September 22, 2022 By Val Besong 3 min read

Reduce licensing costs and increase production throughput with Shared Processor Pools.

Do you need to optimize CPU pooling and sharing on IBM Power Systems Virtual Server to ensure compliance with a software license? Do you want to ensure reserved capacity for disaster recovery or high availability purposes to quickly extend resources of those environments? Do you want to consolidate multiple environments where non-production would not interfere with production while maximizing resource utilization? Shared Processor Pools, now available on IBM Power Systems Virtual Server, can be used to handle these scenarios.

What are Shared Processor Pools?

Shared processors are physical processors whose processing capacity is shared among multiple logical partitions (LPARs). A Shared Processor Pool (SPP) can be used to control the amount of processor capacity that LPARs can use from the available physical processors in the system. Each LPAR is defined with an entitled CPU capacity and gives back to the pool the unused CPU, so uncapped LPARs from the same processor pool can reuse these idle CPU cycles and run higher CPU than the entitled capacity allocated. This mechanism is real CPU sharing instead of common CPU mapping implemented on software-based virtualizations. In Power Virtual Server, the cores defined in a Shared Processor Pool are reserved and dedicated.

Benefits

Shared Processing Pools on IBM Power Virtual Server minimize software licensing costs while increasing throughput. Many software providers charge based on the number of available processors. Shared Processor Pools enable users to combine apps together and define a maximum number of processing unit for each pool.

Shared Processor Pools also guarantee that VMs defined in the pool cannot exceed the CPU capacity of the pool, and CPU consumption is physically limited to the corresponding number of cores. It ensures that VMs are capped to the size of the pool. With Shared Processor Pools, you have more control over managing processor resources and imposing capacity constraints.

Shared Processor Pools on IBM Power Virtual Server gives you the ability to pool LPARs into different groups, depending on their needs — this allows you to isolate workloads for licensing reasons, and it allows you to group LPARs together in a logical manner. As an example, you may have a group of LPARs that each peak at two cores, but they do not peak together. If you were designing this unshared, then you would need a lot more cores than if you put them in a properly sized pool and let them share the resources as they need them. The key is to ensure the pool is sized for the peak processor units needed.

When expanding to run off-premises, most organizations are impacted by either a technology disruption against what is used on-premises or a software licensing rules model. By implementing the same Shared Processor Pool technology in IBM Power Virtual Server that is used on-premises, businesses now have the same pricing metrics and capabilities in both environments while getting a complete consistent architecture for hybrid cloud. Clients maximize their software investments and licenses, regardless of whether they deploy on- or off-premises thanks to bring your own license (BYOL) model.  

Utilizing the SPP pricing model gives you access to reserved capacity, enabling cost-effective high availability and disaster recovery. You can create a Shared Processor Pool with the required capacity and reserve core capacity at capped core pricing for future usage. You can start deploying Shared Processor virtual machines (VMs) into the SPP whenever it is ready to use the resource capacity. As an alternative, you can install the Shared Processor VMs in the SPP up front with limited authorized capacity and increase (or decrease) their capacity as necessary.

Pricing

Shared Processor Pool also offers cost-effective pricing. You are charged on an hourly basis for the core capacity assigned to each SPP you own. Even if the core capacity is entirely allocated for the SPP, the rate is lower than the dedicated processor VM hourly rate. You often pay a comparable total cost and have assured capacity when using SPP:

Shared Processor Pool reserve capacity use case.

Get started today

IBM Power Systems Virtual Server with Shared Processor Pools is now available in all data centers.

To learn more and get started, please contact an IBM Power Expert today.

More from Announcements

Success and recognition of IBM offerings in G2 Summer Reports  

2 min read - IBM offerings were featured in over 1,365 unique G2 reports, earning over 230 Leader badges across various categories.   This recognition is important to showcase our leading products and also to provide the unbiased validation our buyers seek. According to the 2024 G2 Software Buyer Behavior Report, “When researching software, buyers are most likely to trust information from people with similar roles and challenges, and they value transparency above other factors.”  With over 90 million visitors each year and hosting more than 2.6…

Manage the routing of your observability log and event data 

4 min read - Comprehensive environments include many sources of observable data to be aggregated and then analyzed for infrastructure and app performance management. Connecting and aggregating the data sources to observability tools need to be flexible. Some use cases might require all data to be aggregated into one common location while others have narrowed scope. Optimizing where observability data is processed enables businesses to maximize insights while managing to cost, compliance and data residency objectives.  As announced on 29 March 2024, IBM Cloud® released its next-gen observability…

Unify and share data across Netezza and watsonx.data for new generative AI applications

3 min read - In today's data and AI-driven world, organizations are generating vast amounts of data from various sources. The ability to extract value from AI initiatives relies heavily on the availability and quality of an enterprise's underlying data. In order to unlock the full potential of data for AI, organizations must be able to effectively navigate their complex IT landscapes across the hybrid cloud.   At this year’s IBM Think conference in Boston, we announced the new capabilities of IBM watsonx.data, an open…

IBM Newsletters

Get our newsletters and topic updates that deliver the latest thought leadership and insights on emerging trends.
Subscribe now More newsletters