Flow-Based Switch Congestion Policing via Flow Penalties
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network traffic policing methods, such as Re-ECN and Comcast's Protocol-Agnostic Congestion Management System, face challenges in scalability and specificity to certain network architectures, requiring protocol modifications and focusing on volume-based congestion metrics rather than cost-based fairness.
Innovation Solution
A method utilizing flow-based programmable switches, like OpenFlow switches, to detect and penalize congestion-causing flows by monitoring statistics such as drop counts, mark counts, and packet timing, without altering existing network protocols, allowing for dynamic congestion management at the flow level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Re-ECN protocol extensions are implemented at end hosts and IP level, then congestion-based policing capability is improved, but device complexity and deployment difficulty increase
Solution Approach 1:
The patent introduces flow-based programmable switches as intermediaries between end hosts and the core network. These switches monitor flow statistics, detect congestion conditions, and enforce policing decisions without requiring modifications to end host protocols or IP level operations. The switch acts as a mediator that implements congestion-based policing using existing standard protocols while adding intelligence at the network edge.
2Reliability
If Comcast's volume-based congestion management is applied, then congestion detection capability is improved, but measurement precision deteriorates due to lack of flow-level granularity
Solution Approach 1:
The patent segments congestion management from volume-based aggregate monitoring to flow-level granular measurement. Flow-based programmable switches maintain statistics for individual flows, enabling precise identification of congestion-causing flows. This segmentation allows the system to detect congestion at the appropriate granularity level without requiring volume-based approximations.
Solution Approach 2:
The patent applies local quality by enabling different measurement granularities at different network locations. Flow-level monitoring is implemented at the ingress switch where detailed flow statistics are available, while aggregate congestion detection occurs at egress or core network points. This allows each part of the system to operate at the optimal granularity for its function.
3Adaptability or versatility
If flow-based programmable switches are used for congestion policing, then adaptability to different network architectures is improved, but device complexity increases
Solution Approach 1:
The patent leverages the universal capabilities of flow-based programmable switches that can be configured through standardized protocols like OpenFlow. These switches provide multi-functional support for various network architectures and traffic management policies through a common programming interface. The same switch infrastructure can adapt to different network topologies, traffic patterns, and policing requirements without requiring hardware modifications.
Data Source
AI summary
A method of policing network traffic based on congestion on a flow-based programmable switch, such as an OpenFlow switch is provided. The method polices congestion-causing flows in a network by detecting congestion at a flow-based programmable switch on the network. Once congestion has been detected, the method identifies one or more flows that are causing the congestion at the flow-based programmable switch, and penalizes the flows that were identified as causing congestion. A flow-based programmable switch including a data plane having input ports, output ports, and forwarding rules that map packets received on an input port to an output port based on a packet matching a rule in the forwarding rules is also described.