Find me an open-source MapReduce framework that runs on top of Shard-Query.
It is ok if you want to code it yourself and publish as open-source, then submit it here as your deliverable (you may submit first if you want to prevent other developers from finding it). The work must be delivered fully documented and reasonably well tested, like a typical open-source project.
These are my requirements:
I want a framework for running MapReduce jobs in parallel using Shard-Query (MYSQL) as the data source. The framework must be smart about number of cores, and number of shards, to accomplish full parallel execution.
It is not necessary for the framework to run distributed on multiple machines. For this first version I'm happy to run it in a single massively multi-core machine (EC2 10xlarge).
5 freelancere byder i gennemsnit $403 på dette job
Hi I work towards providing reliable, relevant and robust IT solutions at most competitive prices to my customers. I ensure 100% customer satisfaction so lets start Thanks