MC-LAG Rate Limiting via Inter-Peer Information Exchange
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-chassis link aggregation group (MC-LAG) configurations, existing methods fail to effectively coordinate rate limiting among network elements to ensure that the overall data rate transmitted to a common network node does not exceed a predefined maximal rate, leading to potential underutilization or failure to meet the rate constraint.
Innovation Solution
Network elements coordinate rate limiting by exchanging information via inter-peer links, using policers that adjust egress rates based on ingress rates and packet sizes, ensuring that the combined egress rate does not exceed the maximal rate, and implementing token bucket mechanisms to manage token levels for efficient data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If network elements independently limit egress rates without coordination, then each element can control its own output rate, but the combined egress rate may exceed the maximal rate or bandwidth utilization is inefficient
Solution Approach 1:
Network elements exchange rate information through inter-peer links to create a feedback mechanism. Each element reports its ingress rate and receives reports from peers, allowing the system to collectively monitor and adjust the combined egress rate to adhere to the maximal rate constraint while optimizing bandwidth utilization.
Solution Approach 2:
The patent merges the rate control decisions of multiple network elements by having them exchange information about their ingress rates. This combination of information allows the group of elements to collectively manage the aggregate egress rate, ensuring it does not exceed the maximal rate while maximizing bandwidth usage.
2Reliability
If network elements exchange detailed packet information via inter-peer links, then coordinated rate limiting can be achieved, but the complexity of information exchange and processing increases
Solution Approach 1:
The patent extracts only the essential information needed for rate coordination—specifically, the ingress rate and packet size—from the full packet data. By transmitting only these key parameters rather than complete packet information, the system achieves accurate rate coordination while minimizing the complexity of information exchange.
3Productivity
If network elements use token bucket mechanisms with shared bandwidth buckets, then excess bandwidth can be utilized when underutilization occurs, but the management of token levels and bandwidth allocation becomes more complex
Solution Approach 1:
The patent implements a shared bandwidth bucket that serves multiple guaranteed bandwidth buckets simultaneously. This universal bandwidth pool allows network elements to utilize excess bandwidth from underutilized elements, providing multi-functionality that handles both individual guaranteed rates and collective excess bandwidth allocation within a unified management framework.
Data Source
AI summary
A network element connects over a network to a network node via a member link of a Multi-Chassis—Link Aggregation Link Group (MC-LAG), and further connects, using inter-peer ports, to peer network elements coupled to the network node via other MC-LAG member links. A processor of the network element is configured to receive from the network first packets destined to the network node, to receive via the inter-peer ports information indicative of second packets received from the network by the peer network elements that are destined to the network node, to select at least some of the first packets for transmission at an egress rate that jointly with egress rates of the peer network elements does not exceed a predefined MC-LAG maximal rate, based on the first packets and the information, and to transmit the selected first packets to the network node at the egress rate.