Free performance monitoring and capacity planning for IBM Power Systems™

8.6.2012

LPAR2RRD version 3.15 coming with CPU Workload Estimator.
Now you are able to predict future workload of servers after lpar migration or consolidation.

CPU Workload Estimator

It is the feature which allows users make CPU estimation before is moved new workload on the server
Learn here how it can help in your migrations.
Before move any partition to a new server (by any kind of migration) you can assure that new CPU workload fits to CPU resources available on target server
When you enter CPU Workload Estimator page, then simply select on the left panel target server and CPU pool and on the right panel select one or more lpars which will be migrated. Then generate the graph. Default time range is 1 week.
Then you see an aggregated graph of last week with selected CPU pool of target server and selected lpars
You see how would look like the CPU load last week if lpars have been already there.

CPU estimations based on rPerf or CPW benchmark

CPU estimation based on CPU core is correct for situations where target server and lpars are on the same HW platform (same model, CPU frequency, number of cores...)
In case of different platforms like target server is IBM Power 710 and there are going to be migrated lpars from IBM Power 795 then estimations based purely on CPU core will not be accurate. Therefore there is possibility on the main CPU Workload Estimator page to select rPerf benchmark for AIX based server or CPW for IBM i (i5/OS) based server. Then estimations are based on that benchmark. This assures correct estimation for migrations between different IBM Power™ servers.
If you want to see that feature live then go to Live demo where you can try it on-line.
CPU core based estimations are available in free LPAR2RRD distribution. rPerf or CPW estimation feature is available only in full LPAR2RRD version distributed only to customers under support.

Next challenges

  • make price suggestions based on server list price, comparing load of servers based on benchmark and give a price when it would running on different server model.
  • This could even work with SW licenses like PVU
  • Integration with SAP.
    • make graphs based on real usage of servers with additional CPU load manually specified in SAPS
      It can be useful for planning of new SAP deployment where is known number of required SAPS. LPAR2RRD helps here to easily prove if the new SAPS load fits on already running servers
    • make graphs of CPU usage of servers with running SAP and compare it with actual number of SAP application users