Virtual Machine Live Migration Memory Page Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Live migration in cloud computing environments generates significant network traffic due to the transfer of memory states across physical hosts, which can lead to increased bandwidth usage and longer migration times, especially when dealing with virtual machines using managed memory.
Innovation Solution
The method involves providing notifications to virtual machines and their applications during the migration process to reduce the number of memory pages in use, utilizing techniques such as garbage collection and heap size reduction, to minimize the overhead of memory copying and network traffic. This includes invoking the Garbage Collector to identify unused memory pages, suspending applications to prevent modifications during transfer, and reducing the heap size temporarily to decrease the amount of data that needs to be copied.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If live migration transfers all memory pages including unused pages, then migration completeness is ensured, but network traffic increases significantly
Solution Approach 1:
The patent extracts and identifies unused memory pages through garbage collection before migration, separating them from the set of pages that need to be transferred. Only the necessary used pages are included in the migration transfer, eliminating waste of network bandwidth on redundant data while preserving migration completeness.
Solution Approach 2:
The patent performs preliminary garbage collection and memory optimization actions before the migration process begins. By pre-identifying and clearing unused memory pages ahead of time, the system reduces the volume of data to be migrated without compromising the integrity or completeness of the migration process.
2Productivity
If applications continue to run during migration, then service continuity is maintained, but memory modification increases transfer overhead
Solution Approach 1:
The patent implements periodic or phased suspension of applications during migration - briefly pausing them at strategic points to freeze memory state and reduce modifications, then resuming them. This periodic control balances service continuity with reduced transfer overhead by limiting the window of memory changes during critical transfer phases.
Solution Approach 2:
The patent monitors memory modification patterns during migration and uses this feedback to dynamically adjust the migration process. When memory changes are detected, the system can trigger additional synchronization points or adjust transfer priorities, creating a closed-loop control that adapts to actual application behavior and minimizes unnecessary transfers.
3Quantity of substance
If heap size is reduced during migration, then transfer volume decreases, but application performance may be impacted
Solution Approach 1:
The patent performs heap size reduction and memory optimization as a preliminary action before migration begins. By pre-compacting the heap and eliminating unused memory allocations ahead of time, the system reduces the transfer volume without impacting application performance during the actual migration, since the optimization is completed in advance when the application is still running normally.
Solution Approach 2:
The patent temporarily changes memory management parameters such as heap size and garbage collection thresholds during the migration window. These parameter adjustments are made strategically to reduce transfer volume, and are reverted or adjusted after migration completes, allowing the system to optimize for transfer efficiency during migration while restoring normal performance characteristics afterward.
Data Source
AI summary
A computer-implemented method is provided for reducing network traffic associated with live migration. The method comprises selecting a virtual machine on a first physical host for migration to a second physical host, and providing each application running in the selected virtual machine with notification that the migration has started. In response to receiving the notification that the migration has started, each application reducing the number of memory pages in use during the migration. The selected virtual machine and each application is then migrated from the first physical host to the second physical host, wherein the migration of each application includes migration of the reduced number of memory pages. Non-limiting examples of methods that may be used to reduce the number of memory pages includes identifying memory that contains garbage, reducing the size of the heap, increasing the pause time used for garbage collection, deferring just-in-time compilation of hot methods, and releasing caches and buffers.