[olpc-software] Servers

[Kevin Purcell]

I think Ivan has a point. How do you know a large mesh cloud won't  
provide sufficient bandwidth for most uses?

There seems to be a certain amount of "cart before the horse"  
reasoning from a "Westernized" centralized IT standard network here  
rather than a more peer to peer like solution that scales as you add  
laptops with distributed bandwidth increasing in a fashion similar to  
Bittorrent or distributed storage scaling like Freenet.

I suspect for large sites there will be a need for a "server-like" or  
"access-point-like" devices but I think it will resemble an everyday  
rack-mounted server or commercial access point in the same way the  
$100 laptop resembles (say) a Dell Laptop. Once can see this sort of  
device evolving from the $100 laptop design or perhaps using existing  
low-power and no-moving-parts hardware (except perhaps for an optical  
drive).

BTW, I think the papers Ivan sites (for those of us not familiar with  
the literature :-) are:

Feng Zhao, Jie Liu, Juan Liu, Leonidas Guibas, and James Reich,  
“Collaborative Signal and Information Processing: An Information  
Directed Approach”, Proceedings of the IEEE, vol. 91. No. 8, August,  
2003, pp. 1199-1209.

<http://research.microsoft.com/~zhao/pubs/ieee-sn.pdf>

Maurice Chu, Horst Haussecker, and Feng Zhao, "Scalable information- 
driven sensor querying and routing for ad hoc heterogeneous sensor  
networks." Int'l J. High Performance Computing Applications, 16(3): 
90-110, Fall 2002. Also, Xerox Palo Alto Research Center Technical  
Report P2001-10113, May 2001.

<http://research.microsoft.com/~zhao/pubs/idsq.pdf>

On Mar 30, 2006, at 7:40 PM, Ivan Krstic wrote:

>> The laptops, even used as an access point, will function much better
>> than the typical cheap access points you buy in a store.
>
> And there are various approaches to take here. One laptop won't be  
> able
> to serve as an AP to a thousand others if we enact the standard,
> fully-centralized AP model. But there's a lot of research[0] that  
> deals
> with data querying and routing in mesh networks; we could likely turn
> some of it inside out to provide a laptop AP mode that scales to large
> numbers of clients. We can't match the level of service provided by
> high-powered dedicated AP hardware, but we can make things work.
>
>
>
> [0] e.g. Zhao, Liu, Lui, Guibas and Reich (2003) or Chu, Haussecker,
> Zhao (2002)

--
Kevin Purcell
kevinpurcell at pobox.com