Dynamic Routing on Shared IP Address via Virtual Router

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In clustered networks, maintaining dynamic routing adjacencies over a shared IP address is challenging, particularly when dealing with spotted Subnet IP addresses, as it requires specific routing protocols and configurations across multiple nodes, leading to complexity in cluster-to-cluster failover scenarios.

Innovation Solution

A system where one node within the cluster is designated as the Routing Leader (RL) to advertise VIP routes and maintain routing adjacencies, allowing the cluster to advertise a single VIP route with a shared SNIP as a nexthop, and automatically switch to a new RL if the current one goes down, simplifying routing configurations and protocols like BGP.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If dynamic routing adjacencies are maintained over spotted SNIPs in a cluster, then routing protocols can be implemented, but the configuration becomes complex and requires routing protocol peering on multiple nodes

Engineering Contradiction:
Improverouting adjacency maintenanceVSAvoidrouting configuration complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

A virtual router is introduced as an intermediary entity that consolidates routing protocol processing. The virtual router receives routing protocol packets directed to any node in the cluster, performs routing adjacency maintenance centrally, and distributes routing information to all nodes. This eliminates the need for each node to independently maintain routing adjacencies, thereby reducing configuration complexity while preserving routing functionality.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If multiple VIP routes are advertised equal-cost multi-path (ECMP) for cluster-to-cluster failover, then failover capability is provided, but the routing advertisement complexity increases

Engineering Contradiction:
Improvecluster-to-cluster failover capabilityVSAvoidrouting advertisement complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Multiple VIP routes that would otherwise be advertised separately by different nodes are merged into a single routing advertisement processed by the virtual router. The virtual router aggregates the routing information and advertises it as a unified ECMP route set, maintaining failover capability while simplifying the advertisement process to a single coordinated action rather than multiple independent advertisements.

Inventive Principle:
Principle #5Merging (Combining)

3Adaptability or versatility

If routing protocol peering is established on multiple nodes in the cluster, then dynamic routing is supported, but the number of routing protocol connections increases

Engineering Contradiction:
Improvedynamic routing supportVSAvoidnumber of routing protocol connections
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The routing protocol processing function is extracted from individual cluster nodes and consolidated into the virtual router. Instead of each node establishing routing protocol connections independently, the virtual router centralizes this function and manages all routing protocol connections. This reduces the total number of routing protocol connections while maintaining dynamic routing support across the cluster.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11121968B2Systems and methods for dynamic routing on a shared IP address
Publication Date: 2021.09.14 CITRIX SYSTEMS INC
  • US11121968B2 patent drawing
  • US11121968B2 patent drawing
  • US11121968B2 patent drawing

AI summary

The present disclosure is directed towards systems and methods for dynamic routing on an IP address shared by a cluster of nodes. In an implementation, a first node of a cluster of nodes can receive a unicast routing protocol packet from a peer router. The unicast routing protocol packet can be addressed to a shared IP address established across the cluster of nodes. The cluster of nodes can be intermediary to a plurality of clients and a plurality of servers. The first node can identify a second node identified as a routing leader. The first node can steer the packet to the second node in response to determining that the routing protocol packet is a unicast routing protocol packet. The second node can be configured to advertise virtual IP address routes to the network over the routing adjacency and maintain routing adjacencies.