Understanding the behavior of Spark workloads from Linux kernel parameters perspective

Li Wang, Tianni Xu, Jing Wang*, Weigong Zhang, Xiufeng Sui, Yungang Bao

*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

Despite a number of innovative computer systems with high capacity memory have been built, the design principles behind an operating system kernel have remained unchanged for decades. We argue that kernel parameters is a kind of special interface of operating system and must be factored into the operation and maintenance of datacenters. To shed some light on the effectiveness of tuning Linux parameters of virtual memory subsystem when running Spark workloads, we evaluate the benchmarks in a simple standalone deploy mode. Our performance results reveal that some of the Linux memory parameters must be carefully set to efficiently support these processing workloads. We hope this work yields insights for datacenter system operators.

Original languageEnglish
Title of host publicationProceedings of the Posters and Demos Session of the ACM/IFIP/USENIX Middleware 2016 Conference, Middleware Posters and Demos 2016
PublisherAssociation for Computing Machinery, Inc
Pages1-2
Number of pages2
ISBN (Electronic)9781450346665
DOIs
Publication statusPublished - 12 Dec 2016
Externally publishedYes
EventACM/IFIP/USENIX International Middleware Conference, Middleware Posters and Demos 2016 - Trento, Italy
Duration: 12 Dec 201616 Dec 2016

Publication series

NameProceedings of the Posters and Demos Session of the ACM/IFIP/USENIX Middleware 2016 Conference, Middleware Posters and Demos 2016

Conference

ConferenceACM/IFIP/USENIX International Middleware Conference, Middleware Posters and Demos 2016
Country/TerritoryItaly
CityTrento
Period12/12/1616/12/16

Keywords

  • Datacenters
  • Linux
  • Parameters
  • Spark
  • Virtual memory

Fingerprint

Dive into the research topics of 'Understanding the behavior of Spark workloads from Linux kernel parameters perspective'. Together they form a unique fingerprint.

Cite this