VM/SAN benchmark testing

IOMeter is considered the benchmarking tool to use.

1.I/O Meter
http://www.iometer.org/

and then you have these also, that will give you a very quick number to compare

2. CrystalDiskMark
http://crystalmark.info/software/CrystalDiskMark/index-e.html

3. HD Tach
http://www.majorgeeks.com/files/details/hdtach.html

4. Intel NAS Toolkit
http://www.intel.com/products/server/storage/NAS_Perf_Toolkit.htm

5. VDBench
http://sourceforge.net/projects/vdbench

6. VMware Fling IO Blazer
http://labs.vmware.com/flings/ioblazer

7. Jet Stress
http://www.microsoft.com/en-us/download/details.aspx?id=36849

8. SQLIO
http://www.microsoft.com/en-gb/download/details.aspx?id=20163

9. HDPARM
http://linux.about.com/od/commands/l/blcmdl8_hdparm.htm

10. dd for (Linix, Unix and Windows)
http://en.wikipedia.org/wiki/Dd_%28Unix%29

11. ATTO
http://www.attotech.com/disk-benchmark/

12. Bonnie++
http://www.coker.com.au/bonnie++/

13. FIO
http://www.linux.com/learn/tutorials/442451-inspecting-disk-io-performance-with-fio

14. hIOmon
http://www.hyperio.com/productsAndServices.htm

15. DiskTester
http://diglloydtools.com/manual/disktester-iops.html

16. VMware Fling I/O Analyzer
https://labs.vmware.com/flings/io-analyzer

I have tried using VMware's I/O Analyzer but my results are rather puzzling.

I had the deployed VM running on my current SAN (RAID 6 with 6 disk, disks 15k SAS). Connection from SAN to ESXi is to a 1Gb Switch, connection method is iSCSI 1GB Base T. The attached image marked current SAN is the I/O output.

I also migrated the VM to a new SAN, 4 SSD disks in a RAID 10. Connection between the SAN and ESXI is 10Gb Base T, everything is 10Gb end to end, jumbo frame on the vswitch, physical switch and SAN are set to 9000. However I am really puzzled that the IO is lower than my older SAN.

Am I interpreting the results incorrectly.?

Thanks in advance.
old.PNG
newsan.PNG

this is often the issue with benchmarking.....trying to observe an immediate figure, which proves it's faster.

with many All flash SANs, you may need to wait for the Read and Write cache, to "warm up".

Also, you may find, if you had 1000 VMs running on the All flash SAN, compared to your old SAN they would be faster.

What is the SAN, Tegile, Pure, Nimble ?

You would be far better, running I/O Meter, with many workers, and focusing on a real world VM load, you may see results.

The SAN is a HP 2040.

So there isn't enough IOPS to make the SAN work hard to shown it's true performance? I will give IO meter a try.

Use I/O meter, and create many workers, and this will generate a workload like your VMs, if you know what VM workload you need to generate.

Thanks Andrew,

An you give me some indication of how many workers and there settings.
I have 2 workers, both set with 20000000 sectors with outstanding I/Os set to 64. Access Specs are set to 4K 100% read.

Are there any better setting to get a good real world IOPS result?