Hadoop 基礎架構
Hadoop包含了四大基本模組:
- Hadoop Common: The common utilities that support the other Hadoop modules.
- Hadoop Distributed File System (HDFS™): A distributed file system that provides high-throughput access to application data.
- Hadoop YARN: A framework for job scheduling and cluster resource management.
- Hadoop MapReduce: A YARN-based system for parallel processing of large data sets.
- Others: Spark RDD
MapReducer Programming Model
MapReducer可使用多種程式語言,但Java最快速。
-
內部邏輯
HDFS (Input) --> Splitting --> Mapping -->透過網路 --> Shuffling --> Reducing --> HDFS (Final Result)
MapReducer分成Map與Reduce,中間必須透過網路傳輸。
Shuffling: 負責資料彙整; 由YARN的Node Manager執行。
-
Mapreducer 與 Spark RDD 比較
MapReducer --> Disk Killer
Spark RDD --> Memory Killer
Hadoop 基礎架構
Hadoop包含了四大基本模組:
MapReducer Programming Model
MapReducer可使用多種程式語言,但Java最快速。
內部邏輯
HDFS (Input) --> Splitting --> Mapping -->透過網路 --> Shuffling --> Reducing --> HDFS (Final Result)
MapReducer分成Map與Reduce,中間必須透過網路傳輸。
Shuffling: 負責資料彙整; 由YARN的Node Manager執行。
Mapreducer 與 Spark RDD 比較
MapReducer --> Disk Killer
Spark RDD --> Memory Killer