HP-UX Workload Manager User's Guide

Advanced WLM usage: Using performance metrics
Supplying data to WLM
Appendix H 483
NOTE A white paper on data collectors (”Writing a Better WLM Data
Collector”) is available at the following location:
/opt/wlm/share/doc/howto/perfmon.html
This paper provides additional information on implementing your data
collectors.
How applications can make metrics available to WLM
Consider the following overview of how to get metrics to WLM.
Time metrics from instrumentable applications
If the desired metric can be measured in units of time, and the
application can be modified, we recommend using the ARM API provided
by GlancePlus. WLM will then collect the ARM data from GlancePlus,
synchronizing the values used by WLM with those used in VantagePoint
Performance tools.
Adding ARM routines to an application is as simple as specifying your
application with an arm_init call, marking the start of the time period
to be measured with an arm_start call, and marking the end of the time
period with an arm_end call.
For more ARM information, see “Sending ARM transaction data from a
modified C program” on page 504.
Other data collection techniques
If your application cannot be modified to insert ARM calls, or if your
metric does not have time units, then implement an external data
collector. There are three types of external data collectors to consider:
• Independent collectors
• Stream collectors
• Native collectors
These collector types are explained in the remainder of this section.