Replace the manual sleep-and-retry logic in test_kmem_dead_cgroups()
with the new helper `cg_read_key_long_poll()`. This change improves
the robustness of the test by polling the "nr_dying_descendants"
counter in `cgroup.stat` until it reaches 0 or the timeout is exceeded.

Additionally, increase the retry timeout to 8 seconds (from 5 seconds)
based on testing results:
  - With 5-second timeout: 4/20 runs passed.
  - With 8-second timeout: 20/20 runs passed.

The 8 second timeout is based on stress testing of test_kmem_dead_cgroups()
under load: 5 seconds was occasionally not enough for reclaim of dying
descendants to complete, whereas 8 seconds consistently covered the observed
latencies. This value is intended as a generous upper bound for the
asynchronous reclaim and is not tied to any specific kernel constant, so it
can be adjusted in the future if reclaim behavior changes.

Signed-off-by: Guopeng Zhang <[email protected]>
Reviewed-by: Shakeel Butt <[email protected]>
---
 tools/testing/selftests/cgroup/test_kmem.c | 33 ++++++++++------------
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/cgroup/test_kmem.c 
b/tools/testing/selftests/cgroup/test_kmem.c
index ca38525484e3..eeabd34bf083 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -26,6 +26,7 @@
  */
 #define MAX_VMSTAT_ERROR (4096 * 64 * get_nprocs())
 
+#define KMEM_DEAD_WAIT_RETRIES        80
 
 static int alloc_dcache(const char *cgroup, void *arg)
 {
@@ -306,9 +307,7 @@ static int test_kmem_dead_cgroups(const char *root)
 {
        int ret = KSFT_FAIL;
        char *parent;
-       long dead;
-       int i;
-       int max_time = 20;
+       long dead = -1;
 
        parent = cg_name(root, "kmem_dead_cgroups_test");
        if (!parent)
@@ -323,21 +322,19 @@ static int test_kmem_dead_cgroups(const char *root)
        if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
                goto cleanup;
 
-       for (i = 0; i < max_time; i++) {
-               dead = cg_read_key_long(parent, "cgroup.stat",
-                                       "nr_dying_descendants ");
-               if (dead == 0) {
-                       ret = KSFT_PASS;
-                       break;
-               }
-               /*
-                * Reclaiming cgroups might take some time,
-                * let's wait a bit and repeat.
-                */
-               sleep(1);
-               if (i > 5)
-                       printf("Waiting time longer than 5s; wait: %ds (dead: 
%ld)\n", i, dead);
-       }
+       /*
+        * Allow up to ~8s for reclaim of dying descendants to complete.
+        * This is a generous upper bound derived from stress testing, not
+        * from a specific kernel constant, and can be adjusted if reclaim
+        * behavior changes in the future.
+        */
+       dead = cg_read_key_long_poll(parent, "cgroup.stat",
+                                       "nr_dying_descendants ", 0, 
KMEM_DEAD_WAIT_RETRIES,
+                                       DEFAULT_WAIT_INTERVAL_US);
+       if (dead)
+               goto cleanup;
+
+       ret = KSFT_PASS;
 
 cleanup:
        cg_destroy(parent);
-- 
2.25.1


Reply via email to