Narrowing down possible causes of performance anomaly in web applications

Satoshi Iwata, Kenji Kono

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Performance anomalies are a critical problem for commercial web applications. To help administrators discover their cause, many monitoring/analyzing systems have been developed, but their practical use is hindered by their limited scope and/or significant overheads; we cannot attach them all the time to the entire application. In this paper, we propose a front-end narrower that enables us to narrow down possible causes of performance anomalies. Our narrower is much less obtrusive but provides only hints about the cause of performance anomalies. Using control charts on response times of each request type, our "front-end" narrower indicates suspicious components or processes that may contain the root causes of the anomaly. After that, the administrator chooses an appropriate tool as a "back-end" and attaches it to the suspicious components or processes to trace down the original cause. The results of our case studies are encouraging: we succeeded in correcting some performance anomalies (including an unknown one) in default RUBiS.

Original languageEnglish
Title of host publicationEDCC-8 - Proceedings of the 8th European Dependable Computing Conference
Pages185-190
Number of pages6
DOIs
Publication statusPublished - 2010
Event8th European Dependable Computing Conference, EDCC-8 - Valencia, Spain
Duration: 2010 Apr 282010 Apr 30

Other

Other8th European Dependable Computing Conference, EDCC-8
CountrySpain
CityValencia
Period10/4/2810/4/30

Fingerprint

Web Application
Anomaly
Monitoring
Control Charts
Monitoring System
Response Time
Choose
Trace
Roots
Entire
Unknown
Control charts

Keywords

  • Commercial web application
  • Control chart
  • Performance debugging
  • Request type
  • Response time

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Iwata, S., & Kono, K. (2010). Narrowing down possible causes of performance anomaly in web applications. In EDCC-8 - Proceedings of the 8th European Dependable Computing Conference (pp. 185-190). [5474181] https://doi.org/10.1109/EDCC.2010.30

Narrowing down possible causes of performance anomaly in web applications. / Iwata, Satoshi; Kono, Kenji.

EDCC-8 - Proceedings of the 8th European Dependable Computing Conference. 2010. p. 185-190 5474181.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iwata, S & Kono, K 2010, Narrowing down possible causes of performance anomaly in web applications. in EDCC-8 - Proceedings of the 8th European Dependable Computing Conference., 5474181, pp. 185-190, 8th European Dependable Computing Conference, EDCC-8, Valencia, Spain, 10/4/28. https://doi.org/10.1109/EDCC.2010.30
Iwata S, Kono K. Narrowing down possible causes of performance anomaly in web applications. In EDCC-8 - Proceedings of the 8th European Dependable Computing Conference. 2010. p. 185-190. 5474181 https://doi.org/10.1109/EDCC.2010.30
Iwata, Satoshi ; Kono, Kenji. / Narrowing down possible causes of performance anomaly in web applications. EDCC-8 - Proceedings of the 8th European Dependable Computing Conference. 2010. pp. 185-190
@inproceedings{684b66c356ef457d83ec1eb83d6236ad,
title = "Narrowing down possible causes of performance anomaly in web applications",
abstract = "Performance anomalies are a critical problem for commercial web applications. To help administrators discover their cause, many monitoring/analyzing systems have been developed, but their practical use is hindered by their limited scope and/or significant overheads; we cannot attach them all the time to the entire application. In this paper, we propose a front-end narrower that enables us to narrow down possible causes of performance anomalies. Our narrower is much less obtrusive but provides only hints about the cause of performance anomalies. Using control charts on response times of each request type, our {"}front-end{"} narrower indicates suspicious components or processes that may contain the root causes of the anomaly. After that, the administrator chooses an appropriate tool as a {"}back-end{"} and attaches it to the suspicious components or processes to trace down the original cause. The results of our case studies are encouraging: we succeeded in correcting some performance anomalies (including an unknown one) in default RUBiS.",
keywords = "Commercial web application, Control chart, Performance debugging, Request type, Response time",
author = "Satoshi Iwata and Kenji Kono",
year = "2010",
doi = "10.1109/EDCC.2010.30",
language = "English",
isbn = "9780769540078",
pages = "185--190",
booktitle = "EDCC-8 - Proceedings of the 8th European Dependable Computing Conference",

}

TY - GEN

T1 - Narrowing down possible causes of performance anomaly in web applications

AU - Iwata, Satoshi

AU - Kono, Kenji

PY - 2010

Y1 - 2010

N2 - Performance anomalies are a critical problem for commercial web applications. To help administrators discover their cause, many monitoring/analyzing systems have been developed, but their practical use is hindered by their limited scope and/or significant overheads; we cannot attach them all the time to the entire application. In this paper, we propose a front-end narrower that enables us to narrow down possible causes of performance anomalies. Our narrower is much less obtrusive but provides only hints about the cause of performance anomalies. Using control charts on response times of each request type, our "front-end" narrower indicates suspicious components or processes that may contain the root causes of the anomaly. After that, the administrator chooses an appropriate tool as a "back-end" and attaches it to the suspicious components or processes to trace down the original cause. The results of our case studies are encouraging: we succeeded in correcting some performance anomalies (including an unknown one) in default RUBiS.

AB - Performance anomalies are a critical problem for commercial web applications. To help administrators discover their cause, many monitoring/analyzing systems have been developed, but their practical use is hindered by their limited scope and/or significant overheads; we cannot attach them all the time to the entire application. In this paper, we propose a front-end narrower that enables us to narrow down possible causes of performance anomalies. Our narrower is much less obtrusive but provides only hints about the cause of performance anomalies. Using control charts on response times of each request type, our "front-end" narrower indicates suspicious components or processes that may contain the root causes of the anomaly. After that, the administrator chooses an appropriate tool as a "back-end" and attaches it to the suspicious components or processes to trace down the original cause. The results of our case studies are encouraging: we succeeded in correcting some performance anomalies (including an unknown one) in default RUBiS.

KW - Commercial web application

KW - Control chart

KW - Performance debugging

KW - Request type

KW - Response time

UR - http://www.scopus.com/inward/record.url?scp=77954340116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954340116&partnerID=8YFLogxK

U2 - 10.1109/EDCC.2010.30

DO - 10.1109/EDCC.2010.30

M3 - Conference contribution

AN - SCOPUS:77954340116

SN - 9780769540078

SP - 185

EP - 190

BT - EDCC-8 - Proceedings of the 8th European Dependable Computing Conference

ER -