Ítem
Solo Metadatos

Tackling latency via replication in distributed systems

Mostrar el registro sencillo de la publicación
dc.creatorQiu, Zhanspa
dc.creatorPérez, Juan F.spa
dc.creatorHarrison, Peter Gspa
dc.date.accessioned2020-08-28T15:49:15Z
dc.date.available2020-08-28T15:49:15Z
dc.date.created2016-03spa
dc.description.abstractConsistently high reliability and low latency are twin requirements common to many forms of distributed processing; for example, server farms and mirrored storage access. To address them, we consider replication of requests with canceling – i.e. initiate multiple concurrent replicas of a request and use the first successful result returned, canceling all outstanding replicas. This scheme has been studied recently, but mostly for systems with a single central queue, while server farms exploit distributed resources for scalability and robustness. We develop an approximate stochastic model to determine the response-time distribution in a system with distributed queues, and compare its performance against its centralized counterpart. Validation against simulation indicates that our model is accurate for not only the mean response time but also its percentiles, which are particularly relevant for deadline-driven applications. Further, we show that in the distributed set-up, replication with canceling has the potential to reduce response times, even at relatively high utilization. We also find that it offers response times close to those of the centralized system, especially at medium-to-high request reliability. These findings support the use of replication with canceling as an effective mechanism for both fault- and delay-tolerance.eng
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.1145/2851553.2851562
dc.identifier.issnISBN: 978-1-4503-4080-9
dc.identifier.urihttps://repository.urosario.edu.co/handle/10336/28507
dc.language.isoengspa
dc.publisherAssociation for Computing Machineryspa
dc.relation.citationTitleICPE 16: Proceedings of the 7th ACM/SPEC on International Conference on Performance Engineering;ICPE`16: ACM/SPEC International Conference on Performance Engineering Delft The Netherlands March, 2016
dc.relation.ispartofICPE '16: Proceedings of the 7th ACM/SPEC on International Conference on Performance Engineeringspa
dc.relation.ispartofICPE'16: ACM/SPEC International Conference on Performance Engineering Delft The Netherlands, ISBN: 978-1-4503-4080-9 (March, 2016); pp. 197-208spa
dc.relation.urihttps://dl.acm.org/doi/abs/10.1145/2851553.2851562spa
dc.rights.accesRightsinfo:eu-repo/semantics/restrictedAccess
dc.rights.accesoRestringido (Acceso a grupos específicos)spa
dc.sourceICPE '16: Proceedings of the 7th ACM/SPEC on International Conference on Performance Engineeringspa
dc.sourceICPE'16: ACM/SPEC International Conference on Performance Engineering Delft The Netherlands March, 2016spa
dc.source.instnameinstname:Universidad del Rosario
dc.source.reponamereponame:Repositorio Institucional EdocUR
dc.subject.keywordLatency-tolerancespa
dc.subject.keywordFault-tolerancespa
dc.subject.keywordMatrix-analytic methodsspa
dc.subject.keywordResponse time distributionspa
dc.subject.keywordDistributed systemspa
dc.titleTackling latency via replication in distributed systemsspa
dc.title.TranslatedTitleAbordar la latencia mediante la replicación en sistemas distribuidosspa
dc.typebookParteng
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersion
dc.type.spaParte de librospa
Archivos
Colecciones
Libros