Dynamic Compute Resource Allocation for Cloud Recovery Clusters

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Public cloud environments face vulnerabilities due to shared resources, such as the Spectre vulnerability and privilege escalation, which can lead to data breaches and inefficient resource utilization, as well as noisy neighbor issues and potential data disclosure.

Innovation Solution

A system dynamically allocates compute resources to clusters, allowing for dedicated resource allocation to tenants and reducing the number of nodes needed by using compute-only nodes that can be quickly assigned and reassigned, and implementing a recovery cluster architecture with a cluster manager that adds compute resources during recovery events to facilitate failover.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If compute resources are shared between tenants in public cloud environments, then resource utilization efficiency is improved, but security vulnerabilities and data breach risks increase

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidsecurity vulnerabilities and data breach risks

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system segments compute resources into dedicated instances for each tenant, physically isolating CPU and memory resources. This segmentation maintains resource utilization efficiency while eliminating security vulnerabilities associated with shared resources, as each tenant has exclusive access to their allocated compute instance.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a resource allocation intermediary layer that manages the transition between shared and dedicated resource models. This intermediary enables dynamic provisioning of dedicated compute instances while maintaining the efficiency benefits of shared resource management during normal operations.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If dedicated compute instances are provided to tenants, then security vulnerabilities are reduced, but resource utilization efficiency and cost efficiency decrease

Engineering Contradiction:

Improvesecurity and data protectionVSAvoidresource utilization efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system dynamically adjusts resource allocation based on operational conditions. During normal operations, resources are shared efficiently; during recovery events, dedicated compute instances are dynamically provisioned to affected tenants. This dynamic approach maintains security while optimizing resource utilization efficiency across different operational states.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the allocation parameter from static dedicated assignment to dynamic conditional assignment. Compute resources transition between shared and dedicated states based on recovery event detection, allowing the system to maintain security when needed while maximizing efficiency during normal operations.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If compute resources are statically allocated to recovery clusters, then continuous availability during recovery events is ensured, but the number of nodes required and infrastructure complexity increase

Engineering Contradiction:

Improvecontinuous availability during recovery eventsVSAvoidinfrastructure complexity and number of nodes

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates multi-functional compute resources that can serve both primary workloads and recovery cluster needs. The same physical infrastructure is used for both operational and recovery purposes, eliminating the need for separate dedicated recovery nodes and reducing overall infrastructure complexity while ensuring continuous availability during recovery events.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs preliminary setup by establishing the capability to rapidly provision dedicated compute instances during recovery events, without requiring permanent dedicated infrastructure. This preliminary action enables quick response to recovery events while minimizing infrastructure complexity during normal operations.

Inventive Principle:

Principle #10Preliminary action

4Ease of operation

If multiple physical machines are used without virtualization, then resource allocation simplicity is maintained, but resource utilization efficiency and cost management deteriorate

Engineering Contradiction:

Improveresource allocation simplicityVSAvoidresource utilization efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The virtualization system implements self-service automated resource allocation that simplifies management while improving efficiency. The system automatically detects recovery events, provisions dedicated compute instances, and manages resource allocation without manual intervention, maintaining operational simplicity while maximizing resource utilization efficiency through virtualization.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12164398B2Dynamic allocation of compute resources at a recovery site

Publication Date: 2024.12.10 NUTANIX INC

AI summary

Examples of systems are described herein which may dynamically allocate compute resources to recovery clusters. Accordingly, a recovery site may utilize fewer compute resources in maintaining recovery clusters for multiple associate clusters, while ensuring that, during use, compute resources are allocated to a particular cluster. This may reduce and/or avoid vulnerabilities arising from a use of shared resources in a virtualized and/or cloud environment.