IBM’s Relative Performance (rPerf) metric is a great tool for comparing commercial workload performance between different Power System servers. It’s often. This post outlines a recent Nigel Griffiths tweet about estimating rperf for your LPAR. Read on to find out more. Articles on IBM AIX performance including server throughput, system performance and IBM AIX commands.
|Published (Last):||7 August 2010|
|PDF File Size:||3.74 Mb|
|ePub File Size:||15.64 Mb|
|Price:||Free* [*Free Regsitration Required]|
Sizing with rPerf but Don’t Forget the Assumptions (AIXpert Blog)
Many benchmarks exist for comparing servers, so why did IBM create the rPerf measurement? The main reason was to publish data for a broad selection of Power Systems servers. Running industry benchmarks can be very expensive.
In addition, rpetf benchmark rules require that the full benchmark be run and fully documented for each published data point. These requirements would make it extremely costly to publish multiple data points for each Power Systems model.
Since IBM owns and controls the rPerf benchmark, rpperf can report both actual and estimated data for Power servers. This has resulted in the publication of multiple rPerf values for each server based on varying processor core counts. Having this comprehensive set of information makes it easier to estimate the commercial workload CPU performance for any Power Systems server.
Note that rPerf can only be used for making comparisons within Power servers. If your workload is better aligns with two threads per processor core, you should consider reducing the published POWER7 rPerf numbers by approximately 15 to 20 percent to get a more reasonable representation of its rPerf value. For workload migrations and server consolidation projects, rPerf data is frequently reprf for CPU sizing.
The amount of rPerfs required to run existing workloads can be determined and used to size new servers. Charlie Cler supports customers in a solutions-architect role at Forsythe Technology Inc.