Re: [squid-users] Squid network read()'s only 2k long?

On Tue, Nov 02, 2010 at 12:10:25AM +0000, Amos Jeffries wrote:
> On Mon, 1 Nov 2010 22:55:12 +0000, Declan White <declanw_at_is.bbc.co.uk> wrote:
> > On Mon, Nov 01, 2010 at 09:36:53PM +0000, Amos Jeffries wrote:
> >> On Mon, 1 Nov 2010 15:00:21 +0000, declanw_at_is.bbc.co.uk wrote:
>
> Looks like one of the side effects of 3090:
> http://www.squid-cache.org/Versions/v3/3.1/changesets/
>
> (just fixing the reply text makes squid produce a regular error page where
> it should have produced an auth challenge to get some usable Basic-auth
> credentials).

Ah, does that mean there's a cleaner fix somewhere I should be stealing?

> 64KB is about the buffer size Squid uses internally, so that is about
> right for keeping a completely full buffer I think.

Is there any wisdom in me subtracting a few bytes to account for some memory overhead anywhere?
 
By the by, I *think* I've gotten to the bottom of my 2046 byte read() buffer
issue (which wasn't tcp_recv_bufsize after all). *If* I am reading this right:

http.cc:79: HttpStateData::HttpStateData
    readBuf = new MemBuf;
    readBuf->init();

With no arguments, init() will cook up an empty 2048 size buffer, which gets
carried all the way through the OO to the read() call (wherever that is)
that dutifully only reads as much as the buffer says it currently has.

So I'm thinking of hardwiring something in there tomorrow and seeing what explodes.

> Okay. I think from the resource comments above you want it OFF. Squid will
> respond to HTTP/1.1 "Expect:" requests immediately and broken clients that
> can't handle the required HTTP/1.1 replies disappear with error pages.

Ah, by 'broken clients' are we talking IE6 by any chance? :)

DeclanW
Received on Tue Nov 02 2010 - 00:55:42 MDT