| |||||||||||||
Ghosts of Unix past, part 4: High-maintenance designsGhosts of Unix past, part 4: High-maintenance designsPosted Dec 6, 2010 11:31 UTC (Mon) by dlang (✭ supporter ✭, #313)In reply to: Ghosts of Unix past, part 4: High-maintenance designs by pbonzini Parent article: Ghosts of Unix past, part 4: High-maintenance designs
does this vfork advantage still exist (i.e., is it measurable) when the host OS does Copy On Write for the fork instead of actually copying all ram?
yes, the page tables still get modified twice, but is this measurable on modern hardware?
(Log in to post comments)
Ghosts of Unix past, part 4: High-maintenance designs Posted Dec 6, 2010 11:58 UTC (Mon) by pbonzini (subscriber, #60935) [Link]
Yes, I've seen forking take 60% of CPU (that was forking 4 child processes per second from a +2 GB process). Using fork to vfork, or equivalently switching to posix_spawn, brought it down to 3-4%.
|
|||||||||||||