Re: [squid-users] Re: Do we have an algorithm to define the cachabillity of an object by the request and response?

From: Amos Jeffries <squid3_at_treenet.co.nz>
Date: Tue, 08 Apr 2014 22:31:42 +1200

On 8/04/2014 7:24 p.m., babajaga wrote:
>> the only way is to force a fetch of the full object<
>
> I do not see, how this will solve the random (?) range-issue, without a lot
> of new, clever coding.
> Actually, I can not seriously test for random range, but will definitely do.
> (NOTE: With "range" I refere to explicit "range=xxx-yyy" somewhere within
> URL, NOT range request in http-header, which was used and then dumped
> already quite some time ago by youtube.)

If the range is done properly with Range: header then the future random
ranges can be served as HIT on the cached object.

Problem remains if anything in the URL changes and/or the range detail
is sent in the URL query-string values.

Youtube videos are uniquely nasty with their FLV meta header inside the
content and fake "range" request. These things really *are* a whole
unique video chunk per fetch.

Amos
Received on Tue Apr 08 2014 - 10:31:46 MDT

This archive was generated by hypermail 2.2.0 : Tue Apr 08 2014 - 12:00:05 MDT