summaryrefslogtreecommitdiffstats
path: root/app/test/test_mempool_perf.c
blob: c0b3f5ce5e407813f6400bb80ef3ce086a32fbd5 (plain)
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
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <string.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
#include <stdarg.h>
#include <errno.h>
#include <sys/queue.h>

#include <rte_common.h>
#include <rte_log.h>
#include <rte_debug.h>
#include <rte_memory.h>
#include <rte_memzone.h>
#include <rte_launch.h>
#include <rte_cycles.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_atomic.h>
#include <rte_branch_prediction.h>
#include <rte_ring.h>
#include <rte_mempool.h>
#include <rte_spinlock.h>
#include <rte_malloc.h>

#include "test.h"

/*
 * Mempool performance
 * =======
 *
 *    Each core get *n_keep* objects per bulk of *n_get_bulk*. Then,
 *    objects are put back in the pool per bulk of *n_put_bulk*.
 *
 *    This sequence is done during TIME_S seconds.
 *
 *    This test is done on the following configurations:
 *
 *    - Cores configuration (*cores*)
 *
 *      - One core with cache
 *      - Two cores with cache
 *      - Max. cores with cache
 *      - One core without cache
 *      - Two cores without cache
 *      - Max. cores without cache
 *      - One core with user-owned cache
 *      - Two cores with user-owned cache
 *      - Max. cores with user-owned cache
 *
 *    - Bulk size (*n_get_bulk*, *n_put_bulk*)
 *
 *      - Bulk get from 1 to 32
 *      - Bulk put from 1 to 32
 *
 *    - Number of kept objects (*n_keep*)
 *
 *      - 32
 *      - 128
 */

#define N 65536
#define TIME_S 5
#define MEMPOOL_ELT_SIZE 2048
#define MAX_KEEP 128
#define MEMPOOL_SIZE ((rte_lcore_count()*(MAX_KEEP+RTE_MEMPOOL_CACHE_MAX_SIZE))-1)

#define LOG_ERR() printf("test failed at %s():%d\n", __func__, __LINE__)
#define RET_ERR() do {							\
		LOG_ERR();						\
		return -1;						\
	} while (0)
#define GOTO_ERR(var, label) do {					\
		LOG_ERR();						\
		var = -1;						\
		goto label;						\
	} while (0)

static struct rte_mempool *mp;
static struct rte_mempool *mp_cache, *mp_nocache;
static int use_external_cache;
static unsigned external_cache_size = RTE_MEMPOOL_CACHE_MAX_SIZE;

static rte_atomic32_t synchro;

/* number of objects in one bulk operation (get or put) */
static unsigned n_get_bulk;
static unsigned n_put_bulk;

/* number of objects retrived from mempool before putting them back */
static unsigned n_keep;

/* number of enqueues / dequeues */
struct mempool_test_stats {
	uint64_t enq_count;
} __rte_cache_aligned;

static struct mempool_test_stats stats[RTE_MAX_LCORE];

/*
 * save the object number in the first 4 bytes of object data. All
 * other bytes are set to 0.
 */
static void
my_obj_init(struct rte_mempool *mp, __attribute__((unused)) void *arg,
	    void *obj, unsigned i)
{
	uint32_t *objnum = obj;
	memset(obj, 0, mp->elt_size);
	*objnum = i;
}

static int
per_lcore_mempool_test(__attribute__((unused)) void *arg)
{
	void *obj_table[MAX_KEEP];
	unsigned i, idx;
	unsigned lcore_id = rte_lcore_id();
	int ret = 0;
	uint64_t start_cycles, end_cycles;
	uint64_t time_diff = 0, hz = rte_get_timer_hz();
	struct rte_mempool_cache *cache;

	if (use_external_cache) {
		/* Create a user-owned mempool cache. */
		cache = rte_mempool_cache_create(external_cache_size,
						 SOCKET_ID_ANY);
		if (cache == NULL)
			RET_ERR();
	} else {
		/* May be NULL if cache is disabled. */
		cache = rte_mempool_default_cache(mp, lcore_id);
	}

	/* n_get_bulk and n_put_bulk must be divisors of n_keep */
	if (((n_keep / n_get_bulk) * n_get_bulk) != n_keep)
		GOTO_ERR(ret, out);
	if (((n_keep / n_put_bulk) * n_put_bulk) != n_keep)
		GOTO_ERR(ret, out);

	stats[lcore_id].enq_count = 0;

	/* wait synchro for slaves */
	if (lcore_id != rte_get_master_lcore())
		while (rte_atomic32_read(&synchro) == 0);

	start_cycles = rte_get_timer_cycles();

	while (time_diff/hz < TIME_S) {
		for (i = 0; likely(i < (N/n_keep)); i++) {
			/* get n_keep objects by bulk of n_bulk */
			idx = 0;
			while (idx < n_keep) {
				ret = rte_mempool_generic_get(mp,
							      &obj_table[idx],
							      n_get_bulk,
							      cache, 0);
				if (unlikely(ret < 0)) {
					rte_mempool_dump(stdout, mp);
					/* in this case, objects are lost... */
					GOTO_ERR(ret, out);
				}
				idx += n_get_bulk;
			}

			/* put the objects back */
			idx = 0;
			while (idx < n_keep) {
				rte_mempool_generic_put(mp, &obj_table[idx],
							n_put_bulk,
							cache, 0);
				idx += n_put_bulk;
			}
		}
		end_cycles = rte_get_timer_cycles();
		time_diff = end_cycles - start_cycles;
		stats[lcore_id].enq_count += N;
	}

out:
	if (use_external_cache) {
		rte_mempool_cache_flush(cache, mp);
		rte_mempool_cache_free(cache);
	}

	return ret;
}

/* launch all the per-lcore test, and display the result */
static int
launch_cores(unsigned cores)
{
	unsigned lcore_id;
	uint64_t rate;
	int ret;
	unsigned cores_save = cores;

	rte_atomic32_set(&synchro, 0);

	/* reset stats */
	memset(stats, 0, sizeof(stats));

	printf("mempool_autotest cache=%u cores=%u n_get_bulk=%u "
	       "n_put_bulk=%u n_keep=%u ",
	       use_external_cache ?
		   external_cache_size : (unsigned) mp->cache_size,
	       cores, n_get_bulk, n_put_bulk, n_keep);

	if (rte_mempool_avail_count(mp) != MEMPOOL_SIZE) {
		printf("mempool is not full\n");
		return -1;
	}

	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (cores == 1)
			break;
		cores--;
		rte_eal_remote_launch(per_lcore_mempool_test,
				      NULL, lcore_id);
	}

	/* start synchro and launch test on master */
	rte_atomic32_set(&synchro, 1);

	ret = per_lcore_mempool_test(NULL);

	cores = cores_save;
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (cores == 1)
			break;
		cores--;
		if (rte_eal_wait_lcore(lcore_id) < 0)
			ret = -1;
	}

	if (ret < 0) {
		printf("per-lcore test returned -1\n");
		return -1;
	}

	rate = 0;
	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
		rate += (stats[lcore_id].enq_count / TIME_S);

	printf("rate_persec=%" PRIu64 "\n", rate);

	return 0;
}

/* for a given number of core, launch all test cases */
static int
do_one_mempool_test(unsigned cores)
{
	unsigned bulk_tab_get[] = { 1, 4, 32, 0 };
	unsigned bulk_tab_put[] = { 1, 4, 32, 0 };
	unsigned keep_tab[] = { 32, 128, 0 };
	unsigned *get_bulk_ptr;
	unsigned *put_bulk_ptr;
	unsigned *keep_ptr;
	int ret;

	for (get_bulk_ptr = bulk_tab_get; *get_bulk_ptr; get_bulk_ptr++) {
		for (put_bulk_ptr = bulk_tab_put; *put_bulk_ptr; put_bulk_ptr++) {
			for (keep_ptr = keep_tab; *keep_ptr; keep_ptr++) {

				n_get_bulk = *get_bulk_ptr;
				n_put_bulk = *put_bulk_ptr;
				n_keep = *keep_ptr;
				ret = launch_cores(cores);

				if (ret < 0)
					return -1;
			}
		}
	}
	return 0;
}

static int
test_mempool_perf(void)
{
	rte_atomic32_init(&synchro);

	/* create a mempool (without cache) */
	if (mp_nocache == NULL)
		mp_nocache = rte_mempool_create("perf_test_nocache", MEMPOOL_SIZE,
						MEMPOOL_ELT_SIZE, 0, 0,
						NULL, NULL,
						my_obj_init, NULL,
						SOCKET_ID_ANY, 0);
	if (mp_nocache == NULL)
		return -1;

	/* create a mempool (with cache) */
	if (mp_cache == NULL)
		mp_cache = rte_mempool_create("perf_test_cache", MEMPOOL_SIZE,
					      MEMPOOL_ELT_SIZE,
					      RTE_MEMPOOL_CACHE_MAX_SIZE, 0,
					      NULL, NULL,
					      my_obj_init, NULL,
					      SOCKET_ID_ANY, 0);
	if (mp_cache == NULL)
		return -1;

	/* performance test with 1, 2 and max cores */
	printf("start performance test (without cache)\n");
	mp = mp_nocache;

	if (do_one_mempool_test(1) < 0)
		return -1;

	if (do_one_mempool_test(2) < 0)
		return -1;

	if (do_one_mempool_test(rte_lcore_count()) < 0)
		return -1;

	/* performance test with 1, 2 and max cores */
	printf("start performance test (with cache)\n");
	mp = mp_cache;

	if (do_one_mempool_test(1) < 0)
		return -1;

	if (do_one_mempool_test(2) < 0)
		return -1;

	if (do_one_mempool_test(rte_lcore_count()) < 0)
		return -1;

	/* performance test with 1, 2 and max cores */
	printf("start performance test (with user-owned cache)\n");
	mp = mp_nocache;
	use_external_cache = 1;

	if (do_one_mempool_test(1) < 0)
		return -1;

	if (do_one_mempool_test(2) < 0)
		return -1;

	if (do_one_mempool_test(rte_lcore_count()) < 0)
		return -1;

	rte_mempool_list_dump(stdout);

	return 0;
}

REGISTER_TEST_COMMAND(mempool_perf_autotest, test_mempool_perf);