We will talk about MapReduce and HDFS in detail later. Let's go through the evolution of Hadoop, which looks as follows:
|
Year
|
Event
|
|
2003
|
- Research paper for Google File System released
|
|
2004
|
- Research paper for MapReduce released
|
|
2006
|
- JIRA, mailing list, and other documents created for Hadoop
- Hadoop Nutch created
- Hadoop created by moving out NDFS and MapReduce from Nutch
- Doug Cutting names the project Hadoop, which was the name of his son's yellow elephant toy
- Release of Hadoop 0.1.0
- 1.8 TB of data sorts on 188 nodes, which took 47.9 hours
- Three hundred machines deployed at Yahoo! for the Hadoop cluster
- Cluster size at Yahoo! increases to 600
|
|
2007
|
- Two clusters of 1,000 machines run by Yahoo!
- Hadoop ...
|