Redpill me on Hadoop/Apache Spark

What the fuck is MapReduce?

Technically, it's Map-shuffle-Reduce

As such, a single-threaded implementation of MapReduce will usually not be faster than a traditional (non-MapReduce) implementation; any gains are usually only seen with multi-threaded implementations.[9] The use of this model is beneficial only when the optimized distributed shuffle operation (which reduces network communication cost) and fault tolerance features of the MapReduce framework come into play. Optimizing the communication cost is essential to a good MapReduce algorithm.[10]

>>2

still doesn't explain what the fuck it is

explain it like I'm retarded

>>1
Enterprise-grade Functional Programming

>>3
Some funny way of reordering a data processing step when there's heaps of data and many cores, for processing gains. Could just be a memoization-like trick (eg, direct data to the core with the memo/look-up) or something fancier
Supposed to not work as well for repeated access, like iterative learning