Virtual Rack Management Modules Consolidate Data Center Infrastructure

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing architecture for data centers, which includes a rack management module in every rack, is costly due to the need for additional space, power, and cabling, and becomes increasingly complex as the number of racks grows, necessitating a more efficient management solution.

Innovation Solution

Implementing virtual rack management modules, where a single rack management node running a hypervisor manages multiple racks via a network, eliminating the need for physical rack management modules in each rack by utilizing virtual rack management modules that can register and manage nodes across multiple racks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a rack management module is installed in every rack, then each rack can be managed independently, but the cost increases due to additional space, power, and cabling requirements

Engineering Contradiction:
Improverack management capabilityVSAvoidhardware resources
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

Multiple rack management modules are merged into a single physical server through virtualization. The server running the hypervisor hosts multiple virtual rack management modules that collectively manage multiple racks, eliminating the need for separate physical management modules in each rack and reducing hardware resource consumption.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

Virtual copies of rack management modules are created through the hypervisor. Each virtual rack management module is a software-based copy that can manage a specific rack, providing the same functionality as physical modules without requiring additional physical hardware in each rack.

Inventive Principle:
Principle #26Copying

2Ease of operation

If rack management modules are installed in every rack, then local management is enabled, but the system complexity increases as the data center grows

Engineering Contradiction:
Improvelocal rack managementVSAvoidsystem architecture
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

A single physical server is designed to perform multiple rack management functions simultaneously. The hypervisor enables the server to host multiple virtual rack management modules, each capable of managing different racks, making the system more versatile and easier to operate while reducing overall complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Reliability

If physical rack management modules are deployed in each rack, then dedicated management is achieved, but additional cabling and power infrastructure are required

Engineering Contradiction:
Improvededicated managementVSAvoidpower consumption
Core Design Contradiction:
ReliabilityVSUse of energy by stationary object

Solution Approach 1:

The power consumption and energy resources of multiple rack management modules are merged into a single physical server. This consolidated approach maintains dedicated management capabilities for each rack through virtualization while significantly reducing the total power consumption compared to having separate physical modules in each rack.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS10728084B2Virtualized rack management modules
Publication Date: 2020.07.28 QUANTA COMPUTER INC
  • US10728084B2 patent drawing
  • US10728084B2 patent drawing
  • US10728084B2 patent drawing

AI summary

Systems, methods, and computer-readable media for managing nodes through virtual rack management modules. A system can have a first rack that includes a first top-of-rack (ToR) switch and a first group of nodes. The first ToR switch can be connected to the first group of nodes. The system can also have a second rack that includes a second ToR switch and a second group of nodes. The second ToR switch can be connected to the second group of nodes, and the second ToR switch can be connected to the first ToR switch. Furthermore, the system can include a rack management node that executes a hypervisor. The hypervisor can run a first virtual rack management module (vRMM) and a second vRMM. The first vRMM and the second vRMM can manage the first group of nodes and the second group of nodes, respectively.