On Wed, Apr 25, 2018 at 4:13 AM, Vladimir Ozerov <voze...@gridgain.com> wrote:
> Right, as far as I understand we are not arguing on whether BLT is needed > or not. The main questions are how to properly deliver this feature to > users and how to deal with co-location issues between persistent and > non-persistent caches. Looks like change policies are the way to go for the > first question. > > As far as co-location, it is important to note that different affinity > distribution for in-memory and persistent caches automatically means that > we loose SQL joins and predictable behavior of any affinity-based > operations. It means that if we calculated the same affinity for persistent > and in-memory caches at some point, we cannot re-distribute in-memory > caches differently if some nodes go down without breaking co-located > computations, am I right? > Vova, you are right, but this is rather an edge case. I doubt there are many users out there who will need to join memory-only with persistent caches. What you are describing would be nice to support, but I would not make it a hard requirement. However, if we choose not to support it, we should have a very good explanation for why not.
