CN115941540A - Message processing device, node equipment and method - Google Patents

Abstract

The application discloses a message processing device, node equipment and a method; wherein the apparatus is provided in a node device; the device comprises a control module and a message processing module; wherein: a communication connection is established between the control module and the message processing module; the communication connection does not include a protocol stack in the node device for processing network data packets; at least part of processing units in the message processing module are arranged in the kernel space of the node equipment; the message processing module is used for receiving and responding to a control instruction sent by the control module through the communication connection, sending a detection message to the target equipment and receiving a reply message sent by the target equipment; processing the reply message, and determining the link state between the node equipment and the target equipment; wherein, the detection message and the reply message comprise network management and maintenance OAM messages.

Description

Message processing device, node device and method

technical field

The present application relates to the field of network technologies, and in particular to a message processing device, node device and method.

Background technique

In practical applications, the processing method for packets related to network management and maintenance (Operation, Administration, and Management, OAM) is not flexible enough.

Contents of the invention

Based on the above problems, the embodiments of the present application provide a packet processing device, node device and method.

The technical solution provided by the embodiment of this application is as follows:

An embodiment of the present application provides a message processing device, the device includes: the device is set in a node device; the device includes a control module and a message processing module; wherein:

A communication connection is established between the control module and the message processing module; the communication connection does not include a protocol stack for processing network data packets in the node device;

At least part of the processing units in the message processing module are set in the kernel space of the node device; the message processing module is used to receive and respond to the control command sent by the control module through the communication connection, and send a detection send the message to the target device, and receive the reply message sent by the target device; process the reply message, and determine the link state between the node device and the target device; wherein, the detection report The message and the reply message include a network management and maintenance OAM message.

In some embodiments, the message processing module includes a message sending unit and a message sending unit; wherein:

The message sending unit is configured to send a first message to the target device; the message sending unit is arranged in the kernel space; wherein, the first message includes at least a loopback detection message (Loop Back Message, LBM), connectivity detection message (Continuity Check Message, CCM) and link tracking message (Link TraceMessage, LTM);

The message receiving unit is configured to receive the reply message, acquire additional data carried in the reply message, and determine the link state based on the additional data.

In some embodiments, the message receiving unit is configured to determine the node device and the target device based on the time information in the additional data when the reply message is a second message transmission delay and/or packet loss rate; wherein, the second message at least includes a connectivity detection message CCM.

In some embodiments, the message receiving unit is configured to determine the node device and the target device based on the time information in the additional data when the reply message is a third message The transmission delay between; wherein, the third message includes at least a loop back response message (Loop Back Reply, LBR).

In some embodiments, the message receiving unit is configured to determine the node device and the target device based on the device information in the additional data when the reply message is a fourth message Link path information between; wherein, the fourth message includes at least a link trace response message (Link Trace Reply, LTR);

The message receiving unit is further configured to obtain the first address and the second address when receiving the fifth message, and set the source address of the fifth message as the first address, and set the The destination address of the fifth message is the second address, the message type of the fifth message is set as LTR, and the LTR is sent through a fast data path (eXpress DataPath, XDP); wherein, the fifth The packet includes at least the LTM; the first address includes the address of the node device; the second address includes the address of the device sending the LTM.

In some embodiments, the message receiving unit is configured to obtain the first address and the third address when receiving the sixth message, and set the source address of the sixth message as the An address, setting the destination address of the sixth message as the third address, setting the message type of the sixth message as LBR, and sending the LBR through XDP; wherein the sixth message is at least The LBM is included; the first address includes the address of the node device; the third address includes the address of the device sending the LBM.

In some embodiments, the message receiving unit includes a general execution engine (Extended Berkeley Packet Filter, eBPF) XDP of Berkeley Packet Filter (Berkeley Packet Filter, BPF); the control module is used to load the eBPF XDP into A network card of the node device.

In some embodiments, the message receiving unit and the control module are set in the user space; the message processing module also includes a message filtering unit set in the kernel space, which is used to quickly data through the address family The path (Address Family Express Data Path, AF_XDP) sends the OAM message to the message receiving unit.

In some embodiments, the control module is configured to load the message processing module to the network card when it is determined that the network card of the node device is a designated network card.

The embodiment of the present application also provides a node device, where the node device includes the packet processing apparatus as described in any one of the preceding items.

The embodiment of the present application also provides a message processing method, and the method is applied to a message processing device arranged in a node device; the message processing device includes a control module and a message processing module; the control module and A communication connection is established between the message processing modules; the communication connection does not include a protocol stack for processing network data packets in the node device; at least part of the processing units in the message processing module are set in the The kernel space of above-mentioned node equipment; Described method comprises:

The message processing module receives and responds to the control command sent by the control module through the communication connection, sends a detection message to the target device, and receives a reply message sent by the target device;

The message processing module processes the reply message to determine the link status between the node device and the target device; wherein, the detection message and the reply message include an OAM message.

In the message processing device provided in the embodiment of the present application, at least part of the processing units of the message processing module are set in the kernel space of the node device, thereby greatly improving the efficiency of the message processing module in processing detection messages and reply messages; secondly, control The communication connection between the module and the message processing module does not include the protocol stack for processing network data packets, which can reduce the link of data transmission between the control module and the message processing module, and shorten the instruction transparent transmission and data transmission between the two. and the message processing module can directly process the reply message after receiving the reply message to determine the link state between the node device and the target device, thereby improving the processing efficiency of the OAM message Efficiency, which improves the efficiency of link state determination.

Therefore, the message processing device provided by the embodiment of the present application not only gets rid of the dependence on dedicated hardware chips, specific network card devices, and dedicated data processing kits such as DPDK, but also compared to the software OAM message processing scheme in the related art, the present application The efficiency of OAM packet processing by the packet processing device provided by the embodiment is improved.

Description of drawings

FIG. 1 is a schematic structural diagram of processing an OAM message provided in the related art;

FIG. 2 is another schematic structural diagram for processing OAM packets provided by related technologies;

FIG. 3 is a schematic structural diagram of a message processing device provided in an embodiment of the present application;

FIG. 4 is another schematic structural diagram of a message processing device provided in an embodiment of the present application;

FIG. 5 is a schematic structural diagram of the LBM sent by the message sending unit provided by the embodiment of the present application;

FIG. 6 is a schematic structural diagram of sending a CCM by a message sending unit provided in an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an LTM sent by a message sending unit provided in an embodiment of the present application;

FIG. 8 is a schematic structural diagram of OAM packet transmission between a first device and a second device provided in an embodiment of the present application;

FIG. 9 is another schematic structural diagram of OAM message transmission between the first device and the second device according to the embodiment of the present application;

FIG. 10 is a schematic structural diagram of a node device provided in an embodiment of the present application;

FIG. 11 is a schematic flowchart of a message processing method provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

In practical applications, the OAM packet processing logic is usually implemented through dedicated hardware chips such as Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (Field Programmable Gate Array, FPGA) or Network Processor (Network Processor , NP) to achieve. However, such a solution relies heavily on a dedicated hardware chip, and if the support of the dedicated hardware chip is lost, the OAM message processing function cannot be realized.

In order to get rid of the dependence on dedicated hardware chips, a method for realizing OAM packet processing by software is also proposed in the related art, and the OAM packet processing logic is set in user space. Figure 1 shows the OAM packet processing method provided in the related art The structure schematic diagram of text, as shown in Figure 1, the user space of source device 101 is provided with active device OAM 1011, and the kernel space is provided with source device network protocol stack 1012 and source device network card 1013; The user space of target device 102 is provided with target device OAM 1021, the kernel space is provided with target device network protocol stack 1022 and target device network card 1023. Wherein, the source device OAM 1011 and the target device OAM 1021 can realize OAM packet processing logic.

In Fig. 1, no matter the source device 101 sends the OAM message, or the target device 102 receives the OAM message, all need to pass the source device OAM 1011 and the source device network protocol stack 1012, and the target device OAM1021 and the target device network protocol stack 1022 It can only be realized by copying and copying the OAM message between them, which will occupy a large amount of data processing resources.

In order to get rid of the dependence on hardware chips, reduce the occupation of data processing resources, and improve the defect of insufficient time delay accuracy of traditional software implementation schemes, the related technology also proposes the use of Data Plane Development Kit (DPDK) to process The OAM message solution, in which DPDK is mainly based on the Linux system, is a function library and driver set for fast data packet processing, which can greatly improve data processing performance and throughput, and improve the work efficiency of data plane applications.

FIG. 2 is a schematic diagram of another structure for processing OAM packets provided by the related art. As shown in Figure 2, the source device DPDK 1014 in the source device 101 is set in the kernel space, the setting mode of other modules is the same as that in Figure 1, the target device DPDK 1024 in the target device 102 is set in the kernel space, and the setting mode of other modules is the same as that of Figure 1 Figure 1 is the same. In Figure 2, the source device DPDK1014 and the source device OAM1011, and the target device DPDK 1024 and the target device OAM1011 can directly share data through the memory, thereby improving the OAM packet processing efficiency. However, in the above solution, DPDK needs specific network card support, so the versatility is insufficient.

To sum up, the OAM packet processing in the related art is not flexible enough to meet the actual OAM packet processing requirements.

Based on the above problems, an embodiment of the present application provides a packet processing device, a node device and a method, and the packet processing device may be set in a node device.

In one embodiment, the node device may include a computer device, such as a server device or a personal computer device; Exemplarily, the node device may include a physical machine device or a virtual machine device; Exemplarily, the node device may include a maintenance domain (Maintenance Domain, MD) in the maintenance endpoint (Maintenance Association EndPoint, MEP) or maintenance intermediate point (Maintenance Association Intermediate Point, MIP); among them, MEP is used to determine the scope and boundaries of MD, is the Maintenance Association (Maintenance Association, MA) For edge nodes, multiple MAs can be configured in the MD; MIPs are located inside the MD, and the manageability of the MD network can be improved by deploying multiple MIPs between MEPs.

In an implementation manner, the node device may include a device capable of receiving, sending and processing data packets.

FIG. 3 is a schematic structural diagram of a message processing device 3 provided in an embodiment of the present application. As shown in FIG. 3 , the device may include a control module 301 and a message processing module 302; wherein:

A communication connection is established between the control module 301 and the message processing module 302; the communication connection does not include a protocol stack for processing network data packets in the node device;

At least part of the processing units in the message processing module 302 are set in the kernel space of the node device, and are used to receive and respond to the control instructions sent by the control module 301 through the communication connection, send the detection message to the target device, and receive the information sent by the target device. Reply message; process the reply message to determine the link status between the node device and the target device.

Wherein, the detection message and the reply message include an OAM message.

Exemplarily, the user space may include the running space of the user application program in the node device.

In one embodiment, the control module 301 may be set in the user space and/or kernel space of the node device; for example, the control module 301 may include a plurality of control units, and at least part of the control units in the plurality of control units may be set In the user space of the node device.

In one embodiment, the control module 301 and the message processing module 302 can be software modules capable of realizing the control function and the message processing function respectively; for example, the communication connection between them can include the data between the software modules Transmission interface and/or function call relationship; for example, the above-mentioned communication connection may include an electrical connection channel capable of realizing data transmission between two modules, which is not limited in this embodiment of the present application.

In one embodiment, the protocol stack for processing network data packets may include a source device network protocol stack and a target device network protocol stack as shown in FIG. 1 and FIG. 2; The data communication protocol encapsulates and packs the source data to obtain a data packet, and analyzes the data packet based on the data communication protocol to obtain the source data; for example, the above-mentioned data communication protocol may include a standard communication protocol, such as Transmission Control Protocol/Internet Protocol (Transmission Control Protocol/Internet Protocol, TCP/IP).

In an implementation manner, the kernel space of the node device may include a space in which a kernel process in the node device runs and/or manages.

In one embodiment, the control instruction sent by the control module 301 may include triggering the message processing module 302 to start running, sending a message, receiving a message, parsing a message, message processing cycle, message processing time, and message At least one instruction data in the associated target message is processed.

In one embodiment, the control module 301 can also send data to the message processing module 302 through the communication connection, and the message processing module 302 can process the received data to generate a detection message.

In one embodiment, the message processing module 302 may include multiple processing units, and at least one processing unit in the multiple processing units may be set in the kernel space; for example, all the processing units in the message processing module 302 may be All set in kernel space.

In one embodiment, the message processing module 302 can generate a detection message according to the control command when the control command is to send a message, and determine the device information of the target device according to the control command, and then based on the device information of the target device Send the detection message to the target device; Exemplarily, the message processing module 302 can switch to the message receiving state after sending the detection message, and after receiving the reply message, process the reply message to determine Link state: Exemplarily, the message processing module 302 may directly switch to the message receiving state when the control instruction is message interception, so as to receive reply messages or receive detection messages sent by other devices.

In one embodiment, the link status may include at least one of link transmission delay, packet loss rate, number of links between the node device and the target device, and the number of device nodes included in each link; exemplary Specifically, after the link state is determined, the message processing module 302 may send the message to the control module 301 through the communication connection, so that it can manage or output the link state.

In one embodiment, the node device and the target device may be located in the same MA or MD; for example, the node device and the target device may be of the same type, for example, both are MEP, or both are MIP; for example, the node device The type of the target device can be different, for example, the node device is an MEP, and the target device can be a MIP.

In one embodiment, the detection message and the reply message may include a connection fault management (Connectivity Fault Management, CFM) message in OAM, wherein, CFM is used to realize network end-to-end connectivity fault detection, fault notification and The fault location function can monitor the connectivity of the entire network through CFM, and the combination of CFM technology and protection switching technology can improve the reliability of the network.

It can be seen from the above that the message processing device provided by the embodiment of the present application is set in the node device, and the communication connection between the control module and the message processing module does not include the protocol stack used for processing network data packets set in the node device; At least part of the processing units in the text processing module are set in the kernel space of the node device, and after being able to receive and respond to the control command sent by the control module, send a detection message to the target device, receive a reply message sent by the target device, and then The reply message is processed to determine the link state between the node device and the target device, and the detection message and the reply message include an OAM message.

Therefore, in the message processing device provided by the embodiment of the present application, at least part of the processing units in the message processing module are set in the kernel space of the node device, thereby greatly improving the efficiency of the message processing module in processing detection messages and reply messages. efficiency; secondly, the communication connection between the control module and the message processing module does not include a protocol stack for processing network data packets, thereby reducing the link of data transmission between the control module and the message processing module and shortening the time between the two. command transparent transmission and data transmission delay; and, after receiving the reply message, the message processing module can directly process the reply message to determine the link status between the node device and the target device, thereby improving the The efficiency of OAM message processing improves the determination efficiency of the link state. Therefore, the message processing state provided by the embodiment of the present application not only gets rid of the dependence on dedicated hardware chips, specific network card devices, and special data processing kits such as DPDK, but also compares to the software OAM message processing scheme in the related art. The efficiency of OAM packet processing by the packet processing device provided by the embodiment is improved.

FIG. 4 is another schematic structural diagram of a message processing device provided in the embodiment of the present application. As shown in FIG. 4 , the message processing module 302 includes a message sending unit 3021 and a message receiving unit 3022; wherein:

The message sending unit 3021 is configured to send the first message to the target device; the message sending unit 3021 is set in the kernel space; wherein, the first message includes at least LBM, CCM and LTM;

The message receiving unit 3022 is configured to receive a reply message, obtain additional data carried in the reply message, and determine a link state based on the additional data.

In one embodiment, the message sending unit 3021 can analyze the control instruction, and when it is determined that the control instruction indicates that the first message required to be sent is an LBM, it can generate an LBM and obtain the timestamp in the LBM, and then send From LBM to the target device; Exemplarily, Layer 2 Ping (macping/ethping) detection can be implemented through LBM; Exemplarily, when the first message is LBM, the target device can be at least one device.

Fig. 5 is a schematic diagram of the structure of the message sending unit sending LBM provided by the embodiment of the present application. As shown in Fig. 5, the first MEP 501 can be a node device, and the LBM sent by the first MEP 501 can pass through the first MIP 502 and the first MIP 502 and the first MEP 502 After the second MIP 503, transmit to the second MEP 504; Exemplarily, the second MEP 504 may be the target device. Exemplarily, the control module of the first MEP 501 can trigger the message sending unit 3021 to send the LBM through the following control instructions:

Sending CFM LBM to b4:96:91:98:4e:2c.

In the above control instruction, b4:96:91:98:4e:2c may indicate the address of the target device, that is, the second MEP 504.

When sending the LBM, the message sending unit 3021 can output the following information:

64bytes from b4:96:91:98:4e:2c:cfm_seq＝2017870625time＝0.267ms

64bytes from b4:96:91:98:4e:2c:cfm_seq＝2017870626time＝0.239ms

64bytes from b4:96:91:98:4e:2c:cfm_seq＝2017870627time＝0.234ms

In the above information, 64bytes can represent the data volume of the LBM sent, cfm_seq can represent the message identifier of each LBM; time can represent the timestamp of each LBM; it can be seen from the above data that the node device, that is, the first MEP501 can Continuously send the LBM to the target device, that is, the second MEP 504.

Exemplarily, the message sending unit 3021 can time stamp the first message through the eBPF traffic classifier (Traffic Classifier, TC), wherein, the TC is an eBPF hook in the Linux network processing flow, and can mount the eBPF program, It provides a variety of functions including modifying packets, rerouting (reroute), and discarding packets (drop). These functions will affect the traffic statistics of the kernel, and therefore also affect the queuing rules (Queueing Discipline, QD) of data packets. ; Moreover, eBPF TC is the link closest to the hardware at the sending end, so it can improve the efficiency of timestamp setting and shorten the sending time of OAM messages.

In practical applications, CCM can realize the connectivity detection function, wherein, the connectivity detection function is used to detect the connectivity status between the maintenance endpoints, usually the MEP can periodically send the CCM, and other MEPs and MIPs in the same MA can receive the CCM. If the MEP does not receive the CCM message within 3.5 cycles, it can determine that the link status is abnormal.

In one embodiment, the message sending unit 3021 may obtain time information of the CCM, such as a timestamp in the CCM, and send the CCM when it is determined that the control instruction indicates that the first message to be sent is a CCM; Exemplarily, the target device at this time is multiple devices, that is to say, the message sending unit 3021 can broadcast the CCM to multiple devices; Exemplarily, the message sending unit 3021 can multicast the CCM to at least one group of MAs equipment.

Exemplarily, any device in the MA, such as an MEP, can serve as a target device for multicasting CCM by node devices in the MA.

FIG. 6 is a schematic structural diagram of sending a CCM by a message sending unit provided in an embodiment of the present application. As shown in Figure 6, the first MEP 501, the first MIP 502, the second MIP 503, the second MEP 504, the third MEP 505 and the third MIP 506 can be located in the same MA, wherein the first MEP 501, the second Both the MEP 504 and the third MEP 505 can be used as node devices for sending CCMs. At the same time, the target devices corresponding to the first MEP 501 can include the second MEP 504 and the third MEP 505, that is, the target of the MEP sending CCMs in the MA The equipment may include other MEPs in the MA except the MEP sending the CCM.

Exemplarily, the message sending unit 3021 may continuously send the CCM at a specified time interval.

In one embodiment, when the message sending unit 3021 determines that the control instruction indicates that the first message to be sent is an LTM, it can obtain the time information of the LTM, such as the timestamp in the LTM, and send the LTM; example Exemplarily, the target device at this time may be multiple devices, that is, the message sending unit 3021 may broadcast the LTM to multiple devices; for example, any MEP in the MA may serve as the target device for the node device to broadcast the LTM.

FIG. 7 is a schematic structural diagram of a message sending unit sending an LTM according to an embodiment of the present application. As shown in FIG. 7, the first MEP 501 may be a node device sending an LTM, and the second MEP 504 and the third MEP 505 may be target devices receiving an LTM.

Exemplarily, the control module of the first MEP 501 can trigger the message sending unit 3021 to send the LTM to the target device through the following control instructions.

Sending CFM LTM probe to 78:ac:44:1b:33:90

Wherein, 78:ac:44:1b:33:90 may represent the address of any target device.

In an implementation manner, the message receiving unit 3022 may be set in the kernel space.

In one embodiment, the reply message may be sent by the target device, or may be sent by an intermediate device between the node device and the target device, where the intermediate device may include the first MIP as shown in Figures 5 to 7 and the second MIP.

In an implementation manner, the additional data may include data parsed by the message receiving unit 3022 from the reply message, such as a time stamp and device information of the device that sent the reply message.

In one embodiment, the message receiving unit 3022 can obtain the detection message corresponding to the reply message, and then determine the link status based on the detection message and additional data; for example, the message receiving unit 3022 can At least part of the data and additional data carried in the text determine the link state; for example, at least part of the data carried in the detection message may include the address of the node device, the time stamp of the detection message and other data.

In an implementation manner, after determining the link status, the message receiving unit 3022 may send the message to the control module 301 through a communication connection.

In an implementation manner, the packet receiving unit 3022 may also determine that the link state is in an abnormal state if no reply packet is received within a specified time.

As can be seen from the above, the message processing module of the message processing device provided in the embodiment of the present application includes a message sending unit and a message receiving unit, and the message sending unit is used to obtain the time information of the first message and send the first message To the target device; wherein, the first message includes at least LBM, CCM and LTM, and the message receiving unit is used to receive the reply message, obtain additional data in the reply message, and then determine the link state based on the additional data.

Thus, the message sending unit included in the message processing module in the message processing device provided in the embodiment of the present application can realize the flexible sending of various CFM messages; and, since the message sending unit is arranged on the node device Kernel space, so it can also realize the efficient sending of various CFM messages; at the same time, after the message receiving unit receives the reply message, it can directly determine the link status based on the additional data in the reply message, so that it can The time for link state determination is shortened, and the efficiency of link state determination is improved.

Based on the foregoing embodiments, the message receiving unit 3022 in the embodiment of the present application is configured to determine the transmission between the node device and the target device based on the time information in the additional data when the reply message is the second message. Delay and/or packet loss rate; wherein, the second packet includes at least CCM.

Exemplarily, the second message may be a reply message of the CCM.

Exemplarily, when the reply message is not the second message, the message receiving unit 3022 may not perform the process of acquiring additional data and determining the transmission delay and/or packet loss rate between the node device and the target device. operate.

In one embodiment, when the message receiving unit 3022 receives the CCM, it can update the receiving timer of the CCM, and determine the node device and the target device according to the time information in the CCM additional data and the time information when sending the CCM. The data packet transmission time between, that is, the transmission delay of the link.

Exemplarily, after the node device sends the CCM through the message sending unit 3021, the control module 301 can trigger the message receiving unit 3022 to switch to the CCM receiving mode.

Exemplarily, the control module 301 can output the following instruction to trigger the message receiving unit 3022 to switch to the CCM receiving mode. In the following instruction, Listening on interface enol for CFM frames means waiting for the reply of the CFM frame.

Listening on interface enol for CFM frames.

Exemplarily, the message receiving unit 3022 can output the following information during the process of receiving the CCM, wherein, revd CCM:78:ac:44:1b:21:a8,level 0,MD"mdl",MA"mal" Indicates that a CCM is received from a device named mal, an MD named mdl, and an address of 78:ac:44:1b:21:a8, and the priority level of receiving the CCM is 0; meanings of other command lines It is the same as above and will not be repeated here.

revd CCM:78:ac:44:1b:21:a8,level 0,MD"mdl",MA"mal"

revd CCM:9c:dc:71:c3:85:68,level 0,MD"md1",MA"mal"

revd CCM:78;ac:44:1b:21:a8,level 0,MD"mdl",MA"mal"

revd CCM:9c:dc:71:c3:85:68,level 0,MD"mdl",MA"mal"

Exemplarily, as shown in FIG. 6, since the CCM is a multicast message, a node device such as the first MEP 501 may receive a CCM from at least one target device, for example, from the above command line ac:44:1b: The second MEP 504 corresponding to 21:a8 and the third MEP 505 corresponding to 9c:dc:71:c3:85:68 receive the CCM. In practical applications, if the node device does not receive the CCM within 3.5 cycles, the message receiving unit 3022 may determine that the link is in an abnormal state.

Exemplarily, the packet receiving unit 3022 may count the number of CCMs it sends and the number of CCMs it receives, so as to determine the packet loss rate between the node device and the target device.

It can be seen from the above that the message receiving unit of the message processing device provided by the embodiment of the present application can determine the time between the node device and the target device based on the timestamp in the additional data when the reply message is the second message. transmission delay and/or packet loss rate, and the second packet includes at least CCM.

Therefore, the message processing device provided by the embodiment of the present application can directly receive the CCM through the message receiving unit and determine the transmission delay and/or packet loss rate based on the timestamp in the CCM, thereby realizing the communication between the node device and the target device Efficient determination of the transmission delay and/or packet loss rate of the link state between them.

Based on the aforementioned embodiments, in the message processing device provided by the embodiment of the present application, the message receiving unit 3022 is used to determine the node device and the target device based on the time information in the additional data when the reply message is the third message. Transmission delay between devices; wherein, the third packet includes at least LBR.

Exemplarily, if the reply packet received by the packet receiving unit 3022 is not the third packet, the operation of determining the transmission delay between the device node and the target device may not be performed.

In practical applications, the LBR is a reply packet of the LBM.

In one embodiment, the device node sending the LBR may include the target device, and may also include an intermediate device between the device node sending the LBR and the target device. For example, in FIG. 5, the first MEP 501 may be the device node sending the LBM A device node, the second MEP 504 can be a target device, and a first MIP 502 and a second MIP 503 are also set between the first MEP 501 and the second MEP 504, these two node devices can be intermediate devices, the two After the intermediate device receives the LBM, it can send the LBR to the first MEP 501, and these two intermediate devices can also forward the LBM to the next-level node at the same time, until the LBM reaches the second MEP 504, and the second MEP 504 receives the LBR During LBM, LBR may also be sent to the first MEP 501 through the first MIP 502 and the second MIP 503.

Exemplarily, when the message receiving unit 3022 receives the LBR, it can obtain the identification information and time information of the LBR from the additional data of the LBR, and determine the LBM corresponding to the LBR based on the identification information, and then based on the LBM corresponding to the LBR The time information and the time information carried by LBR can determine the transmission delay between the node device and the target device, and can also determine the transmission delay between the node device and the intermediate device, so as to obtain the link from the node device to the target device The overall transmission delay distribution status of .

It can be seen from the above that in the message processing device provided by the embodiment of the present application, when the reply message is the third message, the message receiving unit can determine the distance between the device node and the target device based on the time information in the additional data. The data transmission delay of , wherein, the third packet includes LBR.

Therefore, the message processing device provided by the embodiment of the present application can efficiently and quickly realize the processing of LBR through the message receiving unit, so as to more efficiently determine the data transmission delay between the node device and the target device.

Based on the foregoing embodiments, in the message processing device provided in the embodiment of the present application, the message receiving unit 3022 is configured to determine the node device and Link path information between target devices; wherein, the fourth message includes at least LTR;

The message receiving unit 3022 is further configured to obtain the first address and the second address when the fifth message is received, and set the source address of the fifth message as the first address, and set the purpose of the fifth message The address is the second address, set the message type of the fifth message to LTR, and send LTR through XDP; wherein, the fifth message includes at least LTM; the first address includes the address of the node device, and the second address includes the device sending LTM the address of.

For example, if the reply message received by the message receiving unit 3022 is not the fourth message, the operation of determining the link path information between the node device and the target device based on the device information in the additional data may not be performed. .

Exemplarily, if the message received by the message receiving unit 3022 is not the fifth message, it may not perform obtaining the first address and the second address, and set the original address of the fifth message as the first address, and set An operation in which the destination address of the fifth message is the second address.

In practical applications, the LTR is the reply packet of the LTM.

In one embodiment, the message receiving unit 3022 can obtain and record information such as the time to live (Time To Live, TTL) and Replay Action of the LTR message from the additional data, and determine the node device and the information according to the TTL and Reply Action Link path information between peripheral devices, such as whether the communication link between the node device and the target device is connected, whether there is an intermediate device between the node device and the target device, and the number and type of the intermediate device.

It should be noted that LTM is a multicast message, and LTR is a unicast message. For example, in FIG. During the transmission process, the intermediate devices associated with the second MEP 504 may include the first MIP 502 and the second MIP 503, and the third MIP 506 directly transparently transmits the LTM to the second MEP 504 because it does not have the LTM processing function, that is to say , the first MEP 501 can multicast LTM to at least one MEP, and the intermediate device, the second MEP 504 and the third MEP 505 are unicast operations when sending LTR, that is to say, the above-mentioned node devices only pass the LTR through the intermediate device Send to the first MEP 501, but not send the LTR to other node devices.

In one embodiment, the first address may include an Internet Protocol (Internet Protocol, IP) address or a Media Access Control address (Media Access Control, MAC) of the node device. Exemplarily, the second address may be from the fifth obtained by parsing the message; the second address may include the IP address or MAC address of the device sending the LTM.

In one embodiment, when the message receiving unit 3022 receives the LTM, the node device where the message receiving unit 3022 is located may be the target device, and the node device actively sending the LTM may be the source device; The device node to the target device may include a MEP in the MA, and may also include a MIP in the MA, wherein the node level of the device receiving the LTM is the same as that of the node sending the LTM.

Exemplarily, the LTMs sent by the same node device can be respectively routed to different devices. For example, in FIG. 7, in the process of sending the LTM by the first MEP 501, the first MIP 502 and the second MIP 503 can receive the LTM, and, When the first MIP 502 receives the LTM, it can send it to the second MIP 503, and the second MIP 503 can send the LTM to the second MEP 504 through the third MIP 506. Since the third MIP 506 does not support the LTM processing function, the third MIP 506 When receiving the LTM sent by the node device, it is directly transparently transmitted to the second MEP 504. In the above process, the first MIP 502, the second MIP 503 and the second MEP 504 can all be equipped with a message receiving unit 3022 Similarly, the third MEP 505 in FIG. 7 may also be a node device provided with a message receiving unit 3022.

Exemplarily, in the network, there may be multiple node devices sending LTMs, and the LTMs sent by multiple different node devices may be routed to the same node device, for example, the second MEP 504 and the third MEP 505 in FIG. 7 may Simultaneously send the LTM to the first MEP 501; Exemplarily, the target device sending the LTM and the node device receiving the LTM are located in the same MA or in different MAs.

Exemplarily, after the source address and destination address of the LTM are set, and the packet type of the LTM is changed to LTR, the LTR can be sent through XDP according to the sending path of the LTM.

Among them, XDP is the general execution engine (Extended Berkeley Packet Filter, eBPF) of the Berkeley Packet Filter (BPF) in the Linux network processing flow. Collection can greatly improve data processing performance and throughput, thereby improving the data processing efficiency of data plane applications. Among them, BFP is a network filter. After it is upgraded to eBPF, it is not only used for network analysis, but has developed into a tool and platform including development performance analysis, system tracking, network optimization and other types of functions. The Linux kernel will load eBPF.

It can be seen from the above that the message receiving unit in the message processing device provided by the embodiment of the present application can determine the connection between the node device and the target device based on the device information in the additional data when the received reply message is an LTR. Link path information, thus, the message processing device provided by the embodiment of the present application can quickly and efficiently determine the link path information between any node device and the target device through the message receiving unit; the message receiving unit, It can quickly set the source address and destination address of the received LTM, and can quickly modify the type of LTM message, so as to realize the fast conversion of LTM; and, by quickly sending LTR through XDP, it can also The efficient sending processing of the LTR is realized, thereby realizing the efficient processing of the LTM through the message receiving unit.

Based on the foregoing embodiments, in the message processing device provided in the embodiment of the present application, the message receiving unit 3022 is configured to acquire the first address and the third address when the sixth message is received, and set the sixth message The source address of the message is the first address, the destination address of the sixth message is set as the third address, the message type of the sixth message is set as LBR, and the LBR is sent through XDP.

Wherein, the sixth message includes the LBM, the first address includes the address of the node device, and the third address includes the address of the device sending the LBM.

Exemplarily, if the packet received by the packet receiving unit 3022 is not the sixth packet, the operation of acquiring the first address and the third address may not be performed.

In an implementation manner, the third address may include an IP address or a MAC address of the device sending the LTM, which is not limited in this embodiment of the present application.

Exemplarily, when the message receiving unit 3022 receives the LBM and modifies the message type of the LBM to LBR, the node device where the message receiving unit 3022 is located may be the first MIP 502, the second MIP 503 and the first MIP 503 in FIG. Two MEP 504; Exemplarily, the first MEP 501 can be the source device that sends the LBM, after the first MEP 501 sends the LBM, can obtain the first MIP 502, the second The time information in the LBR sent by the MIP 503 and the second MEP 504, and determine the transmission delay between each node device between the first MEP 501 and the second MEP 504 according to the time information.

As can be seen from the above, after receiving the LBM, the message receiving unit in the message processing device provided by the embodiment of the present application can modify the source address and the destination address for the LBM in real time, and can also modify the message type of the LBM to LBR and The LBR is sent quickly through XDP, which provides data support for any node device in the network to quickly and accurately determine the network transmission delay.

FIG. 8 is a schematic structural diagram of an OAM packet transmission between a first device and a second device according to an embodiment of the present application. As shown in FIG. 8 , the first device 801 may be the node device in the foregoing embodiments, and the second device 802 may be the target device in the foregoing embodiments, such as an MEP, or an intermediate device such as a MIP.

Exemplarily, the user space of the first device 801 may be provided with a first control module 8011, wherein the first control module 8011 may be the control module in the foregoing embodiments, and the kernel space may be provided with a first sending unit 8012, a first receiving A unit 8013, a first protocol stack 8014, and a first driver module 8015; wherein, the first sending unit 8012 and the first receiving unit 8013 can be the message sending unit and the message receiving unit in the foregoing embodiments respectively; the first protocol stack 8014 may be a network protocol stack set in the first device 801; the first driver module 8015 may be a network driver module set in the first device 801.

Exemplarily, the second control module 8021, the second sending unit 8022, the second receiving unit 8023, the second protocol stack 8024, and the second driver module 8025 in the second device 802 are respectively connected with the first control module 8011, the first The functions of the sending unit 8012, the first receiving unit 8013, the first protocol stack 8014, and the first driver module 8015 are the same and will not be repeated here.

Exemplarily, the first control module 8011 set in the user space of the first device 801 can bypass the first protocol stack 8014 and directly control the first sending unit 8012 via the first driver module 8015, through the integrated XDP such as XDP_eBPF sends LBM, CCM and LTM to the second device 802 .

Exemplarily, when the second receiving unit 8023 of the second device 802 receives the CCM, it can determine the time between the first device 801 and the second device 802 based on the time when it receives the CCM and the timestamp in the previously sent CCM. The data transmission delay can also set time information for the CCM, and send the CCM to the first device 801, so that the first device 801 can determine the distance between itself and the second device 802 based on the sent CCM and the received CCM. transmission delay and/or packet loss rate etc.

Exemplarily, when the second receiving unit 8023 receives the LBM, it can set the message type of the LBM to LBR, set the destination address of the LBM to the address of the first device 801, and set the source address of the LBM to the address of the second device 802, and send the LBR to the first device 801 through XDP in the second receiving unit 8023; for example, after the first receiving unit 8013 receives the LBR sent by the second device 802, it can send the time information of the LBM according to it And the time stamp in the LBR to determine the transmission delay between it and the second device 802 .

Exemplarily, when the second receiving unit 8023 receives the LTM, it can modify the message type of the LTM to LTR, and set the source address of the LTR to the address of the second device 802, and set the destination address of the LTR to the address of the first device 801. address, and then send the LTR to the first device 801 through XDP; for example, when the first receiving unit 8013 receives the LTR, it can determine the connection between the first device 801 and the second device 802 according to the TTL and Action Reply in the LTR. Link path information.

Exemplarily, if the second device 802 is the target device of the first device 801, after receiving the OAM message, the second device 802 may generate a reply message and send it to the first device 801; If the device 802 is an intermediate device such as the MIP in the foregoing embodiments, the second device 802 can transmit the message sent by the first device 801 to the node device in the direction of the target device, and can also send a reply message to the first device at the same time.

Exemplarily, if the message received by the first receiving unit 8013, the first sending unit 8012, the second sending unit 8022, and the second receiving unit 8023 is not an OAM message, they may not perform any processing on the message, and Transparently transmit the message to the target device or target application indicated by the message.

It can be seen from the above that since the control module is set in the user space, the message processing modules related to the actual sending and receiving of the message, such as the message sending unit and the message receiving unit, are set in the kernel space, and the message sending can be done through XDP, etc. Realization, thereby realizing the operations such as fast sending, receiving and processing of the OAM data packet by bypassing the protocol stack.

Based on the aforementioned embodiments, in the processing device provided by the embodiments of the present application, the message receiving unit includes eBFP XDP; a control module, configured to load the eBFP XDP to the network card of the node device.

In one embodiment, the control module can obtain the performance parameter information of the network card of the node device, and when determining that the network card of the node device supports the XDP offload mode (offload) function according to the performance parameter information, load the eBFP XDP to the network card of the node device.

It can be seen from the above that the message processing device provided by the embodiment of the present application can load the eBFPXDP of the message receiving unit to the network card of the node device, because eBPF XDP is the link closest to the hardware in the node device, and can directly process the message The operation, zero copy, can reduce the resource overhead in the data copy process, thereby further improving the processing efficiency of the message processing device for sending and receiving messages.

Based on the aforementioned embodiments, in the message processing device provided by the embodiment of the present application, the message receiving unit is set in the user space, and the message processing module also includes a message filtering unit set in the kernel space, which is used to send the OAM message through AF_XDP to the message receiving unit.

FIG. 9 is another schematic structural diagram of OAM message transmission between the first device and the second device provided by the embodiment of the present application. Units and modules with the same names as those in FIG. 8 in FIG. 9 will not be described repeatedly.

As shown in Figure 9, the first receiving unit 8013 and the second receiving unit 8023 are respectively set in the user space of the first device 801 and the user space of the second device 802; and, the first filtering unit 8016 is added to the first device 801 , a second filtering unit 8026 is added to the second device 802; wherein, the first filtering unit 8016 and the second filtering unit 8026 may be the aforementioned packet filtering units.

Exemplarily, the first filtering unit 8016 and the second filtering unit 8026 can judge the type of the message when receiving the message, and if the message is of OAM type, such as LTM, CCM, LBR and LTR, the OAM The message is transparently transmitted to the first receiving unit 8013 and the second receiving unit 8023, so that the first receiving unit 8013 and the second receiving unit 8023 can further process the OAM message; for example, if the message is not of the OAM type , then the packet can be transparently transmitted to the target application in the first device 801 and the second device 802 .

Exemplarily, the first filtering unit 8016 and the second filtering unit 8026 can respectively transmit the OAM message to the first receiving unit 8013 and the second receiving unit 8023 through the AF-XDP socket. Among them, AF_XDP, like AF_INET and AF_PACKET, belongs to a type of Address Family. AF_XDP socket directly reroutes the data packets received by the network card to the user space through XDP, thereby realizing fast data transmission bypassing the network protocol stack and user space. Therefore, high-performance network report processing between the network card and the user space can be realized. In practical applications, AF_XDP is the user mode interface of XDP.

As can be seen from the above, the message processing device provided by the embodiment of the present application can still receive OAM messages through the message filtering unit set in the kernel space when the message receiving unit is set in the user space. In the kernel space, and between it and the message receiving unit, AF_XDP can be used to bypass the protocol stack for fast data transmission, so as to realize fast reception and processing of OAM messages.

Based on the foregoing embodiments, in the message processing device provided in the embodiments of the present application, the control module may load the message processing module to the network card when it is determined that the network card of the node device is a designated network card.

Exemplarily, when the control module determines that the network card of the node device is not the designated network card, it may implement the message processing function through the method provided in the foregoing embodiments.

Exemplarily, the specified network card may include a network card that has the function of efficiently sending and receiving OAM messages, and can quickly process the OAM message, thereby determining the link state; Exemplarily, the specified network card may include an intelligent network card; After the message processing module is loaded into the smart network card, the message processing logic of the message processing module can be realized through the microcode in the smart network card.

As can be seen from the above, the message processing device provided by the embodiment of the present application can load the message processing module to the network card when the network card of the node device is a designated network card, and can load the message processing module to the network card when the designated network card is a smart network card. Efficient data processing capabilities and intelligent data judgment logic can further improve the efficiency and intelligence of OAM packet processing.

Based on the foregoing embodiments, the embodiment of the present application also provides a node device 10. FIG. 10 is a schematic structural diagram of the node device 10 provided in the embodiment of the present application. As shown in FIG. 10, the node device may include the The message processing device 3 provided.

It can be seen from the above that the node device provided by the embodiment of the present application includes a message processing device, and at least part of the processing units of the message processing module in the message processing device are set in the kernel space of the node device, so that the processing and detection of the message processing module can be greatly improved. The efficiency of the message and the reply message; secondly, the communication connection between the control module and the message processing module does not include a protocol stack for processing network data packets, thereby reducing the data transmission between the control module and the message processing module. link, shortening the time delay of instruction transparent transmission and data transmission between the two; and, after receiving the reply message, the message processing module can directly process the reply message to determine the link between the node device and the target device. link state, thereby improving the efficiency of OAM packet processing and improving the efficiency of link state determination.

Based on the aforementioned embodiments, the embodiment of the present application also provides a message processing method, which is applied to a message processing device arranged in a node device; the message processing device includes a control module and a message processing module; the control module and the message processing module A communication connection is established between the message processing modules; the communication connection does not include a protocol stack for processing network data packets in the node device; at least part of the processing units of the message processing module are set in the kernel space of the node device. FIG. 11 is a schematic flow diagram of a message processing method provided in an embodiment of the present application. As shown in 11, the method may include the following flow:

Step 1101, the message processing module receives and responds to the control command sent by the control module through the communication connection, sends a detection message to the target device, and receives a reply message sent by the target device.

Step 1102, the message processing module processes the reply message, and determines the link status between the node device and the target device.

Wherein, the detection message and the reply message include an OAM message.

In an implementation manner, the packet processing apparatus may be the packet processing apparatus provided in any of the preceding embodiments.

In some embodiments, the message processing module includes a message sending unit and a message receiving unit; wherein:

The message sending unit sends the first message to the target device; the message sending unit is set in the kernel space; wherein, the first message includes at least LBM, CCM and LTM;

The message receiving unit receives the reply message, obtains additional data carried in the reply message, and determines the link state based on the additional data.

In some embodiments, when the reply message is the second message, the message receiving unit determines the transmission delay and/or packet loss rate between the node device and the target device based on the time information in the additional data; Wherein, the second packet includes at least CCM.

In some embodiments, when the reply message is the third message, the message receiving unit determines the transmission delay between the node device and the target device based on the time information in the additional data; wherein, the third message Include at least LBR.

In some embodiments, when the reply message is the fourth message, the message receiving unit determines the link path information between the node device and the target device based on the device information in the additional data; wherein, the fourth message The text includes at least LTR;

When the message receiving unit receives the fifth message, it obtains the first address and the second address, and sets the source address of the fifth message as the first address, and sets the destination address of the fifth message as the second address , set the message type of the fifth message to LTR, and send the LTR through XDP; wherein, the fifth message includes at least the LTM; the first address includes the address of the node device; the second address includes the address of the device sending the LTM.

In some embodiments, when the message receiving unit receives the sixth message, it obtains the first address and the third address, and sets the source address of the sixth message as the first address, and sets the source address of the sixth message as The destination address is the third address, the message type of the sixth message is set as LBR, and the LBR is sent through XDP; wherein, the sixth message includes at least the LBM; the first address includes the address of the node device; the third address includes the address of the sending LBM The address of the device.

In some embodiments, the message receiving unit includes eBPF XDP of the Berkeley packet filter; the control module loads the eBPF XDP to the network card of the node device.

In some embodiments, the message receiving unit and the control module are set in the user space; the message processing module further includes a message filtering unit set in the kernel space, and the message filtering unit sends the OAM message to the message receiving unit through AF_XDP.

In the message processing method provided in the embodiment of the present application, at least part of the processing units of the message processing module are set in the kernel space of the node device, thereby greatly improving the efficiency of the message processing module in processing detection messages and replying messages; secondly, The communication connection between the control module and the message processing module does not include a protocol stack for processing network data packets, thereby reducing the link of data transmission between the control module and the message processing module, shortening the instruction transparent transmission and The delay of data transmission; and, after receiving the reply message, the message processing module can directly process the reply message to determine the link state between the node device and the target device, thereby improving the OAM message processing The efficiency improves the link state determination efficiency.

Therefore, the message processing method provided by the embodiment of the present application not only gets rid of the dependence on dedicated hardware chips, specific network card devices, and special data processing kits such as DPDK, but also compared with the software OAM message processing scheme in the related art, the present application The efficiency of OAM packet processing in the packet processing method provided by the embodiment is improved.

Based on the aforementioned embodiments, this embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor of an electronic device, it can realize the aforementioned message Approach.

The above descriptions of the various embodiments tend to emphasize the differences between the various embodiments, the same or similar points can be referred to each other, and for the sake of brevity, details are not repeated herein.

The methods disclosed in the various method embodiments provided in this application can be combined arbitrarily without conflict to obtain new method embodiments.

The features disclosed in the various product embodiments provided in this application can be combined arbitrarily without conflict to obtain new product embodiments.

The features disclosed in each method or device embodiment provided in this application can be combined arbitrarily without conflict to obtain a new method embodiment or device embodiment.

It should be noted that the above-mentioned computer-readable storage medium may be a read-only memory (Read Only Memory, ROM), a programmable read-only memory (Programmable Read-Only Memory, PROM), an erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), Magnetic Random Access Memory (Ferromagnetic Random Access Memory, FRAM), Flash Memory (Flash Memory) , magnetic surface memory, optical disc, or Compact Disc Read-Only Memory (CD-ROM) and other memories; it can also be various electronic devices including one or any combination of the above memories, such as mobile phones, computers, tablets, etc. devices, personal digital assistants, and more.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

The serial numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware nodes, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, disk, CD) contains several instructions to make a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in various embodiments of the present application.

The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structures or equivalent process transformations made by using the description of the application and the accompanying drawings are directly or indirectly used in other related technical fields. , are all included in the patent protection scope of the present application in the same way.

Claims (10)

1. A message processing device, characterized in that, the device is arranged in a node device; the device includes a control module and a message processing module; wherein: A communication connection is established between the control module and the message processing module; the communication connection does not include a protocol stack for processing network data packets in the node device; At least part of the processing units in the message processing module are set in the kernel space of the node device; the message processing module is used to receive and respond to the control command sent by the control module through the communication connection, and send a detection send the message to the target device, and receive the reply message sent by the target device; process the reply message, and determine the link state between the node device and the target device; wherein, the detection report The message and the reply message include a network management and maintenance OAM message. 2. The device according to claim 1, wherein the message processing module comprises a message sending unit and a message receiving unit; wherein: The message sending unit is configured to send a first message to the target device; the message sending unit is set in the kernel space; wherein, the first message includes at least a loopback detection message LBM, Connectivity detection message CCM and link tracking message LTM; The message receiving unit is configured to receive the reply message, acquire additional data carried in the reply message, and determine the link state based on the additional data. 3. The device according to claim 2, wherein the message receiving unit is configured to determine, based on the time information in the additional data, when the reply message is a second message The transmission delay and/or packet loss rate between the node device and the target device; wherein, the second message at least includes a connectivity detection message CCM. 4. The device according to claim 2, wherein the message receiving unit is configured to determine the time information in the additional data based on the time information in the additional data when the reply message is a third message. The transmission delay between the node device and the target device; wherein, the third message includes at least a loopback response message LBR. 5. The device according to claim 2, wherein the message receiving unit is configured to determine the device information in the additional data based on the device information in the additional data when the reply message is the fourth message. Link path information between the node device and the target device; wherein, the fourth message includes at least a link tracking response message LTR; The message receiving unit is further configured to obtain the first address and the second address when receiving the fifth message, and set the source address of the fifth message as the first address, and set the The destination address of the fifth message is the second address, the message type of the fifth message is set as LTR, and the LTR is sent through the fast data path XDP; wherein, the fifth message includes at least LTM ; the first address includes the address of the node device; the second address includes the address of the device sending the LTM. 6. The device according to claim 2, wherein the message receiving unit is configured to obtain the first address and the third address when receiving the sixth message, and set the sixth message The source address of the message is the first address, the destination address of the sixth message is set as the third address, the message type of the sixth message is set as LBR, and the LBR is sent through XDP; wherein , the sixth packet includes at least an LBM; the first address includes an address of the node device; and the third address includes an address of a device sending the LBM. 7. The device according to claim 2, wherein the message receiving unit comprises a general execution engine eBPF XDP of the Berkeley packet filter; the control module is configured to load the eBPF XDP to the node device network card. 8. The device according to claim 2, characterized in that, the message receiving unit and the control module are arranged in the user space; the message processing module also includes a message filter set in the kernel space A unit, configured to send the OAM message to the message receiving unit through the address family fast data path AF_XDP. 9. A node device, characterized in that the node device comprises the packet processing apparatus according to any one of claims 1-8. 10. A message processing method, characterized in that, the method is applied to a message processing device arranged in a node device; the message processing device includes a control module and a message processing module; the control module and the A communication connection is established between the message processing modules; the communication connection does not include a protocol stack for processing network data packets in the node device; at least part of the processing units in the message processing module are set in the A kernel space of a node device; the method includes: The message processing module receives and responds to the control command sent by the control module through the communication connection, sends a detection message to the target device, and receives a reply message sent by the target device; The message processing module processes the reply message to determine the link status between the node device and the target device; wherein, the detection message and the reply message include network management and maintenance OAM message.

Images