Hardware Telemetry Provenance for Fault-Tolerant Distributed Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current network monitoring techniques lack independent methods for managing device metadata, ensuring data integrity, and accessing telemetry data securely, especially in shared hardware environments where trust issues arise due to dependence on software running on the node.

Innovation Solution

A dedicated hardware component with a direct connection to the network interface, powered independently, is used to securely gather, store, and distribute node telemetry, employing a provenance database that can operate even when the node fails, ensuring data integrity and independence from node software.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If software-based monitoring techniques are used, then ease of operation is improved, but reliability deteriorates due to dependence on node software and trust issues in shared hardware environments

Engineering Contradiction:
Improveease of operationVSAvoidreliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The monitoring function is segmented into two independent parts: a hardware component that collects and stores telemetry data independently, and a software component that retrieves and processes the data. This segmentation isolates the critical data collection function from the unreliable node software, ensuring that monitoring reliability is maintained even when node software fails or is compromised.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A hardware component acts as an intermediary between the monitored node and the monitoring system. This intermediary collects telemetry data directly from the node, stores it in a provenance database, and makes it available to monitoring systems without requiring trust in the node's software. The hardware component mediates the data flow, ensuring integrity and availability independent of node software state.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If dedicated hardware components are deployed for independent telemetry collection, then reliability is improved, but device complexity increases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The hardware component is designed to perform multiple functions: collecting telemetry data from the node, storing it in a provenance database, managing cryptographic keys for data integrity, and providing secure access to monitoring systems. By consolidating these functions into a single multi-functional component, the system achieves high reliability without proportionally increasing overall device complexity.

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

Solution Approach 2:

The patent combines data collection, data storage, cryptographic key management, and access control functions into a single integrated hardware component. This merging eliminates the need for multiple separate components, reducing the overall system complexity while maintaining the reliability benefits of dedicated hardware for telemetry collection.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS20220222359A1Fault tolerant telemetry of distributed devices
Publication Date: 2022.07.14 INTEL CORP
  • US20220222359A1 patent drawing
  • US20220222359A1 patent drawing
  • US20220222359A1 patent drawing

AI summary

System and techniques for fault tolerant telemetry of distributed devices are described herein. A node includes a hardware component that receives telemetry from an entity resident on the node. The hardware component signs the telemetry with a cryptographic key to create signed telemetry and stores the signed telemetry in memory of the hardware component. Then, upon request from a remote entity, the hardware component provides the signed telemetry.