The patch titled
Subject: selftests/mm: Introduce a test program to assess swap entry allocation for thp_swapout
has been added to the -mm mm-unstable branch. Its filename is
selftests-mm-introduce-a-test-program-to-assess-swap-entry-allocation-for-thp_swapout.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/selftests-mm-introduce-a-test-program-to-assess-swap-entry-allocation-for-thp_swapout.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Barry Song <v-songbaohua@xxxxxxxx>
Subject: selftests/mm: Introduce a test program to assess swap entry allocation for thp_swapout
Date: Thu, 20 Jun 2024 12:26:48 +1200
Both Ryan and Chris have been utilizing the small test program to aid in
debugging and identifying issues with swap entry allocation. While a real
or intricate workload might be more suitable for assessing the correctness
and effectiveness of the swap allocation policy, a small test program
presents a simpler means of understanding the problem and initially
verifying the improvements being made.
Let's endeavor to integrate it into the self-test suite. Although it
presently only accommodates 64KB and 4KB, I'm optimistic that we can
expand its capabilities to support multiple sizes and simulate more
complex systems in the future as required.
Link: https://lkml.kernel.org/r/20240620002648.75204-1-21cnbao@xxxxxxxxx
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
Cc: Chris Li <chrisl@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Kairui Song <kasong@xxxxxxxxxxx>
Cc: Kalesh Singh <kaleshsingh@xxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
tools/testing/selftests/mm/Makefile | 1
tools/testing/selftests/mm/thp_swap_allocator_test.c | 192 ++++++++++
2 files changed, 193 insertions(+)
--- a/tools/testing/selftests/mm/Makefile~selftests-mm-introduce-a-test-program-to-assess-swap-entry-allocation-for-thp_swapout
+++ a/tools/testing/selftests/mm/Makefile
@@ -65,6 +65,7 @@ TEST_GEN_FILES += mseal_test
TEST_GEN_FILES += seal_elf
TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += pagemap_ioctl
+TEST_GEN_FILES += thp_swap_allocator_test
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += uffd-stress
--- /dev/null
+++ a/tools/testing/selftests/mm/thp_swap_allocator_test.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * thp_swap_allocator_test
+ *
+ * The purpose of this test program is helping check if THP swpout
+ * can correctly get swap slots to swap out as a whole instead of
+ * being split. It randomly releases swap entries through madvise
+ * DONTNEED and do swapout on two memory areas: a memory area for
+ * 64KB THP and the other area for small folios. The second memory
+ * can be enabled by "-s".
+ * Before running the program, we need to setup a zRAM or similar
+ * swap device by:
+ * echo lzo > /sys/block/zram0/comp_algorithm
+ * echo 64M > /sys/block/zram0/disksize
+ * echo never > /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+ * echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled
+ * mkswap /dev/zram0
+ * swapon /dev/zram0
+ * The expected result should be 0% anon swpout fallback ratio w/ or
+ * w/o "-s".
+ *
+ * Author(s): Barry Song <v-songbaohua@xxxxxxxx>
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <errno.h>
+#include <time.h>
+
+#define MEMSIZE_MTHP (60 * 1024 * 1024)
+#define MEMSIZE_SMALLFOLIO (1 * 1024 * 1024)
+#define ALIGNMENT_MTHP (64 * 1024)
+#define ALIGNMENT_SMALLFOLIO (4 * 1024)
+#define TOTAL_DONTNEED_MTHP (16 * 1024 * 1024)
+#define TOTAL_DONTNEED_SMALLFOLIO (768 * 1024)
+#define MTHP_FOLIO_SIZE (64 * 1024)
+
+#define SWPOUT_PATH \
+ "/sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout"
+#define SWPOUT_FALLBACK_PATH \
+ "/sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout_fallback"
+
+static void *aligned_alloc_mem(size_t size, size_t alignment)
+{
+ void *mem = NULL;
+
+ if (posix_memalign(&mem, alignment, size) != 0) {
+ perror("posix_memalign");
+ return NULL;
+ }
+ return mem;
+}
+
+static void random_madvise_dontneed(void *mem, size_t mem_size,
+ size_t align_size, size_t total_dontneed_size)
+{
+ size_t num_pages = total_dontneed_size / align_size;
+ size_t i;
+ size_t offset;
+ void *addr;
+
+ for (i = 0; i < num_pages; ++i) {
+ offset = (rand() % (mem_size / align_size)) * align_size;
+ addr = (char *)mem + offset;
+ if (madvise(addr, align_size, MADV_DONTNEED) != 0)
+ perror("madvise dontneed");
+
+ memset(addr, 0x11, align_size);
+ }
+}
+
+static unsigned long read_stat(const char *path)
+{
+ FILE *file;
+ unsigned long value;
+
+ file = fopen(path, "r");
+ if (!file) {
+ perror("fopen");
+ return 0;
+ }
+
+ if (fscanf(file, "%lu", &value) != 1) {
+ perror("fscanf");
+ fclose(file);
+ return 0;
+ }
+
+ fclose(file);
+ return value;
+}
+
+int main(int argc, char *argv[])
+{
+ int use_small_folio = 0;
+ int i;
+ void *mem1 = aligned_alloc_mem(MEMSIZE_MTHP, ALIGNMENT_MTHP);
+ void *mem2 = NULL;
+
+ if (mem1 == NULL) {
+ fprintf(stderr, "Failed to allocate 60MB memory\n");
+ return EXIT_FAILURE;
+ }
+
+ if (madvise(mem1, MEMSIZE_MTHP, MADV_HUGEPAGE) != 0) {
+ perror("madvise hugepage for mem1");
+ free(mem1);
+ return EXIT_FAILURE;
+ }
+
+ for (i = 1; i < argc; ++i) {
+ if (strcmp(argv[i], "-s") == 0)
+ use_small_folio = 1;
+ }
+
+ if (use_small_folio) {
+ mem2 = aligned_alloc_mem(MEMSIZE_SMALLFOLIO, ALIGNMENT_MTHP);
+ if (mem2 == NULL) {
+ fprintf(stderr, "Failed to allocate 1MB memory\n");
+ free(mem1);
+ return EXIT_FAILURE;
+ }
+
+ if (madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_NOHUGEPAGE) != 0) {
+ perror("madvise nohugepage for mem2");
+ free(mem1);
+ free(mem2);
+ return EXIT_FAILURE;
+ }
+ }
+
+ for (i = 0; i < 100; ++i) {
+ unsigned long initial_swpout;
+ unsigned long initial_swpout_fallback;
+ unsigned long final_swpout;
+ unsigned long final_swpout_fallback;
+ unsigned long swpout_inc;
+ unsigned long swpout_fallback_inc;
+ double fallback_percentage;
+
+ initial_swpout = read_stat(SWPOUT_PATH);
+ initial_swpout_fallback = read_stat(SWPOUT_FALLBACK_PATH);
+
+ random_madvise_dontneed(mem1, MEMSIZE_MTHP, ALIGNMENT_MTHP,
+ TOTAL_DONTNEED_MTHP);
+
+ if (use_small_folio) {
+ random_madvise_dontneed(mem2, MEMSIZE_SMALLFOLIO,
+ ALIGNMENT_SMALLFOLIO,
+ TOTAL_DONTNEED_SMALLFOLIO);
+ }
+
+ if (madvise(mem1, MEMSIZE_MTHP, MADV_PAGEOUT) != 0) {
+ perror("madvise pageout for mem1");
+ free(mem1);
+ if (mem2 != NULL)
+ free(mem2);
+ return EXIT_FAILURE;
+ }
+
+ if (use_small_folio) {
+ if (madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_PAGEOUT) != 0) {
+ perror("madvise pageout for mem2");
+ free(mem1);
+ free(mem2);
+ return EXIT_FAILURE;
+ }
+ }
+
+ final_swpout = read_stat(SWPOUT_PATH);
+ final_swpout_fallback = read_stat(SWPOUT_FALLBACK_PATH);
+
+ swpout_inc = final_swpout - initial_swpout;
+ swpout_fallback_inc = final_swpout_fallback - initial_swpout_fallback;
+
+ fallback_percentage = (double)swpout_fallback_inc /
+ (swpout_fallback_inc + swpout_inc) * 100;
+
+ printf("Iteration %d: swpout inc: %lu, swpout fallback inc: %lu, Fallback percentage: %.2f%%\n",
+ i + 1, swpout_inc, swpout_fallback_inc, fallback_percentage);
+ }
+
+ free(mem1);
+ if (mem2 != NULL)
+ free(mem2);
+
+ return EXIT_SUCCESS;
+}
_
Patches currently in -mm which might be from v-songbaohua@xxxxxxxx are
cifs-drop-the-incorrect-assertion-in-cifs_swap_rw.patch
mm-remove-the-implementation-of-swap_free-and-always-use-swap_free_nr.patch
mm-introduce-pte_move_swp_offset-helper-which-can-move-offset-bidirectionally.patch
mm-introduce-arch_do_swap_page_nr-which-allows-restore-metadata-for-nr-pages.patch
mm-swap-reuse-exclusive-folio-directly-instead-of-wp-page-faults.patch
mm-introduce-pmdpte_needs_soft_dirty_wp-helpers-for-softdirty-write-protect.patch
mm-set-pte-writable-while-pte_soft_dirty-is-true-in-do_swap_page.patch
mm-extend-rmap-flags-arguments-for-folio_add_new_anon_rmap.patch
mm-extend-rmap-flags-arguments-for-folio_add_new_anon_rmap-fix-2.patch
mm-use-folio_add_new_anon_rmap-if-folio_test_anonfolio==false.patch
mm-remove-folio_test_anonfolio==false-path-in-__folio_add_anon_rmap.patch
selftests-mm-introduce-a-test-program-to-assess-swap-entry-allocation-for-thp_swapout.patch
