Rack-Level Control Component for Data Center Fault Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In data centers, as the number of racks of host computing devices increases, service providers face difficulties in distinguishing between errors or faults associated with individual devices, shared resources, and distributed components used to manage these devices.

Innovation Solution

A host computing device control component is introduced, which includes a state monitoring component that independently monitors the operating state of each rack and generates visual indicators to signify the operational state, ensuring continuous monitoring and fault detection even in case of power loss to the main control component.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If the number of racks of host computing devices increases, then the computing resources and capacity of the data center increase, but the difficulty of distinguishing between errors or faults associated with individual devices, shared resources, and distributed components increases

Engineering Contradiction:
Improvenumber of racks of host computing devicesVSAvoiddifficulty of distinguishing faults
Core Design Contradiction:
Quantity of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The patent divides the monitoring function into separate distributed monitoring components, each responsible for a specific rack or group of devices. This segmentation allows faults to be localized to specific segments rather than requiring analysis of the entire system, making it easier to distinguish between individual device faults, shared resource faults, and component faults as the system scales.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary monitoring components that act as intermediaries between the host computing devices and the central management system. These intermediaries aggregate and process fault information locally before reporting to central management, reducing the complexity of fault detection and enabling easier distinction between different fault sources.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If centralized monitoring is used to monitor all host computing devices, then comprehensive fault detection is achieved, but the complexity of the monitoring system increases

Engineering Contradiction:
Improvefault detection capabilityVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The monitoring system is segmented into distributed monitoring components deployed at each rack or device level, rather than a single centralized monitoring system. Each monitoring component independently monitors its local devices and reports to central management, achieving comprehensive fault detection while reducing overall system complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-dimensional centralized monitoring architecture to a multi-dimensional distributed architecture where monitoring occurs at multiple levels (device level, rack level, and data center level). This dimensional change allows comprehensive monitoring while distributing complexity across multiple independent components rather than concentrating it in a single system.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP2751690B1Host computing devices control component status display
Publication Date: 2021.10.06 AMAZON TECH INC
  • EP2751690B1 patent drawingFigure 1
  • EP2751690B1 patent drawingFigure 2
  • EP2751690B1 patent drawingFigure 3

AI summary

Systems and methods are disclosed which facilitate the management of host computing devices through the utilization of a host computing device control component The host competing device control component includes a state monitoring component that monitors operating states of the control component. Based on monitoring the operating of the control component, the state monitoring component causes the generation of one or more visual indicator indicative of the operating state of the control component.