The architecture of the Hadoop architecture for HDFs

The architecture of Hadoop

Hadoop is not only a distributed file system for distributed storage, but a framework designed to perform distributed applications on large clusters of common computing devices.

HDFs and MapReduce are the two most basic, most important members of Hadoop, providing complementary services or higher-level services at the core level.

Pig Chukwa Hive HBase
MapReduce HDFS Zookeeper
Core Avro

1. The design goal of HDFs

2. The structure model of HDFS

3. File System Namespace namespace

4. Copying and storage of data

5. Persistence of File system metadata

6. HDFs Communication Protocol

7. The robustness of HDFs

8. Data organization of HDFS

9, the accessibility of HDFs

10. Storage space Recovery of HDFS

The architecture of the Hadoop architecture for HDFs