SDN Flow Table Segmentation for Memory Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing software defined networking (SDN) systems face challenges in managing traffic efficiently due to high memory capacity requirements and scalability limitations, particularly in data centers with complex topology structures, where the use of ternary content addressable memory (TCAM) leads to increased power consumption and cost, and the reactive and proactive modes of the OpenFlow protocol either increase operational load or require excessive memory.
Innovation Solution
The method employs downlink and uplink flow tables, along with an uplink group table, to manage traffic in SDN without relying on conventional complex flow tables, reducing memory requirements and maintaining low complexity, even as the data center dimension and network traffic increase, by using a centralized controller to generate optimal transmission paths through equal cost multi-path routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the proactive mode is used to preconfigure all transmission paths, then the traffic performance of the switch and controller is improved, but the memory capacity requirement for saving flow tables increases exponentially
Solution Approach 1:
The patent divides the flow table into multiple segments (first flow table, second flow table, third flow table) with different scopes. The first flow table stores transmission paths for a first set of destinations, the second flow table stores transmission paths for a second set of destinations, and the third flow table stores transmission paths for a third set of destinations. This segmentation allows the system to maintain comprehensive routing information while reducing the memory capacity requirement at each switch by distributing the flow table entries across multiple tables and switches.
2Quantity of substance
If the reactive mode is used to determine transmission paths on demand, then the memory capacity requirement is reduced, but the operational load of the switch increases due to frequent query processes
Solution Approach 1:
The patent implements a hybrid approach where the controller preconfigures transmission paths for commonly accessed destinations in the first and second flow tables before data transmission begins. This preliminary action allows switches to directly forward data packets to these destinations without frequent queries to the controller, reducing operational load. For less common destinations, the reactive mode is maintained, allowing switches to query the controller when needed, thus balancing memory requirements with operational load.
3Adaptability or versatility
If the dimension of the topology structure is increased to expand data center scale, then the network coverage is improved, but the memory capacity requirement for saving flow tables increases exponentially
Solution Approach 1:
The patent introduces a hierarchical dimension to the flow table structure by organizing flow tables across multiple levels (first flow table at one level, second flow table at another level, third flow table at a third level). This hierarchical arrangement allows the network to scale to larger dimensions by distributing routing information across the hierarchy, preventing exponential growth of memory requirements at any single level while maintaining comprehensive network coverage.
4Quantity of substance
If the TCAM is used to save flow tables in conventional switches, then the flow table storage capability is improved, but the power consumption and manufacturing cost increase
Solution Approach 1:
The patent replaces the expensive and high-power-consumption TCAM with standard SRAM or DRAM for flow table storage. By using these more economical memory technologies, the system achieves comparable flow table storage capability with significantly reduced power consumption and manufacturing cost. The flow tables are dynamically updated and managed by the controller, making the system adaptable without relying on expensive hardware.
Data Source
AI summary
A method for managing traffic item in software defined networking includes establishing a downlink flow table of a switch according to the flow entries, establishing an uplink flow table of the switch according to the flow entries, acquiring a data packet by the switch, and generating a transmission path to allocate the data packet according to the data packet, the downlink flow table, and the uplink flow table. The downlink flow table includes a correlation between first transmission ports of the switch and down link switches. The uplink flow table includes a correlation between the first transmission ports and a transmission port group of uplink switches.