Re: async-io network / future Squid design

-----BEGIN PGP SIGNED MESSAGE-----

Henrik Nordstrom writes:
> Joe Cooper wrote:
>
> > With some speed improvements I hope? The signaled async network stuff
> > Nikita posted a few days back was cool but quite slow in it's then
> > current state. Has that been addressed? (Or was the problem between
> > the chair and the keyboard? i.e. Mistakes in configuration on my part?)

No. async-tcp is buggy right now. It looks like slow it benchmarks
because it apparently never pushes some requests back to the client.

>
> I don't see the point of async-io network. It already is asyncronous via
> the TCP socket buffers (which is related to but not limited to the TCP
> window) and non-blocking I/O.
>
> What might be needed is to address the CPU overhead of poll(). When you
> have a large number of connections poll() becomes a CPU hog (not as bad
> as select() was, but still..).

That was exactly the idea behind signals. In poll/select amount of
work have to be done depends on the total number of file descriptors,
and when you use signals it depends on the number of fds ready to be
read from/written to, that is, scales much better.

>
> There has been quite extensive discussions on what the networking I/O
> model in Squid should look like, and the current design is far from
> optimal in many respects. Unfortunately things has not been moving along
> as quick as one might hope in that area. The discussion also needs to be
> carried little further to find the wanted design.
>
> What I would like to see from the kernel side is a better alternative to
> poll where you instead of polling each and every filedescriptor get back
> those that are ready when they are, and a quick indication on how ready
> the socket is (amount of data that can be read/written there)

Approximately the same thing is described in
http://www.usenix.org/publications/library/proceedings/usenix99/full_papers/banga/banga_html/index.html

>
> From the Squid side I would like to have a major redesign within the
> next half year to
>
[...]
> /Henrik
Nikita.
- --
Mail me: NikitaDanilov@Yahoo.COM Web me: http://nikita.w3.to
PGP: B4DBBD61 4B B8 7B 9D E8 66 04 69 CB BC 76 8F AB 8A 57 02
Something great and hard to describe a topos seems to be, for it
is a matter and a form simultaneously. // Aristotle. Physics (4) 212a

-----BEGIN PGP SIGNATURE-----
Version: 2.6.3i
Charset: noconv
Comment: Hello, Echelon!

iQCVAwUBOcembwuKNXy0271hAQEG9gQA4VFVSYyVmRueR446b/7CWV3ZO8/RBEi4
Hw9CWlgdYC8be2VnihBGi0HwePlz6fi2NvAXHyi8WFDUPrcI0/BZZoVBit3Osh9C
azRYQpuy7mh/UPdLYM/53kvLzC+rKnP62lSMDNQaT7019ik1UCwt4DMhNAppb/ds
jWTqlCps8HM=
=CowI
-----END PGP SIGNATURE-----
Received on Wed Sep 20 2000 - 11:59:42 MDT