 0)
err(EXIT_FAILURE, "epoll_ctl");
}
if (epoll_ctl(epollfd, EPOLL_CTL_ADD, *epollfdp, &ev) < 0)
err(EXIT_FAILURE, "epoll_ctl");
}
static inline void do_epoll_op(struct worker *w, int op, int fd)
{
int error;
struct epoll_event ev;
ev.events = EPOLLIN;
ev.data.u64 = fd;
switch (op) {
case OP_EPOLL_ADD:
error = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev);
break;
case OP_EPOLL_MOD:
ev.events = EPOLLOUT;
error = epoll_ctl(epollfd, EPOLL_CTL_MOD, fd, &ev);
break;
case OP_EPOLL_DEL:
error = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL);
break;
default:
error = 1;
break;
}
if (!error)
w->ops[op]++;
}
static inline void do_random_epoll_op(struct worker *w)
{
unsigned long rnd1 = random(), rnd2 = random();
int op, fd;
fd = w->fdmap[rnd1 % nfds];
op = rnd2 % EPOLL_NR_OPS;
do_epoll_op(w, op, fd);
}
static void *workerfn(void *arg)
{
unsigned int i;
struct worker *w = (struct worker *) arg;
struct timespec ts = { .tv_sec = 0,
.tv_nsec = 250 };
mutex_lock(&thread_lock);
threads_starting--;
if (!threads_starting)
cond_signal(&thread_parent);
cond_wait(&thread_worker, &thread_lock);
mutex_unlock(&thread_lock);
/* Let 'em loose */
do {
/* random */
if (randomize) {
do_random_epoll_op(w);
} else {
for (i = 0; i < nfds; i++) {
do_epoll_op(w, OP_EPOLL_ADD, w->fdmap[i]);
do_epoll_op(w, OP_EPOLL_MOD, w->fdmap[i]);
do_epoll_op(w, OP_EPOLL_DEL, w->fdmap[i]);
}
}
nanosleep(&ts, NULL);
} while (!done);
return NULL;
}
static void init_fdmaps(struct worker *w, int pct)
{
unsigned int i;
int inc;
struct epoll_event ev;
if (!pct)
return;
inc = 100/pct;
for (i = 0; i < nfds; i+=inc) {
ev.data.fd = w->fdmap[i];
ev.events = EPOLLIN;
if (epoll_ctl(epollfd, EPOLL_CTL_ADD, w->fdmap[i], &ev) < 0)
err(EXIT_FAILURE, "epoll_ct");
}
}
static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
{
pthread_attr_t thread_attr, *attrp = NULL;
cpu_set_t *cpuset;
unsigned int i, j;
int ret = 0;
int nrcpus;
size_t size;
if (!noaffinity)
pthread_attr_init(&thread_attr);
nrcpus = cpu__max_cpu().cpu;
cpuset = CPU_ALLOC(nrcpus);
BUG_ON(!cpuset);
size = CPU_ALLOC_SIZE(nrcpus);
for (i = 0; i < nthreads; i++) {
struct worker *w = &worker[i];
w->tid = i;
w->fdmap = calloc(nfds, sizeof(int));
if (!w->fdmap)
return 1;
for (j = 0; j < nfds; j++) {
w->fdmap[j] = eventfd(0, EFD_NONBLOCK);
if (w->fdmap[j] < 0)
err(EXIT_FAILURE, "eventfd");
}
/*
* Lets add 50% of the fdmap to the epoll instance, and
* do it before any threads are started; otherwise there is
* an initial bias of the call failing (mod and del ops).
*/
if (randomize)
init_fdmaps(w, 50);
if (!noaffinity) {
CPU_ZERO_S(size, cpuset);
CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
size, cpuset);
ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
if (ret) {
CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
}
attrp = &thread_attr;
}
ret = pthread_create(&w->thread, attrp, workerfn,
(void *)(struct worker *) w);
if (ret) {
CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
}
}
CPU_FREE(cpuset);
if (!noaffinity)
pthread_attr_destroy(&thread_attr);
return ret;
}
static void print_summary(void)
{
int i;
unsigned long avg[EPOLL_NR_OPS];
double stddev[EPOLL_NR_OPS];
for (i = 0; i < EPOLL_NR_OPS; i++) {
avg[i] = avg_stats(&all_stats[i]);
stddev[i] = stddev_stats(&all_stats[i]);
}
printf("\nAveraged %ld ADD operations (+- %.2f%%)\n",
avg[OP_EPOLL_ADD], rel_stddev_stats(stddev[OP_EPOLL_ADD],
avg[OP_EPOLL_ADD]));
printf("Averaged %ld MOD operations (+- %.2f%%)\n",
avg[OP_EPOLL_MOD], rel_stddev_stats(stddev[OP_EPOLL_MOD],
avg[OP_EPOLL_MOD]));
printf("Averaged %ld DEL operations (+- %.2f%%)\n",
avg[OP_EPOLL_DEL], rel_stddev_stats(stddev[OP_EPOLL_DEL],
avg[OP_EPOLL_DEL]));
}
int bench_epoll_ctl(int argc, const char **argv)
{
int j, ret = 0;
struct sigaction act;
struct worker *worker = NULL;
struct perf_cpu_map *cpu;
struct rlimit rl, prevrl;
unsigned int i;
argc = parse_options(argc, argv, options, bench_epoll_ctl_usage, 0);
if (argc) {
usage_with_options(bench_epoll_ctl_usage, options);
exit(EXIT_FAILURE);
}
memset(&act, 0, sizeof(act));
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
cpu = perf_cpu_map__new_online_cpus();
if (!cpu)
goto errmem;
/* a single, main epoll instance */
epollfd = epoll_create(1);
if (epollfd < 0)
err(EXIT_FAILURE, "epoll_create");
/*
* Deal with nested epolls, if any.
*/
if (nested)
nest_epollfd();
/* default to the number of CPUs */
if (!nthreads)
nthreads = perf_cpu_map__nr(cpu);
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
goto errmem;
if (getrlimit(RLIMIT_NOFILE, &prevrl))
err(EXIT_FAILURE, "getrlimit");
rl.rlim_cur = rl.rlim_max = nfds * nthreads * 2 + 50;
printinfo("Setting RLIMIT_NOFILE rlimit from %" PRIu64 " to: %" PRIu64 "\n",
(uint64_t)prevrl.rlim_max, (uint64_t)rl.rlim_max);
if (setrlimit(RLIMIT_NOFILE, &rl) < 0)
err(EXIT_FAILURE, "setrlimit");
printf("Run summary [PID %d]: %d threads doing epoll_ctl ops "
"%d file-descriptors for %d secs.\n\n",
getpid(), nthreads, nfds, nsecs);
for (i = 0; i < EPOLL_NR_OPS; i++)
init_stats(&all_stats[i]);
mutex_init(&thread_lock);
cond_init(&thread_parent);
cond_init(&thread_worker);
threads_starting = nthreads;
gettimeofday(&bench__start, NULL);
do_threads(worker, cpu);
mutex_lock(&thread_lock);
while (threads_starting)
cond_wait(&thread_parent, &thread_lock);
cond_broadcast(&thread_worker);
mutex_unlock(&thread_lock);
sleep(nsecs);
toggle_done(0, NULL, NULL);
printinfo("main thread: toggling done\n");
for (i = 0; i < nthreads; i++) {
ret = pthread_join(worker[i].thread, NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
}
/* cleanup & report results */
cond_destroy(&thread_parent);
cond_destroy(&thread_worker);
mutex_destroy(&thread_lock);
for (i = 0; i < nthreads; i++) {
unsigned long t[EPOLL_NR_OPS];
for (j = 0; j < EPOLL_NR_OPS; j++) {
t[j] = worker[i].ops[j];
update_stats(&all_stats[j], t[j]);
}
if (nfds == 1)
printf("[thread %2d] fdmap: %p [ add: %04ld; mod: %04ld; del: %04lds ops ]\n",
worker[i].tid, &worker[i].fdmap[0],
t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]);
else
printf("[thread %2d] fdmap: %p ... %p [ add: %04ld ops; mod: %04ld ops; del: %04ld ops ]\n",
worker[i].tid, &worker[i].fdmap[0],
&worker[i].fdmap[nfds-1],
t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]);
}
print_summary();
close(epollfd);
perf_cpu_map__put(cpu);
for (i = 0; i < nthreads; i++)
free(worker[i].fdmap);
free(worker);
return ret;
errmem:
err(EXIT_FAILURE, "calloc");
}
#endif // HAVE_EVENTFD_SUPPORT
|