openstack team mailing list archive
Mailing list archive
Re: distributed and heterogeneous schedulers
On Apr 15, 2011, at 12:02 PM, Jay Pipes wrote:
> This is getting totally off-track :)
Of course! Don't all email threads do that? :)
> My point was that if you are going to put data in a database table,
> the attributes that go into the main table should be the attributes
> that are common to all types of an entity, otherwise, use the table
> that stores the custom key/value pairs.
Sure, that's just good database design. I was just addressing the fact that with the addition of zones and the distributed scheduler, the current method of determining a suitable host for a new instance is going to change radically, and it will not be relying on database tables to get its information.
-- Ed Leafe