[PATCH v2] mempool: test performance with larger bursts

[fengchengwen]

Hi Morten,

On 2024/1/22 22:34, Morten Brørup wrote:
> 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.
> 
> Some applications keep more than 512 objects, so increase the maximum
> number of kept objects from 512 to 8192, 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 at smartsharesystems.com>
> 
> ---
> 
> v2: Addressed feedback by Chengwen Feng
> * Added get and put burst sizes of 64 packets, which is probably also not
>   uncommon.
> * 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 | 107 ++++++++++++++++++++---------------
>  1 file changed, 62 insertions(+), 45 deletions(-)
> 
> diff --git a/app/test/test_mempool_perf.c b/app/test/test_mempool_perf.c
> index 96de347f04..a5a7d43608 100644
> --- a/app/test/test_mempool_perf.c
> +++ b/app/test/test_mempool_perf.c
> @@ -1,6 +1,6 @@
>  /* SPDX-License-Identifier: BSD-3-Clause
>   * Copyright(c) 2010-2014 Intel Corporation
> - * Copyright(c) 2022 SmartShare Systems
> + * Copyright(c) 2022-2024 SmartShare Systems
>   */
>  
>  #include <string.h>
> @@ -54,22 +54,24 @@
>   *
>   *    - Bulk size (*n_get_bulk*, *n_put_bulk*)
>   *
> - *      - Bulk get from 1 to 32
> - *      - Bulk put from 1 to 32
> - *      - Bulk get and put from 1 to 32, compile time constant
> + *      - Bulk get from 1 to 128
> + *      - Bulk put from 1 to 128
> + *      - Bulk get and put from 1 to 128, compile time constant
>   *
>   *    - Number of kept objects (*n_keep*)
>   *
>   *      - 32
>   *      - 128
>   *      - 512
> + *      - 2048
> + *      - 8192
>   */
>  
>  #define N 65536
>  #define TIME_S 5
>  #define MEMPOOL_ELT_SIZE 2048
> -#define MAX_KEEP 512
> -#define MEMPOOL_SIZE ((rte_lcore_count()*(MAX_KEEP+RTE_MEMPOOL_CACHE_MAX_SIZE))-1)
> +#define MAX_KEEP 8192
> +#define MEMPOOL_SIZE ((rte_lcore_count()*(MAX_KEEP+RTE_MEMPOOL_CACHE_MAX_SIZE*2))-1)
>  
>  /* Number of pointers fitting into one cache line. */
>  #define CACHE_LINE_BURST (RTE_CACHE_LINE_SIZE / sizeof(uintptr_t))
> @@ -204,6 +206,10 @@ per_lcore_mempool_test(void *arg)
>  					CACHE_LINE_BURST, CACHE_LINE_BURST);
>  		else if (n_get_bulk == 32)
>  			ret = test_loop(mp, cache, n_keep, 32, 32);
> +		else if (n_get_bulk == 64)
> +			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
>  			ret = -1;
>  
> @@ -289,9 +295,9 @@ launch_cores(struct rte_mempool *mp, unsigned int cores)
>  static int
>  do_one_mempool_test(struct rte_mempool *mp, unsigned int cores)
>  {
> -	unsigned int bulk_tab_get[] = { 1, 4, CACHE_LINE_BURST, 32, 0 };
> -	unsigned int bulk_tab_put[] = { 1, 4, CACHE_LINE_BURST, 32, 0 };
> -	unsigned int keep_tab[] = { 32, 128, 512, 0 };
> +	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 *get_bulk_ptr;
>  	unsigned *put_bulk_ptr;
>  	unsigned *keep_ptr;
> @@ -301,6 +307,9 @@ do_one_mempool_test(struct rte_mempool *mp, unsigned int cores)
>  		for (put_bulk_ptr = bulk_tab_put; *put_bulk_ptr; put_bulk_ptr++) {
>  			for (keep_ptr = keep_tab; *keep_ptr; keep_ptr++) {
>  
> +				if (*keep_ptr < *get_bulk_ptr || *keep_ptr < *put_bulk_ptr)
> +					continue;
> +
>  				use_constant_values = 0;
>  				n_get_bulk = *get_bulk_ptr;
>  				n_put_bulk = *put_bulk_ptr;
> @@ -323,7 +332,7 @@ do_one_mempool_test(struct rte_mempool *mp, unsigned int cores)
>  }
>  
>  static int
> -test_mempool_perf(void)
> +do_all_mempool_perf_tests(unsigned int cores)
>  {
>  	struct rte_mempool *mp_cache = NULL;
>  	struct rte_mempool *mp_nocache = NULL;
> @@ -376,65 +385,73 @@ test_mempool_perf(void)
>  
>  	rte_mempool_obj_iter(default_pool, my_obj_init, NULL);
>  
> -	/* performance test with 1, 2 and max cores */
>  	printf("start performance test (without cache)\n");
> -
> -	if (do_one_mempool_test(mp_nocache, 1) < 0)
> +	if (do_one_mempool_test(mp_nocache, cores) < 0)
>  		goto err;
>  
> -	if (do_one_mempool_test(mp_nocache, 2) < 0)
> -		goto err;
> -
> -	if (do_one_mempool_test(mp_nocache, rte_lcore_count()) < 0)
> -		goto err;
> -
> -	/* performance test with 1, 2 and max cores */
>  	printf("start performance test for %s (without cache)\n",
>  	       default_pool_ops);
> -
> -	if (do_one_mempool_test(default_pool, 1) < 0)
> +	if (do_one_mempool_test(default_pool, cores) < 0)
>  		goto err;
>  
> -	if (do_one_mempool_test(default_pool, 2) < 0)
> +	printf("start performance test (with cache)\n");
> +	if (do_one_mempool_test(mp_cache, cores) < 0)
>  		goto err;
>  
> -	if (do_one_mempool_test(default_pool, rte_lcore_count()) < 0)
> +	printf("start performance test (with user-owned cache)\n");
> +	use_external_cache = 1;

This variable should set to zero after next test, because we may repeat execute command again.
I think the original code already has this bug, suggest add a bugfix first and then with this commit.

> +	if (do_one_mempool_test(mp_nocache, cores) < 0)
>  		goto err;
>  
> -	/* performance test with 1, 2 and max cores */
> -	printf("start performance test (with cache)\n");
> +	rte_mempool_list_dump(stdout);
>  
> -	if (do_one_mempool_test(mp_cache, 1) < 0)
> -		goto err;
> +	ret = 0;
>  
> -	if (do_one_mempool_test(mp_cache, 2) < 0)
> -		goto err;
> +err:
> +	rte_mempool_free(mp_cache);
> +	rte_mempool_free(mp_nocache);
> +	rte_mempool_free(default_pool);
> +	return ret;
> +}
>  
> -	if (do_one_mempool_test(mp_cache, rte_lcore_count()) < 0)
> -		goto err;
> +static int
> +test_mempool_perf_1core(void)
> +{
> +	return do_all_mempool_perf_tests(1);
> +}
>  
> -	/* performance test with 1, 2 and max cores */
> -	printf("start performance test (with user-owned cache)\n");
> -	use_external_cache = 1;
> +static int
> +test_mempool_perf_2cores(void)
> +{
> +	return do_all_mempool_perf_tests(2);
> +}
>  
> -	if (do_one_mempool_test(mp_nocache, 1) < 0)
> -		goto err;
> +static int
> +test_mempool_perf_allcores(void)
> +{
> +	return do_all_mempool_perf_tests(rte_lcore_count());
> +}
>  
> -	if (do_one_mempool_test(mp_nocache, 2) < 0)
> -		goto err;
> +static int
> +test_mempool_perf(void)
> +{
> +	int ret = -1;
>  
> -	if (do_one_mempool_test(mp_nocache, rte_lcore_count()) < 0)
> +	/* performance test with 1, 2 and max cores */
> +	if (do_all_mempool_perf_tests(1) < 0)
> +		goto err;
> +	if (do_all_mempool_perf_tests(2) < 0)
> +		goto err;
> +	if (do_all_mempool_perf_tests(rte_lcore_count()) < 0)
>  		goto err;
> -
> -	rte_mempool_list_dump(stdout);
>  
>  	ret = 0;
>  
>  err:
> -	rte_mempool_free(mp_cache);
> -	rte_mempool_free(mp_nocache);
> -	rte_mempool_free(default_pool);
>  	return ret;
>  }
>  
>  REGISTER_PERF_TEST(mempool_perf_autotest, test_mempool_perf);
> +REGISTER_PERF_TEST(mempool_perf_autotest_1core, test_mempool_perf_1core);
> +REGISTER_PERF_TEST(mempool_perf_autotest_2cores, test_mempool_perf_2cores);
> +REGISTER_PERF_TEST(mempool_perf_autotest_allcores, test_mempool_perf_allcores);

I'm OK for derivative tests by core-number.

With above bug fixed,
Acked-by: Chengwen Feng <fengchengwen at huawei.com>

Thanks

>