Integrated CPU and network-I/O QoS management in an endsystem

Authors:
K. Lakshman;Raj Yavatkar;Raphael Finkel
Affiliations:
Intel Architecture Labs, 2111 N.E. 25th Avenue, Hillsboro, OR 97124, USA;Intel Architecture Labs, 2111 N.E. 25th Avenue, Hillsboro, OR 97124, USA;University of Kentucky, Department of Computer Science 773 Anderson Hall, Lexington, KY 40506, USA
Venue:
Computer Communications
Year:
1998

Citing 6
Cited 5

Operating systems mechanisms for continuous media

Operating systems mechanisms for continuous media
The QOS Broker

IEEE MultiMedia
Predictable Communication Protocol Processing in Real-Time Mach

RTAS '96 Proceedings of the 2nd IEEE Real-Time Technology and Applications Symposium (RTAS '96)
Resource management for real-time communication: making theory meet practice

RTAS '96 Proceedings of the 2nd IEEE Real-Time Technology and Applications Symposium (RTAS '96)
A scheme for real-time channel establishment in wide-area networks

IEEE Journal on Selected Areas in Communications
The design of a QoS-controlled ATM-based communications system in Chorus

IEEE Journal on Selected Areas in Communications

Application-level differentiated services for Web servers

World Wide Web
Connection management for QoS service on the web

Journal of Network and Computer Applications
QoS-Adaptive Multimedia Resource Regulation Scheme Based on Priority Classification

ICCNMC '01 Proceedings of the 2001 International Conference on Computer Networks and Mobile Computing (ICCNMC'01)
High-speed I/O: the operating system as a signalling mechanism

NICELI '03 Proceedings of the ACM SIGCOMM workshop on Network-I/O convergence: experience, lessons, implications
Towards a generic real-time transport and adaptation protocol for IP networks

Computer Communications

Quantified Score

Hi-index	0.24

Visualization

Abstract

Realtime multimedia applications such as conferencing, broadcast video, and distributed virtual reality demand predictable QoS from both endsystem and network resources. We argue that in a general-purpose computer, applications do not know the exact resource requirements in advance, and resource requirements and resource availability change at runtime. To provide predictable QoS in such an environment, we have designed a resource-management architecture in which applications and the OS cooperate to dynamically adapt to variations in resource requirements and availability. We have implemented the resulting OS architecture, called AQUA (Adaptive Quality of service Architecture), in the Sun Solaris(TM) OS. This paper describes how AQUA can be used to manage CPU to provide predictable QoS. In addition, we describe how to manage the CPU and Network-I/O resources in an integrated fashion. The paper also presents the results of an experimental evaluation.