[asterisk-dev] IBM BladeServer / Clustered Linux

[Greg Boehnlein]

On Mon, 13 Feb 2006, Robert Bedell wrote:

> > However, there is no reason that RealTime cannot be extended to provide
> > High Avilability and Fail-Over capabilities between multiple boxes, albeit
> > at the expense of losing the calls on a server if one of the nodes bites
> > the dust.
> 
> This is where we are currently at.  Do you have any sense of how deep or
> what particular areas would need to be changed in the core?  Obviously
> certain segments would have to be implemented as shared/distributed memory
> or some sort of message passing solution.  I'm sorry, I'm only passingly
> familiar with some of this stuff, but I'm still curious.  I guess I missed
> out by not going to the presentation :)

We need the borg. We need each Asterisk box to be connected to the Hive 
mind such that all data that is accessible to one is accessible in 
real-time to all. Shared memory structures, message handling.. all of that 
infrastructure needs to be built, and this has to be done at wire-speed. 
I.E. you'll need to be able to switch a call in real-time to a new box and 
have it pick up the processing of the RTP data and the voice frames on the 
next packet.

That's a tall order!

-- 
    Vice President of N2Net, a New Age Consulting Service, Inc. Company
         http://www.n2net.net Where everything clicks into place!
                             KP-216-121-ST