From: Kuo-Hsin Yang <vovoy@xxxxxxxxxxxx>
commit 2c012a4ad1a2cd3fb5a0f9307b9d219f84eda1fa upstream.
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@xxxxxxxxxx
Fixes: e9868505987a ("mm,vmscan: only evict file pages when we have plenty")
Fixes: 7c5bd705d8f9 ("mm: memcg: only evict file pages when we have plenty")
Signed-off-by: Kuo-Hsin Yang <vovoy@xxxxxxxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Sonny Rao <sonnyrao@xxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [4.12+]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[backported to 4.14.y, 4.19.y, 5.1.y: adjust context]
Signed-off-by: Kuo-Hsin Yang <vovoy@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
mm/vmscan.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2190,7 +2190,7 @@ static void shrink_active_list(unsigned
* 10TB 320 32GB
*/
static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
- struct scan_control *sc, bool actual_reclaim)
+ struct scan_control *sc, bool trace)
{
enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -2216,7 +2216,7 @@ static bool inactive_list_is_low(struct
* rid of the stale workingset quickly.
*/
refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
- if (file && actual_reclaim && lruvec->refaults != refaults) {
+ if (file && lruvec->refaults != refaults) {
inactive_ratio = 0;
} else {
gb = (inactive + active) >> (30 - PAGE_SHIFT);
@@ -2226,7 +2226,7 @@ static bool inactive_list_is_low(struct
inactive_ratio = 1;
}
- if (actual_reclaim)
+ if (trace)
trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx,
lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
