Re: [PATCH] StoreID latest implementation in sync with rev 12552. stage 2-3 from 3.

On 3/01/2013 5:13 a.m., Alex Rousskov wrote:
> On 12/29/2012 12:16 AM, Eliezer Croitoru wrote:
>> + /**
>> + * a copy of request->store_id which needed in couple places where the request
>> + * cannot be accessed or dosnt exists.
>> + */
>> + String store_id;
> This description does not make sense to me. If request does not exist
> (i.e., the request member is nil), there cannot be a copy of
> request->store_id. And if it exists, then it can be accessed without
> making a copy.

There is the case of internal objects such as icons. Which during
loading need to have a store_id and all the infrastructure for adding to
cache but no request.
  There is also ICP requests which need to oeprate without any
HttRequest state.

>
>> + // XXX: This function is now kept only to check for and display the garbage use-case
>> + // and to map the old helper response format(s) into new format result code and key=value pairs
>> + // it can be removed when the helpers are all updated to the normalized "OK/ERR kv-pairs" format
> Do we need to add this function when we are adding support for a new
> helper? Perhaps it is OK to assume that all Store ID helpers will use
> new key=value format? Is this to support Squid2 Store ID helpers? Will
> those still work with the proposed Squid3 changes?

Yes. It is still needed for the backward compatibility with 2.7 helpers
which are going to be running after upgrade.

Amos
Received on Thu Jan 03 2013 - 00:05:35 MST