Analyzing the overload behavior of a simple web server

Authors:
Niels Provos;Chuck Lever;Stephen Tweedie
Affiliations:
University of Michigan, Ann Arbor;AOL-Netscape, Incorporated, University of Michigan, Ann Arbor;Red Hat Software, University of Michigan, Ann Arbor
Venue:
ALS'00 Proceedings of the 4th annual Linux Showcase & Conference - Volume 4
Year:
2000

Citing 7
Cited 4

Congestion avoidance and control

SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
Improving round-trip time estimates in reliable transport protocols

SIGCOMM '87 Proceedings of the ACM workshop on Frontiers in computer communications technology
UNIX Network Programming: Networking APIs: Sockets and XTI

UNIX Network Programming: Networking APIs: Sockets and XTI
Measuring the capacity of a web server

USITS'97 Proceedings of the USENIX Symposium on Internet Technologies and Systems on USENIX Symposium on Internet Technologies and Systems
Scalable network I/O in Linux

ATEC '00 Proceedings of the annual conference on USENIX Annual Technical Conference
Scalable kernel performance for internet servers under realistic loads

ATEC '98 Proceedings of the annual conference on USENIX Annual Technical Conference
Eliminating receive livelock in an interrupt-driven kernel

ATEC '96 Proceedings of the 1996 annual conference on USENIX Annual Technical Conference

Lightweight kernel/user communication for real-time and multimedia applications

NOSSDAV '01 Proceedings of the 11th international workshop on Network and operating systems support for digital audio and video
Scalability of Linux Event-Dispatch Mechanisms

Proceedings of the General Track: 2002 USENIX Annual Technical Conference
Flexible cross-domain event delivery for quality-managed multimedia applications

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Acceptable strategies for improving web server performance

ATEC '04 Proceedings of the annual conference on USENIX Annual Technical Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Linux introduces POSIX Real Time signals to report I/O activity on multiple connections with more scalability than traditional models. In this paper we explore ways of improving the scalability and performance of POSIX RT signals even more by measuring system call latency and by creating bulk system calls that can deliver multiple signals at once.