Re: aio_read implementaion in Squid

On 13 Sep 2001, at 15:30, Joe Cooper <joe@swelltech.com> wrote:

> Andres Kroonmaa wrote:
> > On 13 Sep 2001, at 18:01, Venkatesh <gv_kovai@yahoo.com> wrote:
> >
> >>* But Before doing that, I should get fair decision of what I/O will be good
> >>for Squid in all aspects to achieve 1k req/sec.
> >
> > Current squid can easily handle 1k req/sec without disks involved. In last
> > days one of our reverse-proxies was handling 540 req/sec with single disk,
> > although its memhitrate is at 90-95%...
> > Next bottleneck after disks is ACL's. If you use no or very few acls, only
> > then comes io model into play.
> > And while at that, it makes a huge difference, whether you service alot of
> > slow clients or few fast clients. When you have few open sockets, poll model
> > is very much okay.
>
> 1k reqs/sec? Are you sure? I wouldn't think so, even entirely from
> RAM. 500, yes. I've seen that in memory only benchmarks (95% memhits),
> but performance starts to degrade when going much above that number (at
> least on an 800MHz Athlon--faster machines can obviously go a little
> faster).

 Well, y'know what benchmarks are. It all heavily depends what you service.
 I've never thought my box is something special. It was running 4 copies
 of Squid at the time, 2 of which were pretty mightily used. And it got
 540/sec before I had to "tune" it some. s2.3 btw. Here most of objects
 serviced were 304 or small <1K bits. So only single pass on "pumping"
 was needed. It lagged. If you need more passes for large objects, things
 degrade very fast. I just think that if my setup did 540/sec then it could
 do better too. Well, I'm not so sure either ;)

> You could gain probably another 50-75% performance using dual
> processors...

 not sure how. I admit I have dual P3-800 here, but only 1 cpu was fully
 utilised.

> We are definitely hitting CPU performance bottlenecks within Squid

 Not just squid. At such extremes, almost any most minimal differences
 in OSes and CPU's can have drastic effects when doing 30K syscalls/sec.
 But sure, Squid is becoming cpu-pig too.

> I've done tests of memory only Squid's, but nothing of alternate
> networking i/o methods (since Squid only has one really).
>
> I would think TUX is probably a good place to look for network I/O
> performance implementation ideas. Almost everything used in TUX has

 yes, but portability goes out of window I guess...

------------------------------------
 Andres Kroonmaa <andre@online.ee>
 CTO, Microlink Online
 Tel: 6501 731, Fax: 6501 725
 Pärnu mnt. 158, Tallinn,
 11317 Estonia
Received on Thu Sep 13 2001 - 15:08:01 MDT