C3: Cutting tail latency in cloud data stores via adaptive replica selection

Lalith Suresh, Marco Canini, Stefan Schmid, Anja Feldmann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

97 Scopus citations

Abstract

Achieving predictable performance is critical for many distributed applications, yet difficult to achieve due to many factors that skew the tail of the latency distribution even in well-provisioned systems. In this paper, we present the fundamental challenges involved in designing a replica selection scheme that is robust in the face of performance fluctuations across servers. We illustrate these challenges through performance evaluations of the Cassandra distributed database on Amazon EC2. We then present the design and implementation of an adaptive replica selection mechanism, C3, that is robust to performance variability in the environment. We demonstrate C3's effectiveness in reducing the latency tail and improving throughput through extensive evaluations on Amazon EC2 and through simulations. Our results show that C3 significantly improves the latencies along the mean, median, and tail (up to 3 times improvement at the 99.9th percentile) and provides higher system throughput.

Original languageEnglish (US)
Title of host publicationProceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2015
PublisherUSENIX
Pages513-527
Number of pages15
ISBN (Electronic)9781931971218
StatePublished - Jan 1 2015
Event12th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2015 - Oakland, United States
Duration: May 4 2015May 6 2015

Publication series

NameProceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2015

Other

Other12th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2015
CountryUnited States
CityOakland
Period05/4/1505/6/15

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'C3: Cutting tail latency in cloud data stores via adaptive replica selection'. Together they form a unique fingerprint.

Cite this