Logical Port Data Forwarding With Idle Unit Rate Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing packet forwarding technologies face challenges in adapting to delay-sensitive applications due to high hardware resource costs, uncertain data cache storage, and variable forwarding delays, particularly in systems with varying port sizes and scales, leading to inefficient bandwidth utilization and increased forwarding delays.
Innovation Solution
A data forwarding method that utilizes logical ports and adjusts the quantity of idle units in data unit sequences to match the rate of egress ports, reducing forwarding pressure and enhancing throughput capability while decreasing forwarding delays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If packet data units are forwarded one by one with table lookup per packet, then forwarding accuracy is maintained, but forwarding delay increases and service throughput decreases
Solution Approach 1:
The patent segments the data stream into data units with idle units inserted between them, transforming the continuous packet stream into discrete segments that can be processed in parallel. This segmentation enables the system to maintain forwarding accuracy while reducing overall forwarding delay by processing multiple segments simultaneously rather than sequentially
Solution Approach 2:
The patent performs preliminary actions by pre-configuring logical port mapping relationships and pre-calculating rate adjustment parameters before actual data forwarding begins. This allows the system to avoid real-time table lookup and complex calculations during data forwarding, significantly reducing forwarding delay while maintaining accuracy through pre-established mapping rules
2Productivity
If data is cached and queued at egress ports to ensure service capability utilization, then bandwidth utilization improves, but forwarding delay increases and hardware resource cost increases
Solution Approach 1:
The patent performs preliminary rate adjustment by inserting or removing idle units before data units reach the egress port queue. This rate matching prevents bandwidth mismatches and queue overflows before they occur, eliminating the need for extensive caching and queuing operations, thereby improving bandwidth utilization without increasing forwarding delay
Solution Approach 2:
The patent extracts the rate adjustment function from the egress port queuing mechanism by performing idle unit insertion/removal at the logical port level. This separates rate matching from queue management, allowing the system to achieve both high bandwidth utilization and low forwarding delay by handling rate adjustment independently of the queuing process
3Measurement precision
If table lookup is performed for each packet based on destination address and label, then forwarding precision is maintained, but hardware resource cost increases and device complexity increases
Solution Approach 1:
The patent segments the forwarding decision process into two parts: logical port identification (performed once per data stream) and data unit forwarding (performed for each unit). This segmentation eliminates the need for repeated table lookups for each packet while maintaining forwarding precision through the established logical port mapping relationship
Solution Approach 2:
The patent performs preliminary forwarding decision-making by establishing logical port mapping relationships based on destination addresses and labels before data forwarding begins. This pre-computation eliminates the need for real-time table lookups during data unit forwarding, significantly reducing hardware resource cost and device complexity while maintaining forwarding precision through the pre-established mappings
4Adaptability or versatility
If logical port rate does not match egress port rate, then data stream flexibility is maintained, but forwarding efficiency decreases and buffering requirements increase
Solution Approach 1:
The patent implements dynamic rate adjustment by inserting or removing idle units based on the rate difference between logical port and egress port. This dynamic adjustment mechanism maintains data stream flexibility while optimizing forwarding efficiency, as the system can adapt the data unit transmission rate to match the egress port capability without requiring extensive buffering
Solution Approach 2:
The patent changes the transmission rate parameter of the data stream by adjusting the number of idle units inserted or removed. This parameter adjustment allows the system to maintain flexibility in handling different data stream rates while improving forwarding efficiency by matching the egress port rate, thereby reducing buffering requirements
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This application discloses a data forwarding method and device. The method includes: obtaining a first data unit sequence stream by using a first logical ingress port, where the first data unit sequence stream includes at least one first data unit; determining, according to a preconfigured mapping relationship between at least one logical ingress port and at least one logical egress port, a first logical egress port corresponding to the first logical ingress port, where the at least one logical ingress port includes the first logical ingress port; adjusting a quantity of idle units in the first data unit sequence stream, so that a rate of an adjusted first data unit sequence stream matches a rate of the first logical egress port; and sending the adjusted first data unit sequence stream by using the first logical egress port. In the method in this application, forwarding pressure of a forwarding device can be effectively reduced, a service throughput capability of the forwarding device can be effectively increased, and a data forwarding delay can be decreased, so that the method can be adapted to a delay-sensitive large-bandwidth service.