Re: [squid-users] Socket option in Squid

Hello Adrian,

> On Fri, Aug 17, 2001, Ronald wrote:
> > Hello Henrik,
> >
> > I am reading Squid code. My squid 24s1 is becoming bottleneck in cpu
usage, found that most of the cpu was with poll calls. I have read this from
one book that we can set SO_SNDLOWAT socket option to high value so that we
can reduce the number of read calls. Does this make sense?
>
> yup. At high connection/data rates this happens.
> I thought SNDLOWAT set the hard watermark - ie if the incoming
> data doesn't ever exceed the watermark, it never becomes ready
> for reading/writing.

Understood now and Agreed.

>
> The squid IO model needs tobe reworked. I've been trying on and off for
> a year to rework the existing codebase but from what I have learnt
> it'd be a lot easier to start from the beginning again (at least from
> the storage/client/server code.)
>
> I'm quite happy to write up a paper on this if people would like.
> But I'm sure its been covered in the squid-users/squid-dev archives
> since around 1999.

I will be very thankful If you do that. Mean time I want to read all the
discussions in squid-dev archives. I have limited net access. Can i download
all the archives to my machine? I tried with some tools. I think hypermail
formats was not accepted by my tools. Please suggest me in this.

> > And another thing, I have seen in cachemgr that no of counters for
select is such and such. Is there any calculation to check whether Squid is
in Normal state like No of requests Vs No of poll calls, etc, etc ????
> >
> > Again, What are the issues when we make Squid as a forking a child
process per request? Will it not be suitable for Squid?
> >
> >
>
> The trouble with child per connection is that the process overhead
> in the operating system actually becomes a serious limitation at more
> than a few tens of requests per second. UNIX wasn't built to have
> high process churn rates. If you don't believe me, take a look
> at apache. In fact, you can run apache in proxy mode.. :)

Ok.

Regards,
Ronald
Received on Fri Aug 17 2001 - 22:35:48 MDT