diff mbox series

[bpf-next,v1,3/3] selftests/bpf: Fixes for test_maps test

Message ID 20250227142646.59711-4-jiayuan.chen@linux.dev (mailing list archive)
State New
Headers show
Series Optimize bpf selftest to increase CI success rate | expand

Commit Message

Jiayuan Chen Feb. 27, 2025, 2:26 p.m. UTC
BPF CI has failed 3 times in the last 24 hours. Add retry for ENOMEM.
It's similar to the optimization plan:
commit 2f553b032cad ("selftsets/bpf: Retry map update for non-preallocated per-cpu map")

Failed CI:
https://github.com/kernel-patches/bpf/actions/runs/13549227497/job/37868926343
https://github.com/kernel-patches/bpf/actions/runs/13548089029/job/37865812030
https://github.com/kernel-patches/bpf/actions/runs/13553536268/job/37883329296

selftests/bpf: Fixes for test_maps test
Fork 100 tasks to 'test_update_delete'
Fork 100 tasks to 'test_update_delete'
Fork 100 tasks to 'test_update_delete'
Fork 100 tasks to 'test_update_delete'
......
test_task_storage_map_stress_lookup:PASS
test_maps: OK, 0 SKIPPED

Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
---
 tools/testing/selftests/bpf/test_maps.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

Comments

Hou Tao March 1, 2025, 1:31 a.m. UTC | #1
Hi,

On 2/27/2025 10:26 PM, Jiayuan Chen wrote:
> BPF CI has failed 3 times in the last 24 hours. Add retry for ENOMEM.
> It's similar to the optimization plan:
> commit 2f553b032cad ("selftsets/bpf: Retry map update for non-preallocated per-cpu map")
>
> Failed CI:
> https://github.com/kernel-patches/bpf/actions/runs/13549227497/job/37868926343
> https://github.com/kernel-patches/bpf/actions/runs/13548089029/job/37865812030
> https://github.com/kernel-patches/bpf/actions/runs/13553536268/job/37883329296

Er, it is suspicious that the allocation of htab_elem failed, because
the size of key and value is small in these cases. It usually means that
there is something wrong with bpf mem allocator or the slub, therefore,
I think it is a bad idea to retry for ENOMEM in this case. Will try to
reproduce the problem first when get some time.
>
> selftests/bpf: Fixes for test_maps test
> Fork 100 tasks to 'test_update_delete'
> Fork 100 tasks to 'test_update_delete'
> Fork 100 tasks to 'test_update_delete'
> Fork 100 tasks to 'test_update_delete'
> ......
> test_task_storage_map_stress_lookup:PASS
> test_maps: OK, 0 SKIPPED
>
> Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
> ---
>  tools/testing/selftests/bpf/test_maps.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
>
> diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
> index 8b40e9496af1..986ce32b113a 100644
> --- a/tools/testing/selftests/bpf/test_maps.c
> +++ b/tools/testing/selftests/bpf/test_maps.c
> @@ -1396,9 +1396,10 @@ static void test_map_stress(void)
>  #define MAX_DELAY_US 50000
>  #define MIN_DELAY_RANGE_US 5000
>  
> -static bool retry_for_again_or_busy(int err)
> +static bool can_retry(int err)
>  {
> -	return (err == EAGAIN || err == EBUSY);
> +	return (err == EAGAIN || err == EBUSY ||
> +		(err == ENOMEM && map_opts.map_flags == BPF_F_NO_PREALLOC));
>  }
>  
>  int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
> @@ -1451,12 +1452,12 @@ static void test_update_delete(unsigned int fn, void *data)
>  
>  		if (do_update) {
>  			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES,
> -						   retry_for_again_or_busy);
> +						   can_retry);
>  			if (err)
>  				printf("error %d %d\n", err, errno);
>  			assert(err == 0);
>  			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES,
> -						   retry_for_again_or_busy);
> +						   can_retry);
>  			if (err)
>  				printf("error %d %d\n", err, errno);
>  			assert(err == 0);
diff mbox series

Patch

diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 8b40e9496af1..986ce32b113a 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1396,9 +1396,10 @@  static void test_map_stress(void)
 #define MAX_DELAY_US 50000
 #define MIN_DELAY_RANGE_US 5000
 
-static bool retry_for_again_or_busy(int err)
+static bool can_retry(int err)
 {
-	return (err == EAGAIN || err == EBUSY);
+	return (err == EAGAIN || err == EBUSY ||
+		(err == ENOMEM && map_opts.map_flags == BPF_F_NO_PREALLOC));
 }
 
 int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
@@ -1451,12 +1452,12 @@  static void test_update_delete(unsigned int fn, void *data)
 
 		if (do_update) {
 			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES,
-						   retry_for_again_or_busy);
+						   can_retry);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
 			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES,
-						   retry_for_again_or_busy);
+						   can_retry);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);