Re: [RFC] cache architecture

From: Alex Rousskov <rousskov_at_measurement-factory.com>
Date: Thu, 26 Jan 2012 08:12:44 -0700

On 01/26/2012 12:50 AM, Henrik Nordström wrote:
>
> ----- Ursprungsmeddelande -----
>> If they have sync problems, they may violate HTTP. I am just doing my
>> best trying to stay focused on the [local] cache architecture topic; I
>> do not want to get into discussion about distributed hierarchies.

> Exactly. HTTP spec is written for a consistent single-path forwarding path, not a mesh.

>> It may be a good idea to polish HTTPbis if it indeed allows both yours
>> and mine points of view to coexist even though they contradict each
>> other.

> It's a little late now for such adjustments. And not needed i think.

I do not think it is too late because we do not need to add or change
any normative text. Just add a paragraph clarifying the specs scope:

"This specification defines behavior of a fixed chain of HTTP agents.
Content Distribution Networks, cache hierarchies, load balancers, and
other complications often result in variable forwarding paths, where two
requests with the same Request-URI from the same client may arrive at
different agents. While all HTTP requirements ought to apply to
collections of cooperating agents, treating each collection as a single
agent, such compliance is usually not guaranteed (and, hence, should not
be relied upon) in complex distributed environments."

Or something of that kind.

Cheers,

Alex.
Received on Thu Jan 26 2012 - 15:12:59 MST

This archive was generated by hypermail 2.2.0 : Thu Jan 26 2012 - 12:00:13 MST