gWLM in Action

This section helps you see gWLM move CPUs among vpars. You can use similar steps to see CPUs move among npars, virtual machines, psets, or fss groups. For psets and fss groups, though, you will need to put processes in the desired pset or fss group. (You place processes by modifying the workload definition or by using the gwlmplace command.) In this example:

The gWLM agent is used on two vpars, which we will call vpar1 and vpar2
These vpars are idle and have a number of unbound CPUs that gWLM can move among them
SIM and the gWLM CMS software are installed, configured, and running on a vpar called vpar3

To see gWLM in action:




	NOTE: You must be logged in as root on the systems where you run the `mxstart`, `gwlmcmsd`, and `gwlmagent` commands mentioned below. In SIM, you must be logged in as root or have authorizations for “All Tools,” “VSE All Tools,” or “gWLM All Tools.”

Start the gWLM agent daemons on vpar1 and vpar2:
# vpar1> /opt/gwlm/bin/gwlmagent
# vpar2> /opt/gwlm/bin/gwlmagent
Alternatively, you can start the agents through SIM, as discussed in the VSE Management Software Installation and Update Guide.
Connect to SIM by pointing your web browser to:
http://hostname:280
where hostname represents the hostname of the CMS, in this case, vpar3.
Create a gWLM SRD containing the two vpars by following the steps given in “Getting Started with gWLM”
1. For hosts, enter the names of the two vpars separated by a space in the field beneath the table
2. Ensure when setting the SRD properties that the mode is Managed.
3. Use an OwnBorrow policy for the vpar1 workload and for the vpar2 workload
  An OwnBorrow policy has a name of the form:
  Owns_4_CPUs-Max_8_CPUs
  Ideally, the sum of the CPUs owned by the workloads will equal the total number of CPUs in the SRD when using this type of policy. (You may need to edit policies to achieve this equality.)
4. Confirm and finish the SRD creation (You are then placed on the SRD View, showing the newly created SRD and its workloads.)
Select the vpar1 workload
View gWLM’s real-time reports to show CPU allocation for vpar1 by selecting in the VSE Management menu bar:
Report
-> gWLM Real-time Reports...
You can also view the reports by selecting the workload’s bar graph.
Select the [View Policy Detail] button to see a graph of vpar1’s CPU allocation
Start a CPU-intensive workload in vpar1
If you already have such a workload configured in vpar1, start it now.
If you need such a workload, the following command prints its PID (24379 in this case) and then just consumes CPU:
# perl -e ’print "$$\n";while (1) {};’ &
[1] 24379
This command will consume most of a single CPU. Start multiple copies of the command to consume additional CPUs.
Wait a few minutes then look at the “Policy Request and Workload Allocation” graph from Step 6 to see how the policy for vpar1’s workload is requesting CPU allocations and how gWLM is granting them
Kill the workloads you started in vpar1
Repeat Step 5 through Step 9 for the vpar2 workload to see gWLM move CPUs to vpar2

gWLM in Action

Technical documentation

» Table of Contents