BGP Backpressure Notifications for Router Overload Prevention

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing techniques for managing Border Gateway Protocol (BGP) updates are inadequate, leading to situations where BGP sessions can overwhelm routers, causing network outages due to the inability to handle high rates of updates within the physical capabilities of the routers.

Innovation Solution

The implementation of backpressure notifications to BGP peers, which involves detecting triggers such as high incoming rates of prefixes or memory/processor usage thresholds, and sending notification messages to peers to either pause or reduce BGP updates, thereby preventing router overload.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If BGP sessions accept high rates of updates from multiple neighbors, then routing information completeness is improved, but router overload and network outages occur

Engineering Contradiction:
Improverouting information completenessVSAvoidrouter stability
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the router monitors its own resource utilization (CPU, memory, RIB fill rate) and sends backpressure notification messages to BGP peers when thresholds are exceeded. This feedback loop enables dynamic adjustment of update rates based on actual router capacity, preventing overload while maintaining routing information completeness.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically adjusts the acceptance rate of BGP updates based on real-time router conditions. Instead of a static acceptance policy, the router transitions between different operational states (normal operation, backpressure applied, backpressure released) based on monitored criteria such as RIB fill rate and CPU utilization, enabling adaptive response to changing load conditions.

Inventive Principle:
Principle #15Dynamics

2Reliability

If filtering is applied to maintain RIB size, then router resource usage is controlled, but routing information completeness deteriorates

Engineering Contradiction:
Improverouter resource managementVSAvoidrouting information completeness
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent applies preliminary action by proactively sending backpressure notifications to BGP peers before the router becomes overloaded. By monitoring thresholds (RIB fill rate, CPU usage, memory usage) and acting in advance when these thresholds are approached, the system prevents resource exhaustion while accepting all valid routing updates, thereby maintaining routing information completeness.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If BGP sessions are terminated to prevent overload, then router stability is improved, but network connectivity and routing information exchange deteriorate

Engineering Contradiction:
Improverouter stabilityVSAvoidrouting information exchange
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The backpressure notification message acts as an intermediary mechanism between the router and BGP peers. Instead of directly terminating BGP sessions when overload occurs, the router sends structured notification messages (with error codes and subcodes) that request peers to temporarily reduce or pause updates. This intermediary approach maintains session continuity while managing load, preserving routing information exchange capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS20250119395A1Backpressure notifications to peers for BGP updates
Publication Date: 2025.04.10 CIENA CORP
  • US20250119395A1 patent drawing
  • US20250119395A1 patent drawing
  • US20250119395A1 patent drawing

AI summary

A router configured to implement Border Gateway Protocol (BGP) includes circuitry configured receive BGP update messages from the one or more BGP peers, monitor one or more operational criteria associated with handling of the received BGP update messages, detect a trigger event indicative of a risk that continued reception of BGP update messages at a current rate could exceed a capacity of the router, and, in response to detecting the trigger event, transmit a BGP notification message to at least one of the BGP peers, the BGP notification message instructing the BGP peer to lock its BGP session with the router so that no prefixes are sent, thereby providing an automatic session lockout mechanism that prevents network fallout without terminating the BGP neighborship or causing route withdrawals.