A Comprehensive Study of MapReduce Over Lustre for Intermediate Data Placement and Shuffle Strategies on HPC Clusters.
Md. Wasi-ur-RahmanNusrat Sharmin IslamXiaoyi LuDhabaleswar K. PandaPublished in: IEEE Trans. Parallel Distributed Syst. (2017)
Keyphrases
- data placement
- high availability
- query optimization
- data partitioning
- fault tolerance
- clustering algorithm
- distributed environment
- parallel processing
- high performance computing
- access patterns
- data center
- hierarchical clustering
- wireless broadcast
- distributed database systems
- storage systems
- cloud computing
- data storage
- fault tolerant
- range queries
- xml queries
- cost effective
- distributed computing
- prefetching