Improving MapReduce performance through data placement in heterogeneous Hadoop clusters.
Jiong XieShu YinXiaojun RuanZhiyang DingYun TianJames MajorsAdam ManzanaresXiao QinPublished in: IPDPS Workshops (2010)
Keyphrases
- data placement
- cloud computing
- data center
- distributed environment
- high availability
- distributed computing
- mapreduce framework
- data partitioning
- map reduce
- query optimization
- access patterns
- clustering algorithm
- hierarchical clustering
- distributed systems
- parallel processing
- data storage
- range queries
- distributed database systems
- wireless broadcast
- b tree
- data points
- database
- data analytics
- data structure