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

On Fri, 2008-12-12 at 09:44 +0100, Henrik Nordstrom wrote:
> > What are we going to do about loops and absolute exchange URLs if the
> > Squid host name is not known?
>
> I would argue neither is a real problem.
>
> Most uses a reasonably unique server name, even if it's not a FQDN. And
> in worst case they get false loop detection. Additionally the percentage
> running into this is most likely less than the number of people setting
> visible_hostname and copying the same squid.conf to multiple hosts..
>
> But we probably should add a restriction that the unique server name
> MUST be a FQDN when accelerator mode is enabled no matter how it's
> derived (squid.conf or system) or things could get a little confusing if
> both the reverse proxy and some random squid proxy accessing it has the
> same name (for example squid1)

Perhaps we could generate a random name if no other name can be derived?
The name does not have to be very persistent until humans start using
it, right? And when/if a human starts using the visible host name by
enabling some peering options, Squid can require that a human configures
the visible host name (if the system does not already provide it).

Given your confidence and Kinkie's clarification, I am not against
dropping the requirement.

Thank you,

Alex.
Received on Fri Dec 12 2008 - 17:19:41 MST