@@ -9,6 +9,8 @@
#include <string.h>
#include <sys/wait.h>
#include <sys/mman.h>
+#include <sys/time.h>
+#include <malloc.h>
#include "../kselftest.h"
#include "cgroup_util.h"
@@ -407,6 +409,74 @@ static int test_zswap_writeback_disabled(const char *root)
return test_zswap_writeback(root, false);
}
+static int zswapin_perf(const char *cgroup, void *arg)
+{
+ long pagesize = sysconf(_SC_PAGESIZE);
+ size_t memsize = MB(1*1024);
+ char buf[pagesize];
+ int ret = -1;
+ char *mem;
+ struct timeval start, end;
+
+ mem = (char *)memalign(2*1024*1024, memsize);
+ if (!mem)
+ return ret;
+
+ /*
+ * Fill half of each page with increasing data, and keep other
+ * half empty, this will result in data that is still compressible
+ * and ends up in zswap, with material zswap usage.
+ */
+ for (int i = 0; i < pagesize; i++)
+ buf[i] = i < pagesize/2 ? (char) i : 0;
+
+ for (int i = 0; i < memsize; i += pagesize)
+ memcpy(&mem[i], buf, pagesize);
+
+ /* Try and reclaim allocated memory */
+ if (cg_write_numeric(cgroup, "memory.reclaim", memsize)) {
+ ksft_print_msg("Failed to reclaim all of the requested memory\n");
+ goto out;
+ }
+
+ gettimeofday(&start, NULL);
+ /* zswpin */
+ for (int i = 0; i < memsize; i += pagesize) {
+ if (memcmp(&mem[i], buf, pagesize)) {
+ ksft_print_msg("invalid memory\n");
+ goto out;
+ }
+ }
+ gettimeofday(&end, NULL);
+ printf ("zswapin took %fms to run.\n", (end.tv_sec - start.tv_sec)*1000 + (double)(end.tv_usec - start.tv_usec) / 1000);
+ ret = 0;
+out:
+ free(mem);
+ return ret;
+}
+
+static int test_zswapin_perf(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *test_group;
+
+ test_group = cg_name(root, "zswapin_perf_test");
+ if (!test_group)
+ goto out;
+ if (cg_create(test_group))
+ goto out;
+
+ if (cg_run(test_group, zswapin_perf, NULL))
+ goto out;
+
+ ret = KSFT_PASS;
+out:
+ cg_destroy(test_group);
+ free(test_group);
+ return ret;
+}
+
/*
* 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
@@ -584,6 +654,7 @@ struct zswap_test {
After large folio zswapout support added in [1], this patch adds support for zswapin of large folios to bring it on par with zram. This series makes sure that the benefits of large folios (fewer page faults, batched PTE and rmap manipulation, reduced lru list, TLB coalescing (for arm64 and amd)) are not lost at swap out when using zswap. It builds on top of [2] which added large folio swapin support for zram and provides the same level of large folio swapin support as zram, i.e. only supporting swap count == 1. Patch 1 skips swapcache for swapping in zswap pages, this should improve no readahead swapin performance [3], and also allows us to build on large folio swapin support added in [2], hence is a prerequisite for patch 3. Patch 3 adds support for large folio zswapin. This patch does not add support for hybrid backends (i.e. folios partly present swap and zswap). The main performance benefit comes from maintaining large folios *after* swapin, large folio performance improvements have been mentioned in previous series posted on it [2],[4], so have not added those. Below is a simple microbenchmark to measure the time needed *for* zswpin of 1G memory (along with memory integrity check). | no mTHP (ms) | 1M mTHP enabled (ms) Base kernel | 1165 | 1163 Kernel with mTHP zswpin series | 1203 | 738 The time measured was pretty consistent between runs (~1-2% variation). There is 36% improvement in zswapin time with 1M folios. The percentage improvement is likely to be more if the memcmp is removed. T(test_zswapin), T(test_zswap_writeback_enabled), T(test_zswap_writeback_disabled), + T(test_zswapin_perf), T(test_no_kmem_bypass), T(test_no_invasive_cgroup_shrink), }; [1] https://lore.kernel.org/all/20241001053222.6944-1-kanchana.p.sridhar@intel.com/ [2] https://lore.kernel.org/all/20240821074541.516249-1-hanchuanhua@oppo.com/ [3] https://lore.kernel.org/all/1505886205-9671-5-git-send-email-minchan@kernel.org/T/#u [4] https://lwn.net/Articles/955575/ Usama Arif (4): mm/zswap: skip swapcache for swapping in zswap pages mm/zswap: modify zswap_decompress to accept page instead of folio mm/zswap: add support for large folio zswapin mm/zswap: count successful large folio zswap loads Documentation/admin-guide/mm/transhuge.rst | 3 + include/linux/huge_mm.h | 1 + include/linux/zswap.h | 6 ++ mm/huge_memory.c | 3 + mm/memory.c | 16 +-- mm/page_io.c | 2 +- mm/zswap.c | 120 ++++++++++++++------- 7 files changed, 99 insertions(+), 52 deletions(-)