Intelligent Message Scheduling in Application Oriented Networking Systems

Abstract

Cisco Systems Application Oriented Networking (AON) product is an important network element towards building next generation service oriented Intelligent Information Network (IIN). AON processes application-level content and moves far beyond a conventional content-aware web switch. It creates a novel content delivery platform and allows more sophisticated load balancing schemes to be deployed in a switch among backend servers to reduce user-perceived response time. In this paper, we investigate different scheduling techniques for an AON system to maximize overall throughput and minimize latency per message for a heterogeneous server cluster consisting of different application servers. Based on a thorough evaluation of the three existing load balancing algorithms of AON, we propose a novel message type based service adaptive scheduling algorithm that makes AON more efficient and more intelligent. Systematic performance measurements, analyses, and comparisons are conducted to demonstrate the superiority of our intelligent message scheduling technique.

An up-to-date survey in web load balancing

“…They do not consider cache hits in the performance evaluation of the Web system. Therefore, other factors are included in these policies like, for instance, the evaluation of the resource utilisation by the different types of requests [14,36,72,85], the introduction of QoS in the service provided [36,48,59,71,72], or the inclusion of an admission control in the load balancing solution [36,72].…”

“…Considering the content of incoming requests and obtaining some metrics from the Web switch that permit estimating the load of the Web servers, Yao et al in [85] propose Message-Aware Adaptive (MAA). It is a scheduling policy that is developed to be executed in the Application Oriented Networking (AON) product of Cisco Systems [24].…”

A Novel Service-Aware Message Scheduler for Cisco Application Oriented Networking Systems

“…Two static and one adaptive load balancing algorithms, currently deployed in AON, are thoroughly evaluated in [13] under various server cluster configurations and traffic patterns in terms of system throughput, average round trip latency, and server utilizations. This study reveals areas for improvement in the existing algorithms based on which we design an original service differentiated adaptive algorithm (SDA) for an intelligent message level load balancer.…”