Switching Element Congestion Synchronization Mechanism
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In network switches, the reassertion of connection requests after initial rejection due to congestion is unpredictable, leading to unfair prioritization and increased complexity in managing multiple ingress ports, which can result in lower network performance and higher latency.
Innovation Solution
A synchronization mechanism that allows reassertion of connection requests from multiple input ports to occur simultaneously after a predetermined time period, ensuring that the highest priority or oldest packets are chosen for transmission, by generating synchronization signals and delaying the expiry of link status signals to prevent overtaking by new requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If connection requests are reasserted after congestion rejection, then network throughput is improved, but reassertion timing becomes unpredictable leading to unfair prioritization
Solution Approach 1:
The patent implements periodic reassertion of connection requests at predetermined time intervals after congestion rejection. This ensures that all input ports reassert their requests simultaneously at regular intervals, maintaining predictable timing while allowing multiple packets to be transmitted, thus resolving the contradiction between improved throughput and maintained prioritization fairness.
2Loss of time
If connection requests are reasserted immediately after rejection, then latency is reduced, but network congestion may worsen due to simultaneous reassertion
Solution Approach 1:
The patent employs periodic reassertion at predetermined intervals rather than immediate reassertion. This timing strategy allows the network to clear some congestion before reassertion occurs, reducing the harmful effect of simultaneous reassertion while still maintaining acceptable latency by not delaying too long.
Solution Approach 2:
The patent delays reassertion by a predetermined time period after congestion rejection is detected. This preliminary waiting period allows the congested output port to clear its buffer and become ready to accept new packets, preventing immediate reassertion from worsening congestion while still preparing for efficient retransmission.
3Loss of time
If multiple input ports reassert requests at different times, then individual port latency is minimized, but overall network fairness deteriorates
Solution Approach 1:
The patent implements synchronized periodic reassertion where all input ports reassert their connection requests simultaneously at predetermined time intervals. This synchronization mechanism ensures that older packets from all ports are reasserted together, maintaining network-wide fairness while still allowing efficient utilization of available bandwidth.
Solution Approach 2:
The patent creates equipotential conditions by ensuring all input ports have equal opportunity to reassert requests at the same time intervals. This equalizes the competitive position of all input ports, preventing any single port from gaining unfair advantage while maintaining overall system efficiency through coordinated reassertion.
Data Source
AI summary
A method and system is provided for efficiently controlling data packet routing through a switching element which has a first plurality of input ports and a second plurality of output ports. The method and system are configured for detecting issuance of a first congestion indicator from an output port of the switching element which is related to a first routing request received from a first input port. Reassertion of the first routing request is then carried out after a first time period. Similarly, the method and system are configured for detecting issuance of a second congestion indicator from the output port of the switching element, which is related to a second routing request from a second input port. Reassertion of the second routing request is then carried out after a second time period. In addition, the first and second time periods are set up so that reassertions of the first and second connection requests occur substantially simultaneously.