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.

Author: Mezigis Vudozil
Country: Sao Tome and Principe
Language: English (Spanish)
Genre: Finance
Published (Last): 7 January 2016
Pages: 270
PDF File Size: 3.17 Mb
ePub File Size: 2.47 Mb
ISBN: 176-5-76456-570-3
Downloads: 84520
Price: Free* [*Free Regsitration Required]
Uploader: Makora

Continue to Wikis

This has resulted in the rperff of multiple rPerf values for each server based on varying processor core counts. There are similar assumptions when dealing with LPARs of smaller sizes than the official rPerf numbers. The most exciting POWER6 enhancement, live partition rpperf, allows one to migrate a running LPAR to another physical box and is designed to move running partitions from one POWER6 processor-based server to another without any application downtime whatsoever.

Running the same computer benchmark on multiple computers allows for comparison. Provide a reason for quarantining this blog entry optional: If you are break just one or two and then only a little bit then you never know – “you might get lucky”. How do I use the vio Performance tuning is always an iterative process of removing one performance bottleneck in order to reveal the next performance bottleneck. Disk Flash Servers Software Tape.

Also no SAN bottlenecks. If it says estimated then it is NOT an official number. Simply stated, benchmarking refers to running a set of programs on various computer and network configurations and measuring the results. rpef


This is the configuration used in working out rPerfs and unused DIMM slots or minimum memory will reduce performance. Achieving a Resilient Data Center Implement these techniques to improve data-center resiliency. If you want to know what rperf rerf to work out your rating use: AIX Live Update with These requirements would make it extremely costly to publish multiple data points for each Power Systems model.

Second, rPerf numbers are expressed in terms of alx as opposed to speed. If you are breaking a lot of these assumptions then you may not get the performance you expected or hoped to achieve.

Sizing with rPerf but Don’t Forget the Assumptions (AIXpert Blog)

I have done this sort of exercise myself in the past. Charlie Cler supports customers in a solutions-architect role at Forsythe Technology Inc. In this case, the script guesses the rPerf based on rPerf numbers in a fairly crude way. More Articles From Tom Farwell.

Running older software from the older machines can cause a mismatch with your rPerf expectation. Thanks for your use, help and feedback, Nigel Griffiths. X We use cookies to optimize your visit to our website. Benchmarks are popular because they have measurable and repeatable performance objectives and workloads.

Turn on JavaScript

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.


The script will give a lower than actual rPerf number. So lets talk about things you should think about when using rPerf to make sizing or performance estimates. If capped rpperf the script use Entitlement and not VP? For example, suppose that a company has plans aiz roll out a new Web-based ordering system.

How to Use rPerfs for Workload Migration and Server Consolidation

The performance capabilities of an server requires systematic work to unleash the full performance potential of the underlying computing platform. The rperf numbers are only available for certain number of CPUs.

If you would like to change your cookie settings at any time please view our privacy policy for additional information. If one is studying the performance of a computer system, logic states that the best way is to apply the actual workload on the system and measure the results.

Management has wix specified the software architecture and is ready to start hardware procurement. The savvy performance analyst knows that it’s neither feasible at this point in rperg nor cost-effective to set up actual performance testing of the new software. For LPARs the number may be estimated but it is a simple maths calculation i.

The Fast Path to Axi Performance.

The official rPerf numbers for current and older machines can be found here: