diff options
| author | Muhammad Usama Anjum <usama.anjum@arm.com> | 2026-07-27 10:52:21 +0100 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2026-08-24 18:43:10 -0700 |
| commit | 746c94b7cb7900327a6ca7c1fcbfdd0243729253 (patch) | |
| tree | 8167e7d7fba5f3e70393990a67c581ede5fedfa5 /tools/testing | |
| parent | e14e52a7ce02f6b62cecbf5c61425b4137422df2 (diff) | |
selftests/mm: retry migration failures for the full runtime
move_pages() is best effort and can temporarily fail when concurrent
faults race with page unmapping. A busy shared-anon workload can exhaust
the current 100 retries long before the intended 20-second runtime and
produce a false failure.
Use the full runtime as the retry window. Since the initial page location
is unknown, require it to reach both alternating NUMA targets to confirm
that cross-node migration made progress despite transient contention.
Link: https://lore.kernel.org/20260727095225.372655-6-usama.anjum@arm.com
Signed-off-by: Muhammad Usama Anjum <usama.anjum@arm.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Sarthak Sharma <sarthak.sharma@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Usama Arif <usama.arif@linux.dev>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'tools/testing')
| -rw-r--r-- | tools/testing/selftests/mm/migration.c | 37 |
1 files changed, 20 insertions, 17 deletions
diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 29f7492453d4..f19d53c69576 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -7,7 +7,7 @@ #include "kselftest_harness.h" #include "hugepage_settings.h" -#include <strings.h> +#include <string.h> #include <pthread.h> #include <numa.h> #include <numaif.h> @@ -20,7 +20,6 @@ #define TWOMEG (2<<20) #define RUNTIME (20) -#define MAX_RETRIES 100 #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) HUGETLB_SETUP_DEFAULT_PAGES(1) @@ -110,7 +109,7 @@ int migrate(uint64_t *ptr, int n1, int n2) int ret, tmp; int status = 0; struct timespec ts1, ts2; - int failures = 0; + int success = 0; if (clock_gettime(CLOCK_MONOTONIC, &ts1)) return -1; @@ -119,29 +118,33 @@ int migrate(uint64_t *ptr, int n1, int n2) if (clock_gettime(CLOCK_MONOTONIC, &ts2)) return -1; - if (ts2.tv_sec - ts1.tv_sec >= RUNTIME) - return 0; + if (ts2.tv_sec - ts1.tv_sec >= RUNTIME) { + /* Reaching both targets verifies a cross-node move. */ + if (success >= 2) + return 0; + else + return -2; + } ret = move_pages(0, 1, (void **) &ptr, &n2, &status, MPOL_MF_MOVE_ALL); - if (ret) { - if (ret > 0) { - /* Migration is best effort; try again */ - if (++failures < MAX_RETRIES) - continue; - printf("Didn't migrate %d pages\n", ret); - } - else - perror("Couldn't migrate pages"); + if (ret < 0) { + perror("Couldn't migrate pages"); + return ret; + } + /* Migration is best effort. Try again */ + if (ret > 0 || status < 0) + continue; + if (status != n2) { + printf("Page is on node %d instead of target node %d\n", + status, n2); return -2; } - failures = 0; + success++; tmp = n2; n2 = n1; n1 = tmp; } - - return 0; } void *access_mem(void *ptr) |