White Paper: Piranha - Load-balanced Web and FTP Clusters

January 1, 2010

Mike WangsmoRed Hat Software
wanger@redhat.com

Clustering is a commonly used phrase these days in computing technology circles. Unfortunately, if you ask 10 people what clustering is, you will likely get nine unique answers. Based on that premise, the first part of this document gives a brief overview of general clustering principles. This quick review is not meant to be a replacement for deep discussions of clustering. For a much more thorough understanding of clusters, please see In Search of Clusters by Gregory Pfister.

Table of contents

 

Coverage

Currently, Piranha only supports the NAT networking model of the IPVS code. The other significant limitation of Piranha is the filesystems. Currently static content on the servers is required. Any dynamic content must come from other shared filesystems or backend databases. For most web sites, the page content is mostly static with CGI activities and dynamic content being pulled from databases.

The primary supported services within a Piranha environment are Web and FTP servers. With the NAT model, the real servers can be any operating system on any hardware platform. The dynamic weight adjustment capabilities are not usable on OSes that do not support rsh (or similar) logins to acquire CPU loads.

The number of real servers that can be supported is theoretically limitless; however, network limitations can be reached with eight to twelve servers, depending on the network connectivity and the server data types. Static FTP content reaches network limitations sooner than dynamic CGI web content.