Jockey: guaranteed job latency in data parallel clusters.
Andrew D. FergusonPeter BodíkSrikanth KandulaEric BoutinRodrigo FonsecaPublished in: EuroSys (2012)
Keyphrases
- data points
- database
- raw data
- data quality
- data processing
- data structure
- data sets
- data objects
- data distribution
- data collection
- input data
- image data
- data analysis
- training data
- low latency
- xml documents
- statistical analysis
- synthetic data
- web pages
- databases
- high throughput
- data samples
- data transfer
- parallel implementation
- input space
- fuzzy clustering
- clustering algorithm
- probability distribution
- spatial data
- high dimensional
- semi supervised