In-band telemetry system, method and device

Abstract

The embodiments of the present application provide an in-band telemetry system, method and device for making full use of the flexibility and efficiency of network edge nodes, and the ability to perceive traffic characteristics, to offload the collection decision of INT information to the edge nodes, and the intermediate switches only act according to the specific INT identifier, so as to achieve flexible and adaptive INT collection. The in-band telemetry system includes a first node, a switching device and a second node; the first node obtains the traffic characteristics of the business traffic; and determines the INT policy of the business traffic based on the traffic characteristics; then the first node sends the business message corresponding to the business traffic and carrying the INT policy to the switching device; the switching device collects the INT information corresponding to the business traffic according to the INT policy; the switching device sends the INT information to the second node; finally, the second node generates an INT report based on the INT information and reports the INT report.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to an in-band telemetry system, method and device. Background Art

[0002] The current data center network is huge in scale and the business traffic is complex, which brings great challenges to network operation and maintenance. The network system of traditional data centers uses an out-of-band telemetry monitoring mechanism, which cannot collect the network status of the data center network (DCN) in real time, and the software defined network (SDN) controller cannot make optimization and management actions according to the real-time network status in time; the out-of-band information collector used in network operation and maintenance needs to collect telemetry information from each network node (network card and switch), resulting in excessive collector load and poor real-time performance; the industry has introduced in-band telemetry (INT) technology, which can support the embedding of telemetry information in network packets, such as delay, port number, queue usage, timestamp, etc., and insert corresponding metadata in each hop network device that supports this feature. Finally, the sink node extracts the telemetry information from the packet and reports it to the collector, thereby realizing real-time collection of network status and tenant-level traffic status perception, and improving network operation and maintenance efficiency.

[0003] Existing INT technologies mainly rely on intermediate devices such as switches to decide on the collection of telemetry information and generate telemetry reports. This not only complicates the design of switches, but also makes it difficult to achieve more refined INT collection control because switches cannot distinguish the characteristics of specific traffic. Summary of the invention

[0004] The embodiments of the present application provide an in-band telemetry system, method and device for making full use of the flexibility and efficiency of network edge nodes and the ability to perceive traffic characteristics, offloading the collection decision of INT information to the edge nodes, and the intermediate switches only act according to specific INT identifiers, thereby realizing flexible and adaptive INT collection.

[0005] In the first aspect, an embodiment of the present application provides an in-band telemetry system, which includes a first node, a switching device, and a second node; wherein the first node serves as a source node, the switching device may be a switch, and the second node serves as a receiving node. In this embodiment, the first node obtains the traffic characteristics of the service traffic; and determines the INT policy of the service traffic based on the traffic characteristics; then the first node sends a service message of the service traffic to the switching device, and the service message carries the INT policy; after receiving the service message, the switching device parses the service message to obtain the INT policy, and collects the INT information corresponding to the service traffic based on the INT policy; the switching device sends the service message corresponding to the service traffic to the second node, and carries the INT information in the service message; finally, after receiving the service message, the second node parses the service message to obtain the INT information, generates an INT report based on the INT information, and reports the INT report.

[0006] In this embodiment, the first node and the second node both include a host and an intelligent network card. The host runs a management process of the control plane, which is mainly responsible for the management of business traffic, and generates corresponding filter table items according to the traffic characteristics of the business traffic, and sends them to the intelligent network card. The intelligent network card performs the identification of part of the business traffic, such as identifying the business traffic as an elephant flow or the business traffic as a mouse flow, and reports the identification result to the host control plane. In addition, an INT unit is also running on the intelligent network card. At the source node, the INT unit is mainly responsible for INT detection identification of the matching business traffic according to the INT filtering rules unloaded by the control plane. At the receiving node, the INT unit is responsible for completing the extraction and reporting of INT information, and undertakes the preprocessing of part of the INT information to reduce the load of the collector. A special INT collection unit is run on the switching device, which mainly inserts corresponding INT information into specific business traffic according to the INT policy in the business message.

[0007] In this embodiment, the network edge nodes (such as the first node and the second node) are fully utilized to be flexible and efficient, and have the ability to perceive traffic characteristics, and the collection decision of INT information is offloaded to the edge nodes. The intermediate switches only act according to specific INT policies, thereby realizing flexible and adaptive INT collection.

[0008] Optionally, the specific manner in which the first node determines the INT policy of the business traffic based on the traffic characteristics may be as follows: the first node determines the INT policy of the business traffic from the INT collection rule table based on the traffic characteristics, wherein the INT collection rule table is used to indicate the correspondence between the traffic characteristics and the INT policy, and the INT policy includes an INT option and a flow type identifier. It can be understood that the INT option is used to indicate which information the switching device collects, and the flow type identifier is used to indicate the traffic characteristics of the business traffic. In this way, the edge node identifies the traffic characteristics of each business traffic, and then determines whether to perform INT collection and how to perform INT collection based on the traffic characteristics, so that the INT policy can be adjusted flexibly and efficiently, thereby reducing the load on the collector that receives the INT report.

[0009] Optionally, the INT option includes at least one of: hop-by-hop forwarding delay, cumulative delay, queue depth, overall buffer occupancy, port utilization, ingress and egress timestamps, cumulative number of bytes forwarded by the port, and cumulative number of packets forwarded by the port.

[0010] Optionally, the flow type identifier includes at least one of the following: the flow type identifier is a mouse flow or an elephant flow; the flow type identifier is a delay-sensitive flow or a non-delay-sensitive flow; the flow type identifier is an east-west flow or a north-south flow. In this embodiment, matching is performed based on the flow type identifier and the INT option, which can effectively ensure the accuracy of the INT collection information, thereby reducing the amount of INT information collected by the switch, thereby reducing the load of the collector receiving the INT report.

[0011] Optionally, based on the above solution, when the first node carries the INT policy through the service message, the first node inserts the INT policy into the service message in the form of an INT header.

[0012] Optionally, the specific manner in which the switching device collects the INT information corresponding to the service flow according to the INT policy may be as follows: the switching device obtains its own status information, wherein the own status information includes information such as port occupancy, buffer occupancy, current information transmission delay or accumulated delay accumulated on the switching device; then the switching device collects the INT information corresponding to the service flow according to the own status information and the INT policy. The switch realizes adaptive collection of INT information according to its own status information and the INT policy, effectively reducing the load of the collector receiving the INT report.

[0013] Optionally, the specific manner in which the second node generates an INT report according to the INT information and reports the INT report may be as follows: the second node pre-processes the INT information according to a preset rule to generate an INT report; and then reports the INT report.

[0014] In an exemplary scheme, the preset rules include at least one of the following: generating an INT report when the accumulated delay is greater than a first threshold; generating an INT report when the link utilization is greater than a second threshold; generating an INT report when the link jitter exceeds a preset range; generating an INT report when the buffer occupancy rate of the switching device is greater than a third threshold; generating an INT report when the path of the service message is switched.

[0015] In an exemplary solution, in order to reduce the load, the second node may use the committed access rate (CAR) to limit the speed of the INT report when reporting the INT report. In an exemplary solution, when the INT report is marked as a non-sensitive report, the second node reports the INT report when the CAR is dyed green, and discards the INT report when the CAR is dyed yellow or red; when the INT report is marked as a sensitive report, the second node reports the INT report when the CAR is dyed green or yellow, and discards the INT report when the CAR is dyed red.

[0016] It is understandable that when the second node adopts the CAR speed limiting system, two layers can be designed, one for the entire network system and one for a single tenant (ie, a single user).

[0017] In the second aspect, an embodiment of the present application provides an in-band telemetry method, including: the first node obtains the traffic characteristics of the business traffic; and determines the INT policy of the business traffic based on the traffic characteristics; then the first node sends a business message of the business traffic to the switching device, and the business message carries the INT policy; after receiving the business message, the switching device parses the business message to obtain the INT policy, and collects INT information corresponding to the business traffic based on the INT policy.

[0018] In this embodiment, the first node includes a host and an intelligent network card. The host runs a management process of the control plane, which is mainly responsible for the management of business traffic, and generates corresponding filter table items according to the traffic characteristics of the business traffic, and sends them to the intelligent network card. The intelligent network card performs the identification of part of the business traffic, such as identifying the business traffic as an elephant flow or the business traffic as a mouse flow, and reports the identification result to the host control plane. In addition, an INT unit is also running on the intelligent network card. At the source node, the INT unit is mainly responsible for INT detection identification of the matching business traffic according to the INT filtering rules unloaded by the control plane. If the first node is a receiving node, the INT unit is responsible for completing the extraction and reporting of INT information, and undertakes the preprocessing of part of the INT information to reduce the load of the collector. A special INT collection unit is run on the switching device, which mainly inserts corresponding INT information into specific business traffic according to the INT policy in the business message.

[0019] In this embodiment, the network edge nodes (such as the first node) are fully utilized to be flexible and efficient, and have the ability to perceive traffic characteristics, and the collection decision of INT information is offloaded to the edge nodes. The intermediate switches only act according to specific INT policies, thereby achieving flexible and adaptive INT collection.

[0020] Optionally, the specific manner in which the first node determines the INT policy of the business traffic based on the traffic characteristics may be as follows: the first node determines the INT policy of the business traffic from the INT collection rule table based on the traffic characteristics, wherein the INT collection rule table is used to indicate the correspondence between the traffic characteristics and the INT policy, and the INT policy includes an INT option and a flow type identifier. It can be understood that the INT option is used to indicate which information the switching device collects, and the flow type identifier is used to indicate the traffic characteristics of the business traffic. In this way, the edge node identifies the traffic characteristics of each business traffic, and then determines whether to perform INT collection and how to perform INT collection based on the traffic characteristics, so that the INT policy can be adjusted flexibly and efficiently, thereby reducing the load on the collector that receives the INT report.

[0021] Optionally, the INT option includes at least one of the following: hop-by-hop forwarding delay, cumulative delay, queue depth, overall buffer occupancy, port utilization, ingress and egress timestamps, cumulative number of bytes forwarded by a port, and cumulative number of packets forwarded by a port.

[0022] Optionally, the flow type identifier includes at least one of the following: the flow type identifier is a mouse flow or an elephant flow; the flow type identifier is a delay-sensitive flow or a non-delay-sensitive flow; the flow type identifier is an east-west flow or a north-south flow. In this embodiment, matching is performed based on the flow type identifier and the INT option, which can effectively ensure the accuracy of the INT collection information, thereby reducing the amount of INT information collected by the switch, thereby reducing the load of the collector receiving the INT report.

[0023] Optionally, based on the above solution, when the first node carries the INT policy through the service message, the first node inserts the INT policy into the service message in the form of an INT header.

[0024] Optionally, when the first node serves as a receiving node, the first node may also receive INT information sent by an INT switching device; then generate an INT report according to the INT information, and report the INT report.

[0025] In an exemplary solution, the specific manner in which the first node generates an INT report according to the INT information and reports the INT report may be as follows: the first node pre-processes the INT information according to a preset rule to generate an INT report; and then reports the INT report.

[0026] In an exemplary scheme, the preset rules include at least one of the following: generating an INT report when the accumulated delay is greater than a first threshold; generating an INT report when the link utilization is greater than a second threshold; generating an INT report when the link jitter exceeds a preset range; generating an INT report when the buffer occupancy rate of the switching device is greater than a third threshold; generating an INT report when the path of the service message is switched.

[0027] In an exemplary solution, in order to reduce the load, the first node may use the CAR rate limit system to report the INT report when reporting the INT report. In an exemplary solution, when the INT report is marked as a non-sensitive report, the first node reports the INT report when the CAR is dyed green, and discards the INT report when the CAR is dyed yellow or red; when the INT report is marked as a sensitive report, the first node reports the INT report when the CAR is dyed green or yellow, and discards the INT report when the CAR is dyed red.

[0028] It is understandable that when the first node adopts the CAR rate limiting system, two layers can be designed, one for the entire network system and one for a single tenant (ie, a single user).

[0029] In a third aspect, the present application provides a communication device having a function of implementing the first node behavior in the second aspect. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0030] In a possible implementation, the device includes a unit or module for executing each step of the second aspect above. For example, the device includes: an acquisition module for acquiring traffic characteristics of service traffic; a processing module for determining the in-band telemetry INT strategy of the service traffic according to the traffic characteristics; a sending module for sending the service message of the service traffic to the switching device, the service message carrying the INT strategy, so that the switching device collects the INT information of the service traffic according to the INT strategy.

[0031] Optionally, a storage module is also included for storing necessary program instructions and data of the communication device.

[0032] In a possible implementation, the device includes: a processor and a transceiver, the processor being configured to support the communication device to perform the corresponding functions in the method provided in the second aspect. The transceiver is used to instruct the communication between the communication device and the switching device and its network device, and to send the service message involved in the above method to the switching device or receive the service message sent by the switching device. Optionally, the device may also include a memory, which is coupled to the processor and stores the necessary program instructions and data of the communication device.

[0033] In a possible implementation, when the device is a chip in a communication device, the chip includes: a processing module and a transceiver module. The processing module may be, for example, a processor, which is used to obtain the traffic characteristics of the service traffic; determine the in-band telemetry INT strategy of the service traffic according to the traffic characteristics, and the transceiver module may be, for example, an input / output interface, a pin or a circuit on the chip, etc., and transmit the service message carrying the INT strategy generated by the processor to other chips or modules coupled to the chip. The processing module can execute the computer execution instructions stored in the storage unit to support the communication device to execute the method provided in the first aspect above. Optionally, the storage unit may be a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit located outside the chip, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), etc.

[0034] In a possible implementation, the device includes: a processor, a baseband circuit, a radio frequency circuit and an antenna. The processor is used to control the functions of each circuit part, and the baseband circuit is used to generate a service message containing an INT strategy, which is processed by the radio frequency circuit for analog conversion, filtering, amplification and up-conversion, and then sent to the switching device via the antenna. Optionally, the device also includes a memory, which stores the necessary program instructions and data of the communication device.

[0035] In one possible implementation, the device includes a communication interface and a logic circuit, the communication interface is used to obtain traffic characteristics of business traffic; the logic circuit is used to determine the in-band telemetry INT strategy of the business traffic based on the traffic characteristics; the communication interface is used to send the business message of the business traffic to the switching device, the business message carries the INT strategy, so that the switching device collects the INT of the business traffic according to the INT strategy.

[0036] Among them, the processor mentioned in any of the above places can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the above-mentioned data transmission methods.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to execute any possible implementation method of any of the above aspects.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method of any one of the above aspects.

[0039] In a sixth aspect, the present application provides a chip system, which includes a processor for supporting a communication device to implement the functions involved in the above aspects, such as generating or processing the data and / or information involved in the above methods. In one possible design, the chip system also includes a memory, which is used to store the necessary program instructions and data of the communication device to implement the functions of any of the above aspects. The chip system can be composed of chips, or it can include chips and other discrete devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is an exemplary schematic diagram of the system architecture in the embodiment of the present application;

[0041] Figure 2 This is an exemplary structural diagram of an edge node in an embodiment of the present application;

[0042] Figure 3 This is an exemplary structural diagram of a switching device in an embodiment of the present application;

[0043] Figure 4 This is a schematic diagram of an embodiment of the in-band telemetry method in the embodiment of the present application;

[0044] Figure 5 A schematic diagram of the service message format with an INT header in an embodiment of the present application;

[0045] Figure 6 A schematic diagram of a service message format with an INT header and INT information in an embodiment of the present application;

[0046] Figure 7 This is another schematic diagram of the service message format with an INT header and INT information in an embodiment of the present application;

[0047] Figure 8 This is a schematic diagram of the workflow of CAR speed limiting in an embodiment of the present application;

[0048] Fig. 9 This is an application scenario diagram of in-band telemetry in an embodiment of the present application;

[0049] Fig.10 This is a schematic diagram of an embodiment of an in-band telemetry system in an embodiment of the present application;

[0050] Fig.11 A schematic diagram of an embodiment of a communication device in an embodiment of the present application;

[0051] Fig.12 FIG. 2 is a schematic diagram of another embodiment of a communication device in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present application more clear, the embodiments of the present application are described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. It is known to those skilled in the art that with the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0053] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of units in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between units can be electrical or other similar forms, which are not limited in this application. In addition, the units or sub-units described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0054] The technical solutions of the embodiments of the present invention can be applied to various communication systems, such as: Global System of Mobile Communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, Universal Mobile Telecommunication System (UMTS), 5G communication system, and future wireless communication systems, etc.

[0055] like Figure 1 As shown, the system architecture used in the embodiment of the present application can be as follows Figure 1 As shown, the network includes a first node, a switching device, and a second node. The first node and the second node (i.e., edge node) both include a host and an intelligent network card. In an exemplary solution, the structural diagram of the edge node can be as follows: Figure 2 As shown, the control plane process runs on the host of the edge node, which is mainly responsible for the management of business traffic, and generates corresponding filter table entries according to the traffic characteristics of the business traffic, and sends them to the smart network card. The smart network card performs the identification of part of the business traffic, such as identifying the business traffic as elephant flow or the business traffic as mouse flow, and reports the identification results to the host control plane. In addition, an INT unit runs on the smart network card. At the source node, the INT unit is mainly responsible for INT detection and identification of the matching business traffic according to the INT filtering rules unloaded by the control plane. At the receiving node, the INT unit is responsible for completing the extraction and reporting of INT information, and undertakes the preprocessing of part of the INT information to reduce the load of the collector. A special INT collection unit runs on the switching device, which mainly inserts corresponding INT information into specific business traffic according to the INT policy in the business message.

[0056] The switching device in the present application may be a switch, and the network may include multiple switches. The switch may be an access layer switch, a convergence layer switch, or a core layer switch, and the specific situation is not limited here. In an exemplary solution, the structural diagram of the switch may be as follows: Figure 3 As shown, a dedicated INT collection unit is run on the switch, which mainly inserts corresponding INT information into specific service traffic according to the INT policy in the service message. At the same time, the switch can also perform adaptive collection based on its own status information and the INT policy to reduce the load of INT collection.

[0057] It is understandable that the in-band telemetry system also has a centralized collector, which mainly receives INT reports reported by the receiving node, thereby being responsible for aggregating the INT information of the entire network and synchronizing the information to the analyzer or other control planes according to actual operation and maintenance requirements.

[0058] For ease of understanding, some terms in the embodiments of the present application are explained below:

[0059] Inband Network Telemetry (INT): A framework proposed by the P4 Language Alliance (P4.org) to collect and report network status on the data plane. It can integrate data according to network status and quickly detect network failures and sub-health conditions. Inband telemetry does not affect the forwarding path of the original business message, and has low overhead, greatly reducing the operation and maintenance costs of the data center network.

[0060] Data Center Network (DCN): Data Center Network is a network used in data centers. Its internal traffic shows typical characteristics such as centralized exchange data and increased east-west traffic. Data Center Network has strong symmetry and regularity, and is relatively closed.

[0061] Please refer to Figure 4 As shown, an embodiment of the in-band telemetry method in the embodiment of the present application includes:

[0062] 401. The first node identifies traffic characteristics of service traffic.

[0063] When the service traffic is running, the first node senses and identifies the traffic characteristics of the service traffic through the host or smart network card of the first node.

[0064] In this embodiment, the first node may pre-generate a service flow table, wherein the service flow table includes all service flows that may be run in the network where the first node is located. The service flow table may also classify service flows according to the flow characteristics. In an exemplary solution, the specific rules for classifying service flows based on flow characteristics may be as follows:

[0065] 1. Based on the duration and bandwidth usage of business traffic, business traffic is divided into elephant flow or mouse flow. Among them, elephant flow refers to the process of large-scale, continuous data transmission through network links (that is, the data occupies a large bandwidth and the data transmission time is long). Mouse flow refers to the process of small-scale, short-term data transmission through network links (that is, the data occupies a small bandwidth and the duration is short). For example, the information transmission of social software belongs to mouse flow; while the migration of virtual machines belongs to elephant flow.

[0066] 2. Based on the protocol type, priority and other information of the service traffic, the service traffic is divided into delay-sensitive flow or non-delay-sensitive flow. Among them, delay-sensitive flow refers to the data transmission process that achieves low delay, low jitter and zero packet loss rate through the network link (that is, the data transmission process needs to ensure service quality).

[0067] 3. Based on the type of destination node of the business traffic, the business traffic is divided into east-west traffic or north-south traffic. Among them, the business traffic between the client and the server is called north-south traffic, that is, the north-south traffic is server-client traffic. The business traffic between different servers and the business traffic between different data centers is called east-west traffic, that is, the east-west traffic is server-server traffic.

[0068] It is understandable that the same service flow can be marked with at least one flow type identifier at the same time, for example, the service flow can be a rat flow and a delay-sensitive flow.

[0069] 402. The first node determines an INT policy corresponding to the service traffic according to the traffic characteristics.

[0070] After identifying the traffic feature, the first node determines the flow type identifier of the service traffic according to the service flow table, and determines whether the service traffic needs to be detected by INT. If the service traffic needs to be detected by INT, the INT policy corresponding to the service traffic is determined from the pre-generated INT collection rule table according to the flow type identifier of the service traffic, wherein the INT policy at least includes an INT option and the flow type identifier.

[0071] In an exemplary solution, the specific method of the first node in generating the INT collection rule table can be as follows: the host control plane of the first node identifies and classifies the traffic characteristics of part of the business traffic to generate a corresponding business flow table, and unloads the business flow table to the smart network card. The smart network card identifies and classifies the traffic characteristics of part of the business traffic, records the results of the identification and classification into the business flow table, and finally synchronizes the updated business flow table to the host control plane. The host control plane makes decisions on whether to perform INT collection on each business traffic, what information to collect, and the collection interval based on the information recorded in the business flow table. In addition to the switch ID, ingress port and egress port number as mandatory items for identifying the attribution of relevant information, the collected INT information can also include other INT options. The INT option includes at least one of the following: hop-by-hop forwarding delay; cumulative delay; queue depth; overall buffer occupancy; port utilization; timestamp of the ingress port and the timestamp of the egress port; the cumulative number of bytes forwarded by the port and the cumulative number of messages forwarded by the port. The control plane generates an INT collection rule table based on the above information and unloads it to the smart network card. Each information to be collected in the INT collection rule table is marked by an enable bit, and the traffic characteristics are marked by the flow type identifier (and the flow type identifier of the same service traffic can include at least one). Each collection rule can also specify the sampling interval. The optional format of the INT collection rule table is shown in Table 1:

[0072] Table 1

[0073]

[0074] In Table 1, "queue depth: 0" can be used to indicate that the queue depth is not collected, and "port utilization: 1" can be used to indicate that the port utilization is collected. The key can be in other forms besides the five-tuple. The collection interval can be expressed by time, such as "10 microseconds" shown in Table 1; it can also be expressed by the number of service packets, such as collecting every 4 service packets.

[0075] When forwarding a service message, the first node needs to first query the INT collection rule table according to the traffic characteristics of the service traffic corresponding to the service message, and then determine the INT strategy (i.e., a certain INT collection rule in the INT collection rule table) according to the INT collection rule table if the query hits.

[0076] 403. The first node sends a service message corresponding to the service traffic to a switching device, wherein the service message carries the INT policy.

[0077] When forwarding a service message, the first node needs to first query the INT collection rule table according to the traffic characteristics of the service traffic corresponding to the service message, and then insert the INT policy (i.e., the INT collection rule in the INT collection rule table that matches the service traffic) into the service message according to the collection interval setting of the INT collection rule table if the query is hit. In an exemplary solution, the first node can insert the INT policy by inserting the INT header into the service message. At this time, the format of the service message with the INT header can be as follows: Figure 5 As shown: the INT header is inserted between the message header and the payload, wherein the INT header includes the flow type identifier in the INT collection rule table and the enable identifier of the INT option.

[0078] 404. The switching device collects INT information corresponding to the service traffic according to the INT policy.

[0079] After receiving the service message, the switching device parses the service message to obtain the INT policy carried by the service message, and then collects INT information corresponding to the service traffic according to the INT policy.

[0080] In an exemplary solution, in order to reduce the load, the switching device can adaptively collect the INT information corresponding to the service flow according to its own state information and the INT strategy. That is, the switching device determines the collected information according to the flow type indicated by the flow type identifier, the enable bit of the INT option and the state of the switching device itself. The switching device makes adjustments based on its own state in combination with the flow type identified in the INT header, and only when the enable bit is marked as valid, the switching device further determines whether the corresponding INT information needs to be inserted into the service message. For example, for delay-sensitive service traffic, the INT option is to collect hop-by-hop forwarding delay. At this time, the switching device can only perform INT collection (i.e., collect the current hop-by-hop forwarding delay) when it is detected that the forwarding delay of this hop exceeds the preset threshold. In addition, the switching device can also make collection decisions based on buffer usage, port utilization, etc. The general principle is to feedback sensitive states such as congestion and delay in the network as much as possible, and for low load, low delay and other states, INT collection can be reduced or not performed to reduce the load.

[0081] In an exemplary solution, if the switching device identifies that the service traffic is in a sensitive state, the switching device may also mark the INT information as sensitive information in the INT header. The sensitive state here may be used to indicate that the network state is abnormal.

[0082] 405. The switching device sends the INT information to the second node.

[0083] The switching device inserts the collected INT information into the service message, and forwards the service message to the second node.

[0084] In an exemplary solution, the switching device inserts the INT information between the INT header and the payload of the service message. In this case, an optional format of the service message may be as follows: Figure 6 As shown. The metadata is used to indicate the INT information collected by the switching device, and the INT information includes the identification information of the switching device, the ingress port, the egress port number, and the information corresponding to the INT option. If there are multiple switching devices between the first node and the second node, and at least two of the multiple switching devices collect INT information, the format of the service message can be as follows: Figure 7 shown.

[0085] 406. The second node generates an INT report according to the INT information.

[0086] After receiving the service message, the second node parses the service message to obtain INT information on the entire forwarding path, and finally generates an INT report according to the INT information.

[0087] In an exemplary solution, in order to reduce the load, the second node can analyze the INT information of the hop-by-hop switching device and process the INT information according to a preset rule, and only the INT information that meets the preset rule is generated into an INT report. Among them, an exemplary solution of the preset rule and the preprocessing method can be shown in Table 2:

[0088] Table 2

[0089]

[0090] In this embodiment, Table 2 only shows some examples of preset rules. There may be other specific preset rules, which are not limited here, as long as the load can be reduced as much as possible while meeting the operation and maintenance requirements.

[0091] 407. The second node sends the INT report to the collector.

[0092] After generating the INT report, the second node reports the INT to the collector.

[0093] In an exemplary solution, in order to further control the load of the collector, the second node can perform hierarchical CAR rate limiting on the reporting of the INT report. The workflow can be as follows: Figure 8 As shown, after the second node generates the INT report, the INT report is first limited in speed according to the overall network (i.e. Figure 8 After the overall network speed limit stage is passed, the speed of a single user is limited (i.e., the second level speed limit). After the second level speed limit stage is passed, the second node reports the INT report. The specific implementation methods of the overall speed limit and the second level speed limit can be as follows:

[0094] When the INT report is marked as a non-sensitive report, the second node reports the INT report when the CAR is colored green, and discards the INT report when the CAR is colored yellow or red; when the INT report is marked as a sensitive report, the second node reports the INT report when the CAR is colored green or yellow, and discards the INT report when the CAR is colored red.

[0095] In this embodiment, the overall speed limit is taken as an example. The second node performs CAR speed limit coloring on the INT report, and then the second node determines whether the INT report is colored green. If the INT report is colored green, the second node can directly determine that the INT report passes the overall speed limit; if the INT report is not colored green, the second node determines whether the INT report is colored red. If the INT report is colored red, the second node chooses to discard the INT report; if the INT report is not colored red, the second node determines whether the INT report is marked as a sensitive state. If so, the second node determines that the INT report passes the overall speed limit; if not, the second node chooses to discard the INT report. In the overall speed limit, the second node CAR colors the INT report by comparing the bandwidth required for reporting the INT report with the available bandwidth of the entire network for reporting the INT report. If the difference between the available bandwidth and the bandwidth required for the INT report is large, the second node determines that the INT report is colored green; if the available bandwidth is less than the bandwidth required for the INT report, the second node determines that the INT report is colored red; if the difference between the available bandwidth and the bandwidth required for the INT report is small (that is, the available bandwidth is close to the bandwidth required for the INT report), the second node determines that the INT report is colored yellow.

[0096] Similarly, the second level speed limit also adopts the above process, except that the available bandwidth of the second level speed limit is the available bandwidth of a single user. The specific process will not be repeated here.

[0097] The following is an explanation of the in-band telemetry method in the embodiment of the present application using a specific application scenario. Fig. 9 The two-stage three-hop network shown in the figure includes an edge node 1, a first ToR switch, a Leaf switch, a second ToR switch and an edge node 2. The edge node 1 includes a host 1 and a smart network card 1, the first ToR switch serves as a first-hop switch, the Leaf switch serves as a second-hop switch, the second ToR switch serves as a third-hop switch, and the edge node 2 includes a host 2 and a smart network card 2. In this network, the smart network card 1 on the host 1 cooperates with the host 1 to complete the identification of the traffic characteristics of each service flow, and the host 1 sends the pre-generated rule table to the smart network card 1. A service message currently sent matches the hit rule table, and the smart network card 1 identifies the current service message as a delay-sensitive flow message according to the content of the rule table, and the INT information to be collected is the port utilization rate hop by hop.

[0098] After receiving the message, the first ToR switch on the forwarding path parses the service message and finds that there is an INT policy in the service message (that is, the flow type is identified as a delay-sensitive flow, and the INT option is port utilization). At this time, the port utilization of the first ToR switch has reached 126%, exceeding the collection upper limit of 120%, and there is a risk of path overload. Therefore, the first ToR switch inserts its own switch identification, message forwarding port and other necessary information, as well as the current port utilization as INT metadata after the INT option of the original service message, and identifies the INT information in the service message as sensitive information. Then the first ToR switch forwards the service message with the INT metadata inserted to the Leaf switch.

[0099] The Leaf switch parses and processes the message in the same process. At this time, the port utilization of the Leaf switch is only 24%, and there is no risk of path overload. At the same time, under the low-load state of the link, the current service message can be forwarded with low latency to meet the latency-sensitive requirements of the current service message. Therefore, the Leaf switch can collect port utilization information according to the calculated probability. In an exemplary solution, the algorithm description is as follows:

[0100]

[0101] According to the above algorithm, if the value of p is 1, there is only a 6.11% probability that the port utilization information of the current switch will be collected under a link load of 24% of the port utilization. Assume that the leaf switch does not collect port utilization at this time. Then the leaf switch will not insert INT metadata into the service message forwarded by the first ToR switch, but will forward the service message forwarded by the first ToR switch to the second ToR switch again.

[0102] Finally, on the second ToR switch, the port utilization rate of the message forwarding port also exceeds the collection upper limit, so the second ToR switch inserts its own switch identification, message forwarding port and other necessary information, and the current port utilization rate as INT metadata into the metadata of the service message forwarded by the first ToR switch, and identifies the INT information in the service message as sensitive information. Then the second ToR switch forwards the service message with the INT metadata inserted to edge node 2.

[0103] After receiving the service message, edge node 2 strips out the collected INT data and performs preprocessing. It detects that there is an overload risk on the message forwarding path and decides to generate an INT report and report it to the collector. Assuming that all source hosts (i.e. nodes with edge node 1 function) have strict control over INT collection, and the overall INT information collected on the network is within the processing capacity of the collector, the two-level rate limit filtering on the destination host (i.e. node with edge node 2 function) passes, and the final generated INT report is sent to the collector.

[0104] In the embodiment of the present application, the network edge nodes (such as the first node and the second node) are fully utilized to be flexible and efficient, and have the ability to perceive traffic characteristics, and the collection decision of INT information is unloaded to the edge nodes. The intermediate switch only acts according to the specific INT strategy, thereby realizing flexible and adaptive INT collection. At the same time, the collection of INT information and INT reporting are restricted, thereby reducing the load.

[0105] The in-band telemetry method in the embodiment of the present application is described above. The in-band telemetry system and the communication device in the embodiment of the present application are described below.

[0106] Please refer to Fig.10 As shown, the in-band telemetry system in the embodiment of the present application includes a first node 1001, a switching device 1002, and a second node 1003. The first node 1001 is used to obtain the traffic characteristics of the service traffic; determine the in-band telemetry INT strategy of the service traffic according to the traffic characteristics; send the service message of the service traffic to the switching device 1002, and the service message carries the INT strategy;

[0107] The switching device 1002 is used to collect INT information corresponding to the service flow according to the INT policy; and send the INT information to the second node 1003;

[0108] The second node 1003 is used to generate and report an INT report according to the INT information.

[0109] Optionally, the first node 1001 is specifically used to determine the INT policy of the business traffic from the INT collection rule table according to the traffic characteristics, wherein the INT collection rule table is used to indicate the correspondence between the traffic characteristics and the INT policy, and the INT policy includes an INT option and a flow type identifier.

[0110] Optionally, the INT option includes at least one of the following: hop-by-hop forwarding delay, cumulative delay, queue depth, overall buffer occupancy, port utilization, ingress and egress timestamps, cumulative number of bytes forwarded by the port, and cumulative number of packets forwarded by the port.

[0111] Optionally, the flow type identifier includes at least one of the following: the flow type identifier is mouse flow or elephant flow; the flow type identifier is delay-sensitive flow or non-delay-sensitive flow; the flow type identifier is east-west flow or north-south flow.

[0112] Optionally, the first node 1001 is further configured to insert the INT policy into the service message.

[0113] Optionally, the switching device 1002 is specifically configured to obtain its own state information; and collect INT information corresponding to the service traffic according to the own state information and the INT policy.

[0114] Optionally, the second node 1003 is specifically configured to pre-process the INT information according to a preset rule to generate an INT report; and report the INT report.

[0115] Optionally, the preset rules include at least one of the following: generating an INT report when the accumulated delay is greater than a first threshold; generating an INT report when the link utilization is greater than a second threshold; generating an INT report when the link jitter exceeds a preset range; generating an INT report when the buffer occupancy rate of the switching device 1002 is greater than a third threshold; generating an INT report when the path of the service message is switched.

[0116] Optionally, the second node 1003 is specifically configured to report the INT report according to the CAR rate limit.

[0117] Optionally, the second node 1003 is specifically used to, when the INT report is marked as a non-sensitive report, report the INT report when the CAR is colored green, and discard the INT report when the CAR is colored yellow or red; when the INT report is marked as a sensitive report, report the INT report when the CAR is colored green or yellow, and discard the INT report when the CAR is colored red.

[0118] Please refer to Fig.11 As shown, in the embodiment of the present application, the communication device 1100 includes: an acquisition module 1101, a processing module 1102, and a sending module 1103, wherein the acquisition module 1101, the processing module 1102, and the sending module 1103 are connected via a bus. The communication device 1100 can be the first node or the second node in the above method embodiment, and can also be configured as one or more chips in the first node or the second node. The communication device 1100 can be used to perform some or all of the functions of the first node or the second node in the above method embodiment.

[0119] For example, the acquisition module 1101 can be used to execute step 401 in the above method embodiment. For example, the acquisition module 1101 acquires the traffic characteristics of the service traffic; the processing module 1102 can be used to execute step 402 or 406 in the above method embodiment, for example, the processing module 1102 determines the in-band telemetry INT policy of the service traffic according to the traffic characteristics; the sending module 1103 can be used to execute step 403 or step 407 in the above method embodiment. For example, the sending module 1103 sends the service message of the service traffic to the switching device, and the service message carries the INT policy, so that the switching device collects the INT information of the service traffic according to the INT policy.

[0120] Optionally, the communication device 1100 further includes a storage module, which is coupled to the processing module so that the processing module can execute the computer-executable instructions stored in the storage module to implement the functions of the terminal in the above method embodiment. In an example, the storage module optionally included in the communication device 1100 can be a storage unit in the chip, such as a register, a cache, etc., and the storage module can also be a storage unit located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0121] It should be understood that the above Fig.11 The processes executed between the modules of the first node or the second node in the corresponding embodiment are the same as those in the above Figures 1 to 9 The process executed by the first node or the second node in the corresponding method embodiment is similar, and the details will not be repeated here.

[0122] Fig.12 A possible structural diagram of a communication device 1200 in the above embodiment is shown, and the communication device 1200 can be configured as the aforementioned first node or second node. The communication device 1200 may include: a processor 1202, a computer-readable storage medium / memory 1203, a transceiver 1204, an input device 1205 and an output device 1206, and a bus 1201. Among them, the processor, the transceiver, the computer-readable storage medium, etc. are connected via a bus. The embodiment of the present application does not limit the specific connection medium between the above components.

[0123] In one example, the processor 1202 obtains traffic characteristics of the service traffic; determines an in-band telemetry INT strategy of the service traffic according to the traffic characteristics;

[0124] The transceiver 1204 sends the service message of the service traffic to the switching device, and the service message carries the INT policy, so that the switching device collects the INT information of the service traffic according to the INT policy.

[0125] In another example, the processor 1202 may run an operating system to control functions between various devices and components. The transceiver 1204 may include a baseband circuit and a radio frequency circuit, for example, the service message may be processed via the baseband circuit and the radio frequency circuit and then sent to a switching device or a collector.

[0126] The transceiver 1204 and the processor 1202 can implement the above Figures 1 to 9 The corresponding steps in any of the embodiments will not be described in detail here.

[0127] Understandably, Fig.12 Only a simplified design of the communication device is shown. In actual applications, the communication device may include any number of transceivers, processors, memories, etc., and all communication devices that can implement the present application are within the protection scope of the present application.

[0128] The processor 1202 involved in the above-mentioned device 1200 can be a general-purpose processor, such as a CPU, a network processor (NP), a microprocessor, etc., or an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application. It can also be a digital signal processor (DSP), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The controller / processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessors, etc. The processor usually performs logical and arithmetic operations based on program instructions stored in the memory.

[0129] The bus 1201 mentioned above may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.12 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0130] The computer-readable storage medium / memory 1203 involved above may also store an operating system and other application programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the above-mentioned memory may be a ROM, other types of static storage devices that can store static information and instructions, RAM, other types of dynamic storage devices that can store information and instructions, disk storage, etc. The memory 1203 may be a combination of the above-mentioned storage types. And the above-mentioned computer-readable storage medium / memory may be in the processor, or may be outside the processor, or distributed on multiple entities including a processor or a processing circuit. The above-mentioned computer-readable storage medium / memory may be specifically embodied in a computer program product. For example, a computer program product may include a computer-readable medium in a packaging material.

[0131] Alternatively, the embodiment of the present application also provides a general processing system, such as a chip, which includes: one or more microprocessors that provide processor functions; and an external memory that provides at least a portion of the storage medium, all of which are connected to other supporting circuits through an external bus architecture. When the instructions stored in the memory are executed by the processor, the processor executes the communication device in Figures 1 to 9 Part or all of the steps in the in-band telemetry method in this embodiment, and / or other processes used for the technology described in this application.

[0132] The steps of the method or algorithm described in conjunction with the disclosure of the present application can be implemented in a hardware manner, or can be implemented by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile hard disk, a CD-ROM or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a communication device. Of course, the processor and the storage medium can also be present in a communication device as discrete components.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0138] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An in-band telemetry system, characterized in that: include: A first node, a switching device, and a second node, wherein the first node includes a host and a smart network card; The first node obtains traffic characteristics of the service traffic; The first node determines the in-band telemetry INT strategy of the service traffic according to the traffic characteristics; The first node sends the service message of the service traffic to the switching device, where the service message carries the INT policy; The switching device collects INT information corresponding to the service traffic according to the INT policy; The switching device sends the INT information to the second node; The second node generates an INT report according to the INT information and reports it; The first node determines the in-band telemetry INT strategy of the service traffic according to the traffic characteristics, including: The first node determines the INT policy of the service traffic from an INT collection rule table according to the traffic characteristics, wherein the INT collection rule table is used to indicate the correspondence between traffic characteristics and INT policies, and the INT policy includes INT options and flow type identifiers.

2. The system according to claim 1, characterized in that The INT option includes at least one of: hop-by-hop forwarding delay, cumulative delay, queue depth, overall buffer occupancy, port utilization, ingress and egress timestamps, port cumulative forwarding bytes and port cumulative forwarding messages.

3. The system according to claim 1, characterized in that The stream type identifier includes at least one of: The flow type is identified as a mouse flow or an elephant flow; The flow type is identified as a delay-sensitive flow or a delay-insensitive flow; The flow type is identified as east-west flow or north-south flow.

4. The system according to any one of claims 1 to 3, characterized in that Before the first node sends the service message of the service flow to the switching device, the first node is further configured to insert the INT policy into the service message.

5. The system according to claim 1, characterized in that The switching device collecting INT information corresponding to the service traffic according to the INT policy includes: The switching device obtains its own status information; The switching device collects INT information corresponding to the service traffic according to the own status information and the INT policy.

6. The system according to claim 1, characterized in that The second node generates an INT report according to the INT information and reports the INT report including: The second node pre-processes the INT information according to a preset rule to generate an INT report; The second node reports the INT report.

7. The system according to claim 6, characterized in that The preset rules include at least one of the following: Generate an INT report when the accumulated delay is greater than a first threshold; generating an INT report when the link utilization is greater than a second threshold; Generate an INT report when the link jitter exceeds the preset range; When the buffer occupancy rate of the switching device is greater than the third threshold, an INT report is generated; An INT report is generated when the path of a service message is switched.

8. The system according to any one of claims 6 or 7, characterized in that The second node reporting the INT report includes: The second node reports the INT report according to the committed access rate CAR speed limit.

9. The system according to claim 8, characterized in that The second node reporting the INT report according to the CAR speed limit system includes: When the INT report is marked as a non-sensitive report, the second node reports the INT report when the CAR is colored green, and discards the INT report when the CAR is colored yellow or red; When the INT report is marked as a sensitive report, the second node reports the INT report when the CAR is colored green or yellow, and discards the INT report when the CAR is colored red.

10. An in-band telemetry method, characterized in that: include: The first node obtains traffic characteristics of service traffic, wherein the first node includes a host and a smart network card; The first node determines the in-band telemetry INT strategy of the service traffic according to the traffic characteristics; The first node sends the service message of the service traffic to the switching device, where the service message carries the INT policy, so that the switching device collects INT information of the service traffic according to the INT policy; The first node determines the in-band telemetry INT strategy of the service traffic according to the traffic characteristics, including: The first node determines the INT policy of the service traffic from an INT collection rule table according to the traffic characteristics, wherein the INT collection rule table is used to indicate the correspondence between traffic characteristics and INT policies, and the INT policy includes INT options and flow type identifiers.

11. The method according to claim 10, characterized in that The INT options include at least one of: hop-by-hop forwarding delay, cumulative delay, queue depth, overall buffer occupancy, port utilization, ingress and egress timestamps, cumulative number of bytes forwarded by the port, and cumulative number of messages forwarded by the port.

12. The method according to claim 10, characterized in that The stream type identifier includes at least one of: The flow type is identified as a mouse flow or an elephant flow; The flow type is identified as a delay-sensitive flow or a delay-insensitive flow; The flow type is identified as east-west flow or north-south flow.

13. The method according to any one of claims 10 to 12, characterized in that Before the first node sends the service message of the service flow to the switching device, the method further includes: The first node inserts the INT policy into the service message.

14. The method according to claim 10, characterized in that The method further comprises: The first node receives INT information sent by the switching device; The first node generates an INT report according to the INT information and reports it.

15. The method according to claim 14, characterized in that The first node generating an INT report according to the INT information and reporting the report includes: The first node pre-processes the INT information according to a preset rule to generate an INT report; The first node reports the INT report.

16. The method according to claim 15, characterized in that The preset rules include at least one of the following: Generate an INT report when the accumulated delay is greater than a first threshold; generating an INT report when the link utilization is greater than a second threshold; Generate an INT report when the link jitter exceeds the preset range; When the buffer occupancy rate of the switching device is greater than the third threshold, an INT report is generated; An INT report is generated when the path of a service message is switched.

17. The method according to any one of claims 15 or 16, characterized in that The first node reporting the INT report includes: The first node reports the INT report according to the CAR rate limiting system.

18. The method according to claim 17, characterized in that The first node reporting the INT report according to the CAR speed limit system includes: When the INT report is marked as a non-sensitive report, the first node reports the INT report when the CAR is colored green, and discards the INT report when the CAR is colored yellow or red; When the INT report is marked as a sensitive report, the first node reports the INT report when the CAR is colored green or yellow, and discards the INT report when the CAR is colored red.

19. A communication device, characterized in that: The device is used to implement the behavior of the first node according to claim 1 to claim 18, and the device includes: An acquisition module, used to acquire traffic characteristics of business traffic; A processing module, used for determining an in-band telemetry INT strategy for the service traffic according to the traffic characteristics; A sending module, used for sending the service message of the service flow to the switching device, wherein the service message carries the INT policy, so that the switching device collects the INT information of the service flow according to the INT policy; The processing module is specifically used to determine the INT policy of the business traffic from the INT collection rule table according to the traffic characteristics, wherein the INT collection rule table is used to indicate the correspondence between the traffic characteristics and the INT policy, and the INT policy includes an INT option and a flow type identifier.

20. The communication device according to claim 19, characterized in that The INT options include at least one of: hop-by-hop forwarding delay, cumulative delay, queue depth, overall buffer occupancy, port utilization, ingress and egress timestamps, cumulative number of bytes forwarded by the port, and cumulative number of messages forwarded by the port.

21. The communication device according to claim 19, characterized in that: The stream type identifier includes at least one of: The flow type is identified as a mouse flow or an elephant flow; The flow type is identified as a delay-sensitive flow or a delay-insensitive flow; The flow type is identified as east-west flow or north-south flow.

22. The communication device according to any one of claims 19 to 21, characterized in that: The processing module is further used to insert the INT policy into the service message.

23. The communication device according to claim 19, characterized in that The communication device also includes a receiving module for receiving INT information sent by the switching device; The processing module is used to generate an INT report according to the INT information; The sending module is used to report the INT report.

24. The communication device according to claim 23, characterized in that The processing module is specifically used to pre-process the INT information according to preset rules to generate an INT report.

25. The communication device according to claim 24, characterized in that The preset rules include at least one of the following: Generate an INT report when the accumulated delay is greater than a first threshold; generating an INT report when the link utilization is greater than a second threshold; Generate an INT report when the link jitter exceeds the preset range; When the buffer occupancy rate of the switching device is greater than the third threshold, an INT report is generated; An INT report is generated when the path of a service message is switched.

26. The communication device according to any one of claims 24 or 25, characterized in that: The sending module is specifically configured to report the INT report according to the CAR speed limit system.

27. The communication device according to claim 26, characterized in that The sending module is specifically configured to report the INT report when the INT report is marked as a non-sensitive report and when the CAR is colored green, and discard the INT report when the CAR is colored yellow or red; When the INT report is marked as a sensitive report, the INT report is reported when the CAR is dyed green or yellow, and the INT report is discarded when the CAR is dyed red.

28. A communication device, characterized in that: The device comprises at least one processor and a memory, wherein the processor is configured to be coupled to the memory, and the processor calls instructions stored in the memory to control the communication device to execute the method according to any one of claims 10 to 18.

29. A computer storage medium storing computer instructions for executing the method of any one of claims 10 to 18.

30. A computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the method according to any one of claims 10 to 18.

Images