Hardware-Accelerated PBR for Subscriber Traffic Consistency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing load balancer systems for service gateways in packet-switched networks require sticky tables to maintain consistency between control plane and data plane traffic, leading to resource consumption and processing overhead, especially in high availability deployments, and lack hardware acceleration for data plane traffic processing.

Innovation Solution

Implementing a method that uses hardware-accelerated policy-based routing (PBR) to direct both control plane and data plane traffic to the same service gateway without the need for sticky tables, by segregating traffic based on subscriber IP addresses and utilizing a data plane ACL to determine the next hop network address, thereby reducing processing load and resource consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If sticky tables are used to maintain consistency between control plane and data plane traffic, then traffic consistency is improved, but resource consumption and processing overhead increase

Engineering Contradiction:

Improvetraffic consistencyVSAvoidprocessing overhead

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts the sticky table mechanism from the load balancing system and replaces it with hardware-accelerated policy-based routing. By removing the software-based sticky table approach, the system eliminates the associated resource consumption and processing overhead while maintaining traffic consistency through hardware-based ACL rules that operate at line rate without burdening the control plane.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent substitutes the mechanical/software-based sticky table system with a hardware-based policy-based routing engine. This replacement moves the load balancing function from software processing to hardware acceleration, eliminating the processing overhead and resource consumption associated with sticky tables while maintaining the same traffic consistency function.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If sticky tables are used for load balancing, then traffic distribution consistency is improved, but resource consumption increases especially in high availability deployments

Engineering Contradiction:

Improvetraffic distribution consistencyVSAvoidresource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent replaces the software-based sticky table mechanism with hardware-accelerated policy-based routing. This substitution moves the load balancing function from CPU-intensive software processing to hardware-based ACL rule matching, dramatically reducing resource consumption and energy usage while maintaining traffic distribution consistency across high availability deployments.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The hardware-accelerated PBR engine performs load balancing decisions autonomously at line rate without requiring control plane involvement or sticky table management. The system serves itself by using hardware-based classification and forwarding decisions, eliminating the need for software-based tracking and reducing overall resource consumption.

Inventive Principle:

Principle #25Self-service

3Productivity

If hardware acceleration is implemented for data plane traffic, then processing speed is improved, but system complexity increases

Engineering Contradiction:

Improveprocessing speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent leverages the existing hardware-accelerated policy-based routing engine, which was originally designed for other functions, to perform load balancing. By making the PBR engine multi-functional, the system achieves hardware-accelerated processing speed without adding dedicated new hardware complexity, as the same hardware infrastructure serves multiple purposes including load balancing and traffic classification.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentEP1985076B1Techniques for load balancing over a cluster of subscriber-aware application servers

Publication Date: 2018.05.02 CISCO TECHNOLOGY INC

Figure 1A
Figure 1B~2
Figure 3

AI summary

Techniques for distributing control plane traffic, from an end node to a cluster of service gateway nodes that host subscriber aware application servers, include receiving a control plane message for supporting data plane traffic from a particular subscriber. A particular service gateway node is determined among the cluster of service gateway nodes based on policy based routing (PBR) for the data plane traffic from the particular subscriber. A message based on the control plane message is sent to a control plane process on the particular service gateway node. Thereby, data plane traffic and control plane traffic from the same subscriber are directed to the same gateway node, or otherwise related gateway nodes, of the cluster of service gateway nodes. This approach allows currently available, hardware accelerated PBR to be used with clusters of subscriber aware service gateways that must also monitor control plane traffic from the same subscriber.