Dynamic Throttling for Virtual Machine Live Migration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current live migration techniques for virtual machines often result in excessively long convergence periods or performance degradation due to frequent memory changes and slow network data transfer rates, leading to unacceptable downtime and performance throttling.
Innovation Solution
Implementing a live migration tool that sets adjustable throttling and downtime limits, allowing users to define performance expectations, and dynamically modifying the throttling rate based on the amount of modified memory to ensure efficient data transfer and minimize downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If incremental data copying is performed during live migration, then the virtual machine can remain operational, but the convergence period becomes excessively long
Solution Approach 1:
The patent implements dynamic throttling that adjusts the virtual machine's data modification rate in real-time during live migration. The throttling amount changes based on the difference between data modification rate and data transfer rate, allowing the system to adaptively balance operational continuity with convergence speed.
Solution Approach 2:
The system continuously monitors the data modification rate and data transfer rate, calculating a throttling amount based on their difference. This feedback mechanism adjusts the virtual machine's operation dynamically, reducing the convergence period while maintaining operational continuity.
2Loss of time
If data transfer rate is increased to reduce convergence period, then migration time decreases, but virtual machine performance degrades below user acceptability
Solution Approach 1:
Instead of using a fixed high transfer rate that degrades performance, the system dynamically adjusts the virtual machine's data modification rate through throttling. This allows the data transfer rate to be optimized without sacrificing virtual machine performance below user acceptability.
Solution Approach 2:
The patent changes the operational parameters of the virtual machine by applying dynamic throttling to the data modification rate. This parameter adjustment enables faster convergence while maintaining performance within user-acceptable limits.
3Productivity
If throttling is applied to reduce data modification rate, then convergence is achieved faster, but virtual machine performance is throttled excessively
Solution Approach 1:
The system applies dynamic rather than static throttling, adjusting the throttling amount in real-time based on the difference between data modification rate and data transfer rate. This ensures faster migration speed while preventing excessive performance throttling by adapting to current system conditions.
Solution Approach 2:
The feedback mechanism continuously calculates the optimal throttling amount based on real-time monitoring of data modification and transfer rates. This ensures that throttling is applied only to the extent necessary for convergence, minimizing impact on virtual machine performance.
4Ease of manufacture
If fixed throttling rate is used during live migration, then implementation is simple, but it cannot adapt to varying data modification rates
Solution Approach 1:
The patent replaces fixed throttling with dynamic throttling that automatically adapts to varying data modification rates. The system calculates throttling amount based on real-time differences between modification and transfer rates, providing adaptability without excessive implementation complexity.
Solution Approach 2:
The live migration system performs self-adjustment by automatically calculating and applying appropriate throttling based on its own monitoring of data modification rates. This eliminates the need for complex external control mechanisms while providing adaptive behavior.
Data Source
AI summary
A system and method include initiating a live migration of a virtual machine from a first host machine to a second host machine. The system and method include copying an initial copy of data stored in a memory of the first host machine to a memory of the second host machine, determining a set of modified data, determining that transferring the set of modified data exceeds a downtime limit, calculating an increased throttling amount based on a rate of data copying and a rate of data change using from the set of modified data, determining the increased throttling amount does not exceed a throttling limit, applying the increased throttling to the virtual machine executing on the first host machine, and copying the set of modified data while the increased throttling is applied to the virtual machine executing on the first host machine.