CN111901195A - SDN flow dynamic distribution method and system - Google Patents
SDN flow dynamic distribution method and system Download PDFInfo
- Publication number
- CN111901195A CN111901195A CN202010717820.8A CN202010717820A CN111901195A CN 111901195 A CN111901195 A CN 111901195A CN 202010717820 A CN202010717820 A CN 202010717820A CN 111901195 A CN111901195 A CN 111901195A
- Authority
- CN
- China
- Prior art keywords
- flow
- average value
- sdn
- vip
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0894—Packet rate
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/22—Traffic shaping
- H04L47/225—Determination of shaping rate, e.g. using a moving window
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2416—Real-time traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
Abstract
The invention relates to a dynamic SDN flow distribution method and a system, which are used for obtaining the average value of flow data in a certain time period of a downlink port of an SDN switch; judging whether the average value of the flow data exceeds a preset threshold value M of the system, if not, returning to S00, and if so, executing the next step; the invention realizes the separation of control and forwarding of the traditional physical network based on the SDN technology, reasonably allocates the speed limit to the flow through an open programming interface and centralized network control, and provides dynamic bandwidth allocation service under the principle of ensuring the bandwidth utilization rate and user fairness.
Description
Technical Field
The invention relates to the field of internet, in particular to a method and a system for dynamically distributing SDN (software defined network) flow.
Background
The traditional flow distribution system provides an unbalanced flow of the outlet flow and the flow demand of the users, and although certain fairness among the users is ensured in the flow distribution process, the utilization rate of the bandwidth is reduced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a dynamic SDN flow allocation method and a system, which realize the separation of control and forwarding of the traditional physical network based on the SDN technology, reasonably limit the speed of the flow allocation through an open programming interface and centralized network control and provide dynamic bandwidth allocation service under the principle of ensuring the bandwidth utilization rate and user fairness.
The purpose of the invention is realized by the following technical scheme:
a SDN flow dynamic allocation method comprises the following steps:
s00: acquiring a flow data average value of a downlink port of the SDN switch within a certain time period;
s10: judging whether the average value of the flow data exceeds a preset threshold value M of the system, if not, returning to S00, and if so, executing the next step;
s20: and issuing an openflow flow table and a flow table association meter table to the equipment under the SDN switch according to a speed limiting mechanism to carry out speed limiting operation.
Further, the speed limiting mechanism is as follows:
defining the total traffic data of the VIP host in the time period as x, the total traffic data of the non-VIP host as y, and the port link bandwidth D, then having a threshold M = kD, where k is a threshold coefficient value (0, 1);
if x + y > kD limits non-VIP hosts, then y ^ M-x.
Further, the traffic data average value refers to a port traffic data average value, a host traffic data average value, and a traffic data average value of an application flow of each partition room SDN switch.
An SDN traffic dynamic allocation system, the system comprising:
the data monitoring module is connected with the SDN switch of each partition machine room and used for acquiring the average value of flow data of a downlink port of the SDN switch within a certain time period;
the flow calculation module is used for comparing the obtained flow data average value with a threshold value M, and if the flow data average value exceeds the threshold value, the system starts a speed limiting mechanism;
issuing a flow table and associating a meter table module: and after the speed limiting mechanism is started, issuing an openflow flow table and a flow table association meter table to the equipment under the SDN switch according to the speed limiting mechanism to carry out speed limiting operation.
Furthermore, the equipment is divided into a VIP host and a non-VIP host, wherein the VIP host sends a flow table which is matched with the ip mask in the openflow flow table, and the non-VIP host directly sends a flow table which is matched with the port flow table and is associated with the flow table associated with the calculated speed limit condition.
Further, the speed limiting mechanism is as follows:
defining the total traffic data of the VIP host in the time period as x, the total traffic data of the non-VIP host as y, and the port link bandwidth D, then having a threshold M = kD, where k is a threshold coefficient value (0, 1);
if x + y > kD limits non-VIP hosts, then y ^ M-x.
Further, the data monitoring module obtains a port traffic data average value, a host traffic data average value, and a traffic data average value of an application flow of the SDN switch of each machine room by executing a Python crawler code on the server.
The invention has the beneficial effects that: the invention adopts an intelligent flow distribution strategy to realize real-time monitoring, automatic load balancing and real-time control; when the user demand changes, the method can reasonably distribute the bandwidth flow according to the user demand, and improve the bandwidth utilization rate in time; the intelligent flow distribution function can completely ensure the fairness of distribution; when the network is abnormal, the network can ensure the normal internet access requirement of the user; in general, the method has the advantages of improving the network utilization rate, reducing the operation and maintenance cost and workload, intelligently and actively finding out network faults, monitoring and counting network data in real time, reducing the packet loss rate and jitter delay, finding out and preventing network loops in time and reducing the network construction cost.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a diagram of a partitioned computer room architecture;
figure 3 is an SDN system overall architecture diagram.
Detailed Description
The technical solution of the present invention is further described in detail with reference to the following specific examples, but the scope of the present invention is not limited to the following.
Referring to fig. 1, a method for dynamically allocating SDN traffic includes:
s00: acquiring a flow data average value of a downlink port of the SDN switch within a certain time period;
s10: judging whether the average value of the flow data exceeds a preset threshold value M of the system, if not, returning to S00, and if so, executing the next step;
s20: and issuing an openflow flow table and a flow table association meter table to the equipment under the SDN switch according to a speed limiting mechanism to carry out speed limiting operation.
Wherein, the speed limit mechanism is as follows:
defining the total traffic data of the VIP host in the time period as x, the total traffic data of the non-VIP host as y, and the port link bandwidth D, then having a threshold M = kD, where k is a threshold coefficient value (0, 1);
if x + y > kD limits non-VIP hosts, then y ^ M-x.
More specifically, the traffic data average value refers to a port traffic data average value, a host traffic data average value, and a traffic data average value of an application flow of each partition room SDN switch.
An SDN traffic dynamic allocation system, the system comprising:
the data monitoring module is connected with the SDN switch of each partition machine room and used for acquiring the average value of flow data of a downlink port of the SDN switch within a certain time period;
the flow calculation module is used for comparing the obtained flow data average value with a threshold value M, and if the flow data average value exceeds the threshold value, the system starts a speed limiting mechanism;
issuing a flow table and associating a meter table module: and after the speed limiting mechanism is started, issuing an openflow flow table and a flow table association meter table to the equipment under the SDN switch according to the speed limiting mechanism to carry out speed limiting operation.
In a preferred embodiment, the device is divided into a VIP host and a non-VIP host, wherein the VIP host issues a flow table matching an ip mask in an openflow flow table, and the non-VIP host directly issues a flow table matching a port, and associates the flow table with the flow table associated with the calculated speed limit condition.
In the system, the speed limiting mechanism is as follows:
defining the total traffic data of the VIP host in the time period as x, the total traffic data of the non-VIP host as y, and the port link bandwidth D, then having a threshold M = kD, where k is a threshold coefficient value (0, 1);
if x + y > kD limits non-VIP hosts, then y ^ M-x.
On the other hand, the data monitoring module acquires the port traffic data average value, the host traffic data average value and the application flow traffic data average value of the SDN switch of each machine room by executing Python crawler code on the server.
On the other hand, the speed limit execution is to perform speed limit operation on devices under the SDN switch by issuing openflow flow tables and flow table association meter tables according to a speed limit mechanism. Monitoring downlink ports of the machine room SDN switches at regular time, and obtaining an average value of flow data of the downlink ports within a certain period of time, wherein the average value of the flow data refers to an average value of port flow data, an average value of host flow data and an average value of flow data of application flows of the SDN switches of each subarea machine room. For example, the measurement may be performed every 10 minutes, and a device under the SDN switch issues an openflow table (flow table) and a meter table according to a fixed algorithm (that is, a rate limiting mechanism) to perform a rate limiting operation. The flow distribution module comprises a data calculation module, issues a flow table and is associated with a meter table module. The invention has a mechanism for monitoring the flow data of the downlink port of the SDN switch at regular time, and the operation of issuing an openflow table and a flow table association meter table to the device under the SDN switch is carried out according to the acquired flow data. Therefore, the invention can realize the speed-limiting operation of the equipment under the SDN switch, effectively and reasonably utilize the bandwidth and avoid the bandwidth waste or congestion phenomenon.
Basic idea of flow control: the hosts in the network can be divided into VIP hosts and non-VIP hosts, where the VIP hosts need protection from speed limit operation and the non-VIP hosts can perform speed limit operation.
The method comprises the following steps:
a flow acquisition module: acquiring data of a downlink port of the SDN switch at regular time, and calculating an average value;
a flow calculation module: the retrieved value is compared to a threshold (e.g., threshold = link bandwidth 80%), and if the port detects that the traffic data of the link is greater than the threshold, the system initiates a rate limiting mechanism. The algorithm of the speed limit is as follows: acquiring the total traffic data of the VIP host and the total traffic data of the non-VIP host in the last monitoring time window from the network traffic monitoring system, wherein the fact that the total traffic data of the VIP host is x and the total traffic data of the non-VIP host is y exceeds a threshold value means that x + y > port link bandwidth 80%, and then limiting the speed of y: y ^ 80% -x port link bandwidth.
Issuing a flow table and associating a meter table module: issuing openflow flow table according to the above calculated result (wherein VIP host issues the flow table of matching ip mask in openflow flow table, and non-VIP host can directly issue the flow table of matching port and associate the above calculated meter table of speed limit condition)
In another aspect, the present invention further provides an SDN system architecture, and referring to fig. 2, an SDN controller is connected to an ETH port of an SDN switch through a switch. An SDN controller is deployed in an edge machine room in a distributed deployment manner, and fig. 2 is an overall deployment structure of the SDN controller and an SDN switch in one zone machine room, which is the same as the deployment structure of the other zone machine rooms. In fig. 2, ETH ports of the SDN controller and the SDN switch are respectively connected to the bodka switch, so that the SDN controller can control the SDN switch, and the central office server (i.e., the monitoring host) can also monitor the SDN switch through the bodka switch. In fig. 2, the router is connected to an upstream port of the SDN switch, and a downstream port of the SDN switch is connected to an optical line terminal olt (optical line termination) for connecting to a terminal device of the optical fiber trunk.
Referring to fig. 3, the overall layout is shown in a system, and the supervisory host is connected to the SDN switches of the rooms through the management router. An SDN controller is used for controlling an SDN switch, and SDN distributed controllers are deployed in each zone machine room, and each zone machine room is provided with an SDN control which controls the whole network system environment under one SDN switch of the machine room. Different SDN controllers may be deployed in each tile room to control one SDN switch in the room.
The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A SDN flow dynamic distribution method is characterized by comprising the following steps:
s00: acquiring a flow data average value of a downlink port of the SDN switch within a certain time period;
s10: judging whether the average value of the flow data exceeds a preset threshold value M of the system, if not, returning to S00, and if so, executing the next step;
s20: and issuing an openflow flow table and a flow table association meter table to the equipment under the SDN switch according to a speed limiting mechanism to carry out speed limiting operation.
2. The SDN traffic dynamic allocation method of claim 1, wherein the rate limiting mechanism is:
defining the total traffic data of the VIP host in the time period as x, the total traffic data of the non-VIP host as y, and the port link bandwidth D, then having a threshold M = kD, where k is a threshold coefficient value (0, 1);
if x + y > kD limits non-VIP hosts, then y ^ M-x.
3. The method of claim 2, wherein the average value of the flow data refers to an average value of port flow data, an average value of host flow data, and an average value of flow data of an application flow of each zone room SDN switch.
4. An SDN traffic dynamic allocation system, the system comprising:
the data monitoring module is connected with the SDN switch of each partition machine room and used for acquiring the average value of flow data of a downlink port of the SDN switch within a certain time period;
the flow calculation module is used for comparing the obtained flow data average value with a threshold value M, and if the flow data average value exceeds the threshold value, the system starts a speed limiting mechanism;
issuing a flow table and associating a meter table module: and after the speed limiting mechanism is started, issuing an openflow flow table and a flow table association meter table to the equipment under the SDN switch according to the speed limiting mechanism to carry out speed limiting operation.
5. The SDN traffic dynamic distribution system of claim 4, wherein the devices are divided into VIP hosts and non-VIP hosts, wherein the VIP hosts issue flow tables matching with ip masks in openflow flow tables, and the non-VIP hosts issue matching port flow tables directly, and associate the flow table association meter tables of the speed limit conditions calculated above.
6. The SDN traffic dynamic distribution system of claim 5, wherein the rate limiting mechanism is:
defining the total traffic data of the VIP host in the time period as x, the total traffic data of the non-VIP host as y, and the port link bandwidth D, then having a threshold M = kD, where k is a threshold coefficient value (0, 1);
if x + y > kD limits non-VIP hosts, then y ^ M-x.
7. The SDN traffic dynamic distribution system of claim 6, wherein the data monitoring module obtains a port traffic data average value, a host traffic data average value, and a traffic data average value of an application flow of the SDN switch of each machine room by executing Python crawler code on a server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010717820.8A CN111901195B (en) | 2020-07-23 | 2020-07-23 | SDN flow dynamic distribution method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010717820.8A CN111901195B (en) | 2020-07-23 | 2020-07-23 | SDN flow dynamic distribution method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111901195A true CN111901195A (en) | 2020-11-06 |
CN111901195B CN111901195B (en) | 2022-02-15 |
Family
ID=73190535
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010717820.8A Active CN111901195B (en) | 2020-07-23 | 2020-07-23 | SDN flow dynamic distribution method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111901195B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112866019A (en) * | 2021-01-11 | 2021-05-28 | 科大讯飞股份有限公司 | Method for limiting bandwidth of elastic IP address, related equipment and readable storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150154257A1 (en) * | 2013-12-04 | 2015-06-04 | Nec Laboratories America, Inc. | System and method for adaptive query plan selection in distributed relational database management system based on software-defined network |
WO2015080525A1 (en) * | 2013-11-28 | 2015-06-04 | 주식회사 케이티 | Method and apparatus for dynamic traffic control in sdn environment |
US20150236968A1 (en) * | 2014-02-14 | 2015-08-20 | Telefonaktiebolaget L M Ericsson (Publ) | Denial of service prevention in a software defined network |
US20160036706A1 (en) * | 2013-03-15 | 2016-02-04 | Hewlett-Packard Development Company, L.P. | Traffic control across a layer 2 layer 3 boundary in a software defined network |
CN105791152A (en) * | 2014-12-19 | 2016-07-20 | 杭州华三通信技术有限公司 | Traffic control method, SDN (Soft Define Network) controller and SDN device |
CN105812281A (en) * | 2014-12-31 | 2016-07-27 | 中国电信股份有限公司 | Method, device and system for service quality QOS level control |
CN106130928A (en) * | 2016-06-29 | 2016-11-16 | 浪潮集团有限公司 | Flow control methods under a kind of SDN and system |
US20160373361A1 (en) * | 2015-06-17 | 2016-12-22 | Citrix Systems, Inc. | System for bandwidth optimization with high priority traffic awareness and control |
CN107147585A (en) * | 2017-03-31 | 2017-09-08 | 北京奇艺世纪科技有限公司 | A kind of flow control methods and device |
-
2020
- 2020-07-23 CN CN202010717820.8A patent/CN111901195B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160036706A1 (en) * | 2013-03-15 | 2016-02-04 | Hewlett-Packard Development Company, L.P. | Traffic control across a layer 2 layer 3 boundary in a software defined network |
WO2015080525A1 (en) * | 2013-11-28 | 2015-06-04 | 주식회사 케이티 | Method and apparatus for dynamic traffic control in sdn environment |
US20150154257A1 (en) * | 2013-12-04 | 2015-06-04 | Nec Laboratories America, Inc. | System and method for adaptive query plan selection in distributed relational database management system based on software-defined network |
US20150236968A1 (en) * | 2014-02-14 | 2015-08-20 | Telefonaktiebolaget L M Ericsson (Publ) | Denial of service prevention in a software defined network |
CN105791152A (en) * | 2014-12-19 | 2016-07-20 | 杭州华三通信技术有限公司 | Traffic control method, SDN (Soft Define Network) controller and SDN device |
CN105812281A (en) * | 2014-12-31 | 2016-07-27 | 中国电信股份有限公司 | Method, device and system for service quality QOS level control |
US20160373361A1 (en) * | 2015-06-17 | 2016-12-22 | Citrix Systems, Inc. | System for bandwidth optimization with high priority traffic awareness and control |
CN106130928A (en) * | 2016-06-29 | 2016-11-16 | 浪潮集团有限公司 | Flow control methods under a kind of SDN and system |
CN107147585A (en) * | 2017-03-31 | 2017-09-08 | 北京奇艺世纪科技有限公司 | A kind of flow control methods and device |
Non-Patent Citations (3)
Title |
---|
张莉敏等: "基于多队列切换的SDN拥塞控制", 《软件》 * |
杨骥等: "OpenFlow交换机动态共享限速机制的研究", 《计算机学报》 * |
高平等: "基于SDN的云架构网络高确定性流量控制方法", 《计算机工程》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112866019A (en) * | 2021-01-11 | 2021-05-28 | 科大讯飞股份有限公司 | Method for limiting bandwidth of elastic IP address, related equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111901195B (en) | 2022-02-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2651149C2 (en) | Sdn-controller, data processing center system and the routed connection method | |
CN108667743B (en) | Congestion control in packet data networking | |
CN109547340A (en) | SDN data center network jamming control method based on heavy-route | |
EP3033860B1 (en) | Transparent software-defined network management | |
JP2019533913A (en) | Load balancing optimization method and apparatus based on cloud monitoring | |
CN102932281B (en) | A kind of dynamic allocation method of resource and equipment | |
Xu et al. | Minimizing flow statistics collection cost using wildcard-based requests in SDNs | |
CN106059942A (en) | Traffic control method based on load prediction in SDN network | |
CN106411664A (en) | Metropolitan area network system | |
CN107346259B (en) | Method for realizing dynamic deployment safety capability | |
WO2020077696A1 (en) | Domain name bandwidth adjusting method and related device | |
CN109327401B (en) | Flow scheduling method and system of SDN (software defined network) | |
CN108476175B (en) | Transfer SDN traffic engineering method and system using dual variables | |
CN111901195B (en) | SDN flow dynamic distribution method and system | |
CN103812750A (en) | Message receiving and sending protecting system and method for CPU of data communication equipment | |
CN104539558A (en) | Capacity-expansible IP telephone exchange blade mechanism frame and automatic capacity expansion method | |
CN105207856A (en) | Load balancing system and method based on SDN virtual switch | |
US10965605B2 (en) | Communication system, communication control method, and communication apparatus | |
CN108768698B (en) | SDN-based multi-controller dynamic deployment method and system | |
CN102209028A (en) | Flow control device and method for CPU (Central Processing Unit) | |
CN110177056A (en) | A kind of self-reacting band width control method | |
CN114928614B (en) | Deterministic network load balancing method and system based on SDN | |
CN105812281B (en) | Service quality QOS level control method, apparatus and system | |
CN111901196B (en) | Software Defined Network (SDN) flow monitoring and visualization system | |
CN111294406B (en) | Software defined network controller hybrid mapping method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |