A quality of service architecture that combines resource reservation and application adaptation

Abstract

Abstract-Reservation and adaptation are two well-known and effective techniques for enhancing the end-to-end performance of network applications. However, both techniques also have limitations, particularly when dealing with high-bandwidth, dynamic flows: fixed-capability reservations tend to be wasteful of resources and hinder graceful degradation in the face of congestion, while adaptive techniques fail when congestion becomes excessive. We propose an approach to quality of service (QoS) that overcomes these difficulties by combining features of reservations and adaptation. In this approach, a combination of online control interfaces for resource management, a sensor permitting online monitoring, and decision procedures embedded in resources enable a rich variety of dynamic feedback interactions between applications and resources. We describe a QoS architecture, GARA, that has been extended to support these mechanisms, and use three examples of application-level adaptive strategies to show how this framework can permit applications to adapt both their resource requests and behavior in response to online sensor information.

Deadline-sensitive workflow orchestration without explicit resource control

“…Several research efforts have proposed bounded resource units such as leases, slices, advanced reservations, etc [6,9,12,13]. These abstractions define properties for time and resource information but have little or no QoS information.…”

Market‐Oriented Computing and Global Grids: An Introduction

“…A number of research systems have explored QoS-based resource (e.g., CPU time and network bandwidth [22,23]) allocation in operating systems and queuing systems, but the inclusion of QoS into mainstream systems has been slowpaced (e.g., the Internet mostly uses the best effort allocation policy [24], but this is changing with IPv6 [25]). Some research systems support resource reservation in advance (e.g., reserving a slot from time t 1 to t 2 using the Globus Architecture for Reservation and Allocation (GARA) [21] and binding a job to it) and allocate resources during reserved time (value enforcement).…”

QoS management in service-oriented architectures

“…QoS in Grid computing was studied in GARA [6,7], and G-QoSM [1]. In GARA [6,7], resource reservation and actual allocation are separated in order to support advanced resource reservation for critical requests.…”

“…In GARA [6,7], resource reservation and actual allocation are separated in order to support advanced resource reservation for critical requests. G-QoSM [1] extended a UDDI registry.…”