diff mbox series

mempool: test performance with larger bursts

Message ID 20240121045249.22465-1-mb@smartsharesystems.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series mempool: test performance with larger bursts |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/loongarch-compilation success Compilation OK
ci/loongarch-unit-testing success Unit Testing PASS
ci/github-robot: build success github build: passed
ci/iol-abi-testing success Testing PASS
ci/iol-broadcom-Functional success Functional Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-unit-amd64-testing success Testing PASS
ci/iol-unit-arm64-testing success Testing PASS
ci/iol-compile-amd64-testing success Testing PASS
ci/iol-compile-arm64-testing success Testing PASS
ci/iol-sample-apps-testing success Testing PASS
ci/iol-mellanox-Performance success Performance Testing PASS
ci/Intel-compilation success Compilation OK
ci/intel-Testing success Testing PASS
ci/intel-Functional success Functional PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-intel-Functional success Functional Testing PASS

Commit Message

Morten Brørup Jan. 21, 2024, 4:52 a.m. UTC 
  Bursts of up to 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 4096.
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>
---
 app/test/test_mempool_perf.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

Comments

fengchengwen Jan. 22, 2024, 7:10 a.m. UTC | #1 
Hi Morten,

On 2024/1/21 12:52, Morten Brørup wrote:
> Bursts of up to 128 packets are not uncommon, so increase the maximum
> tested get and put burst sizes from 32 to 128.

How about add 64 ?

> 
> Some applications keep more than 512 objects, so increase the maximum
> number of kept objects from 512 to 4096.
> This exceeds the typical mempool cache size of 512 objects, so the test
> also exercises the mempool driver.

And for 2048? (I notice below already has 1024)

PS: with this commit, the number of combinations will grow much, and every
subtest cost 5sec, so the total time will increases great. So could this perf suite
support paramters or derivative command ? for instance:

REGISTER_PERF_TEST(mempool_perf_autotest, test_mempool_perf);
REGISTER_PERF_TEST(mempool_perf_autotest_keeps256, test_mempool_perf_keeps256);

Thanks.

> 
> Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
> ---
>  app/test/test_mempool_perf.c | 25 ++++++++++++++++---------
>  1 file changed, 16 insertions(+), 9 deletions(-)
> 
> diff --git a/app/test/test_mempool_perf.c b/app/test/test_mempool_perf.c
> index 96de347f04..f52106e833 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
> + *      - 1024
> + *      - 4096
>   */
>  
>  #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 4096
> +#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 +206,8 @@ 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 == 128)
> +			ret = test_loop(mp, cache, n_keep, 128, 128);
>  		else
>  			ret = -1;
>  
> @@ -289,9 +293,9 @@ 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, 128, 0 };
> +	unsigned int bulk_tab_put[] = { 1, 4, CACHE_LINE_BURST, 32, 128, 0 };
> +	unsigned int keep_tab[] = { 32, 128, 512, 1024, 4096, 0 };
>  	unsigned *get_bulk_ptr;
>  	unsigned *put_bulk_ptr;
>  	unsigned *keep_ptr;
> @@ -301,6 +305,9 @@ 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;
>
diff mbox series

Patch

diff --git a/app/test/test_mempool_perf.c b/app/test/test_mempool_perf.c
index 96de347f04..f52106e833 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
+ *      - 1024
+ *      - 4096
  */
 
 #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 4096
+#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 +206,8 @@  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 == 128)
+			ret = test_loop(mp, cache, n_keep, 128, 128);
 		else
 			ret = -1;
 
@@ -289,9 +293,9 @@  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, 128, 0 };
+	unsigned int bulk_tab_put[] = { 1, 4, CACHE_LINE_BURST, 32, 128, 0 };
+	unsigned int keep_tab[] = { 32, 128, 512, 1024, 4096, 0 };
 	unsigned *get_bulk_ptr;
 	unsigned *put_bulk_ptr;
 	unsigned *keep_ptr;
@@ -301,6 +305,9 @@  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;