pSeries Processors Test

This test reports the quantity of allocated and unallocated physical CPU resources of the pSeries server, and the percentage of allocated CPU that has been utilized by the LPARs on that server. In the process, the test helps assess the impact of the guest CPU usage on the physical CPU resources of the pSeries server. If the server experiences a CPU contention, then this test will enable you to figure out whether the resource-crunch is owing to improper CPU allocation to the LPARs, or the existence of one/more CPU-intensive processes on the LPARs.

Target of the test : An IBM pSeries server

Agent deploying the test : A remote agent

Outputs of the test : One set of results for the IBM pSeries server being monitored.

Configurable parameters for the test
Parameter Description

Test period

How often should the test be executed

Host

The IP address of the host for which this test is to be configured.

Port

Indicate the port at which the specified Host listens. By default, this is NULL.

HMC Server IP

This test connects to an HMC server to perform LPAR discovery and to collect host-level and "outside view" metrics from the pSeries server. To enable this communication, first, provide the IP address/host name of the HMC server in the HMC Server IP text box. If the eG manager had automatically discovered the target pSeries server by connecting to an HMC server in the environment, then, the IP address/host name will be automatically displayed in the HMC Server IP text box. and user credentials pertaining to that HMC server

However, if the pSeries server being monitored was manually added to the eG Enterprise system (and not auto-discovered via the HMC server), then, you will have to explicitly provide the IP address of the HMC server that manages the target pSeries server in the HMC Server IP text box.

HMC Console Username, HMC Console Password and Confirm Password

This test makes REST API requests to the HMC console to pull the metrics. For this purpose, the test needs to be configured with the credentials of a user who can access the HMC console in the HMC Console Username and HMC Console Password text boxes.

Confirm the HMC Console Password by retyping it in the Confirm Password text box.

Measurements made by the test
Measurement Description Measurement Unit Interpretation

Installed processing units

Indicates the number of processing units installed on the pSeries server.

Number

 

Available processing units

Indicates the number of free processing units on the pSeries server.

Number

Typically, a large number of free processing units implies that more logical partitions can be configured on the server. If the value of this measure is very low, it could mean that almost all the CPU resources have been allocated to the LPAR guests. You can use the detailed diagnosis of the Used processing units measure to accurately identify the LPAR that has been allocated the maximum CPU.

Used processing units

Indicates the total number of processing units allocated to the LPAR guests on the pSeries server.

Number

If the value of this measure is very high or is close to the value of the Installed processing units measure, it could mean that almost all the CPU resources of the host have been allocated to the LPAR guests. In this case, you can use the detailed diagnosis of this measure to understand how many processing units have been allocated to each LPAR, and thus accurately identify the LPAR that has been allocated the maximum CPU.

Processing units utilization

Indicates the percentage of physical CPU resources allocated to the LPAR guests.

Percent

If the value of this measure is very high or is close to 100%, it could mean that almost all the CPU resources of the host have been allocated to the LPAR guests. In this case, you can use the detailed diagnosis of this measure to understand how many processing units have been allocated to each LPAR, and thus accurately identify the LPAR that has been allocated the maximum CPU.

Total physical processors consumed

Indicates the total number of allocated processing units used by LPAR guests.

Number

The detailed diagnosis of this measure reports the number of physical processors consumed by each LPAR guest on the pSeries server. In the event of a CPU contention, you can use this information to accurately identify the LPAR which is consuming the maximum CPU.

Physical processors consumed out of allocation

Indicates the percentage of allocated CPU utilized by the LPAR guests.

Percent

A high value for this measure could indicate that one/more LPARs have resource-intensive processes executing on them.

Physical processors utilization

Indicates the percentage of physical CPU resources utilized by the LPAR guests.

Percent

A high value for this measure could indicate that one/more LPARs are over-utilizing the physical CPU resources.

Total physical processors

Indicates the total number of physical processors installed on the pSeries server.

Number

Dedicated processors

Indicates the total number of dedicated processors used by the LPAR guests.

Number

A dedicated processor partition has an entire processor that is assigned to a partition. These processors are owned by the partition where they are running and are not shared with other partitions. Also, the amount of processing capacity on the partition is limited by the total processing capacity of the number of processors configured in that partition, and it cannot go over this capacity (unless you add or move more processors from another partition to the partition that is using a dynamic LPAR operation).

Shared processors

Indicates the total number of shared processing units used by the LPAR guests.

Number

A partition that has its processors virtualized from a pool of shared physical processors is a shared processor partition. When the processors are in the shared processing pool, an uncapped partition that needs more processing power can use the idle processing resources in the pool.

You can use the detailed diagnosis of the Used processing units measure to accurately identify the LPAR that has been allocated the maximum CPU.

Figure 1 : The detailed diagnosis of the Used Processing Units measure

The detailed diagnosis of the Total physical processors consumed measure reports the number of physical processors consumed by each LPAR guest on the pSeries server. In the event of a CPU contention, you can use this information to accurately identify the LPAR which is consuming the maximum CPU.

Figure 2 : The detailed diagnosis of the Total physical processors consumed measure

Configuring Users for LPAR Monitoring

In order to enable the eG agent to connect to multiple LPARs and pull out metrics from them, the eG administrative interface provides a special page using which the different Admin User names and Admin Passwords can be specified. To access this page, just click on the Click here hyperlink in any of the test configuration pages.

Figure 3 : Configuring a test

Upon clicking, will appear, using which the user details can be configured.

Figure 4 : The LPAR user configuration page

To add a user specification, do the following:

  1. By default, the Domain will be set to none (see ).
  2. Next, provide the credentials of a valid user to one of the LPARs in the Admin User text box.
  3. The password of the specified Admin User should be mentioned in the Admin Password text box.
  4. Confirm the password by retyping it in the Confirm Password text box.
  5. To add more users, click on the Add More button in . This will allow you to add one more user specification as depicted by Figure 5.

    Figure 5 : Adding another user

    When this is done, then, while attempting to connect to an LPAR, the eG agent will begin by using the first Admin User name of the specification. If, for some reason, the agent is unable to login using the first Admin User name, then it will try to login again, but this time using the second Admin User name of the specification. If the first login attempt itself is successful, then the agent will ignore the second Admin User name.

  6. To clear all the user specifications, simply click the Clear button in Figure 5.
  7. To remove the details of a particular user alone, just click the button in Figure 5.
  8. To save the specification, just click on the Update button in Figure 5. This will lead you back to the test configuration page, where you will find user names, and passwords listed against the respective fields (see Figure 6).

Figure 6 : The test configuration page displaying multiple user names, and passwords