earticle

논문검색

A Reduce Task Scheduler for MapReduce with Minimum Transmission Cost Based on Sampling Evaluation

초록

영어

MapReduce is a popular framework for processing large datasets in parallel over a cluster. It has gained wide attention for its high scalability, reliability and low cost. However, its performance may be degraded by excessive network traffic when processing jobs, for such two problems as data locality in reduce task scheduling and partitioning skew. We propose a Minimum Transmission Cost Reduce task Scheduler (MTCRS) based on sampling evaluation to solve the two problems. The MTCRS takes the waiting time of each reduce task and the transmission cost set as indicators to decide appropriate launching locations for Reduce tasks. The transmission cost set is computed by a mathematical model, in which the parameters are the sizes and the locations of intermediate data partitions generated by Average Reservoir Sampling (ARS) algorithm. The experiments show that the MTCRS reduces network traffic by 8.4% compared with Fair scheduler.

목차

Abstract
 1. Introduction
  1.1. Data Locality in Reduce Tasks Scheduling
  1.2. Partitioning Skew
 2. Background and Related Work
  2.1. The Process from Job Submission to Job Launching
  2.2. Typical Network Topology of Hadoop Cluster
  2.3. Research on Task Scheduling
 3. The Design of the New Reduce Task Scheduler
  3.1. ARS Sampling Algorithm
  3.2. Transmission Cost Mathematical Model
  3.3. MTCRS
 4. Experiments and Evaluation
  4.1. Environment and Datasets
  4.2. ARS
  4.3. MTCRS
 5. Conclusion and Future Work
 Acknowledgements
 References

저자정보

  • Xia Tang College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, 10029, China
  • Lijun Wang Network Research Center, Tsinghua University, Beijing 100084, China
  • Zhiqiang Geng College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, 10029, China

참고문헌

    ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

    0개의 논문이 장바구니에 담겼습니다.