karanth/ln-compute-II.md

## ln-compute-II.md

      
    Raw
  

              ln-compute-II.md
            
          
    Data to the compute vs Compute to the data
Data Streaming vs MapReduce
MapReduce model
"Program once, deploy at scale"
Allows programmers without background in parallel/distributed computing to use the distributed systems efficiently.
batch processing
Streaming model
No random access to data
Limited memory, single CPU
single pass, multiple pass within a window
Low-latency