Partition Availability Priority

Use this window to specify the partition-availablity priority of each logical partition on this managed system. The managed system uses partition-availablity priorities in the case of processor failure. If a processor fails on a logical partition, and there are no unassigned processors available on the managed system, the logical partition can acquire a replacement processor from logical partitions with a lower partition-availability priority. This allows the logical partition with the higher partition-availability priority to continue running after a processor failure.

When a processor fails on a high-priority logical partition, the managed system follows these steps to acquire a replacement processor for the high-priority logical partition.

1. If there are unassigned processors on the managed system, the managed system replaces the failed processor with an unassigned processor.
2. If there are no unassigned processors on the managed system, the managed system checks the logical partitions with lower partition-availability priorities, starting with the lowest partition-availability priority.
   • If a lower-priority logical partition uses dedicated processors, the managed system shuts down the logical partition and replaces the failed processor with one of the processors from the dedicated-processor partition.
   • If a lower-priority logical partition uses shared processors, and removing a whole processor from the logical partition would not cause the logical partition to go below its minimum value, the managed system removes a whole processor from the shared-processor partition using Dynamic Logical Partitioning and replaces the failed processor with the processor that the managed system removed from the shared-processor partition.
   • If a lower-priority logical partition uses shared processors, but removing a whole processor from the logical partition would cause the logical partition to go below its minimum value, the managed system skips that logical partition and continues to the logical partition with the next higher partition availability.
3. If the managed system still cannot find a replacement processor, the managed system shuts down as many of the shared-processor partitions as it needs to acquire the replacement processor. The managed system shuts down the shared-processor partitions in partition-availability priority order, starting with the lowest partition-availability priority.

A logical partition can take processors only from logical partitions with lower partition-availability priorities. If all of the logical partitions on your managed system have the same partition-availability priority, then a logical partition can replace a failed processor only if the managed system has unassigned processors.

By default, the partition availability priority of Virtual I/O Server logical partitions is set to 191. The partition-availablity priority of all other logical partitions is set to 127 by default.

Do not set the priority of Virtual I/O Server logical partitions to be lower than the priority of the logical partitions that use the resources on the Virtual I/O Server logical partition.

Set the priority of IBMi logical partitions with virtual SCSI adapters to be higher than the priority of any logical partitions that use the resources on the IBMi logical partition.

You can find more detailed help on the following elements of this window:

Partition list

Availablilty priority