Re: async-io network / future Squid design

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

Henrik Nordstrom writes:
[...]
>
> Actual signal delivery is a quite heavy and destructive operation yes (I
> assume. Haven't actually measured this, and is not interested in it
> either), but with queued signals we do not actually need signal delivery
> and can instead use the signal queue to batch things. The trick is then

Another problem with signal delivery is that there are not many things
you can do from the signal handler safely. Moreover in traditional
UNIX, signal presence is only checked just before returning from the
kernel mode, which can amount to some measurable latency.

> to not make the queue overflow more than absolutely needed, and to
> properly detect when it happens and deal with it. But first the actual
> overhead of poll() should be measured I think.
>
> Also, given the apparently relatively minimal overhead of sigtimedwait I
> would say adding a batch version of that call will only give you a
> minimal increase in performance if any at all. Not worth the effort.

But it is already here, and I just added you timeout patch. :)

>
> /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
Mathematics is like checkers in being suitable for the young,
not too difficult, amusing, and without peril to the state. // Plato

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

iQCVAwUBOcorqQuKNXy0271hAQFwfQP+O2MppL/yggVaNuqSwQifzO5xS4WZZ29i
eUhgL6TQLukdfvY/Bltgt1Uux3AiQAEAedxX7WdDYPHZWkIBpNQGrEw74tpGYn+O
hiSSUOWHhFNnbbpcgAGL6SmFJkyNq5OrAP5lnsiXd2y40+tXjkdh5tQ2xHkFQ+FP
MIFciyfkT6s=
=Sxxe
-----END PGP SIGNATURE-----
Received on Thu Sep 21 2000 - 10:14:53 MDT