Top all-time · #648
Dan Kegel
Personal blog · kegel.comprogrammingsystems
Dan Kegel's personal blog at kegel.com covers programming and systems. Since 2007, 97 different Hacker News readers have linked it 122 times, most often “The C10K problem”. No feed was found, so read it on the site itself.
Sometimes recommended · 8 of 40 sampled comments recommend it?
Why HN links it
HN readers link kegel.com mainly for the C10K essay, a classic reference on serving many clients at once with threads, poll and epoll. Other pages like crosstool and ANET come up less.
- Recommended for · 8 comments
- Called 'fascinating reading', a 'classic' and 'the most comprehensive single place' for server strategies; 'captured pretty well'.
Summarised by Claude from a sample of 40 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- The C10K problem71 people · 89 mentions · first linked 2007-08-23
- Wine on Windows3 people · 3 mentions · first linked 2016-11-14
- How To Get Hired -- What CS Students Need to Know3 people · 3 mentions · first linked 2011-11-14
- The C10K problem2 people · 2 mentions · first linked 2011-05-07
- We "solved" C10K years ago yet we keep reinventing it2 people · 2 mentions · first linked 2025-07-24
What Hacker News says?
I hope they bring back Battlezone - Activision rebooted it in 1998 ( https://en.wikipedia.org/wiki/Battlezone_(1998_video_game) ) A great single player and co-op "real time strategy" game that ran on a simple protocol called ANET ( http://www.kegel.com/anet/ ) ( http://www.strickleton.com/anet/ ) Most servers are dark now but there's still a great community keeping this game alive. It had very robust tools for build…
Comment linking /anet/
on “Microsoft to Acquire Activision Blizzard”Submitted The C10K problem as a story · 112 points
HN discussionYou don't need it for WSL, wWine can already run on Windows natively: http://www.kegel.com/wine/wow.html
Comment linking /wine/wow.html
on “Wine 3.0 Released”Submitted The C10k problem: time for web servers to handle ten thousand clients as a story · 14 points
HN discussionAs a backend web developer you can learn about the difference in pre-fork and polling model in web servers, which interconnected with c10k http://www.kegel.com/c10k.html This will give you ability to reason about the web server configuration you want to use. But both fork(2) and epoll(7) [kqueue(2), iocp] would stay at low level relatively of place where you operate. Don't know what to say about fronted though, but…
Comment linking /c10k.html
on “From Nand to Tetris (2017)”Submitted How to get involved with open source as a story · 13 points
HN discussionMaybe everyone needs their ansi.sys moment though. Back in the early 1990's, I, and probably half the programmers using DOS, rewrote the dos ansi.sys driver/TSR because its was _SLOW_. mostly IIRC because it was calling the BIOS text output, but also because it was a pretty solid implementation of the ANSI terminal/esc sequence "standard". So, the first half took about an hour or two to handle output (just write a c…
Comment linking /nansi/
on “It takes a PhD to develop that”Submitted c10k: Handling 10 thousand symultaneous connections. as a story · 13 points
HN discussionedit: see replies to my comment. I mistook the Hyper pull request being merged for being in the latest release, but it isn't. Rocket uses Hyper for its HTTP server. So I checked to see if the Hyper HTTP server was really production-ready. Particularly, if it could handle async IO / solve the C10K problem[0]. It looks like Hyper implemented async IO[1], so it should be adequate for production use in this regard. This…
Comment linking /c10k.html
on “Show HN: Rocket – Web Framework for Rust”Submitted The C10K problem - scaling servers to 10,000+ clients as a story · 7 points
HN discussionThe general issue if serving one vs multiple clients per thread has been discussed extensively in the last two decades, see http://www.kegel.com/c10k.html I’m not familiar with python but it seems like there is a glaring performance bug iff using one thread per connection is faster than using async io.
Comment linking /c10k.html
on “Async Python is not faster”Submitted The C10K Problem as a story · 5 points
HN discussionWikipedia says Nginx started in 2004. If you look at the state of things for threads and other "lots of sockets to deal with" things in that timeframe, you can see multiprocess was probably a safer choice, especially if you intended on running well on a variety of Unix or Unix like OSes. This page has some of that state captured pretty well: http://www.kegel.com/c10k.html
Comment linking /c10k.html
on “Pingora, the proxy that connects Cloudflare to the Internet”Submitted How To Get Hired -- What CS Students Need to Know as a story · 5 points
HN discussionepoll on linux. Other apis on other oses. More reading: http://www.kegel.com/c10k.html
Comment linking /c10k.html
on “Beej's Guide to C Programming (2007)”Submitted C10K - serving thousands of clients as a story · 5 points
HN discussionDo you know if the most optimal FreeBSD zero copy support is only available for Tigeon NICs? I couldn't quite figure it out from reading the following pages: - http://www.freebsd.org/cgi/man.cgi?query=zero_copy - http://www.kegel.com/c10k.html#zerocopy - http://people.freebsd.org/~ken/zero_copy/
Comment linking /c10k.html
on “Why do we use the Linux kernel's TCP stack?”Submitted The C10K problem as a story · 4 points
HN discussionAnd now you have 32 cores just waiting for slow HTTP clients. Apache with the prefork MPM does exactly that. See http://www.kegel.com/c10k.html for an in-depth, if old, discussion.
Comment linking /c10k.html
on “Rust 1.37.0”Submitted The C10K problem as a story · 3 points
HN discussionHow about the marvel that was Walnut Creek's cdrom.com that served 10,000 simultaneous FTP connections back in 1999? [1] I was always blown away by how much more efficient FreeBSD's network stack was compared to Linux at the time. It convinced me to go FreeBSD-only for a few years. [1] http://www.kegel.com/c10k.html
Comment linking /c10k.html
on “FreeBSD optimizations used by Netflix to serve video at 800Gb/s [pdf]”Submitted The C10K problem as a story · 3 points
HN discussionhttp://www.kegel.com/c10k.html FTW
Comment linking /c10k.html
on “The Various Kinds of IO – Blocking, Non-Blocking, Multiplexed and Async”Submitted The C10K problem as a story · 3 points
HN discussion> Synchronous sequences are generally faster than asynchronous ones because yielding and getting scheduled back has a non-zero overhead Indeed. I remember being shocked when I first read "Thousands of Threads and Blocking I/O" [0] by Paul Tyma. After reading the C10k problem [1], I just believed that a big pile of threads would never work and never updated my beliefs. While such an approach is still quite memory lim…
Comment linking /c10k.html
on “Fast, Safe, and Complete(ish) Web Service in Rust”Submitted The C10K problem as a story · 3 points
HN discussionEven if the OS can take it, it requires proper engineering in your stack (ie, node.js here). it wasn't long ago that even managing 10K connections on a server was considered quite a feat - see http://www.kegel.com/c10k.html
Comment linking /c10k.html
on “600k concurrent websocket connections on AWS using Node.js (2015)”Submitted We "solved" C10K years ago yet we keep reinventing it as a story · 2 points
HN discussionhttp://www.kegel.com/c10k.html
Comment linking /c10k.html
on “Is it just me or is networking really hard?”Submitted The C10K Problem (1999) as a story · 2 points
HN discussion
