Enhancing reliability and response times via replication in computing clusters

Zhan Qiu, Juan F. Perez

Research output: Chapter in Book/ReportConference contribution

18 Scopus citations

Abstract

Computing clusters have been widely deployed for scientific and engineering applications to support intensive computation and massive data operations. As applications and resources in a cluster are subject to failures, fault-tolerance strategies are commonly adopted, sometimes at the expense of additional delays in job response times, or unnecessarily increasing resource usage. In this paper, we explore concurrent replication with canceling, a fault-tolerance approach where jobs and their replicas are processed concurrently, and the successful completion of either triggers the removals of its replica. We propose a stochastic model to study how this approach affects the cluster service level objectives (SLOs), particularly the offered response time percentiles. In addition to the expected gains in reliability, the proposed model allows us to determine the regions of the utilization where introducing replication with canceling effectively reduces the response times. Moreover, we show how this model can support resource provisioning decisions with reliability and response time guarantees.

Translated title of the contributionMejora de la fiabilidad y los tiempos de respuesta mediante la replicación en clústeres informáticos
Original languageEnglish (US)
Title of host publication2015 IEEE Conference on Computer Communications, IEEE INFOCOM 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1355-1363
Number of pages9
Volume26
ISBN (Electronic)9781479983810
DOIs
StatePublished - Aug 21 2015
Externally publishedYes
Event34th IEEE Annual Conference on Computer Communications and Networks, IEEE INFOCOM 2015 - Hong Kong, Hong Kong
Duration: Apr 26 2015May 1 2015

Conference

Conference34th IEEE Annual Conference on Computer Communications and Networks, IEEE INFOCOM 2015
Country/TerritoryHong Kong
CityHong Kong
Period4/26/155/1/15

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Enhancing reliability and response times via replication in computing clusters'. Together they form a unique fingerprint.

Cite this