ARG_PERF_MODE,
ARG_NUM_OF_ITERATIONS,
ARG_NUM_OF_QPS,
+ ARG_NUM_OF_LCORES,
+ ARG_NUM_OF_MBUF_SEGS,
};
struct job_ctx {
struct rte_regex_ops **ops;
struct job_ctx *jobs_ctx;
char *buf;
+ uint64_t start;
+ uint64_t cycles;
+};
+
+struct qps_per_lcore {
+ unsigned int lcore_id;
+ int socket;
+ uint16_t qp_id_base;
+ uint16_t nb_qps;
+};
+
+struct regex_conf {
+ uint32_t nb_jobs;
+ bool perf_mode;
+ uint32_t nb_iterations;
+ char *data_file;
+ uint8_t nb_max_matches;
+ uint32_t nb_qps;
+ uint16_t qp_id_base;
+ char *data_buf;
+ long data_len;
+ long job_len;
+ uint32_t nb_segs;
};
static void
" --nb_jobs: number of jobs to use\n"
" --perf N: only outputs the performance data\n"
" --nb_iter N: number of iteration to run\n"
- " --nb_qps N: number of queues to use\n",
+ " --nb_qps N: number of queues to use\n"
+ " --nb_lcores N: number of lcores to use\n"
+ " --nb_segs N: number of mbuf segments\n",
prog_name);
}
static void
args_parse(int argc, char **argv, char *rules_file, char *data_file,
uint32_t *nb_jobs, bool *perf_mode, uint32_t *nb_iterations,
- uint32_t *nb_qps)
+ uint32_t *nb_qps, uint32_t *nb_lcores, uint32_t *nb_segs)
{
char **argvopt;
int opt;
{ "nb_iter", 1, 0, ARG_NUM_OF_ITERATIONS},
/* Number of QPs. */
{ "nb_qps", 1, 0, ARG_NUM_OF_QPS},
+ /* Number of lcores. */
+ { "nb_lcores", 1, 0, ARG_NUM_OF_LCORES},
+ /* Number of mbuf segments. */
+ { "nb_segs", 1, 0, ARG_NUM_OF_MBUF_SEGS},
/* End of options */
{ 0, 0, 0, 0 }
};
case ARG_NUM_OF_QPS:
*nb_qps = atoi(optarg);
break;
+ case ARG_NUM_OF_LCORES:
+ *nb_lcores = atoi(optarg);
+ break;
+ case ARG_NUM_OF_MBUF_SEGS:
+ *nb_segs = atoi(optarg);
+ break;
case ARG_HELP:
- usage("RegEx test app");
+ usage(argv[0]);
break;
default:
- fprintf(stderr, "Invalid option: %s\n", argv[optind]);
- usage("RegEx test app");
- rte_exit(EXIT_FAILURE, "Invalid option\n");
+ usage(argv[0]);
+ rte_exit(EXIT_FAILURE, "Invalid option: %s\n", argv[optind]);
break;
}
}
{
}
+static inline struct rte_mbuf *
+regex_create_segmented_mbuf(struct rte_mempool *mbuf_pool, int pkt_len,
+ int nb_segs, void *buf) {
+
+ struct rte_mbuf *m = NULL, *mbuf = NULL;
+ uint8_t *dst;
+ char *src = buf;
+ int data_len = 0;
+ int i, size;
+ int t_len;
+
+ if (pkt_len < 1) {
+ printf("Packet size must be 1 or more (is %d)\n", pkt_len);
+ return NULL;
+ }
+
+ if (nb_segs < 1) {
+ printf("Number of segments must be 1 or more (is %d)\n",
+ nb_segs);
+ return NULL;
+ }
+
+ t_len = pkt_len >= nb_segs ? (pkt_len / nb_segs +
+ !!(pkt_len % nb_segs)) : 1;
+ size = pkt_len;
+
+ /* Create chained mbuf_src and fill it with buf data */
+ for (i = 0; size > 0; i++) {
+
+ m = rte_pktmbuf_alloc(mbuf_pool);
+ if (i == 0)
+ mbuf = m;
+
+ if (m == NULL) {
+ printf("Cannot create segment for source mbuf");
+ goto fail;
+ }
+
+ data_len = size > t_len ? t_len : size;
+ memset(rte_pktmbuf_mtod(m, uint8_t *), 0,
+ rte_pktmbuf_tailroom(m));
+ memcpy(rte_pktmbuf_mtod(m, uint8_t *), src, data_len);
+ dst = (uint8_t *)rte_pktmbuf_append(m, data_len);
+ if (dst == NULL) {
+ printf("Cannot append %d bytes to the mbuf\n",
+ data_len);
+ goto fail;
+ }
+
+ if (mbuf != m)
+ rte_pktmbuf_chain(mbuf, m);
+ src += data_len;
+ size -= data_len;
+
+ }
+ return mbuf;
+
+fail:
+ if (mbuf)
+ rte_pktmbuf_free(mbuf);
+ return NULL;
+}
+
static int
-run_regex(uint32_t nb_jobs,
- bool perf_mode, uint32_t nb_iterations,
- uint8_t nb_max_matches, uint32_t nb_qps,
- char *data_buf, long data_len, long job_len)
+run_regex(void *args)
{
+ struct regex_conf *rgxc = args;
+ uint32_t nb_jobs = rgxc->nb_jobs;
+ uint32_t nb_segs = rgxc->nb_segs;
+ uint32_t nb_iterations = rgxc->nb_iterations;
+ uint8_t nb_max_matches = rgxc->nb_max_matches;
+ uint32_t nb_qps = rgxc->nb_qps;
+ uint16_t qp_id_base = rgxc->qp_id_base;
+ char *data_buf = rgxc->data_buf;
+ long data_len = rgxc->data_len;
+ long job_len = rgxc->job_len;
+
char *buf = NULL;
uint32_t actual_jobs = 0;
uint32_t i;
unsigned long d_ind = 0;
struct rte_mbuf_ext_shared_info shinfo;
int res = 0;
- time_t start;
- time_t end;
- double time;
+ long double time;
struct rte_mempool *mbuf_mp;
struct qp_params *qp;
struct qp_params *qps = NULL;
bool update;
uint16_t qps_used = 0;
+ char mbuf_pool[16];
shinfo.free_cb = extbuf_free_cb;
- mbuf_mp = rte_pktmbuf_pool_create("mbuf_pool", nb_jobs * nb_qps, 0,
- 0, MBUF_SIZE, rte_socket_id());
+ snprintf(mbuf_pool,
+ sizeof(mbuf_pool),
+ "mbuf_pool_%2u", qp_id_base);
+ mbuf_mp = rte_pktmbuf_pool_create(mbuf_pool,
+ rte_align32pow2(nb_jobs * nb_qps * nb_segs),
+ 0, 0, (nb_segs == 1) ? MBUF_SIZE :
+ (rte_align32pow2(job_len) / nb_segs +
+ RTE_PKTMBUF_HEADROOM),
+ rte_socket_id());
if (mbuf_mp == NULL) {
printf("Error, can't create memory pool\n");
return -ENOMEM;
goto end;
}
+ if (clone_buf(data_buf, &buf, data_len)) {
+ printf("Error, can't clone buf.\n");
+ res = -EXIT_FAILURE;
+ goto end;
+ }
+
+ /* Assign each mbuf with the data to handle. */
+ actual_jobs = 0;
+ pos = 0;
/* Allocate the jobs and assign each job with an mbuf. */
- for (i = 0; i < nb_jobs; i++) {
+ for (i = 0; (pos < data_len) && (i < nb_jobs) ; i++) {
+ long act_job_len = RTE_MIN(job_len, data_len - pos);
+
ops[i] = rte_malloc(NULL, sizeof(*ops[0]) +
nb_max_matches *
sizeof(struct rte_regexdev_match), 0);
res = -ENOMEM;
goto end;
}
- ops[i]->mbuf = rte_pktmbuf_alloc(mbuf_mp);
+ if (nb_segs > 1) {
+ ops[i]->mbuf = regex_create_segmented_mbuf
+ (mbuf_mp, act_job_len,
+ nb_segs, &buf[pos]);
+ } else {
+ ops[i]->mbuf = rte_pktmbuf_alloc(mbuf_mp);
+ if (ops[i]->mbuf) {
+ rte_pktmbuf_attach_extbuf(ops[i]->mbuf,
+ &buf[pos], 0, act_job_len, &shinfo);
+ ops[i]->mbuf->data_len = job_len;
+ ops[i]->mbuf->pkt_len = act_job_len;
+ }
+ }
if (!ops[i]->mbuf) {
- printf("Error, can't attach mbuf.\n");
+ printf("Error, can't add mbuf.\n");
res = -ENOMEM;
goto end;
}
- }
-
- if (clone_buf(data_buf, &buf, data_len)) {
- printf("Error, can't clone buf.\n");
- res = -EXIT_FAILURE;
- goto end;
- }
- /* Assign each mbuf with the data to handle. */
- actual_jobs = 0;
- pos = 0;
- for (i = 0; (pos < data_len) && (i < nb_jobs) ; i++) {
- long act_job_len = RTE_MIN(job_len, data_len - pos);
- rte_pktmbuf_attach_extbuf(ops[i]->mbuf, &buf[pos], 0,
- act_job_len, &shinfo);
jobs_ctx[i].mbuf = ops[i]->mbuf;
- ops[i]->mbuf->data_len = job_len;
- ops[i]->mbuf->pkt_len = act_job_len;
ops[i]->user_id = i;
ops[i]->group_id0 = 1;
pos += act_job_len;
qp->buf = buf;
qp->total_matches = 0;
+ qp->start = 0;
+ qp->cycles = 0;
}
- start = clock();
for (i = 0; i < nb_iterations; i++) {
for (qp_id = 0; qp_id < nb_qps; qp_id++) {
qp = &qps[qp_id];
for (qp_id = 0; qp_id < nb_qps; qp_id++) {
qp = &qps[qp_id];
if (qp->total_dequeue < actual_jobs) {
+ qp->start = rte_rdtsc_precise();
struct rte_regex_ops **
cur_ops_to_enqueue = qp->ops +
qp->total_enqueue;
qp->total_enqueue +=
rte_regexdev_enqueue_burst
(dev_id,
- qp_id,
+ qp_id_base + qp_id,
cur_ops_to_enqueue,
actual_jobs -
qp->total_enqueue);
qp->total_dequeue +=
rte_regexdev_dequeue_burst
(dev_id,
- qp_id,
+ qp_id_base + qp_id,
cur_ops_to_dequeue,
qp->total_enqueue -
qp->total_dequeue);
+ qp->cycles +=
+ (rte_rdtsc_precise() - qp->start);
update = true;
}
}
} while (update);
}
- end = clock();
- time = ((double)end - start) / CLOCKS_PER_SEC;
- printf("Job len = %ld Bytes\n", job_len);
- printf("Time = %lf sec\n", time);
- printf("Perf = %lf Gbps\n",
- (((double)actual_jobs * job_len * nb_iterations * 8) / time) /
- 1000000000.0);
-
- if (perf_mode)
+ for (qp_id = 0; qp_id < nb_qps; qp_id++) {
+ qp = &qps[qp_id];
+ time = (long double)qp->cycles / rte_get_timer_hz();
+ printf("Core=%u QP=%u Job=%ld Bytes Time=%Lf sec Perf=%Lf "
+ "Gbps\n", rte_lcore_id(), qp_id + qp_id_base,
+ job_len, time,
+ (((double)actual_jobs * job_len * nb_iterations * 8)
+ / time) / 1000000000.0);
+ }
+
+ if (rgxc->perf_mode)
goto end;
for (qp_id = 0; qp_id < nb_qps; qp_id++) {
- printf("\n############ QP id=%u ############\n", qp_id);
+ printf("\n############ Core=%u QP=%u ############\n",
+ rte_lcore_id(), qp_id + qp_id_base);
qp = &qps[qp_id];
/* Log results per job. */
for (d_ind = 0; d_ind < qp->total_dequeue; d_ind++) {
return res;
}
+static int
+distribute_qps_to_lcores(uint32_t nb_cores, uint32_t nb_qps,
+ struct qps_per_lcore **qpl)
+{
+ int socket;
+ unsigned lcore_id;
+ uint32_t i;
+ uint16_t min_qp_id;
+ uint16_t max_qp_id;
+ struct qps_per_lcore *qps_per_lcore;
+ uint32_t detected_lcores;
+
+ if (nb_qps < nb_cores) {
+ nb_cores = nb_qps;
+ printf("Reducing number of cores to number of QPs (%u)\n",
+ nb_cores);
+ }
+ /* Allocate qps_per_lcore array */
+ qps_per_lcore =
+ rte_malloc(NULL, sizeof(*qps_per_lcore) * nb_cores, 0);
+ if (!qps_per_lcore)
+ rte_exit(EXIT_FAILURE, "Failed to create qps_per_lcore array\n");
+ *qpl = qps_per_lcore;
+ detected_lcores = 0;
+ min_qp_id = 0;
+
+ RTE_LCORE_FOREACH_WORKER(lcore_id) {
+ if (detected_lcores >= nb_cores)
+ break;
+ qps_per_lcore[detected_lcores].lcore_id = lcore_id;
+ socket = rte_lcore_to_socket_id(lcore_id);
+ if (socket == SOCKET_ID_ANY)
+ socket = 0;
+ qps_per_lcore[detected_lcores].socket = socket;
+ qps_per_lcore[detected_lcores].qp_id_base = min_qp_id;
+ max_qp_id = min_qp_id + nb_qps / nb_cores - 1;
+ if (nb_qps % nb_cores > detected_lcores)
+ max_qp_id++;
+ qps_per_lcore[detected_lcores].nb_qps = max_qp_id -
+ min_qp_id + 1;
+ min_qp_id = max_qp_id + 1;
+ detected_lcores++;
+ }
+ if (detected_lcores != nb_cores)
+ return -1;
+
+ for (i = 0; i < detected_lcores; i++) {
+ printf("===> Core %d: allocated queues: ",
+ qps_per_lcore[i].lcore_id);
+ min_qp_id = qps_per_lcore[i].qp_id_base;
+ max_qp_id =
+ qps_per_lcore[i].qp_id_base + qps_per_lcore[i].nb_qps;
+ while (min_qp_id < max_qp_id) {
+ printf("%u ", min_qp_id);
+ min_qp_id++;
+ }
+ printf("\n");
+ }
+ return 0;
+}
+
int
main(int argc, char **argv)
{
char *data_buf;
long data_len;
long job_len;
+ uint32_t nb_lcores = 1, nb_segs = 1;
+ struct regex_conf *rgxc;
+ uint32_t i;
+ struct qps_per_lcore *qps_per_lcore;
/* Init EAL. */
ret = rte_eal_init(argc, argv);
argv += ret;
if (argc > 1)
args_parse(argc, argv, rules_file, data_file, &nb_jobs,
- &perf_mode, &nb_iterations, &nb_qps);
+ &perf_mode, &nb_iterations, &nb_qps,
+ &nb_lcores, &nb_segs);
if (nb_qps == 0)
rte_exit(EXIT_FAILURE, "Number of QPs must be greater than 0\n");
+ if (nb_lcores == 0)
+ rte_exit(EXIT_FAILURE, "Number of lcores must be greater than 0\n");
+ if (distribute_qps_to_lcores(nb_lcores, nb_qps, &qps_per_lcore) < 0)
+ rte_exit(EXIT_FAILURE, "Failed to distribute queues to lcores!\n");
ret = init_port(&nb_max_payload, rules_file,
&nb_max_matches, nb_qps);
if (ret < 0)
if (job_len > nb_max_payload)
rte_exit(EXIT_FAILURE, "Error, not enough jobs to cover input.\n");
- ret = run_regex(nb_jobs, perf_mode,
- nb_iterations, nb_max_matches, nb_qps,
- data_buf, data_len, job_len);
- if (ret < 0) {
- rte_exit(EXIT_FAILURE, "RegEx function failed\n");
+ rgxc = rte_malloc(NULL, sizeof(*rgxc) * nb_lcores, 0);
+ if (!rgxc)
+ rte_exit(EXIT_FAILURE, "Failed to create Regex Conf\n");
+ for (i = 0; i < nb_lcores; i++) {
+ rgxc[i] = (struct regex_conf){
+ .nb_jobs = nb_jobs,
+ .nb_segs = nb_segs,
+ .perf_mode = perf_mode,
+ .nb_iterations = nb_iterations,
+ .nb_max_matches = nb_max_matches,
+ .nb_qps = qps_per_lcore[i].nb_qps,
+ .qp_id_base = qps_per_lcore[i].qp_id_base,
+ .data_buf = data_buf,
+ .data_len = data_len,
+ .job_len = job_len,
+ };
+ rte_eal_remote_launch(run_regex, &rgxc[i],
+ qps_per_lcore[i].lcore_id);
}
+ rte_eal_mp_wait_lcore();
rte_free(data_buf);
+ rte_free(rgxc);
+ rte_free(qps_per_lcore);
return EXIT_SUCCESS;
}