IPFIX-based elephant flow processing method and device

Abstract

The invention discloses an IPFIX-based elephant flow processing method and device. The method comprises the steps of receiving a message marked as an elephant flow and learning the elephant flow intoan IPFIX flow table through an IPFIX flow table statistical mechanism, wherein the IPFIX flow table performs byte number statistics on each elephant flow; periodically scanning the IPFIX flow table, determining whether the byte number of each elephant flow in the IPFIX flow table is greater than a preset threshold value or not, determining the elephant flow of which the byte number is smaller thanthe preset threshold value as a mistakenly detected mice flow, and uploading the elephant flow to a CPU for processing. According to the method, the mice flow which is mistakenly detected as the elephant flow in the elephant flow can be accurately removed, the accuracy of data center network optimization is improved, and CPU resources are saved.

Description

technical field [0001] The invention relates to the field of network technology, in particular to an IPFIX-based elephant stream processing method and device. Background technique [0002] In the data center network, the traffic includes elephant traffic and mouse traffic. There are many types of mouse traffic and relatively large proportion, while elephant traffic has fewer types and relatively small proportion. Among them, elephant traffic usually refers to the The data flow of most of the bandwidth of the center network, the mouse flow usually refers to the data flow that occupies a small part of the bandwidth of the data center network. Because the mouse flow is sensitive to delay, it consumes a small amount of bandwidth in the data center, while the elephant flow consumes more than 80% of the bandwidth of the data center, so the elephant flow is effectively detected, and corresponding policies and controls (such as forwarding path, QoS, etc.) are implemented for the ele...

AI Technical Summary

Problems solved by technology

[0004] However, since the Counter in the Bloom Filter algorithm model is shared, only four Hash polynomials are used to break up the flow, which will easily cause a certain collision rate when there is a lot of traffic, resulting in false detection. The higher the detection rate, the easier it is to misdetect the mouse flow as an elephant flow

In order to remove the mouse flow in the elephant flow, software methods are usually used to remove it, which will easily lead to high CPU load and affect the progress of other businesses

Images