Dynamic Virtual Machine Migration for SLA Compliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In consolidated server environments, end-user application performance degrades due to overutilization of critical resources, leading to service level agreement (SLA) violations, and existing consolidation approaches fail to account for the migration cost of reallocating virtual machines (VMs) to maintain SLA compliance.
Innovation Solution
A dynamic virtual machine management technique that monitors performance metrics and migration costs to determine an optimal migration policy, automatically reallocating VMs to maintain SLA compliance by minimizing migration costs and maximizing resource utilization across physical servers, using an iterative approach that works at the operating system level and is independent of application software.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If virtual machines are reallocated to maintain SLA compliance, then service level agreement compliance is improved, but migration cost increases
Solution Approach 1:
The system dynamically changes the parameters of VM allocation by monitoring performance metrics and adjusting VM-to-physical-machine mappings based on changing workload conditions. This allows the system to maintain SLA compliance by transitioning from a static allocation to a dynamic one that adapts to performance degradation, thereby resolving the contradiction between maintaining compliance and avoiding unnecessary migration costs.
Solution Approach 2:
The system implements a feedback mechanism where performance measurements are continuously monitored and used to trigger VM reallocation decisions. When performance metrics indicate SLA violations, the system responds by migrating VMs to appropriate physical machines. This closed-loop feedback ensures SLA compliance is maintained while migration costs are incurred only when necessary, not continuously.
2Productivity
If multiple virtual machines are consolidated onto fewer physical machines, then resource utilization is improved, but application performance degrades due to overutilization
Solution Approach 1:
The system transforms the static VM-to-physical-machine mapping into a dynamic allocation model where VMs can be migrated between physical machines based on real-time performance conditions. This dynamic approach allows the system to maintain high resource utilization through consolidation while preventing performance degradation by migrating VMs when physical machines become overutilized, thus resolving the contradiction between productivity and reliability.
Solution Approach 2:
The system enables self-service through automated monitoring and migration of virtual machines based on performance metrics. When a physical machine becomes overutilized, the system automatically identifies and migrates affected VMs to underutilized physical machines without manual intervention. This self-service mechanism maintains both high resource utilization and application performance by continuously balancing the load across the infrastructure.
3Reliability
If virtual machines are migrated frequently to maintain optimal performance, then application performance is improved, but migration cost increases
Solution Approach 1:
The system applies partial action by migrating only the specific virtual machines that are causing performance issues rather than migrating all VMs. The system identifies individual VMs on overutilized physical machines and migrates only those, leaving other VMs undisturbed. This selective approach maintains application performance while minimizing migration costs by avoiding unnecessary migrations of VMs that are already performing optimally.
Data Source
AI summary
Techniques for dynamic management of virtual machine environments are disclosed. For example, a technique for automatically managing a first set of virtual machines being hosted by a second set of physical machines comprises the following steps/operations. An alert is obtained that a service level agreement (SLA) pertaining to at least one application being hosted by at least one of the virtual machines in the first set of virtual machines is being violated. Upon obtaining the SLA violation alert, the technique obtains at least one performance measurement for at least a portion of the machines in at least one of the first set of virtual machines and the second set of physical machines, and a cost of migration for at least a portion of the virtual machines in the first set of virtual machines. Based on the obtained performance measurements and the obtained migration costs, an optimal migration policy is determined for moving the virtual machine hosting the at least one application to another physical machine.