Using file system cache for storage pools

By default, the Tivoli® Storage Manager server reads and writes storage pool data with non-buffered I/O, which bypasses the file system cache. Using file system cache can be beneficial in certain situations but it is not a best practice.

About this task

If you switch to file system cache, change the default with care. The use of file system cache can decrease overall server throughput and increase server processor usage. Use file system cache for storage pool I/O only if it results in a significant performance improvement.

You might see benefits from using file system cache in the following environments:

A disk storage system that you are using for storage pools has a relatively small cache memory size.
The disk storage system does not provide read-ahead capability. You must improve storage pool migration throughput from the disk volumes by using the operating system read-ahead capability.
Data that is stored on the Tivoli Storage Manager server is expected to be immediately retrieved through some other process.

Restriction: Enabling the server to use file system cache is not a preferred practice. If you contact IBM® Software Support for a performance issue, you must disclose that you are using this option. You might be asked to disable this option before IBM can resolve the issue.

Procedure

To use file system cache for storage pool I/O, complete the following steps:

Specify one of the following options in the dsmserv.opt file:
- Container storage pools: DIOENABLED NO
- Other types of storage pools: DIRECTIO NO
Tips: For better performance, make the following adjustments:
- Disable direct I/O for IBM Spectrum Scale™
- Enable IBM Elastic Storage™ Server
Restart the server.
Observe operations for the effects of the change and determine whether to keep the DIRECTIO NO entry in the options file or remove it.
Tip: To display the current value for the DIRECTIO option, specify the option name when you issue the QUERY OPTION command.