Virtual Machine Migration Rescheduling with Semi-Constraint Exclusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual machine migration scheduling systems face challenges in efficiently rescheduling migrations with minimal impact on existing schedules, especially when user demands change, due to the complexity of constraints and large number of virtual machines and physical machines involved.
Innovation Solution
An apparatus that acquires change information for virtual machine migration time slots, generates constraint information, and excludes specific constraints to minimize differences in scheduled migration times for other virtual machines, using semi-constraint information to reschedule migrations while reducing the impact on existing schedules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If rescheduling is performed to accommodate user demand changes, then adaptability improves, but the complexity of managing constraints increases
Solution Approach 1:
The patent segments the constraint management process into distinct components: acquiring change information, generating constraint information, creating semi-constraint information by excluding specific constraints, and rescheduling. This segmentation allows the system to handle complex rescheduling by breaking it into manageable steps, where each step deals with specific aspects of the constraint set rather than all constraints simultaneously.
Solution Approach 2:
The patent extracts and excludes specific constraints from the full constraint set to create semi-constraint information. By taking out certain constraints that would make rescheduling infeasible or overly complex, the system can find satisfactory solutions more efficiently. This extraction principle allows the system to balance between maintaining constraint satisfaction and achieving rescheduling feasibility.
2Adaptability or versatility
If rescheduling is performed to accommodate user demand changes, then adaptability improves, but the impact on existing migration schedules increases
Solution Approach 1:
The patent applies partial action by excluding only specific constraints from the full constraint set rather than re-evaluating all constraints. This partial approach to constraint management allows rescheduling to proceed with reduced complexity while minimizing disruption to existing schedules. The system performs just enough rescheduling to accommodate the change information without unnecessarily altering other scheduled migrations.
Solution Approach 2:
The patent changes the parameter set by using semi-constraint information instead of full constraint information. This parameter change allows the rescheduling algorithm to operate with a modified constraint set that is more favorable to maintaining existing schedules while still accommodating necessary changes. The exclusion of certain constraints effectively changes the optimization parameters to prioritize schedule stability.
3Reliability
If all constraints are maintained during rescheduling, then reliability of schedule satisfaction improves, but the difficulty of finding a solution increases
Solution Approach 1:
The patent extracts specific constraints from the full constraint set to create semi-constraint information. By removing certain constraints that would make the problem intractable, the system can find rescheduling solutions more easily. This extraction maintains the essential constraints needed for schedule validity while eliminating overly restrictive constraints that would prevent finding any solution.
Solution Approach 2:
The patent applies partial constraint satisfaction by using semi-constraints rather than full constraints. This partial approach allows the system to find satisfactory rescheduling solutions without requiring complete constraint satisfaction, which would be too difficult to achieve. The system performs rescheduling with a relaxed constraint set that still provides adequate schedule control.
Data Source
AI summary
An apparatus, for an existing schedule indicating time slots during which virtual-machines are to be migrated between physical-machines, acquires change information indicating a change of first time slots during which first virtual-machines are to be migrated, and generates constraint information including a group of constraints regarding the change information and second time slots during which second virtual-machines other than the first virtual-machines are to be migrated. The apparatus generates semi-constraint information items each generated by excluding, from the constraint information, an exclusion target constraint that is selected in turn from among the group of constraints, and generates, for each semi-constraint information item, a rescheduling result by rescheduling migrations of the virtual-machines. The apparatus outputs a first rescheduling result that is one of the generated rescheduling results which reduces a difference between a scheduled migration time indicated by the first rescheduling result and scheduled migration times of the second virtual-machines.