Data packet recursive flow sorting method

Abstract

The present invention discloses a data packet recursion flow classification method, said method includes the following steps: pretreatment stage, dividing the fields contained by rule in rule base into several domains and defining number for stages for recursive classificaltion and combination condition of every domain; the domain according to rule is determined value or range, making respective treatment and producing pretreatment victor table of every stage for recursive classification; and search stage, searching the received data packet in pretreatment vector table or every stage, defining class identification belonging to the data packet, then respectively processing data packets according to the service types correspondent to the class identifications of data packets.

Description

Technical field [0001] The invention relates to a method for classifying data streams in an IP network, in particular to a method for classifying recursive streams of data packets, which can rapidly classify and process data streams. Background technique [0002] In the Internet, there are many kinds of network services that need to classify data packets and mark the business class that each data packet belongs to, so as to determine which service type they should accept. One of the simplest examples of data packet flow classification is IP address routing lookup, that is, searching the routing table according to the destination IP address in the data packet to select different routes. With the rapid development of the Internet, many new business requirements have emerged, such as access control lists, policy routing, differentiated services, and traffic accounting. The corresponding data flow classification technology has become more and more important. More and more compl...

AI Technical Summary

Problems solved by technology

When the number of stages increases, the total memory space required decreases, but increases the number of memory accesses and time during the search

[0009] However, there are generally two types of domains for classification rules of data packets: a certain range or a certain value, which makes the preprocessing process quite complicated

Since the value included in the domain in the rule is a definite value or a range, its preprocessing should be very different, and the RFC classification method in the prior art does not make a good distinction.

Moreover, when the existing RFC classification method only generates a preprocessing vector table (table table) at the end, it does not perform differentiated processing according to different business characteristics

Images