aboutsummaryrefslogtreecommitdiffstats
path: root/examples/eventdev_pipeline/main.c
blob: 92e08bc0c81b1a7bca42c6a5f8ad2f5b8761114e (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
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2016-2017 Intel Corporation
 */

#include <getopt.h>
#include <stdint.h>
#include <stdio.h>
#include <signal.h>
#include <sched.h>

#include "pipeline_common.h"

struct config_data cdata = {
	.num_packets = (1L << 25), /* do ~32M packets */
	.num_fids = 512,
	.queue_type = RTE_SCHED_TYPE_ATOMIC,
	.next_qid = {-1},
	.qid = {-1},
	.num_stages = 1,
	.worker_cq_depth = 16
};

static bool
core_in_use(unsigned int lcore_id) {
	return (fdata->rx_core[lcore_id] || fdata->sched_core[lcore_id] ||
		fdata->tx_core[lcore_id] || fdata->worker_core[lcore_id]);
}

/*
 * Parse the coremask given as argument (hexadecimal string) and fill
 * the global configuration (core role and core count) with the parsed
 * value.
 */
static int xdigit2val(unsigned char c)
{
	int val;

	if (isdigit(c))
		val = c - '0';
	else if (isupper(c))
		val = c - 'A' + 10;
	else
		val = c - 'a' + 10;
	return val;
}

static uint64_t
parse_coremask(const char *coremask)
{
	int i, j, idx = 0;
	unsigned int count = 0;
	char c;
	int val;
	uint64_t mask = 0;
	const int32_t BITS_HEX = 4;

	if (coremask == NULL)
		return -1;
	/* Remove all blank characters ahead and after .
	 * Remove 0x/0X if exists.
	 */
	while (isblank(*coremask))
		coremask++;
	if (coremask[0] == '0' && ((coremask[1] == 'x')
		|| (coremask[1] == 'X')))
		coremask += 2;
	i = strlen(coremask);
	while ((i > 0) && isblank(coremask[i - 1]))
		i--;
	if (i == 0)
		return -1;

	for (i = i - 1; i >= 0 && idx < MAX_NUM_CORE; i--) {
		c = coremask[i];
		if (isxdigit(c) == 0) {
			/* invalid characters */
			return -1;
		}
		val = xdigit2val(c);
		for (j = 0; j < BITS_HEX && idx < MAX_NUM_CORE; j++, idx++) {
			if ((1 << j) & val) {
				mask |= (1UL << idx);
				count++;
			}
		}
	}
	for (; i >= 0; i--)
		if (coremask[i] != '0')
			return -1;
	if (count == 0)
		return -1;
	return mask;
}

static struct option long_options[] = {
	{"workers", required_argument, 0, 'w'},
	{"packets", required_argument, 0, 'n'},
	{"atomic-flows", required_argument, 0, 'f'},
	{"num_stages", required_argument, 0, 's'},
	{"rx-mask", required_argument, 0, 'r'},
	{"tx-mask", required_argument, 0, 't'},
	{"sched-mask", required_argument, 0, 'e'},
	{"cq-depth", required_argument, 0, 'c'},
	{"work-cycles", required_argument, 0, 'W'},
	{"mempool-size", required_argument, 0, 'm'},
	{"queue-priority", no_argument, 0, 'P'},
	{"parallel", no_argument, 0, 'p'},
	{"ordered", no_argument, 0, 'o'},
	{"quiet", no_argument, 0, 'q'},
	{"use-atq", no_argument, 0, 'a'},
	{"dump", no_argument, 0, 'D'},
	{0, 0, 0, 0}
};

static void
usage(void)
{
	const char *usage_str =
		"  Usage: eventdev_demo [options]\n"
		"  Options:\n"
		"  -n, --packets=N              Send N packets (default ~32M), 0 implies no limit\n"
		"  -f, --atomic-flows=N         Use N random flows from 1 to N (default 16)\n"
		"  -s, --num_stages=N           Use N atomic stages (default 1)\n"
		"  -r, --rx-mask=core mask      Run NIC rx on CPUs in core mask\n"
		"  -w, --worker-mask=core mask  Run worker on CPUs in core mask\n"
		"  -t, --tx-mask=core mask      Run NIC tx on CPUs in core mask\n"
		"  -e  --sched-mask=core mask   Run scheduler on CPUs in core mask\n"
		"  -c  --cq-depth=N             Worker CQ depth (default 16)\n"
		"  -W  --work-cycles=N          Worker cycles (default 0)\n"
		"  -P  --queue-priority         Enable scheduler queue prioritization\n"
		"  -o, --ordered                Use ordered scheduling\n"
		"  -p, --parallel               Use parallel scheduling\n"
		"  -q, --quiet                  Minimize printed output\n"
		"  -a, --use-atq                Use all type queues\n"
		"  -m, --mempool-size=N         Dictate the mempool size\n"
		"  -D, --dump                   Print detailed statistics before exit"
		"\n";
	fprintf(stderr, "%s", usage_str);
	exit(1);
}

static void
parse_app_args(int argc, char **argv)
{
	/* Parse cli options*/
	int option_index;
	int c;
	opterr = 0;
	uint64_t rx_lcore_mask = 0;
	uint64_t tx_lcore_mask = 0;
	uint64_t sched_lcore_mask = 0;
	uint64_t worker_lcore_mask = 0;
	int i;

	for (;;) {
		c = getopt_long(argc, argv, "r:t:e:c:w:n:f:s:m:paoPqDW:",
				long_options, &option_index);
		if (c == -1)
			break;

		int popcnt = 0;
		switch (c) {
		case 'n':
			cdata.num_packets = (int64_t)atol(optarg);
			if (cdata.num_packets == 0)
				cdata.num_packets = INT64_MAX;
			break;
		case 'f':
			cdata.num_fids = (unsigned int)atoi(optarg);
			break;
		case 's':
			cdata.num_stages = (unsigned int)atoi(optarg);
			break;
		case 'c':
			cdata.worker_cq_depth = (unsigned int)atoi(optarg);
			break;
		case 'W':
			cdata.worker_cycles = (unsigned int)atoi(optarg);
			break;
		case 'P':
			cdata.enable_queue_priorities = 1;
			break;
		case 'o':
			cdata.queue_type = RTE_SCHED_TYPE_ORDERED;
			break;
		case 'p':
			cdata.queue_type = RTE_SCHED_TYPE_PARALLEL;
			break;
		case 'a':
			cdata.all_type_queues = 1;
			break;
		case 'q':
			cdata.quiet = 1;
			break;
		case 'D':
			cdata.dump_dev = 1;
			break;
		case 'w':
			worker_lcore_mask = parse_coremask(optarg);
			break;
		case 'r':
			rx_lcore_mask = parse_coremask(optarg);
			popcnt = __builtin_popcountll(rx_lcore_mask);
			fdata->rx_single = (popcnt == 1);
			break;
		case 't':
			tx_lcore_mask = parse_coremask(optarg);
			popcnt = __builtin_popcountll(tx_lcore_mask);
			fdata->tx_single = (popcnt == 1);
			break;
		case 'e':
			sched_lcore_mask = parse_coremask(optarg);
			popcnt = __builtin_popcountll(sched_lcore_mask);
			fdata->sched_single = (popcnt == 1);
			break;
		case 'm':
			cdata.num_mbuf = (uint64_t)atol(optarg);
			break;
		default:
			usage();
		}
	}

	cdata.worker_lcore_mask = worker_lcore_mask;
	cdata.sched_lcore_mask = sched_lcore_mask;
	cdata.rx_lcore_mask = rx_lcore_mask;
	cdata.tx_lcore_mask = tx_lcore_mask;

	if (cdata.num_stages == 0 || cdata.num_stages > MAX_NUM_STAGES)
		usage();

	for (i = 0; i < MAX_NUM_CORE; i++) {
		fdata->rx_core[i] = !!(rx_lcore_mask & (1UL << i));
		fdata->tx_core[i] = !!(tx_lcore_mask & (1UL << i));
		fdata->sched_core[i] = !!(sched_lcore_mask & (1UL << i));
		fdata->worker_core[i] = !!(worker_lcore_mask & (1UL << i));

		if (fdata->worker_core[i])
			cdata.num_workers++;
		if (core_in_use(i))
			cdata.active_cores++;
	}
}

/*
 * Initializes a given port using global settings and with the RX buffers
 * coming from the mbuf_pool passed as a parameter.
 */
static inline int
port_init(uint8_t port, struct rte_mempool *mbuf_pool)
{
	struct rte_eth_rxconf rx_conf;
	static const struct rte_eth_conf port_conf_default = {
		.rxmode = {
			.mq_mode = ETH_MQ_RX_RSS,
			.max_rx_pkt_len = ETHER_MAX_LEN,
		},
		.rx_adv_conf = {
			.rss_conf = {
				.rss_hf = ETH_RSS_IP |
					  ETH_RSS_TCP |
					  ETH_RSS_UDP,
			}
		}
	};
	const uint16_t rx_rings = 1, tx_rings = 1;
	const uint16_t rx_ring_size = 512, tx_ring_size = 512;
	struct rte_eth_conf port_conf = port_conf_default;
	int retval;
	uint16_t q;
	struct rte_eth_dev_info dev_info;
	struct rte_eth_txconf txconf;

	if (!rte_eth_dev_is_valid_port(port))
		return -1;

	rte_eth_dev_info_get(port, &dev_info);
	if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
		port_conf.txmode.offloads |=
			DEV_TX_OFFLOAD_MBUF_FAST_FREE;
	rx_conf = dev_info.default_rxconf;
	rx_conf.offloads = port_conf.rxmode.offloads;

	port_conf.rx_adv_conf.rss_conf.rss_hf &=
		dev_info.flow_type_rss_offloads;
	if (port_conf.rx_adv_conf.rss_conf.rss_hf !=
			port_conf_default.rx_adv_conf.rss_conf.rss_hf) {
		printf("Port %u modified RSS hash function based on hardware support,"
			"requested:%#"PRIx64" configured:%#"PRIx64"\n",
			port,
			port_conf_default.rx_adv_conf.rss_conf.rss_hf,
			port_conf.rx_adv_conf.rss_conf.rss_hf);
	}

	/* Configure the Ethernet device. */
	retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
	if (retval != 0)
		return retval;

	/* Allocate and set up 1 RX queue per Ethernet port. */
	for (q = 0; q < rx_rings; q++) {
		retval = rte_eth_rx_queue_setup(port, q, rx_ring_size,
				rte_eth_dev_socket_id(port), &rx_conf,
				mbuf_pool);
		if (retval < 0)
			return retval;
	}

	txconf = dev_info.default_txconf;
	txconf.offloads = port_conf_default.txmode.offloads;
	/* Allocate and set up 1 TX queue per Ethernet port. */
	for (q = 0; q < tx_rings; q++) {
		retval = rte_eth_tx_queue_setup(port, q, tx_ring_size,
				rte_eth_dev_socket_id(port), &txconf);
		if (retval < 0)
			return retval;
	}

	/* Start the Ethernet port. */
	retval = rte_eth_dev_start(port);
	if (retval < 0)
		return retval;

	/* Display the port MAC address. */
	struct ether_addr addr;
	rte_eth_macaddr_get(port, &addr);
	printf("Port %u MAC: %02" PRIx8 " %02" PRIx8 " %02" PRIx8
			   " %02" PRIx8 " %02" PRIx8 " %02" PRIx8 "\n",
			(unsigned int)port,
			addr.addr_bytes[0], addr.addr_bytes[1],
			addr.addr_bytes[2], addr.addr_bytes[3],
			addr.addr_bytes[4], addr.addr_bytes[5]);

	/* Enable RX in promiscuous mode for the Ethernet device. */
	rte_eth_promiscuous_enable(port);

	return 0;
}

static int
init_ports(uint16_t num_ports)
{
	uint16_t portid;

	if (!cdata.num_mbuf)
		cdata.num_mbuf = 16384 * num_ports;

	struct rte_mempool *mp = rte_pktmbuf_pool_create("packet_pool",
			/* mbufs */ cdata.num_mbuf,
			/* cache_size */ 512,
			/* priv_size*/ 0,
			/* data_room_size */ RTE_MBUF_DEFAULT_BUF_SIZE,
			rte_socket_id());

	RTE_ETH_FOREACH_DEV(portid)
		if (port_init(portid, mp) != 0)
			rte_exit(EXIT_FAILURE, "Cannot init port %"PRIu16 "\n",
					portid);

	return 0;
}

static void
do_capability_setup(uint8_t eventdev_id)
{
	int ret;
	uint16_t i;
	uint8_t generic_pipeline = 0;
	uint8_t burst = 0;

	RTE_ETH_FOREACH_DEV(i) {
		uint32_t caps = 0;

		ret = rte_event_eth_tx_adapter_caps_get(eventdev_id, i, &caps);
		if (ret)
			rte_exit(EXIT_FAILURE,
				"Invalid capability for Tx adptr port %d\n", i);
		generic_pipeline |= !(caps &
				RTE_EVENT_ETH_TX_ADAPTER_CAP_INTERNAL_PORT);
	}

	struct rte_event_dev_info eventdev_info;
	memset(&eventdev_info, 0, sizeof(struct rte_event_dev_info));

	rte_event_dev_info_get(eventdev_id, &eventdev_info);
	burst = eventdev_info.event_dev_cap & RTE_EVENT_DEV_CAP_BURST_MODE ? 1 :
		0;

	if (generic_pipeline)
		set_worker_generic_setup_data(&fdata->cap, burst);
	else
		set_worker_tx_enq_setup_data(&fdata->cap, burst);
}

static void
signal_handler(int signum)
{
	static uint8_t once;
	uint16_t portid;

	if (fdata->done)
		rte_exit(1, "Exiting on signal %d\n", signum);
	if ((signum == SIGINT || signum == SIGTERM) && !once) {
		printf("\n\nSignal %d received, preparing to exit...\n",
				signum);
		if (cdata.dump_dev)
			rte_event_dev_dump(0, stdout);
		once = 1;
		fdata->done = 1;
		rte_smp_wmb();

		RTE_ETH_FOREACH_DEV(portid) {
			rte_event_eth_rx_adapter_stop(portid);
			rte_event_eth_tx_adapter_stop(portid);
			rte_eth_dev_stop(portid);
		}

		rte_eal_mp_wait_lcore();

		RTE_ETH_FOREACH_DEV(portid) {
			rte_eth_dev_close(portid);
		}

		rte_event_dev_close(0);
	}
	if (signum == SIGTSTP)
		rte_event_dev_dump(0, stdout);
}

static inline uint64_t
port_stat(int dev_id, int32_t p)
{
	char statname[64];
	snprintf(statname, sizeof(statname), "port_%u_rx", p);
	return rte_event_dev_xstats_by_name_get(dev_id, statname, NULL);
}

int
main(int argc, char **argv)
{
	struct worker_data *worker_data;
	uint16_t num_ports;
	int lcore_id;
	int err;

	signal(SIGINT, signal_handler);
	signal(SIGTERM, signal_handler);
	signal(SIGTSTP, signal_handler);

	err = rte_eal_init(argc, argv);
	if (err < 0)
		rte_panic("Invalid EAL arguments\n");

	argc -= err;
	argv += err;

	fdata = rte_malloc(NULL, sizeof(struct fastpath_data), 0);
	if (fdata == NULL)
		rte_panic("Out of memory\n");

	/* Parse cli options*/
	parse_app_args(argc, argv);

	num_ports = rte_eth_dev_count_avail();
	if (num_ports == 0)
		rte_panic("No ethernet ports found\n");

	const unsigned int cores_needed = cdata.active_cores;

	if (!cdata.quiet) {
		printf("  Config:\n");
		printf("\tports: %u\n", num_ports);
		printf("\tworkers: %u\n", cdata.num_workers);
		printf("\tpackets: %"PRIi64"\n", cdata.num_packets);
		printf("\tQueue-prio: %u\n", cdata.enable_queue_priorities);
		if (cdata.queue_type == RTE_SCHED_TYPE_ORDERED)
			printf("\tqid0 type: ordered\n");
		if (cdata.queue_type == RTE_SCHED_TYPE_ATOMIC)
			printf("\tqid0 type: atomic\n");
		printf("\tCores available: %u\n", rte_lcore_count());
		printf("\tCores used: %u\n", cores_needed);
	}

	if (rte_lcore_count() < cores_needed)
		rte_panic("Too few cores (%d < %d)\n", rte_lcore_count(),
				cores_needed);

	const unsigned int ndevs = rte_event_dev_count();
	if (ndevs == 0)
		rte_panic("No dev_id devs found. Pasl in a --vdev eventdev.\n");
	if (ndevs > 1)
		fprintf(stderr, "Warning: More than one eventdev, using idx 0");


	do_capability_setup(0);
	fdata->cap.check_opt();

	worker_data = rte_calloc(0, cdata.num_workers,
			sizeof(worker_data[0]), 0);
	if (worker_data == NULL)
		rte_panic("rte_calloc failed\n");

	int dev_id = fdata->cap.evdev_setup(worker_data);
	if (dev_id < 0)
		rte_exit(EXIT_FAILURE, "Error setting up eventdev\n");

	init_ports(num_ports);
	fdata->cap.adptr_setup(num_ports);

	int worker_idx = 0;
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (lcore_id >= MAX_NUM_CORE)
			break;

		if (!fdata->rx_core[lcore_id] &&
			!fdata->worker_core[lcore_id] &&
			!fdata->tx_core[lcore_id] &&
			!fdata->sched_core[lcore_id])
			continue;

		if (fdata->rx_core[lcore_id])
			printf(
				"[%s()] lcore %d executing NIC Rx\n",
				__func__, lcore_id);

		if (fdata->tx_core[lcore_id])
			printf(
				"[%s()] lcore %d executing NIC Tx\n",
				__func__, lcore_id);

		if (fdata->sched_core[lcore_id])
			printf("[%s()] lcore %d executing scheduler\n",
					__func__, lcore_id);

		if (fdata->worker_core[lcore_id])
			printf(
				"[%s()] lcore %d executing worker, using eventdev port %u\n",
				__func__, lcore_id,
				worker_data[worker_idx].port_id);

		err = rte_eal_remote_launch(fdata->cap.worker,
				&worker_data[worker_idx], lcore_id);
		if (err) {
			rte_panic("Failed to launch worker on core %d\n",
					lcore_id);
			continue;
		}
		if (fdata->worker_core[lcore_id])
			worker_idx++;
	}

	lcore_id = rte_lcore_id();

	if (core_in_use(lcore_id))
		fdata->cap.worker(&worker_data[worker_idx++]);

	rte_eal_mp_wait_lcore();

	if (!cdata.quiet && (port_stat(dev_id, worker_data[0].port_id) !=
			(uint64_t)-ENOTSUP)) {
		printf("\nPort Workload distribution:\n");
		uint32_t i;
		uint64_t tot_pkts = 0;
		uint64_t pkts_per_wkr[RTE_MAX_LCORE] = {0};
		for (i = 0; i < cdata.num_workers; i++) {
			pkts_per_wkr[i] =
				port_stat(dev_id, worker_data[i].port_id);
			tot_pkts += pkts_per_wkr[i];
		}
		for (i = 0; i < cdata.num_workers; i++) {
			float pc = pkts_per_wkr[i]  * 100 /
				((float)tot_pkts);
			printf("worker %i :\t%.1f %% (%"PRIu64" pkts)\n",
					i, pc, pkts_per_wkr[i]);
		}

	}

	return 0;
}