From: A Pareto-based scheduler for exploring cost-performance trade-offs for MapReduce workloads
Workload | Jobs | No. of map tasks | No. of reduce tasks | Deadline (s) | Input size |
---|---|---|---|---|---|
Twitter friendship | 3 | 20 | 10 | 1000 | 1.2 GB tweetsa |
Sort | 3 | 80 | 10 | 2500 | 5 GB random data |
Wordcount | 3 | 47 | 10 | 1000 | 3.2 GB movie reviews |
Twitter-Wordcount | 1 Twitter and | 20 Twitter and | 10 Twitter and | 1000 | 3.2 GB movie reviews |
2 Wordcount | 47 Wordcount | 10 Wordcount | and 1.2 GB tweets |