lkml.org 
[lkml]   [2019]   [Jul]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH] mm: vmscan: scan anonymous pages on file refaults
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)\n", 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\n");
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\n", anon_mb);
ret1 = alloc_anon(anon_mb * MB);
printf("Access %ld MB file pages\n", file_mb);
ret2 = access_file(filename, file_mb * MB, file_rounds);
printf("Print result to prevent optimization: %ld\n",
*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)

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@chromium.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org> # 4.12+
---
mm/vmscan.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7889f583ced9f..da0b97204372e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2125,7 +2125,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
* 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);
@@ -2151,7 +2151,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
* rid of the stale workingset quickly.
*/
refaults = lruvec_page_state_local(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);
@@ -2161,7 +2161,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
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,
--
2.22.0.410.gd8fdbe21b5-goog
\
 
 \ /
  Last update: 2019-07-01 10:11    [W:0.130 / U:49.540 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site