On submission of the job by the User, Hadoop initiates the Job Tracker process at Master Node. Internally, the execution undergoes 3 major tasks/steps as below:
A map task is created that runs the user-supplied map function on each record. The map function takes a key-value pair as input and produces zero or more intermediate key-value pairs. Map tasks are executed in parallel by various machines across the cluster.
Mapper output (intermediate data) is stored on the Local file system (NOT HDFS) of each individual mapper nodes. This is typically a temporary directory location which can be setup in config by the Hadoop administrator. The intermediate data is cleaned up after the Hadoop Job completes.
2. Shuffle and Sort
It is preformed by the reducers (reduce tasks). Each reducer is assigned one of the partitions on which it should work. This is a flurry of network copies between each reducer in the cluster so it can get the partition (intermediate key-value) data it was assigned to work on.
The output of the reduce is normally stored in HDFS for reliability. This step uses a lot of bandwidth between servers and benefits from very fast networking like 10G.
After the partition data has been copied we can start performing a merge sort of the data. A merge sort takes a number of sorted items and merges them together to form a fully sorted list.
Each reducer produces a separate output file, usually in HDFS. Each reducer output file usually named part-, where is the number of the reduce task within the job. The output format of the file is specified by the author of the MapReduce job. The number of reducers is defined by the developer.
Attached image depicts the execution flow of Hadoop job.