On Mar 13 10:32, Mojmir Svoboda wrote: > hello, > > i'm runing cygwin (1.5.25?) under win xp sp2 and i ran a simple test > which was supposed to measure the speed of pthread_mutex_lock, > increment, pthread_mutex_unlock compared to interlocked increment and > windows critical section. > > the thing is that cygwin's pthread_mutex_lock performs quite lazily - it > takes about seven times more than using native critical section. > > i wonder why, of course :)
Bookkeeping overhead? Just have a look into the Cygwin source. If you want to speed up Cygwin's pthread implementation, feel free to contribute: http://cygwin.com/contrib.html Corinna -- Corinna Vinschen Please, send mails regarding Cygwin to Cygwin Project Co-Leader cygwin AT cygwin DOT com Red Hat -- Unsubscribe info: http://cygwin.com/ml/#unsubscribe-simple Problem reports: http://cygwin.com/problems.html Documentation: http://cygwin.com/docs.html FAQ: http://cygwin.com/faq/
