Improved prediction for web server delay control

Dan Henriksson, Ying Lu, Tarek Abdelzaher

Research output: Contribution to journalConference articlepeer-review

Abstract

Control methods are being used increasingly for uncertainty management and QoS in modern web server systems. Previous approaches have suggested combined feed-forward and feedback control strategies, using queuing theory for feed-forward delay prediction. While queuing theory allows one to predict delay as a function of arrival and service rates, the prediction applies only to long-term averages, and is therefore insensitive to sudden load changes. Unfortunately, Internet load is very bursty, leaving room for predictor improvement. The main contribution of this paper is an extension of the combined feed-forward/feedback framework in which the queuing model is replaced with a predictor that instead uses instantaneous measurements to predict future delays. The proposed strategy is evaluated in simulation and by experiments on an Apache web server. It is shown that the new approach performs better than the combined queuing model based feed-forward and feedback control presented in earlier papers.

Original languageEnglish (US)
Pages (from-to)61-68
Number of pages8
JournalProceedings - Euromicro Conference on Real-Time Systems
Volume16
StatePublished - Oct 27 2004
Externally publishedYes
EventProceedings - 16th Euromicro Conference on Real-Time Systems (ECRTS 2004) - Catania, Italy
Duration: Jun 30 2004Jul 2 2004

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Improved prediction for web server delay control'. Together they form a unique fingerprint.

Cite this