Hi,
seems like the perfect use case for Map Reduce yep.
2011/5/26 Mirko Kämpf :
> Hello,
>
> we are working on a scientific project to analyze information spread in
> networks. Our simulations are independent from each other but we need a
> large amount of runs and we have to collect all data for the interpretation
> of results by our reporting tools. So my was to use hadoop as a base, with
> its distributed filesystem. So we could start independent runs on each node
> of the cluster and at the end we collect the data for the calculation of
> average values. The simulation tool is written in java and consists of about
> 2 MB jar files.
> Is this a situation there hadoop can help us?
> One fact is, that we want to parallize the production of large data sets.
> Best wishes
> Mirko
>