Using a Tunable Knob for Reducing Makespan of MapReduce Jobs in a Hadoop Cluster.
Yi YaoJiayin WangBo ShengNingfang MiPublished in: IEEE CLOUD (2013)
Keyphrases
- mapreduce framework
- processing times
- cloud computing
- flowshop
- scheduling problem
- release dates
- batch processing
- scheduling jobs
- unrelated parallel machines
- permutation flowshop
- single machine
- open shop
- minimizing makespan
- large scale data sets
- map reduce
- strongly np hard
- parallel machine scheduling problem
- setup times
- sequence dependent setup times
- parallel machines
- data intensive
- distributed computing
- precedence constraints
- deteriorating jobs
- single machine scheduling problem
- big data
- tabu search
- data management
- frequent itemset mining
- release times
- open source
- job scheduling
- real world
- cluster analysis
- clustering algorithm
- optimal solution
- maximum lateness
- np hard
- special case
- distributed systems
- data sets
- identical parallel machines
- data analytics
- job shop
- data clustering
- approximation algorithms