What is the process used by Hadoop to perform input splits?

edit

Hadoop divides input data into fixed-size chunks called input splits. The process of input splitting is carried out by the following steps:

1. The Hadoop framework first determines the size of the input data by consulting the underlying file system.

2. It then calculates the total number of input splits based on the size of the data and the size of the default block size in HDFS.

3. Hadoop then assigns each split to a different mapper task to ensure parallel processing.

4. The framework also considers the location of the data on the nodes in the cluster to ensure that the execution of the task is closest to where the data is stored, to minimize data movement.

5. Once the input splits have been created, they are sent to the mapper functions for further processing.