Many people have asked Ali Legend data platform, ladder 2, MaxCompute, real-time computing in the end what is, and what is the difference self Hadoop platform.
Let me talk about Hadoop
What is Hadoop?
Hadoop is an open, highly reliable, scalable, distributed computing frameworks large data systems, mainly used to solve the mass data storage, analysis, distributed resource scheduling. The biggest advantage is the ability to provide Hadoop parallel computing, using the full power of a cluster of high-speed computing and storage.
The core Hadoop has two main sections: HDFS and MapReduce.
HDFS full name of the Hadoop Distributed File System, is a distributed file storage system. Distributed File System refers to a fixed location of a file system, be extended to any number of file systems, a large number of nodes a network file system. Each node may be distributed in different locations, for communication and data transfer between nodes via a network. When people use a distributed file system, without concern for which data is stored on the node