Distributed Virtual Machine Management for Networked Virtualization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional networked virtualization environments rely on a central management virtual machine, which acts as a single point of failure and bottleneck, leading to unavailability and potential data loss during failures, and cannot handle increased workloads as the number of user virtual machines grows.

Innovation Solution

Implementing a distributed virtual machine management system where each management virtual machine instance services a subset of virtualization components and has access to a corresponding shard of a distributed database, allowing for load balancing and failover capabilities, ensuring continuous virtual machine management functionality even if individual instances or shards become unavailable.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a central management virtual machine is used to manage all virtual machines in the cluster, then centralized control and simplified management architecture are achieved, but the system becomes vulnerable to single point of failure and cannot handle increased workloads as the cluster grows

Engineering Contradiction:

Improvemanagement architecture complexityVSAvoidsystem availability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent divides the centralized management virtual machine into multiple distributed management virtual machine instances, each managing a subset of virtual machines. This segmentation eliminates the single point of failure by distributing management responsibilities across multiple instances, while each instance maintains access to the shared database for coordinated operation.

Inventive Principle:

Principle #1Segmentation

2Ease of operation

If a central management virtual machine handles all virtual machine management operations, then unified control is achieved, but the central machine becomes a bottleneck as the number of user virtual machines increases

Engineering Contradiction:

Improvecentralized control capabilityVSAvoidmanagement processing capacity

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The management workload is segmented across multiple management virtual machine instances, each capable of handling operations for a subset of user virtual machines. This allows the system to scale horizontally by adding more management instances, thereby increasing overall processing capacity while maintaining operational simplicity through standardized interfaces.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Each management virtual machine instance is designed with universal capabilities to perform all necessary management operations (creation, deletion, migration, etc.) for its assigned subset of virtual machines. This multi-functionality at the instance level eliminates bottlenecks while preserving the ease of operation through consistent, standardized management interfaces across all instances.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Stability of the object's composition

If all virtual machine management data is accessible only through the central management virtual machine, then data consistency is maintained, but access latency increases and the central machine becomes a performance bottleneck

Engineering Contradiction:

Improvedata consistencyVSAvoiddata access latency

Core Design Contradiction:

Stability of the object's compositionVSLoss of time

Solution Approach 1:

The patent segments the centralized database access model into a distributed architecture where each management virtual machine instance has direct access to the shared database. This segmentation allows parallel data operations without requiring all accesses to route through a single central machine, thereby reducing access latency while maintaining data consistency through coordinated database transactions.

Inventive Principle:

Principle #1Segmentation

4Device complexity

If a single central management virtual machine is used, then simplified failure handling is achieved, but the system experiences complete management unavailability and potential data loss when the central machine fails

Engineering Contradiction:

Improvefailure handling complexityVSAvoidmanagement continuity

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent implements beforehand cushioning by creating multiple management virtual machine instances that are prepared in advance to take over management responsibilities. When a failure occurs, the remaining healthy instances can immediately continue managing their assigned virtual machines without complete system unavailability, preventing data loss and maintaining operational continuity.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Solution Approach 2:

The system enables discarding of failed management instances and recovering of management capabilities through the remaining healthy instances. When a management virtual machine instance fails, its management responsibilities are automatically reassigned to other instances, allowing the system to discard the failed component and recover full management functionality without manual intervention or complete system downtime.

Inventive Principle:

Principle #34Discarding and recovering

Data Source

PatentEP3117322B1Method and system for providing distributed management in a networked virtualization environment

Publication Date: 2019.10.02 NUTANIX INC

Figure 1
Figure 2A
Figure 2B

AI summary

A method for handling failure in a networked virtualization environment having distributed virtual machine management.