Ensuring the Performance of Apache HTTP Server Affected by Aging

Author

Jing Zhao ; Trivedi, Kishor S. ; Grottke, Michael ; Alonso, J. Marcos ; Yanbin Wang

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Eng. Univ., Harbin, China

Volume

11

Issue

2

fYear

2014

fDate

March-April 2014

Firstpage

130

Lastpage

141

Abstract

Failures due to software aging are typically caused by resource exhaustion, which is often preceded by progressive software performance degradation. Response time as a customer-affecting metric can thus be used to detect the onset of software aging. In this paper, we propose the distribution-based rejuvenation algorithm (DBRA), which uses a validated M/E₂/1/K queuing model of the Apache HTTP server to decide when to trigger rejuvenation. We compare the performance of the DBRA with the one of the static rejuvenation algorithm with averaging (SRAA) presented by Avritzer et al. Simulation results show the effectiveness of the DBRA and its advantages over the SRAA in reducing the average response time. However, the DBRA generally tends to trigger rejuvenation more frequently than the SRAA, which increases the request blocking probability.

Keywords

hypermedia; queueing theory; software maintenance; transport protocols; Apache HTTP server performance; DBRA; M/E₂/1/K queuing model; SRAA; average response time; customer-affecting metric; distribution-based rejuvenation algorithm; progressive software performance degradation; request blocking probability; resource exhaustion; software aging; static rejuvenation algorithm with averaging; Aging; Equations; Mathematical model; Numerical models; Servers; Software; Software algorithms; Queuing model; distribution-based rejuvenation algorithm; response time distribution; software aging detection; static rejuvenation algorithm with averaging;

fLanguage

English

Journal_Title

Dependable and Secure Computing, IEEE Transactions on

Publisher

ieee

ISSN

1545-5971

Type

jour

DOI

10.1109/TDSC.2013.38

Filename

6594734