Mailing Lists: Apple Mailing Lists
Image of Mac OS face in stamp
 
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Fork, Memory, Copy-on-Write -- Horribly Slow?


For some reason, it seems that copy-on-write is atrociously slow after a fork, and I'm curious as to why this is.

Here's a pretty simple test. The last bit will take more than 10 minutes on my Mac Pro. Insane!



#import <Foundation/Foundation.h>

int main (int argc, const char * argv[]) {
   NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init];


   uint32_t size = 1024 * 1024 * 512;
   uint8_t * buffer1 = malloc(size);
   uint32_t i;
   for (i = 0; i < size; i++) { buffer1[i] = 3; }



   pid_t pid = fork();
   if (pid != 0) {
       waitpid(pid, NULL, 0);
   } else {

       // Very very fast
       uint8_t * buffer2 = malloc(size);
       memcpy(buffer2, buffer1, size);
       NSLog(@"Child memcpy done");
       sleep(3);

// Very VERY ***VERY*** sloth-on-a-snail's-back-in-molasses- at-0.00001-degrees-Kelvin slow
NSLog(@"Child starting reassignments to b1");
for (i = 0; i < size; i += 1024 * 4) {
buffer1[i] = i;
}
NSLog(@"Child done reassignments to b1");
sleep(3);
}


   [pool drain];
   return 0;
}




Any ideas?


--
Seth Willits




_______________________________________________
Do not post admin requests to the list. They will be ignored.
PerfOptimization-dev mailing list      (email@hidden)
Help/Unsubscribe/Update your Subscription:
http://lists.apple.com/mailman/options/perfoptimization-dev/email@hidden

This email sent to email@hidden


Visit the Apple Store online or at retail locations.
1-800-MY-APPLE

Contact Apple | Terms of Use | Privacy Policy

Copyright © 2007 Apple Inc. All rights reserved.