Generating representative Web workloads for network and server performance evaluation

Barford, Paul; Crovella, Mark

doi:10.1145/277851.277897

Cited by 921 publications

(428 citation statements)

References 19 publications

(1 reference statement)

Supporting

Mentioning

415

Contrasting

Unclassified

Order By: Relevance

“…If the distribution is uniform, the generated reference stream will, of course, not display any locality. But as we noted earlier, distributions of popularity are generally highly skewed, and, in particular, follow a Zipf distribution [95,57,85]. When some addresses are much more popular than others, they will be selected much more often, leading to significant locality.…”

Section: Independent Reference Modelmentioning

confidence: 91%

“…If the most popular file is accessed k times, the next most popular may be expected to be accessed about k/2 times, the third most popular k/3 times, and so on. Another example is the popularity of documents on a web server [57,85,571] or the websites themselves [9,10]. A third is the popularity of online games [116].…”

Section: Usesmentioning

confidence: 99%

“…• The distribution of popularity of items on a web server, and the distribution of popularity of websites [57,85,571,9,524].…”

Section: Heavy Tailsmentioning

confidence: 99%

“…For example, Barford and Crovella made such an observation when studying early data regarding request sizes on the world wide web, where the maximal size was about 10 6 bytes. They therefore included a heavy tail as one of the features of their SURGE workload generator [57]. Years later this decision was justified when further data showed that the heavy tail indeed extends at least up to a size of 10 9 bytes [329].…”

Section: Generalization and Extrapolationmentioning

confidence: 99%

“…Instead, the load is manipulated by a highlevel modification of the user population: adding more users increases the load, and removing users reduces the load [57,108,749]. Alternatively, load can be modified by changing the characteristics of the active users.…”

Section: Load Manipulationmentioning

confidence: 99%

See 4 more Smart Citations

Workload Modeling for Computer Systems Performance Evaluation

Feitelson

2015

196

131

View full text Add to dashboard Cite

Reliable performance evaluations require the use of representative workloads. This is no easy task since modern computer systems and their workloads are complex, with many interrelated attributes and complicated structures. Experts often use sophisticated mathematics to analyze and describe workload models, making these models difficult for practitioners to grasp. This book aims to close this gap by emphasizing the intuition and the reasoning behind the definitions and derivations related to the workload models. It provides numerous examples from real production systems, with hundreds of graphs. Using this book, readers will be able to analyze collected workload data and clean it if necessary, derive statistical models that include skewed marginal distributions and correlations, and consider the need for generative models and feedback from the system. The descriptive statistics techniques covered are also useful for other domains.

show abstract

Section: Independent Reference Modelmentioning

confidence: 91%

Section: Usesmentioning

confidence: 99%

“…• The distribution of popularity of items on a web server, and the distribution of popularity of websites [57,85,571,9,524].…”

Section: Heavy Tailsmentioning

confidence: 99%

Section: Generalization and Extrapolationmentioning

confidence: 99%

Section: Load Manipulationmentioning

confidence: 99%

See 3 more Smart Citations

Workload Modeling for Computer Systems Performance Evaluation

Feitelson

2015

196

131

View full text Add to dashboard Cite

show abstract

Self‐Similar Network Traffic: An Overview

2000

View full text Add to dashboard Cite

SELF-SIMILAR NETWORK TRAFFIC: AN OVERVIEWto the shape of the whole, i.e., it is self-similar. Of course, this is not too surprising since the constructive process-by its recursive action-endows the limiting object with the scale-invariance property.The 1-dimensional Cantor set, e.g., as obtained by projecting the 2-D Cantor set onto the line, can be given an interpretation as a traffic series Xt 2 f 0; 1g-call it "Cantor traffic"-where Xt = 1 means that there is a packet transmission at time t. This is depicted in Figure 1. 1.2 (left). If the constructive process is terminated at iteration n 0, then the contiguous line segments of length 1=3 n may be interpreted as on-periods or packet trains of duration 1=3 n , and the segments between successive on-periods as off-periods or absence of traffic activity. Nonuniform traffic intensities may be imparted by generalizing the constructive framework via the use of probability measures. For example, for the 1-dimensional Cantor set, instead of letting the left and right components after scaling have identical "mass," they may be assigned different mass, subject to the constraint that the total mass be preserved at each stage of the iterative construction. This modification corresponds to defining a probability measure on the Borel subsets of 0; 1 and distributing the measure at each iteration nonuniformly left and right. Note that the classical Cantor set construction-viewed as a map-is not measure-preserving. Figure 1shows such a construction with weights L = 2 =3, R = 1 =3 for the left and right components, respectively. The probability measure is represented by "height"; we observe that scale-invariance is exactly preserved. In general, the traffic patterns producible with fixed weights L , R are limited, but one can extend the framework by allowing possibly different weights associated with every edge in the weighted viii SELF-SIMILAR NETWORK TRAFFIC: AN OVERVIEW processes which are nondecreasing processes whose differences-also called increment process-constitute the original process. For example, for the on/off Cantor traffic construction (cf. Figure 1.1.2 (left)), let us assign the interpretation that time is discrete such that at step n 0, it ranges over the values t = 0; 1=3 n ; 2=3 n ; : : : ; 3 n , 1=3 n ; 1. Thus we can equivalently index the discrete time steps by i = 0; 1; 2; : : : ; 3 n . With a slight abuse of notation, let us redefine X as Xi = 1 if, and only if, in the original process Xi=3 n = 1 and Xi=3 n , " = 1 for all 0 " 1=3 n . That is, for i values for which an on-period in the original process Xt begins at t = i=3 n , Xi is defined to be zero. Thus, in the case of n = 2 , we have

show abstract

Web Quality of Service

Abdelzaher

2004

The Internet Encyclopedia

View full text Add to dashboard Cite

The commercialization of the Internet has made this medium a prime venue for conducting business and selling a myriad of priced services. The World Wide Web provides a uniform and widely accepted application interface used by these services to reach multitudes of clients. These changes place the Web infrastructure at the center of a new marketplace with increasing requirements for service quality, predictability, and reliability in an unpredictable and highly dynamic environment. This chapter describes policies and mechanisms for meeting these requirements in contemporary Web services. It surveys the state of the art in quality of service provisioning, describes the most important open challenges, and concludes with an outlook on some emerging directions and novel foundations for providing software performance guarantees on the Web.

show abstract

Generating representative Web workloads for network and server performance evaluation

Cited by 921 publications

References 19 publications

Workload Modeling for Computer Systems Performance Evaluation

Workload Modeling for Computer Systems Performance Evaluation

Self‐Similar Network Traffic: An Overview

Web Quality of Service

Contact Info

Product

Resources

About