On 04/14/2014 06:37 PM, Kirill A. Shutemov wrote:
gux.fnst wrote:
Hi Kirill,
Hi Xing,
Please always CC to mailing list for upstream-related questions.
I've added linux-mm@ to CC.
OK, got it.
VM_FAULT_FALLBACK is
fallback required.
---------------------------------------------------------------------------------------------------------------------------
It is a little difficult to reproduce this problem fixed by this patch
for me. Could you give me some
hint about how to do this - “allocate a huge page to replace zero page
but hit the memcg limit"?
I used this script:
#!/bin/sh -efu
set -efux
mount -t cgroup none /sys/fs/cgroup
mkdir /sys/fs/cgroup/test
echo "10M" > /sys/fs/cgroup/test/memory.limit_in_bytes
echo "10M" > /sys/fs/cgroup/test/memory.memsw.limit_in_bytes
echo $$ > /sys/fs/cgroup/test/tasks
/host/home/kas/var/mmaptest_zero
echo ok
Where /host/home/kas/var/mmaptest_zero is:
#include <assert.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/mman.h>
#define MB (1024 * 1024)
#define SIZE (256 * MB)
int main(int argc, char **argv)
{
int i;
char *p;
posix_memalign((void **)&p, 2 * MB, SIZE);
printf("p: %p\n", p);
fork();
for (i = 0; i < SIZE; i += 4096)
assert(p[i] == 0);
for (i = 0; i < SIZE; i += 4096)
p[i] = 1;
pause();
return 0;
}
Without the patch it hangs, but should trigger OOM.
Thank you very much.
Regards,
Xing Gu
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href