login
Header Space

 
 

Re: poll(2) vs kqueue(2) performance

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: <misc@...>
Date: Monday, April 21, 2008 - 8:31 am

* Edwin Eyan Moragas <haaktu@gmail.com> [2008-04-19 07:34]:

yes. poll is the way better API, easier to use, easier kernel-side, 
avoids a lot of problems (common!) improper use of select() brings, ...


using kqueue directly is painful. I'd recommend libevent if you really 
want to go that route.
That said, kqueue really only pays out when you have _lots_ of 
concurrent connections, say, >10000.


programming w/ libevent is convenient at times, the decision poll vs 
libevent should not be made based on performance considerations, 
exception beeing the above massive concurrent connection case.

-- 
Henning Brauer, hb@bsws.de, henning@openbsd.org
BS Web Services, http://bsws.de
Full-Service ISP - Secure Hosting, Mail and DNS Services
Dedicated Servers, Rootservers, Application Hosting - Hamburg & Amsterdam
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
poll(2) vs kqueue(2) performance, Edwin Eyan Moragas, (Sat Apr 19, 1:27 am)
Re: poll(2) vs kqueue(2) performance, Henning Brauer, (Mon Apr 21, 8:31 am)
Re: poll(2) vs kqueue(2) performance, Marco Peereboom, (Mon Apr 21, 10:43 am)
Re: poll(2) vs kqueue(2) performance, Gilles Chehade, (Mon Apr 21, 5:05 pm)
Re: poll(2) vs kqueue(2) performance, Niels Provos, (Wed Apr 23, 11:31 pm)
Re: poll(2) vs kqueue(2) performance, Marco Peereboom, (Sat Apr 26, 1:53 pm)
Re: poll(2) vs kqueue(2) performance, Jonathan Schleifer, (Sat Apr 19, 5:43 am)
Re: poll(2) vs kqueue(2) performance, Marc Espie, (Mon Apr 21, 8:38 am)
Re: poll(2) vs kqueue(2) performance, Edwin Eyan Moragas, (Mon Apr 21, 9:49 am)
Re: poll(2) vs kqueue(2) performance, Edwin Eyan Moragas, (Sat Apr 19, 11:29 pm)
Re: poll(2) vs kqueue(2) performance, Eric Faurot, (Sat Apr 19, 4:17 am)
Re: poll(2) vs kqueue(2) performance, Edwin Eyan Moragas, (Sat Apr 19, 4:38 am)
Re: poll(2) vs kqueue(2) performance , Theo de Raadt, (Sat Apr 19, 1:50 am)
Re: poll(2) vs kqueue(2) performance, Edwin Eyan Moragas, (Sat Apr 19, 2:46 am)
speck-geostationary