diff mbox series

[v3] mempool: test performance with larger bursts

Message ID 20240124085800.83509-1-mb@smartsharesystems.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series [v3] mempool: test performance with larger bursts |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/loongarch-compilation warning apply patch failure
ci/Intel-compilation warning apply issues

Commit Message

Morten Brørup Jan. 24, 2024, 8:58 a.m. UTC 
  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 <mb@smartsharesystems.com>
---

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 mbox series

Patch

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);