Re: [MERGE] RFC-compliant object invalidation behaviour.

On 29/08/2008, at 2:13 PM, Alex Rousskov wrote:

>
> On Thu, 2008-08-28 at 15:16 +1000, Benno Rice wrote:
>> RFC-compliant object invalidation behaviour.
>>
>> - Switch the default from not purging if the method is unknown to
>> purging if
>> the method is unknown.
>
>> - return false; // be conservative: we do not know some methods
>> specs
>> + return true; // RFC says to purge if we don't know the method
>
> Perhaps add that the RFC says SHOULD purge and refer to Section 13.10?
> This requirement will probably surprise a few developers so it is
> better
> to be explicit.

Already done, as per Amos' request earlier in the thread.

> Also, if you change the default to return true, then we can delete all
> "return true" cases in the same HttpRequestMethod::purgesOthers()
> method. This will make the method a tiny bit faster.

That's true, although the gain will probably be minor as it would (I
hope) be optimised that way. It may also be worth leaving this layout
in case it's desired to make this behaviour conditional.

>> - When purging URIs sourced from Location and Content-Location
>> headers, make
>> sure the URL is absolute before a) comparing it to see if hosts
>> match and b)
>> actually trying to find it in the store.
>>
>> These changes are based on changes made to squid 2. In particular,
>> the
>> urlAbsolute function was ported from squid 2. I would appreciate
>> it if people
>> paid particular attention to urlAbsolute to make sure I'm not doing
>> anything
>> that would cause problems in squid 3.
>
> urlAbsolute() is not yet documented in the patch. Please add a few
> comments to explain what it does and why we cannot use some of the
> existing URL formatting routines [and then check their output] to
> arrive
> at the answer.

Can do. The idea is to form an absolute URL based on a provided
relative URL and an exisiting record, eg a relative URL contained in
the Content-Location header of a request. If you know of a function
that can do that, or if you can suggest a better way of doing this
please let me know. Otherwise I'll tidy the existing function up
somewhat and add some comments describing its purpose.

-- 
Benno Rice
benno_at_jeamland.net