[openib-general] Re: SA cache design

[Sean Hefty]

Michael S. Tsirkin wrote:
> I've been thinking about distributed SA myself for a while now.
> This seems like an elegant way to improve the SA scalability.
> 
> How would distributed copies sync with the central SA?
> I guess we could simply use sockets on top of IPoIB - the sync
> it probably a rare occurrence.

I think this moves beyond what the cache is trying to accomplish at this point.

Personally, if the SA were implemented using a database, I'd let the database 
worry about synchronizing the data.