The following testcase brought down 2.4.17 mainline on an
8-way P-III 700MHz machine with 12GB of RAM. The last thing
logged from it was a LowFree of 2MB with 9GB of highmem free
after something like 6-8 hours of pounding away, at which
time the machine stopped responding (IIRC it was given ~12
hours to echo another character).
This testcase is a blatant attempt to fill the direct-mapped
portion of the kernel virtual address space with process pagetables.
It was suspected such a thing was happening in another failure scenario
which is what motivated me to devise this testcase. I believe a fix
already exists (i.e. aa's ptes in highmem stuff) though I've not yet
verified its correct operation here.
The driver script was this:
#!/bin/sh
for n in `seq 0 1023`
do
./death &
done
and the C program was the following:
#define __USE_LARGEFILE64
#include <stdio.h>
#include <unistd.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#define __USE_LARGEFILE64
#include <fcntl.h>
#include <errno.h>
#define MAPPING_START 0x20000000
#define MAPPING_SIZE (0x80000000/sizeof(unsigned long))
#define MAPPING_END (MAPPING_START + MAPPING_SIZE*sizeof(unsigned long))
int main(void)
{
int fd;
unsigned long *data = NULL;
unsigned long try = 64;
unsigned long k = 0;
fd = open("/home/wli/bench/mapfile", O_RDWR|O_LARGEFILE);
if (fd < 0) {
perror("death");
printf("could not open mapfile!\n");
exit(1);
}
data = mmap((void *)MAPPING_START,
MAPPING_SIZE,
PROT_READ|PROT_WRITE,
MAP_FIXED | MAP_SHARED,
fd,
0);
if (!try || data == MAP_FAILED) {
printf("mmap() failed, tries = %lu!\n", 64 - try + 1);
exit(1);
}
printf("managed to mmap() at %p\n", (void *)data);
sleep(60);
try = 0;
while (1) {
printf("entered iteration %lu\n", k);
data[k++] = try++;
k %= MAPPING_SIZE;
if (k >= MAPPING_SIZE-1)
k = 0;
}
return 0;
}
Cheers,
Bill
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Fri Feb 15 2002 - 21:01:05 EST