Managing CPU resources for high availability micro-partitions

摘要

A partition manager relocates a logical partition from a primary shared processor pool to a secondary shared processor pool in response to a predetermined condition, such as a hardware failure. The relocated logical partition is allocated a smaller quantity of processing units from the secondary pool than it was allocated from the primary pool. A quantity of processing units reserved for a second logical partition is identified in the secondary shared processor pool, and a portion of those reserved processing units are allocated to the relocated logical partition. The reserved processing units may be redistributed among multiple relocated logical partitions.

主权项

1. A method for managing a logical partition, the method comprising:
relocating, by a partition manager in response to a predetermined condition, the logical partition from a first quantity of processing units in a primary shared processor pool to a second quantity of processing units in a secondary shared processor pool, the second quantity less than the first quantity; identifying a third quantity of processing units in the secondary shared processor pool, the third quantity of processing units reserved for a second logical partition; and allocating a portion of the third quantity of processing units to the relocated logical partition.