Re: benchmarking squid on solaris/x86

From: Lincoln Dale <ltd@dont-contact.us>
Date: Thu, 21 Mar 2002 13:15:31 -0800

At 03:09 PM 21/03/2002 +0100, Henrik Nordstrom wrote:
>On Thursday 21 March 2002 11.11, Lincoln Dale wrote:
>
> > as for [1], SIGIO sucks. if you really want to know the gory details why,
> > see http://marc.theaimsgroup.com/?l=linux-kernel&m=100888541205739&w=2
> > http://marc.theaimsgroup.com/?l=linux-kernel&m=100888593806860&w=2
> > http://marc.theaimsgroup.com/?l=linux-aio&m=100888973615146&w=2
>
>I know enought of it to say that the Linux approach to SIGIO (use of RT
>signals) do not suck, only some "minor" details of the acutal implementation
>sucks.
>
>SIGIO in general do indeed suck badly by the design of the event delivery
>mechanism...

feel free to convert squid to use them and you'll become a non-believer in
SIGIO like i am.
my experience comes from taking a few weeks to convert a commercial proxy
to use SIGIO and being underwhelmed by the new bottlenecks and races
inherent in SIGIO.

> > if you're really interested in following this, take a look at linux-aio ...
>
>AIO do not really solve all of these problems either, but in principle the
>approach
..

i agree here. my own personal opinion is that AIO isn't exactly perfect
either -- i believe i know a better API but that is effectively
commercial-in-confidence - but AIO is the closest i've seen to actually
understanding all the issues involved.

cheers,

lincoln.
Received on Thu Mar 21 2002 - 14:25:23 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:14:52 MST