Re:Kore: a fast web server for writing web apps in C
by luikore on Sunday May 17, 2015 @12:59AM
(#9558776)
I think the authors want to avoid thundering herd. You can find this basic pattern in the book UNIX Network Programming.
[ Parent
| on HN ]
Re:Kore: a fast web server for writing web apps in C
by jvink on Sunday May 17, 2015 @10:50AM
(#9560221)
Correct.
The accepting socket is shared between multiple workers which each have its own fd for epoll or kqueue. Because of this a form of serialising the accepts between said workers is needed to avoid unnecessary wakeups.
Re:Kore: a fast web server for writing web apps in C
by rdtsc on Sunday May 17, 2015 @11:49AM
(#9560460)
Actually that is being changed:
http://lwn.net/Articles/633422/
See part about EPOLLEXCLUSIVE
Re:Kore: a fast web server for writing web apps in C
by jvink on Sunday May 17, 2015 @12:29PM
(#9560620)
That is great, thanks for sharing.
Re:Kore: a fast web server for writing web apps in C
by rdtsc on Sunday May 17, 2015 @12:57PM
(#9560711)
If you are the author, thanks for sharing the project. You did a great job and made the right choice of having per CPU worker processes each with their own epoll loop.
Re:Kore: a fast web server for writing web apps in C
by rdtsc on Sunday May 17, 2015 @01:57AM
(#9558896)
Hmm, thought that was fixed 10 years ago or so. I can't believe the standard accept() call will wake up all threads on a modern Linux kernel.
Maybe if it is using epoll/select/etc. it would exhibit the thundering herd issue.