Automatic Tuning of the Keep-alive Parameter of Web Servers based on Request-waiting Intervals.

Akiyoshi Sugiki, Kenji Kono, Hideya Iwasaki

Research output: Contribution to journalArticle

Abstract

Manual parameter-tuning of Internet servers causes high administrative costs because it requires administrator's expertise and huge amounts of time. The keep-alive parameter, which is one of major parameters in web servers, may cause severe degradation if it is not set properly. In this paper, we present an automatic tuning technique of the keep-alive parameter. Our mechanism adjusts the parameter without administrator's intervention so as to maintain active connections between clients and a server while closing inactive connections by observing request-waiting intervals. We implemented a prototype for Apache web server. Experimental results show that our prototype automatically adjusted the parameter and successfully yielded the nearly optimal server performance on two different workloads.

Original languageEnglish
Pages (from-to)68-78
Number of pages11
JournalComputer Software
Volume24
Issue number2
DOIs
Publication statusPublished - 2007

Fingerprint

Servers
Tuning
Internet
Degradation
Costs

ASJC Scopus subject areas

  • Software

Cite this

Automatic Tuning of the Keep-alive Parameter of Web Servers based on Request-waiting Intervals. / Sugiki, Akiyoshi; Kono, Kenji; Iwasaki, Hideya.

In: Computer Software, Vol. 24, No. 2, 2007, p. 68-78.

Research output: Contribution to journalArticle

@article{94c6ab717615407ebeed1f8c8dc96e73,
title = "Automatic Tuning of the Keep-alive Parameter of Web Servers based on Request-waiting Intervals.",
abstract = "Manual parameter-tuning of Internet servers causes high administrative costs because it requires administrator's expertise and huge amounts of time. The keep-alive parameter, which is one of major parameters in web servers, may cause severe degradation if it is not set properly. In this paper, we present an automatic tuning technique of the keep-alive parameter. Our mechanism adjusts the parameter without administrator's intervention so as to maintain active connections between clients and a server while closing inactive connections by observing request-waiting intervals. We implemented a prototype for Apache web server. Experimental results show that our prototype automatically adjusted the parameter and successfully yielded the nearly optimal server performance on two different workloads.",
author = "Akiyoshi Sugiki and Kenji Kono and Hideya Iwasaki",
year = "2007",
doi = "10.11309/jssst.24.2_68",
language = "English",
volume = "24",
pages = "68--78",
journal = "Computer Software",
issn = "0289-6540",
publisher = "Japan Society for Software Science and Technology",
number = "2",

}

TY - JOUR

T1 - Automatic Tuning of the Keep-alive Parameter of Web Servers based on Request-waiting Intervals.

AU - Sugiki, Akiyoshi

AU - Kono, Kenji

AU - Iwasaki, Hideya

PY - 2007

Y1 - 2007

N2 - Manual parameter-tuning of Internet servers causes high administrative costs because it requires administrator's expertise and huge amounts of time. The keep-alive parameter, which is one of major parameters in web servers, may cause severe degradation if it is not set properly. In this paper, we present an automatic tuning technique of the keep-alive parameter. Our mechanism adjusts the parameter without administrator's intervention so as to maintain active connections between clients and a server while closing inactive connections by observing request-waiting intervals. We implemented a prototype for Apache web server. Experimental results show that our prototype automatically adjusted the parameter and successfully yielded the nearly optimal server performance on two different workloads.

AB - Manual parameter-tuning of Internet servers causes high administrative costs because it requires administrator's expertise and huge amounts of time. The keep-alive parameter, which is one of major parameters in web servers, may cause severe degradation if it is not set properly. In this paper, we present an automatic tuning technique of the keep-alive parameter. Our mechanism adjusts the parameter without administrator's intervention so as to maintain active connections between clients and a server while closing inactive connections by observing request-waiting intervals. We implemented a prototype for Apache web server. Experimental results show that our prototype automatically adjusted the parameter and successfully yielded the nearly optimal server performance on two different workloads.

UR - http://www.scopus.com/inward/record.url?scp=85024734532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024734532&partnerID=8YFLogxK

U2 - 10.11309/jssst.24.2_68

DO - 10.11309/jssst.24.2_68

M3 - Article

AN - SCOPUS:85024734532

VL - 24

SP - 68

EP - 78

JO - Computer Software

JF - Computer Software

SN - 0289-6540

IS - 2

ER -