Skip to contentSkip to conversation

madvise06: shrink to 1 MADV_WILLNEED page to stabilize the test

RFC PATCH Superseded Li Wang 2 participants 5 messages Jun 15, 2022 – Jun 20, 2022

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Li Wang

author
#0 lore raw

RFC PATCH 1/1 madvise06: shrink to 1 MADV_WILLNEED page to stabilize the test

Paul Bunyan reports that the madvise06 test fails intermittently with many LTS kernels, after checking with mm developer we prefer to think this is more like a test issue (but not kernel bug):

madvise06.c:231: TFAIL: 4 pages were faulted out of 2 max

So this improvement is target to reduce the false positive happens from three points:

1. Adding the while-loop to give more chances for madvise_willneed() reads memory asynchronously
2. Raise value of loop to let test waiting for more times if swapchache haven't reached the expected
3. Shrink to only 1 page for MADV_WILLNEED verifying to make the system easily takes effect on it

From Rafael Aquini:

The problem here is that MADV_WILLNEED is an asynchronous non-blocking hint, which will tell the kernel to start doing read-ahead work for the hinted memory chunk, but will not wait up for the read-ahead to finish. So, it is possible that when the dirty_pages() call start re-dirtying the pages in that target area, is racing against a scheduled swap-in read-ahead that hasn't yet finished. Expecting faulting only 2 pages out of 102400 also seems too strict for a PASS threshold.

Note:
As Rafael suggested, another possible approach to tackle this failure is to tally up, and loosen the threshold to more than 2 major faults after a call to madvise() with MADV_WILLNEED.
But from my test, seems the faulted-out page shows a significant variance in different platforms, so I didn't take this way.

Btw, this patch get passed on my two easy reproducible systems more than 1000 times

Cc Rafael Aquini <[email protected]>
Cc Paul Bunyan <[email protected]>
Cc Richard Palethorpe <[email protected]>
---
 testcases/kernel/syscalls/madvise/madvise06.c | 21 +++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)
testcases/kernel/syscalls/madvise/madvise06.c +15 -6
index 6d218801c..bfca894f4 100644
@@ -164,7 +164,7 @@ static int get_page_fault_num(void)
 
 static void test_advice_willneed(void)
 {
-	int loops = 50, res;
+	int loops = 100, res;
 	char *target;
 	long swapcached_start, swapcached;
 	int page_fault_num_1, page_fault_num_2;
@@ -202,23 +202,32 @@ static void test_advice_willneed(void)
 		"%s than %ld Kb were moved to the swap cache",
 		res ? "more" : "less", PASS_THRESHOLD_KB);
 
-
-	TEST(madvise(target, PASS_THRESHOLD, MADV_WILLNEED));
+	loops = 100;
+	SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld", &swapcached_start);
+	TEST(madvise(target, pg_sz, MADV_WILLNEED));
 	if (TST_RET == -1)
 		tst_brk(TBROK | TTERRNO, "madvise failed");
+	do {
+		loops--;
+		usleep(100000);
+		if (stat_refresh_sup)
+			SAFE_FILE_PRINTF("/proc/sys/vm/stat_refresh", "1");
+		SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld",
+				&swapcached);
+	} while (swapcached < swapcached_start + pg_sz/1024 && loops > 0);
 
 	page_fault_num_1 = get_page_fault_num();
 	tst_res(TINFO, "PageFault(madvice / no mem access): %d",
 			page_fault_num_1);
-	dirty_pages(target, PASS_THRESHOLD);
+	dirty_pages(target, pg_sz);
 	page_fault_num_2 = get_page_fault_num();
 	tst_res(TINFO, "PageFault(madvice / mem access): %d",
 			page_fault_num_2);
 	meminfo_diag("After page access");
 
 	res = page_fault_num_2 - page_fault_num_1;
-	tst_res(res < 3 ? TPASS : TFAIL,
-		"%d pages were faulted out of 2 max", res);
+	tst_res(res == 0 ? TPASS : TFAIL,
+		"%d pages were faulted out of 1 max", res);
 
 	SAFE_MUNMAP(target, CHUNK_SZ);
 }
Signature · 5 lines
2.35.3


-- 
Mailing list info: https://lists.linux.it/listinfo/ltp
#1 lore raw

Hello Li,

Quoted 71 lines · Li Wang

Paul Bunyan reports that the madvise06 test fails intermittently with many LTS kernels, after checking with mm developer we prefer to think this is more like a test issue (but not kernel bug):

madvise06.c:231: TFAIL: 4 pages were faulted out of 2 max

So this improvement is target to reduce the false positive happens from three points:

1. Adding the while-loop to give more chances for madvise_willneed() reads memory asynchronously
2. Raise value of loop to let test waiting for more times if swapchache haven't reached the expected
3. Shrink to only 1 page for MADV_WILLNEED verifying to make the system easily takes effect on it

From Rafael Aquini:

The problem here is that MADV_WILLNEED is an asynchronous non-blocking hint, which will tell the kernel to start doing read-ahead work for the hinted memory chunk, but will not wait up for the read-ahead to finish. So, it is possible that when the dirty_pages() call start re-dirtying the pages in that target area, is racing against a scheduled swap-in read-ahead that hasn't yet finished. Expecting faulting only 2 pages out of 102400 also seems too strict for a PASS threshold.

Note:
As Rafael suggested, another possible approach to tackle this failure is to tally up, and loosen the threshold to more than 2 major faults after a call to madvise() with MADV_WILLNEED.
But from my test, seems the faulted-out page shows a significant variance in different platforms, so I didn't take this way.

Btw, this patch get passed on my two easy reproducible systems more than 1000 times

Cc Rafael Aquini <[email protected]>
Cc Paul Bunyan <[email protected]>
Cc Richard Palethorpe <[email protected]>
---
 testcases/kernel/syscalls/madvise/madvise06.c | 21 +++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)
testcases/kernel/syscalls/madvise/madvise06.c +8 -3
index 6d218801c..bfca894f4 100644
@@ -164,7 +164,7 @@ static int get_page_fault_num(void)
 
 static void test_advice_willneed(void)
 {
-	int loops = 50, res;
+	int loops = 100, res;
 	char *target;
 	long swapcached_start, swapcached;
 	int page_fault_num_1, page_fault_num_2;
@@ -202,23 +202,32 @@ static void test_advice_willneed(void)
 		"%s than %ld Kb were moved to the swap cache",
 		res ? "more" : "less", PASS_THRESHOLD_KB);
 
-
-	TEST(madvise(target, PASS_THRESHOLD, MADV_WILLNEED));
+	loops = 100;
+	SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld", &swapcached_start);
+	TEST(madvise(target, pg_sz, MADV_WILLNEED));
 	if (TST_RET == -1)
 		tst_brk(TBROK | TTERRNO, "madvise failed");
+	do {
+		loops--;
+		usleep(100000);
+		if (stat_refresh_sup)

testcases/kernel/syscalls/madvise/madvise06.c static void test_advice_willneed(void) · line 222

Quoted 10 lines
testcases/kernel/syscalls/madvise/madvise06.c +5 -1
+			SAFE_FILE_PRINTF("/proc/sys/vm/stat_refresh", "1");
+		SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld",
+				&swapcached);
+	} while (swapcached < swapcached_start + pg_sz/1024 && loops > 0);
 
 	page_fault_num_1 = get_page_fault_num();
 	tst_res(TINFO, "PageFault(madvice / no mem access): %d",
 			page_fault_num_1);
-	dirty_pages(target, PASS_THRESHOLD);
+	dirty_pages(target, pg_sz);

Adding the loop makes sense to me. However I don't understand why you have also switched from PASS_THRESHOLD to only a single page?

I guess calling MADV_WILLNEED on a single page is the least realistic scenario.

If there is an issue with PASS_THRESHOLD perhaps we could scale it based on page size?

Quoted 13 lines
testcases/kernel/syscalls/madvise/madvise06.c +2 -2
 	page_fault_num_2 = get_page_fault_num();
 	tst_res(TINFO, "PageFault(madvice / mem access): %d",
 			page_fault_num_2);
 	meminfo_diag("After page access");
 
 	res = page_fault_num_2 - page_fault_num_1;
-	tst_res(res < 3 ? TPASS : TFAIL,
-		"%d pages were faulted out of 2 max", res);
+	tst_res(res == 0 ? TPASS : TFAIL,
+		"%d pages were faulted out of 1 max", res);
 
 	SAFE_MUNMAP(target, CHUNK_SZ);
 }
Signature · 5 lines
Thank you,
Richard.

-- 
Mailing list info: https://lists.linux.it/listinfo/ltp
author
#2 lore raw

Hi Richard,

Quoted 32 lines · Richard Palethorpe
Quoted 12 lines
testcases/kernel/syscalls/madvise/madvise06.c +1 -1
@@ -164,7 +164,7 @@ static int get_page_fault_num(void)
 
 static void test_advice_willneed(void)
 {
-     int loops = 50, res;
+     int loops = 100, res;
      char *target;
      long swapcached_start, swapcached;
      int page_fault_num_1, page_fault_num_2;

testcases/kernel/syscalls/madvise/madvise06.c static void test_advice_willneed(void) · line 206

Quoted 7 lines
testcases/kernel/syscalls/madvise/madvise06.c +2 -2
@@ -202,23 +202,32 @@ static void test_advice_willneed(void)
              "%s than %ld Kb were moved to the swap cache",
              res ? "more" : "less", PASS_THRESHOLD_KB);
 
-
-     TEST(madvise(target, PASS_THRESHOLD, MADV_WILLNEED));
+     loops = 100;
+     SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld",

&swapcached_start);

Quoted 12 lines
testcases/kernel/syscalls/madvise/madvise06.c +9 -0
+     TEST(madvise(target, pg_sz, MADV_WILLNEED));
      if (TST_RET == -1)
              tst_brk(TBROK | TTERRNO, "madvise failed");
+     do {
+             loops--;
+             usleep(100000);
+             if (stat_refresh_sup)
+                     SAFE_FILE_PRINTF("/proc/sys/vm/stat_refresh", "1");
+             SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld",
+                             &swapcached);
+     } while (swapcached < swapcached_start + pg_sz/1024 && loops > 0);
 
Quoted 9 lines

testcases/kernel/syscalls/madvise/madvise06.c static void test_advice_willneed(void) · line 222

Quoted 5 lines
testcases/kernel/syscalls/madvise/madvise06.c +1 -1
      page_fault_num_1 = get_page_fault_num();
      tst_res(TINFO, "PageFault(madvice / no mem access): %d",
                      page_fault_num_1);
-     dirty_pages(target, PASS_THRESHOLD);
+     dirty_pages(target, pg_sz);

Adding the loop makes sense to me. However I don't understand why you have also switched from PASS_THRESHOLD to only a single page?

In the test, we use two checks combined to confirm the bug reproduces:

1. swap cached increasing less than PASS_THRESHOLD_KB
2. page_fault number large than expected

The 2. case is more easily get failed on kind of platforms and hard to count an average value for tolerating. So maybe we just reduce the page to one that would not affect the final result. Because we rely on both checks happening simultaneously then assume a bug.

Quoted 4 lines

I guess calling MADV_WILLNEED on a single page is the least realistic scenario.

Okay, perhaps it's a step backward:).

I was just thinking it is a regression test and if 1 page works to reproduce that (but more chunks of memory easily cause false positive), why not.

Quoted 4 lines

If there is an issue with PASS_THRESHOLD perhaps we could scale it based on page size?

This sounds acceptable too.

How many pages do you think are proper, 100 or more? and, loosen the faulted-out numbers to 1/10 pages?

Signature · 2 lines
Regards,
Li Wang
Signature · 2 lines
-- 
Mailing list info: https://lists.linux.it/listinfo/ltp
#3 lore raw

Hello Li,

Quoted 56 lines · Li Wang

Hi Richard,

Quoted 26 lines · Richard Palethorpe
testcases/kernel/syscalls/madvise/madvise06.c +8 -3
@@ -164,7 +164,7 @@ static int get_page_fault_num(void)
 
 static void test_advice_willneed(void)
 {
-     int loops = 50, res;
+     int loops = 100, res;
      char *target;
      long swapcached_start, swapcached;
      int page_fault_num_1, page_fault_num_2;
@@ -202,23 +202,32 @@ static void test_advice_willneed(void)
              "%s than %ld Kb were moved to the swap cache",
              res ? "more" : "less", PASS_THRESHOLD_KB);
 
-
-     TEST(madvise(target, PASS_THRESHOLD, MADV_WILLNEED));
+     loops = 100;
+     SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld", &swapcached_start);
+     TEST(madvise(target, pg_sz, MADV_WILLNEED));
      if (TST_RET == -1)
              tst_brk(TBROK | TTERRNO, "madvise failed");
+     do {
+             loops--;
+             usleep(100000);
+             if (stat_refresh_sup)

testcases/kernel/syscalls/madvise/madvise06.c static void test_advice_willneed(void) · line 222

Quoted 10 lines
testcases/kernel/syscalls/madvise/madvise06.c +5 -1
+                     SAFE_FILE_PRINTF("/proc/sys/vm/stat_refresh", "1");
+             SAFE_FILE_LINES_SCANF("/proc/meminfo", "SwapCached: %ld",
+                             &swapcached);
+     } while (swapcached < swapcached_start + pg_sz/1024 && loops > 0);
 
      page_fault_num_1 = get_page_fault_num();
      tst_res(TINFO, "PageFault(madvice / no mem access): %d",
                      page_fault_num_1);
-     dirty_pages(target, PASS_THRESHOLD);
+     dirty_pages(target, pg_sz);

Adding the loop makes sense to me. However I don't understand why you have also switched from PASS_THRESHOLD to only a single page?

In the test, we use two checks combined to confirm the bug reproduces:

1. swap cached increasing less than PASS_THRESHOLD_KB
2. page_fault number large than expected

The 2. case is more easily get failed on kind of platforms and hard to count an average value for tolerating. So maybe we just reduce the page to one that would not affect the final result. Because we rely on both checks happening simultaneously then assume a bug.

Quoted 7 lines

I guess calling MADV_WILLNEED on a single page is the least realistic scenario.

Okay, perhaps it's a step backward:).

I was just thinking it is a regression test and if 1 page works to reproduce that (but more chunks of memory easily cause false positive), why not.

That makes sense, but this test has also found other bugs. I'm not sure if they are reproducible with only one page.

Quoted 10 lines

If there is an issue with PASS_THRESHOLD perhaps we could scale it based on page size?

This sounds acceptable too.

How many pages do you think are proper, 100 or more? and, loosen the faulted-out numbers to 1/10 pages?

I suppose that 100 pages would be too much memory on some systems. I guess at least 2 or 3 pages are needed so there is some traversal. Beyond that I don't know what would make a difference.

If there are only max 3 pages and we have a loop, I would not expect any to be faulted. Although maybe we could allow 1/3 because MADV_WILLNEED is only an advisory and a lot of time has been spent discussing this test already.

Signature · 5 lines
Thank you,
Richard.

-- 
Mailing list info: https://lists.linux.it/listinfo/ltp
author
#4 lore raw

Hi Richard,

Quoted 18 lines · Richard Palethorpe
Quoted 18 lines

Adding the loop makes sense to me. However I don't understand why you have also switched from PASS_THRESHOLD to only a single page?

In the test, we use two checks combined to confirm the bug reproduces:

1. swap cached increasing less than PASS_THRESHOLD_KB
2. page_fault number large than expected

The 2. case is more easily get failed on kind of platforms and hard to count an average value for tolerating. So maybe we just reduce the page to one that would not affect the final result. Because we rely on both checks happening simultaneously then assume a bug.

I guess calling MADV_WILLNEED on a single page is the least realistic scenario.

Quoted 9 lines
Quoted 3 lines

Okay, perhaps it's a step backward:).

I was just thinking it is a regression test and if 1 page works to

reproduce

Quoted 1 line

that (but more chunks of memory easily cause false positive), why not.

That makes sense, but this test has also found other bugs. I'm not sure if they are reproducible with only one page.

Indeed.

Quoted 12 lines
Quoted 11 lines

If there is an issue with PASS_THRESHOLD perhaps we could scale it based on page size?

This sounds acceptable too.

How many pages do you think are proper, 100 or more? and, loosen the faulted-out numbers to 1/10 pages?

Quoted 9 lines

I suppose that 100 pages would be too much memory on some systems. I guess at least 2 or 3 pages are needed so there is some traversal. Beyond that I don't know what would make a difference.

If there are only max 3 pages and we have a loop, I would not expect any to be faulted. Although maybe we could allow 1/3 because MADV_WILLNEED is only an advisory and a lot of time has been spent discussing this test already.

It sounds reasonable. Thanks!

I would have a try and go touch 3 pages (with expect 0 page fault) if that does work.

Signature · 2 lines
Regards,
Li Wang
Signature · 2 lines
-- 
Mailing list info: https://lists.linux.it/listinfo/ltp