CN117240748A

CN117240748A - Communication link detection method and device

Info

Publication number: CN117240748A
Application number: CN202210640136.3A
Authority: CN
Inventors: 李�杰; 刘世兴; 冀智刚
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-06-08
Filing date: 2022-06-08
Publication date: 2023-12-15
Also published as: WO2023236874A1

Abstract

The application discloses a method and a device for detecting a communication link, and relates to the technical field of communication. When the method detects whether the communication link of the network is abnormal, the bandwidth resources of the nodes in the network can be saved. The method is applied to the target access equipment, and comprises the following steps: determining a data stream corresponding to a stream table item of which the first data volume is not updated within a preset duration as a suspected abnormal stream; generating a first message for determining whether a communication link transmitting the suspected abnormal flow is abnormal based on flow information of the suspected abnormal flow; and sending a first message to the source access equipment sending the suspected abnormal flow. In this way, the source access device that sends the suspected abnormal flow can determine whether the communication link that transmits the suspected abnormal flow is abnormal based on the first data volume of the suspected abnormal flow carried in the received first message and the data volume of the sent suspected abnormal flow. The first data size of the suspected abnormal flow is the data size of the suspected abnormal flow received by the target access device.

Description

Communication link detection method and device

Technical Field

The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for detecting a communication link.

Background

There are various types of communication link anomalies in the network, such as physical link failures between nodes in the network, route black holes caused by routing table configuration anomalies/errors, link congestion caused by traffic maldistribution or traffic bursts, and the like. Communication link anomalies may affect the performance of the network, such as affecting the throughput of nodes in the network, or increasing the latency of data transmission in the network, and thus the user experience.

Currently, whether a link is abnormal or not may be detected by periodically sending bidirectional forwarding detection (bidirectional forwarding detection, BFD) messages to nodes at both ends of a communication link to be detected (hereinafter referred to as a link to be detected). For example, when the end node of the detected link does not receive the BFD packet sent by the opposite node within a preset period of time, the link is determined to be abnormal.

However, when detecting whether the communication link of the network is abnormal through the BFD packet, each node in the network needs to generate the BFD packet, and periodically send the BFD packet to the correspondent node, which continuously consumes bandwidth resources of the nodes in the network.

Disclosure of Invention

The application provides a method and a device for detecting a communication link, which can save bandwidth resources of nodes in a network when detecting whether the communication link of the network is abnormal or not.

In a first aspect, the present application provides a method for detecting a communication link, where the method is applied to a destination access device. The method comprises the following steps: and determining a suspected abnormal flow, wherein the suspected abnormal flow is a data flow corresponding to a flow table item of which the first data volume is not updated within a preset time period. The stream table item is created by the target access device after receiving the first message of the data stream and is used for recording stream information of the data stream. The flow information of the data flow may comprise a first data amount of the data flow, the first data amount of the data flow being a data size of the data flow that has been received by the destination access device. And generating a first message comprising a first data volume of the suspected abnormal flow based on the flow information of the suspected abnormal flow. And sending a first message to the source access equipment for sending the suspected abnormal flow, wherein the first message is used for determining whether a communication link for transmitting the suspected abnormal flow is abnormal.

When the method provided by the application is used for detecting the communication link, the destination access equipment in the network system only needs to monitor the data volume of the received data flow, so that the data flow which does not increase the data volume within the preset time period is determined to be a suspected abnormal flow in time, and the received data volume of the suspected abnormal flow is notified to the source access equipment. Further, the source access device may determine whether the communication link transmitting the suspected abnormal flow is abnormal based on the difference between the amount of data that has been transmitted and received by the suspected abnormal flow. It can be seen that the method does not require that every node in the network system generate a communication link detection message and send the messages to each other. Therefore, the method can save bandwidth resources of nodes in the network system.

In addition, when the destination access device in the method of the application determines whether the updated preset duration of the first data volume recorded in the flow table entry of the data flow is set to be a duration of hundred microseconds, whether the communication line for transmitting the data flow is abnormal or not can be detected within the duration of hundred microseconds. Further, the link convergence time of the communication link can be controlled at the millisecond level or the sub-millisecond level. Therefore, compared with the method that only the link convergence time can be controlled to be in the level of hundred milliseconds (generally 200 milliseconds) when the communication link is detected through the BFD message, the method provided by the application greatly shortens the link convergence time of the communication link, thereby reducing the time delay of data transmission of a network system and further improving the user experience.

In addition, the method provided by the application realizes the detection of whether the communication link used for transmitting the data stream is abnormal or not at the data layer. For a data stream, the method provided by the application is to determine whether a communication link transmitting the data stream is abnormal by detecting a difference between a transmitted data amount of the data stream at a source access device and a received data amount of the data stream at a destination access device in an access layer of a communication network. Therefore, for the fault that the routing black hole appears in the communication network in the data transmission process, so that the target access equipment expected by the user cannot receive the data stream, the method provided by the embodiment of the application can be also applied.

In one possible design, the determining the suspected abnormal flow includes: and detecting flow information in the flow table item according to the first period. And when the data volume in the stream information of the data stream is not updated within the preset time, determining that the data stream is a suspected abnormal stream.

Through the possible design, the target access device can timely determine the data stream with the data volume not increased in the preset time period as the suspected abnormal stream.

In another possible design, the method further includes: and receiving a second message sent by the source access device and indicating to prolong the period of the stream information of the detection data stream. And adjusting the period of the stream information of the detection data stream from the first period to the second period according to the second message. Wherein the second period is greater than the first period.

In another possible design, the method further includes: and receiving indication information sent by the source access device and indicating to reduce the period of the stream information of the detection data stream. The period of the stream information of the detected data stream is adjusted from the second period to the third period according to the instruction information. Wherein the third period is less than the second period. Alternatively, the third period may be the same as the first period described above, or may be different from the first period described above.

Through the two possible designs, the target access device can flexibly set the period of the flow information of the detection data flow under the instruction of the source access device, so that the length of the preset duration can be flexibly adjusted.

In another possible design, the sending the first packet to the source access device that sends the suspected abnormal flow includes: and sending the first message to the source access device through one or more uplink ports of the destination access device.

Through the possible design, the target access device can send the first message to the source access device sending the suspected abnormal flow through the plurality of uplink ports, namely, the target access device sends the first message to the source access device through the plurality of upper nodes. In other words, the communication link for transmitting the first message from the destination access device to the source access device comprises a plurality of communication links. In this way, even if a communication link among a plurality of communication links used for transmitting the first message is abnormal/faulty, the method provided by the application can ensure that the destination access device transmits the first message to the source access device through other communication links.

In another possible design, if the flow information of the data flow further includes the latest packet sequence number of the data flow, the latest packet sequence number of the data flow is the sequence number of the latest packet of the data flow that has been received by the destination access device. In this case, the first message further includes a latest message sequence number of the suspected abnormal flow, and further the first message further indicates the source access device to send, to the destination access device, a message in the suspected abnormal flow, which is not received by the destination access device, based on the latest message sequence number of the suspected abnormal flow after the communication link for transmitting the suspected abnormal flow is restored to be normal.

By means of the possible design, the latest message sequence number of the suspected abnormal flow carried in the first message can indicate the source access device to accurately determine messages which are sent out by the source access device and are not received by the destination access device due to abnormal/fault of the communication link, and the source access device can send the messages to the destination access device through the recovered communication link, so that the situation of packet loss of data is avoided.

In another possible design, the destination access device and the source access device are nodes of a leaf layer in a communication network, where the communication network further includes a backbone layer. Wherein each node on a leaf layer in the communication network is in full-connection communication with a node on a backbone layer in the communication network.

In another possible design, the destination access device and the source access device are nodes of an access layer in a communication network, where the communication network further includes a backbone layer and a core layer. Each node of the access layer in the communication network is connected with a part of nodes of the backbone layer in the communication network for communication, and each node of the backbone layer in the communication network is connected with a part of nodes of the core layer in the communication network for communication.

With the two possible designs, when the access device detects the communication link abnormality and switches the route, in the network in the two possible designs, the route after the access device is switched can ensure that the communication link detected to be abnormal is not passed.

In a second aspect, the present application further provides a method for detecting a communication link, where the method is applied to a source access device. The method comprises the following steps: and receiving a first message which is sent by the target access equipment and used for determining whether the communication link for transmitting the suspected abnormal flow is abnormal. The first message includes a first data amount of the suspected abnormal flow, wherein the first data amount of the suspected abnormal flow is a data size of the suspected abnormal flow received by the target access device. Determining whether a difference between the amount of data of the transmitted suspected abnormal flow and the first amount of data of the suspected abnormal flow is greater than a threshold. If the difference is greater than a threshold, determining that the communication link for transmitting the suspected abnormal stream is abnormal.

When the method provided by the application is used for detecting the communication link, the source access equipment in the network system can determine whether the communication link for transmitting the suspected abnormal flow is abnormal or not only by the data volume of the transmitted suspected abnormal flow and the data volume of the received suspected abnormal flow carried by the target access equipment in the received first message. It can be seen that the method does not require that every node in the network system generate a communication link detection message and send the messages to each other. Therefore, the method can save bandwidth resources of nodes in the network system.

In addition, the method provided by the application realizes the detection of whether the communication link used for transmitting the data stream is abnormal or not at the data layer. For a data stream, the method provided by the application is to determine whether a communication link for transmitting the data stream is abnormal or not by detecting the difference between the transmitted data amount of the data stream at the source access device side and the received data amount at the destination access device in an access layer of a communication network. Therefore, for the fault that the routing black hole appears in the communication network in the data transmission process, so that the target access equipment expected by the user cannot receive the data stream, the method provided by the embodiment of the application can be also applied.

In one possible design, before determining whether the difference between the transmitted data amount of the suspected abnormal flow and the first data amount of the suspected abnormal flow is greater than a threshold, the method further includes: and determining whether the stopping time of the message of stopping sending the suspected abnormal flow by the source access equipment is less than a preset time. If the stopping time period is less than the predetermined time period, it is determined whether the difference is greater than a threshold.

In one possible design, the method further includes: and if the stopping time period is longer than the preset time period, sending a second message indicating to prolong the period of the flow information for detecting the suspected abnormal flow to the target access equipment.

In the two possible designs, when determining whether the communication link transmitting the suspected abnormal flow is abnormal, the factor of whether the suspected abnormal flow is cutoff is considered. It should be understood that when the time period of stopping the source access device from sending the message of the suspected abnormal flow is greater than or equal to the predetermined time period, the suspected abnormal flow is a flow break. When the suspected abnormal flow is not a flow break, i.e., the suspected abnormal flow is a normally transmitted data flow, in this case, it may be determined whether the communication link transmitting the suspected abnormal flow is abnormal based on the amount of data that has been transmitted and received by the suspected abnormal flow. And when the suspected abnormal flow is cut off, the source access equipment does not send a message of the suspected abnormal flow to the target access equipment in a period of time. Correspondingly, the target access device can not receive the message of the suspected abnormal flow any more in a period of time. Therefore, for the flow information recorded in the flow table entry of the suspected abnormal flow, the destination access device does not need to continue to detect the flow information of the suspected abnormal flow at a higher frequency (i.e. with a shorter period) to determine whether the first data volume of the suspected abnormal flow is updated. Furthermore, in order to save the resource consumption caused by the flow information of the suspected abnormal flow detected by the target access device, the source access device may generate a second message indicating to extend the period of detecting the flow information of the suspected abnormal flow, and send the second message to the target access device, so that the target access device may extend the period of detecting the flow information of the suspected abnormal flow, so as to save the excessive resource consumption caused by the flow information of the high-frequency detected suspected abnormal flow.

In another possible design, the method further includes: and when the message of the suspected abnormal flow is sent to the target access equipment again after the stopping time, sending indication information for indicating to reduce the period of the flow information for detecting the suspected abnormal flow to the target access equipment.

Through the possible design, when the source access device starts to send the message of the suspected abnormal flow to the target access device again, the target access device can reduce the period of detecting the flow information of the suspected abnormal flow, so that the purpose of reducing whether the first data volume recorded in the flow table entry is updated or not is achieved. In this way, the destination access device can quickly determine the suspected abnormal flow based on the detection result, and the source access device can determine whether the communication link transmitting the suspected abnormal flow is abnormal based on the flow information of the suspected abnormal flow announced by the first message. Therefore, the period of the stream information of the suspected abnormal stream detected by the target access device is reduced, and the speed of detecting whether the communication link is abnormal can be increased, so that the link convergence time of the communication link is shortened.

In another possible design, if the first message further includes a last message sequence number of the suspected abnormal flow, the last message sequence number of the suspected abnormal flow is a sequence number of a last message of the suspected abnormal flow that has been received by the target access device. The method further comprises: and after the communication link for transmitting the suspected abnormal flow is recovered to be normal, starting from the next message of the message indicated by the latest message serial number in the suspected abnormal flow, and transmitting the message of the suspected abnormal flow to the target access equipment.

Through the possible design, the source access device can accurately determine the messages which are sent out but not received by the destination access device due to the abnormal/fault of the communication link according to the latest message sequence number of the suspected abnormal flow carried in the first message, and then the source access device can send the messages to the destination access device through the recovered communication link, so that the situation of packet loss of data is avoided.

In another possible design, the destination access device and the source access device are nodes of a leaf layer in a communication network, where the communication network further includes a backbone layer. Wherein each node on the leaf layer and a node on the backbone layer in the communication network are in full-connection communication.

In a third aspect, the present application provides a detection apparatus for a communication link.

In a possible design, the detection device is configured to perform any of the methods provided in the first aspect. The present application may provide a method according to any one of the first aspect, wherein the detecting device is divided into functional modules. For example, each functional module may be divided corresponding to each function, or two or more functions may be integrated in one processing module. The present application may be divided into a determination unit, a generation unit, a transmission unit, and the like by functions, for example. The description of possible technical solutions and beneficial effects executed by each of the above-divided functional modules may refer to the technical solutions provided by the above first aspect or the corresponding possible designs thereof, and will not be repeated herein.

In another possible design, the detection device is configured to perform any of the methods provided in the second aspect. The present application may provide a method according to any one of the second aspect, wherein the detecting device is divided into functional modules. For example, each functional module may be divided corresponding to each function, or two or more functions may be integrated in one processing module. The present application may, for example, divide the detection means into a receiving unit, a determining unit, etc. by function. The description of possible technical solutions and beneficial effects executed by each of the above-divided functional modules may refer to the technical solutions provided by the above second aspect or the corresponding possible designs thereof, and will not be repeated herein.

In another possible design, the detection device includes: a network interface and one or more processors to receive or transmit data over the network interface, the one or more processors being configured to read program instructions stored in the memory to cause the detection apparatus to perform any one of the methods as provided in the first aspect and any one of the possible designs thereof, or to perform any one of the methods as provided in the second aspect and any one of the possible designs thereof.

In a fourth aspect, the present application provides a network system comprising a destination access device and a source access device. Wherein the destination access device is adapted to perform any one of the methods as provided in the first aspect and any one of the possible designs thereof, and the source access device is adapted to perform any one of the methods as provided in the second aspect and any one of the possible designs thereof.

In a fifth aspect, the application provides a computer readable storage medium comprising program instructions which, when run on a computer or processor, cause the computer or processor to perform any of the methods provided in any of the possible implementations of the first or second aspects.

In a sixth aspect, the application provides a computer program product which, when run on a detection apparatus of a communication link, causes any one of the methods provided in any one of the possible implementations of the first or second aspects to be performed.

In a seventh aspect, the present application provides a chip system, comprising: a processor for calling from a memory and running a computer program stored in the memory, performing any one of the methods provided by the implementation manner in the first aspect or in the second aspect.

It should be appreciated that any of the apparatus, computer storage medium, computer program product, or chip system provided above may be applied to the corresponding method provided above, and thus, the benefits achieved by the apparatus, computer storage medium, computer program product, or chip system may refer to the benefits in the corresponding method, which are not described herein.

In the present application, the names of the above-mentioned detecting means of the communication link do not constitute limitations on the devices or function modules themselves, and in actual implementation, these devices or function modules may appear under other names. Insofar as the function of each device or function module is similar to that of the present application, it falls within the scope of the claims of the present application and the equivalents thereof.

Drawings

Fig. 1 is a schematic diagram of a network system 10 according to an embodiment of the present application;

fig. 2 is a schematic diagram of a network system 20 according to an embodiment of the present application;

fig. 3 is a schematic hardware structure of an access device according to an embodiment of the present application;

fig. 4 is a flow chart of a method for detecting a communication link according to an embodiment of the present application;

fig. 5 is a flow chart of another method for detecting a communication link according to an embodiment of the present application;

fig. 6 is a flow chart of another method for detecting a communication link according to an embodiment of the present application;

fig. 7 is a flow chart of another method for detecting a communication link according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a detection device 80 for a communication link according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a detection device 90 for a communication link according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a chip system according to an embodiment of the present application.

Detailed Description

For a clearer understanding of embodiments of the present application, some terms or techniques related to the embodiments of the present application are described below:

1) Routing black hole

The routing black hole is a communication fault, and specifically refers to a communication fault that an actual forwarding path and an expected forwarding path of a message are different due to a configuration error of a routing table of a network node, so that a destination network node which should originally receive the message cannot receive the message. The actual forwarding path of the message is a path of the message actually forwarded through the network node, and the expected forwarding path of the message refers to a message forwarding path originally expected by a user.

The routing table configuration error of the network node may be an error caused by a manual error when the routing table is manually configured, an error caused by a memory storing the routing table in the network node being operated by an error (for example, an error writing operation or deleting operation), or an error caused by an abnormality (or failure, etc.) of a memory unit storing the memory of the routing table in the network node, which is not limited.

It will be appreciated that the configuration error of the routing table of the network node may occur when the routing is configured before the message is transmitted, or may occur during the transmission of the message, which is not limited thereto.

2) Other terms

In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion. It should be appreciated that reference throughout this specification to "one embodiment," "an embodiment," "one possible implementation" means that a particular feature, structure, or characteristic described in connection with the embodiment or implementation is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment," "one possible implementation" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

In embodiments of the application, the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The term "at least one" in the present application means one or more, and the term "plurality" in the present application means two or more.

It will also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. The term "and/or" is an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B, and may mean: a exists alone, A and B exist together, and B exists alone. It should be appreciated that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.

Currently, when detecting whether a communication link of a network is abnormal through a BFD packet, bandwidth resources of each node in the network are continuously consumed. And the link convergence time when detecting a communication link via BFD messages is typically only controlled to the order of hundred milliseconds (typically 200 milliseconds), which is far from satisfactory for networks running high latency applications such as games. The link convergence time is a time for repairing the communication link when detecting the communication link abnormality and when the communication link abnormality so as to enable the communication link to be recovered to be normal.

In addition, when the BFD packet is used to detect whether the communication link of the network is abnormal, the BFD packet can only detect the broken link caused by whether the communication link has physical failure, and cannot detect the routing black hole in the network.

Based on the above, the embodiment of the application provides a method for detecting a communication link, which is applied to an access device in a network system. The method comprises the following steps: and the target access equipment determines the data stream with the data volume which is not increased in the preset time length in the received data stream as the suspected abnormal stream. Further, the source access device transmitting the suspected abnormal flow determines whether the communication link transmitting the suspected abnormal flow is abnormal according to the difference value between the data volume of the transmitted suspected abnormal flow and the data volume of the suspected abnormal flow received by the target access device.

Therefore, the method provided by the embodiment of the application can realize the detection of whether the communication link is abnormal or not only by monitoring the data volume of the receiving and transmitting data stream by the access equipment in the network system. The method does not need each node in the network system to generate a communication link detection message and send the message to each other. Therefore, the method can save bandwidth resources of nodes in the network system.

In addition, when the preset duration is set to a duration of hundred microseconds, when the communication link of the network system is detected by the method provided by the embodiment of the present application, the link convergence time of the communication link may reach a millisecond level or a sub-millisecond level. Compared with the hundred millisecond link convergence time when the communication link is detected through the BFD message, the method provided by the embodiment of the application greatly shortens the link convergence time of the communication link, thereby reducing the time delay of data transmission of a network system and further improving the user experience. In addition, the method provided by the embodiment of the application can also detect the routing black hole caused by the configuration error of the routing table of one or more nodes in the data transmission process of the network system.

The embodiment of the application also provides a network system, wherein the communication network of the network system is a first communication network, and the first communication network comprises an access layer, a backbone layer (spin) and a core layer (core). The node of the access layer is used for accessing the terminal (or the server) to the first communication network, and can be used for executing the method for detecting the communication link provided by the embodiment of the application so as to detect whether the communication link in the first communication network is abnormal. The nodes of the backbone layer and the core layer are used for forwarding the message in the first communication network. The nodes of the backbone layer are used for forwarding messages between the access layer nodes and the core layer nodes, and the nodes of the core layer are used for forwarding messages between the nodes of the backbone layer.

In the embodiment of the application, each node of the access layer in the first communication network is connected to communicate with a part of nodes of the backbone layer in the first communication network, and each node of the backbone layer in the first communication network is connected to communicate with a part of nodes of the core layer in the first communication network.

By way of example, referring to fig. 1, fig. 1 shows a schematic diagram of a network system 10 according to an embodiment of the present application. As shown in fig. 1, a first communication network configured by a network system 10 includes an access layer 11, a backbone layer 12, and a core layer 13.

The access layer 11 includes a node 111, a node 112, a node 113, a node 114, a node 115, and a node 116. The node of the access layer 11 is for connecting a terminal (or server) and accessing the terminal (or server) to the first communication network. The nodes of the access layer 11 are used to forward messages between the terminals (or servers) and the nodes of the backbone layer 12. For example, the node 111 of the access layer 11 is used for forwarding messages between the terminal 101 and the node 121 of the backbone layer 12 and/or for forwarding messages between the terminal 101 and the node 122 of the backbone layer 12.

The backbone layer 12 comprises nodes 121, 122, 123, 124, 125 and 126, and the nodes of the backbone layer 12 are used for forwarding messages in the first communication network, and in particular for forwarding messages between the nodes of the access layer 11 and the nodes of the core layer 13. For example, the node 121 of the backbone layer 12 is used for forwarding messages between the node 111 of the access layer 11 and the node 131 of the core layer 13 and/or for forwarding messages between the node 111 of the access layer 11 and the node 132 of the core layer 13.

The core layer 13 includes a node 131, a node 132, a node 133 and a node 134, and the nodes of the core layer 13 are used for forwarding messages in the first communication network, and in particular for forwarding messages between the nodes of the backbone layer 12. For example, the node 131 of the core layer 13 may be used to forward messages between the node 121 and the node 123 of the backbone layer 12 and/or to forward messages between the node 121 and the node 125 of the backbone layer 12 or to forward messages between the node 123 and the node 125 of the backbone layer 12.

Furthermore, each node of the access layer 11 is in connection communication with 2 out of 6 nodes of the backbone layer 12, e.g. node 111 of the access layer 11 is in connection communication with nodes 121, 122 of the backbone layer 12. Each node of the backbone layer 12 communicates with 2 of the 4 nodes of the core layer 13, e.g. node 121 of the backbone layer 12 communicates with the nodes 131, 132 of the core layer 13. And will not be described in detail.

The embodiment of the application also provides another network system, wherein the communication network of the network system is a second communication network, and the second communication network comprises a leaf layer (leaf) and a backbone layer. The node of the leaf layer is used for accessing the terminal (or the server) to the second communication network, and can be used for executing the detection method of the communication link provided by the embodiment of the application so as to detect whether the communication link in the second communication network is abnormal. The nodes of the backbone layer are used for forwarding messages in the second communication network, and are specifically used for forwarding messages between the nodes of the leaf layer.

In the embodiment of the application, each node of the leaf layer in the second communication network is fully connected with a node of the backbone layer in the second communication network. In other words, each node of the leaf layer in the second communication network and each node of the backbone layer in the second communication network can communicate.

As an example, referring to fig. 2, fig. 2 shows a schematic diagram of a network system 20 according to an embodiment of the present application. As shown in fig. 2, the second communication network configured by the network system 20 includes a leaf layer 21 and a backbone layer 22, and each node of the leaf layer 21 is fully connected with a node of the backbone layer 22, i.e., each node of the leaf layer 21 and each node of the backbone layer 22 can communicate.

Among them, the leaf layer 21 includes a node 211, a node 212, a node 213, a node 214, a node 215, and a node 216. The nodes of the leaf layer 21 are used to connect terminals (or servers) and to access the terminals (or servers) to the second communication network. The nodes of the leaf layer 21 are used to forward messages between the terminals (or servers) and the nodes of the backbone layer 22. For example, the node 211 of the leaf layer 21 may be used to forward messages between the terminal 201 and the node 221 of the backbone layer 22, and/or to forward messages between the terminal 201 and the node 222 of the backbone layer 22, and/or to forward messages between the terminal 201 and the node 223 of the backbone layer 22.

The backbone layer 22 comprises nodes 221, 222 and 223, and the nodes of the backbone layer 22 are used for forwarding messages in the second communication network, and in particular for forwarding messages between the nodes of the leaf layer 21. For example, the node 221 of the backbone layer 22 may be used to forward messages between any two nodes of the leaf layer 21 (e.g., node 211 and node 212).

Alternatively, the network system shown in fig. 1 and 2 may be a network system of a data center. Thus, the first communication network and the second communication network are not limited to the data center network.

The embodiment of the application also provides a device for detecting the communication link, which is applied to the network system shown in fig. 1 or fig. 2 and is used for executing the method for detecting the communication link provided by the embodiment of the application. As an example, in connection with fig. 1, the detection device may be an access stratum node in the network system shown in fig. 1, or a functional module in the access stratum node, which is not limited thereto. As an example, in connection with fig. 2, the detection device may be a leaf level node in the network system shown in fig. 2, or a functional module in the leaf level node, which is not limited thereto.

For simplicity of description, in the embodiment of the present application, the device of the access layer node in the network system shown in fig. 1 and the device of the leaf layer node in the network system shown in fig. 2 are referred to as access devices. In this way, the detection device of the communication link provided by the embodiment of the present application may be the access device or a functional module in the access device, which is not limited. Alternatively, the access device may be a switch, a top of rack (ToR), a router (router), or the like, without being limited thereto.

In an embodiment of the present application, when one access device (e.g., a first access device) in a network system transmits a first data stream received from a terminal (or server) to another access device (e.g., a second access device) via a backbone layer node (or via a backbone layer and a core layer node), the second access device forwards the received first data stream to the terminal (or server) connected to the second access device. In this case, the embodiment of the present application refers to the first access device as a source access device transmitting the first data stream in the network system, and refers to the second access device as a destination access device receiving the first data stream in the network system.

It will be appreciated that the second access device may also send the second data stream received from the terminal (or server) to the first access device via the backbone layer node (or via the backbone layer and core layer nodes) so that the first access device forwards the received second data stream to the terminal (or server) connected to the first access device. In this case, the first access device is referred to as a destination access device in the network system that receives the second data stream, and the second access device is referred to as a source access device in the network system that transmits the second data stream. That is, for different data streams, the same access device may be used as a source access device for transmitting data streams in the network system, or may be used as a destination access device for receiving data streams in the network system.

As an example, referring to fig. 1, when node 111 of access layer 11 transmits data stream 1 received from terminal 101 in network system 10, it is sequentially transmitted to node 115 of access layer 11 via node 121 of backbone layer 12, node 131 of core layer 13, and node 125 of backbone layer 12. Node 111 is the source access device in network system 10 that sent data stream 1 and node 115 is the destination access device in network system 10 that received data stream 1. When the node 115 of the access layer 11 in the network system 10 transmits the data stream 2 received from the terminal 105 to the node 111 of the access layer 11 sequentially through the node 125 of the backbone layer 12, the node 131 of the core layer 13, and the node 121 of the backbone layer 12. Node 115 is the source access device in network system 10 that sent data stream 2 and node 111 is the destination access device in network system 10 that received data stream 2.

As another example, referring to fig. 2, when a node 211 of a leaf layer 21 in a network system 20 transmits a data stream 3 received from a terminal 201 to a node 215 of the leaf layer 21 via a node 221 of a backbone layer 22. Node 211 is the source access device in network system 20 that sent data stream 3 and node 215 is the destination access device in network system 20 that received data stream 3. When the node 215 of the leaf layer 21 in the network system 20 transmits the data stream 4 received from the terminal 205 to the node 211 of the leaf layer 21 via the node 221 of the backbone layer 22. Node 215 is the source access device in network system 20 that sent data stream 4 and node 211 is the destination access device in network system 20 that received data stream 4.

It should be understood that the data stream described in the embodiments of the present application may be any data stream including a plurality of messages, such as a video stream and an audio stream, which is not limited thereto. It should be noted that different data streams may be distinguished by a stream identification for each data stream. The flow identifier of the data flow may be, for example, a name, an Identifier (ID) of the data flow, or quintuple information (or quad information) carried by a packet in the data flow, which is not limited thereto. The five-tuple information may include a source address, a source port, a destination address, a destination port, and a transport protocol. The quadruple information may include a source address, a source port, a destination address, and a destination port. As an example, taking the flow identification of the data flow a as the five-tuple information of the packet in the data flow a as an example, the data flow a can be distinguished from other data flows by the five-tuple information (source address a1, source port b1, destination address a2, destination port b2, transport protocol). The source port b1 is one port of the source access device indicated by the source address a1, and the destination port b2 is one port of the destination access device indicated by the destination address a 2.

In some examples, the data stream according to embodiments of the present application may be a long steady stream. Long stationary flows are understood to be data flows transmitted from a source access device to a destination access device at a relatively steady rate over a period of time.

Taking the above-mentioned detecting device of the communication link as an example of the above-mentioned access device, referring to fig. 3, fig. 3 shows a schematic hardware structure of an access device according to an embodiment of the present application. As shown in fig. 3, the access device 30 includes a processor 301, a memory 302, a network interface 303, and a bus 304. The processor 301, the memory 302 and the network interface 303 are connected via a bus 304.

The processor 301 is a control center of the access device 30 and may be a general-purpose central processing unit (central processing unit, CPU), the processor 301 may also be other general-purpose processors, digital signal processors (digital signal processor, DSP), application-specific integrated circuits (application-specific integrated circuit, ASIC), field-programmable gate arrays (field-programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, graphics processors (graphics processing unit, GPU), neural network processing units (neural processing unit, NPU), tensor processors (tensor processing unit, TPU) or artificial intelligence (artificial intelligent, AI) chips, data processors (data processing unit, DPU), etc.

Processor 301 may include one or more CPUs, such as CPU 0 and CPU 1 shown in fig. 3. Furthermore, the present application is not limited to the number of processor cores in each processor.

The memory 302 is used for storing program instructions or data to be accessed by an application process, and the processor 301 may implement the method for detecting a communication link according to the embodiment of the present application by executing the program instructions in the memory 302.

Memory 302 includes volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM). The nonvolatile memory may be a storage class memory (storage class memory, SCM), a solid state disk (solid state drive, SSD), a mechanical hard disk (HDD), or the like. The storage level memory may be, for example, a nonvolatile memory (NVM), a phase-change memory (PCM), a persistent memory, or the like.

In one possible implementation, the memory 302 exists independent of the processor 301. The memory 302 is coupled to the processor 301 through the bus 304 for storing data, instructions or program code. The processor 301, when calling and executing instructions or program codes stored in the memory 302, can implement the method for detecting a communication link according to the embodiment of the present application.

In another possible implementation, the memory 302 and the processor 301 are integrated.

A network interface 303 for the access device 30 to communicate with other devices, such as backbone layer nodes or terminals (or servers) as shown in fig. 1 or 2, through a communication network, which may be an ethernet network, a radio access network (radio access network, RAN), a wireless local area network (wireless local area networks, WLAN), etc. The network interface 303 comprises a receiving unit for receiving data/messages and a transmitting unit for transmitting data/messages.

Bus 304 may be an industry standard architecture (industry standard architecture, ISA) bus, an external device interconnect (peripheral component interconnect, PCI) bus, a high-speed serial computer expansion bus (peripheral component interconnect express, PCIe), a computing fast link (compute express link, CXL), or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 3, but not only one bus or one type of bus.

It should be noted that the structure shown in fig. 3 does not constitute a limitation of the access device 30, and that the access device 30 comprises more or less components than shown in fig. 3, or certain components are combined, or a different arrangement of components, than shown in fig. 3.

The following describes in detail a method for detecting a communication link according to an embodiment of the present application with reference to the accompanying drawings.

Optionally, the method for detecting a communication link provided by the embodiment of the present application may be applied to the network system described in fig. 1 or fig. 2, and executed by an access device having the hardware structure shown in fig. 3, where the access device includes a source access device and a destination access device. The detailed descriptions of the source access device and the destination access device may refer to the above description, and will not be repeated.

It should be noted that, in the embodiment of the present application, the destination access device and the source access device are configured with a flow table, where the flow table includes one or more flow table entries, and each flow table entry in the flow table is used to record flow information of one data flow. The flow tables configured by the destination access device and the source access device are first described below.

Flow table for destination access device configuration

For any data stream (e.g., a third data stream) transmitted between the source access device and the destination access device, after the destination access device receives the first message of the third data stream, the destination access device creates a stream table entry of the third data stream in the stream table, and records stream information of the third data stream in the stream table entry.

Wherein the flow information of the third data flow comprises a flow identification of the third data flow and a first data amount of the third data flow. Here, the detailed description of the flow identifier of the data flow may refer to the above description, and will not be repeated. The first data amount of the third data stream refers to a data size of the third data stream that the destination access device has received at the current time in the process of receiving the third data stream. For example, when the destination access device receives the first message of the third data stream at the current moment, the first data amount of the third data stream is the size of the first message. Alternatively, the first data amount of the third data stream may be characterized by a number of bytes comprised by the message of the third data stream that has been received by the access device. Or, the first data amount of the third data stream may be represented by a number of messages, where the number of messages is the number of messages of the third data stream that the destination access device has received. The embodiment of the present application is not limited thereto. It will be appreciated that when the first data volume of the third data stream is characterized by a number of messages, the actual size of the first data volume of the third data stream is the product of the number of messages and the size of each message.

Optionally, the flow information of the third data flow may further include a latest packet sequence number of the third data flow, or include a latest packet sequence number of the third data flow and a latest packet receiving time of the third data flow, which is not limited. The latest message sequence number of the third data stream is the sequence number of the message of the third data stream which is latest received by the target access device at the current moment, and the latest message receiving time of the third data stream is the time of the message of the third data stream which is latest received by the target access device at the current moment, that is, the latest message receiving time of the third data stream is the time of the message indicated by the latest message sequence number of the third data stream which is latest received by the target access device.

For example, assuming that the destination access device receives the first packet of the third data flow at the current time, the flow information of the third data flow recorded by the destination access device in the flow table entry created for the third data flow includes: the flow identifier of the third data flow, the size of the first message, the sequence number of the first message, and the receiving time of the first message. The size of the first message is the first data amount of the third data stream, the first message is the message of the third data stream which is received by the target access device at the current moment, therefore, the sequence number of the first message is the sequence number of the latest message of the third data stream, and the receiving time of the first message is the latest message receiving time of the third data stream.

By way of example, taking the flow table entry created for data flow 3 by the destination access device after receiving the first message of data flow 3 as an example, referring to table 1, table 1 shows a schematic diagram of the flow table entry for data flow 3. As shown in table 1, the stream information of the data stream 3 recorded in the stream entry shown in table 1 includes: the stream identifier D3 of the data stream 3, the number of bytes (e.g., 5 bytes) included in the first message of the data stream 3, the sequence number N1 of the first message, and the reception time T1 of the first message.

TABLE 1

Flow identification	First data volume	Latest message sequence number	Time of latest message reception
				D3	5byte	N1	T1

It will be appreciated that after the destination access device creates the flow entry for the third data flow, the first amount of data in the flow entry for the third data flow is also updated during receipt of the third data flow.

Optionally, when the flow information of the third data flow further includes the latest packet sequence number of the third data flow, or includes the latest packet sequence number of the third data flow and the latest packet receiving time of the third data flow, after the destination access device creates the flow table entry of the third data flow, the latest packet sequence number in the flow table entry of the third data flow is updated in the process of receiving the third data flow, or the latest packet sequence number of the third data flow and the latest packet receiving time of the third data flow are updated in the process of receiving the third data flow.

In one possible implementation manner, the destination access device may update, in real time, the first data amount, the latest packet sequence number, and the latest packet reception time in the flow table entry of the third data flow during the process of receiving the third data flow. Or it may be understood that, each time the destination access device receives a message of the third data flow, the first data amount, the latest message sequence number, and the latest message receiving time in the flow table entry of the third data flow are updated once. For example, after receiving the second packet of the data flow 3, and the size of the second packet is 8 bytes, the sequence number of the second packet is N2, and the receiving time of the second packet is T2, the destination access device updates the first data amount in the flow table entry shown in table 1 to 13 bytes (i.e. 5 bytes+8 bytes), updates the sequence number of the latest packet to N2, and updates the receiving time of the latest packet to T2, as shown in table 2.

TABLE 2

Flow identification	First data volume	Latest message sequence number	Time of latest message reception
				D3	13byte	N2	T2

Further, after receiving the third message of the data flow 3, and the size of the third message is 4byte, the sequence number of the third message is N3, and the receiving time of the third message is T3, the destination access device updates the first data amount in the flow table entry shown in table 2 to 17byte (i.e. 13byte+4byte), the sequence number of the latest message to N3, and the receiving time of the latest message to T3, as shown in table 3.

TABLE 3 Table 3

Flow identification	First data volume	Latest message sequence number	Time of latest message reception
				D3	17byte	N3	T3

In another possible implementation manner, the destination access device may also periodically update the first data amount, the latest packet sequence number, and the latest packet reception time in the flow entry of the third data flow during the process of receiving the third data flow.

Optionally, in the process of receiving the third data stream, the destination access device may periodically update the first data amount, the latest packet sequence number, and the latest packet receiving time in the flow table entry of the third data stream with an arbitrary duration as a period. To ensure timeliness of the flow entries, the arbitrary duration may be a short duration, such as a duration on the order of microseconds.

Optionally, in the process of receiving the third data stream, the destination access device updates the first data volume, the latest message sequence number and the latest message receiving time in the stream table entry of the third data stream once every m messages are received. To ensure timeliness of the flow table entry, the value of m may be a small positive integer, for example, the value of m is 2.

Flow table configured by source access device

For any data stream (such as a fourth data stream) sent by the source access device to the destination access device, after the source access device sends the first message of the fourth data stream to the destination access device, the source access device creates a stream table entry of the fourth data stream in the stream table, and records stream information of the fourth data stream in the stream table entry.

Wherein the flow information of the fourth data flow comprises a flow identification of the fourth data flow and a second data amount of the fourth data flow. The detailed description of the flow identifier of the data flow may refer to the above description, and will not be repeated. The second data amount of the fourth data stream refers to the data size of the fourth data stream that has been sent out by the source access device at the current time in the process of sending the fourth data stream. Here, the description of the specific representation form of the second data volume may refer to the related description of the first data volume, which is not repeated.

For example, when the source access device sends out the first packet of the third data stream at the current moment, the flow information of the fourth data stream recorded by the source access device in the flow table entry created for the fourth data stream includes: the flow identification of the fourth data flow and the size of the first message. The size of the first message is the second data amount of the fourth data stream.

By way of example, taking the flow table entry created by the source access device for data flow 4 after sending the first message of data flow 4 as an example, referring to table 4, table 4 shows a schematic diagram of the flow table entry for data flow 4. As shown in table 4, the flow table entry shown in table 4 includes a flow identifier D4 of the data flow 4, a byte number (e.g., 6 bytes) included in a first packet of the data flow 4, a sequence number N4 of the first packet, and a transmission time T4 of the first packet.

TABLE 4 Table 4

Flow identification	First data volume
		D4	6byte

It will be appreciated that after the source access device creates the flow entry for the fourth data flow, the second amount of data in the flow entry for the fourth data flow is also updated during transmission of the fourth data flow.

In a possible implementation manner, the source access device may update the second data amount in the flow table entry of the fourth data flow in real time during the process of transmitting the fourth data flow. Or it may be understood that the second data amount in the flow table entry of the fourth data flow is updated once every time the source access device sends a message of the fourth data flow. For example, after the source access device sends the second packet of the data flow 4, and the second packet has a size of 5 bytes, the source access device updates the second data amount in the flow table entry shown in table 4 to 11 bytes (i.e. 6byte+5 bytes), as shown in table 5.

TABLE 5

Flow identification	First data volume
		D4	11byte

Further, after the source access device sends the third packet of the data flow 4, and the size of the third packet is 7 bytes, the source access device updates the second data amount in the flow table entry shown in table 5 to 18 bytes (i.e. 11 bytes+7bytes), as shown in table 6.

TABLE 6

Flow identification	First data volume
		D4	18byte

In another possible implementation manner, the source access device may also periodically update the second data amount in the flow table entry of the fourth data flow during the process of transmitting the fourth data flow.

Optionally, the source access device may periodically update the second data amount in the flow table entry of the fourth data flow with an arbitrary duration as a period during the process of sending the fourth data flow. To ensure timeliness of the flow entries, the arbitrary duration may be a short duration, such as a duration on the order of microseconds.

Alternatively, the source access device may update the second data amount in the flow table entry of the fourth data flow once every n messages are received during the process of transmitting the fourth data flow. To ensure timeliness of the flow table entry, the value of n may be a small positive integer, for example, n is 3.

Referring to fig. 4, fig. 4 is a schematic flow chart of a method for detecting a communication link according to an embodiment of the present application. Alternatively, the method may be applied to the network system described in fig. 1 or fig. 2, and performed by an access device having a hardware structure shown in fig. 3, where the access device includes a source access device and a destination access device, and flow tables for recording flow information of data flows are configured in the source access device and the destination access device. The source access device, the destination access device, the flow information of the data flow, and the detailed description of the flow table may refer to the above description, and will not be repeated. The method comprises the following steps:

S101, the target access equipment determines suspected abnormal flow.

The suspected abnormal flow is a data flow corresponding to a flow table item of which the target access device does not update the first data volume within a preset time. The suspected abnormal flow is a data flow transmitted from the source access device to the destination access device. The method comprises the steps that a flow table entry of a suspected abnormal flow is created after receiving a first message of the suspected abnormal flow by an access device, and the flow table entry of the suspected abnormal flow is used for recording flow information of the suspected abnormal flow. Here, description of the flow entry of the suspected abnormal flow, the creation process of the flow entry of the suspected abnormal flow, the flow information recorded in the flow entry of the suspected abnormal flow, and the update process of the first data amount in the flow entry of the suspected abnormal flow may refer to description of the flow entry of the third data flow, the creation process of the flow entry of the third data flow, the flow information recorded in the flow entry of the third data flow, and the update process of the first data amount in the flow entry of the third data flow, which are not described herein.

The destination access device may periodically detect flow information of each flow entry in the flow table, thereby determining whether the flow information of each flow entry updates the first data amount within a preset duration. For example, the destination access device may periodically traverse each flow entry in the flow table to determine whether the flow information in each flow entry has updated the first amount of data within a preset time period. The period of detecting the flow information of each flow table item in the flow table by the target access device may be a first period with a duration of the preset duration, and the specific value of the preset duration is not limited in the embodiment of the present application. As one example, the preset duration may be 300 microseconds.

In a possible case, when the destination access device determines that a certain flow entry in the flow table updates the first data amount within the preset duration, it determines that the data flow corresponding to the flow entry is a normal transmission data flow, and the destination access device may determine that a communication link for transmitting the data flow is normal.

It can be understood that if the destination access device updates the first data amount in a certain flow table entry within a preset time period, it indicates that the destination access device receives a message of a data flow corresponding to the flow table entry within the preset time period. I.e. the communication link for transmitting the data stream is normal.

In another possible case, when the destination access device determines that a certain flow table entry in the flow table does not update the first data amount within a preset duration, determining the data flow corresponding to the flow table entry as a suspected abnormal flow.

It can be understood that if the destination access device does not update the first data amount of a certain flow table entry within the preset time period, it indicates that the destination access device does not receive the message of the data flow corresponding to the flow table entry within the preset time period. The reason why the destination access device does not receive the message of the data flow corresponding to the flow table entry within the preset duration may be that the communication link for transmitting the data flow is abnormal/faulty, or that the source access device transmitting the data flow stops transmitting the data flow. In this case, therefore, the destination access device determines the data flow corresponding to the flow table entry of the first data volume that is not updated within the preset duration as the suspected abnormal flow.

It should be noted that, the data flow corresponding to the flow table entry is the data flow identified by the flow identifier in the flow table entry.

S102, the target access equipment generates a first message based on stream information of the suspected abnormal stream.

After the destination access device determines the suspected abnormal flow, the destination access device may determine the source address in the received message of the suspected abnormal flow as the destination address of the first message.

And the destination access equipment generates a first message according to the determined destination address and the flow information recorded by the flow table entry of the suspected abnormal flow. Here, the first message is used to notify the source access device that sends the suspected abnormal flow, and the communication link that transmits the suspected abnormal flow may have abnormality/failure. Further, the source access device may determine whether a communication link transmitting the suspected abnormal flow is abnormal/failed based on the first message.

The first message includes a flow identifier of the suspected abnormal flow and a first data volume of the suspected abnormal flow. The flow identifier of the suspected abnormal flow may be used to determine the suspected abnormal flow in the plurality of data flows, and the first data amount of the suspected abnormal flow is used to indicate the data size of the suspected abnormal flow that has been received by the target access device.

S103, the target access device sends a first message to the source access device which sends the suspected abnormal flow.

The destination access device may send the first message to the source access device that sent the suspected abnormal flow based on its own network interface (e.g., network interface 303 shown in fig. 3).

Optionally, the destination access device may send the first packet to the source access device that sends the suspected abnormal flow through one or more uplink ports in the network interface.

The uplink port of the destination access device refers to a port in the destination access device, which is used for sending a message to an upper node (for example, a backbone layer node) in a communication network where the destination access device is located. It should be noted that an upstream port of the destination access device is used to communicate with an upper node.

As an example, referring to fig. 1, assuming that the destination access device is the node 115 of the access layer 11 in the network system shown in fig. 1, the uplink port of the destination access device includes: a port 11 that sends messages to a node 125 of the backbone layer 12 shown in fig. 1, and a port 12 that sends messages to a node 126 of the backbone layer 12 shown in fig. 1.

As another example, referring to fig. 2, assuming that the destination access device is a node 215 of the leaf layer 21 in the network system shown in fig. 2, the upstream port of the destination access device includes: a port 21 for sending a message to a node 221 of the backbone layer 22 shown in fig. 2, a port 22 for sending a message to a node 222 of the backbone layer 22 shown in fig. 2, and a port 23 for sending a message to a node 223 of the backbone layer 22 shown in fig. 2.

In this way, when the destination access device sends the first message to the source access device sending the suspected abnormal flow through the plurality of uplink ports, the destination access device sends the first message to the source access device through the plurality of upper nodes. In other words, the communication link for transmitting the first message from the destination access device to the source access device comprises a plurality of communication links. In this way, even if a communication link among a plurality of communication links used for transmitting the first message is abnormal/faulty, the method provided by the application can ensure that the destination access device transmits the first message to the source access device through other communication links.

S104, the source access device sending the suspected abnormal flow determines whether the suspected abnormal flow is cutoff or not based on the received first message.

After the source access device receives the first message, the source access device may determine, according to the flow identifier carried in the first message, a data flow corresponding to the flow identifier as a suspected abnormal flow in all data flows sent by the source access device.

Optionally, when the destination access device sends the first message to the source access device that sends the suspected abnormal flow through a plurality of uplink ports in the network interface, the source access device may receive a plurality of first messages transmitted through a plurality of communication links. In this case, after receiving the first packet from the destination access device, the source access device determines, according to the flow identifier carried in the first packet, the data flow corresponding to the flow identifier as a suspected abnormal flow in all the data flows sent by the source access device. It should be appreciated that for one or more first messages that the source access device repeatedly receives after receiving the first message, the source access device discards those repeatedly received first messages.

Further, the source access device determines whether the suspected abnormal flow is a flow break. It will be appreciated that for any data stream, when the source access device stops transmitting the data stream for more than a predetermined period of time, the source access device determines that the data stream is a break. Here, the specific value of the predetermined time period is not limited in the embodiment of the present application. For example, the predetermined time period may be 400 microseconds, 800 microseconds, or the like.

Alternatively, the source access device may determine whether the suspected abnormal flow is a flow break by determining whether the suspected abnormal flow is marked as a flow break after determining the suspected abnormal flow. When the source access device determines that the suspected abnormal flow is not marked as a flow break, it determines that the suspected abnormal flow is not a flow break. In this case, the stop time period indicating that the source access device stops transmitting the suspected abnormal flow does not exceed (is less than or equal to) the predetermined time period. That is, the source access device normally transmits the suspected abnormal flow at present, and the source access device performs S105. In contrast, when the source access device determines that the suspected abnormal flow has been marked as a flow break, the suspected abnormal flow is determined to be a flow break. In this case, the stop time period indicating that the source access device stops transmitting the suspected abnormal flow exceeds (is greater than or equal to) the predetermined time period.

In one possible implementation manner, the source access device may determine whether the suspected abnormal flow is marked as a flow break by determining whether a flow entry of the suspected abnormal flow includes a flow mark indicating a flow break. The source access device may determine a flow entry for the suspected abnormal flow in the flow table described above according to the flow identification for the suspected abnormal flow. For example, the destination access device may traverse the flow entries in the flow table described above, and determine the flow entry including the flow identifier of the suspected abnormal flow as the flow entry of the suspected abnormal flow. Further, when the source access device determines that the flow entry of the suspected abnormal flow includes a flow flag indicating flow break, it determines that the suspected abnormal flow is marked as flow break. When the source access device determines that the flow table item of the suspected abnormal flow does not comprise the flow mark indicating the flow break or comprises the flow mark indicating the normal flow, the suspected abnormal flow is determined not to be marked as the flow break.

Here, description of the creating and updating process of the flow table entry of the suspected abnormal flow in the source access device may refer to description of the creating and updating of the flow table entry of the fourth message described above, and will not be repeated. However, in the embodiment of the present application, after the source access device creates a flow table entry for each transmitted data flow, it may also periodically detect whether the second data amount of each flow table entry is updated in each detection period, so as to determine whether to add a flow flag indicating flow break in the flow table entry of the data flow, or add a flow flag indicating normal flow.

And when the source access device determines that the second data amount in the flow table item of a certain data flow is not updated in one or more detection periods, and the duration of the one or more detection periods is greater than or equal to the preset duration, the stopping duration of stopping sending the certain data flow by the source access device exceeds the preset duration. In this case, the source access device adds a flag for indicating a flow break in the flow entry of the certain data flow. In contrast, in any detection period, if the source access device determines that the second data amount in the flow table entry of a certain data flow is updated, it indicates that the certain data flow is a normally transmitted data flow. In this case, the source access device does not add a flag indicating a flow break to the flow entry of the certain data flow, or adds a flow flag indicating a normal flow to the flow entry of the certain data flow, which is not limited. It should be noted that the embodiment of the present application is not limited to a specific form of the flag for indicating the interruption and the flag for indicating the normal flow.

In another possible implementation, the source access device may determine whether the suspected abnormal flow is marked as a flow break by determining whether a flow identification of the suspected abnormal flow is included in a flow break log (or a flow break table). For example, when the source access device traverses a flow log (or flow table), determines that the flow log (or flow table) includes a flow identification of suspected abnormal flows, then it is determined that the suspected abnormal flows are marked as flow. When the source access device traverses the flow log (or flow chart), determines that the flow log (or flow chart) does not include the flow identification of the suspected abnormal flow, then determines that the suspected abnormal flow is not marked as flow.

Alternatively, for any data stream transmitted by the source access device, the source access device may monitor the port used to transmit the any data stream. When the source access device monitors that the port for transmitting any one data stream has stopped transmitting any one data stream for more than a preset time period, the stream identification of any one data stream is recorded in a flow break log (or a flow break table). It may be further understood that, when the source access device monitors that the port for transmitting the arbitrary data stream starts to transmit the packet of the arbitrary data stream and the flow identification of the arbitrary data stream is included in the flow log (or the flow table), the source access device deletes the flow identification of the arbitrary data stream in the flow log (or the flow table), or sets the flow identification of the arbitrary data stream in the flow log (or the flow table) to be invalid, which is not limited.

And S105, when the source access device determines that the suspected abnormal flow is not the cutoff, determining whether the difference value between the data quantity of the suspected abnormal flow sent by the source access device and the first data quantity of the suspected abnormal flow is larger than a threshold value or not based on the first message received from the target access device.

The first data amount of the suspected abnormal flow is the first data amount of the suspected abnormal flow carried in the first message received by the source access device from the destination access device. The data amount of the suspected abnormal flow sent by the source access device is the second data amount recorded by the source access device in the flow table entry of the suspected abnormal flow (hereinafter referred to as the second data amount of the suspected abnormal flow for short). Here, the flow table entry of the suspected abnormal flow is a flow table entry including the flow identifier carried by the first message in the flow table configured by the source access device.

The source access device determines whether a difference of the second data amount of the suspected abnormal flow subtracted by the first data amount of the suspected abnormal flow is greater than a threshold. When the source access device determines that the difference of the second data amount of the suspected abnormal flow minus the first data amount of the suspected abnormal flow is greater than or equal to the threshold, the source access device performs S106.

Optionally, the threshold may be a preset arbitrary value, and the specific value of the arbitrary value is not limited in the embodiment of the present application.

Alternatively, the threshold may be the size of all flight messages when the source access device transmits a message to the destination access device. Here, a flight message refers to a message that has been sent from a source access device while the communication link between the source access device and a destination access device is normal, but is still transmitted within the communication link without reaching the destination access device. Alternatively, the number of flight messages when the source access device transmits a message to the destination access device may be approximately equal to the number of messages transmitted within a Round Trip Time (RTT). In this way, the threshold may be approximately equal to the product of the number of flight messages and the size of a single flight message when the source access device transmits messages to the destination access device. The size of the single flight message is generally a preset size, which is not limited in the embodiment of the present application.

Wherein, for any two devices capable of communication (such as device 1 and device 2), RTT refers to a period of time between a time 1 when device 1 transmits a message 1 to device 2 and a time 2 when device 1 receives feedback information of device 2 in a case that a communication link is normal. It should be understood that the feedback information sent by the device 2 to the device 1 refers to acknowledgement information that the device 2 received the message 1 sent by the device 1.

It can be seen that in practice, the number of messages transmitted by a source access device to a destination access device in one RTT is typically greater than the actual number of flight messages when messages are transmitted between the source access device and the destination access device. Therefore, by determining the number of messages transmitted by the source access device to the destination access device within one RTT as the number of flight messages when the messages are transmitted between the source access device and the destination access device, the value of the threshold can be appropriately increased, so that the threshold can be suitable for a scenario including multiple communication links between the source access device and the destination access device, which is not described in detail.

And S106, when the source access equipment determines that the difference value between the second data volume of the suspected abnormal flow and the first data volume of the suspected abnormal flow is greater than or equal to a threshold value, determining that the communication link for transmitting the suspected abnormal flow is abnormal.

Taking the threshold value as an example of the size of all flight messages when the source access device transmits messages to the destination access device, when the difference value of the second data volume of the suspected abnormal flow minus the first data volume of the suspected abnormal flow is larger than or equal to the threshold value, the difference value of the data volume sent by the suspected abnormal flow on the source access device side minus the data volume received by the destination access device side is larger than or equal to the size of all flight messages when the source access device transmits messages to the destination access device. That is, in this case, the message corresponding to the difference of the second data amount of the suspected abnormal flow minus the first data amount of the suspected abnormal flow includes, in addition to all flight messages transmitted in the communication link but not reaching the destination access device when the communication link is normal, a message that the source access device has transmitted but not received by the destination access device, and thus the source access device determines that the communication link transmitting the suspected abnormal flow is abnormal.

It can be understood that, when the source access device determines that the difference value of the second data amount of the suspected abnormal flow minus the first data amount of the suspected abnormal flow is smaller than the threshold value, the difference value of the data amount sent by the suspected abnormal flow on the source access device side minus the data amount received by the destination access device side is smaller than the size of all flight messages when the source access device transmits the messages to the destination access device. That is, the destination access device detects that the suspected abnormal flow does not update the first data amount for the preset time period, because the message of the suspected abnormal flow sent by the source access device is also transmitted in the communication link, but does not reach the destination access device temporarily. In this case, therefore, the source access device determines that the communication link transmitting the suspected abnormal flow is normal.

Optionally, after determining that the communication link for transmitting the suspected abnormal flow is abnormal, the source access device may reconfigure and switch the communication link for transmitting the suspected abnormal flow to the destination access device based on the address of the destination access device for receiving the suspected abnormal flow, so that the source access device may continue to transmit the message of the suspected abnormal flow to the destination access device through the switched communication link.

Optionally, after the source access device determines that the communication link for transmitting the suspected abnormal flow is abnormal, the source access device may send alarm information of the communication link abnormality to a network management device of a network system where the source access device is located, where the alarm information is used to indicate that the communication link between the source access device and the destination access device for transmitting the suspected abnormal flow is abnormal. And the network management equipment re-plans the communication link for transmitting the suspected abnormal flow between the source access equipment and the target access equipment based on the address of the target access equipment for receiving the suspected abnormal flow and the network topology of the network system, and transmits the route information of the planned communication link to the source access equipment. In response, the source access device updates the routing table based on the received routing information, and continues to send the message of the suspected abnormal flow to the destination access device through the communication link re-planned by the network management device based on the updated routing table.

It can be seen that, in the method described in S101-S106, only the access devices (the source access device and the destination access device) in the network system are required to monitor the data volume of the data stream received and transmitted, so as to implement detection on whether the communication link is abnormal based on the difference between the data volumes of the data stream received and transmitted. It can be seen that the method does not require that every node in the network system generate a communication link detection message and send the messages to each other. Therefore, the method can save bandwidth resources of nodes in the network system.

In addition, when the destination access device in the method described in S101-S106 determines whether the updated preset duration of the first data amount recorded in the flow table entry of the data flow is set to a duration of hundred microseconds, it can be implemented to detect whether the communication line for transmitting the data flow is abnormal within the duration of hundred microseconds. Further, the link convergence time of the communication link can be controlled at the millisecond level or the sub-millisecond level. Therefore, compared with the method that only the link convergence time can be controlled to be in the hundred milliseconds (generally 200 milliseconds) level when the communication link is detected through the BFD message, the method provided by the embodiment of the application greatly shortens the link convergence time of the communication link, thereby reducing the time delay of data transmission of a network system and further improving the user experience.

Furthermore, as can be seen from the above description, the method provided by the embodiment of the present application realizes detecting whether the communication link for transmitting the data stream is abnormal at the data layer. For a data stream, the method provided by the embodiment of the application is to determine whether a communication link for transmitting the data stream is abnormal by detecting a difference between a transmitted data amount of the data stream at a source access device side and a received data amount of a destination access device in an access layer of a communication network. Therefore, for the fault that the routing black hole appears in the communication network in the data transmission process, so that the target access equipment expected by the user cannot receive the data stream, the method provided by the embodiment of the application can be also applied.

In some embodiments, when the source access device determines that the suspected abnormal flow is a flow break in S104, that is, when the stopping time period of the source access device for stopping sending the suspected abnormal flow exceeds (is greater than or equal to) the predetermined time period, referring to fig. 5, after S104, the method for detecting a communication link according to the embodiment of the present application further includes S107 to S108.

And S107, when the source access equipment determines that the suspected abnormal flow is cut-off, a second message is sent to the target access equipment, and the second message indicates to prolong the period of flow information for detecting the suspected abnormal flow.

After the source access device determines that the suspected abnormal flow is cut-off, the source access device may send a second message to the destination access device, where the second message indicates the destination access device to extend the period of flow information for detecting the suspected abnormal flow.

It can be understood that when the suspected abnormal flow is a flow break, the source access device does not send a message of the suspected abnormal flow to the destination access device for a period of time. Correspondingly, the target access device can not receive the message of the suspected abnormal flow any more in a period of time. Therefore, for the flow information recorded in the flow table entry of the suspected abnormal flow, the destination access device does not need to continue to detect the flow information of the suspected abnormal flow at a higher frequency (i.e. with a shorter period) to determine whether the first data volume of the suspected abnormal flow is updated. Furthermore, in order to save resource consumption caused by the target access device detecting the flow information of the suspected abnormal flow, the source access device may generate a second message indicating to extend the period of detecting the flow information of the suspected abnormal flow, and send the second message to the target access device.

S108, the target access equipment adjusts the period of stream information for detecting the suspected abnormal stream based on the received second message.

The target access device receives the second message and prolongs the period of detecting the flow information of the suspected abnormal flow based on the indication of the second message.

As an example, assuming that the period of the flow information of the suspected abnormal flow that the destination access device originally detects is the first period, the destination access device may adjust the period of the flow information of the suspected abnormal flow from the first period to the second period based on the indication of the second message. Wherein the second period is greater than the first period. For example, the first period is 300 microseconds and the second period is 800 microseconds, which is not limited.

And then, the target access equipment periodically detects the flow information of the suspected abnormal flow by taking the second period as a period to determine whether the first data volume of the suspected abnormal flow is updated within the indication duration of the second period.

Optionally, when the destination access device detects that the first data amount of the suspected abnormal flow is not updated in all k consecutive periods, the destination access device may delete the flow table entry of the suspected abnormal flow from the flow table, or set the flow table entry of the suspected abnormal flow in the flow table as invalid, which is not limited. Wherein k is a positive integer, and the value of k is not particularly limited in the embodiment of the application.

By the method provided by the possible embodiment, when the suspected abnormal flow is cut off, the target access device can prolong the period of detecting the flow information of the suspected abnormal flow, so that whether the communication link for transmitting the suspected abnormal flow is abnormal or not can be ensured to be continuously detected by detecting whether the first data volume of the suspected abnormal flow is updated or not, and resource consumption caused by the target access device for detecting the flow information of the suspected abnormal flow can be saved.

In still other embodiments, when the source access device determines that the suspected abnormal flow is a flow break in S104 and the source access device starts sending a message of the suspected abnormal flow to the destination access device again after the stopping time, referring to fig. 6, after S108 described above, the method for detecting a communication link according to the embodiment of the present application further includes the following steps.

S109, the source access device transmits, to the destination access device, indication information indicating that the period of flow information for detecting the suspected abnormal flow is reduced.

As can be seen from S107 to S108, when the source access device determines that the suspected abnormal flow is a current interruption, the destination access device is configured to ensure whether the communication link for transmitting the suspected abnormal flow is abnormal by detecting whether the first data amount of the suspected abnormal flow is updated continuously, and further to save resource consumption caused when detecting the flow information of the suspected abnormal flow, and the destination access device extends the period of detecting the flow information of the suspected abnormal flow based on the indication of the source access device.

When the source access device starts to send the message of the suspected abnormal flow to the target access device again after the stopping time, the target access device can reduce the period of detecting the flow information of the suspected abnormal flow, so that the purpose of reducing whether the first data volume recorded in the flow table entry is updated or not is achieved. In this way, the destination access device can quickly determine the suspected abnormal flow based on the detection result, and the source access device can determine whether the communication link transmitting the suspected abnormal flow is abnormal based on the flow information of the suspected abnormal flow announced by the first message. Therefore, the period of the stream information of the suspected abnormal stream detected by the target access device is reduced, and the speed of detecting whether the communication link is abnormal can be increased, so that the link convergence time of the communication link is shortened.

In a possible implementation manner, when the source access device starts to send the message of the suspected abnormal flow to the destination access device again after the stopping time, the source access device may carry the indication information in the first message of the suspected abnormal flow sent to the destination access device after the stopping time. In response, the destination access device analyzes the indication information from the first message after receiving the first message. Further, the destination access device may reduce the period of detecting the suspected abnormal flow based on the indication of the indication information.

In an exemplary embodiment, the period of detecting the flow information of the suspected abnormal flow is a second period before the destination access device receives the first message of the suspected abnormal flow sent by the source access device to the destination access device after the stopping period, and after the destination access device receives the first message including the indication information, the destination access device adjusts the period of detecting the suspected abnormal flow from the second period to a third period according to the indication of the indication information analyzed from the first message. Wherein the third period is less than the second period. Alternatively, the third period may be equal to the first period described above, or may not be equal to the first period described above, which is not limited.

In another possible implementation manner, the source access device may send the indication information to the destination access device when starting to send the message of the suspected abnormal flow to the destination access device again after the stopping time. Optionally, the source access device may send the indication information to the destination access device while starting to send the first message of the suspected abnormal flow to the destination access device again after the stopping time. Or, the source access device may send the indication information to the destination access device before or after starting to send the first message of the suspected abnormal flow to the destination access device again after the stopping time. This is not limited thereto. In response, the destination access device reduces the period of detecting the suspected abnormal flow based on the indication of the indication information after receiving the indication information. And will not be described in detail.

In yet another possible implementation manner, the destination access device may reduce the period of detecting the suspected abnormal flow after receiving the first packet of the suspected abnormal flow that the source access device sends to the destination access device again after the stopping period. For example, the period for detecting the suspected abnormal flow is adjusted from the second period to the third period, which is not described in detail. That is, in this implementation manner, the target access device receives, as a trigger event for triggering to reduce the period for detecting the suspected abnormal flow, an event that the source access device receives the first message of the suspected abnormal flow, which is sent again to the target access device after the stop period. That is, in this implementation, the source access device does not need to send the indication information indicating to reduce the period of detecting the suspected abnormal flow to the destination access device, so that the resource consumption of the source access device and the bandwidth resource of the source access device can be saved.

Thus, by the method described in this embodiment, the destination access device may reduce the period of detecting the flow information of the suspected abnormal flow after the suspected abnormal flow is recovered from the flow interruption to the data flow that is normally transmitted, so as to achieve the purpose of reducing the preset duration for the destination access device to determine whether the first data amount recorded in the flow table entry is updated. In this way, the destination access device can quickly determine the suspected abnormal flow based on the detection result, and the source access device can further determine whether the communication link transmitting the suspected abnormal flow is abnormal. It can be seen that the method according to this embodiment can ensure the speed of detecting whether the communication link is abnormal, thereby shortening the link convergence time of the communication link.

In other embodiments, if the first message generated in S102 further includes the latest message sequence number of the suspected abnormal flow, the source access device may send the message of the suspected abnormal flow to the destination access device based on the latest message sequence number in the first message after the communication link for transmitting the suspected abnormal flow is restored to be normal. The description of the latest packet sequence number in the third data stream may refer to the description of the latest packet sequence number in the third data stream, which is not repeated. Referring to fig. 7, after S106 described above, the method for detecting a communication link according to the embodiment of the present application further includes S110.

S110, after the communication link for transmitting the suspected abnormal flow is restored, the source access device sends the message of the suspected abnormal flow to the target access device based on the latest message serial number in the first message.

It will be appreciated that in some possible cases, the source access device will buffer messages that have been sent in the data stream transmitted over the last period of time. As an example, for a suspected abnormal flow, the source access device may buffer messages of the suspected abnormal flow that have been sent between the current time and a time 1 ms away from the current time.

In other possible scenarios, the source access device may buffer a preset number of recently sent messages for the data stream being transmitted. For example, for a suspected abnormal flow, when the source access device has recently sequentially sent message 1, message 2, …, and message 50 at the current time, the source access device may buffer 20 messages, i.e., message 31 to message 50.

Optionally, when the source access device sends the data stream, the messages are sent sequentially in the order of increasing the sequence numbers of the messages, and based on the messages cached by the source access device, the source access device can determine the next message of the messages indicated by the latest message sequence number in the cached messages of the suspected abnormal stream according to the latest message sequence number carried in the first message. Further, the source access device may continue to send the message of the suspected abnormal flow to the destination access device through the recovered communication link from the next message. In response, the destination access device may receive a message in a suspected abnormal flow that was not received prior to the communication link being restored.

Optionally, when the source access device caches the sent messages and also caches the sending time of each sent message, based on the message cached by the source access device, the source access device may determine the sending time of the message indicated by the latest message sequence number according to the latest message sequence number carried in the first message, and send the message with the sending time after the sending time to the destination access device through the recovered communication link in the cached message of the suspected abnormal flow. In response, the destination access device may receive a message in a suspected abnormal flow that was not received prior to the communication link being restored.

It can be seen that, by the method described in this embodiment, the source access device can accurately determine the messages that have been sent out but not received by the destination access device due to the abnormal/faulty communication link, and further, the source access device can send these messages to the destination access device through the recovered communication link, so as to avoid the situation of packet loss of data.

The foregoing description of the solution provided by the embodiments of the present application has been mainly presented in terms of a method.

In order to achieve the above functions, as shown in fig. 8, fig. 8 shows a schematic structural diagram of a detection device 80 for a communication link according to an embodiment of the present application. The detecting means 80 of the communication link is applied to the destination access device as described above, and the detecting means 80 of the communication link is used to perform a portion of the method for detecting a communication link performed by the destination access device, for example, a portion of the method shown in fig. 4, 5, 6 or 7 performed by the destination access device. The detection means 80 of the communication link may comprise a determination unit 81, a generation unit 82 and a transmission unit 83.

The determining unit 81 is configured to determine a suspected abnormal flow, where the suspected abnormal flow is a data flow corresponding to a flow table entry that does not update a first data amount within a preset duration, the flow table entry is created by the destination access device after receiving a first packet of the data flow, the flow table entry is used to record flow information of the data flow, the flow information of the data flow includes the first data amount of the data flow, and the first data amount of the data flow is the data size of the data flow received by the destination access device. The generating unit 82 is configured to generate, based on the flow information of the suspected abnormal flow, a first packet including a first data amount of the suspected abnormal flow. The sending unit 83 is configured to send a first packet to a source access device that sends a suspected abnormal flow, where the first packet is used to determine whether a communication link that transmits the suspected abnormal flow is abnormal.

As an example, in connection with fig. 4, the determining unit 81 may be used to perform S101, the generating unit 82 may be used to perform S102, and the transmitting unit 83 may be used to perform S103.

Optionally, the detecting device 80 of the communication link further includes: the detecting unit 84 is configured to periodically detect the flow information in the flow table entry according to the first period. The determining unit 81 is specifically configured to determine that the data stream is a suspected abnormal stream when the data amount in the stream information of the data stream is not updated within a preset duration.

As an example, in connection with fig. 4, the detection unit 84 and the determination unit 81 may be used to perform S101.

Optionally, the detecting device 80 of the communication link further includes: a receiving unit 85, configured to receive a second packet sent by the source access device and indicating to extend the period of the flow information of the detected data flow. An adjusting unit 86, configured to adjust the first period of detecting the flow information in the flow table entry to the second period according to the second message.

As an example, in connection with fig. 5, the receiving unit 85 is configured to respond S107, and the adjusting unit 86 may be configured to perform S108.

Optionally, the receiving unit 85 is further configured to receive periodic sending indication information sent by the source access device, where the periodic sending indication information is used to indicate to reduce the flow information of the detected data flow. The adjusting unit 86 is further configured to adjust the second period of detecting the flow information in the flow table entry to a third period according to the instruction information.

As an example, in connection with fig. 6, the receiving unit 85 is configured to respond S109.

Optionally, the sending unit 83 is specifically configured to send the first message to the source access device through one or more uplink ports of the destination access device.

As an example, in connection with fig. 4, the transmitting unit 83 may be used to perform S103.

Optionally, the flow information of the data flow further includes a latest packet sequence number of the data flow, where the latest packet sequence number of the data flow is a sequence number of a latest packet of the data flow that has been received by the destination access device. In this case, the first message further includes a last message sequence number of the suspected abnormal flow, and the first message further indicates the source access device to send, to the destination access device, a message in the suspected abnormal flow that is not received by the destination access device, based on the last message sequence number of the suspected abnormal flow after the communication link for transmitting the suspected abnormal flow returns to normal.

For a specific description of the above alternative modes, reference may be made to the foregoing method embodiments, and details are not repeated here. In addition, the explanation and description of the beneficial effects of any of the detection devices 80 for communication links provided above may refer to the corresponding method embodiments described above, and will not be repeated.

As an example, in connection with fig. 3, the functions implemented by the determining unit 81, the generating unit 82, the detecting unit 84 and the adjusting unit 86 in the detecting device 80 of the communication link may be implemented by the processor 301 in fig. 3 executing the program code in the memory 302 in fig. 3. The functions performed by the transmitting unit 83 and the receiving unit 85 can be realized by the network interface 303 in fig. 3.

As shown in fig. 9, fig. 9 is a schematic structural diagram of a detection device 90 for a communication link according to an embodiment of the present application. The detection means 90 of the communication link is applied to the source access device described above, and the detection means 90 of the communication link is used to perform the portion of the detection method of the communication link performed by the source access device, for example, the portion of the method shown in fig. 4, 5, 6 or 7 performed by the source access device. The detection means 90 of the communication link may comprise, among other things, a receiving unit 91 and a determining unit 92.

A receiving unit 91, configured to receive a first packet sent by a destination access device and used to determine whether a communication link for transmitting a suspected abnormal flow is abnormal. The first message includes a first data amount of the suspected abnormal flow, wherein the first data amount of the suspected abnormal flow is a data size of the suspected abnormal flow received by the target access device. A determining unit 92, configured to determine whether a difference between the transmitted data amount of the suspected abnormal flow and the first data amount of the suspected abnormal flow is greater than a threshold; and if the difference is greater than the threshold, determining that the communication link for transmitting the suspected abnormal flow is abnormal.

As an example, in connection with fig. 4, the receiving unit 91 is configured to respond to S103, and the determining unit 92 may be configured to perform S105-S106.

Optionally, the determining unit 92 is further configured to: before determining whether a difference value between the sent data amount of the suspected abnormal flow and the first data amount of the suspected abnormal flow is greater than a threshold value, determining whether a stop time length of a message for stopping sending the suspected abnormal flow by the source access device is less than a preset time length. And if the stopping time period is less than the predetermined time period, determining whether the difference is greater than a threshold.

As an example, in connection with fig. 4, the determination unit 92 may be used to perform S104-S105.

Optionally, the detecting device 90 for a communication link further includes: and a transmitting unit 93 configured to transmit a second message indicating that the period of the flow information for detecting the suspected abnormal flow is prolonged to the destination access device if the stop time period is longer than the predetermined time period.

As an example, in connection with fig. 5, the transmission unit 93 may be used to perform S107.

Optionally, the sending unit 93 is further configured to send, to the destination access device, indication information indicating to reduce a period of detecting flow information of the suspected abnormal flow when sending the message of the suspected abnormal flow to the destination access device again after the above-mentioned stop period.

As an example, in connection with fig. 6, the transmission unit 93 may be used to perform S109.

Optionally, the first message further includes a last message sequence number of the suspected abnormal flow, where the last message sequence number of the suspected abnormal flow is a sequence number of a last message of the suspected abnormal flow that has been received by the target access device. The sending unit 93 is further configured to send, after the communication link for transmitting the suspected abnormal flow is restored to be normal, a message of the suspected abnormal flow to the destination access device, starting from a next message of the message indicated by the latest message sequence number in the suspected abnormal flow.

As an example, in connection with fig. 7, the transmission unit 93 may be used to perform S110.

For a specific description of the above alternative modes, reference may be made to the foregoing method embodiments, and details are not repeated here. In addition, the explanation and the description of the beneficial effects of any of the detection devices 90 for communication links provided above may refer to the corresponding method embodiments described above, and are not repeated.

As an example, in connection with fig. 3, the functions implemented by the determining unit 92 in the detecting means 90 of the communication link may be implemented by the processor 301 in fig. 3 executing the program code in the memory 302 in fig. 3. The functions performed by the receiving unit 91 and the transmitting unit 93 may be performed by the network interface 303 in fig. 3.

Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It should be noted that the division of the modules in fig. 8 or fig. 9 is illustrative, and is merely a logic function division, and other division manners may be implemented in practice. For example, two or more functions may also be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules.

The embodiment of the application also provides a network system which comprises the destination access equipment and the source access equipment. Wherein the destination access device is configured to perform the portion of the method described in fig. 4, 5, 6 or 7 that is performed by the destination access device and the source access device is configured to perform the portion of the method described in fig. 4, 5, 6 or 7 that is performed by the source access device. And will not be described in detail herein.

The embodiment of the present application further provides a chip system 100, as shown in fig. 10, where the chip system 100 includes at least one processor and at least one interface circuit. By way of example, when the chip system 100 includes one processor and one interface circuit, the one processor may be the processor 101 shown in the solid line box (or the processor 101 shown in the broken line box) in fig. 10, and the one interface circuit may be the interface circuit 102 shown in the solid line box (or the interface circuit 102 shown in the broken line box) in fig. 10. When the chip system 100 includes two processors including the processor 101 shown in the solid line box and the processor 101 shown in the broken line box in fig. 10, and two interface circuits including the interface circuit 102 shown in the solid line box and the interface circuit 102 shown in the broken line box in fig. 10. This is not limited thereto.

The processor 101 and the interface circuit 102 may be interconnected by wires. For example, the interface circuit 102 may be configured to receive a signal (e.g., receive a first message, a second message, or indication information, etc.). For another example, interface circuit 102 may be used to send signals to other devices (e.g., processor 101). The interface circuit 102 may, for example, read instructions stored in a memory and send the instructions to the processor 101. The instructions, when executed by the processor 101, may cause the detection means of the communication link to perform the steps of the above-described embodiments. Of course, the chip system 100 may also include other discrete devices, which are not particularly limited in this embodiment of the present application.

Embodiments of the present application also provide a computer program product, and a computer readable storage medium for storing the computer program product. The computer program product may include one or more program instructions that, when executed by one or more processors, may provide the functionality or portions of the functionality described above with respect to fig. 4, 5, 6, or 7. Thus, for example, one or more features described with reference to S101-S106 of FIG. 4 may be carried by one or more instructions in the computer program product.

In some examples, a detection apparatus, such as the communication link described with respect to fig. 8 or 9, may be configured to provide various operations, functions, or actions in response to one or more program instructions stored through a computer-readable storage medium.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The processes or functions in accordance with embodiments of the present application are produced in whole or in part on and when the computer-executable instructions are executed by a computer. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, a website, computer, server, or data center via a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices including one or more servers, data centers, etc. that can be integrated with the media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method of detecting a communication link for use with a destination access device, the method comprising:

determining a suspected abnormal flow, wherein the suspected abnormal flow is a data flow corresponding to a flow table item with a first data volume which is not updated within a preset time period, the flow table item is created by the target access equipment after receiving the first message of the data flow, the flow table item is used for recording flow information of the data flow, the flow information of the data flow comprises the first data volume of the data flow, and the first data volume of the data flow is the data size of the data flow received by the target access equipment;

generating a first message based on the flow information of the suspected abnormal flow, wherein the first message comprises a first data volume of the suspected abnormal flow;

And sending the first message to a source access device sending the suspected abnormal flow, wherein the first message is used for determining whether a communication link for transmitting the suspected abnormal flow is abnormal.

2. The method of claim 1, wherein the determining a suspected abnormal flow comprises:

periodically detecting flow information in the flow table item according to a first period;

and when the data volume in the stream information of the data stream is not updated within the preset time length, determining that the data stream is the suspected abnormal stream.

3. The method according to claim 2, wherein the method further comprises:

receiving a second message sent by the source access equipment, wherein the second message indicates to prolong the period of detecting the stream information of the data stream;

and adjusting the first period to a second period according to the second message.

4. A method according to claim 3, characterized in that the method further comprises:

receiving indication information sent by the source access equipment, wherein the indication information is used for indicating to reduce the period of detecting stream information of the data stream;

and adjusting the second period to a third period according to the indication information.

5. The method according to any one of claims 1-4, wherein the sending the first message to a source access device that sent the suspected abnormal flow comprises:

And sending the first message to the source access device through one or more uplink ports of the destination access device.

6. The method according to any one of claims 1-5, wherein the flow information of the data flow further includes a latest packet sequence number of the data flow, the latest packet sequence number of the data flow being a sequence number of a latest packet of the data flow that has been received by the destination access device, the first packet further includes a latest packet sequence number of the suspected abnormal flow, and the first packet further instructs the source access device to send, to the destination access device, a packet in the suspected abnormal flow that has not been received by the destination access device, based on the latest packet sequence number of the suspected abnormal flow after the communication link that transmitted the suspected abnormal flow is restored to normal.

7. A method of detecting a communication link, for use with a source access device, the method comprising:

receiving a first message sent by a target access device, where the first message is used to determine whether a communication link for transmitting a suspected abnormal flow is abnormal, the suspected abnormal flow is a data flow sent by the source access device to the target access device, the first message includes a first data volume of the suspected abnormal flow, and the first data volume of the suspected abnormal flow is a data size of the suspected abnormal flow received by the target access device;

Determining whether a difference between the transmitted data amount of the suspected abnormal flow and the first data amount of the suspected abnormal flow is greater than a threshold;

and if the difference value is larger than the threshold value, determining that the communication link for transmitting the suspected abnormal flow is abnormal.

8. The method of claim 7, wherein prior to the determining whether the difference between the amount of transmitted data of the suspected abnormal flow and the first amount of data of the suspected abnormal flow is greater than a threshold, the method further comprises:

determining whether the stopping time length of the message for stopping sending the suspected abnormal flow by the source access equipment is less than a preset time length;

if the stopping time period is less than the predetermined time period, determining whether the difference is greater than the threshold.

9. The method of claim 8, wherein the method further comprises:

and if the stopping time length is longer than the preset time length, sending a second message to the target access equipment, wherein the second message indicates to prolong the period of detecting the flow information of the suspected abnormal flow.

10. The method according to claim 9, wherein the method further comprises:

and sending indication information to the target access equipment when the message of the suspected abnormal flow is sent to the target access equipment again after the stopping time, wherein the indication information indicates to reduce the period of flow information for detecting the suspected abnormal flow.

11. The method according to any of claims 7-10, wherein the first message further comprises a latest message sequence number of the suspected abnormal flow, the latest message sequence number of the suspected abnormal flow being a sequence number of a latest message of the suspected abnormal flow that has been received by the destination access device; the method further comprises the steps of:

and after the communication link for transmitting the suspected abnormal flow is recovered to be normal, starting from the next message of the message indicated by the latest message sequence number in the suspected abnormal flow, and transmitting the message of the suspected abnormal flow to the target access equipment.

12. A device for detecting a communication link, for use with a destination access device, the device comprising:

a determining unit, configured to determine a suspected abnormal flow, where the suspected abnormal flow is a data flow corresponding to a flow table entry with a first data volume not updated within a preset duration, where the flow table entry is created by the destination access device after receiving a first packet of the data flow, and the flow table entry is used to record flow information of the data flow, where the flow information of the data flow includes the first data volume of the data flow, and the first data volume of the data flow is a data size of the data flow that has been received by the destination access device;

The generating unit is used for generating a first message based on the flow information of the suspected abnormal flow, wherein the first message comprises a first data volume of the suspected abnormal flow;

the sending unit is configured to send the first packet to a source access device that sends the suspected abnormal flow, where the first packet is used to determine whether a communication link that transmits the suspected abnormal flow is abnormal.

13. The apparatus of claim 12, wherein the apparatus further comprises:

the detection unit is used for periodically detecting the flow information in the flow table item according to the first period;

the determining unit is specifically configured to determine that the data stream is the suspected abnormal stream when the data amount in the stream information of the data stream is not updated within the preset duration.

14. The apparatus of claim 13, wherein the apparatus further comprises:

a receiving unit, configured to receive a second packet sent by the source access device, where the second packet indicates to extend a period of detecting flow information of the data flow;

and the adjusting unit is used for adjusting the first period into a second period according to the second message.

15. The apparatus of claim 14, wherein the device comprises a plurality of sensors,

The receiving unit is further configured to receive indication information sent by the source access device, where the indication information is used to indicate to reduce a period of detecting stream information of the data stream;

the adjusting unit is further configured to adjust the second period to a third period according to the indication information.

16. The device according to any one of claims 12-15, wherein,

the sending unit is specifically configured to send the first message to the source access device through one or more uplink ports of the destination access device.

17. The apparatus according to any one of claims 12-16, wherein the flow information of the data flow further includes a latest packet sequence number of the data flow, the latest packet sequence number of the data flow being a sequence number of a latest packet of the data flow that has been received by the destination access device, the first packet further includes a latest packet sequence number of the suspected abnormal flow, and the first packet further instructs the source access device to send, to the destination access device, a packet in the suspected abnormal flow that has not been received by the destination access device, based on the latest packet sequence number of the suspected abnormal flow after the communication link that transmitted the suspected abnormal flow is restored to normal.

18. A device for detecting a communication link, for use with a source access device, the device comprising:

a receiving unit, configured to receive a first packet sent by a destination access device, where the first packet is used to determine whether a communication link that transmits a suspected abnormal flow is abnormal, where the suspected abnormal flow is a data flow sent by the source access device to the destination access device, the first packet includes a first data amount of the suspected abnormal flow, and the first data amount of the suspected abnormal flow is a data size of the suspected abnormal flow that has been received by the destination access device;

a determining unit, configured to determine whether a difference between the transmitted data amount of the suspected abnormal flow and the first data amount of the suspected abnormal flow is greater than a threshold; and if the difference is greater than the threshold, determining that the communication link used to transmit the suspected abnormal flow is abnormal.

19. The apparatus of claim 18, wherein the determining unit is further configured to:

before determining whether a difference value between the sent data amount of the suspected abnormal flow and the first data amount of the suspected abnormal flow is greater than a threshold value, determining whether a stop time length of a message for stopping sending the suspected abnormal flow by the source access device is less than a preset time length;

20. The apparatus of claim 19, wherein the apparatus further comprises:

and the sending unit is used for sending a second message to the target access equipment if the stop time length is longer than the preset time length, wherein the second message indicates to prolong the period of detecting the flow information of the suspected abnormal flow.

21. The apparatus of claim 20, wherein the device comprises a plurality of sensors,

the sending unit is further configured to send, when sending the message of the suspected abnormal flow to the destination access device again after the stopping time, indication information to the destination access device, where the indication information indicates to reduce a period of detecting flow information of the suspected abnormal flow.

22. The apparatus according to any one of claims 18-21, wherein the first message further comprises a latest message sequence number of the suspected abnormal flow, the latest message sequence number of the suspected abnormal flow being a sequence number of a latest message of the suspected abnormal flow that has been received by the destination access device;

the sending unit is further configured to send, after the communication link for transmitting the suspected abnormal flow is restored to normal, a message of the suspected abnormal flow to the destination access device from a next message of the message indicated by the latest message sequence number in the suspected abnormal flow.

23. A device for detecting a communication link, comprising: a network interface, one or more processors to receive or transmit data through the network interface, the one or more processors configured to read program instructions stored in memory to perform the method of any of claims 1-6, or 7-11.

24. A network system comprising a destination access device and a source access device; wherein the destination access device is adapted to perform the method of any of claims 1-6 and the source access device is adapted to perform the method of any of claims 7-11.

25. A computer readable storage medium comprising program instructions which, when run on a computer or a processor, cause the computer or the processor to perform the method of any of claims 1-6, or claims 7-11.