From patchwork Wed Jan 24 08:58:00 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?q?Morten_Br=C3=B8rup?= X-Patchwork-Id: 136093 X-Patchwork-Delegate: thomas@monjalon.net Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 4065C439B2; Wed, 24 Jan 2024 09:58:06 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 2F1484026F; Wed, 24 Jan 2024 09:58:06 +0100 (CET) Received: from dkmailrelay1.smartsharesystems.com (smartserver.smartsharesystems.com [77.243.40.215]) by mails.dpdk.org (Postfix) with ESMTP id D725C400D5 for ; Wed, 24 Jan 2024 09:58:04 +0100 (CET) Received: from smartserver.smartsharesystems.com (smartserver.smartsharesys.local [192.168.4.10]) by dkmailrelay1.smartsharesystems.com (Postfix) with ESMTP id AFB42205F3; Wed, 24 Jan 2024 09:58:04 +0100 (CET) Received: from dkrd2.smartsharesys.local ([192.168.4.12]) by smartserver.smartsharesystems.com with Microsoft SMTPSVC(6.0.3790.4675); Wed, 24 Jan 2024 09:58:02 +0100 From: =?utf-8?q?Morten_Br=C3=B8rup?= To: andrew.rybchenko@oktetlabs.ru, fengchengwen@huawei.com Cc: dev@dpdk.org, =?utf-8?q?Morten_Br=C3=B8rup?= Subject: [PATCH v3] mempool: test performance with larger bursts Date: Wed, 24 Jan 2024 09:58:00 +0100 Message-Id: <20240124085800.83509-1-mb@smartsharesystems.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20240121045249.22465-1-mb@smartsharesystems.com> References: <20240121045249.22465-1-mb@smartsharesystems.com> MIME-Version: 1.0 X-OriginalArrivalTime: 24 Jan 2024 08:58:02.0499 (UTC) FILETIME=[6FE86D30:01DA4EA3] X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Bursts of up to 64 or 128 packets are not uncommon, so increase the maximum tested get and put burst sizes from 32 to 128. For convenience, also test get and put burst sizes of RTE_MEMPOOL_CACHE_MAX_SIZE. Some applications keep more than 512 objects, so increase the maximum number of kept objects from 512 to 32768, still in jumps of factor four. This exceeds the typical mempool cache size of 512 objects, so the test also exercises the mempool driver. Signed-off-by: Morten Brørup --- v3: * Increased max number of kept objects to 32768. * Added get and put burst sizes of RTE_MEMPOOL_CACHE_MAX_SIZE objects. * Print error if unable to allocate mempool. * Initialize use_external_cache with each test. A previous version of this patch had a bug, where all test runs following the first would use external cache. (Chengwen Feng) v2: Addressed feedback by Chengwen Feng * Added get and put burst sizes of 64 objects, which is probably also not uncommon packet burst size. * Fixed list of number of kept objects so list remains in jumps of factor four. * Added three derivative test cases, for faster testing. --- app/test/test_mempool_perf.c | 42 ++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 16 deletions(-) diff --git a/app/test/test_mempool_perf.c b/app/test/test_mempool_perf.c index a5a7d43608..481263186a 100644 --- a/app/test/test_mempool_perf.c +++ b/app/test/test_mempool_perf.c @@ -54,9 +54,9 @@ * * - Bulk size (*n_get_bulk*, *n_put_bulk*) * - * - Bulk get from 1 to 128 - * - Bulk put from 1 to 128 - * - Bulk get and put from 1 to 128, compile time constant + * - Bulk get from 1 to 128, and RTE_MEMPOOL_CACHE_MAX_SIZE + * - Bulk put from 1 to 128, and RTE_MEMPOOL_CACHE_MAX_SIZE + * - Bulk get and put from 1 to 128, and RTE_MEMPOOL_CACHE_MAX_SIZE, compile time constant * * - Number of kept objects (*n_keep*) * @@ -65,12 +65,13 @@ * - 512 * - 2048 * - 8192 + * - 32768 */ -#define N 65536 +#define N 262144 #define TIME_S 5 #define MEMPOOL_ELT_SIZE 2048 -#define MAX_KEEP 8192 +#define MAX_KEEP 32768 #define MEMPOOL_SIZE ((rte_lcore_count()*(MAX_KEEP+RTE_MEMPOOL_CACHE_MAX_SIZE*2))-1) /* Number of pointers fitting into one cache line. */ @@ -210,6 +211,9 @@ per_lcore_mempool_test(void *arg) ret = test_loop(mp, cache, n_keep, 64, 64); else if (n_get_bulk == 128) ret = test_loop(mp, cache, n_keep, 128, 128); + else if (n_get_bulk == RTE_MEMPOOL_CACHE_MAX_SIZE) + ret = test_loop(mp, cache, n_keep, + RTE_MEMPOOL_CACHE_MAX_SIZE, RTE_MEMPOOL_CACHE_MAX_SIZE); else ret = -1; @@ -293,11 +297,13 @@ launch_cores(struct rte_mempool *mp, unsigned int cores) /* for a given number of core, launch all test cases */ static int -do_one_mempool_test(struct rte_mempool *mp, unsigned int cores) +do_one_mempool_test(struct rte_mempool *mp, unsigned int cores, int external_cache) { - unsigned int bulk_tab_get[] = { 1, 4, CACHE_LINE_BURST, 32, 64, 128, 0 }; - unsigned int bulk_tab_put[] = { 1, 4, CACHE_LINE_BURST, 32, 64, 128, 0 }; - unsigned int keep_tab[] = { 32, 128, 512, 2048, 8192, 0 }; + unsigned int bulk_tab_get[] = { 1, 4, CACHE_LINE_BURST, 32, 64, 128, + RTE_MEMPOOL_CACHE_MAX_SIZE, 0 }; + unsigned int bulk_tab_put[] = { 1, 4, CACHE_LINE_BURST, 32, 64, 128, + RTE_MEMPOOL_CACHE_MAX_SIZE, 0 }; + unsigned int keep_tab[] = { 32, 128, 512, 2048, 8192, 32768, 0 }; unsigned *get_bulk_ptr; unsigned *put_bulk_ptr; unsigned *keep_ptr; @@ -310,6 +316,7 @@ do_one_mempool_test(struct rte_mempool *mp, unsigned int cores) if (*keep_ptr < *get_bulk_ptr || *keep_ptr < *put_bulk_ptr) continue; + use_external_cache = external_cache; use_constant_values = 0; n_get_bulk = *get_bulk_ptr; n_put_bulk = *put_bulk_ptr; @@ -346,8 +353,10 @@ do_all_mempool_perf_tests(unsigned int cores) NULL, NULL, my_obj_init, NULL, SOCKET_ID_ANY, 0); - if (mp_nocache == NULL) + if (mp_nocache == NULL) { + printf("cannot allocate mempool (without cache)\n"); goto err; + } /* create a mempool (with cache) */ mp_cache = rte_mempool_create("perf_test_cache", MEMPOOL_SIZE, @@ -356,8 +365,10 @@ do_all_mempool_perf_tests(unsigned int cores) NULL, NULL, my_obj_init, NULL, SOCKET_ID_ANY, 0); - if (mp_cache == NULL) + if (mp_cache == NULL) { + printf("cannot allocate mempool (with cache)\n"); goto err; + } default_pool_ops = rte_mbuf_best_mempool_ops(); /* Create a mempool based on Default handler */ @@ -386,21 +397,20 @@ do_all_mempool_perf_tests(unsigned int cores) rte_mempool_obj_iter(default_pool, my_obj_init, NULL); printf("start performance test (without cache)\n"); - if (do_one_mempool_test(mp_nocache, cores) < 0) + if (do_one_mempool_test(mp_nocache, cores, 0) < 0) goto err; printf("start performance test for %s (without cache)\n", default_pool_ops); - if (do_one_mempool_test(default_pool, cores) < 0) + if (do_one_mempool_test(default_pool, cores, 0) < 0) goto err; printf("start performance test (with cache)\n"); - if (do_one_mempool_test(mp_cache, cores) < 0) + if (do_one_mempool_test(mp_cache, cores, 0) < 0) goto err; printf("start performance test (with user-owned cache)\n"); - use_external_cache = 1; - if (do_one_mempool_test(mp_nocache, cores) < 0) + if (do_one_mempool_test(mp_nocache, cores, 1) < 0) goto err; rte_mempool_list_dump(stdout);