CN114500354A

CN114500354A - Switch control method, device, control equipment and storage medium

Info

Publication number: CN114500354A
Application number: CN202210088251.4A
Authority: CN
Inventors: 袁超
Original assignee: Agricultural Bank of China
Current assignee: Agricultural Bank of China
Priority date: 2022-01-25
Filing date: 2022-01-25
Publication date: 2022-05-13
Anticipated expiration: 2042-01-25
Also published as: CN114500354B

Abstract

The invention discloses a switch control method, a switch control device and a storage medium. The method comprises the following steps: acquiring network topology information of a software definition system; determining at least one target forwarding path according to the network topology information; and generating a target forwarding flow table according to the target forwarding path, and sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal equipment according to the target forwarding flow table. By the technical scheme, the network topology information of the software defined system can be monitored in real time, and the target forwarding path is configured according to the network topology information, so that multi-path parallel transmission is realized by controlling the switch in the network topology without a terminal device supporting a protocol.

Description

Switch control method, device, control equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of software defined system control, in particular to a switch control method, a switch control device, switch control equipment and a storage medium.

Background

With the advent of ultra-low network latency or high throughput based applications such as unmanned driving, cloud gaming, VR video, and cloud storage; more and more data and compute intensive applications are given responsibility for execution by data centers.

In a data center network architecture, common network topologies include Fat-Tree, DCell, BCube, and the like. Different network topology architectures are suitable for different demand environments, but the network topology architectures have the common point that devices often have multiple paths between the devices.

However, in the conventional network, due to the limitation of data transmission by routing protocols, transmission mechanisms, and the like, a plurality of paths existing between hosts cannot be effectively utilized for transmission.

Disclosure of Invention

Embodiments of the present invention provide a switch control method, an apparatus, a control device, and a storage medium, so as to implement real-time monitoring of network topology information of a software defined system, and determine a target forwarding path according to the network topology information, thereby implementing multipath parallel transmission by controlling a switch in a network topology without a terminal supporting a protocol.

In a first aspect, an embodiment of the present invention provides a switch control method, which is applied to a control device of a software defined SDN system, where the SDN system includes: a control device, a switching subsystem comprising a plurality of switches, and a plurality of terminal devices connected to the switching subsystem, the method comprising:

acquiring network topology information of a software definition system;

determining at least one target forwarding path according to the network topology information;

and generating a target forwarding flow table according to the target forwarding path, and sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal equipment according to the target forwarding flow table.

Further, the network topology information includes:

the network topology structure of the software defined system, the bandwidth of each topological path in the network topology structure and the time delay of each topological path; wherein the topological path comprises a plurality of segments of links formed between two switch ports;

correspondingly, the acquiring of the network topology information of the software defined system includes:

acquiring a network topology structure of a software defined system;

determining a plurality of topological paths based on the network topology;

and acquiring the time delay of the topological path and the link bandwidth of the link contained in the topological path.

Further, the determining at least one target forwarding path according to the network topology information includes:

determining a preset number of forwarding paths with minimum time delay ascending sequencing according to the time delay of each topological path; the preset number is used for representing the maximum number of the target forwarding paths;

and determining at least one target forwarding path from the forwarding paths based on the time delay of each topological path and the link bandwidth of the included link.

Further, the determining at least one target forwarding path from a preset number of forwarding paths based on the time delay of each topology path and the link bandwidth of the included link includes:

for each of the forwarding paths, determining an available bandwidth for the forwarding path based on a link bandwidth of the included link;

determining a forwarding path with the minimum time delay and the available bandwidth larger than a first preset bandwidth value as a preferred forwarding path;

respectively determining the delay coefficients of all the forwarding paths except the preferred forwarding path;

determining a forwarding path with a delay coefficient larger than a preset coefficient and an available bandwidth larger than a first preset bandwidth value as an alternative forwarding path;

and determining the alternative forwarding path and the preferred forwarding path as target forwarding paths.

Further, the determining the available bandwidth of the forwarding path based on the latency and the link bandwidth of the included link includes:

for a first forwarding path that all contains a unique link, determining a minimum link bandwidth of the contained links as a first available bandwidth of the first forwarding path;

for a plurality of second forwarding paths comprising a common link, sequentially determining a second available bandwidth of each second forwarding path according to the time delay ascending sequence of each second forwarding path;

wherein the second available bandwidth is determined according to a minimum link bandwidth of each link included in the second forwarding path and/or a link bandwidth of the common link.

Further, the obtaining the time delay of the topology path includes:

creating a probe packet, the probe packet comprising: creating a first detection forwarding flow table corresponding to time and a first switch in the topology path;

sending the probe packet to the first switch to cause the first switch to forward the probe packet to a next switch based on the first probe forwarding flow table;

acquiring the forwarding time of the first switch for forwarding the probe packet and executing forwarding control operation, wherein the forwarding control operation comprises: when receiving a feedback message sent by the next switch, determining a second probe forwarding flow table corresponding to the next switch based on the topology path, and sending the second probe forwarding flow table to the next switch, so that the next switch forwards the probe data packet based on the second probe forwarding flow table; acquiring the forwarding time of the next switch for forwarding the detection data packet;

repeatedly performing the forwarding control operation until the probe packet is forwarded to a last switch in the topological path;

receiving the detection data packet forwarded by the last switch, and recording the receiving time of the detection data packet;

and determining the time delay of the topological path according to the creation time, the forwarding time of the data packet forwarded by each switch in the topological path and the receiving time.

Further, acquiring a link bandwidth of a link included in the topology path includes:

respectively sending port information request messages to switches at two ends of a link included in the topology path, and acquiring the maximum throughput and the current used throughput of each switch port;

for each switch port, determining a difference between the maximum throughput and the current used throughput as a throughput difference;

and determining the minimum value of the throughput difference values of the switch ports at the two ends of the link as the bandwidth of the link.

In a second aspect, an embodiment of the present invention further provides a switch control apparatus, where the apparatus includes:

the control device integrated in the software defined SDN system comprises: the SDN system comprises: control equipment, a switching subsystem including a plurality of switches, and a plurality of terminal devices connected to the switching subsystem, the apparatus comprising:

the acquisition module is used for acquiring network topology information of the software definition system;

a determining module, configured to determine at least one target forwarding path according to the network topology information;

and the control module is used for generating a target forwarding flow table according to the target forwarding path, and sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal equipment according to the target forwarding flow table.

In a third aspect, an embodiment of the present invention further provides a control device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the switch control method according to any one of the embodiments of the present invention.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the switch control method according to any one of the embodiments of the present invention.

The embodiment of the invention obtains the network topology information of the software definition system; determining at least one target forwarding path according to the network topology information; and generating a target forwarding flow table according to the target forwarding path, sending the target forwarding flow table to a target switch in a switching subsystem so as to control the target switch to forward the service data of the terminal device according to the target forwarding flow table, monitoring the network topology information of the software definition system in real time, and configuring the target forwarding path according to the network topology information, so that the switch in the network topology is controlled to realize multi-path parallel transmission under the condition of not supporting a protocol by the terminal device.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a flowchart of a switch control method according to a first embodiment of the present invention;

figure 2 is a schematic diagram of the overall architecture of an SDN system;

fig. 3 is a flowchart of a switch control method according to a second embodiment of the present invention;

fig. 4 is a schematic structural diagram of a switch control apparatus in a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of a control device in a fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

Example one

Fig. 1 is a flowchart of a method for controlling an exchange according to an embodiment of the present invention, where the embodiment is applicable to a case where a target exchange is controlled to forward service data of a terminal device in a software defined system.

A Software Defined Network (SDN) is a novel Network innovation architecture, and a Network is managed in a centralized manner based on a layering idea of separating forwarding and control. The SDN network architecture can be divided into three layers from top to bottom, and the five parts are an application layer, a northbound interface, a control layer, a southbound interface and an infrastructure layer.

The control layer is a brain of the whole network, is located between the infrastructure layer and the application layer, abstracts bottom hardware equipment, enables application development of the application layer to access and call bottom network equipment in a transparent mode, mainly comprises control equipment, and commonly comprises OpenDaylight, ONOS, Ryu and the like.

The infrastructure layer is located at the lowest layer of the SDN system, and is similar to a conventional network, and is composed of some network devices such as routers, switches and intermediate devices. Unlike conventional networks, network devices in an SDN system are only responsible for handling the forwarding of data, and are not responsible for controlling and deciding what forwarding the data is going on. And the modules in the infrastructure layer, which are in charge of control and decision making, are extracted from the distributed equipment and are centralized on the control layer, and the control layer performs overall planning on the global network equipment and then issues the decision making to the infrastructure layer.

Fig. 2 is a schematic diagram of an overall architecture of an SDN system, as shown in fig. 2, the SDN system includes: a control device 10, a switching subsystem 20 comprising a plurality of switches 21, and a plurality of terminal devices 30 (only two terminal devices, terminal device a and terminal device B, are illustrated in fig. 2) connected to the switching subsystem. The switches in the switching subsystem 20 directly connected to any terminal device are edge switches, such as switch 1 and switch 6; the switches, both ends of which are connected to other switches respectively, are intermediate switches such as switch 2, switch 3, switch 4, and switch 5. The switch 21 comprises switch ports 22. Specifically, the terminal device a and the terminal device B perform service data interaction through a plurality of switches in the switching subsystem. The control device is used for determining the target forwarding path, generating a target forwarding flow table, sending the target forwarding flow table to a target switch related to the target forwarding path, and controlling the target switch to forward the service data of the terminal device to the terminal device or the next switch according to the target forwarding flow table.

The switch control method provided by the embodiment of the present invention may be executed by a switch control apparatus in the embodiment of the present invention, where the apparatus may be implemented in a software and/or hardware manner, and the switch control apparatus may be integrated in a control device of a software defined SDN system.

As shown in fig. 1, the method specifically includes the following steps:

s110, acquiring network topology information of the software defined system.

Wherein the network topology information includes: the network topology structure, the bandwidth of each topological path in the network topology structure and the time delay of each topological path.

The network topology structure refers to a form that each terminal device and each switch in the SDN system are connected with each other; common network topologies include: bus-type topologies, star topologies, ring topologies, and tree topologies. In the network topology structure, a transmission path formed by two terminal devices through a plurality of links is a topology path, and the links are connections between switch ports of two different switches. Generally, as shown in fig. 2, an SDN system includes a plurality of topological paths. The elements of the topology path include switches 21, switch ports 22, and links 23.

For example, as shown in fig. 2, one of the topology paths between the terminal device a and the terminal device B is terminal device a-switch 1-switch 2-switch 3-switch 6-terminal device B, and then the links included in the topology path include: switch 1-switch 2, switch 2-switch 3, and switch 3-switch 6.

For example, the manner of obtaining the bandwidth of the topological path may be to obtain the bandwidth of each link in the topological path, and determine the bandwidth of the topological path based on the minimum link bandwidth of each link in the topological path. The time delay of the obtained topological path can be sent to the switching subsystem by the control equipment, the data packet is fed back to the control equipment after being transmitted by any topological path, and the time delay of the topological path is calculated according to the difference value of the sending time and the receiving time.

And S120, determining at least one target forwarding path according to the network topology information.

The target forwarding path is a forwarding path selected from the multiple topology paths based on network topology information of the SDN system, and is used for transmitting service data. The number of target forwarding paths may be one or more and is less than the total number of topological paths in the SDN system.

Specifically, all topological paths between two terminal devices are determined based on a network topological structure of a software defined system, and a target forwarding path is determined from the topological paths according to the bandwidth and the time delay of each topological path.

And S130, generating a target forwarding flow table according to the target forwarding path, and sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal device according to the target forwarding flow table.

The target forwarding path is composed of multiple sections of links, two ends of each section of link are respectively connected with a switch, the switch connected with the start end of the link is a source switch, the switch connected with the end of the link is a target switch, and the target switch is the source switch.

The target forwarding flow table is used for indicating the receiving switch and the receiving switch port of the target switch for forwarding the service data. The target forwarding flow table includes: source switch information and destination switch information; the source switch information includes: a source switch identification and a source port number; the destination switch information includes: destination switch identification information and a destination port number.

Specifically, a target forwarding flow table corresponding to the source switch is generated based on source switch information and destination switch information of each link in the target forwarding path; and sending the target forwarding flow table to a corresponding target switch so as to control the target switch to forward the received service data generated by the terminal equipment to the target switch based on the target switch information in the target forwarding flow table.

According to the technical scheme, at least one target forwarding path can be determined according to the network topology information, and under the condition that a terminal device does not need to support a protocol, multipath parallel transmission can be achieved by controlling a switch in the network topology.

For example, as shown in fig. 2, if the target forwarding path is: the method comprises the following steps that terminal equipment A-switch 1-switch 2-switch 3-switch 6-terminal B, and a link included in a target forwarding path is a first link: switch 1-switch 2; the second link: switch 2-switch 3; and a third link: switch 3-switch 6.

And taking the source switch (switch 1) of the first link as a first target switch, generating a first target forwarding flow table, sending the first target forwarding flow table to the first target switch, and controlling the first target switch of the first link to forward the received service data of the terminal device A to the target switch (switch 2) of the first link. So that the first destination switch of the first link acts as the source switch (switch 2) of the next link, i.e. the second destination switch; and generating a second target forwarding flow table corresponding to a second target switch based on the source switch information and the target switch information of a second link in the target forwarding path, sending the second target forwarding flow table to the second target switch, controlling the second target switch of the second link to forward the received service data forwarded by the first target switch to the target switch (switch 3) of the second link until the service data is forwarded to a switch 6 connected with the terminal device B, and finally, forwarding the service data to the terminal device 6 by the switch 6 to finish the sending of the service data from the terminal device A to the terminal device B through a switch word subsystem.

According to the technical scheme of the embodiment, network topology information of a software definition system is acquired; determining at least one target forwarding path according to the network topology information; and generating a target forwarding flow table according to the target forwarding path, sending the target forwarding flow table to a target switch in a switching subsystem so as to control the target switch to forward the service data of the terminal device according to the target forwarding flow table, monitoring the network topology information of the software definition system in real time, and configuring the target forwarding path according to the network topology information, so that the switch in the network topology is controlled to realize multi-path parallel transmission under the condition of not supporting a protocol by the terminal device.

Example two

Fig. 3 is a flowchart of a switch control method in the second embodiment of the present invention, and the present embodiment optimizes network topology information based on the above embodiments.

As shown in fig. 3, the method of this embodiment specifically includes the following steps:

s210, acquiring a network topology structure of the software defined system.

The network topology structure of the software defined system can be obtained by acquiring the three elements.

Specifically, a topology Discovery Unit of the control device senses an available switch in the SDN system in real time, and constructs a Link Layer Discovery Protocol (LLDP) Data packet, where the LLDP Data packet provides a standard Link Layer Discovery manner, and may organize Information such as a main capability, a Management address, a device identifier, and an interface identifier of a local node into different TLVs (Type/Length/Value), and encapsulate the TLVs (Type/Length/Value) into an LLDPDU (Link Layer Discovery Protocol Data Unit), where the LLDPDU may publish the Information to an adjacent node directly connected to the local node, and the adjacent node may store the Information in a standard MIB (Management Information Base) form after receiving the Information, so as to enable a network Management system to query and determine a communication status of a Link.

When the system is started, a network topology model is firstly established and stored, and the network topology discovery operation is periodically carried out in the later system operation process, so that the change information of the network topology is obtained in real time. If the topology changes during the operation of the system, the network topology needs to be acquired again. The network topology established in this step provides a basis for the correct operation of the path selection.

Illustratively, fig. 4 is a schematic diagram of a discovery link, as shown in fig. 4, a control device sends an LLDP packet to a switch through a switch port connected to the control device, the switch forwards the LLDP packet to a next switch through a port connected to the switch, and the next switch returns the LLDP packet to the control device. After receiving the LLDP data packet, the control device parses it, and can obtain the source switch and source port number of the link from the switch identification field and port field in the LLDP data packet, and can obtain the destination switch address and port number through the received message, thereby determining the connection information of a link, and repeats the above processes to complete topology discovery of all switches, and collects the connection information of all switches connected between two terminal devices. And determining the network topology of the software defined system according to the connection information of all the switches.

S220, determining a plurality of topological paths based on the network topological structure.

Specifically, links included in the network topology structure may determine multiple topology paths, where each topology path includes multiple links connected end to end, and enables service data interaction between two terminal devices.

And S230, acquiring the time delay of the topological path and the link bandwidth of the link included in the topological path.

Specifically, based on the topology path determined by the network topology structure, the monitoring unit in the control device monitors the time delay of each topology path and the link bandwidth of the link included in the topology path in real time, and stores the monitored information in the control device in real time as the basis for path selection.

For example, the bandwidth monitoring unit may estimate the bandwidth of the path by counting the throughput of the ports on both sides of the link in real time; the delay monitoring unit can enable the system to reliably and effectively determine the delay of each link in the operation process of the network topology under the condition that the network occupation is very limited through a monitoring mechanism based on the OpenFlow protocol.

S240, determining a preset number of forwarding paths with minimum time delay ascending sequence according to the time delay of each topological path; the preset number is used to represent the maximum number of target forwarding paths.

The preset number of the forwarding paths is the maximum number of the target forwarding paths, namely the finally determined target forwarding paths do not exceed the preset number; the setting can be performed according to the user requirement and the system parameter, for example, by writing a preset number as a parameter into a configuration file.

Specifically, the path selection unit in the control device is controlled to perform increasing sequencing on each topological path based on the time delay of each topological path monitored by the monitoring unit, and the forwarding paths with the minimum time delay increasing sequencing and the preset number are determined.

And S250, determining at least one target forwarding path from the forwarding paths based on the time delay of each topological path and the link bandwidth of the included link.

Specifically, when the preset number of forwarding paths with the smallest time delay ascending order is determined, the target forwarding path needs to be determined by combining the bandwidth of the forwarding path. The number of the target forwarding paths can be one or more, and is determined by the delay difference between the forwarding paths, and the delay difference can be measured by a delay coefficient.

If the delay difference between multiple forwarding paths is large, the effect of aggregating the bandwidths of these multiple forwarding paths is worse than selecting a single forwarding path. Therefore, a maximum delay imbalance concept is introduced, that is, when the delay imbalance coefficients of a plurality of paths are higher than a threshold value, the delay difference is considered to be too high to provide the bandwidth advantage of path aggregation, so that single-path transmission is selected. And if the delay difference of the multiple forwarding paths is smaller, determining the multiple forwarding paths as target forwarding paths, and transmitting the service data by using the aggregated bandwidth of each target forwarding path.

And S260, generating a target forwarding flow table according to the target forwarding path, and sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal device according to the target forwarding flow table.

Illustratively, after receiving a target forwarding flow table, a target switch determines a switch port for forwarding service data, calculates the service data to be distributed by each switch port according to the target forwarding flow table, and sends a control instruction to the switch port to control the switch port to forward the service data.

The method for calculating the service data to be distributed by each switch port may adopt a weighted round robin scheduling algorithm, specifically, the number of data packets of each path to be distributed in a polling manner. To maximize performance, an optimal amount of data should be distributed over different target forwarding paths, neither overloading congested paths, nor ensuring that the available bandwidth of the target forwarding paths is fully utilized. In order to reduce the problem of packet disorder in the high-speed transmission process, when service data is sent, a method of sending a plurality of service data packets instead of a single service data packet by polling each time is adopted, wherein the number of the service data packets is in direct proportion to the bandwidth and the maximum delay coefficient, namely, the larger the bandwidth and the maximum delay coefficient, the more the service data packets sent by polling each time are, and thus, the service data packets at the receiving end part can be ensured to arrive in sequence as much as possible.

For a new switch that receives service data forwarded by a target switch during multipath transmission, the new switch may receive service data packets forwarded by multiple target switches at the same time, and therefore the target switch needs to further configure a data packet receiver for reordering the received service data packets from multiple paths, so as to avoid the influence of out-of-order data packets on transmission performance. The packet receiver comprises the packet: a buffer unit and a data packet sorting unit.

The packet buffer unit is responsible for maintaining a record of the next expected sequence number for each data flow and maintaining a buffer pool in the switch for each data flow, and for temporarily storing packets that are not suitable for immediate forwarding in the buffer pool.

And the data packet sequencing unit is responsible for sequencing and forwarding the service data packet positioned in the data packet cache unit and the newly received service data packet according to a packet rearrangement algorithm. The rule of the packet rearrangement algorithm is as follows: and when the sequence number of the service data packet is matched with the expected sequence number, forwarding the service data packet, sequentially searching the service data packets in the cache pool, forwarding the service data packet with the sequence number smaller than the current expected sequence number, otherwise, storing the service data packet into the cache pool, representing the service data packet to be sent, sequencing the service data packets according to the sequence numbers, possibly transmitting the service data packets from multiple paths, and enabling the sequence number larger than the sequence number of the currently expected service data packet, namely, the service data packet sent earlier arrives later, updating the expected sequence number, and waiting for the next service data packet.

According to the technical scheme of the embodiment, the network topology structure of the software definition system is obtained; determining a plurality of topological paths based on the network topology; acquiring time delay of a topological path and link bandwidth of a link included in the topological path; determining a preset number of forwarding paths with minimum time delay ascending sequence according to the time delay of each topological path; determining at least one target forwarding path from the forwarding paths based on the time delay of each topological path and the link bandwidth of the included link; and generating a target forwarding flow table according to the target forwarding path, sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal device according to the target forwarding flow table, monitoring the network topology information of the software definition system in real time, and configuring the target forwarding path according to the network topology information, so that the switch in the network topology is controlled to realize multi-path parallel transmission under the condition of not supporting a protocol by the terminal device. In addition, bandwidth aggregation of multiple paths is realized, transmission delay caused by difference of the multiple paths is reduced, and throughput and utilization rate of redundant links are improved.

Optionally, determining at least one target forwarding path from the predetermined number of forwarding paths based on the time delay of each topology path and the link bandwidth of the included link, includes:

for each forwarding path, determining available bandwidth of the forwarding path based on link bandwidth of the included link;

Wherein the available bandwidth of the forwarding path is determined by the minimum value of the bandwidth of the link included in the forwarding path and whether the link belongs to a common link of the multiple paths. The first preset bandwidth value may be determined according to actual requirements, and may be zero, for example, or the minimum bandwidth available for the forwarding path to forward data.

The delay coefficient of the forwarding path is used to represent a ratio of the delay of the forwarding path to the minimum delay corresponding to the preferred forwarding path, where the minimum delay corresponding to the preferred forwarding path may be considered as 1, so as to reflect a delay difference between the forwarding path and the preferred forwarding path.

Specifically, the available bandwidth of the forwarding path is determined based on the link bandwidth of the link included in the forwarding path, and the forwarding path with the minimum time delay and the available bandwidth greater than a first preset bandwidth value is determined as the preferred forwarding path; the path may be considered as an optimal forwarding path among all forwarding paths, and the optimal forwarding path is taken as one of the target forwarding paths. In addition, the forwarding path with the delay coefficient larger than the preset coefficient and the available bandwidth larger than the first preset bandwidth value is determined as an alternative forwarding path, and the alternative forwarding path is also used as a target forwarding path, so that the parallel transmission of a plurality of paths is realized.

The preset coefficient can be determined according to the delay requirement of service data transmission, and the difference between the delays of the alternative forwarding path and the preferred forwarding path is within a preset range, so that the transmission delay caused by the difference of multiple paths is reduced.

It should be noted that, if there is no candidate forwarding path that meets the condition, the system cannot implement multi-path parallel transmission, and single-path transmission in which the target forwarding path is the preferred forwarding path is implemented.

Optionally, determining an available bandwidth of the forwarding path based on the link bandwidth of the included link includes:

wherein the second available bandwidth is determined according to the minimum link bandwidth of each link included in the second forwarding path and/or the bandwidth of the common link.

The unique link refers to a link belonging to only one forwarding path, such as the link between the switch 1 and the switch 2 and the link between the switch 2 and the switch 3 (belonging to only the forwarding path 1: switch 1-switch 2-switch 3-switch 6) and the link between the switch 4 and the switch 5 and the link between the switch 5 and the switch 6 (belonging to only the forwarding path 2: switch 1-switch 4-switch 5-switch 6) shown in fig. 2. The common link refers to a link belonging to multiple forwarding paths at the same time, and the link between the switch 1 and the switch 4 shown in fig. 2 belongs to the forwarding path 2 at the same time: switch 1-switch 4-switch 5-switch 6 and forwarding path 3: switch 1-switch 4-switch 3-switch 6.

Specifically, for a first forwarding path including all unique links, for example, the forwarding path 1 shown in fig. 2 includes all unique links: switch 1-switch 2-switch 3-switch 6, the first available bandwidth being link 1: switch 1-switch 2, link 2: switch 2-switch 3 and link 3: minimum link bandwidth in switch 3-switch 6.

For a plurality of second forwarding paths containing common links, such as those shown in fig. 2 containing common links: forwarding path 2 and forwarding path 3 of the link between switch 1 and switch 4. Wherein, the forwarding path 2: switch 1-switch 4-switch 5-switch 6 and forwarding path 3: switch 1-switch 4-switch 3-switch 6. If the delay of the forwarding path 2 is smaller than the delay of the forwarding path 3, the second available bandwidth of the forwarding path 2 is determined first, and the method for determining the second available bandwidth of the forwarding path 2 is as follows: the minimum link bandwidth of the forwarding path 2 is determined according to the link bandwidths of all links in the forwarding path 2 (including the link bandwidth of the common link), and the minimum link bandwidth of the forwarding path 2 is determined as the second available bandwidth of the forwarding path 2.

Then, a second available bandwidth of the forwarding path 3 is determined, and the method for determining the second available bandwidth of the forwarding path 3 is as follows: determining the minimum link bandwidth of the forwarding path 3 according to the link bandwidths of all links in the forwarding path 3, determining the link bandwidth of the common link in the forwarding path 3 obtained by subtracting the minimum link bandwidth of the forwarding path 2 from the link bandwidth of the common link, and determining the minimum link bandwidth (including the link bandwidth of the common link in the forwarding path 3) in all the link bandwidths in the forwarding path 3 as the second available bandwidth of the forwarding path 3.

It will be appreciated that if the common link bandwidth is the minimum link bandwidth of forwarding path 2, then the available bandwidth of forwarding path 3 is zero.

If the common link also belongs to the forwarding path 4, the second available bandwidth of the forwarding path 4 is calculated in a similar manner to the second available bandwidth of the forwarding path 3. Subtracting the minimum link bandwidth of the forwarding path 2 from the link bandwidth of the common link, and subtracting the minimum link bandwidth of the forwarding path 3 to obtain a difference value, to obtain the link bandwidth of the common link on the forwarding path 4, and determining the minimum link bandwidth (including the link bandwidth of the common link on the forwarding path 4) in all the link bandwidths on the forwarding path 4 as the second available bandwidth of the forwarding path 4.

Optionally, obtaining the time delay of the topology path includes:

creating a probe packet, the probe packet comprising: creating a first detection forwarding flow table corresponding to the first switch of the time and topology path;

sending the probe data packet to a first switch so that the first switch forwards the probe data packet to a next switch based on a first probe forwarding flow table;

acquiring the forwarding time of the first switch for forwarding the detection data packet and executing forwarding control operation, wherein the forwarding control operation comprises the following steps: when receiving a feedback message sent by the next switch, determining a second detection forwarding flow table corresponding to the next switch based on the topology path, and sending the second detection forwarding flow table to the next switch so that the next switch forwards a detection data packet based on the second detection forwarding flow table; acquiring the forwarding time of the next switch for forwarding the detection data packet;

repeatedly executing forwarding control operation until the detection data packet is forwarded to the last switch in the topological path;

receiving a detection data packet forwarded by the last switch, and recording the receiving time of the detection data packet;

Specifically, an ethernet frame based on the OpenFlow protocol is created as a probe packet, and the round-trip time of the probe packet on a path is used to estimate the delay of the path. The probe data packet includes: detecting the creation time of a data packet and a first detection forwarding flow table corresponding to a first switch of a topology path; the first probe forwarding flow table is used for instructing the first switch to forward the probe data to the next switch. And acquiring the forwarding time of the first switch for forwarding the detection data packet and executing forwarding control operation to control the next switch to continue forwarding the detection data packet.

Wherein the forwarding control operation comprises: and when receiving a feedback message sent by the next switch, determining a second detection forwarding flow table corresponding to the next switch based on the topology path, and sending the second detection forwarding flow table to the next switch, so that the next switch forwards the detection data packet based on the second detection forwarding flow table. And after each switch forwards the detection data packet, acquiring the forwarding time for forwarding the detection data packet.

And repeatedly executing the forwarding control operation until the detection data packet is forwarded to the last switch in the topological path.

Therefore, the repeatedly executed forwarding control operation can control the probe data packet to be forwarded from the first switch to the last switch of the topology path, receive the probe data packet forwarded by the last switch, and record the receiving time of the received probe data packet; therefore, the sending time of the controller, the forwarding time of each switch and the time for the controller to receive the data packet can be obtained by analyzing the detection data packet, and the time delay of the topological path is determined.

Specifically, the feedback message sent by the next switch may be that when the next switch receives the probe packet forwarded by the previous switch, because the probe packet cannot be forwarded without matching the probe forwarding flow table with the next switch, a feedback message is sent to the controller to request to control the issuing of the probe forwarding flow table, instead of forwarding the probe packet to all switch ports. But it is inevitable that a delay will occur in this process.

Optionally, obtaining the link bandwidth of the link included in the topology path includes:

respectively sending port information request messages to switches at two ends of a link included in a topology path, and acquiring the maximum throughput and the current used throughput of each switch port;

for each switch port, determining the difference value between the maximum throughput and the current used throughput as the throughput difference value;

Where throughput refers to the amount of data (measured in bits, bytes, packets, etc.) successfully transmitted per unit time to a port.

Specifically, a port information request message is periodically sent to each switch, a port information message returned by the switch is acquired, the port information message includes flow count information and maximum throughput of a current port, the current used throughput is calculated based on a flow count difference and cycle time of the port in a statistical cycle, and for each switch port, a difference between the maximum throughput and the current used throughput is determined as a throughput difference, and the throughput difference is used for reflecting the number of data which can be transmitted by the port. The bandwidth of the link is the minimum value of the difference of the throughput of the switch ports at the two ends.

EXAMPLE III

Fig. 4 is a schematic structural diagram of a switch control apparatus according to a third embodiment of the present invention. The present embodiment is applicable to a case where a target switch is controlled to forward service data of a terminal device in a software-defined system, and the apparatus may be implemented in software and/or hardware, and may be integrated in a control device of a software-defined SDN system, where the SDN system includes: the system comprises a control device, a switching subsystem comprising a plurality of switches, and a plurality of terminal devices connected to the switching subsystem. As shown in fig. 4, the switch control apparatus specifically includes: an acquisition module 410, a determination module 420, and a control module 430.

The acquiring module 410 is configured to acquire network topology information of the software defined system;

a determining module 420, configured to determine at least one target forwarding path according to the network topology information;

the control module 430 is configured to generate a target forwarding flow table according to the target forwarding path, and send the target forwarding flow table to a target switch in the switching subsystem, so as to control the target switch to forward service data of a terminal device according to the target forwarding flow table.

Optionally, the network topology information includes:

the network topology structure of the software defined system, the bandwidth of each topological path in the network topology structure and the time delay of each topological path; wherein the topological path includes a plurality of segments of links formed between two switch ports;

correspondingly, the obtaining module includes:

a network topology structure obtaining unit, configured to obtain a network topology structure of the software defined system;

a topological path determination unit for determining a plurality of topological paths based on the network topology;

and the acquisition unit is used for acquiring the time delay of the topological path and the link bandwidth of the link contained in the topological path.

Optionally, the determining module includes:

a forwarding path determining unit, configured to determine, according to the time delay of each topology path, a preset number of forwarding paths with the smallest time delay increment order; the preset number is used for representing the maximum number of the target forwarding paths;

and the target forwarding path determining unit is used for determining at least one target forwarding path from the forwarding paths based on the time delay of each topological path and the link bandwidth of the included link.

Optionally, the target forwarding path determining unit includes:

an available bandwidth determining subunit, configured to determine, for each of the forwarding paths, an available bandwidth of the forwarding path based on a link bandwidth of the included link;

a preferred forwarding path determining subunit, configured to determine, as a preferred forwarding path, a forwarding path with the minimum time delay and an available bandwidth greater than a first preset bandwidth value;

a delay coefficient determining subunit, configured to determine delay coefficients of the forwarding paths other than the preferred forwarding path, respectively;

the alternative forwarding path determining subunit is configured to determine, as an alternative forwarding path, a forwarding path for which the delay coefficient is greater than the preset coefficient and the available bandwidth is greater than a first preset bandwidth value;

and the target forwarding path determining subunit is used for determining the alternative forwarding path and the preferred forwarding path as the target forwarding path.

Optionally, the available bandwidth determining subunit is specifically configured to:

Optionally, the obtaining unit is specifically configured to:

Optionally, the obtaining unit is further configured to:

The product can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

Example four

Fig. 5 is a block diagram of a control apparatus according to a fourth embodiment of the present invention, as shown in fig. 5, the control apparatus includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the control device may be one or more, and one processor 410 is taken as an example in fig. 5; the processor 410, the memory 420, the input device 430 and the output device 440 in the control apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 5.

The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the switch control method in the embodiment of the present invention (for example, the acquisition module 310, the determination module 320, and the control module 330 in the switch control apparatus). The processor 410 executes various functional applications of the control device and data processing by executing software programs, instructions, and modules stored in the memory 420, that is, implements the switch control method described above.

The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 420 may further include memory located remotely from the processor 410, which may be connected to the control device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input means 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the control device. The output device 440 may include a display device such as a display screen.

EXAMPLE five

Fifth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a switch control method according to any embodiment of the present invention: acquiring network topology information of a software definition system; determining at least one target forwarding path according to the network topology information; and generating a target forwarding flow table according to the target forwarding path, and sending the target forwarding flow table to a target switch in the switching subsystem so as to control the target switch to forward the service data of the terminal equipment according to the target forwarding flow table.

Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A switch control method applied to a control device of a software defined SDN system, the SDN system comprising: a control device, a switching subsystem comprising a plurality of switches, and a plurality of terminal devices connected to the switching subsystem, the method comprising:

acquiring network topology information of a software definition system;

2. The method of claim 1, wherein the network topology information comprises:

acquiring a network topology structure of a software defined system;

determining a plurality of topological paths based on the network topology;

3. The method of claim 2, wherein determining at least one target forwarding path based on the network topology information comprises:

4. The method of claim 3, wherein the determining at least one target forwarding path from a preset number of the forwarding paths based on the latency of each of the topology paths and the link bandwidth of the included link comprises:

5. The method of claim 4, wherein determining the available bandwidth of the forwarding path based on the latency and the link bandwidth of the included links comprises:

for a first forwarding path which all contains a unique link, determining a minimum link bandwidth of the contained link as a first available bandwidth of the first forwarding path;

6. The method of claim 2, wherein obtaining the latency of the topological path comprises:

sending the probe packet to a first switch to cause the first switch to forward the probe packet to a next switch based on the first probe forwarding flow table;

7. The method according to claim 2, wherein obtaining the link bandwidth of the link included in the topological path comprises:

8. A switch control apparatus, wherein a control device integrated in a software defined SDN system includes: the SDN system comprises: control equipment, a switching subsystem including a plurality of switches, and a plurality of terminal devices connected to the switching subsystem, the apparatus comprising:

9. A control device applied to a software defined SDN system, the SDN system comprising: the system comprises a control device, a switching subsystem comprising a plurality of switches and a plurality of terminal devices connected with the switching subsystem; the control apparatus includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the switch control method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the switch control method according to any one of claims 1 to 7.