Virtualized Forwarding in Network Elements

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional network element architectures struggle with efficient virtualized forwarding, scalability, and distributed traffic management in multi-function Ethernet aggregation networks, particularly in handling link aggregation, protection switching, and flow identification, which leads to resource inefficiencies and scalability issues.

Innovation Solution

The method involves assigning virtual destination addresses and VLAN ingress/egress connection identifiers to frames, allowing for internal switching and policing, and supporting client-to-network, network-to-client, and network-to-network flows across multiple plug-in units, enabling efficient virtualized forwarding and distributed traffic management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional network element architectures are used with specific egress destination identification, then routing simplicity is maintained, but scalability and resource utilization deteriorate

Engineering Contradiction:
ImprovescalabilityVSAvoidarchitecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the forwarding architecture into multiple plug-in units (PIUs), each capable of independent packet processing. This segmentation allows the system to scale by adding more PIUs without requiring a complete architectural redesign, thereby improving scalability while maintaining manageable complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension to forwarding by implementing virtualized forwarding with virtual destination addresses that are independent of physical egress ports. This abstraction layer allows multiple virtual networks to coexist and be managed separately, enhancing scalability without proportionally increasing physical infrastructure complexity.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If distributed architecture with multiple PIUs is implemented, then resource utilization improves, but flow identification and path management complexity increases

Engineering Contradiction:
Improveresource utilizationVSAvoidflow management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

Each plug-in unit is designed with universal packet processing capabilities, including switching, traffic management, and flow identification functions. This multi-functionality allows any PIU to handle any traffic flow, improving resource utilization through flexible load distribution while simplifying flow management through standardized interfaces.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces connection identifiers (connection IDs) as intermediaries to manage flows across distributed PIUs. These connection IDs provide a standardized mechanism for identifying and tracking traffic flows throughout the network element, reducing the complexity of flow management in distributed architectures.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If link aggregation and protection switching are implemented, then network reliability improves, but internal link specification and traffic management complexity increases

Engineering Contradiction:
Improvenetwork availabilityVSAvoidtraffic management complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges link aggregation and protection switching functions into the virtualized forwarding framework. By combining multiple physical links into logical aggregates and implementing protection groups at the virtualization layer, the system achieves high reliability while managing complexity through unified abstraction rather than separate complex control mechanisms.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary configuration of protection groups and link aggregates during initialization, establishing fallback paths and redundancy relationships in advance. This preliminary action ensures rapid failover capability for high reliability while reducing runtime complexity by pre-computing traffic management decisions.

Inventive Principle:
Principle #10Preliminary action

4Adaptability or versatility

If virtualized forwarding with virtual destination addresses is implemented, then forwarding flexibility and scalability improve, but address translation overhead increases

Engineering Contradiction:
Improveforwarding flexibilityVSAvoidaddress translation time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent performs address translation in advance by pre-computing mapping tables that correlate virtual destination addresses with physical egress ports. These pre-computed mappings are stored and reused for subsequent forwarding decisions, significantly reducing the time penalty of address translation while maintaining forwarding flexibility.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates and maintains copy of forwarding information in multiple locations (including in each PIU and in centralized controllers) to enable fast local lookups. This copying strategy reduces translation overhead by allowing parallel access to forwarding information without requiring centralized sequential processing.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS8885475B2Method and system for virtualized forwarding
Publication Date: 2014.11.11 FUJITSU LTD
  • US8885475B2 patent drawing
  • US8885475B2 patent drawing
  • US8885475B2 patent drawing

AI summary

According to one embodiment, a method may include receiving a frame via an ingress port of a network element. The method may also include assigning a virtual destination address to the frame of the traffic. The method may further include internally switching the frame within the network element based on the virtual destination address. The method may additionally include modifying the virtual destination address one or more times such that the virtual destination address is translated to an actual destination address identifying an actual egress port of the network element. Moreover, the method may include routing the frame to an egress port of the network element based on the actual destination address.