VM Migration Duration Calculation Using Memory and Bandwidth
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for hot virtual machine migration lack accuracy in assessing migration duration time due to variations in specifications and services, leading to inaccurate decision-making.
Innovation Solution
A method and system that dynamically calculate migration duration time based on parameters such as allocated memory size, memory change rate, and migration network bandwidth, allowing for real-time determination of whether a virtual machine can be migrated between source and destination computing nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple virtual machines are migrated concurrently based on average historical migration duration, then resource integration and power supply speed are improved, but migration duration time assessment accuracy deteriorates due to large deviations caused by specification and service differences
Solution Approach 1:
The patent changes the assessment parameters from using a single average historical migration duration to using multiple parameters including CPU configuration, memory configuration, storage configuration, and network configuration. This allows the system to account for specification differences between virtual machines and provides a more accurate prediction of migration duration for each specific VM type.
Solution Approach 2:
The patent segments the migration duration assessment into multiple independent components: CPU migration time, memory migration time, storage migration time, and network migration time. Each component is calculated separately based on its specific configuration parameters, and then aggregated to provide the total migration duration. This segmentation eliminates the large deviations caused by using a single average value.
2Ease of operation
If virtual machine migration is performed without accurate migration duration assessment, then migration decision-making is simplified, but migration scheduling efficiency deteriorates due to inaccurate available time calculations
Solution Approach 1:
The patent performs preliminary calculation of migration duration for each virtual machine type before the actual migration decision is made. By pre-calculating the expected migration time based on VM specifications and the current load states of source and destination hosts, the system establishes an accurate baseline for scheduling decisions, thereby improving overall migration scheduling efficiency.
Solution Approach 2:
The patent implements a feedback mechanism where the calculated migration duration is continuously compared with the available time on source and destination hosts. This feedback loop allows the system to dynamically adjust migration decisions based on real-time host conditions, ensuring that migrations are scheduled when both source and destination have sufficient available time, thus optimizing scheduling efficiency.
3Ease of operation
If virtual machine migration is performed without considering real-time available migration duration of source and destination nodes, then migration execution is simplified, but service continuity deteriorates due to potential migration failures affecting user services
Solution Approach 1:
The patent introduces dynamic assessment of available migration duration for both source and destination hosts based on their real-time load conditions. Instead of using static thresholds, the system continuously monitors CPU utilization, memory usage, storage I/O, and network bandwidth of both source and destination hosts, dynamically adjusting the available time window for migration. This ensures that migrations are only executed when both hosts have sufficient capacity, maintaining service continuity while keeping the execution process straightforward.
Data Source
AI summary
Embodiments of the present invention disclose a virtual machine migration management method, where the method includes: calculating, according to migration parameters of a to-be-migrated virtual machine, migration duration time required for migrating the to-be-migrated virtual machine from a source computing node to a destination computing node, where the migration parameters include an allocated memory size, a memory change rate, and migration network bandwidth that are of the to-be-migrated virtual machine; separately acquiring current available migration duration time of the source computing node and current available migration duration time of the destination computing node; and, if neither the current available migration duration time of the source computing node nor the current available migration duration time of the destination computing node is less than the migration duration time, determining to migrate the to-be-migrated virtual machine from the source computing node to the destination computing node.