> of course. ibm developer works articles say that thread creation speeds > are way beyond process creation (>10,000 versus between 300 to 350 per > second on a 648MHz P3). one of reasons is the simple fact that thread > creation consumes less overhead(no process id, not true for linux > though, minimal stack, shared protection space), but you already know > that. :)
More than creation speed, I would think that the bigger _memory_ overhead of processes is what hurts the scalability of a forking server like Apache most. Whereas 100 processes might take up 64MB of RAM, you could instead have 1000 threads before you start VM swapping/thrashing. Or can this be alleviated by using some sort of shared memory among parent and child processes (and if it does, does Apache use something technique like that)? _ Philippine Linux Users Group. Web site and archives at http://plug.linux.org.ph To leave: send "unsubscribe" in the body to [EMAIL PROTECTED] To subscribe to the Linux Newbies' List: send "subscribe" in the body to [EMAIL PROTECTED]
