Measuring NetBackup Performance

---

Introduction to NetBackup Performance

Before we examine the factors that affect backup performance, please note that an important first step is to ensure that your system meets NetBackup's recommended minimum requirements. Refer to your NetBackup Installation Guide and Release Notes for information about these requirements. Additionally, we recommend that you have the most recent NetBackup software patch installed. For example, if you are testing with NetBackup 3.4x, patch 341_2 includes significant restore performance enhancement to tar32.exe.

The final measure of performance is the length of time required for backup operations to complete (usually known as the backup window), or the length of time required for a critical restore operation to complete. However, in order to measure performance and then use those measurements to implement changes to improve performance, a performance metric more reliable and reproducible than simple wall clock time should be used. We will discuss these types of metrics in this document.

Many performance issues can be traced to hardware or other environmental issues. A basic understanding of the entire data transfer path is essential in determining the maximum obtainable performance in your environment. Poor performance is often the result of poor planning, which can be based on unrealistic expectations of any particular component of the data transfer path.

The slowest component in the data transfer path (for a backup, the path usually starts at the data on the disk and ends with a backup copy on tape) will be the bottleneck that will limit the overall performance of NetBackup. For example, a fast tape drive combined with an overloaded server will yield poor performance. Similarly, a slow network combined with a fast tape drive will also yield poor performance.

This document subdivides the standard NetBackup data transfer path into four basic components: the NetBackup client, the network, the NetBackup server, and the storage device. While it may be useful to subdivide the data transfer path even further in some installations, to identify and ease specific bottlenecks, these four components offer a good general approach to illustrate the ‘divide and conquer' approach to improving overall NetBackup performance.

This document discusses NetBackup performance evaluation and improvement from a testing perspective. It describes ways to isolate performance variables in order to get a sense of the effect each variable has on overall system performance, and to optimize NetBackup performance with regTard to that variable. It may not be possible to optimize every variable on your production system.

This document was written with file system backups in mind. Database backups may have different requirements.

---