Fabric Controller Goal State Communication Protocol

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current cloud computing tools lack effective communication mechanisms between fabric controllers and compute instances in computer clusters, limiting the ability to manage and monitor the goal states of compute instances independently and efficiently.

Innovation Solution

Implementing a structured protocol for communicating goal state indicators from fabric controllers to compute instances, allowing instances to transition towards defined goal states while reporting their current status, with support for multiple protocol versions to accommodate different instance capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a structured protocol is implemented for communicating goal state indicators, then communication reliability between fabric controller and compute instances is improved, but device complexity increases due to protocol version management

Engineering Contradiction:
Improvecommunication reliabilityVSAvoidprotocol version management
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically adapts to different protocol versions by implementing version detection and negotiation mechanisms. The fabric controller and compute instances can operate with different protocol versions simultaneously, with the system automatically adjusting communication patterns based on the capabilities of each component. This dynamic approach allows reliable communication across heterogeneous versions without requiring all components to upgrade simultaneously.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The communication protocol is segmented into multiple versions, each with clearly defined capabilities and requirements. By dividing the protocol space into discrete, manageable versions, the system can selectively implement and test specific versions independently. This segmentation reduces the complexity of managing the entire protocol suite by allowing focused development and validation of individual version iterations.

Inventive Principle:
Principle #1Segmentation

2Productivity

If compute instances are given independence to achieve goal states autonomously, then productivity of compute instances is improved, but control precision over instance states deteriorates

Engineering Contradiction:
Improveinstance autonomyVSAvoidstate control precision
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The system implements continuous feedback loops where compute instances report their current state to the fabric controller, which compares the reported state against the desired goal state. Based on this feedback, the fabric controller can issue corrective instructions to guide instances back toward their goal states if deviations occur. This feedback mechanism maintains control precision while allowing instances operational independence to achieve goals autonomously.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The fabric controller performs preliminary actions by pre-defining goal states and transition paths for compute instances before autonomous execution begins. By establishing the desired end state and acceptable transition criteria in advance, the system provides a framework for autonomous operation that ensures instances remain aligned with overall system objectives. This preliminary configuration enables productivity through autonomy while maintaining precision through pre-established constraints.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2630576B1Goal state communication in computer clusters
Publication Date: 2018.10.24 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2630576B1 patent drawingFigure 1
  • EP2630576B1 patent drawingFigure 2
  • EP2630576B1 patent drawingFigure 3

AI summary

Goal state indicators can be communicated from a fabric controller of a computer cluster to each of multiple compute instances in the computer cluster managed by the fabric controller. The goal state indicators can be formatted according to a structured protocol that defines multiple possible goal states. Additionally, status reports can be received from the compute instances. Each of the status reports can indicate a current state of one of the compute instances relative to a goal state previously indicated in a goal state indicator communicated to that one of the compute instances.