Clustering for performance, availability
In the 1980s, computer researchers believed computer performance was best improved by creating faster, more efficient processors. But this idea was challenged by the idea of clustering which, in essence, means linking together two or more computers to work together on performing functions. The goal is to develop infrastructure so that end users never know they are actually working off a cluster.
Clustering is catching on fast, especially in the corporate world. Why? Because it permits organizations to boost processing power using commodity components -- that is, standard technology that can be purchased relatively inexpensively. This provides "scalability," an affordable upgrade path that lets organizations increase their computing power, while preserving their existing investment and without incurring a lot of extra expense. Another benefit of clustering is "failover" capabilities that allow a backup computer to take over the tasks of a failed computer located in its cluster.
Low-cost Clustering
IBM researchers at several of its labs have produced clustering solutions. One that offers enormous promise for UNIX-based computing is the IBM RS/6000 Cluster Technology. RS/6000 CT, as it is known, is a low-cost clustering technology that can run on any kind of network of UNIX-based (or windows NT based) computer systems. While RS/6000 CT is optimized to work for applications that are "cluster-enabled", even applications that are not cluster-enabled can be made highly available using it.