Efficient Coflow Scheduling Without Prior Knowledge

Abstract

Inter-coflow scheduling improves application-level communication performance in data-parallel clusters. However, existing efficient schedulers require a priori coflow information and ignore cluster dynamics like pipelining, task failures, and speculative executions, which limit their applicability. Schedulers without prior knowledge compromise on performance to avoid head-of-line blocking. In this paper, we present Aalo that strikes a balance and efficiently schedules coflows without prior knowledge.

Document Details

Document Type
Pub Defense Publication
Publication Date
Aug 17, 2015
Source ID
10.1145/2829988.2787480

Entities

People

  • Ion Stoica
  • Mosharaf Chowdhury

Organizations

  • Defense Advanced Research Projects Agency
  • Lawrence Berkeley National Laboratory
  • National Science Foundation
  • University of California, Berkeley

Tags

Fields of Study

  • Computer science

Readers

  • Combustion science or combustion engineering.
  • Educational Psychology
  • Parallel and Distributed Computing.