Unlock instant, AI-driven research and patent intelligence for your innovation.

Online Package Classification Method Based on Range Tuple Search

A packet classification and range technology, applied in the field of online packet classification based on range tuple search, can solve the problems of rule fluctuation, large running memory, small memory size, etc., to achieve the effect of fast update, improve performance, and reduce switching

Active Publication Date: 2022-03-18
HUNAN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The on-chip memory size of such chips is often relatively small
The data structure designed by the existing package classification method occupies a large amount of running memory, or the running memory is very unstable (there is a large fluctuation with the type of rules)

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Online Package Classification Method Based on Range Tuple Search
  • Online Package Classification Method Based on Range Tuple Search
  • Online Package Classification Method Based on Range Tuple Search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] A range tuple is a special kind of tuple, each element of which represents the length range of the corresponding field of the rule. Compared with the tuple (a, b, c, ...) in the TSS, each tuple represents the bit length of the corresponding field, each of the range tuples (A, B, C, ...) in the present invention An element represents a range of lengths. Each range tuple corresponds to a hash table, and the hash table stores all the rules that the range tuple can cover. In order to index rules with a hash function, each hash table needs to specify the length of its hash key. A natural approach is to concatenate all matching fields of the rule as a hash key. However, different rules may correspond to match fields of different lengths, and in practice rules in a hash table require hash keys of the same length. In order to solve this problem, the present invention further introduces the concept of primitive group. More specifically, for each range in the range tuple, its...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an online packet classification method based on range tuple search, including a data structure construction method, a data packet classification search method, and a classification rule update method; the invention uses a hash function to ensure the constant-level time complexity of rule update , realizing the fast update of classification rules; the invention maps the rules to a small number of range tuples, greatly improving the classification speed of data packets while ensuring the rule update speed; the invention can well store the data structure in the on-chip memory In this way, the switching of on-chip storage content is reduced, and the performance of the method is improved.

Description

technical field [0001] The invention relates to data packet classification technology, in particular to an online packet classification method based on range tuple search. Background technique [0002] Packet classification is one of the fundamental operations in switches, routers, and other network devices used to support security, QoS, and advanced features, where packets are matched in a classifier based on a multi-field rule set. In traditional web applications, rules remain relatively static. Therefore, classifiers built offline usually have well-designed data structures, which can achieve efficient packet classification, and because the rules are updated infrequently, classifiers can be built offline. [0003] The emergence of software-defined networking (SDN) provides a huge opportunity for network innovation to enable the network to support new features and value-added functions. These capabilities include support for traffic engineering, network functions virtuali...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/764G06K9/62H04L47/2441
Inventor 张大方沈潼谢高岗张昕怡
Owner HUNAN UNIV