NEWS from the SAP Benchmarking Front
For those of you who follow the published SAP benchmarks, there are already quite a few VMware-based results. You can find the results here:
http://www.sap.com/benchmark -> 2 tier results.
- 1.) * 2008007 HP on Windows with 516 SD users on ESX 3.5. This is the first Benchmark published on VMware ESX 3.5 and it shows an improvement of about 10 percent compared to a similar setup with ESX Server 3.0.2.
- 2.) * 2008009 FSC on Linux with 550 SD users on ESX 3.5. This is the first Benchmark published with Linux as the OS.
All of the published benchmarks were run using only two virtual CPUs.
As you can see, over a timeframe of less than a year the results have improved significantly from a little over 400 SD users to more than 500 SD users. This increase is due to faster processor speeds along with improvements to the VMware ESX platform. These benchmarks show how well-performing a virtual environment can be, and give an idea of what can be achieved with a virtual machine. As always the results will vary with the server used and the setup of the SAP system.
Michael
The above mentioned SD Benchmarks were achieved with
SAP ERP 6.0 (2005) and the following configuration:
2008007: Windows Server 2003 Enterprise Edition on VMware ESX Server 3.5 (using 2 virtual CPUs)
RDBMS: SQL Server 2005
HP ProLiant DL580 G5, 4 processors / 16 cores / 16 threads, Quad-Core Intel Xeon Processor X7350 2.93 GHz, 64 KB L1 cache per core and 4 MB L2 cache per 2 cores, 64 GB main memory
2008009: SuSE Linux Enterprise Server 10 on VMware ESX Server 3.5 (using 2 virtual CPUs)
RDBMS: MaxDB 7.7
Fujitsu Siemens Computers PRIMERGY Model TX300 S4 | RX300 S4,2 processors / 8 cores / 8 threads, Quad-Core Intel Xeon Processor X5460, 3.16 GHz, 64 KB L1 cache per core and 6 MB L2 cache per 2 cores, 32 GB main memory
