lkml.org 
[lkml]   [2009]   [Dec]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [RFC][mmotm][PATCH] percpu mm struct counter cache
This is a test program for measuring page fault cost, I used.
This program creates threads on cpu 0,4,8,....(because I use 4code cpu)
and cause page faults on each cpu in parallel.
If you run too many threads, spin_lock costs will dominates all...
I used just 2 threads in measurements, cpu 0 and 4.

==
/*
* multi-fault.c :: causes 60secs of parallel page fault in multi-thread.
* % gcc -O2 -o multi-fault multi-fault.c -lpthread
* % multi-fault # of cpus.
*/

#define _GNU_SOURCE
#include <stdio.h>
#include <pthread.h>
#include <sched.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <signal.h>

#define CORE_PER_SOCK 4
#define NR_THREADS 8
pthread_t threads[NR_THREADS];
/*
* For avoiding contention in page table lock, FAULT area is
* sparse. If FAULT_LENGTH is too large for your cpus, decrease it.
*/
#define MMAP_LENGTH (8 * 1024 * 1024)
#define FAULT_LENGTH (2 * 1024 * 1024)
void *mmap_area[NR_THREADS];
#define PAGE_SIZE 4096

pthread_barrier_t barrier;
int name[NR_THREADS];

void segv_handler(int sig)
{
sleep(100);
}
void *worker(void *data)
{
cpu_set_t set;
int cpu;

cpu = *(int *)data;

CPU_ZERO(&set);
CPU_SET(cpu, &set);
sched_setaffinity(0, sizeof(set), &set);

cpu /= CORE_PER_SOCK;

while (1) {
char *c;
char *start = mmap_area[cpu];
char *end = mmap_area[cpu] + FAULT_LENGTH;
pthread_barrier_wait(&barrier);
//printf("fault into %p-%p\n",start, end);

for (c = start; c < end; c += PAGE_SIZE)
*c = 0;
pthread_barrier_wait(&barrier);

madvise(start, FAULT_LENGTH, MADV_DONTNEED);
}
return NULL;
}

int main(int argc, char *argv[])
{
int i, ret;
unsigned int num;

if (argc < 2)
return 0;

num = atoi(argv[1]);
pthread_barrier_init(&barrier, NULL, num);

mmap_area[0] = mmap(NULL, MMAP_LENGTH * num, PROT_WRITE|PROT_READ,
MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
for (i = 1; i < num; i++) {
mmap_area[i] = mmap_area[i - 1]+ MMAP_LENGTH;
}

for (i = 0; i < num; ++i) {
name[i] = i * CORE_PER_SOCK;
ret = pthread_create(&threads[i], NULL, worker, &name[i]);
if (ret < 0) {
perror("pthread create");
return 0;
}
}
sleep(60);
return 0;
}



\
 
 \ /
  Last update: 2009-12-03 02:37    [W:1.735 / U:0.488 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site