Tuning mechanisms for two major parameters of Apache web servers

Akiyoshi Sugiki, Kenji Kono, Hideya Iwasaki

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Apache web servers are widely used as stand-alone servers or front-ends in multi-tiered web servers. Despite the wide availability of software, it is quite difficult for many administrators to properly configure their web servers. In particular, setting the performance-related parameters is an error-prone and timeconsuming task because their values heavily depend on the server environment. In this paper, two mechanisms are described for automatically tuning two performance-related parameters of Apache web servers: KeepAliveTimeout and MaxClients. These mechanisms are easy to deploy because no modifications to the server or the operating system are required. Moreover, they are parameter specific. Although interference between KeepAliveTimeout and MaxClients is inevitable, the tuning mechanisms minimize the correlation by using almost completely independent metrics. Experimental results show that these mechanisms work well for two different workloads; the parameter values are close to optimal and can adapt to workload changes.

Original languageEnglish
Pages (from-to)1215-1240
Number of pages26
JournalSoftware - Practice and Experience
Volume38
Issue number12
DOIs
Publication statusPublished - 2008 Oct

Fingerprint

Servers
Tuning
Computer operating systems
Availability

Keywords

  • Parameter tuning
  • Server management
  • Web servers

ASJC Scopus subject areas

  • Software

Cite this

Tuning mechanisms for two major parameters of Apache web servers. / Sugiki, Akiyoshi; Kono, Kenji; Iwasaki, Hideya.

In: Software - Practice and Experience, Vol. 38, No. 12, 10.2008, p. 1215-1240.

Research output: Contribution to journalArticle

Sugiki, Akiyoshi ; Kono, Kenji ; Iwasaki, Hideya. / Tuning mechanisms for two major parameters of Apache web servers. In: Software - Practice and Experience. 2008 ; Vol. 38, No. 12. pp. 1215-1240.
@article{a7b5081c6ec84b0993ae41422e441b4f,
title = "Tuning mechanisms for two major parameters of Apache web servers",
abstract = "Apache web servers are widely used as stand-alone servers or front-ends in multi-tiered web servers. Despite the wide availability of software, it is quite difficult for many administrators to properly configure their web servers. In particular, setting the performance-related parameters is an error-prone and timeconsuming task because their values heavily depend on the server environment. In this paper, two mechanisms are described for automatically tuning two performance-related parameters of Apache web servers: KeepAliveTimeout and MaxClients. These mechanisms are easy to deploy because no modifications to the server or the operating system are required. Moreover, they are parameter specific. Although interference between KeepAliveTimeout and MaxClients is inevitable, the tuning mechanisms minimize the correlation by using almost completely independent metrics. Experimental results show that these mechanisms work well for two different workloads; the parameter values are close to optimal and can adapt to workload changes.",
keywords = "Parameter tuning, Server management, Web servers",
author = "Akiyoshi Sugiki and Kenji Kono and Hideya Iwasaki",
year = "2008",
month = "10",
doi = "10.1002/spe.861",
language = "English",
volume = "38",
pages = "1215--1240",
journal = "Software - Practice and Experience",
issn = "0038-0644",
publisher = "John Wiley and Sons Ltd",
number = "12",

}

TY - JOUR

T1 - Tuning mechanisms for two major parameters of Apache web servers

AU - Sugiki, Akiyoshi

AU - Kono, Kenji

AU - Iwasaki, Hideya

PY - 2008/10

Y1 - 2008/10

N2 - Apache web servers are widely used as stand-alone servers or front-ends in multi-tiered web servers. Despite the wide availability of software, it is quite difficult for many administrators to properly configure their web servers. In particular, setting the performance-related parameters is an error-prone and timeconsuming task because their values heavily depend on the server environment. In this paper, two mechanisms are described for automatically tuning two performance-related parameters of Apache web servers: KeepAliveTimeout and MaxClients. These mechanisms are easy to deploy because no modifications to the server or the operating system are required. Moreover, they are parameter specific. Although interference between KeepAliveTimeout and MaxClients is inevitable, the tuning mechanisms minimize the correlation by using almost completely independent metrics. Experimental results show that these mechanisms work well for two different workloads; the parameter values are close to optimal and can adapt to workload changes.

AB - Apache web servers are widely used as stand-alone servers or front-ends in multi-tiered web servers. Despite the wide availability of software, it is quite difficult for many administrators to properly configure their web servers. In particular, setting the performance-related parameters is an error-prone and timeconsuming task because their values heavily depend on the server environment. In this paper, two mechanisms are described for automatically tuning two performance-related parameters of Apache web servers: KeepAliveTimeout and MaxClients. These mechanisms are easy to deploy because no modifications to the server or the operating system are required. Moreover, they are parameter specific. Although interference between KeepAliveTimeout and MaxClients is inevitable, the tuning mechanisms minimize the correlation by using almost completely independent metrics. Experimental results show that these mechanisms work well for two different workloads; the parameter values are close to optimal and can adapt to workload changes.

KW - Parameter tuning

KW - Server management

KW - Web servers

UR - http://www.scopus.com/inward/record.url?scp=54949155503&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54949155503&partnerID=8YFLogxK

U2 - 10.1002/spe.861

DO - 10.1002/spe.861

M3 - Article

VL - 38

SP - 1215

EP - 1240

JO - Software - Practice and Experience

JF - Software - Practice and Experience

SN - 0038-0644

IS - 12

ER -