Server Design: The Limitations of Horizontal Scaling

Today's powerful and affordable low-end servers have resulted in a scaling out in the data center to a more distributed computing model. As servers become overloaded or databases grow, IT has traditionally added servers or distributed multiple functions residing on one server across several others.

This approach, known as scaling out, or horizontal scaling, can increase performance (e.g., Web server farms), improve availability (e.g., high-availability clusters) or provide an immediate fix to a pressing IT need. But an abundance of small servers can also create too much of an administrative burden -- especially when hundreds of servers are present. Every server added to the data center requires space, power, telecommunications and networking interfaces, storage capacity and connections, backup and restore systems, and an update to asset management inventories and supplier contracts.

When taken to extremes, scaling out can result in fragmented databases and a series of disconnected, hard-to-manage servers. Some servers end up underutilized, while others are badly overloaded. "The proliferation of distributed servers within large enterprise organizations has proved to be an administrative money pit as well as a nightmare. As more systems are added to the network, the costs of administration and maintenance increase," says Susan Clark, an analyst at the Butler Group in Hull, England.

Horizontally scaled systems are characterized by multiple servers connected by relatively slow communication links. Although networks and cluster interconnects continue to improve performance in terms of high bandwidth/low latency, their speed is still dwarfed by the capabilities of bus and switch interconnects. As scaled-out systems communicate by message passing, therefore, the elapsed time to complete a task can sometimes increase markedly.

Additionally, each horizontally scaled server runs a copy of the operating system. This can result in synchronization challenges, as well as trouble with the division of workload among servers. At a minimum, distributed server environments still tend to offer much coarser granularity when it comes to server management and workload planning. In situations where these limitations become a problem, users should consider a vertically scalable design that can consolidate many of those smaller, distributed servers.

Related:

Copyright © 2002 IDG Communications, Inc.

7 inconvenient truths about the hybrid work trend
Shop Tech Products at Amazon