To take full advantage of an in-memory platform, it’s often not enough to upload your data into a cluster and start querying it with key-value or SQL APIs. You need to distribute the data efficiently and tap into distributed computations that minimize data movement over the network.
In this webinar, you’ll see how to design and execute distributed computations considering all the pros and cons. In particular, the following will be covered:
- How to distribute data in the cluster with proper data modeling and affinity collocation
- How MapReduce APIs are implemented and work in Apache Ignite
- How to minimize operations latencies by collocating data with compute
- How complex SQL queries rely on the MapReduce concept internally to execute efficiently in a distributed environment
The webinar will be useful for those who would like to optimally design and run distributed computations in Apache Ignite.