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

On 01/03/2013 03:16 AM, Eliezer Croitoru wrote:

> Maybe a description like:
> "A copy of StoreID reply for the specific cases which the
> request->store_id needed but not present"

Yes, this is better, but still rather convoluted. I suggest something
like "Store ID for transactions where the request member is nil",
accompanied with an appropriate getter method that uses request when
possible and this member when not.

FWIW, this problem reflects the design flaw -- we should either have the
request member set for all transactions (using internally generated
request structures where necessary) OR we should not store
meta-information such as Store ID in optional parts of transactions such
as request. Fixing this flaw is outside your project scope though. For
now, we just need to make sure that the workarounds are properly defined
and implemented.

Thank you,

Alex.

> On 1/3/2013 10:13 AM, Alex Rousskov wrote:
>> Yes, I know, but request-less transactions do not make the description
>> correct AFAICT because, when there is no request, the stored value is
>> not a copy of request->store_id.
>>
>> Cheers,
>>
>> Alex.
>
Received on Thu Jan 03 2013 - 15:43:08 MST