Robert Collins wrote:
> I'm not sure it will work in the current store model. At least, not
> without potentially unacceptable memory overhead, xor a callback based
> storeGetEntry.
>
> The basic idea was to make the store key based on the URL alone contain
> a list of all variants of that URL, varying by Etag or method.
>
> So, when we retrieve the metadata about the object found at the URL, we
> retrieve a list of objects, and can choose the object best suiting our
> needs depending on what we need it for.
>
> ie: PURGE: we release all of them.
> general methods: we look for ones matching our method.
> HEAD: we look for HEAD or GET methods.
Yes. I fully agree when put in this context, which is a different context than
the question on why the request method is encoded into the store key in the
current version..
Regards
Henrik
Received on Mon Sep 09 2002 - 07:17:22 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:16:30 MST