Packet loss identification method and device, communication equipment, readable storage medium and program product

Abstract

The invention relates to a packet loss identification method and device, communication equipment, a computer readable storage medium and a computer program product. The method is applied to a switch, and comprises the following steps: dyeing a data packet received by an entry field processor of the switch with a target color and carrying out statistics for a current time period so as to determine packet receiving statistical information; the corresponding data packets in the same time period are dyed with the same color, and the corresponding data packets in two adjacent time periods are dyed with different colors; counting the data packets which are output from an exit field processor of the switch and are dyed into the target color so as to determine packet sending statistical information; in the delay time corresponding to the current time period, reading target packet receiving information dyed as the target color from the packet receiving statistical information, and reading target packet sending information dyed as the target color from the packet sending statistical information and storing the target packet receiving information and the target packet sending information; and determining corresponding packet loss information based on the difference between the target packet receiving information and the target packet sending information. According to the method, more accurate packet loss identification can be realized.

Description

Technical Field

[0001] The present application relates to the field of network communication technology, and in particular to a packet loss identification method, apparatus, communication equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Packet loss is one of the factors that affect network stability. Packet loss may occur when a switch forwards data, but the existing technology has poor recognition accuracy for switch packet loss, which affects the handling of packet loss problems. Summary of the invention

[0003] Based on this, it is necessary to provide a packet loss identification method, apparatus, communication equipment, computer-readable storage medium and computer program product to address the above technical problems, so as to improve the accuracy of packet loss identification when the switch is working.

[0004] In a first aspect, the present application provides a packet loss identification method, which is applied to a switch, and the method includes:

[0005] For the current period, the data packets received by the ingress field processor of the switch are dyed with the target color and counted to determine the packet receiving statistical information; wherein, the corresponding data packets in the same period are dyed with the same color, and the data packets corresponding to two adjacent periods are dyed with different colors;

[0006] Count the data packets colored as the target color transferred from the egress field processor of the switch to determine the packet sending statistics information;

[0007] During the delay time corresponding to the current period, the target packet receiving information colored as the target color is read from the packet receiving statistics information and saved, and the target packet sending information colored as the target color is read from the packet sending statistics information and saved;

[0008] Determine the difference between the target packet receiving information and the target packet sending information; and based on the difference, determine the packet loss information corresponding to the switch in the current time period.

[0009] In one embodiment, for the current time period, data packets received by the ingress field processor of the switch are dyed with a target color and counted, including: for the current time period, when data packets received in the previous time period of the current time period are dyed with a first color, data packets received by the ingress field processor of the switch are dyed with a second color and counted.

[0010] In one embodiment, during the delay time corresponding to the current time period, target packet receiving information colored as the target color is read from the packet receiving statistics information and saved, and target packet sending information colored as the target color is read from the packet sending statistics information and saved, including:

[0011] According to the delay time corresponding to the current time period, the statistical information of the data packets dyed as the second color is read from the packet receiving statistical information as the target packet receiving information; and the statistical information of the data packets dyed as the second color is read from the packet sending statistical information as the target packet sending information.

[0012] In one of the embodiments, the packet receiving statistical information includes a first packet receiving statistical parameter and a second packet receiving statistical parameter, and the first packet receiving statistical parameter and the second packet receiving statistical parameter are used to perform statistical counting on received data packets of the first color and data packets of the second color, respectively;

[0013] The packet sending statistical information includes a first packet sending statistical parameter and a second packet sending statistical parameter, and the first packet sending statistical parameter and the second packet sending statistical parameter are used to perform statistical counting on the transferred first color data packets and second color data packets respectively;

[0014] During the delay time corresponding to the current period, the target packet receiving information colored as the target color is read from the packet receiving statistics information and saved, and the target packet sending information colored as the target color is read from the packet sending statistics information and saved, including:

[0015] Determine a time point in the next period of the current period as the delay time;

[0016] During the delay time, the statistical count of the second packet receiving statistical parameter is read and saved, and the statistical count of the second packet receiving statistical parameter is cleared, and the statistical count of the second packet sending statistical parameter is read and saved, and the statistical count of the second packet sending statistical parameter is cleared;

[0017] The method further includes: in a next time period of the current time period, performing statistical counting on the received first color data packets based on the first packet receiving statistical parameter, and performing statistical counting on the transferred first color data packets based on the first packet sending statistical parameter;

[0018] In the next time period of the next time period, the received data packets of the second color are counted based on the second packet receiving statistical parameter, and the transferred data packets of the second color are counted based on the second packet sending statistical parameter.

[0019] In one of the embodiments, the difference between target packet receiving information and target packet sending information is determined; and based on the difference, the packet loss information corresponding to the switch in the current time period is determined, including: determining the difference between the number of received packets and the number of sent packets of data packets colored as the target color, and determining the number of packet losses based on the difference; and determining the packet loss information corresponding to the switch in the current time period according to the number of packet losses.

[0020] In one of the embodiments, the method further includes: uploading the packet loss information, the packet receiving statistics information and the packet sending statistics information to a monitoring platform to which the switch belongs, so that the monitoring platform can monitor and warn the packet loss situation of the switch.

[0021] In a second aspect, the present application further provides a packet loss identification device, which is applied to a switch, and the device includes:

[0022] The dyeing statistics module is used to dye the data packets received by the inlet field processor of the switch with the target color for the current period and to count the data packets to determine the packet receiving statistics information; wherein the corresponding data packets in the same period are dyed with the same color, and the data packets corresponding to two adjacent periods are dyed with different colors; and the data packets transferred from the egress field processor of the switch and dyed with the target color are counted to determine the packet sending statistics information;

[0023] The reading module is used to read and save the target packet receiving information dyed as the target color from the packet receiving statistics information during the delay time corresponding to the current time period, and to read and save the target packet sending information dyed as the target color from the packet sending statistics information;

[0024] The determination module is used to determine the difference between the target packet receiving information and the target packet sending information; and based on the difference, determine the packet loss information corresponding to the switch in the current period.

[0025] In a third aspect, the present application further provides a communication device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the packet loss identification method in the first aspect when executing the computer program.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the packet loss identification method in the first aspect are implemented.

[0027] In a fifth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the packet loss identification method in the first aspect.

[0028] The above packet loss identification method, device, communication equipment, computer-readable storage medium and computer program product, in the current period, the data packets received by the inlet field processor of the switch are dyed with the target color and counted, the corresponding data packets in the same period are dyed with the same color, and the data packets corresponding to different periods are dyed with different colors; the dyed data packets transferred from the outlet field processor of the switch are counted. By distinguishing the dyeing, the data packets in the switch are marked, and the tracking of the data packets is convenient, which can facilitate the statistics of the switch receiving and forwarding data packets and avoid statistical confusion, so as to facilitate the determination of whether the data packet is lost. At the same time, by reading the target packet receiving information and the target bidding information at the delay time corresponding to the current period, this can avoid the number of data packets dyed as the target color in the current period is still changing, resulting in incomplete and inaccurate information read, that is, complete and accurate target packet receiving information and target bidding information can be read. On this basis, according to the difference between the target packet receiving information and the target bidding information, more accurate packet loss information corresponding to the switch in the current period can be determined, that is, more accurate packet loss identification is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments of the present application or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A schematic diagram of a flow chart of a packet loss identification method in an embodiment;

[0031] Figure 2 is another flowchart of a packet loss identification method in one embodiment;

[0032] Figure 3 A schematic diagram of switch traffic statistics in one embodiment;

[0033] Figure 4 is a schematic diagram of the enabling states of the IFP and EFP over time in one embodiment;

[0034] Figure 5 Schematic diagram of the corresponding flow chart of IFP and EFP in one embodiment;

[0035] Figure 6 is a structural block diagram of a packet loss identification device in an embodiment;

[0036] Figure 7 FIG. 4 is a diagram showing the internal structure of a communication device in one embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0038] Before describing the technical solution of the present application, the following describes the relevant terms:

[0039] COPP (Control Plane Policing): Control plane traffic control is a network security mechanism used to limit and manage data traffic on the control plane, such as routing protocols, to prevent malicious traffic attacks or unexpected traffic surges from affecting network stability.

[0040] IFP (Ingress Field Processor): An ingress field processor is a network chip hardware module that is responsible for performing preliminary processing on data packets when they enter the network device, such as coloring and counting. In this application, IFP is used to implement the coloring function and distinguish data packets in different time periods.

[0041] EFP (Egress Field Processor): A network chip hardware module that is responsible for final processing of data packets before they leave the network device, such as modifying specific fields of the data packet. In this application, EFP is used in conjunction with IFP to count the number of colored data packets.

[0042] Coloring: In network packet processing, coloring is a marking technique that distinguishes packets of different time periods or categories by assigning specific colors, such as red or yellow, to packets. In this application, coloring is used to achieve accurate capture and monitoring of packet loss.

[0043] Telemetry: Telemetry technology is a real-time monitoring and data collection mechanism used to collect performance indicators and status information of network devices. In this application, statistical information is passed to the monitoring platform through the Telemetry channel.

[0044] CONFIG_DB: Configuration database, used to store all configuration information of network devices. In this application, CONFIG_DB is specifically used to store configuration parameters of the GLOBAL_DROP function, such as the capture interval, etc.

[0045] COUNTERS_DB: Counter database, used to store performance counter data of network devices, such as number of lost packets, number of messages, etc. In this application, COUNTERS_DB is used to record the statistical information of the GLOBAL_DROP function.

[0046] OrchAgent: Orchestration agent, a software component used to manage and coordinate various services and tasks in network devices. In this application, OrchAgent subscribes to configuration changes in CONFIG_DB and starts or stops the GLOBAL_DROP function based on the configuration.

[0047] GLOBAL_DROP: Global packet loss detection.

[0048] Flooding: If the switch receives a data frame but does not know the port corresponding to the destination MAC address, that is, the MAC address is not in the MAC address table, it will adopt a flooding strategy - that is, copy the frame and send it to all other ports except the receiving port.

[0049] After explaining the relevant terms, the technical solution provided by this application is explained below.

[0050] In modern network architecture, the number of network devices is huge and widely distributed, and they jointly carry complex data transmission tasks. Packet loss is a key factor affecting network stability. In an environment where network devices are growing exponentially, the ability to quickly find packet loss devices is particularly important. However, existing network packet loss detection technologies usually face the following challenges: 1. There are many devices and it is difficult to locate: In a large network, when packet loss occurs, it is a challenge to quickly and accurately find the problem device. Existing technologies often lack effective mechanisms to quickly identify and locate the specific device where packet loss occurs. 2. Accuracy of packet loss statistics: Traditional port-based packet loss statistics, in the absence of formal traffic forwarding, the loss of protocol messages or miscellaneous packets is counted into packet loss statistics. When carrying traffic, port packet loss cannot effectively determine whether the device has actually forwarded packet loss. 3. Minor packet loss is difficult to distinguish: For occasional or minor packet loss, existing technologies are often difficult to accurately capture and identify. This makes it difficult for network operation and maintenance personnel to determine whether packet loss occurs and the specific time of packet loss. 4. Demand for accuracy and effectiveness of operation and maintenance: As network services have increasing requirements for stability and response speed, the accuracy and effectiveness of network operation and maintenance have become crucial. Existing technologies are insufficient in quickly responding to packet loss issues and providing accurate data support.

[0051] Based on the above analysis, it can be seen that how to improve the accuracy of packet loss identification is a problem to be solved. In view of this, the present application proposes a packet loss identification method, which is applied to a switch, and for the inlet field processor (IFP) and the egress field processor (EFP) in the switch, the data packets are alternately dyed and counted, and the packet loss situation is identified based on the statistical information, thereby improving the accuracy of packet loss identification. The method is described in detail below through multiple embodiments:

[0052] In one embodiment, Figure 1 As shown, a packet loss identification method is provided. This embodiment uses the method applied to a switch as an example. The method includes steps S102 to S108:

[0053] Step S102: for the current time period, the data packets received by the ingress field processor of the switch are dyed with the target color and counted to determine the packet receiving statistical information; wherein, the corresponding data packets in the same time period are dyed with the same color, and the data packets corresponding to two adjacent time periods are dyed with different colors.

[0054] The time period may be divided into specific time lengths, such as 5 seconds, and accordingly, the current time period may represent the current time period.

[0055] The packet receiving statistics information may be a statistic reflecting the coloring of data packets received by the ingress field processor in the switch, which may include the coloring corresponding to the current time period, and may also include the coloring corresponding to the previous time period of the current time period.

[0056] In some possible embodiments, the durations corresponding to different time periods may be the same or different. For example, the duration corresponding to the current time period may be 5 seconds, the next time period of the current time period may be 3 seconds, the next time period of the next time period of the current time period may be 3 seconds or 5 seconds, etc.

[0057] Exemplarily, the data packets received by the ingress field processor of the switch are dyed with a target color and counted, and the dyeing rule or the determination of the target color can be based on the time period. Specifically, the data packets received by the ingress field processor in the same time period can be dyed with the same color, and the data packets received in different time periods can be dyed with different colors. Therefore, the data packets may be dyed with at least two colors.

[0058] Step S104: Count the data packets colored as the target color transferred from the egress field processor of the switch to determine the packet sending statistical information.

[0059] Since the ingress field processor of the switch can receive data packets, the egress field processor of the switch can forward corresponding data packets, and the received data packets are colored, the forwarded data packets are naturally colored, and the forwarded colored data packets can be counted.

[0060] The packet sending statistics information may be a statistical information reflecting the coloring of data packets received and transferred by the egress field processor in the switch, which may include the coloring corresponding to the current period, and may also include the coloring corresponding to the previous period of the current period.

[0061] In some possible embodiments, the information counted in the packet receiving statistics information and the packet sending statistics information may only involve two adjacent time periods, for example, the current time period and the previous time period of the current time period, or the current time period and the next time period of the current time period, or the next time period of the current time period and the next time period of the next time period of the current time period. In this case, two colors may be used for alternating coloring. Since the information counted in the packet receiving statistics information and the packet sending statistics information involves two adjacent time periods, the same color will not involve data packets in two different time periods, thus avoiding confusion.

[0062] Step S106: During the delay time corresponding to the current period, the target packet receiving information colored in the target color is read from the packet receiving statistics information and saved, and the target packet sending information colored in the target color is read from the packet sending statistics information and saved.

[0063] The delay time may represent the time after the current time period. For example, if the current time period is from time A to time B, the delay time may be the time after time B.

[0064] In some possible embodiments, the delay time may be any time point or time period in the next period of the current period.

[0065] In some possible embodiments, since the number of data packets dyed into the target color may still be changing in the current time period, and the switch needs time to forward data packets and may experience congestion, if the target packet receiving information is read in the current time period, the read target packet receiving information may be incomplete or have accuracy issues, and thus the target packet receiving information may be read with a delay, such as reading it during the delay time corresponding to the current time period.

[0066] Step S108: determining the difference between the target packet receiving information and the target packet sending information; and based on the difference, determining the packet loss information corresponding to the switch in the current period.

[0067] In this embodiment, in the current period, the data packets received by the inlet field processor of the switch are dyed with the target color and counted, and the corresponding data packets in the same period are dyed with the same color, and the corresponding data packets in different periods are dyed with different colors; the dyed data packets transferred from the outlet field processor of the switch are counted. By distinguishing the dyeing, the data packets in the switch are marked, and the tracking of the data packets is convenient, which can facilitate the statistics of the switch receiving and forwarding data packets and avoid statistical confusion, thereby facilitating the determination of whether the data packets are lost. At the same time, by reading the target packet receiving information and the target bidding information during the delay time corresponding to the current period, this can avoid the number of data packets dyed as the target color in the current period still changing, resulting in incomplete and inaccurate information read, that is, complete and accurate target packet receiving information and target bidding information can be read. On this basis, according to the difference between the target packet receiving information and the target bidding information, more accurate packet loss information corresponding to the switch in the current period can be determined, that is, more accurate packet loss identification can be achieved.

[0068] In one of the embodiments, the aforementioned embodiment of "for the current time period, dyeing and counting the data packets received by the ingress field processor of the switch with a target color" may include: for the current time period, when the data packets received in the previous time period of the current time period are dyed with a first color, dyeing and counting the data packets received by the ingress field processor of the switch with a second color.

[0069] As described in the above embodiment, different colors can be used to color data packets in different time periods. Exemplarily, for the current time period, if the data packets received in the previous time period of the current time period are colored with the first color, then the data packets received by the ingress field processor of the switch can be colored and counted with the second color. The first color and the second color are different colors, and there is no restriction on which color the first color and the second color are.

[0070] In some possible embodiments, in the next period of the current period, the first color can be used to dye the data packets received by the ingress field processor of the switch, and the corresponding statistical information of the data packets dyed with the first color in the previous period of the current period should be cleared or transferred out, so as to avoid the first color appearing in the corresponding packet receiving statistical information and packet sending statistical information and involving both the previous period of the current period and the next period of the current period, thereby avoiding confusion.

[0071] In this embodiment, when the first color is used to color the data packets received by the ingress field processor of the switch in the previous period of the current period, the second color is used to color the data packets in the current period. This can distinguish the current period from the previous period of the current period, avoid confusion, and thus help to obtain more accurate and clear packet receiving statistics information and packet sending statistics information, and also facilitate the subsequent reading of target packet receiving information and target packet sending information.

[0072] In one of the embodiments, the aforementioned embodiment of "reading and saving target packet receiving information dyed as the target color from the packet receiving statistics information during the delay time corresponding to the current time period, and reading and saving target packet sending information dyed as the target color from the packet sending statistics information" may include: reading statistical information of data packets dyed as the second color from the packet receiving statistics information as the target packet receiving information according to the delay time corresponding to the current time period; and reading statistical information of data packets dyed as the second color from the packet sending statistics information as the target packet sending information.

[0073] As described in the above embodiments, the packet receiving statistics information may involve different time periods, and different colors are used to color data packets in different time periods. Therefore, when it is necessary to determine the statistics corresponding to a certain time period, the packet receiving statistics information can be read according to the corresponding color. The same is true for the packet sending statistics information.

[0074] In some possible embodiments, in order to subsequently determine the packet loss information corresponding to the switch in the current time period, it is necessary to determine the statistical information corresponding to the current time period, namely, the target packet receiving information and the target packet sending information. Exemplarily, it can be seen from the above embodiments that in the current time period, the second color is used to dye the data packets, so the statistical information of the data packets dyed in the second color can be read from the packet receiving statistical information as the target packet receiving information; and the statistical information of the data packets dyed in the second color can be read from the packet sending statistical information as the target packet sending information.

[0075] In some possible embodiments, reading the statistical information of the data packets dyed as the second color from the packet receiving statistical information can be understood as reading out the statistical information of the data packets dyed as the second color in the packet receiving statistical information, and the statistical information of the data packets dyed as the second color is no longer retained in the packet receiving statistical information.

[0076] In this embodiment, since the data packets are dyed with the second color in the current time period, the corresponding statistical information also corresponds to the second color. By taking the second color as the basis, the target packet receiving information is read from the packet receiving statistical information and the target packet sending information is read from the packet sending statistical information. This ensures that the time period corresponding to the read target packet receiving information and the target packet sending information is the current time period, rather than other time periods, thereby helping to provide an accurate basis for subsequent steps such as determining the packet loss information corresponding to the current time period.

[0077] In one embodiment, the packet receiving statistical information in the aforementioned embodiment may include a first packet receiving statistical parameter and a second packet receiving statistical parameter, and the first packet receiving statistical parameter and the second packet receiving statistical parameter are used to perform statistical counting on received first color data packets and second color data packets, respectively.

[0078] The first packet receiving statistical parameter and the second packet receiving statistical parameter may correspond to different time periods, for example, a time period before the current time period and the current time period.

[0079] The packet sending statistical information in the aforementioned embodiment may include a first packet sending statistical parameter and a second packet sending statistical parameter, and the first packet sending statistical parameter and the second packet sending statistical parameter are used to perform statistical counting on the transferred first color data packets and second color data packets, respectively.

[0080] The first packet sending statistical parameter and the second packet sending statistical parameter may correspond to different time periods, for example, a time period before the current time period and the current time period.

[0081] like Figure 2 As shown, in the aforementioned embodiment, “at the delay time corresponding to the current time period, reading and saving the target packet receiving information dyed as the target color from the packet receiving statistics information, and reading and saving the target packet sending information dyed as the target color from the packet sending statistics information” may include steps S202 to S204:

[0082] Step S202: Determine a time point in the next period of the current period as the delay time.

[0083] In some possible embodiments, as described above, the purpose of the delay time is to avoid the corresponding coloring and statistics are still in progress, which causes the read data to be incomplete and inaccurate. Therefore, for the determination of the delay time, the delay time is first required to be after the end of the current period. At the same time, the delay time should not be too late, in order to avoid the situation where the data packets dyed in the same color involve two or more time periods at the same time. For example, the current time period is A, corresponding to red, the next time period of the current time period is B, corresponding to green, and the next time period of the next time period of the current time period is C, corresponding to red. If the delay time is determined in time period C, then the data packets dyed in red may be read to involve both time periods A and C, which will cause confusion; if the delay time is determined in time period B, then the data packets dyed in red are read to involve only time period A, that is, the current time period. Therefore, the delay time can be determined in the next time period of the current time period.

[0084] Exemplarily, any time point in the next time period of the current time period may be selected as the delay time.

[0085] Step S204: during the delay time, reading and saving the statistical count of the second packet receiving statistical parameter, and clearing the statistical count of the second packet sending statistical parameter; and reading and saving the statistical count of the second packet sending statistical parameter, and clearing the statistical count of the second packet sending statistical parameter.

[0086] As mentioned above, during the delay time, the statistical count of the second packet receiving statistical parameter is read and saved, and the statistical count of the second packet receiving statistical parameter can be cleared, that is, read to clear and read clear. In this way, when the second color is used for coloring in the next time period of the next time period of the current time period, the second packet receiving statistical parameter corresponds to the next time period of the next time period of the current time period, rather than the current time period. The same is true for the second packet sending statistical parameter.

[0087] The packet loss identification method in the above embodiment also includes the following steps: Figure 2 Steps S206 to S208 shown in the figure:

[0088] Step S206: In the next time period of the current time period, the received data packets of the first color are counted based on the first packet receiving statistical parameter, and the transferred data packets of the first color are counted based on the first packet sending statistical parameter.

[0089] Step S208: In the next time period of the next time period, the received second color data packets are counted based on the second packet receiving statistical parameter, and the transferred second color data packets are counted based on the second packet sending statistical parameter.

[0090] In some possible embodiments, in the next time period of the next time period, the statistical count of the first packet receiving statistical parameter may be read and saved, and the statistical count of the first packet receiving statistical parameter may be cleared.

[0091] In this embodiment, the first packet receiving statistical parameter and the second packet receiving statistical parameter included in the packet receiving statistical information may correspond to different time periods. The statistical count of the second packet receiving statistical parameter is clearly read from the packet receiving statistical information to avoid the second packet receiving statistical parameter corresponding to the next time period of the next time period of the current time period when the second color is used for dyeing, rather than the current time period. The same is true for the packet sending statistical information. By reading it clearly in time, it can be ensured that the packet receiving statistical information and the packet sending statistical information only involve two adjacent time periods to avoid confusion.

[0092] In one of the embodiments, the "determining the difference between the target packet receiving information and the target packet sending information; and based on the difference, determining the packet loss information corresponding to the switch in the current time period" in the aforementioned embodiment may include: determining the difference between the number of received packets and the number of sent packets of the data packets colored as the target color, and determining the number of packet losses based on the difference; and determining the packet loss information corresponding to the switch in the current time period based on the number of packet losses.

[0093] Exemplarily, the difference between the target packet receiving information and the target packet sending information can be the difference in the number of packets, i.e., the difference. For example, if the target color is red, the target packet receiving information and the target packet sending information corresponding to the data packet dyed red in the current period can be obtained through the above steps. Since the data packet can be received by the switch and forwarded by the switch, in an ideal state, the number of data packets received by the switch is equal to the number forwarded, i.e., the number of received packets is equal to the number of sent packets. If packet loss occurs, the equation does not hold, for example, the number of sent packets is less than the number of received packets.

[0094] In this embodiment, the corresponding number of lost packets is determined according to the difference between the number of received packets and the number of sent packets of the data packets colored as the target color, thereby being able to determine more accurate packet loss information corresponding to the switch in the current period.

[0095] In one embodiment, the packet loss identification method in the above embodiment further includes: uploading the packet loss information, the packet receiving statistics information and the packet sending statistics information to the monitoring platform to which the switch belongs, so that the monitoring platform can monitor and warn the packet loss situation of the switch.

[0096] The monitoring platform may be a platform for monitoring the working conditions of the switch.

[0097] Exemplarily, the packet loss information, the packet receiving statistics information, and the packet sending statistics information may be uploaded once in each time period.

[0098] In some possible embodiments, the monitoring platform can analyze and determine the severity level of the switch packet loss situation based on the packet information, the packet receiving statistics information, and the packet sending statistics information. For example, the corresponding severity level can be determined based on the size of the packet loss number relative to a preset value in a preset period, such as a day or an hour. Then, an early warning is issued based on the determined severity level.

[0099] In this embodiment, packet loss information, packet receiving statistics information, and packet sending statistics information are uploaded to the monitoring platform to which the switch belongs, so that the monitoring platform can monitor and warn the packet loss situation of the switch. This realizes the reporting of information such as packet loss information of the switch, supports monitoring the switch, determines whether the switch has packet loss, and the specific situation of packet loss, thereby providing a decision-making basis for subsequent work such as handling packet loss.

[0100] In one embodiment, a packet loss identification method is provided, which may include the contents of "the switch captures global forwarding information in real time" and "the monitoring platform monitors and alarms the packet loss of the entire machine". The method can implement the GLOBAL_DROP function on a single switch, that is, through the method of alternating coloring statistics, the statistical information of the global forwarding message of a single switch is captured in real time. The statistical information includes ingress direction statistics, egress direction statistics and corresponding time period information. At the same time, the monitoring platform records the global forwarding information, monitors the whole machine forwarding statistics and corresponding time period of each switch, and triggers an alarm when the packet loss rate exceeds the preset threshold. This method aims to enhance the troubleshooting capability of network operation and maintenance and ensure the continuous and stable operation of the network.

[0101] The content of the "Switch captures global forwarding information in real time" section is as follows:

[0102] [Function description] The user can configure the interval for capturing packet loss from 1 to 3600 seconds. The system will count the number of forwarded messages within a period of time. The statistical information carries the time period, packet receiving statistics and packet sending statistics. The difference is the number of packet loss. The statistical information is saved in COUNTERS_DB (statistical database) and transmitted to the monitoring platform through a specific communication channel.

[0103] The system uses alternating coloring to distinguish time periods. For example, in time period ABCDE, AB is colored red, BC is colored yellow, CD is colored red, DE is colored yellow, and so on.

[0104] Because forwarding takes time and congestion needs to be considered, a delayed reading method is used. Time C captures the statistics of time periods AB, time D captures the statistics of time periods BC, and time E captures the statistics of time periods CD.

[0105] In some possible embodiments, data packets in a switch can be tracked by dyeing; time periods can be distinguished and delayed reading can be achieved by alternating dyeing, while continuous and uninterrupted dyeing can also be achieved to ensure that there are no missing or interrupted time periods.

[0106] In some possible embodiments, the time period carried in the statistical information may include the start time and the end time corresponding to the time period, thereby providing more information reference for subsequent steps such as packet loss identification and packet loss warning.

[0107] Usage restrictions: 1. This function will cause abnormal statistics when there are duplicate messages. For example, in L2 forwarding, the statistics of the egress will increase due to flooding. 2. When this function is configured, the user-configured coloring function cannot be used. When this function is implemented, the IFP action is colored red and yellow, which will conflict with the user-defined coloring behavior.

[0108] [Usage scenario]: Based on the above analysis, this solution is fully applicable to the three-layer forwarding network in the data center network. The de-stacking mode used by LEAF and the BUM configuration are 0, which ensures that all forwarding is three-layer forwarding.

[0109] [Implementation plan]: Use IFP action coloring + statistics, EFP matches the colored message, and uses action statistics to record the global number of incoming and outgoing messages. Figure 3 As shown, the principle of single-machine traffic statistics is given, that is, the principle of counting data packets in a single switch.

[0110] It takes a certain amount of time to forward a message, so there is a certain delay in reading statistics. Considering an extreme case of back pressure, it takes about 98ms to send a 24MB buffer at a rate of 2Gbps. It is relatively safe to set the interval for reading statistics to be more than 1 second. If the message stays in the buffer for longer than the interval, it is considered that the message is forwarded abnormally on this device and is considered as packet loss.

[0111] Considering that the whole process needs to be monitored, at least two colors are needed, and the default color of the message is green. Therefore, red R and yellow Y are used to alternate colors.

[0112]

Working Principle

[0113] The following is a possible implementation code to illustrate the corresponding working principle, where the content after " / / " is a description of the corresponding code:

[0114] Some codes about internal data structure are as follows:

[0115] / / Define the polling interval in seconds, using an unsigned integer type

[0116] unsigned int pollingInterval;

[0117] / / Define the status of the red IFP (Ingress Field Processor), using enumeration types to represent the status

[0118] typedef enum {

[0119] RED_RUNNING, / / Indicates that the red IFP is running

[0120] RED_STOPPED / / Indicates that the red IFP has stopped

[0121] } RedIfpState;

[0122] / / Declare the red IFP state variable

[0123] RedIfpState red_ifp_state;

[0124] / / Define the start and end time of the red IFP, using the timestamp type

[0125] unsigned long long red_start_time; / / Equivalent to yellow_stop_time, indicating the start time of red IFP dyeing

[0126] unsigned long long red_stop_time; / / Equivalent to yellow_start_time, indicating the end time of red IFP dyeing

[0127] Some of the codes for saving statistical information data in COUNTERS_DB are as follows:

[0128] START_TIMESTAMP = timestamp ; start time for global drop counters "20240612 10:45:33"END_TIMESTAMP = timestamp ; end time for global drop counters "20240612 10:45:34"

[0129] GLOBAL_INGRESS_PACKETS = 1*20DIGIT; number of global ingresspackets

[0130] GLOBAL_EGRESS_PACKETS = 1*20DIGIT; number of global egresspackets

[0131] like Figure 4 As shown in the figure, a possible reference of the change of the enabling state of IFP and EFP over time is provided, where R represents RED, i.e., red FP (Field Processor), and Y represents YELLOW, i.e., yellow FP. As shown in the figure, the reading statistics are performed after delaying one cycle (period).

[0132] The specific process of decomposition is as follows, please refer to Figure 5 and Figure 4 , specifically including the following:

[0133] (1) EFP sends two system ACLs (Access Control Lists), matching color R and action account, that is, matching red packets and counting them, matching color Y and action account, that is, matching yellow packets and counting them, and the priority needs to be lower than the current COPP. The default enable=0, that is, closed. This corresponds to "counting the packets colored with the target color transferred from the egress field processor of the switch to determine the packet statistics information" and other related content.

[0134] (2) IFP sends two system ACLs, the action is to dye R and account, that is, dye red and count, and the action is to dye Y and account, that is, dye yellow and count. The priority needs to be lower than the current COPP. The default enable=0. This can correspond to "for the current time period, the data packets received by the ingress field processor of the switch are dyed with the target color and counted to determine the packet receiving statistics; among which, the corresponding data packets in the same time period are dyed with the same color, and the data packets corresponding to two adjacent time periods are dyed with different colors" and other related content.

[0135] (3) OrchAgent subscribes to the GLOBAL_DROP configuration of CONFIG_DB. When it receives the subscription message, if it is enabled, it initializes the memory data and sets the enable of the four FPs to 1, that is, it is enabled. According to the configured pollinginterval value, the timer is started.

[0136] (4) The status is RED_RUNNING and RED_STOPPED, indicating whether the red IFP is running.

[0137] (5) When the cycle (i.e., time period) arrives, if the current state is RED_STOPPED, read the R statistics of IFP and EFP, write the statistics and time data of RED, i.e., red_start_time (red start time) to red_stop_time (red stop time), write them to COUNTERS_DB, update red_start_time (equivalent to yellow_stop_time, i.e., yellow stop time), start the IFP of RED, and update the state to RED_RUNNING (red running). Reading clearly means reading and clearing, i.e., reading the R statistics of IFP and EFP, and clearing the R statistics of IFP and EFP, which can make only the Y statistics of IFP and EFP, i.e., the statistics in yellow color, remain at present, so that the data packets dyed red in the next cycle are the data packets received in the next cycle, and do not involve the data packets in the current cycle, i.e., avoid the data packets dyed red from involving two or more cycles at the same time. The following about reading the Y statistics of IFP and EFP is similar.

[0138] (6) When the cycle arrives, if the current state is RED_RUNNING, read the Y statistics of IFP and EFP, write the statistics and time data of Yellow, that is, yellow_start_time (yellow start time) to yellow_stop_time (yellow stop time), into COUNTERS_DB, update yellow_start (equivalent to red_stop_time), stop the IFP of RED, and update the state to RED_STOPPED.

[0139] The subsequent states (5) and (6) are cycled until the stop configuration is received. In other words, when red stops, the statistics of the data packets dyed red are cleared; when yellow stops, the statistics of the data packets dyed yellow are cleared, and the cycle continues. This corresponds to "at the delay time corresponding to the current period, read the target packet receiving information dyed as the target color from the packet receiving statistics information and save it, and read the target packet sending information dyed as the target color from the packet sending statistics information and save it" and other related content.

[0140] The content of the section "Monitoring platform monitors and alarms packet loss of the entire machine" is as follows:

[0141] [Function Description] The monitoring platform in this solution collects the global forwarding statistics of the switch, can analyze the packet loss statistics forwarded by the switch in real time, and evaluate whether there is packet loss in each switch based on the congestion packet loss information. When an abnormality is detected, an alarm is issued in time to enhance the initiative of network operation and maintenance.

[0142]

Implementation plan

[0143] 1. Data synchronization. The monitoring platform collects packet loss statistics and congestion status data of the switch through telemetry, and filters and saves them.

[0144] 2. Real-time alarm system. Packet loss is the inbound direction statistics minus the outbound direction statistics. When it exceeds the threshold, the system will immediately issue an alarm.

[0145] 3. Visual monitoring and reporting. Provides a visual monitoring interface for network status, showing the current inbound and outbound statistics and packet loss rate of each device; view the N devices with the most packet loss and the N devices with the highest packet loss rate over a period of time.

[0146] For example, to query the five devices with the largest number of packet losses, use the prometheus query language promQL. Here is a possible implementation code:

[0147] topN(5, sort_desc(sum by (device) (ingress_packets - egress_packets)[1h]))

[0148] 4. Comprehensive analysis. Combined with forwarding message statistics and congestion information, the network utility rate and packet loss rate of each switch are evaluated, and the traffic peaks and valleys in the data center area are evaluated for cloud resource regulation.

[0149] In some possible embodiments, based on determining the number of packet losses of the entire machine, the reasons for the packet losses can be further analyzed. According to the time point when the packet losses occur, a relevant packet loss reason analysis program is triggered and collected.

[0150] In some possible embodiments, the packet loss of each device in a computer room can be counted, and the device with the most packet loss can be determined and located, so as to find the main device where the packet loss problem occurs, thereby facilitating the rapid resolution of the problem.

[0151] In this embodiment, by introducing the alternating dyeing technology, accurate packet loss capture based on time series is achieved. Compared with traditional port packet loss statistics, this technology ensures that the counted packet losses are real, and can record the specific time when the packet loss occurs, which helps to accurately capture the packet loss of the entire switch. Among many network devices, this technology can determine and locate the device with the most packet loss at present, which helps to improve the initiative and response speed of operation and maintenance. By aggregating data of different dimensions, the message forwarding status of various levels such as POD and ZONE can be obtained, and the subsequent deployment of network resources can be reasonably planned according to the peaks and troughs of traffic. At the same time, it allows to set appropriate alarm thresholds for each computer room according to different business needs, thereby enhancing the initiative and efficiency of network management.

[0152] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0153] Based on the same inventive concept, the embodiment of the present application also provides a packet loss identification device for implementing the packet loss identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more packet loss identification device embodiments provided below can refer to the limitations of the packet loss identification method above, and will not be repeated here.

[0154] In an exemplary embodiment, Figure 6 As shown, a packet loss identification device 600 is provided, which is applied to a switch and includes:

[0155] The dyeing statistics module 601 is used to dye the data packets received by the inlet field processor of the switch with the target color for the current period and to count the data packets to determine the packet receiving statistics information; wherein the corresponding data packets in the same period are dyed with the same color, and the data packets corresponding to two adjacent periods are dyed with different colors; and to count the data packets transferred from the egress field processor of the switch and dyed with the target color to determine the packet sending statistics information;

[0156] The reading module 602 is used to read and save the target packet receiving information colored as the target color from the packet receiving statistics information during the delay time corresponding to the current time period, and to read and save the target packet sending information colored as the target color from the packet sending statistics information;

[0157] The determination module 603 is used to determine the difference between the target packet receiving information and the target packet sending information; and based on the difference, determine the packet loss information corresponding to the switch in the current time period.

[0158] In one embodiment, the dyeing statistics module 601 is also used to dye and count the data packets received by the ingress field processor of the switch with a target color for the current time period, including: for the current time period, when the data packets received in the previous time period of the current time period are dyed with a first color, the data packets received by the ingress field processor of the switch are dyed with a second color and counted.

[0159] In one embodiment, the reading module 602 is further used to read and save the target packet receiving information colored as the target color from the packet receiving statistics information during the delay time corresponding to the current time period, and read and save the target packet sending information colored as the target color from the packet sending statistics information, including:

[0160] According to the delay time corresponding to the current time period, the statistical information of the data packets dyed as the second color is read from the packet receiving statistical information as the target packet receiving information; and the statistical information of the data packets dyed as the second color is read from the packet sending statistical information as the target packet sending information.

[0161] In one of the embodiments, the packet receiving statistical information includes a first packet receiving statistical parameter and a second packet receiving statistical parameter, and the first packet receiving statistical parameter and the second packet receiving statistical parameter are used to perform statistical counting on the received first color data packets and the second color data packets, respectively; the packet sending statistical information includes a first packet sending statistical parameter and a second packet sending statistical parameter, and the first packet sending statistical parameter and the second packet sending statistical parameter are used to perform statistical counting on the transferred first color data packets and the second color data packets, respectively;

[0162] The reading module 602 is also used to read and save the target packet receiving information dyed as the target color from the packet receiving statistical information during the delay time corresponding to the current time period, and read and save the target packet sending information dyed as the target color from the packet sending statistical information, including: determining a time point in the next time period of the current time period as the delay time; during the delay time, reading and saving the statistical count of the second packet receiving statistical parameter, and clearing the statistical count of the second packet receiving statistical parameter, and reading and saving the statistical count of the second packet sending statistical parameter, and clearing the statistical count of the second packet sending statistical parameter;

[0163] The reading module 602 is also used to perform statistical counting of the received first color data packets based on the first packet receiving statistical parameter in the next time period of the current time period, and perform statistical counting of the transferred first color data packets based on the first packet sending statistical parameter; in the next time period of the next time period, perform statistical counting of the received second color data packets based on the second packet receiving statistical parameter, and perform statistical counting of the transferred second color data packets based on the second packet sending statistical parameter.

[0164] In one embodiment, the determination module 603 is further used to determine the difference between the target packet receiving information and the target packet sending information; and based on the difference, determine the packet loss information corresponding to the switch in the current time period, including: determining the difference between the number of received packets and the number of sent packets of the data packets colored as the target color, and determining the number of packet losses based on the difference; and determining the packet loss information corresponding to the switch in the current time period according to the number of packet losses.

[0165] In one embodiment, the determination module 603 is further used to upload the packet loss information, the packet receiving statistics information and the packet sending statistics information to the monitoring platform to which the switch belongs, so that the monitoring platform can monitor and warn the packet loss situation of the switch.

[0166] Each module in the above-mentioned packet loss identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the communication device in the form of hardware, or can be stored in the memory in the communication device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0167] In an exemplary embodiment, a communication device is provided. The communication device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The communication device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the communication device is used to provide computing and control capabilities. The memory of the communication device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the communication device is used to store data required for executing the packet loss identification method, for example, target packet information. The input / output interface of the communication device is used to exchange information between the processor and an external device. The communication interface of the communication device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a packet loss identification method is implemented.

[0168] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the communication device to which the scheme of the present application is applied. The specific communication device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0169] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0170] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0171] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0172] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0173] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0174] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A packet loss identification method, characterized in that: Applied to a switch, the method comprises: For the current time period, the data packets received by the ingress field processor of the switch are dyed with the target color and counted to determine the packet receiving statistical information; wherein the corresponding data packets in the same time period are dyed with the same color, and the data packets corresponding to two adjacent time periods are dyed with different colors; Counting the data packets colored with the target color transferred from the egress field processor of the switch to determine the packet sending statistical information; During the delay time corresponding to the current time period, the target packet receiving information colored in the target color is read from the packet receiving statistical information and saved, and the target packet sending information colored in the target color is read from the packet sending statistical information and saved; Determine a difference between the target packet receiving information and the target packet sending information; and based on the difference, determine packet loss information corresponding to the switch in the current time period.

2. The method according to claim 1, characterized in that The step of coloring and counting the data packets received by the ingress field processor of the switch in the current period with a target color includes: For the current period, when the data packets received in the period before the current period are dyed with the first color, the data packets received by the ingress field processor of the switch are dyed with the second color and counted.

3. The method according to claim 2, characterized in that The delay time corresponding to the current time period, reading and saving the target packet receiving information dyed with the target color from the packet receiving statistical information, and reading and saving the target packet sending information dyed with the target color from the packet sending statistical information, include: According to the delay time corresponding to the current time period, statistical information of the data packets colored in the second color is read from the packet receiving statistical information as the target packet receiving information; and The statistical information of the data packet dyed as the second color is read from the packet sending statistical information as the target packet sending information.

4. The method according to claim 2, characterized in that: The packet receiving statistical information includes a first packet receiving statistical parameter and a second packet receiving statistical parameter, wherein the first packet receiving statistical parameter and the second packet receiving statistical parameter are used to perform statistical counting on received data packets of the first color and received data packets of the second color, respectively; The packet sending statistical information includes a first packet sending statistical parameter and a second packet sending statistical parameter, wherein the first packet sending statistical parameter and the second packet sending statistical parameter are respectively used to perform statistical counting on the transferred data packets of the first color and the data packets of the second color; The delay time corresponding to the current time period, reading and saving the target packet receiving information dyed with the target color from the packet receiving statistical information, and reading and saving the target packet sending information dyed with the target color from the packet sending statistical information, include: Determine a time point in the next time period of the current time period as the delay time; During the delay time, reading and saving the statistical count of the second packet receiving statistical parameter, and clearing the statistical count of the second packet sending statistical parameter, and reading and saving the statistical count of the second packet sending statistical parameter, and clearing the statistical count of the second packet sending statistical parameter; The method further comprises: In a time period next to the current time period, performing statistical counting on the received data packets of the first color based on the first packet receiving statistical parameter, and performing statistical counting on the transferred data packets of the first color based on the first packet sending statistical parameter; In the next time period of the next time period, the received data packets of the second color are counted based on the second packet receiving statistical parameter, and the transferred data packets of the second color are counted based on the second packet sending statistical parameter.

5. The method according to claim 1, characterized in that: Determining the difference between the target packet receiving information and the target packet sending information; Based on the difference, determining the packet loss information corresponding to the switch in the current time period includes: Determine the difference between the number of received packets and the number of sent packets of the data packets dyed as the target color, and determine the number of lost packets based on the difference; According to the number of lost packets, packet loss information corresponding to the switch in the current time period is determined.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: The packet loss information, the packet receiving statistics information and the packet sending statistics information are uploaded to a monitoring platform to which the switch belongs, so that the monitoring platform can monitor and warn the packet loss situation of the switch.

7. A packet loss identification device, characterized in that: Applied to a switch, the device comprises: The dyeing statistics module is used to dye the data packets received by the inlet field processor of the switch with a target color for the current period and to count the data packets so as to determine the packet receiving statistics information; wherein the corresponding data packets in the same period are dyed with the same color, and the data packets corresponding to two adjacent periods are dyed with different colors; and to count the data packets transferred from the egress field processor of the switch and dyed with the target color so as to determine the packet sending statistics information; A reading module, configured to read and save target packet receiving information dyed with the target color from the packet receiving statistical information during the delay time corresponding to the current time period, and to read and save target packet sending information dyed with the target color from the packet sending statistical information; The determination module is used to determine the difference between the target packet receiving information and the target packet sending information; and based on the difference, determine the packet loss information corresponding to the switch in the current time period.

8. A communication device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images