Network Queuing Engine Congestion Management via Timer-Based Holding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computer networks face congestion management challenges due to congested nodes unable to send more data traffic than they receive, leading to packet dropping or slowdowns, which degrade application performance and spread congestion throughout the network.
Innovation Solution
A method and apparatus for congestion management involving a queuing engine that accumulates and dequeues data traffic based on congestion notifications, allowing for rate limiting and pausing/resuming data delivery to manage congestion effectively across network domains.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the congested node drops packets to redress congestion, then the network can clear backlog, but application performance degrades due to retransmissions after timeout
Solution Approach 1:
The patent introduces an intermediary mechanism (the queueing engine with timer-based holding) between the congested node and the packet dropping decision. Instead of immediately dropping packets, the system holds them in a queue for a predetermined time period to see if congestion resolves itself, thereby mediating between the need to clear backlog and the need to maintain application performance.
2Reliability
If the congested node uses flow control to slow down delivery, then packet loss is prevented, but congestion spreads through the entire network
Solution Approach 1:
The patent applies local quality by implementing queueing and holding on a per-node basis rather than network-wide flow control. Each congested node independently manages its own queue for a predetermined time, allowing local congestion resolution without triggering network-wide slowdown. This localized approach prevents congestion from spreading throughout the entire network.
3Reliability
If the queue holds packets for a long time, then packet loss is reduced, but latency increases
Solution Approach 1:
The patent applies parameter changes by using a predetermined time period as a configurable parameter for queue holding duration. This time parameter is set to balance two opposing requirements: long enough to allow congestion to resolve and prevent packet loss, but not so long as to cause excessive latency. The parameter can be adjusted based on network conditions and requirements.
Data Source
AI summary
A method, apparatus, and queuing engine implement congestion management. The method may include receiving, via a first interface of the apparatus, data traffic for forwarding to a node of a network. The method may also include receiving, at a second interface of the apparatus, a notification that indicates that congestion is affecting communication with the node, and responsive to the notification, accumulating the data traffic into the queue for a given time period. The method may further include dequeuing the data traffic from the queue after the given time period; and sending the portion of the data traffic to the node via the second interface.