Performance characterization and acceleration of in-memory file systems for Hadoop and Spark applications on HPC clusters.
Nusrat Sharmin IslamMd. Wasi-ur-RahmanXiaoyi LuDipti ShankarDhabaleswar K. PandaPublished in: IEEE BigData (2015)
Keyphrases
- file system
- scientific computing
- storage devices
- flash memory
- data transfer
- storage systems
- clustering algorithm
- open source
- access patterns
- hierarchical clustering
- high performance computing
- data points
- big data
- random access
- search tools
- distributed data
- memory requirements
- cloud computing
- fault tolerance
- map reduce
- distributed systems
- continuous media
- hard disk
- multi tiered
- software package
- application specific
- data management
- scalable distributed