[squid-users] Getting the full file content on a range request, but not on EVERY get ...

[Amos Jeffries]

On 14/05/2016 12:38 a.m., Garri Djavadyan wrote:
> On Fri, 2016-05-13 at 08:36 +1200, Amos Jeffries wrote:
>> Have you given collapsed_forwarding a try? Its supposed to prevent
>> all
>> the duplicate requests making all those extra upstream connections
>> unti
>> at least the first one has finished getting the object.
> 
> Amos, I believe that the above quote describes default Squid's action,
> which does not require collapsed_forwarding. The details of my
> experiments can be found here http://bugs.squid-cache.org/show_bug.cgi?
> id=4511#c0. Thanks.

What you are describing i that report is more along the lines of what
can happen with collapsed_forwarding, shared cache by two workers, or
such features linking the two requests which are supposed to be
differently delay pooled.


Heiler's problem is almost the opposite - the transactions *not* being
linked, so they use upstream bandwidth over N connections for N times
the bandwidth usage despite any per-message controls. Not just one
connection using more data than expected.

Amos