Web and other Internet-based server farms are a critical company resource. A solution to the increased complexity of server farms and to the need to improve the server performance in terms of scalability, fault tolerance and management is to implement a load balancing technique. It consists of a front-end machine which intelligently redirects the traffic to several Real Servers. We discuss the feasibility of implementing adaptive load balancing with minimal flow disruption on the IBM PowerNP Network Processor. We focus our attention on the steady-state part of the algorithm and propose a PowerNP-tailored mapping algorithm derived by Robust Hash Mapping. We propose and show a fast algorithm solution (despite the simple arithmetical logic of the PowerNP), as well as a scalable approach (aiming at minimizing the packet processing time) and, finally, we present some initial performance results.
By: Riccardo Russo, Lukas Kencl, Bernard Metzler, and Patrick Droz
Published in: RZ3431 in 2002
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .