A computational complexity-aware model for performance analysis of software servers

Increased response time during periods of overload on a Web server may cause impatient users to time-out, causing the server to do unproductive work in processing these abandoned requests. Overhead time spent in preprocessing each request adds to the unproductive work even for requests that are not taken up for service. This causes the usable throughput, i.e. goodput, of the overloaded Web server to drop drastically, while resource utilization remains at 100%. Although this behaviour can be easily reproduced experimentally, existing analytical models of queues with abandonments are not able to do so.We present an analytical model that captures characteristics specific to networked software servers, namely, overhead processing and contention for shared hardware resources, that is able to explain the goodput degradation typically observed in overloaded servers. We use this model to compare the performance of the LIFO and FIFO queueing disciplines during overload and show that LIFO goodput and response time are better than those of FIFO.

show abstract

Web Services Resilience Evaluation using LDS Load dependent Server Models.

Rak¹,

Aversa²,

Martino³

et al. 2010

JCM

View full text Add to dashboard Cite

In the field of ICT, the term resilience is commonly used, understanding to mean the ability of a system to deliver acceptable service in the presence of faults. We interpret resilience assessment to mean assessment of ICT systems in evolving environments and conditions and in the presence of faults or failures of any kind. Resilience Measurement and benchmarking is an open problem, mainly referred to security-related problems. In this paper we propose to model Web Services (WS)as Load Dependent Servers (LDS), i.e. systems whose response time to a given request depends on the load at the time the request is received. Adoption of LDS-based models enable us to have a simple way to represent the System state. We propose to use this simple representation to quantify the system resilience comparing models built using off-line measurement and models built using on-line measurement.

show abstract

A computational complexity-aware model for performance analysis of software servers

Abstract: Abstract

Cited by 3 publications

References 8 publications

Instantaneous Load Dependent Servers (iLDS) Model for Web Services

Instantaneous Load Dependent Servers (iLDS) Model for Web Services

An overhead and resource contention aware analytical model for overloaded web servers

Web Services Resilience Evaluation using LDS Load dependent Server Models.

Contact Info

Product

Resources

About