From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 97742A09FD; Sun, 20 Dec 2020 11:43:26 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 6AE86CBEC; Sun, 20 Dec 2020 11:42:22 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by dpdk.org (Postfix) with ESMTP id 48F0CCBA8 for ; Sun, 20 Dec 2020 11:42:16 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from ophirmu@nvidia.com) with SMTP; 20 Dec 2020 12:42:10 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 0BKAg9pw031499; Sun, 20 Dec 2020 12:42:09 +0200 From: Ophir Munk To: dev@dpdk.org, Ori Kam , Ophir Munk Cc: Thomas Monjalon Date: Sun, 20 Dec 2020 10:41:44 +0000 Message-Id: <20201220104148.13961-3-ophirmu@nvidia.com> X-Mailer: git-send-email 2.8.4 In-Reply-To: <20201220104148.13961-1-ophirmu@nvidia.com> References: <20201216164931.1517-2-ophirmu@nvidia.com> <20201220104148.13961-1-ophirmu@nvidia.com> Subject: [dpdk-dev] [PATCH v2 2/6] app/regex: support multi QPs X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Up to this commit the regex application used one QP which was assigned a number of jobs, each with a different segment of a file to parse. This commit adds support for multiple QPs assignments. All QPs will be assigned the same number of jobs, with the same segments of file to parse. It will enable comparing functionality with different numbers of QPs. All queues are managed on one core with one thread. This commit focuses on changing routines API to support multi QPs, mainly, QP scalar variables are replaced by per-QP struct instance. The enqueue/dequeue operations are interleaved as follows: enqueue(QP #1) enqueue(QP #2) ... enqueue(QP #n) dequeue(QP #1) dequeue(QP #2) ... dequeue(QP #n) A new parameter 'nb_qps' was added to configure the number of QPs: --nb_qps . If not configured, nb_qps is set to 1 by default. Signed-off-by: Ophir Munk --- app/test-regex/main.c | 322 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 204 insertions(+), 118 deletions(-) diff --git a/app/test-regex/main.c b/app/test-regex/main.c index cb2a065..d225267 100644 --- a/app/test-regex/main.c +++ b/app/test-regex/main.c @@ -33,12 +33,22 @@ enum app_args { ARG_NUM_OF_JOBS, ARG_PERF_MODE, ARG_NUM_OF_ITERATIONS, + ARG_NUM_OF_QPS, }; struct job_ctx { struct rte_mbuf *mbuf; }; +struct qp_params { + uint32_t total_enqueue; + uint32_t total_dequeue; + uint32_t total_matches; + struct rte_regex_ops **ops; + struct job_ctx *jobs_ctx; + char *buf; +}; + static void usage(const char *prog_name) { @@ -47,13 +57,15 @@ usage(const char *prog_name) " --data NAME: data file to use\n" " --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_iter N: number of iteration to run\n" + " --nb_qps N: number of queues to use\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_jobs, bool *perf_mode, uint32_t *nb_iterations, + uint32_t *nb_qps) { char **argvopt; int opt; @@ -71,6 +83,8 @@ args_parse(int argc, char **argv, char *rules_file, char *data_file, { "perf", 0, 0, ARG_PERF_MODE}, /* Number of iterations to run with perf test */ { "nb_iter", 1, 0, ARG_NUM_OF_ITERATIONS}, + /* Number of QPs. */ + { "nb_qps", 1, 0, ARG_NUM_OF_QPS}, /* End of options */ { 0, 0, 0, 0 } }; @@ -104,6 +118,9 @@ args_parse(int argc, char **argv, char *rules_file, char *data_file, case ARG_NUM_OF_ITERATIONS: *nb_iterations = atoi(optarg); break; + case ARG_NUM_OF_QPS: + *nb_qps = atoi(optarg); + break; case ARG_HELP: usage("RegEx test app"); break; @@ -163,15 +180,17 @@ read_file(char *file, char **buf) } static int -init_port(uint16_t *nb_max_payload, char *rules_file, uint8_t *nb_max_matches) +init_port(uint16_t *nb_max_payload, char *rules_file, uint8_t *nb_max_matches, + uint32_t nb_qps) { uint16_t id; + uint16_t qp_id; uint16_t num_devs; char *rules = NULL; long rules_len; struct rte_regexdev_info info; struct rte_regexdev_config dev_conf = { - .nb_queue_pairs = 1, + .nb_queue_pairs = nb_qps, .nb_groups = 1, }; struct rte_regexdev_qp_conf qp_conf = { @@ -203,7 +222,8 @@ init_port(uint16_t *nb_max_payload, char *rules_file, uint8_t *nb_max_matches) *nb_max_matches = info.max_matches; *nb_max_payload = info.max_payload_size; if (info.regexdev_capa & RTE_REGEXDEV_SUPP_MATCH_AS_END_F) - dev_conf.dev_cfg_flags |= RTE_REGEXDEV_CFG_MATCH_AS_END_F; + dev_conf.dev_cfg_flags |= + RTE_REGEXDEV_CFG_MATCH_AS_END_F; dev_conf.nb_max_matches = info.max_matches; dev_conf.nb_rules_per_group = info.max_rules_per_group; dev_conf.rule_db_len = rules_len; @@ -214,12 +234,16 @@ init_port(uint16_t *nb_max_payload, char *rules_file, uint8_t *nb_max_matches) goto error; } if (info.regexdev_capa & RTE_REGEXDEV_CAPA_QUEUE_PAIR_OOS_F) - qp_conf.qp_conf_flags |= RTE_REGEX_QUEUE_PAIR_CFG_OOS_F; - res = rte_regexdev_queue_pair_setup(id, 0, &qp_conf); - if (res < 0) { - printf("Error, can't setup queue pair for device %d.\n", - id); - goto error; + qp_conf.qp_conf_flags |= + RTE_REGEX_QUEUE_PAIR_CFG_OOS_F; + for (qp_id = 0; qp_id < nb_qps; qp_id++) { + res = rte_regexdev_queue_pair_setup(id, qp_id, + &qp_conf); + if (res < 0) { + printf("Error, can't setup queue pair %u for " + "device %d.\n", qp_id, id); + goto error; + } } printf(":: initializing device: %d done\n", id); } @@ -239,122 +263,171 @@ extbuf_free_cb(void *addr __rte_unused, void *fcb_opaque __rte_unused) static int run_regex(uint32_t nb_jobs, uint16_t nb_max_payload, bool perf_mode, uint32_t nb_iterations, - char *data_file, uint8_t nb_max_matches) + char *data_file, uint8_t nb_max_matches, uint32_t nb_qps) { char *buf = NULL; - long buf_len; - long job_len; + long buf_len = 0; + long job_len = 0; uint32_t actual_jobs = 0; uint32_t i; - struct rte_regex_ops **ops; + uint16_t qp_id; uint16_t dev_id = 0; - uint16_t qp_id = 0; uint8_t nb_matches; struct rte_regexdev_match *match; - long pos = 0; + long pos; unsigned long d_ind = 0; struct rte_mbuf_ext_shared_info shinfo; - uint32_t total_enqueue = 0; - uint32_t total_dequeue = 0; - uint32_t total_matches = 0; int res = 0; time_t start; time_t end; double time; - struct job_ctx *jobs_ctx; struct rte_mempool *mbuf_mp; + struct qp_params *qp; + struct qp_params *qps = NULL; + bool update; + uint16_t qps_used = 0; shinfo.free_cb = extbuf_free_cb; - - mbuf_mp = rte_pktmbuf_pool_create("mbuf_pool", nb_jobs, 0, + mbuf_mp = rte_pktmbuf_pool_create("mbuf_pool", nb_jobs * nb_qps, 0, 0, MBUF_SIZE, rte_socket_id()); if (mbuf_mp == NULL) { printf("Error, can't create memory pool\n"); return -ENOMEM; } - ops = rte_malloc(NULL, sizeof(*ops) * nb_jobs, 0); - if (!ops) { - printf("Error, can't allocate memory for ops.\n"); - return -ENOMEM; - } - - jobs_ctx = rte_malloc(NULL, sizeof(struct job_ctx)*nb_jobs, 0); - if (!jobs_ctx) { - printf("Error, can't allocate memory for jobs_ctx.\n"); - return -ENOMEM; + qps = rte_malloc(NULL, sizeof(*qps) * nb_qps, 0); + if (!qps) { + printf("Error, can't allocate memory for QPs\n"); + res = -ENOMEM; + goto end; } - /* Allocate the jobs and assign each job with an mbuf. */ - for (i = 0; i < nb_jobs; i++) { - ops[i] = rte_malloc(NULL, sizeof(*ops[0]) + nb_max_matches * - sizeof(struct rte_regexdev_match), 0); - if (!ops[i]) { - printf("Error, can't allocate memory for op.\n"); + for (qp_id = 0; qp_id < nb_qps; qp_id++) { + struct rte_regex_ops **ops; + struct job_ctx *jobs_ctx; + + qps_used++; + qp = &qps[qp_id]; + qp->jobs_ctx = NULL; + qp->buf = NULL; + qp->ops = ops = rte_malloc(NULL, sizeof(*ops) * nb_jobs, 0); + if (!ops) { + printf("Error, can't allocate memory for ops.\n"); res = -ENOMEM; goto end; } - ops[i]->mbuf = rte_pktmbuf_alloc(mbuf_mp); - if (!ops[i]->mbuf) { - printf("Error, can't attach mbuf.\n"); + + qp->jobs_ctx = jobs_ctx = + rte_malloc(NULL, sizeof(*jobs_ctx) * nb_jobs, 0); + if (!jobs_ctx) { + printf("Error, can't allocate memory for jobs_ctx.\n"); res = -ENOMEM; goto end; } - } - buf_len = read_file(data_file, &buf); - if (buf_len <= 0) { - printf("Error, can't read file, or file is empty.\n"); - res = -EXIT_FAILURE; - goto end; - } + /* Allocate the jobs and assign each job with an mbuf. */ + for (i = 0; i < nb_jobs; i++) { + ops[i] = rte_malloc(NULL, sizeof(*ops[0]) + + nb_max_matches * + sizeof(struct rte_regexdev_match), 0); + if (!ops[i]) { + printf("Error, can't allocate " + "memory for op.\n"); + res = -ENOMEM; + goto end; + } + ops[i]->mbuf = rte_pktmbuf_alloc(mbuf_mp); + if (!ops[i]->mbuf) { + printf("Error, can't attach mbuf.\n"); + res = -ENOMEM; + goto end; + } + } - job_len = buf_len / nb_jobs; - if (job_len == 0) { - printf("Error, To many jobs, for the given input.\n"); - res = -EXIT_FAILURE; - goto end; - } + buf_len = read_file(data_file, &buf); + if (buf_len <= 0) { + printf("Error, can't read file, or file is empty.\n"); + res = -EXIT_FAILURE; + goto end; + } - if (job_len > nb_max_payload) { - printf("Error, not enough jobs to cover input.\n"); - res = -EXIT_FAILURE; - goto end; - } + job_len = buf_len / nb_jobs; + if (job_len == 0) { + printf("Error, To many jobs, for the given input.\n"); + res = -EXIT_FAILURE; + goto end; + } + + if (job_len > nb_max_payload) { + printf("Error, not enough jobs to cover input.\n"); + res = -EXIT_FAILURE; + goto end; + } - /* Assign each mbuf with the data to handle. */ - for (i = 0; (pos < buf_len) && (i < nb_jobs) ; i++) { - long act_job_len = RTE_MIN(job_len, buf_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; - actual_jobs++; + /* Assign each mbuf with the data to handle. */ + actual_jobs = 0; + pos = 0; + for (i = 0; (pos < buf_len) && (i < nb_jobs) ; i++) { + long act_job_len = RTE_MIN(job_len, buf_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; + actual_jobs++; + } + + qp->buf = buf; + qp->total_matches = 0; } start = clock(); for (i = 0; i < nb_iterations; i++) { - total_enqueue = 0; - total_dequeue = 0; - while (total_dequeue < actual_jobs) { - struct rte_regex_ops **cur_ops_to_enqueue = ops + - total_enqueue; - struct rte_regex_ops **cur_ops_to_dequeue = ops + - total_dequeue; - - if (actual_jobs - total_enqueue) - total_enqueue += rte_regexdev_enqueue_burst - (dev_id, qp_id, cur_ops_to_enqueue, - actual_jobs - total_enqueue); - - total_dequeue += rte_regexdev_dequeue_burst - (dev_id, qp_id, cur_ops_to_dequeue, - total_enqueue - total_dequeue); + for (qp_id = 0; qp_id < nb_qps; qp_id++) { + qp = &qps[qp_id]; + qp->total_enqueue = 0; + qp->total_dequeue = 0; } + do { + update = false; + for (qp_id = 0; qp_id < nb_qps; qp_id++) { + qp = &qps[qp_id]; + if (qp->total_dequeue < actual_jobs) { + struct rte_regex_ops ** + cur_ops_to_enqueue = qp->ops + + qp->total_enqueue; + + if (actual_jobs - qp->total_enqueue) + qp->total_enqueue += + rte_regexdev_enqueue_burst + (dev_id, + qp_id, + cur_ops_to_enqueue, + actual_jobs - + qp->total_enqueue); + } + } + for (qp_id = 0; qp_id < nb_qps; qp_id++) { + qp = &qps[qp_id]; + if (qp->total_dequeue < actual_jobs) { + struct rte_regex_ops ** + cur_ops_to_dequeue = qp->ops + + qp->total_dequeue; + + qp->total_dequeue += + rte_regexdev_dequeue_burst + (dev_id, + qp_id, + cur_ops_to_dequeue, + qp->total_enqueue - + qp->total_dequeue); + update = true; + } + } + } while (update); } end = clock(); time = ((double)end - start) / CLOCKS_PER_SEC; @@ -364,51 +437,59 @@ run_regex(uint32_t nb_jobs, (((double)actual_jobs * job_len * nb_iterations * 8) / time) / 1000000000.0); - if (!perf_mode) { + if (perf_mode) + goto end; + for (qp_id = 0; qp_id < nb_qps; qp_id++) { + printf("\n############ QP id=%u ############\n", qp_id); + qp = &qps[qp_id]; /* Log results per job. */ - for (d_ind = 0; d_ind < total_dequeue; d_ind++) { - nb_matches = ops[d_ind % actual_jobs]->nb_matches; + for (d_ind = 0; d_ind < qp->total_dequeue; d_ind++) { + nb_matches = qp->ops[d_ind % actual_jobs]->nb_matches; printf("Job id %"PRIu64" number of matches = %d\n", - ops[d_ind]->user_id, nb_matches); - total_matches += nb_matches; - match = ops[d_ind % actual_jobs]->matches; + qp->ops[d_ind]->user_id, nb_matches); + qp->total_matches += nb_matches; + match = qp->ops[d_ind % actual_jobs]->matches; for (i = 0; i < nb_matches; i++) { - printf("match %d, rule = %d, start = %d,len = %d\n", + printf("match %d, rule = %d, " + "start = %d,len = %d\n", i, match->rule_id, match->start_offset, match->len); match++; } } - printf("Total matches = %d\n", total_matches); + printf("Total matches = %d\n", qp->total_matches); printf("All Matches:\n"); - /* Log absolute results. */ - for (d_ind = 0; d_ind < total_dequeue; d_ind++) { - nb_matches = ops[d_ind % actual_jobs]->nb_matches; - total_matches += nb_matches; - match = ops[d_ind % actual_jobs]->matches; + for (d_ind = 0; d_ind < qp->total_dequeue; d_ind++) { + nb_matches = qp->ops[d_ind % actual_jobs]->nb_matches; + qp->total_matches += nb_matches; + match = qp->ops[d_ind % actual_jobs]->matches; for (i = 0; i < nb_matches; i++) { printf("start = %ld, len = %d, rule = %d\n", - match->start_offset + d_ind * job_len, - match->len, match->rule_id); + match->start_offset + + d_ind * job_len, + match->len, match->rule_id); match++; } } } end: - for (i = 0; i < actual_jobs; i++) { - if (ops[i]) - rte_free(ops[i]); - if (jobs_ctx[i].mbuf) - rte_pktmbuf_free(jobs_ctx[i].mbuf); + for (qp_id = 0; qp_id < qps_used; qp_id++) { + qp = &qps[qp_id]; + for (i = 0; i < actual_jobs && qp->ops; i++) + rte_free(qp->ops[i]); + rte_free(qp->ops); + qp->ops = NULL; + for (i = 0; i < actual_jobs && qp->jobs_ctx; i++) + rte_pktmbuf_free(qp->jobs_ctx[i].mbuf); + rte_free(qp->jobs_ctx); + qp->jobs_ctx = NULL; + rte_free(qp->buf); + qp->buf = NULL; } - rte_free(ops); - rte_free(jobs_ctx); - if (buf) - rte_free(buf); if (mbuf_mp) rte_mempool_free(mbuf_mp); - + rte_free(qps); return res; } @@ -418,12 +499,14 @@ main(int argc, char **argv) char rules_file[MAX_FILE_NAME]; char data_file[MAX_FILE_NAME]; uint32_t nb_jobs = 0; - uint16_t nb_max_payload = 0; bool perf_mode = 0; uint32_t nb_iterations = 0; - uint8_t nb_max_matches = 0; int ret; + uint16_t nb_max_payload = 0; + uint8_t nb_max_matches = 0; + uint32_t nb_qps = 1; + /* Init EAL. */ ret = rte_eal_init(argc, argv); if (ret < 0) rte_exit(EXIT_FAILURE, "EAL init failed\n"); @@ -431,13 +514,16 @@ main(int argc, char **argv) argv += ret; if (argc > 1) args_parse(argc, argv, rules_file, data_file, &nb_jobs, - &perf_mode, &nb_iterations); + &perf_mode, &nb_iterations, &nb_qps); - ret = init_port(&nb_max_payload, rules_file, &nb_max_matches); + if (nb_qps == 0) + rte_exit(EXIT_FAILURE, "Number of QPs must be greater than 0\n"); + ret = init_port(&nb_max_payload, rules_file, + &nb_max_matches, nb_qps); if (ret < 0) rte_exit(EXIT_FAILURE, "init port failed\n"); ret = run_regex(nb_jobs, nb_max_payload, perf_mode, - nb_iterations, data_file, nb_max_matches); + nb_iterations, data_file, nb_max_matches, nb_qps); if (ret < 0) { rte_exit(EXIT_FAILURE, "RegEx function failed\n"); } -- 2.8.4