Logical Partition Live Migration via Call Checkpoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The migration of logical partitions in computer systems is time-consuming, resulting in unacceptable delays and excessive downtime, as existing methods require the partition to be halted or restarted, leading to inefficiencies in resource allocation and utilization.
Innovation Solution
A partition migration mechanism that uses a call checkpoint mechanism to save the operating system's state and resume execution before all resources are migrated, allowing for live migration by preempting virtual CPUs and handling resource faults, enabling the logical partition to function in a new location before complete resource migration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional migration methods are used to migrate a logical partition, then the partition can be moved to a new computer system, but the partition must be halted or restarted causing excessive downtime and unacceptable delays
Solution Approach 1:
The patent creates a new logical partition in the destination computer system before migrating resources. The partition manager code is installed and the new partition is configured in advance, so when migration occurs, the partition can be resumed immediately without halt or restart, eliminating downtime and ensuring continuous availability.
2Productivity
If resources are migrated completely before resuming the logical partition, then the partition can function correctly in the new location, but the migration process becomes time-consuming
Solution Approach 1:
The patent migrates essential resources and configuration data before resuming the logical partition. The partition manager code and critical resource assignments are transferred in advance, allowing the partition to be resumed quickly without waiting for complete resource migration, thus increasing migration speed while maintaining functionality.
Solution Approach 2:
The patent enables the logical partition to continue executing operations in the new location while resource migration is still in progress. By maintaining continuous execution capability through the pre-configured new partition, the system achieves both fast migration and uninterrupted operation, resolving the contradiction between migration speed and completeness.
3Loss of time
If the logical partition is resumed before all resources are migrated, then downtime is minimized, but resource faults may occur during migration
Solution Approach 1:
The patent implements a feedback mechanism where the partition manager continuously monitors resource migration status and availability. When resources are needed during partition resumption, the system checks migration progress and can pause or adjust resource allocation accordingly, ensuring reliable operation while maintaining minimal downtime through active feedback control.
Data Source
AI summary
A partition migration mechanism migrates a logical partition executing an operating system and resumes the logical partition before all resources in the logical partition have been migrated. When a partition is being migrated, a call checkpoint mechanism creates checkpoints of the state of the operating system when the partition manager is called. Before performing the call to the partition manager, a check is made to determine if all resources required by the call are available. If so, the partition manager call is executed. If all resources required by the call are not available, a resource fault is indicated, which causes the operating system state from the last checkpoint to be restored and a corresponding virtual CPU to be preempted until the resource that caused the fault becomes available. Exceptions that do not require the missing resource may be performed while the virtual CPU awaits the resource to become available.