Low-Impact Live-Migration System for Cloud Containers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cloud computing systems face challenges in minimizing the unfavorable impacts of live-migrating virtual machines and computing containers between server nodes, leading to service interruptions, blackouts, and brownouts that negatively affect customer experiences.
Innovation Solution
A low-impact live-migration system that evaluates characteristics of virtual services to predict and minimize the impact of migration by selectively identifying virtual machines and scheduling migrations based on usage patterns, sensitivity, and other factors, using a prediction engine to determine impact scores and optimize the migration process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If virtual machines are live-migrated between server nodes to balance storage capacity and enable OS updates, then storage space and processing capabilities are enhanced, but service interruptions, blackouts, and brownouts occur that negatively affect customer experience
Solution Approach 1:
The system performs preliminary evaluation of virtual machine characteristics and migration impact before executing live migration. By assessing factors such as VM sensitivity to migration, current workload, and predicted impact on services, the system prepares and schedules migrations during periods of minimal customer impact, thus enhancing storage capabilities while maintaining service reliability
Solution Approach 2:
The system continuously monitors service performance and migration impact, using this feedback to dynamically adjust migration scheduling decisions. By evaluating actual service disruption patterns and customer impact metrics, the system optimizes future migration timing and selection to minimize interruptions while achieving storage balancing goals
2Reliability
If virtual machines are selectively migrated based on evaluated characteristics and impact prediction, then service interruption is minimized, but system complexity increases due to evaluation and scheduling mechanisms
Solution Approach 1:
The system implements self-service mechanisms where virtual machines are automatically evaluated, ranked by migration impact, and scheduled for migration without manual intervention. The automated evaluation framework assesses VM characteristics and predicts service impact, enabling the system to manage its own migration processes intelligently while maintaining service continuity, thus reducing the operational complexity burden
3Reliability
If migration scheduling is based on usage patterns and sensitivity evaluation, then customer experience is improved, but migration time and processing overhead increase
Solution Approach 1:
The system performs preliminary evaluation of virtual machine migration impact and schedules migrations in advance during periods of minimal customer activity. By pre-assessing VM characteristics, usage patterns, and predicted service impact, the system identifies optimal migration windows beforehand, improving customer experience while managing the time investment through proactive planning
Solution Approach 2:
The system dynamically adjusts migration parameters such as timing, source-destination pairing, and VM selection based on evaluated usage patterns and sensitivity metrics. By changing these parameters optimally, the system minimizes customer experience impact while efficiently managing the time and resources required for migration evaluation and execution
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to systems, methods, and computer readable media that utilize a low-impact live-migration system to reduce unfavorable impacts caused as a result of live-migrating computing containers between physical server devices of a cloud computing system. For example, systems disclosed herein evaluates characteristics of computing containers on server devices to determine a predicted unfavorable impact of live-migrating the computing containers between the server devices. Based on the predicted impact, the systems disclosed herein can selectively identify which computing containers to live-migrate as well as carry out live-migration of the select computing containers in such a way the significantly reduces unfavorable impacts to a customer or client device associated with the computing containers.