The MapReduce framework and its open source implementation Hadoop have become the defacto platform for scalable analysis on large data sets in recent years. One of the primary concerns in Hadoop is how to minimize the completion length (i.e., makespan) of a set of MapReduce jobs. The current Hadoop only allows static slot configuration, i.e., fixed numbers of map slots and reduce slots throughout the lifetime of a cluster. However, we found that such a static configuration may lead to low system resource utilizations as well as long completion length. Motivated by this, we propose a simple yet effective scheme which uses slot ratio between map and reduce tasks as a tunable knob for reducing the makespan of a given set. By leveraging the workload information of recently completed jobs, our scheme dynamically allocates resources (or slots) to map and reduce tasks. We implemented the presented scheme in Hadoop V0.20.2 and evaluated it with representative MapReduce benchmarks at Amazon EC2. The experimental results demonstrate the effectiveness and robustness of our scheme under both simple workloads and more complex mixed workloads.
|Number of pages||8|
|Journal||IEEE International Conference on Cloud Computing, CLOUD|
|Publication status||Published - 1 Dec 2013|
|Event||2013 IEEE 6th International Conference on Cloud Computing, CLOUD 2013 - Santa Clara, CA, United States|
Duration: 27 Jun 2013 → 2 Jul 2013