Re: Should we drop the fully qualified server name requirement?

Alex Rousskov wrote:
> On Thu, 2008-12-11 at 21:11 +0100, Henrik Nordstrom wrote:
>> tor 2008-12-11 klockan 12:53 -0700 skrev Alex Rousskov:
>>
>>> Would removing the requirement open more doors for malicious attacks via
>>> "looking like normal" URLs? For example, is it easier for somebody with
>>> local access to change the name resolution for "citi" than for
>>> "citi.com"?
>> I don't see how it's related.
>>
>> My question is on Squid's requirements on the hostname of the server
>> where Squid runs, not proxied hostnames.
>
> Ah, I see. We already have a visible host name option for that and it
> accepts non-FQDNs, right? I agree that this requirement is rather
> idealistic, but I would like to hear why Kinkie would prefer to keep it.
>
> What are we going to do about loops and absolute exchange URLs if the
> Squid host name is not known?
>
> Thank you,
>
> Alex.
>
>
>> I propose that we drop this requirement, only warn if we can't figure
>> out the local hostname FQDN.
>>
>> The local server FQDN is used for
>>
>> - Via headers, as a unique identifier. used for loop prevention.
>>
>> - Absolute URLs pointing to the server. I.e. icons if use of absolute
>> URLs have been enabled. (default shortnames without host).
>>
>> - Absolute URLs for digest & netdb exchanges.
>

netdb may not be much of a problem. I have a re-work in planning to
cope with IPv6. Should be easy to integrate a URI alteration during that
upgrade.

For peer exchanges it may be a better idea to generate the URI based on
the peer IP:port/path than a FQDN/path.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE5 or 3.0.STABLE10
   Current Beta Squid 3.1.0.3 or 3.0.STABLE11-RC1