Resizing partitions automatically with HP-UX Workload Manager

– On the Integrity VM host, run WLM with a strictly host-based configuration designed

exclusively for moving cores across partitions or activating Temporary Instant Capacity

(TiCAP) or Pay per use (PPU) cores. For purposes of this paper, using WLM on an

Integrity VM host is the same as using WLM to manage an nPartition with a strictly

host-based configuration.

– Inside any Integrity VM (guest), run WLM to manage resources of the guest HP-UX

resources. You cannot use Instant Capacity, PPU, and vPar integration; however,

WLM does take advantage of cores added to the Integrity VM host by Instant

Capacity and PPU.

Note

For more robust management of virtual machines, you can use

HP-UX Global Workload Manager (gWLM). For more

information, see the following web site:

http://www.hp.com/go/gwlm

• Resource partitions—Provided by PRM, which manages pSets and Fair Share Scheduler (FSS)

groups, resource partitions enable you to partition system resources (including memory and disk

bandwidth) within a single instance of HP-UX and consolidate multiple workloads within that

instance. These workloads are usually referred to as “workload groups.” To enable you to manage

workload groups within resource partitions, WLM creates and manages its own PRM configuration

(PRM must be installed on the same system). You can use the resource partitions within (but not

across) hard partitions and virtual partitions.

Note

In WLM interfaces (such as the WLM configuration wizard or

wlminfo displays), the term “workload group” typically refers to

a workload; “workload” and “workload group” are often used

interchangeably. However, workload groups need be created

and referred to as such only when referring to a pSet or FSS

group in one HP-UX instance.

• Temporary Instant Capacity—Using Temporary Instant Capacity (version 6 or later), WLM can

automatically activate and deactivate Instant Capacity cores that are licensed temporarily. (A core

is the actual data processing engine within a processor; a processor can have multiple cores.) WLM

optimizes the number of active cores to the smallest number of cores needed to satisfy the SLOs.

This optimization minimizes your costs.

• Pay per use (PPU)—WLM integrates with PPU versions 4, 7, or later. With PPU version 4, capacity

can be increased or decreased by whole cores as needed, with billing determined by the number

of active cores. Beginning with PPU version 5, all cores on a PPU system are active and billing is

based on your percentage of usage of those cores. Starting with PPU version 7, which includes PPU

version 5 capabilities, billing can also be based on the number of active cores on the system, with

WLM activating only those cores that are needed. (With pSets on the same complex, only use PPU

v7 or later.)

Using WLM in such an environment, you can have the system CPU capacity increased or decreased

automatically. After you set your SLOs in the WLM configuration file, WLM automatically optimizes

the number of active cores to the smallest number of cores needed to satisfy the SLOs. PPU allows

you to pay only for the amount of cores you use. Therefore, you minimize the number of active

cores—and, thus, your costs.