DARE: Adaptive data replication for efficient cluster scheduling

Cristina L. Abad, Yi Lu, Roy H. Campbell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Placing data as close as possible to computation is a common practice of data intensive systems, commonly referred to as the data locality problem. By analyzing existing production systems, we confirm the benefit of data locality and find that data have different popularity and varying correlation of accesses. We propose DARE, a distributed adaptive data replication algorithm that aids the scheduler to achieve better data locality. DARE solves two problems, how many replicas to allocate for each file and where to place them, using probabilistic sampling and a competitive aging algorithm independently at each node. It takes advantage of existing remote data accesses in the system and incurs no extra network usage. Using two mixed workload traces from Face book, we show that DARE improves data locality by more than 7 times with the FIFO scheduler in Hadoop and achieves more than 85% data locality for the FAIR scheduler with delay scheduling. Turnaround time and job slowdown are reduced by 19% and 25%, respectively.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 IEEE International Conference on Cluster Computing, CLUSTER 2011
Pages159-168
Number of pages10
DOIs
StatePublished - 2011
Event2011 IEEE International Conference on Cluster Computing, CLUSTER 2011 - Austin, TX, United States
Duration: Sep 26 2011Sep 30 2011

Publication series

NameProceedings - IEEE International Conference on Cluster Computing, ICCC
ISSN (Print)1552-5244

Other

Other2011 IEEE International Conference on Cluster Computing, CLUSTER 2011
CountryUnited States
CityAustin, TX
Period9/26/119/30/11

Keywords

  • MapReduce
  • locality
  • replication
  • scheduling

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Signal Processing

Fingerprint Dive into the research topics of 'DARE: Adaptive data replication for efficient cluster scheduling'. Together they form a unique fingerprint.

Cite this