Skip to main content

Servers   >  

z/OS RMF spec sheet (flyer)

Performance management for z/OS single system and sysplex environments



 Highlights
 The four components of RMF
 Productivity, growth and investment protection
 What's new in RMF for z/OS V1.9
 What's new in RMF for z/OS V1.8
 What's new in RMF for z/OS V1.7
 What's new in RMF for z/OS V1.6
 What's new in RMF for z/OS V1.5
  RMF at a glance

What's new in RMF for z/OS Version 1 Release 5
Enhanced Enterprise Disk Systems Support
The ESS Statistics Postprocessor report now contains two new sections, Extent Pool Statistics and Rank Statistics, to support the IBM TotalStorage DS family. Also new response and transfer statistics are available with the Cache Activity report: at the subsystem level in the Cache Subsystem Activity report, and at the volume level in the Cache Device Activity report. In addition, RMF provides new overview conditions for the Postprocessor based on SMF records 74-5 and 74-8. This new functionality is available as an SPE and needs to be installed as APAR OA06476.

Support of the eServer  zSeries Application Assist Processor
z/OS V1.5 provides the ability to run Java applications on a new type of processor called the eServer zSeries Application Assist Processor (zAAP). The zSeries Application Assist Processor is also known as an IFA (Integrated Facility for Applications). RMF uses the term IFA in the affected reports. RMF provides measurements of IFA processor activity in the Postprocessor CPU and WLMGL reports as well as in Monitor III CPC Capacity, Enclave and Sysinfo reports. Also, RMF provides new overview conditions based on SMF records 70-1 and 72-3 to assess IFA processor activity. This new functionality is available as an SPE and needs to be installed as APAR OA05731.

WLM Support: Enqueue contention management
To allow customers to better understand when and to what degree their work is being delayed by resource contention, new measurements (resource contention usage and delay states) are available in the Postprocessor WLMGL report.

Shared memory support
In order to track the usage of virtual storage above the 2 GB bar for individual address spaces, the Private Area Detail section of the Virtual Storage Activity report is enhanced by reporting on shared pages that are allocated to virtual addresses above the 2 GB bar.

z990 Exploitation and Compatibility support
Performance monitoring of I/O queuing has been enhanced in the Monitor III, Monitor II and Postprocessor I/O Queuing reports. The following data is now available: Average control unit busy delay time, Average initial command response time and Average channel subsystem delay time. In addition, new overview and exception conditions are available for the Postprocessor.

With the availability of the new cryptographic hardware (PCIX cryptographic card), the Postprocessor Crypto Hardware Activity report has been enhanced to provide performance monitoring for the PCIX Cryptographic Coprocessor.

The following delay metrics or pending reasons have been removed from the Device Activity reports: director port busy and control unit busy. The initial command response time has been added to the Device Activity reports. Overview and exception conditions for device activity have changed. The following conditions are no longer available: CUBDL (Average control unit busy delay time) and DPBDL (Average director port busy delay time); while the following new condition is supported: CMRDL (Average command response delay time).

Support of the cryptographic hardware
The Crypto Hardware Activity report, introduced with RMF for z/OS 1.2, now includes measurements for the cryptographic coprocessor facility (CCF). In addition, new overview conditions are available for the Postprocessor.

Support of FICON switch cascading
The FICON® Director Activity report has been enhanced to indicate that another switch is connected to a port in the case of FICON cascaded switches.

State samples breakdown in the WLMGL report
Up to this release, state samples have been reported as a percentage of average transaction response time (response time breakdown). The response time is calculated when a transaction ends. This can result in percentages greater than 100 when samples are included for long running transactions that have not ended in the gathering interval. Percentages greater than 100 in the breakdown section are now avoided by showing the state values as percentages of the total transaction samples (state samples breakdown) instead of percentages of response time.