Abstract
A bottleneck occurs when any server subsystem prevents the other subsystems from running at peak capacity.
This paper provides information that will help you detect a bottleneck problem on a Windows server. It also discusses what to look for in components that are bottlenecks so that you have all the data that you need to identify possible solutions. The information in this paper is useful if you are facing a situation where a performance problem is already affecting a server. In such a reactive situation, you need to follow a series of steps that you can implement to restore the server to an acceptable performance level. In addition, the experience that you gain over time from solving server bottlenecks can be very useful when doing new server configuration or server consolidation exercises.
This IBM Redpaper is extracted from the IBM Redbooks publication "Tuning IBM eServer xSeries Servers for Performance", SG24-5287.
Table of Contents
Bottleneck-detection strategy
Bottleneck-detection techniques
Step 1: Gathering information
Step 2: Monitoring the server’s performance
Step 3: Fixing the bottleneck
Conclusion
The team that wrote this Redpaper
Related product families
Product families related to this document are the following: