Processors

This information describes how you can set the managed system to distribute its processing capacity among the logical partitions on the managed system.

A processor is a device that processes programmed instructions. The more processors that you assign to a logical partition, the greater the number of concurrent operations that the logical partition can run at any given time.

You can set up a logical partition to use either shared processors from a shared processor pool or processors that are dedicated to that logical partition. If a logical partition uses dedicated processors, then you must assign processors (in increments of whole numbers) to the logical partition. A logical partition that uses dedicated processors cannot use any processing capacity beyond the processors that are assigned to the logical partition, and no other logical partition can use the dedicated processors that are assigned to that logical partition.

All processors that are not dedicated to specific logical partitions are placed in the shared processor pool. The shared processor pool can be used by logical partitions that are set to use shared processors. You can set a logical partition that uses shared processors to use as little as 0.10 processing units, which is approximately one tenth of the processing capacity of a single processor. You can specify the number of processing units to be used by a shared processor logical partition down to the hundredth of a processing unit. Also, you can set a shared processor logical partition so that, if the logical partition requires more processing capacity than its assigned number of processing units, the logical partition can use unused processing units from the shared processor pool. (Some IBM^® eServer™ p5, IBM System p5™, and IBM eServer OpenPower™ server models might require you to enter an activation code before you can create logical partitions that use shared processors.)

Unless the operating system or server model limits the number of processors that a logical partition can use, you can assign up to the entire processing capacity on the managed system to a single logical partition. An i5/OS^® logical partition can use a maximum of 32 processors at a time. Also, IBM eServer p5 servers limit the total number of processors that can be used by all i5/OS logical partitions on the managed system. The number of processors that can be used by i5/OS logical partitions on IBM eServer p5 servers varies by server model. In turn, this limits the number of i5/OS logical partitions that you can create on these IBM eServer p5 servers and the possible configurations of those i5/OS logical partitions.

On IBM eServer p5 servers that support one processor for i5/OS logical partitions, you can create the following i5/OS logical partitions:

One logical partition that uses one dedicated processor.
One logical partition that uses uncapped shared processing units, with a maximum of one virtual processor for the logical partition.
Up to ten logical partitions that use capped shared processing units, with a minimum of 0.10 processing units for each logical partition.

On IBM eServer p5 servers that support two processors for i5/OS logical partitions, you can create the following i5/OS logical partitions:

One logical partition that uses one or two dedicated processors.
Two logical partitions that use one dedicated processor each.
One logical partition that uses uncapped shared processing units, with a maximum of two virtual processors for the logical partition.
Two logical partitions that use uncapped shared processing units, with a maximum of one virtual processor for each logical partition.
One logical partition that uses one dedicated processor and one logical partition that uses uncapped shared processing units, with a maximum of one virtual processor for the logical partition that uses uncapped shared processing units.
One logical partition that uses one dedicated processor and from one to ten logical partitions that use capped shared processing units, with a minimum of 0.10 processing units for each logical partition that uses capped shared processing units.
One logical partition that uses uncapped shared processors, with a maximum of one virtual processor for each logical partition that uses uncapped shared processing units, and from one to ten logical partitions that use capped shared processing units, with a minimum of 0.10 processing units for each logical partition that uses capped shared processing units.
From one to twenty logical partitions that use capped shared processors, with a minimum of 0.10 processing units for each logical partition.

Automatic redistribution of work when a processor fails

If the server firmware detects that a processor is about to fail, or if a processor fails when the processor is not in use, then the server firmware creates a serviceable event. The server firmware can also deconfigure the failing processor automatically, depending upon the type of failure and the deconfiguration policies that you set up using the Advanced System Management Interface (ASMI). You can also deconfigure a failing processor manually using the ASMI. For more information, see Setting deconfiguration policies and Deconfiguring hardware.

If a processor fails when the processor is in use, then the entire managed system shuts down. When a processor failure causes the entire managed system to shut down, the system deconfigures the processor and restarts. The managed system attempts to start the logical partitions that were running at the time of the processor failure with their minimum processor values. If the managed system does not have enough processor resources to start all of the logical partitions with their minimum processor values, then the managed system starts as many logical partitions as it can with their minimum processor values. If there are any processor resources remaining after the managed system has started the logical partitions, then the managed system distributes any remaining processor resources to the running logical partitions in proportion to their desired processor values.