Hybrid Cloud VM Migration for I/O Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In hybrid cloud topologies, network input/output communications between private and public clouds during cloud bursting or capacity scale out are inefficient due to slower and less reliable external links, which diminishes runtime performance of application workloads.
Innovation Solution
A method that measures network I/O operations between virtual machines, generates scores based on I/O operations per second, and migrates high-scoring virtual machines or groups to the public cloud to minimize cross-cloud communication, optimizing runtime performance by prioritizing those with high I/O rates and interdependencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If cloud bursting is used to scale out application workload to public cloud resources, then resource capacity is improved, but network input/output communication performance deteriorates
Solution Approach 1:
The system performs preliminary analysis of network I/O patterns between virtual machines before cloud bursting occurs. By measuring and scoring potential I/O operations in advance, the system identifies which virtual machines should be migrated together to minimize cross-cloud communication, thereby preventing performance degradation before it happens.
Solution Approach 2:
The patent introduces an intermediary scoring mechanism that evaluates virtual machines based on their network I/O patterns. This scoring system acts as a mediator to determine optimal migration groups, balancing the need for additional public cloud resources with the requirement to maintain good network performance by keeping frequently communicating virtual machines together.
2Adaptability or versatility
If virtual machines are migrated to public cloud during cloud bursting, then resource scalability is improved, but runtime performance deteriorates due to slower external links
Solution Approach 1:
The system performs preliminary analysis of network I/O patterns between virtual machines before cloud bursting occurs. By measuring and scoring potential I/O operations in advance, the system identifies which virtual machines should be migrated together to minimize cross-cloud communication, thereby preventing performance degradation before it happens.
Solution Approach 2:
The patent applies local quality by treating different virtual machines differently based on their specific network I/O patterns. Instead of applying a uniform migration strategy, the system scores each virtual machine individually and creates customized migration groups, ensuring that virtual machines with high mutual I/O communication are kept together while others can be migrated independently to public cloud.
3Adaptability or versatility
If cross-cloud communication is used between private and public clouds, then workload flexibility is improved, but communication reliability deteriorates due to slower external links
Solution Approach 1:
The patent introduces an intermediary scoring mechanism that evaluates virtual machines based on their network I/O patterns. This scoring system acts as a mediator to determine optimal migration groups, balancing the need for additional public cloud resources with the requirement to maintain good network performance by keeping frequently communicating virtual machines together.
Solution Approach 2:
The system performs preliminary analysis of network I/O patterns between virtual machines before cloud bursting occurs. By measuring and scoring potential I/O operations in advance, the system identifies which virtual machines should be migrated together to minimize cross-cloud communication, thereby preventing performance degradation before it happens.
Data Source
AI summary
A method, system and computer program product for optimizing runtime performance of an application workload. Network input/output (I/O) operations between virtual machines of a pattern of virtual machines servicing the application workload in a private cloud are measured over a period of time and depicted in a histogram. A score is generated for each virtual machine or group of virtual machines in the pattern of virtual machines based on which range in the ranges of I/O operations per seconds (IOPS) depicted in the histogram has the largest sample size and the number of virtual machines in the same pattern that are allowed to be in the public cloud. In this manner, the runtime performance of the application workload is improved by minimizing the network input/output communications between the two cloud environments by migrating those virtual machine(s) or group(s) of virtual machines with a score that exceeds a threshold value.


