The test_no_invasive_cgroup_shrink selftest checks that when a cgroup
has zswapped out more memory than memory.zswap.max, it does not
trigger writeback for other cgroups. To do this, it compares the
writeback count in a control cgroup and makes sure that it is 0,
and then checks the writeback count in an aggressor cgroup who does
expect to see writeback.
However, when the zswap shrinker is enabled, the victim cgroup can see
legitimate writebacks not triggered by the aggressor. In some Meta CI
tests, we have seen this failure mode happen.
Instead of checking that the victim cgroup has 0 writeback, compare the
writeback values before and after the aggressor runs and check that
the victim cgroup did not perform any additional writeback. Note that
this can still lead to probabilistic failures if writebacks take longer
than 5 seconds, but this should fix the systematic failure case.
Fixes: b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure")
Reported-by: Krush Chavan <[email protected]>
Suggested-by: Nhat Pham <[email protected]>
Signed-off-by: Joshua Hahn <[email protected]>
---
v1 --> v2:
- Instead of skipping the test when the zswap shrinker is enabled,
compare the victim's writeback counts before and after the aggressor
runs, as Nhat suggested.
tools/testing/selftests/cgroup/test_zswap.c | 28 +++++++++++++++++++--
1 file changed, 26 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/cgroup/test_zswap.c
b/tools/testing/selftests/cgroup/test_zswap.c
index 9c5bd503c3f73..1ac7790727757 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -20,6 +20,7 @@ static int page_size;
#define PATH_ZSWAP "/sys/module/zswap"
#define PATH_ZSWAP_ENABLED "/sys/module/zswap/parameters/enabled"
+#define PATH_ZSWAP_SHRINKER_ENABLED
"/sys/module/zswap/parameters/shrinker_enabled"
#define PATH_ZSWAP_STORED_PAGES "/sys/kernel/debug/zswap/stored_pages"
static int read_int(const char *path, size_t *value)
@@ -446,6 +447,16 @@ static int test_zswap_writeback_disabled(const char *root)
return test_zswap_writeback(root, false);
}
+static bool zswap_shrinker_enabled(void)
+{
+ char value[2];
+
+ if (read_text(PATH_ZSWAP_SHRINKER_ENABLED, value, sizeof(value)) <= 0)
+ return 0;
+
+ return value[0] == 'Y';
+}
+
/*
* When trying to store a memcg page in zswap, if the memcg hits its memory
* limit in zswap, writeback should affect only the zswapped pages of that
@@ -455,6 +466,7 @@ static int test_no_invasive_cgroup_shrink(const char *root)
{
int ret = KSFT_FAIL;
unsigned int off;
+ long zswpwb_before, zswpwb_after, zswpwb_target;
size_t allocation_size = page_size * 1024;
unsigned int nr_pages = allocation_size / page_size;
char zswap_max_buf[32], mem_max_buf[32];
@@ -490,6 +502,14 @@ static int test_no_invasive_cgroup_shrink(const char *root)
if (cg_read_key_long(zw_group, "memory.stat", "zswapped") < 1)
goto out;
+ /* If the shrinker is enabled, try to let the writebacks finish first */
+ if (zswap_shrinker_enabled())
+ sleep(5);
+
+ zswpwb_before = get_cg_wb_count(zw_group);
+ if (zswpwb_before < 0)
+ goto out;
+
/* Push wb_group memory into zswap with hard-to-compress data to
trigger wb */
if (cg_enter_current(wb_group))
goto out;
@@ -502,9 +522,13 @@ static int test_no_invasive_cgroup_shrink(const char *root)
getrandom(&wb_allocation[off], page_size/4, 0);
}
- /* Verify that only zswapped memory from gwb_group has been written
back */
- if (wait_for_writeback(wb_group, 5000) > 0 && get_cg_wb_count(zw_group)
== 0)
+ /* Verify that only zswapped memory from wb_group has been written back
*/
+ zswpwb_target = wait_for_writeback(wb_group, 5000);
+ zswpwb_after = get_cg_wb_count(zw_group);
+
+ if (zswpwb_target > 0 && zswpwb_before == zswpwb_after)
ret = KSFT_PASS;
+
out:
cg_enter_current(root);
if (zw_group) {
--
2.53.0-Meta
