Data Plane Packet Loop for Forwarding Path Failure Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current fault detection methods in data networks, such as BFD protocols, are slow and resource-intensive, relying on the control plane for processing, which limits speed and scalability, and are limited to single-hop operations.

Innovation Solution

Implementing packet loops that run in the data plane, using probe packets forwarded between endpoint devices, allowing for rapid detection of path failures without continuous control plane processing, and enabling multi-hop operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If heartbeat packets are sent between systems for fault detection, then fault detection capability is provided, but detection speed is limited by predetermined time windows and control plane processing

Engineering Contradiction:

Improvefault detection speedVSAvoidcontrol plane processing overhead

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The patent extracts the fault detection function from the control plane and implements it in the data plane using packet loops. Probe packets are forwarded through the data plane forwarding paths, allowing fault detection to occur independently of control plane processing, thereby eliminating the speed limitations imposed by control plane time windows and processing overhead.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces probe packets as intermediaries to detect path failures. These probe packets circulate through the network path in loops, and their return or absence provides fault detection information without requiring direct control plane communication between adjacent systems, thus bypassing control plane bottlenecks.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If conventional routing protocols are used for path failure detection, then alternate paths can be selected, but convergence time is delayed due to slow fault detection

Engineering Contradiction:

Improvepath failure recoveryVSAvoidconvergence time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent implements preliminary fault detection by continuously circulating probe packets through the data plane before actual failures occur. This allows the network to detect path failures immediately when they happen, providing advance warning to routing protocols so they can quickly converge on alternate paths without waiting for traditional heartbeat timeout periods.

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If control plane processing is used for fault detection, then fault information can be gathered, but processing bottlenecks limit scalability and speed

Engineering Contradiction:

Improvefault information accuracyVSAvoidfault detection throughput

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

The patent segments the fault detection function from the control plane and distributes it across multiple data plane components. Each network device independently processes probe packets through its data plane forwarding paths, allowing parallel fault detection across multiple paths simultaneously without overwhelming a central control plane, thus improving both throughput and scalability.

Inventive Principle:

Principle #1Segmentation

4Reliability

If single-hop fault detection is implemented, then adjacent system failures can be detected, but multi-hop path failures remain undetected

Engineering Contradiction:

Improveadjacent system fault detectionVSAvoidmulti-hop detection capability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements continuous packet loops that circulate probe packets through multiple hops in the network. The probe packets traverse entire multi-hop paths and return to their origin, allowing continuous monitoring of end-to-end path health. This continuous circulation enables detection of failures anywhere along the multi-hop path, not just at adjacent system boundaries.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS11153199B2Forwarding path failure detection using packet loop

Publication Date: 2021.10.19 ARISTA NETWORKS INC

AI summary

A packet loop runs between two participating endpoint network devices, and in particular runs in the respective data planes of the endpoint devices. A probe packet is provided to the data plane of an initiating device and is forwarded to the other device to initiate the packet loop. The source and destination addresses in the probe packet are set equal to a common address. Based on the common address, entries in the respective forwarding tables of the endpoint devices are established to point to each other so that the probe packet is forwarded back and forth between the two devices thus sustaining the packet loop. A broken loop indicates a forwarding path failure at which time corrective action to be taken.