Running performance analysis after server virtualization

After virtualization, you'll need tools to analyze server performance and predict data. This chapter excerpt helps you develop a performance overview and response time forecast.

After virtualization has been implemented, there are specialized tools to assist with performance analysis. After virtualization has been implemented, analysis is more complex because there are many virtual machines running on a single server. One such tool my firm has used on virtualized environments is Akorri BalancePoint. This performance-analysis tool for servers, storage systems, and applications is "virtualization aware" and ideally suited for use with VMware. Because of the virtualization of all the normally physical components of a data center -- network, server and storage -- it can be difficult to diagnose and resolve problems with traditional software tools. BalancePoint does the following in your virtualized environment:

About the book:
This chapter excerpt on The Virtualized Server Environment (download PDF) is taken from the book Foundations of Green IT: Consolidation, Virtualization, Efficiency, and ROI in the Data Center. This book has case studies for server and desktop consolidation and virtualization, designing data centers for power efficiency, using cloud computing, consolidating Microsoft SQL Server instances and more. 

• Displays a mapping of physical to virtual resources for each application running on a VM
• Measures the performance of physical and virtual elements
• Provides alerts and recommendations when problems are discovered
• Provides historical baselines of all virtual machines
• Identifies which virtual machines are overutilizing resources
• Provides detailed I/O data
• Provides comprehensive reporting

Even the most well-run data center is not immune to problems and bottlenecks. BalancePoint can provide invaluable troubleshooting capabilities. It facilitates deep analysis into the critical elements: operating systems, databases, servers, storage, virtualization systems, helping to accelerate the troubleshooting process. Figure 3-6 is a performance overview produced by BalancePoint.

Figure 3-6 Performance Overview

The report shown in Figure 3-6 illustrates the response time and throughput of a Microsoft Exchange server with the underlying storage system. The thresholds can help alert potential bottlenecks. Response time is often the measure of whether an environment has been successfully virtualized, so this detailed analysis is immensely helpful.

Despite the gains in server utilization offered by virtualization, capacity planning is still a challenge. BalancePoint helps indicate where additional resources are available and where more virtual machines can be allocated without running into capacity or performance problems. Rather than waiting until problems are evident, BalancePoint can help an administrator strategically plan how virtual and physical resources are allocated. Virtualization is addictive, and with these useful outputs, you can clearly see where you can add additional virtual machines and still maintain the desired response times. Figure 3-7 shows the response time.

Figure 3-7 Response Time Forecast

About the author:
Marty Poniatowski has been a systems engineer for Hewlett-Packard Co. for the past 15 years and has worked with UNIX for more than 27 years. Poniatowski has written ten books on UNIX-related topics, including HP-UX 11i System Administration Handbook and Toolkit and the UNIX User's Handbook.

Although the colors in Figure 3-7 are lost, you can see that actual and forecast data are provided The tool shows what you can expect to see when applications are added to the environment which, in some cases, may have an adverse impact on the applications currently running on the server.

It is easy to see how this tool can be invaluable for managing a virtual infrastructure. This, and similar software tools, can make the already impressive ROI that virtualization provides even more impressive with the ability to add forecast data to existing data.


The benefits presented in this chapter make a compelling argument for server virtualization. The results presented are typical for server virtualization. The case study illustrates what can be expected in any server virtualization and is by no means extreme. Every such assessment I've run has resulted in a sever virtualization project because, with immense benefits presented in this chapter, it is difficult to decline taking on server virtualization.

The next chapter covers the Return on Investment (ROI) for the new

The virtualized server environment
  Analyzing data in a virtualized server environment
  Running performance analysis after server virtualization

Printed with permission from Prentice Hall. Copyright 2009. Foundations of Green IT: Consolidation, Virtualization, Efficiency, and ROI in the Data Center by Marty Poniatowski. For more information about this title and other similar books, please visit Prentice Hall.

Dig Deeper on Server virtualization technology and services

Start the conversation

Send me notifications when other members comment.

Please create a username to comment.