SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
MapReduce: simplified data processing on large clusters
Communications of the ACM - 50th anniversary issue: 1958 - 2008
Quincy: fair scheduling for distributed computing clusters
Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles
Delay scheduling: a simple technique for achieving locality and fairness in cluster scheduling
Proceedings of the 5th European conference on Computer systems
An Analysis of Traces from a Production MapReduce Cluster
CCGRID '10 Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing
The Hadoop Distributed File System
MSST '10 Proceedings of the 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)
Hadoop: The Definitive Guide
Scarlett: coping with skewed content popularity in mapreduce clusters
Proceedings of the sixth conference on Computer systems
PACMan: coordinated memory caching for parallel jobs
NSDI'12 Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation
Dynamic server allocation to parallel queues with randomly varying connectivity
IEEE Transactions on Information Theory
Hi-index | 0.00 |
MapReduce/Hadoop framework has been widely used to process large-scale datasets on computing clusters. Scheduling map tasks to improve data locality is crucial to the performance of MapReduce. Many works have been devoted to increasing data locality for better efficiency. However, to the best of our knowledge, fundamental limits of MapReduce computing clusters with data locality, including the capacity region and throughput optimal algorithms, have not been studied. In this paper, we address these problems from a stochastic network perspective. Our focus is to strike the right balance between data-locality and load-balancing to maximize throughput. We present a new queueing architecture and propose a map task scheduling algorithm constituted by the Join the Shortest Queue policy together with the MaxWeight policy. We identify an outer bound on the capacity region, and then prove that the proposed algorithm can stabilize any arrival rate vector strictly within this outer bound. It shows that the algorithm is throughput optimal and the outer bound coincides with the actual capacity region. The proofs in this paper deal with random processing time with different parameters and nonpreemptive tasks, which differentiate our work from many other works, so the proof technique itself is also a contribution of this paper.