Most well-managed web servers perform well most of the time. Occasionally, however, every popular web server experiences transient overload. An overloaded web server typically displays signs of its a#iction within a few seconds. Work enters the web server at a greater rate than the web server can complete it, causing the number of connections at the server to build up. This implies large delays for clients accessing the server. This paper provides a systematic performance study of exactly what happens when a web server is run under transient overload, both from the perspective of the server and from the perspective of the client. Second, this paper proposes and evaluates a particular kernel-level solution for improving the performance of web servers under overload. The solution is based on SRPT connection scheduling. We show that SRPT-based scheduling improves overload performance across a variety of client and server-oriented metrics. 1
|
610
|
Generating Representative Web Workloads for Network and Server Performance Evaluation
– Barford, Crovella
- 1998
|
|
371
|
Resource containers: A new facility for resource management in server systems
– Banga, Druschel, et al.
- 1999
|
|
303
|
Dummynet: A simple approach to the evaluation of network protocols
– Rizzo
- 1997
|
|
302
|
Computer Networking: A Top-Down Approach Featuring the Internet
– Kurose, Ross
- 2001
|
|
260
|
The case for geographical push-caching
– Gwertzman, Seltzer
- 1995
|
|
235
|
Eliminating receive livelock in an interrupt-driven kernel
– MOGUL, RAMAKRISHNAN
- 1997
|
|
220
|
Flash: An efficient and portable Web server
– Pai, Druschel, et al.
- 1999
|
|
204
|
Modeling TCP Reno Performance: A Simple Model and Its Empirical Validation
– Padhye, Firoiu, et al.
- 2000
|
|
172
|
Lazy receiver processing (LRP): A network subsystem architecture for server systems
– Druschel, Banga
- 1996
|
|
158
|
The Case for Persistent-Connection HTTP
– Mogul
- 1995
|
|
143
|
Workload Characterization of the 1998 World Cup Web Site
– Arlitt, Jin
- 1999
|
|
131
|
TCP Behavior of a Busy Internet Server: Analysis and Improvements
– Balakrishnan, Padmanabhan, et al.
- 1998
|
|
121
|
Computing TCP’s Retransmission Timer
– Paxson, Allman
- 2000
|
|
108
|
Analysis of SRPT scheduling: investigating unfairness
– BANSAL, HARCHOL-BALTER
- 2001
|
|
107
|
On the use and performance of content distribution networks
– Krishnamurthy, Wills, et al.
- 2001
|
|
107
|
Network behavior of a busy Web server and its clients
– Mogul
- 1995
|
|
100
|
A scalable and highly available web server
– Dias, Kish, et al.
- 1996
|
|
97
|
Flow and stretch metrics for scheduling continuous job streams
– Bender, Chakrabarti, et al.
- 1998
|
|
93
|
Connection scheduling in Web servers
– Crovella, Frangioso, et al.
- 1999
|
|
92
|
Web facts and fantasy
– Manley, Seltzer
- 1997
|
|
87
|
The measured performance of content distribution networks
– JOHNSON, CARR, et al.
- 2000
|
|
75
|
Adaptive Overload Control for Busy Internet Servers
– Welsh, Culler
- 2003
|
|
70
|
Session based admission control: a mechanism for improving the performance of an overloaded web server
– Cherkasova, Phaal
- 1998
|
|
68
|
Web traffic characterization: an assessment of the impact of caching documents from NCSA's Web server
– Braun, Claffy
- 1994
|
|
65
|
Server Operating Systems
– Kaashoek, Engler, et al.
- 1996
|
|
62
|
Size-based scheduling to improve web performance
– HARCHOL-BALTER, SCHROEDER, et al.
- 2003
|
|
58
|
Web Content Adaptation to Improve Server Overload Behavior
– Abdelzaher, Bhatti
- 1999
|
|
57
|
A proof of the optimality of the shortest remaining processing time discipline
– SCHRAGE
- 1968
|
|
55
|
Measuring the capacity of a Web server under realistic loads
– Banga, Druschel
- 1999
|
|
55
|
Classifying scheduling policies with respect to unfairness in an M/GI/1
– Wierman, Harchol-Balter
- 2003
|
|
54
|
Analysis of task assignment policies in scalable distributed Web-server systems
– Colajanni, Yu, et al.
- 1998
|
|
53
|
A performance evaluation of hyper text transfer protocols
– Barford, Crovella
- 1999
|
|
53
|
Kernel mechanisms for service differentiation in overloaded Web servers
– Voigt, Tewari, et al.
- 2001
|
|
51
|
Application-level document caching in the Internet
– Bestavros, Carter, et al.
- 1995
|
|
48
|
A method for transparent admission control and request scheduling in e-commerce web sites
– Elnikety, Nahum, et al.
- 2004
|
|
48
|
The queue M/G/1 with the shortest remaining processing time discipline
– Schrage, Miller
- 1966
|
|
37
|
Analysis of LAS scheduling for job size distributions with high variance
– Rai, Urvoy-Keller, et al.
- 2003
|
|
35
|
The Effects of Wide-Area Conditions on WWW Server Performance
– Nahum, Rosu, et al.
- 2001
|
|
34
|
Session-based overload control in qos-aware web servers
– Chen, Mohapatra
- 2002
|
|
33
|
Linux network traffic control — implementation overview. Available at http://lrcwww.epfl.ch/linux-diffserv
– Almesberger
- 1999
|
|
31
|
Priority mechanisms for OLTP and transactional web applications
– McWherter, Schroeder, et al.
- 2004
|
|
31
|
Operating System Concepts, 5th Edition
– Silberschatz, Galvin
- 1998
|
|
27
|
Syn cookies. http://cr.yp.to/syncookies.html
– Bernstein
- 1997
|
|
26
|
Overload Control Mechanisms for Web Servers
– Iyer, Tewari, et al.
- 2000
|
|
18
|
Operating System Concepts, Sixth Edition
– Silberschatz, Galvin, et al.
- 2002
|
|
17
|
TCP implementation enhancements for improving Webserver performance
– Aron, Druschel
- 1999
|
|
16
|
Fairness and efficiency in web server protocols
– Friedman, Henderson
- 2003
|
|
16
|
CNN.com: Facing a World Crisis
– LeFebvre
- 2002
|
|
16
|
Flash: An ecient and portable Web server
– Pai, Druschel, et al.
- 1999
|
|
15
|
SWIFT: Scheduling in web servers for fast response time
– Rawat, Kshemkalyani
- 2003
|
|
