<br><br><div class="gmail_quote">2009/2/25 Alberto G. Corona <span dir="ltr"><<a href="mailto:agocorona@gmail.com">agocorona@gmail.com</a>></span><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
And it would solve a lot of problem: scalability, system re-configuraition and installation: just by adding or removing nodes at runtime.. heavy numerical computations are also good candidates. <div><br></div><div><div>
<br><div class="gmail_quote">2009/2/25 Rick R <span dir="ltr"><<a href="mailto:rick.richardson@gmail.com" target="_blank">rick.richardson@gmail.com</a>></span><div><div></div><div class="Wj3C7c"><br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">I agree. A distributed database could be made as usable as a standard<br>
RDBMS by offering an interface by which you supply a map/reduce pair<br>
of functions and a list (range?) of keys.<br>
<br>
This could be easily implemented with a database such as Scalaris, in<br>
which the Chord algorithm is responsible for placing and finding the<br>
data among nodes.<br>
<br>
The user would interface with any node in the distributed database,<br>
supplying a map and reduce function. It would distribute the map<br>
function to nodes of its choosing (weighted by some metrics such as<br>
idle cpu), retrieve the intermediate sets and run reduce if supplied.<br>
<br>
<br>
2009/2/25 Alberto G. Corona <<a href="mailto:agocorona@gmail.com" target="_blank">agocorona@gmail.com</a>>:<br>
<div><div></div><div>> Galchin,<br>
><br>
> Maybe you are asking not only about remote execution, but also mobility of<br>
> code. This is a problem that is previous to mapReduce, since mapReduce<br>
> assumes that all the code (and the data) is in place in the respective<br>
> nodes. In fact, the distribution of resources in order to efficiently use<br>
> mapReduce is a design problem that the google people has done by hand.<br>
> But my intuition says that there are a general algorithm for distribution<br>
> of code, data, bandwidth and resources in general that moves around at<br>
> execution time to achieve better and better performance for a given grid of<br>
> nodes and for any task, for example, a mapReduce task. I would be very<br>
> interesting to read something about this.<br>
> I know that some efforts have been carried out the past , for example mobile<br>
> haskell<br>
> <a href="http://homepages.inf.ed.ac.uk/stg/workshops/TFP/book/DuBois/duboismhaskell/cameraready.pdf" target="_blank">http://homepages.inf.ed.ac.uk/stg/workshops/TFP/book/DuBois/duboismhaskell/cameraready.pdf</a><br>
> which is a first step for this goal but I this has been discontinued and the<br>
> source code is not available.<br>
><br>
> 2009/2/25 Galchin, Vasili <<a href="mailto:vigalchin@gmail.com" target="_blank">vigalchin@gmail.com</a>><br>
>><br>
>> Hello,<br>
>><br>
>> Here is an interesting paper of Google's MapReduce reverse engineered<br>
>> into Haskell. I apologize if already posted .....<br>
>> <a href="http://www.cs.vu.nl/~ralf/MapReduce/" target="_blank">http://www.cs.vu.nl/~ralf/MapReduce/</a><br>
>><br>
>> Kind regards, Vasili<br>
>><br>
>> _______________________________________________<br>
>> Haskell-Cafe mailing list<br>
>> <a href="mailto:Haskell-Cafe@haskell.org" target="_blank">Haskell-Cafe@haskell.org</a><br>
>> <a href="http://www.haskell.org/mailman/listinfo/haskell-cafe" target="_blank">http://www.haskell.org/mailman/listinfo/haskell-cafe</a><br>
>><br>
><br>
><br>
> _______________________________________________<br>
> Haskell-Cafe mailing list<br>
> <a href="mailto:Haskell-Cafe@haskell.org" target="_blank">Haskell-Cafe@haskell.org</a><br>
> <a href="http://www.haskell.org/mailman/listinfo/haskell-cafe" target="_blank">http://www.haskell.org/mailman/listinfo/haskell-cafe</a><br>
><br>
><br>
<br>
<br>
<br>
</div></div><font color="#888888">--<br>
We can't solve problems by using the same kind of thinking we used<br>
when we created them.<br>
- A. Einstein<br>
</font></blockquote></div></div></div><br>
</div></div>
</blockquote></div><br>