OpenFlow large-scale flow table elastic energy-saving and high-efficiency search framework and OpenFlow large-scale flow table elastic energy-saving and high-efficiency search method

Abstract

The invention discloses an OpenFlow large-scale flow table elastic energy-saving and efficient search architecture and method, and the architecture comprises an active precise flow layer which is usedfor caching active precise flow table entries in a network, and achieving the high-speed and low-power flow table cache search; a convergent flow layer which is used for storing universal flow tableentries so as to relieve the problem of insufficient TCAM storage capacity and improve the TCAM cache hit rate; wherein the convergent flow layer comprises a TCAM and a DRAM; the individual flow layeris used for storing accurate flow table entries which do not meet the aggregation condition temporarily so as to improve the packet forwarding capability of the OpenFlow switch; the bulk flow layer includes an SRAM and a DRAM. According to the method, the sparse grid is constructed by using the cross linked list, the cache space is dynamically applied, all accurate flows meeting conditions can bestored, no empty table item exists, the space utilization rate is very high, and the method can adapt to dynamic change of network flow and is rich in elasticity.

Description

technical field [0001] The invention relates to the field of OpenFlow flow tables, in particular to an OpenFlow large-scale flow table elastic energy saving and high-efficiency search architecture and method. Background technique [0002] As a new type of network architecture, Software Defined Networking (SDN) extracts the control functions of traditional forwarding devices and centralizes them in the SDN controller to manage all forwarding devices in the data plane, thereby realizing Flexible control over network traffic. The SDN controller formulates flow rules based on the global network view, issues them uniformly through the southbound protocol interface, and hands them over to the switches on the data plane for learning and caching to generate local rule sets to guide the processing of network packets. The OpenFlow protocol is one of the most widely used southbound interface protocols at present. It extracts the important fields of the network protocol headers of each...

AI Technical Summary

Problems solved by technology

Existing energy-saving solutions often need to pre-set the size of the flow cache, which is poor in scalability and is prone to the following problems: If the energy-saving cache is set too small, the number of flow entries it can accommodate is limited, which will cause some important flow entries to be hashed. If the energy-saving cache is set too large, although it can accommodate all important flow entries, due to the unevenness of the hash algorithm, there will be many empty tables in the cache. items, resulting in a waste of cache space

[0007] 2. Large-scale flow table lookup performance problem

The comparison file scheme does not optimize the storage of the cache space well, so that the utilization rate of the cache space is not high, and table entries are frequently replaced due to insufficient cache space

Images