Multicast Queue Aggregation in Network Switches

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Network switching systems face challenges in efficiently utilizing processing power, memory, and bandwidth to process multicast traffic flows, particularly in larger networks, due to the need for a large number of queues and potential waste of bandwidth through unnecessary data packet distribution.

Innovation Solution

A method and apparatus for a network switching device that stores and aggregates multicast data units into frames, allowing for efficient transmission to superset multicast groups, using a multicast forwarding engine to manage queues and determine data unit storage and aggregation, thereby reducing the number of required queues and minimizing bandwidth waste.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If separate queues are maintained for each multicast group, then multicast traffic can be processed individually, but the number of queues increases significantly consuming memory resources

Engineering Contradiction:
Improvemulticast traffic processing accuracyVSAvoidmemory resources for queues
Core Design Contradiction:
ReliabilityVSVolume of stationary object

Solution Approach 1:

The patent combines multiple multicast group queues into a single shared queue structure. Instead of maintaining separate queues for each multicast group, the system uses one queue to store data units for multiple groups, reducing memory consumption while maintaining the ability to process traffic for each group individually through selective retrieval and forwarding.

Inventive Principle:
Principle #5Merging (Combining)

2Adaptability or versatility

If data packets are distributed to all multicast groups, then all groups receive the data, but bandwidth is wasted on unnecessary distribution

Engineering Contradiction:
Improvemulticast group coverageVSAvoidbandwidth utilization efficiency
Core Design Contradiction:
Adaptability or versatilityVSLoss of energy

Solution Approach 1:

The patent applies local quality by enabling selective forwarding of data units from the shared queue to specific multicast groups based on their individual requirements. Each multicast group receives data units only when needed, rather than all groups receiving all data units. This selective distribution mechanism optimizes bandwidth utilization by avoiding unnecessary transmissions to groups that do not require particular data units.

Inventive Principle:
Principle #3Local quality

3Ease of operation

If multiple separate queues are used for different multicast groups, then each group can be managed independently, but processing complexity increases

Engineering Contradiction:
Improveindependent queue managementVSAvoidqueue management system
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements a universal queue management approach where a single shared queue serves multiple multicast groups simultaneously. The queue management system is designed to handle data units for different groups within the same queue structure, using identifiers and forwarding rules to manage independent group requirements. This multi-functional design reduces the number of queue objects while maintaining independent manageability through a unified control mechanism.

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

Data Source

PatentUS9137030B1Multicast queueing in a network switch
Publication Date: 2015.09.15 MARVELL ASIA PTE LTD
  • US9137030B1 patent drawing
  • US9137030B1 patent drawing
  • US9137030B1 patent drawing

AI summary

First data units corresponding to a first multicast group (MCG) and second data units corresponding to a second MCG are stored in a first queue of a network switching device. At least one first data unit retrieved from the first queue and at least one second data unit retrieved from the first queue are aggregated into a first frame. The first frame is transmitted by the network switching device to a superset MCG that includes at least the first MCG and the second MCG. Only third data units corresponding to a third MCG are stored in a second queue of the network switching device. Third data units retrieved from the second queue are transmitted by the network switching device to the third MCG.