Amazon Thursday added Hadoop number crunching to its other cloud skills.
It's put out a public beta of a new Web Service called Elastic MapReduce for processing vast amounts of data using a hosted Hadoop framework running on its giant EC2/S3 infrastructure.
It says the widgetry can instantly provision as much or as little capacity as the user wants to do data-intensive tasks for distributed applications such as web indexing, data mining, log file analysis, machine learning, financial analysis, scientific simulation and bioinformatics research at pay-as-you-go prices.
Amazon claims it's taken the pain out of running Hadoop, which - like other MapReduce-based clusters - used to involve time-consuming set-up, management and cluster tuning.
With Elastic MapReduce, it says, users should be able spin up and tear down Hadoop clusters at "a moment's notice."
It's got sample applications and tutorials to show people how.
Amazon Web Services VP of product management and developer relations Adam Selipsky said some researchers and developers had been running Hadoop on EC2 for large-scale data analysis and asked for simpler tools.
As the processing is completed, data is re-combined and reduced into a final solution, and the results returned to S3.
Users can configure, manipulate and monitor job flows through web service APIs or the AWS Management Console.
0 comments:
Post a Comment