IOmeter is the primary tool I use to benchmark a disk subsystem, It could be SAN, NAS or DAS.
- Start with 4KB as it represents the default NTFS Unit Allocation Size.
- Next with 8KB because it represents Microsoft Exchange 2007 default workload.
- Next test with 64KB because it represents Microsoft SQL 2005 default workload.
- Finally 256KB because it represents default backup (and restore) workload.
For tests 1. 2. and 3. use different I/O mixes and randomness. For test 4. use 100% sequential read (backup) and 100% sequential write (restore).
Chad Sakac recommends on his blog a series of tests you should perform:
- 8K, 50/50 r/w, 50/50 random
- 64K 100 r, 100 sequential
- 64K 100 w, 100 sequential
- 256K 100 r, 100 sequential
- 256K 100 w, 100 sequential
This a file system benchmarking tool available at IOzone.org. It is well know in the *NIX world. You can test NFS and SMB/CIFS shares with this tool. It produces a binary file you can open with Excel to produce great 3D graphs. Here is the IOzone command I used to launch to generate the load: iozone -Ra -g 2G -b output.wks
HD Tune is well-known benchmark tool, simple to use, fast as well, it gives you enough information for a comprehensive benchmark baseline.
Jetstrees tool simulate disk I/O load on a test server running Exchange to verify the performance and stability of your disk subsystem before putting your server into a production environment.
Get details on SQLIOsim here. It simulates the I/O patterns of Microsoft SQL Server 2005, of SQL Server 2000, and of SQL Server 7.0.
Exchange Load Generator is a simulation tool to measure the impact of MAPI, OWA, IMAP, POP and SMTP clients on Exchange servers. This tool is damn complicated to setup and run.