Re: Large Rock Store

On 10/17/2012 09:37 AM, Kinkie wrote:
>> Are you suggesting changes to the Storage class hierarchy that would
>> contradict the proposed polishing? If yes, what are those changes?

> Unfortunately I don't have the needed low-level knowledge to go
> in-depth, and I'm currently focused elswehere. The only suggestion I
> have at this time is that if it's agreed that (in an uncertain future)
> we may want to de-storeify the memory cache, we may start to do so now
> by breaking it out of the hierarchy.

Perhaps I misunderstand what "de-storeifing the memory cache" means or
why it is needed in the future, but todays memory cache is an object
cache storage and, hence, has to be a part of of the Storage hierarchy.

In your rendition of the future, you still have a memory cache (you
called it RAM-backed) so I do not see why we should move the current
memory cache away from storage instead of expecting future code to add
support for new layers/levels of caches and "specialized, synchronous,
transient area used to shuttle data" outside the hierarchy.

In fact, that "specialized, synchronous, transient area used to shuttle
data" may be needed much sooner. I am not sure, but it may have to be
introduced when we start removing the store_table global.

Thank you,

Alex.
Received on Wed Oct 17 2012 - 16:01:50 MDT