Section 2 – AIX Multiuser Performance (rPerf, POWER8 and up). CPW results of IBM Power Systems servers running the IBM i operating. rPerf is a computer benchmark that evaluates the relative OLTP performance of servers based on IBM POWER microprocessors. It is published by IBM and. Section 2a – AIX Multiuser Performance (rPerf, SPEC CPU, . All performance measurements for the IBM Power™ Systems, IBM.
|Published (Last):||12 June 2014|
|PDF File Size:||6.97 Mb|
|ePub File Size:||19.65 Mb|
|Price:||Free* [*Free Regsitration Required]|
As you can see, no significant grow after patching. Getting the PTF on the system was a big question mark and probably lbm users still feel uncomfortable with number of available information. The amount of rPerfs required to run existing workloads can be determined and used to size new servers.
I wrote a post how to collect it few years ago here. Martin February 19, at Leave a Reply Cancel reply Enter your comment here Jimmy May 7, at Do not forget that fixes powet VIOSes were released as well.
The first patch was delivered on January 9th.
Mark as Duplicate
Notify me of new comments via email. Not sure if there is anyone in IT world who has not heard about latest vulnerabilities in the modern chips. This tool collects statistics delivered by the HMC, which are the processor cycles dispatched by the Power Hypervisor. This has resulted in the publication of multiple rPerf values roerf each server based on varying processor core counts.
Continue to Wikis
We have carefully put this patch to test systems and closely monitored the performance. There is no difference again. If not, a server reboot is needed.
Email required Address never made public.
IBM Power Systems Performance Report
I will be giving updates in comming weeks. Fill in your details below or click an icon to log in: Charlie Cler supports customers in a solutions-architect role at Forsythe Technology Inc. The fix is concurrent as long as you run the latest release level. To find out more, including how to control cookies, see here: Today Jan 31st we applied the fix on few test systems. Read The Current Issue: Unfortunately, IBM is very conservative in published information regarding the vulnerability.
As you can see, there is almost the same utilization, no spectacular grow. More Articles From Charlie Cler.
Note that rPerf can only be used for making comparisons within Power servers. Patching is scheduled in waves.
Since IBM owns and controls the rPerf benchmark, it can report both actual and estimated data for Power servers. For workload migrations and server consolidation projects, rPerf data jbm frequently used for CPU sizing. Cover letter again is very mysterious.
Left graph before patches, right one pkwer patches. The only way how to solve it, is to redesign the chip or patch the OS in the way that it will not allow to use this vulnerability. Bart February 19, at Running industry benchmarks can be very expensive. These requirements would make it extremely costly to publish multiple data points for each Power Systems model.
Actually, in the OS V7R2 no performance degradation noted either.