2. PERFORMANCE REPORTING ANALYSIS › 2.1 ILM Analysis › 2.1.2 Usage Guidelines › 2.1.2.1 MSU Consumption Rate and Soft Capping Analysis

2.1.2.1 MSU Consumption Rate and Soft Capping Analysis

The MSU Consumption Rate and Soft Capping plot and report
analyzes HARCPU data collected from z/OS workloads. Using
detail-level data, this query tracks MSU consumption rate,
four-hour rolling averages, and the percentage of time an LP
has been soft-capped. These metrics are plotted along
with the total number of SUs available to the partition.
When defined capacity limits are implemented, the SUs
available to the partitions reflects the defined capacity
limit.  The tabular report lists these metrics along with a
soft capping threshold indicator.

The soft capping percentage threshold can be specified on the
extended options panel. The query uses a default of 05%,
unless otherwise specified. The threshold indicator is
populated with an eye catcher of "<- EXCEEDED 05%" when the
user-specified soft capping percentage is exceeded. The
MICSLOG message PER03900I indicates at a glance if any LPARs
exceeded the threshold.

The query also lets you generate a ServicePlus Service Desk
alert when the soft capping threshold has been exceeded. This
can be done by activating threshold alerting on the extended
option panel. This feature works in conjunction with the soft
capping threshold extended option.  The MICSLOG message
PER03900I indicates at a glance if any LPARs exceeded the
threshold, and the MICSLOG BAS63099I message indicates if the
Service Desk alert was generated and the request number for
reference.

When analyzing the report generated by this query, the
following are some guidelines to follow:

o When the defined capacity is exceeded by the MSU four-hour
  rolling average.

  If the MSU four-hour rolling average exceeds the defined
  capacity for long periods (high WLM capping percentage
  reported), you may consider performing a workload analysis
  on the four hours leading up to this event, to help you
  understand the workload associated with the spiking in MSU
  consumption rate. You may also consider looking at the
  performance impact that the soft capping had on your
  performance groups.

o When the MSU four-hour rolling average and the WLM capping
  percentage values are always zero while the MSU consumption
  rate is non zero.

  When this occurs, it signifies that you are processing z/OS
  data but ILM's soft capping has not been activated. The LP
  in question has implemented either a hard cap or an
  uncapped LP.

o Setting your defined capacity

  Ideally, your peak MSU consumption rate must always be as
  close as possible to the defined capacity, without
  exceeding it. A general rule to follow when setting your
  defined capacity is to set it near the MSU consumption
  rate's 95th percentile.

  Remember that capping affects all workloads running in the
  partition and can result in elongated response times and
  generally unacceptable performance.

The following are some additional guidelines to follow once
you have set the defined capacity:

o If the peak MSU consumption rate is constantly lower than
  the defined limit, you may consider decreasing the LPAR
  capacity until WLM begins capping the partition. (A capping
  percentage of 1% to 5% ensures the work is done optimally
  at the lowest cost.)

o If the peak value exceeds the defined capacity for long
  periods (high WLM capping percentage reported), you may
  consider increasing the LPAR capacity limit until the WLM
  capping percentage falls to within an acceptable range.

o If the peak value occasionally exceeds the defined capacity
  (low WLM capping percentage), you may consider
  time-shifting the workload.