HP-UX Workload Manager User's Guide

Example configuration files

par_manual_allocation.wlm

Chapter 9306

# num_cpus value to see how the workload behaves with various

# numbers of cores. With small partitions, you should be able to

# step through all the available cores and evaluate workload

# response quickly.

# 8. Monitor each SLO’s request for CPU shares, using the following

# wlminfo command:

# wlminfo slo -v [-l]

# The output will show the shares request (“Req” column)

# change for the partition as you change the num_cpus value

# using wlmsend.

# To monitor the partitions, use the following wlminfo command

# at the host on which wlmpard is running:

# wlminfo par -l

# The output will include information about the CPU resources

# associated with each partition.

# Now for the actual configuration components.

# The primary_host keyword specifies the host name for the partition where

# WLM’s global arbiter will run. (This keyword has the same value on each

# partition.)

# See wlmconf(4) for complete HP-UX WLM configuration information.

primary_host = myserver; # Change this value

# Set the interval on which WLM takes CPU requests and makes changes in CPU

# allocations to 5 seconds. (The default interval is 60 seconds. Using a

# smaller interval allows WLM to respond more quickly. If you change this

# interval, be sure the global arbiter interval set in par_usage_goal.wlmpar

# is greater than the new wlm_interval value you set here.)

tune {

wlm_interval = 5;

}

# Change the priority (pri) value after copying this file to each partition.

# This value (1 being the highest priority) indicates the importance of the