massive tcp servers
Thu Jun 24 13:49:55 CEST 2004
> If you wrote your own TCP (or simpler custom protocol) in userspace
> then maybe you could pull it off with just one box. You could keep the
> TCP control structures in a database on disk and map the active ones
> into a large-but-bounded-size pool in memory.
> I have only limited experience with hacking TCP/IP, but my impression
> is that writing your own TCP is probably no harder than e.g. writing a
> good HTTP/1.1 implementation. I recommend the first two volumes of
> Douglas Comer's networking series, in turn recommended to me by Tobbe
> from when he wrote a TCP in Erlang.
I suspect it might be pretty easy - Adam Dunkels wrote a TCP/IP
"thingy" in PHP - not a full TCP but just enough to answer an HTTP
I talked to Adam he said it took him "3 hours" - including the time
to learn PHP - now Adam has admittedly implemented TCP many times -
but staring at his code might provide some inspiration.
If you wrote "enough" TCP to just handle a HTTP request you might
come up with a pretty high performance, highly concurrent web server -
IMHO the tricky bit is making a tunnel so that a regular Erlang
program can see the raw IP datagrams - the rest is just plain coding.
Luke sees to have some code that does this bit - (am I right Luke).
> On Linux I think the most practical option would be to use a 'tun'
> interface (linux/Documentation/networking/tuntap.txt), which allows
> you to write a user-space network interface that operates at IP-level
> (rather than ethernet-level). That way you can use Linux's IPv4
> implementation and only worry about TCP yourself.
More information about the erlang-questions