Port State Table Maintenance in Network Forwarding Planes

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional network elements take too long to recover from port failures, leading to prolonged downtime and increased packet loss due to inefficient detection and distribution of port states, which relies heavily on management and control plane software.

Innovation Solution

Maintaining port state tables in the forwarding plane of network elements, allowing for fast and efficient detection and distribution of port states within a cluster of nodes, enabling seamless failover without dynamic assistance from management or control plane software, using periodic determination and updating of port states and transmission of these states to other Forwarding Data Units (FDUs).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional mechanisms are used to detect and respond to port failures, then the system can handle failures, but the recovery time is too long causing prolonged downtime and packet loss

Engineering Contradiction:
Improvefailure recovery capabilityVSAvoiddowntime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent pre-computes and stores alternate forwarding paths in port state tables before failures occur. When a port failure is detected, the forwarding plane can immediately switch to pre-calculated alternate paths without waiting for control plane computation, achieving sub-10-millisecond failover time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent divides the forwarding plane into multiple independent FDU units, each maintaining its own port state table. This segmentation allows parallel failure detection and independent failover decisions at each FDU, eliminating the single-point bottleneck of centralized control plane processing and reducing overall recovery time.

Inventive Principle:
Principle #1Segmentation

2Reliability

If management and control plane software are used to handle port failures, then failures can be detected and responded to, but the response time is delayed due to software processing overhead

Engineering Contradiction:
Improvefailure detection capabilityVSAvoiddetection speed
Core Design Contradiction:
ReliabilityVSSpeed

Solution Approach 1:

The patent replaces software-based failure detection in the control plane with hardware-based detection in the forwarding plane. FDU units continuously monitor port states using hardware circuits, enabling detection and response in microseconds rather than the milliseconds required by software polling, thus dramatically increasing detection speed.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The forwarding plane FDUs autonomously monitor their own port states and make independent failover decisions without requiring control plane software intervention. Each FDU maintains local port state tables and can immediately detect and respond to failures, eliminating the delay inherent in centralized software-based monitoring and control.

Inventive Principle:
Principle #25Self-service

3Reliability

If traffic is concentrated on a single alternate port during failover, then connectivity is restored, but the alternate port becomes overloaded

Engineering Contradiction:
Improveconnectivity restorationVSAvoidport load
Core Design Contradiction:
ReliabilityVSStress or pressure

Solution Approach 1:

The patent implements dynamic load distribution across multiple alternate ports based on real-time port state table information. When a primary port fails, traffic is automatically redistributed across several available alternate ports proportionally, preventing any single alternate port from becoming overloaded and maintaining balanced network traffic flow during failover.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the forwarding parameters in port state tables to reflect alternate path selections. When failures occur, the system dynamically adjusts traffic distribution parameters to spread load across multiple alternate ports rather than concentrating all traffic on a single designated backup port, thereby preventing port overload while restoring connectivity.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS8619605B2Method and apparatus for maintaining port state tables in a forwarding plane of a network element
Publication Date: 2013.12.31 AVAYA INC
  • US8619605B2 patent drawing
  • US8619605B2 patent drawing
  • US8619605B2 patent drawing

AI summary

A method, apparatus and computer program product for maintaining port state tables in a forwarding plane of a network element are presented. The state of a first set of ports associated with a first Forwarding Data Unit (FDU) are periodically determined, the first FDU being one of a plurality of FDUs. The determined state is used to update a first port state table of the port state database associated with the first FDU. The determined state is transmitted to each other FDUs on the network element to enable each of the other FDUs to store the state of the first set of ports in a port state database local to each of the other FDUs. The port state database is used by the forwarding plane to perform fast reroute of packets.