summaryrefslogtreecommitdiffstats
path: root/app/test/test_ring_perf.c
blob: b4e4daeca72d952922b3fc519a1b6acc62128ad6 (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
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
/*-
 *   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 <stdio.h>
#include <inttypes.h>
#include <rte_ring.h>
#include <rte_cycles.h>
#include <rte_launch.h>

#include "test.h"

/*
 * Ring
 * ====
 *
 * Measures performance of various operations using rdtsc
 *  * Empty ring dequeue
 *  * Enqueue/dequeue of bursts in 1 threads
 *  * Enqueue/dequeue of bursts in 2 threads
 */

#define RING_NAME "RING_PERF"
#define RING_SIZE 4096
#define MAX_BURST 32

/*
 * the sizes to enqueue and dequeue in testing
 * (marked volatile so they won't be seen as compile-time constants)
 */
static const volatile unsigned bulk_sizes[] = { 8, 32 };

struct lcore_pair {
	unsigned c1, c2;
};

static volatile unsigned lcore_count = 0;

/**** Functions to analyse our core mask to get cores for different tests ***/

static int
get_two_hyperthreads(struct lcore_pair *lcp)
{
	unsigned id1, id2;
	unsigned c1, c2, s1, s2;
	RTE_LCORE_FOREACH(id1) {
		/* inner loop just re-reads all id's. We could skip the first few
		 * elements, but since number of cores is small there is little point
		 */
		RTE_LCORE_FOREACH(id2) {
			if (id1 == id2)
				continue;
			c1 = lcore_config[id1].core_id;
			c2 = lcore_config[id2].core_id;
			s1 = lcore_config[id1].socket_id;
			s2 = lcore_config[id2].socket_id;
			if ((c1 == c2) && (s1 == s2)){
				lcp->c1 = id1;
				lcp->c2 = id2;
				return 0;
			}
		}
	}
	return 1;
}

static int
get_two_cores(struct lcore_pair *lcp)
{
	unsigned id1, id2;
	unsigned c1, c2, s1, s2;
	RTE_LCORE_FOREACH(id1) {
		RTE_LCORE_FOREACH(id2) {
			if (id1 == id2)
				continue;
			c1 = lcore_config[id1].core_id;
			c2 = lcore_config[id2].core_id;
			s1 = lcore_config[id1].socket_id;
			s2 = lcore_config[id2].socket_id;
			if ((c1 != c2) && (s1 == s2)){
				lcp->c1 = id1;
				lcp->c2 = id2;
				return 0;
			}
		}
	}
	return 1;
}

static int
get_two_sockets(struct lcore_pair *lcp)
{
	unsigned id1, id2;
	unsigned s1, s2;
	RTE_LCORE_FOREACH(id1) {
		RTE_LCORE_FOREACH(id2) {
			if (id1 == id2)
				continue;
			s1 = lcore_config[id1].socket_id;
			s2 = lcore_config[id2].socket_id;
			if (s1 != s2){
				lcp->c1 = id1;
				lcp->c2 = id2;
				return 0;
			}
		}
	}
	return 1;
}

/* Get cycle counts for dequeuing from an empty ring. Should be 2 or 3 cycles */
static void
test_empty_dequeue(struct rte_ring *r)
{
	const unsigned iter_shift = 26;
	const unsigned iterations = 1<<iter_shift;
	unsigned i = 0;
	void *burst[MAX_BURST];

	const uint64_t sc_start = rte_rdtsc();
	for (i = 0; i < iterations; i++)
		rte_ring_sc_dequeue_bulk(r, burst, bulk_sizes[0]);
	const uint64_t sc_end = rte_rdtsc();

	const uint64_t mc_start = rte_rdtsc();
	for (i = 0; i < iterations; i++)
		rte_ring_mc_dequeue_bulk(r, burst, bulk_sizes[0]);
	const uint64_t mc_end = rte_rdtsc();

	printf("SC empty dequeue: %.2F\n",
			(double)(sc_end-sc_start) / iterations);
	printf("MC empty dequeue: %.2F\n",
			(double)(mc_end-mc_start) / iterations);
}

/*
 * for the separate enqueue and dequeue threads they take in one param
 * and return two. Input = burst size, output = cycle average for sp/sc & mp/mc
 */
struct thread_params {
	struct rte_ring *r;
	unsigned size;        /* input value, the burst size */
	double spsc, mpmc;    /* output value, the single or multi timings */
};

/*
 * Function that uses rdtsc to measure timing for ring enqueue. Needs pair
 * thread running dequeue_bulk function
 */
static int
enqueue_bulk(void *p)
{
	const unsigned iter_shift = 23;
	const unsigned iterations = 1<<iter_shift;
	struct thread_params *params = p;
	struct rte_ring *r = params->r;
	const unsigned size = params->size;
	unsigned i;
	void *burst[MAX_BURST] = {0};

	if ( __sync_add_and_fetch(&lcore_count, 1) != 2 )
		while(lcore_count != 2)
			rte_pause();

	const uint64_t sp_start = rte_rdtsc();
	for (i = 0; i < iterations; i++)
		while (rte_ring_sp_enqueue_bulk(r, burst, size) != 0)
			rte_pause();
	const uint64_t sp_end = rte_rdtsc();

	const uint64_t mp_start = rte_rdtsc();
	for (i = 0; i < iterations; i++)
		while (rte_ring_mp_enqueue_bulk(r, burst, size) != 0)
			rte_pause();
	const uint64_t mp_end = rte_rdtsc();

	params->spsc = ((double)(sp_end - sp_start))/(iterations*size);
	params->mpmc = ((double)(mp_end - mp_start))/(iterations*size);
	return 0;
}

/*
 * Function that uses rdtsc to measure timing for ring dequeue. Needs pair
 * thread running enqueue_bulk function
 */
static int
dequeue_bulk(void *p)
{
	const unsigned iter_shift = 23;
	const unsigned iterations = 1<<iter_shift;
	struct thread_params *params = p;
	struct rte_ring *r = params->r;
	const unsigned size = params->size;
	unsigned i;
	void *burst[MAX_BURST] = {0};

	if ( __sync_add_and_fetch(&lcore_count, 1) != 2 )
		while(lcore_count != 2)
			rte_pause();

	const uint64_t sc_start = rte_rdtsc();
	for (i = 0; i < iterations; i++)
		while (rte_ring_sc_dequeue_bulk(r, burst, size) != 0)
			rte_pause();
	const uint64_t sc_end = rte_rdtsc();

	const uint64_t mc_start = rte_rdtsc();
	for (i = 0; i < iterations; i++)
		while (rte_ring_mc_dequeue_bulk(r, burst, size) != 0)
			rte_pause();
	const uint64_t mc_end = rte_rdtsc();

	params->spsc = ((double)(sc_end - sc_start))/(iterations*size);
	params->mpmc = ((double)(mc_end - mc_start))/(iterations*size);
	return 0;
}

/*
 * Function that calls the enqueue and dequeue bulk functions on pairs of cores.
 * used to measure ring perf between hyperthreads, cores and sockets.
 */
static void
run_on_core_pair(struct lcore_pair *cores, struct rte_ring *r,
		lcore_function_t f1, lcore_function_t f2)
{
	struct thread_params param1 = {0}, param2 = {0};
	unsigned i;
	for (i = 0; i < sizeof(bulk_sizes)/sizeof(bulk_sizes[0]); i++) {
		lcore_count = 0;
		param1.size = param2.size = bulk_sizes[i];
		param1.r = param2.r = r;
		if (cores->c1 == rte_get_master_lcore()) {
			rte_eal_remote_launch(f2, &param2, cores->c2);
			f1(&param1);
			rte_eal_wait_lcore(cores->c2);
		} else {
			rte_eal_remote_launch(f1, &param1, cores->c1);
			rte_eal_remote_launch(f2, &param2, cores->c2);
			rte_eal_wait_lcore(cores->c1);
			rte_eal_wait_lcore(cores->c2);
		}
		printf("SP/SC bulk enq/dequeue (size: %u): %.2F\n", bulk_sizes[i],
				param1.spsc + param2.spsc);
		printf("MP/MC bulk enq/dequeue (size: %u): %.2F\n", bulk_sizes[i],
				param1.mpmc + param2.mpmc);
	}
}

/*
 * Test function that determines how long an enqueue + dequeue of a single item
 * takes on a single lcore. Result is for comparison with the bulk enq+deq.
 */
static void
test_single_enqueue_dequeue(struct rte_ring *r)
{
	const unsigned iter_shift = 24;
	const unsigned iterations = 1<<iter_shift;
	unsigned i = 0;
	void *burst = NULL;

	const uint64_t sc_start = rte_rdtsc();
	for (i = 0; i < iterations; i++) {
		rte_ring_sp_enqueue(r, burst);
		rte_ring_sc_dequeue(r, &burst);
	}
	const uint64_t sc_end = rte_rdtsc();

	const uint64_t mc_start = rte_rdtsc();
	for (i = 0; i < iterations; i++) {
		rte_ring_mp_enqueue(r, burst);
		rte_ring_mc_dequeue(r, &burst);
	}
	const uint64_t mc_end = rte_rdtsc();

	printf("SP/SC single enq/dequeue: %"PRIu64"\n",
			(sc_end-sc_start) >> iter_shift);
	printf("MP/MC single enq/dequeue: %"PRIu64"\n",
			(mc_end-mc_start) >> iter_shift);
}

/*
 * Test that does both enqueue and dequeue on a core using the burst() API calls
 * instead of the bulk() calls used in other tests. Results should be the same
 * as for the bulk function called on a single lcore.
 */
static void
test_burst_enqueue_dequeue(struct rte_ring *r)
{
	const unsigned iter_shift = 23;
	const unsigned iterations = 1<<iter_shift;
	unsigned sz, i = 0;
	void *burst[MAX_BURST] = {0};

	for (sz = 0; sz < sizeof(bulk_sizes)/sizeof(bulk_sizes[0]); sz++) {
		const uint64_t sc_start = rte_rdtsc();
		for (i = 0; i < iterations; i++) {
			rte_ring_sp_enqueue_burst(r, burst, bulk_sizes[sz]);
			rte_ring_sc_dequeue_burst(r, burst, bulk_sizes[sz]);
		}
		const uint64_t sc_end = rte_rdtsc();

		const uint64_t mc_start = rte_rdtsc();
		for (i = 0; i < iterations; i++) {
			rte_ring_mp_enqueue_burst(r, burst, bulk_sizes[sz]);
			rte_ring_mc_dequeue_burst(r, burst, bulk_sizes[sz]);
		}
		const uint64_t mc_end = rte_rdtsc();

		uint64_t mc_avg = ((mc_end-mc_start) >> iter_shift) / bulk_sizes[sz];
		uint64_t sc_avg = ((sc_end-sc_start) >> iter_shift) / bulk_sizes[sz];

		printf("SP/SC burst enq/dequeue (size: %u): %"PRIu64"\n", bulk_sizes[sz],
				sc_avg);
		printf("MP/MC burst enq/dequeue (size: %u): %"PRIu64"\n", bulk_sizes[sz],
				mc_avg);
	}
}

/* Times enqueue and dequeue on a single lcore */
static void
test_bulk_enqueue_dequeue(struct rte_ring *r)
{
	const unsigned iter_shift = 23;
	const unsigned iterations = 1<<iter_shift;
	unsigned sz, i = 0;
	void *burst[MAX_BURST] = {0};

	for (sz = 0; sz < sizeof(bulk_sizes)/sizeof(bulk_sizes[0]); sz++) {
		const uint64_t sc_start = rte_rdtsc();
		for (i = 0; i < iterations; i++) {
			rte_ring_sp_enqueue_bulk(r, burst, bulk_sizes[sz]);
			rte_ring_sc_dequeue_bulk(r, burst, bulk_sizes[sz]);
		}
		const uint64_t sc_end = rte_rdtsc();

		const uint64_t mc_start = rte_rdtsc();
		for (i = 0; i < iterations; i++) {
			rte_ring_mp_enqueue_bulk(r, burst, bulk_sizes[sz]);
			rte_ring_mc_dequeue_bulk(r, burst, bulk_sizes[sz]);
		}
		const uint64_t mc_end = rte_rdtsc();

		double sc_avg = ((double)(sc_end-sc_start) /
				(iterations * bulk_sizes[sz]));
		double mc_avg = ((double)(mc_end-mc_start) /
				(iterations * bulk_sizes[sz]));

		printf("SP/SC bulk enq/dequeue (size: %u): %.2F\n", bulk_sizes[sz],
				sc_avg);
		printf("MP/MC bulk enq/dequeue (size: %u): %.2F\n", bulk_sizes[sz],
				mc_avg);
	}
}

static int
test_ring_perf(void)
{
	struct lcore_pair cores;
	struct rte_ring *r = NULL;

	r = rte_ring_create(RING_NAME, RING_SIZE, rte_socket_id(), 0);
	if (r == NULL)
		return -1;

	printf("### Testing single element and burst enq/deq ###\n");
	test_single_enqueue_dequeue(r);
	test_burst_enqueue_dequeue(r);

	printf("\n### Testing empty dequeue ###\n");
	test_empty_dequeue(r);

	printf("\n### Testing using a single lcore ###\n");
	test_bulk_enqueue_dequeue(r);

	if (get_two_hyperthreads(&cores) == 0) {
		printf("\n### Testing using two hyperthreads ###\n");
		run_on_core_pair(&cores, r, enqueue_bulk, dequeue_bulk);
	}
	if (get_two_cores(&cores) == 0) {
		printf("\n### Testing using two physical cores ###\n");
		run_on_core_pair(&cores, r, enqueue_bulk, dequeue_bulk);
	}
	if (get_two_sockets(&cores) == 0) {
		printf("\n### Testing using two NUMA nodes ###\n");
		run_on_core_pair(&cores, r, enqueue_bulk, dequeue_bulk);
	}
	rte_ring_free(r);
	return 0;
}

REGISTER_TEST_COMMAND(ring_perf_autotest, test_ring_perf);