mirror of
https://github.com/brain-hackers/linux-brain.git
synced 2024-06-09 23:36:23 +09:00
2c012a4ad1
When file refaults are detected and there are many inactive file pages,
the system never reclaim anonymous pages, the file pages are dropped
aggressively when there are still a lot of cold anonymous pages and
system thrashes. This issue impacts the performance of applications
with large executable, e.g. chrome.
With this patch, when file refault is detected, inactive_list_is_low()
always returns true for file pages in get_scan_count() to enable
scanning anonymous pages.
The problem can be reproduced by the following test program.
---8<---
void fallocate_file(const char *filename, off_t size)
{
struct stat st;
int fd;
if (!stat(filename, &st) && st.st_size >= size)
return;
fd = open(filename, O_WRONLY | O_CREAT, 0600);
if (fd < 0) {
perror("create file");
exit(1);
}
if (posix_fallocate(fd, 0, size)) {
perror("fallocate");
exit(1);
}
close(fd);
}
long *alloc_anon(long size)
{
long *start = malloc(size);
memset(start, 1, size);
return start;
}
long access_file(const char *filename, long size, long rounds)
{
int fd, i;
volatile char *start1, *end1, *start2;
const int page_size = getpagesize();
long sum = 0;
fd = open(filename, O_RDONLY);
if (fd == -1) {
perror("open");
exit(1);
}
/*
* Some applications, e.g. chrome, use a lot of executable file
* pages, map some of the pages with PROT_EXEC flag to simulate
* the behavior.
*/
start1 = mmap(NULL, size / 2, PROT_READ | PROT_EXEC, MAP_SHARED,
fd, 0);
if (start1 == MAP_FAILED) {
perror("mmap");
exit(1);
}
end1 = start1 + size / 2;
start2 = mmap(NULL, size / 2, PROT_READ, MAP_SHARED, fd, size / 2);
if (start2 == MAP_FAILED) {
perror("mmap");
exit(1);
}
for (i = 0; i < rounds; ++i) {
struct timeval before, after;
volatile char *ptr1 = start1, *ptr2 = start2;
gettimeofday(&before, NULL);
for (; ptr1 < end1; ptr1 += page_size, ptr2 += page_size)
sum += *ptr1 + *ptr2;
gettimeofday(&after, NULL);
printf("File access time, round %d: %f (sec)
", i,
(after.tv_sec - before.tv_sec) +
(after.tv_usec - before.tv_usec) / 1000000.0);
}
return sum;
}
int main(int argc, char *argv[])
{
const long MB = 1024 * 1024;
long anon_mb, file_mb, file_rounds;
const char filename[] = "large";
long *ret1;
long ret2;
if (argc != 4) {
printf("usage: thrash ANON_MB FILE_MB FILE_ROUNDS
");
exit(0);
}
anon_mb = atoi(argv[1]);
file_mb = atoi(argv[2]);
file_rounds = atoi(argv[3]);
fallocate_file(filename, file_mb * MB);
printf("Allocate %ld MB anonymous pages
", anon_mb);
ret1 = alloc_anon(anon_mb * MB);
printf("Access %ld MB file pages
", file_mb);
ret2 = access_file(filename, file_mb * MB, file_rounds);
printf("Print result to prevent optimization: %ld
",
*ret1 + ret2);
return 0;
}
---8<---
Running the test program on 2GB RAM VM with kernel 5.2.0-rc5, the program
fills ram with 2048 MB memory, access a 200 MB file for 10 times. Without
this patch, the file cache is dropped aggresively and every access to the
file is from disk.
$ ./thrash 2048 200 10
Allocate 2048 MB anonymous pages
Access 200 MB file pages
File access time, round 0: 2.489316 (sec)
File access time, round 1: 2.581277 (sec)
File access time, round 2: 2.487624 (sec)
File access time, round 3: 2.449100 (sec)
File access time, round 4: 2.420423 (sec)
File access time, round 5: 2.343411 (sec)
File access time, round 6: 2.454833 (sec)
File access time, round 7: 2.483398 (sec)
File access time, round 8: 2.572701 (sec)
File access time, round 9: 2.493014 (sec)
With this patch, these file pages can be cached.
$ ./thrash 2048 200 10
Allocate 2048 MB anonymous pages
Access 200 MB file pages
File access time, round 0: 2.475189 (sec)
File access time, round 1: 2.440777 (sec)
File access time, round 2: 2.411671 (sec)
File access time, round 3: 1.955267 (sec)
File access time, round 4: 0.029924 (sec)
File access time, round 5: 0.000808 (sec)
File access time, round 6: 0.000771 (sec)
File access time, round 7: 0.000746 (sec)
File access time, round 8: 0.000738 (sec)
File access time, round 9: 0.000747 (sec)
Checked the swap out stats during the test [1], 19006 pages swapped out
with this patch, 3418 pages swapped out without this patch. There are
more swap out, but I think it's within reasonable range when file backed
data set doesn't fit into the memory.
$ ./thrash 2000 100 2100 5 1 # ANON_MB FILE_EXEC FILE_NOEXEC ROUNDS
PROCESSES Allocate 2000 MB anonymous pages active_anon: 1613644,
inactive_anon: 348656, active_file: 892, inactive_file: 1384 (kB)
pswpout: 7972443, pgpgin: 478615246 Access 100 MB executable file pages
Access 2100 MB regular file pages File access time, round 0: 12.165,
(sec) active_anon: 1433788, inactive_anon: 478116, active_file: 17896,
inactive_file: 24328 (kB) File access time, round 1: 11.493, (sec)
active_anon: 1430576, inactive_anon: 477144, active_file: 25440,
inactive_file: 26172 (kB) File access time, round 2: 11.455, (sec)
active_anon: 1427436, inactive_anon: 476060, active_file: 21112,
inactive_file: 28808 (kB) File access time, round 3: 11.454, (sec)
active_anon: 1420444, inactive_anon: 473632, active_file: 23216,
inactive_file: 35036 (kB) File access time, round 4: 11.479, (sec)
active_anon: 1413964, inactive_anon: 471460, active_file: 31728,
inactive_file: 32224 (kB) pswpout: 7991449 (+ 19006), pgpgin: 489924366
(+ 11309120)
With 4 processes accessing non-overlapping parts of a large file, 30316
pages swapped out with this patch, 5152 pages swapped out without this
patch. The swapout number is small comparing to pgpgin.
[1]: https://github.com/vovo/testing/blob/master/mem_thrash.c
Link: http://lkml.kernel.org/r/20190701081038.GA83398@google.com
Fixes:
|
||
|---|---|---|
| .. | ||
| kasan | ||
| backing-dev.c | ||
| balloon_compaction.c | ||
| cleancache.c | ||
| cma_debug.c | ||
| cma.c | ||
| cma.h | ||
| compaction.c | ||
| debug_page_ref.c | ||
| debug.c | ||
| dmapool.c | ||
| early_ioremap.c | ||
| fadvise.c | ||
| failslab.c | ||
| filemap.c | ||
| frame_vector.c | ||
| frontswap.c | ||
| gup_benchmark.c | ||
| gup.c | ||
| highmem.c | ||
| hmm.c | ||
| huge_memory.c | ||
| hugetlb_cgroup.c | ||
| hugetlb.c | ||
| hwpoison-inject.c | ||
| init-mm.c | ||
| internal.h | ||
| interval_tree.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| khugepaged.c | ||
| kmemleak-test.c | ||
| kmemleak.c | ||
| ksm.c | ||
| list_lru.c | ||
| maccess.c | ||
| madvise.c | ||
| Makefile | ||
| memblock.c | ||
| memcontrol.c | ||
| memfd.c | ||
| memory_hotplug.c | ||
| memory-failure.c | ||
| memory.c | ||
| mempolicy.c | ||
| mempool.c | ||
| memtest.c | ||
| migrate.c | ||
| mincore.c | ||
| mlock.c | ||
| mm_init.c | ||
| mmap.c | ||
| mmu_context.c | ||
| mmu_gather.c | ||
| mmu_notifier.c | ||
| mmzone.c | ||
| mprotect.c | ||
| mremap.c | ||
| msync.c | ||
| nommu.c | ||
| oom_kill.c | ||
| page_alloc.c | ||
| page_counter.c | ||
| page_ext.c | ||
| page_idle.c | ||
| page_io.c | ||
| page_isolation.c | ||
| page_owner.c | ||
| page_poison.c | ||
| page_vma_mapped.c | ||
| page-writeback.c | ||
| pagewalk.c | ||
| percpu-internal.h | ||
| percpu-km.c | ||
| percpu-stats.c | ||
| percpu-vm.c | ||
| percpu.c | ||
| pgtable-generic.c | ||
| process_vm_access.c | ||
| quicklist.c | ||
| readahead.c | ||
| rmap.c | ||
| rodata_test.c | ||
| shmem.c | ||
| shuffle.c | ||
| shuffle.h | ||
| slab_common.c | ||
| slab.c | ||
| slab.h | ||
| slob.c | ||
| slub.c | ||
| sparse-vmemmap.c | ||
| sparse.c | ||
| swap_cgroup.c | ||
| swap_slots.c | ||
| swap_state.c | ||
| swap.c | ||
| swapfile.c | ||
| truncate.c | ||
| usercopy.c | ||
| userfaultfd.c | ||
| util.c | ||
| vmacache.c | ||
| vmalloc.c | ||
| vmpressure.c | ||
| vmscan.c | ||
| vmstat.c | ||
| workingset.c | ||
| z3fold.c | ||
| zbud.c | ||
| zpool.c | ||
| zsmalloc.c | ||
| zswap.c | ||