Data transmission method and apparatus

Abstract

The application discloses a data transmission method and device. The method comprises the following steps: in response to detecting that a first queue has a first microburst event, obtaining first microburst data of the first queue, wherein the first microburst data is used for representing changes of data of the first queue in a forwarding dimension; based on the first microburst data, obtaining target data in a first period, wherein the target data comprises the first microburst data and first statistical data, and the first statistical data is used for representing a frequency of occurrence of the first microburst event; and sending the target data to a network analysis device.

Description

Technical Field

[0001] This application relates to the field of network technology, and in particular to data transmission methods and apparatus. Background Technology

[0002] Currently, real-time monitoring of multi-dimensional network metrics typically employs second- or minute-level statistical reporting. To reduce the amount of reported data, the controller acquires second- or minute-level average, maximum, and quantile values ​​of traffic on the link based on the required metric data. This information, combined with link packet loss and latency data, is then analyzed to determine if link congestion exists. However, current link congestion monitoring methods suffer from relatively large granularity, detecting only second- or minute-level traffic characteristics, thus failing to achieve effective micro-burst monitoring. Summary of the Invention

[0003] This application provides a data transmission method and apparatus, which helps to improve the comprehensiveness of monitoring data and the effectiveness of data analysis in micro-emergency scenarios.

[0004] In a first aspect, this application provides a data transmission method executed by a forwarding device. The method includes: in response to detecting a first micro-burst event in a first queue, acquiring first micro-burst data of the first queue, the first micro-burst data being used to characterize the changes in data of the first queue in the forwarding dimension; based on the first micro-burst data, acquiring target data within a first period, the target data including the first micro-burst data and first statistical data, the first statistical data being used to characterize the frequency of occurrence of the first micro-burst event; and sending the target data to a network analysis device.

[0005] The forwarding device generates target data, including first micro-burst data containing data changes under the forwarding dimension and first statistical data representing the occurrence frequency of the first micro-burst event, according to the first cycle. The target data can be reported to the network analysis device according to the first cycle, which improves the comprehensiveness of the micro-burst data obtained by the network analysis device, thereby ensuring the effectiveness of subsequent data analysis.

[0006] In one possible implementation, the first microburst data includes the identifier of the first queue, the start time of the first microburst event, and the end time of the first microburst event.

[0007] In one possible implementation, the first micro-burst data also includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

[0008] In a network data analysis scenario where the focus is on analyzing packet loss in queues corresponding to micro-burst events, the first micro-burst data obtained by the forwarding device includes at least one of packet loss information and packet gain information. The first statistical data can also be used to characterize the frequency of occurrence of the first micro-burst event with packet loss, thereby improving the effectiveness of network data analysis in micro-burst scenarios.

[0009] In one possible implementation, the first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs, and the first statistical data is also used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds a threshold.

[0010] In a network data analysis scenario where the peak queue size of micro-burst events is the primary focus, the first micro-burst data acquired by the forwarding device also includes the peak queue depth and the time when the peak queue depth occurs. The first statistical data can also be used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds a threshold, thereby improving the effectiveness of network data analysis in micro-burst scenarios.

[0011] In one possible implementation, the method further includes: obtaining second statistical data within a second period based on the second micro-burst data, the second statistical data being used to characterize the frequency of the occurrence of the second micro-burst event, the second period being longer than the first period, the second statistical data including the first statistical data, the second micro-burst data being used to characterize the changes in data of the queue where the second micro-burst event occurred under the forwarding dimension; and sending the second statistical data to a network analysis device.

[0012] By reporting summary micro-burst data and detailed micro-burst data at different intervals, the problem of high bandwidth occupancy and waste of computing and storage resources caused by reporting the full amount of data is avoided, and the problem of lost traffic characteristics caused by aggregated reporting is solved.

[0013] In one possible implementation, the method further includes: in response to detecting the occurrence of the second micro-burst event in the second queue, acquiring the second micro-burst data, the second micro-burst data being used to characterize the changes in data of the second queue in the forwarding dimension; or in response to detecting the occurrence of the second micro-burst event in the first queue, acquiring the second micro-burst data, the second micro-burst data being used to characterize the changes in data of the first queue in the forwarding dimension.

[0014] In this system, after a second micro-burst event occurs in any queue of the forwarding device according to the second cycle, the forwarding device can obtain the corresponding second micro-burst data, which improves the comprehensiveness of network data reporting in micro-burst scenarios.

[0015] In one possible implementation, obtaining target data within the first period includes: obtaining first target data within the third period, where the first period is longer than the third period; the first target data includes third micro-burst data and third statistical data; the third micro-burst data is used to characterize the changes in data of the first queue where the third micro-burst event occurred under the forwarding dimension; the third micro-burst event is a first micro-burst event with packet loss; and the third statistical data includes the number of times the third micro-burst event occurred; and obtaining target data within the first period based on the first target data, where the target data also includes the first target data.

[0016] In one possible implementation, obtaining the target data within the first period includes: obtaining the second target data within the third period, where the first period is longer than the third period; the second target data includes fourth micro-burst data and fourth statistical data; the fourth micro-burst data is used to characterize the changes in the data of the first queue where the fourth micro-burst event occurred in the forwarding dimension; the fourth micro-burst event is the first micro-burst event where the peak queue depth exceeds a threshold; and the fourth statistical data includes the number of times the fourth micro-burst event occurs; based on the second target data, obtaining the target data within the first period, where the target data also includes the second target data.

[0017] Secondly, this application provides a data transmission method executed by a network analysis device. The method includes: receiving target data sent by a forwarding device, the target data including first micro-burst data within a first period and first statistical data, the first statistical data being used to characterize the frequency of occurrence of the first micro-burst event; the first micro-burst data being used to characterize the changes in data of a first queue in the forwarding dimension; the first micro-burst data being the micro-burst data of the first queue obtained by the forwarding device when it detects the occurrence of the first micro-burst event in the first queue; and outputting and displaying the target data.

[0018] The forwarding device generates target data, including first micro-burst data containing data changes under the forwarding dimension and first statistical data representing the occurrence frequency of the first micro-burst event, according to the first cycle. The target data can be reported to the network analysis device according to the first cycle, which improves the comprehensiveness of the micro-burst data obtained by the network analysis device, thereby ensuring the effectiveness of subsequent data analysis.

[0019] In one possible implementation, the first microburst data includes the identifier of the first queue, the start time of the first microburst event, and the end time of the first microburst event.

[0020] In one possible implementation, the first micro-burst data also includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

[0021] In a network data analysis scenario where the focus is on analyzing packet loss in queues corresponding to micro-burst events, the first micro-burst data obtained by the forwarding device includes at least one of packet loss information and packet gain information. The first statistical data can also be used to characterize the frequency of occurrence of the first micro-burst event with packet loss, thereby improving the effectiveness of network data analysis in micro-burst scenarios.

[0022] In one possible implementation, the first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs, and the first statistical data is also used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds a threshold.

[0023] In a network data analysis scenario where the peak queue size of micro-burst events is the primary focus, the first micro-burst data acquired by the forwarding device also includes the peak queue depth and the time when the peak queue depth occurs. The first statistical data can also be used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds a threshold, thereby improving the effectiveness of network data analysis in micro-burst scenarios.

[0024] In one possible implementation, the output of target data includes: displaying first statistical data within a first period through a first graphical output of a first display interface; and displaying first micro-burst data within a first period through a second graphical output of the first display interface.

[0025] Within the same interface, the first statistical data and the first micro-burst data within the first cycle can be displayed separately.

[0026] In one possible implementation, the first statistical data within a first period is displayed through the first graphic output of the first display interface, including: outputting and displaying the total occurrence frequency of the first micro-burst event within the first period through the first colored first graphic in the first display interface; if the first statistical data is also used to characterize the occurrence frequency of the first micro-burst event with packet loss, the occurrence frequency of the first micro-burst event with packet loss within the first period is output and displayed through the second colored first graphic in the first display interface.

[0027] Specifically, different shades of the same graphic are used to distinguish the frequency of the first micro-burst event of packet loss within the first cycle and the total frequency of the first micro-burst event within each first cycle.

[0028] In one possible implementation, the first statistical data within a first period is displayed through the first graphic output of the first display interface, including: outputting the total occurrence frequency of the first micro-burst event within the first period through the first colored first graphic in the first display interface; if the first statistical data is also used to characterize the occurrence frequency of the first micro-burst event where the peak queue depth exceeds a threshold, the occurrence frequency of the first micro-burst event where the peak queue depth exceeds a threshold is output through the first graphic in the first display interface with a third color.

[0029] Among them, different colors of the same graphic are used to distinguish the frequency of the first micro-burst event when the peak queue depth exceeds the threshold in the first period and the total frequency of the first micro-burst event in the first period.

[0030] In one possible implementation, the method further includes: outputting a third statistical data point and a third micro-burst data point within the first period; the third statistical data point includes the number of occurrences of the third micro-burst event, where the third micro-burst event is a first micro-burst event with packet loss, and the third micro-burst data point is used to characterize the changes in data of the first queue where the third micro-burst event occurred in the forwarding dimension; or, outputting a fourth statistical data point and a fourth micro-burst data point within the first period; the fourth statistical data point includes the number of occurrences of the fourth micro-burst event, where the fourth micro-burst event is a first micro-burst event where the peak queue depth exceeds a threshold, and the fourth micro-burst data point is used to characterize the changes in data of the first queue where the fourth micro-burst event occurred in the forwarding dimension.

[0031] In one possible implementation, the method further includes: receiving a second statistical data sent by the forwarding device; the second statistical data is used to characterize the frequency of the occurrence of the second microburst event; the second microburst event is a microburst event that occurs in the queue detected by the forwarding device within a second period; the second period is greater than the first period; and the second statistical data is output and displayed.

[0032] By receiving summary micro-burst data and detailed micro-burst data reported at different periods, the problem of high bandwidth occupancy and waste of computing and storage resources caused by reporting the full amount of data is avoided, and the problem of lost traffic characteristics caused by aggregated reporting is solved.

[0033] In one possible implementation, the output displays the second statistical data, including: displaying the second statistical data within a second period through a third graphical output of a second display interface.

[0034] In one possible implementation, the output displays the second statistical data, including: outputting the total frequency of the second micro-burst event within the second period through a third graphic colored by a fourth color in the second display interface; if the second statistical data is also used to characterize the frequency of the second micro-burst event with packet loss, outputting the frequency of the second micro-burst event with packet loss within the second period through a third graphic colored by a fifth color in the second display interface.

[0035] In one possible implementation, the output displays second statistical data, including: outputting the total frequency of second micro-burst events within a second period through a third graphic colored by a fourth color in a second display interface; if the second statistical data is also used to characterize the frequency of first micro-burst events where the peak queue depth exceeds a threshold, outputting the frequency of second micro-burst events where the peak queue depth exceeds a threshold within a second period through a third graphic colored by a sixth color in the second display interface.

[0036] In one possible implementation, outputting target data includes: in response to receiving a selection operation on a third graphic, outputting target data within each of the first cycles in the second cycle corresponding to the third graphic.

[0037] Thirdly, this application provides a data transmission apparatus for performing any of the data transmission methods provided in the first aspect above.

[0038] In one possible implementation, this application can divide the data transmission device into functional modules according to the method provided in the first aspect above. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. For example, this application can divide the data transmission device into an acquisition module, a determination module, and a transmission module according to their functions. The descriptions of the possible technical solutions and beneficial effects performed by the above-described functional modules can be found in the technical solutions provided in the first aspect above or its corresponding possible implementations, and will not be repeated here.

[0039] Fourthly, this application provides a data transmission apparatus for performing any of the data transmission methods provided in the second aspect above.

[0040] In one possible implementation, this application can divide the data transmission device into functional modules according to the method provided in the second aspect above. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. For example, this application can divide the data transmission device into a receiving module and an output display module, etc., according to their functions. The descriptions of the possible technical solutions and beneficial effects of the various functional modules described above can be found in the technical solutions provided in the second aspect above or its corresponding possible implementations, and will not be repeated here.

[0041] Fifthly, embodiments of this application provide a forwarding device, which includes a first processor, a first memory, and a forwarding chip. The forwarding chip is coupled to the first memory and is used to detect a first micro-burst event occurring in a first queue, acquire the first micro-burst data of the first queue, and provide the first micro-burst data to the first memory. The first processor is coupled to the first memory. The first memory is used to store the first micro-burst data and also to store computer instructions. The first processor is used to load and execute the computer instructions so that the forwarding device acquires the first micro-burst data of the first queue based on the forwarding chip and the first memory, acquires target data within a first period based on the first micro-burst data, and sends the target data to a network analysis device.

[0042] In addition, the first processor is also used to load and execute the computer instructions so that the forwarding device implements the technical solution provided by the corresponding possible implementation of the first aspect.

[0043] In a sixth aspect, embodiments of this application provide a network analysis device, which includes a processor and a memory, the processor being coupled to the memory; the memory is used to store computer instructions, which are loaded and executed by the processor to enable the network analysis device to implement the data transmission method as described in the second aspect above.

[0044] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to implement the data transmission method as described above.

[0045] Eighthly, embodiments of this application provide a computer program product including computer instructions that, when executed by a processor, can perform the data transmission method described above.

[0046] For a detailed description of aspects three through eight and their various implementations in this application, please refer to the detailed description in aspects one and its various implementations or aspects two and their various implementations; and for a detailed description of the beneficial effects of aspects three through eight and their various implementations, please refer to the beneficial effect analysis in aspects one and its various implementations and aspects two and their various implementations, which will not be repeated here.

[0047] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0048] Figure 1 A schematic diagram illustrating a micro-burst data transmission scenario is shown as an exemplary embodiment of this application;

[0049] Figure 2 This is a schematic diagram illustrating a data transmission system as shown in an exemplary embodiment of this application;

[0050] Figure 3 This is a schematic diagram illustrating the structure of a network analysis device as an exemplary embodiment of this application;

[0051] Figure 4 A schematic flowchart of a data transmission method provided in an embodiment of this application is shown;

[0052] Figure 5 yes Figure 4 The illustrated embodiment is a schematic diagram of a data format for a first microburst of data.

[0053] Figure 6 A schematic flowchart of a data transmission method provided in an embodiment of this application is shown;

[0054] Figure 7 yes Figure 6 The illustrated embodiment is a schematic diagram of a first display interface;

[0055] Figure 8 yes Figure 6 The illustrated embodiment is a schematic diagram of a first display interface;

[0056] Figure 9 yes Figure 6 The illustrated embodiment is a schematic diagram of a second display interface;

[0057] Figure 10 yes Figure 6 The illustrated embodiment is a schematic diagram of outputting and displaying target data after outputting and displaying second statistical data.

[0058] Figure 11 A schematic diagram of the structure of a data transmission apparatus 500 provided in an exemplary embodiment of this application;

[0059] Figure 12 This is a schematic diagram of the structure of a data transmission device 600 provided for an exemplary embodiment of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0061] In this document, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0062] The application scenarios of the embodiments of this application are described below by way of example.

[0063] With the rapid development of video services such as short videos, live streaming, and video calls, the proportion of video traffic transmitted by forwarding devices is increasing. Due to the surge in video traffic and the pre-loading mechanism inherent in these services, the frequency of micro-bursts in the network is increasing, leading to frequent network congestion and traffic suppression, severely impacting network experience. A micro-burst refers to the receipt of a large amount of sudden data within a short period (e.g., milliseconds), typically lasting between 1 and 100 milliseconds. In related technologies, forwarding devices can detect changes in port traffic during micro-bursts, such as the input and output data rates. Because of the short duration of micro-bursts, the second / minute-level aggregated data from typical network monitoring devices cannot reveal specific traffic characteristics. Furthermore, due to asynchronous data acquisition, it is difficult to establish a clear causal relationship between traffic statistics and metrics such as packet loss and latency. Most forwarding devices use queues for congestion control; without queue depth information, there is theoretically no direct causal relationship between traffic data and metrics such as packet loss. Typical micro-burst monitoring functions only collect traffic data-related information; and due to the large volume of millisecond-level data, they can only collect data for short periods of time as needed, and cannot provide continuous monitoring. If a second-level / minute-level aggregation method is used to reduce the data volume, the characteristics of business traffic will be greatly lost, which is counterproductive.

[0064] To address the problems existing in the aforementioned traditional technologies, the forwarding device provided in this application, upon detecting a first micro-burst event in the first queue, collects first micro-burst data to characterize the data changes of the first queue in the forwarding dimension. Based on the first micro-burst data, target data including the first micro-burst data and first statistical data within a first period can be obtained. The first statistical data is used to characterize the occurrence frequency of the first micro-burst event. Then, the target data is sent to the network analysis device. The forwarding device can generate target data containing the first micro-burst data containing the data changes in the forwarding dimension and the first statistical data characterizing the occurrence frequency of the first micro-burst event according to the first period, and can report the target data to the network analysis device according to the first period, thereby improving the comprehensiveness of the micro-burst data obtained by the network analysis device, thus ensuring the effectiveness of subsequent data analysis.

[0065] Figure 1 This illustration, for the purpose of providing an exemplary embodiment of this application, provides a schematic diagram of a micro-burst data transmission scenario. For example... Figure 1As shown, the forwarding device sends micro-burst data to the network analysis device via telemetry technology. Telemetry is a network monitoring technology that remotely collects data at high speed from the forwarding device. The forwarding device periodically and proactively sends device information to the network analysis device through a "push mode," providing more real-time, faster, and more accurate network monitoring capabilities. In the event of a micro-burst event in a queue within the forwarding device, the forwarding device can periodically send data about the queue during the micro-burst event to the network analysis device, allowing the network analysis device to determine the status of the queue experiencing the micro-burst based on the data from the forwarding device.

[0066] Figure 2 This is a schematic diagram illustrating a data transmission system according to an exemplary embodiment of this application. The system includes a forwarding device 10 and a network analysis device 20. The forwarding device 10 can be a network device with forwarding capabilities, such as a switch or router. The network analysis device 20 can be a network management device or control device with analysis and control functions. Specifically, the network management device can be a network cloud engine (NCE), a virtual machine providing cloud services, etc. The network analysis device 20 communicates with the forwarding device 10 via a simple network management protocol (SNMT), such as signaling interaction and / or data transmission. Optionally, the forwarding device 10 includes a first processor 111, a first memory 113, a forwarding chip 112, and ports. The forwarding chip 112 may include a processing module, a storage module, and a register module.

[0067] like Figure 2 As shown, forwarding device 1 includes ports, such as port 1 and port 2. Forwarding device 1 communicates with forwarding device 2 through port 1, and forwarding device 1 communicates with forwarding device 3 through port 2. Figure 2 The data transmission direction is from forwarding device 3 through forwarding device 1 to forwarding device 2. Subsequent data transmission through forwarding device 2 will not be described further. Forwarding chip 112 of forwarding device 1 receives data from forwarding device 3 via port 2 and places it into a queue buffer in the buffer area. Forwarding chip 112 of forwarding device 1 retrieves data from the corresponding queue in the buffer area according to the queue scheduling policy and sends it to forwarding device 2 via port 1.

[0068] The forwarding device 1 includes a forwarding chip 112, which can be a network processor (NP) or other chip used to implement forwarding functions. The forwarding chip 112 is used to monitor the queue status in real time to obtain indicator data during micro-burst events in the queue. The forwarding chip 112 may include a processing module, a storage module, and a register module. The forwarding chip 112 is used to write the real-time collected indicator data into the storage module of the forwarding chip 112. For example, the indicator data and the time information of the micro-burst event can be encapsulated into tuple information according to a specified data format and stored in the storage module of the forwarding chip 112. The forwarding device 1 can also obtain the time information of the micro-burst event and the indicator data during the micro-burst event in the queue from the storage module of the forwarding chip 112, and based on the time information of the micro-burst event, obtain other indicator data of the queue within the time period corresponding to the time information of the micro-burst event from the register module of the forwarding chip 112. This other indicator data includes indicator data written to the register module of the forwarding chip 112 during continuous queue statistics. During data transmission, the queue continuously outputs information such as data packet transmission status, byte data transmission status, inbound traffic, or outbound traffic to the register module included in the forwarding chip 112.

[0069] Optionally, the forwarding chip 112 includes a register module that stores binary data to represent packet loss or packet transmission information, inbound traffic, or outbound traffic in the packet transmission process. In this embodiment, packet transmission refers to packets passing through the forwarding device, and packet loss refers to packets dropped by the forwarding device. Packet transmission information can be the number of packets or bytes passed, and packet loss information can be the number of lost packets or the number of dropped bytes.

[0070] The forwarding chip 112 of forwarding device 1 can superimpose partial indicator data from the micro-burst event occurring in the queue, along with other indicator data obtained from the storage module in the forwarding chip 112, to obtain the encapsulated N-tuple information corresponding to the micro-burst event. The forwarding chip 112 of forwarding device 1 outputs this encapsulated N-tuple information to the first memory 113 for caching. The N-tuple information cached in the first memory 113 can include N-tuple information corresponding to micro-burst events occurring in multiple queues within a certain time period. Forwarding device 1 performs the following two processes on the N-tuple information cached in the first memory 113 through the first processor 111.

[0071] On one hand, the forwarding device 1 filters the multiple N-tuple information stored in the first memory 113 through the first processor 111. That is, since the features valued in subsequent network condition analysis are different, the multiple N-tuple information can be sampled for one or more key features. The sampled N-tuple information that reflects the features valued in subsequent network condition analysis can be filtered out from the multiple N-tuple information, thereby reducing the amount of sampled N-tuple information that the forwarding device 1 sends to the network analysis device 20 through the first processor 111. On the other hand, the first processor 111 of the forwarding device 1 can aggregate the multiple N-tuple information and obtain statistical data, so that the forwarding device 1 can send the statistical data to the network analysis device 20 through the first processor 111.

[0072] The sampled N-tuple information includes indicator data used to highlight the features valued in network condition analysis. This indicator data includes indicator data from multiple dimensions in micro-burst events, which are periodically sent to the network analysis device 20. The time granularity corresponding to the period of sending statistical data is relatively coarse, and the amount of statistical data sent to the network analysis device 20 is relatively small. On the other hand, the forwarding device 10 sends the sampled N-tuple information to the network analysis device 20 when it is triggered. The time granularity for determining whether the forwarding device 10 meets the triggering conditions is relatively fine, and when the forwarding device 10 is triggered and meets the triggering conditions, the amount of sampled N-tuple information sent to the network analysis device 20 through the first processor 111 is relatively large.

[0073] The network analysis device 20 analyzes the data changes of the micro-burst event that occurred in the forwarding device 1 based on the received reported data (including sampled N-tuple information and statistical data), and can output and display the data to the user in a visual form.

[0074] Figure 2 Forwarding devices 2 and 3 can adopt the same structure as forwarding device 1, which will not be described in detail here.

[0075] in, Figure 3 A schematic diagram of the structure of a network analysis device 20 provided in an embodiment of this application is shown. Figure 3 As shown, the network analysis device 20 can be a network management device or a control device capable of analysis and control functions. Specifically, the network management device can be an NCE (Network Entity), a virtual machine providing cloud services, etc. The network analysis device 20 includes at least: a processor 210, a memory 220, a communication port 230, and a bus 240.

[0076] The communication port 230 may include an Ethernet port, etc., and can be used to receive data transmitted by the forwarding device 10. Specifically, the network analysis device 20 can communicate with the forwarding device 10 via SNMT. The network analysis device 20 can store the received data in the memory 220. In addition, the memory 220 is also used to store the logic code corresponding to the data transmission method provided in the embodiments of this application, or in other words, the memory 220 can store the logic code corresponding to a certain step performed by the network analysis device 20 as described in the following embodiments.

[0077] The processor 210 can be used to output and display target data based on the acquired target data.

[0078] Optionally, bus 240 can be a peripheral component interconnect (PCI) bus, etc., and this application does not limit the type of bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus 240 may be represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 240 may include a path for transmitting information between various components of the network analysis device 20 (e.g., processor 210, memory 220, and communication port 230).

[0079] Optional, Figure 2 The first memory 113 shown and Figure 3 The memory 220 shown may include random access memory (RAM), read-only memory (ROM), etc. Figure 2 The first processor 111 shown and Figure 3 The processor 210 shown can be a central processing unit (CPU) or other general-purpose processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), digital signal processor (DSP) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0080] The system architecture and application scenarios described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0081] For ease of understanding, the data transmission method provided in this application is described below with reference to the accompanying drawings. This data transmission method is applicable to… Figure 2 The relay device shown.

[0082] Figure 4 A schematic flowchart of a data transmission method provided in an embodiment of this application is shown. This method is executed by a forwarding device. The forwarding device may be... Figure 2 Any forwarding device in the process. The data transmission method includes the following steps:

[0083] S301, in response to detecting a first micro-burst event in the first queue, the forwarding device acquires the first micro-burst data of the first queue.

[0084] In this embodiment of the application, when the forwarding device detects a first micro-burst event in the first queue, the forwarding device can obtain the first micro-burst data of the first queue.

[0085] Specifically, the first micro-burst data characterizes the changes in data within the first queue across different forwarding dimensions. In other words, the first micro-burst data includes indicator data for the first queue across different forwarding dimensions during the duration of the first micro-burst event. This indicator data indicates the changes in data within the queue. Indicator data across different forwarding dimensions refers to different indicators that can evaluate the queue status or data transmission status.

[0086] In one possible implementation, the first microburst data includes the identifier of the first queue, the start time of the first microburst event, and the end time of the first microburst event.

[0087] Since the buffer of the forwarding device can contain multiple queues, in order to distinguish the queue in which the first micro-burst event occurred, the identifier of the first queue can be recorded when it is determined that the first micro-burst event occurred in the first queue.

[0088] Specifically, when the forwarding device detects the start of the first micro-burst event in the first queue, it records the start time of the first micro-burst event, for example, by recording the start time of the first micro-burst event as a burst start timestamp. When it detects the end of the first micro-burst event in the first queue, it records the end time of the first micro-burst event, for example, by recording the end time of the first micro-burst event as a burst end timestamp.

[0089] In one possible implementation, the forwarding device determines whether to initiate the first micro-burst event by detecting the real-time queue depth of the first queue. Specifically, when the forwarding device detects that the queue depth of the first queue has reached the burst alarm threshold (BAT), it records the burst start timestamp (startTime) of the first micro-burst event; when the forwarding device detects that the queue depth of the first queue has reached the burst release threshold (BRT), it records the burst end timestamp (endTime) of the first micro-burst event.

[0090] In one possible implementation, the first micro-burst data also includes at least one of packet loss information and packet overage information.

[0091] The packet loss information includes the number of dropped packets, the frequency of dropped packets, the number of dropped bytes, and the frequency of dropped bytes; the packet passing information includes the number of passed packets, the frequency of passed packets, the number of passed bytes, and the frequency of passed bytes.

[0092] Optionally, during the data input / output queuing process through the first queue, the forwarding device records at least one of the packet loss information and packet overload information (for example, recorded in the register module included in the forwarding chip of the forwarding device). After the forwarding device determines the time period of the first micro-burst event, that is, the time period between the start time and the end time of the first micro-burst event, it obtains the information within the corresponding time period and statistically analyzes the packet loss information or packet overload information contained in the first micro-burst data.

[0093] In one possible implementation, the first micro-burst data also includes the peak queue depth and the time at which the peak queue depth occurred.

[0094] Optionally, when the first micro-burst event begins to occur in the first queue, the forwarding device can obtain the queue depth of the first queue in real time. When the first micro-burst event ends, it can determine the peak queue depth and the time when the peak queue depth occurs during the duration of the first micro-burst event. The time when the peak queue depth occurs is recorded as a burst peak timestamp in the form of a timestamp.

[0095] In one possible implementation, in response to the forwarding device detecting a first micro-burst event in the first queue, the forwarding device obtains the quadruple information of the first queue, and then obtains other indicator data of the first queue within the time period between the start time and the end time of the first micro-burst event. The forwarding device combines the quadruple information with other indicator data to obtain the first micro-burst data.

[0096] The quaternion information may include the start time of the first micro-burst event, the end time of the first micro-burst event, the peak queue depth, and the time when the peak queue depth occurred; other indicator data may include at least one of packet loss information or packet overage information, inbound traffic information, or outbound traffic information.

[0097] In other words, when the forwarding device detects the start of the first micro-burst event in the first queue, it records the start time of the first micro-burst event, for example, by recording the start time of the first micro-burst event as a burst start timestamp. Then, the forwarding device can record the queue depth of the first queue at various moments during the duration of the first micro-burst event, and when it detects the end of the first micro-burst event in the first queue, it records the end time of the first micro-burst event, for example, by recording the end time of the first micro-burst event as a burst end timestamp. Simultaneously, it calculates the peak queue depth (the maximum queue depth during the duration of the first micro-burst event) and the corresponding peak burst timestamp. The forwarding device obtains the start time, end time, peak queue depth, and peak burst timestamp of the first micro-burst event occurring in the first queue, and generates a four-tuple information in the form of a four-tuple encapsulation. Then, based on the start time and end time of the first micro-burst event in the four-tuple information, the forwarding device obtains at least one other indicator data of the first queue during the time period between the start time and end time of the first micro-burst event, including packet loss information or packet gain information, inbound traffic information or outbound traffic information. The forwarding device then superimposes the obtained other indicator data with the data in the four-tuple information to form the first micro-burst data. The first micro-burst data is an N-tuple information encapsulated with at least one of the start time, end time, peak queue depth, peak burst time, and other indicator data of the first micro-burst event.

[0098] In one possible implementation, the forwarding device determines whether to initiate a micro-burst event by detecting the real-time queue depth of the first queue. Specifically, when the forwarding device detects that the queue depth of the first queue has reached the burst alarm threshold (BAT), it records the burst start timestamp (startTime). When the forwarding device detects that the queue depth has reached the burst release threshold (BRT), it records the burst end timestamp (endTime), the burst peak timestamp (peakTime), and the peak queue depth (peak).

[0099] In one possible implementation, the forwarding device includes a forwarding chip, which in turn includes a storage module. The forwarding chip can be used to detect a first micro-burst event occurring in the first queue and generate a four-tuple of information about the first queue where the first micro-burst event occurred. The storage module can be used to store the four-tuple information about the first micro-burst event, which includes the start time, end time, peak queue depth, and peak burst time of the micro-burst event.

[0100] In other words, forwarding devices may include, for example Figure 2 The forwarding chip shown is used by the forwarding device to detect whether micro-burst events have occurred in each queue. Specifically, the forwarding device detects the queue depth of each queue through the forwarding chip. When the queue depth reaches BAT, the startTime is recorded in the storage module of the forwarding chip. When the forwarding device detects that the queue depth reaches BRT through the processing module of the forwarding chip, the endTime, peakTime, and peak are recorded in the storage module of the forwarding chip, and are recorded together with the startTime corresponding to the micro-burst event.

[0101] In one possible implementation, after obtaining the quadruple information, the forwarding device determines the duration of the first micro-burst event based on the start and end times of the micro-burst event in the quadruple information, and obtains other indicator data of the first queue in which the micro-burst event occurred within the duration of the first micro-burst event. Specifically, the forwarding device can obtain other indicator data of the first queue in which the first micro-burst event occurred within the duration of the first micro-burst event from the register module of the forwarding chip.

[0102] The forwarding chip of the forwarding device includes a register module, which is used to continuously record other indicator data of the first queue. The other indicator data includes at least one of packet loss information and inbound / outbound traffic information. The first micro-burst data includes other indicator data during the duration of the first micro-burst event.

[0103] In one possible scenario, other metrics generated during the normal data input and output process of the first queue, such as packet loss information and inbound / outbound traffic information, can be recorded in the register module, which can be read.

[0104] For example, if there is a queue 1 in the buffer of the forwarding device, when a packet loss occurs during normal data input and output, the time of packet loss and the number of lost packets can be recorded in the register module. Alternatively, the time of byte dropping and the amount of dropped bytes can also be recorded in the register module. Or, the inbound traffic information and the corresponding occurrence time or the outbound traffic information and the corresponding occurrence time can also be recorded in the register module.

[0105] In one possible implementation, after the forwarding device obtains the quadruple information through the forwarding chip, it calls the register module to obtain other indicator data according to the start and end times of the micro-burst events in the quadruple information, and then encapsulates the indicator data in the quadruple information with other indicator data into N-tuple information.

[0106] For example, Figure 5 This is a schematic diagram of a data format for a first microburst data according to an embodiment of this application. For example... Figure 5 As shown, the first micro-burst data includes queue identifier, micro-burst start timestamp, micro-burst end timestamp, queue peak depth, burst peak timestamp, received data packet count, received byte count, dropped data packet count, dropped byte count, maximum traffic, and other data.

[0107] In this process, after generating the N-tuple information, which is the first micro-burst data, the forwarding device can store the first micro-burst data in the forwarding device's memory.

[0108] S302, the forwarding device acquires the target data within the first cycle based on the first micro-burst data.

[0109] In this embodiment of the application, after the forwarding device obtains the first micro-burst data generated by the first micro-burst event in the first queue, it can obtain the target data within the first period based on the first micro-burst data.

[0110] The target data includes first micro-burst data and first statistical data, which characterize the frequency of occurrence of the first micro-burst event. The first statistical data includes the number of times the first micro-burst event occurred, and also includes the number of times the indicator data of the first cohort meets the specified conditions for the occurrence of the first micro-burst event.

[0111] In one possible implementation, the first micro-burst data also includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

[0112] In other words, if the first micro-burst data also includes at least one of packet loss information and packet gain information, the first statistical data includes not only the number of occurrences of the first micro-burst event, but also the number of occurrences of the first micro-burst event with packet loss.

[0113] Since the forwarding device can obtain one or more first micro-burst data determined in the first period, if the first micro-burst data includes packet loss information or packet gain information, the forwarding device can count the number of first micro-burst data with packet loss or packet loss number meeting the specified conditions. The number of first micro-burst data corresponds to the number of first micro-burst events. Therefore, in addition to counting the number of first micro-burst events in the first period, the forwarding device can also count the number of first micro-burst events with packet loss or packet loss number meeting the specified conditions in the first period.

[0114] In one possible implementation, the forwarding device acquires first target data within a third period, where the first period is longer than the third period. The first target data includes third micro-burst data and third statistical data. The third micro-burst data is used to characterize the changes in data of the first queue where the third micro-burst event occurred in the forwarding dimension. The third micro-burst event is a first micro-burst event with packet loss. The third statistical data includes the number of times the third micro-burst event occurred. Based on the first target data, target data within the first period is acquired, where the target data also includes the first target data.

[0115] In other words, the forwarding device acquires the first target data within the third cycle, collects the micro-burst events with packet loss from one or more micro-burst events within the third cycle as the third micro-burst events, and uses the third micro-burst data and third statistical data corresponding to the third micro-burst events as the content of the first target data. Based on each first target data collected according to the third cycle, the target data within the first cycle is acquired.

[0116] For example, taking a third period of 10ms as an example, the forwarding device monitors in real time whether micro-burst events occur in each queue. After the forwarding device detects that the first micro-burst event has occurred in the first queue, it can store the first micro-burst data of the first queue during the occurrence of the first micro-burst event. The forwarding device will then retrieve and filter the first micro-burst events every 10ms to determine whether there is a third micro-burst event in the first micro-burst event. Specifically, the forwarding device analyzes the first micro-burst data stored in every 10ms to determine the number of first micro-burst data with packet loss or packet loss meeting the specified conditions. The number of first micro-burst data with packet loss or packet loss meeting the specified conditions can represent the number of times the third micro-burst event occurs in that 10ms.

[0117] In one possible implementation, the first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs, and the first statistical data is also used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds a threshold.

[0118] In other words, if the first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs, the first statistical data includes not only the number of times the first micro-burst event occurs, but also the number of times the peak queue depth exceeds the threshold for the first micro-burst event.

[0119] Since the forwarding device can obtain one or more first micro-burst data determined in the first period, if the first micro-burst data includes the queue depth peak and the time when the queue depth peak occurs, the forwarding device can count the number of first micro-burst data where the queue depth peak exceeds the threshold. The number of first micro-burst data corresponds to the number of times the first micro-burst event occurs. Therefore, in addition to counting the number of times the first micro-burst event occurs in the first period, the forwarding device can also count the number of times the first micro-burst event where the queue depth peak exceeds the threshold occurs in the first period.

[0120] In one possible implementation, the forwarding device acquires second target data within a third period, where the first period is longer than the third period. The second target data includes fourth micro-burst data and fourth statistical data. The fourth micro-burst data is used to characterize the changes in data of the first queue where the fourth micro-burst event occurred in the forwarding dimension. The fourth micro-burst event is the first micro-burst event where the queue depth peak exceeds a threshold. The fourth statistical data includes the number of times the fourth micro-burst event occurs. Based on the second target data, target data within the first period is acquired, and the target data also includes the second target data.

[0121] In other words, the forwarding device acquires the second target data within the third period, takes one or more micro-burst events within the third period whose peak collection queue depth exceeds the threshold as the fourth micro-burst event, takes the fourth micro-burst data and the fourth statistical data corresponding to the fourth micro-burst event as the content of the second target data, and acquires the target data within the first period based on each second target data acquired according to the third period.

[0122] For example, taking a third period of 10ms as an example, the forwarding device monitors in real time whether micro-burst events occur in each queue. After the forwarding device detects that the first micro-burst event has occurred in the first queue, it can store the first micro-burst data of the first queue during the occurrence of the first micro-burst event. The forwarding device will then retrieve and filter the first micro-burst events every 10ms to determine whether there is a fourth micro-burst event in the first micro-burst event. Specifically, the forwarding device analyzes the first micro-burst data stored in every 10ms to determine the number of first micro-burst data whose queue depth peak exceeds the threshold. The number of first micro-burst data whose queue depth peak exceeds the threshold can represent the number of times the fourth micro-burst event occurs in that 10ms.

[0123] After executing S302, the forwarding device can execute S303 according to the first cycle or S304 according to the second cycle.

[0124] S303, the forwarding device sends target data to the network analysis device.

[0125] In this embodiment of the application, after obtaining the target data within the first period, the forwarding device can send the target data to the network analysis device.

[0126] In one possible scenario, the forwarding device can send the target data to the network analysis device according to the first cycle.

[0127] In other words, after the forwarding device obtains the target data in the first cycle, it directly sends the target data to the network analysis device.

[0128] In another possible scenario, the forwarding device can send the target data to the network analysis device in the first cycle if it determines that a third micro-burst event has occurred.

[0129] In other words, if the first micro-burst data also includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss, the forwarding device determines whether a third micro-burst event exists in each first period according to the third period. If a third micro-burst event is determined to exist in the first period, the forwarding device starts sending target data to the network analysis device according to the first period. If a third micro-burst event is determined not to exist in the first period, the forwarding device determines whether a third micro-burst event exists in the next first period, until a first period in which a third micro-burst event is determined to exist, and takes the first period in which the third micro-burst event exists as the starting point, and sends target data to the network analysis device according to the first period.

[0130] For example, taking a first period of 1 second and a third period of 10 ms as an example, the forwarding device analyzes the first micro-burst data stored within each 10 ms to determine the number of first micro-burst data with packet loss or whose packet loss quantity meets specified conditions. This number of first micro-burst data with packet loss or whose packet loss quantity meets specified conditions can characterize the number of times the third micro-burst event occurs within that 10 ms. The forwarding device can use the third statistical data, the first statistical data, and the first micro-burst data of each first micro-burst event within each 10 ms period as target data and send them to the network analysis device at a 1-second cycle.

[0131] In another possible scenario, the forwarding device can send the target data to the network analysis device in the first cycle if it determines that a fourth micro-burst event has occurred.

[0132] In other words, when the first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs, and the first statistical data is also used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds the threshold, the forwarding device determines whether there is a fourth micro-burst event in each first cycle according to the third cycle. If it is determined that there is a fourth micro-burst event in the first cycle, it starts sending target data to the network analysis device according to the first cycle. If the forwarding device determines that there is no fourth micro-burst event in the first cycle, the forwarding device can determine whether there is a fourth micro-burst event in the next first cycle, until the first cycle in which the fourth micro-burst event is determined to exist. Starting from the first cycle in which the fourth micro-burst event exists, the forwarding device can send target data to the network analysis device according to the first cycle.

[0133] For example, taking a first period of 1 second and a third period of 10 ms as an example, the forwarding device analyzes the first micro-burst data stored within each 10 ms to determine the number of first micro-burst data whose queue depth peak exceeds a threshold. The number of first micro-burst data whose queue depth peak exceeds the threshold can characterize the number of times the fourth micro-burst event occurs within that 10 ms. The forwarding device uses the fourth statistical data, the first statistical data, and the first micro-burst data of each first micro-burst event within each 10 ms as target data and sends them to the network analysis device at a period of 1 second.

[0134] Since the third or fourth statistical data obtained by the forwarding device according to the third cycle does not need to be directly reported to the network analysis device, in order to reduce the number of data reports and reduce the data reporting pressure of the forwarding device, the forwarding device will report to the network analysis device according to the first cycle. That is, the forwarding device determines whether there is a third micro-burst event or a fourth micro-burst event in each of the third cycles within the current cycle according to the first cycle. If there is, the forwarding device will report the target data obtained in the first cycle to the network analysis device according to the first cycle.

[0135] S304, the forwarding device obtains the second statistical data within the second period based on the second micro-burst data and sends the second statistical data to the network analysis device.

[0136] The second statistical data is used to characterize the frequency of the second micro-burst event. The second period is longer than the first period. The second statistical data includes the first statistical data. The second micro-burst data is used to characterize the changes in the data of the queues where the second micro-burst event occurred under the forwarding dimension. The second micro-burst event is a micro-burst event that occurs within the second period.

[0137] In other words, in addition to sending the target data corresponding to the queue where the first micro-burst event occurred to the network analysis device according to the first cycle, the forwarding device can also obtain the second statistical data according to a second cycle that is longer than the first cycle, and send the second statistical data to the network analysis device according to the second cycle that is longer than the first cycle.

[0138] Specifically, the forwarding device sends target data to the network analysis device according to the first cycle, enabling more granular acquisition and reporting of target data. The forwarding device then sends second statistical data to the network analysis device according to the second cycle, maintaining periodic reporting of relatively coarser-grained second statistical data. This ensures that the network analysis device can obtain more comprehensive data related to micro-emergencies.

[0139] For example, when a forwarding device sends target data to a network analysis device, it encapsulates the target data according to a message format, which may include the field content shown in Table 1 below.

[0140]

[0141] Table 1

[0142] When a forwarding device sends target data to a network analysis device, the message format encapsulated with the target data includes fields such as time, device identifier, interface identifier, queue identifier, number of micro-burst events, number of micro-burst events resulting in packet loss, and micro-burst data within the third period. There may be one or more micro-burst events counted in the third period. In the case of multiple micro-burst events, to reduce the amount of data reported to the network analysis device and to ensure the micro-burst data reported to the network analysis device has high analyzability, one or more micro-burst data can be selected from the multiple micro-burst data in the third period and reported to the network analysis device.

[0143] Among them, micro-burst data is used to characterize the changes in the data of the queue in the forwarding dimension during the occurrence of micro-burst events in the queue.

[0144] For example, the forwarding device can identify the micro-burst with the highest number of packet losses or the top few micro-bursts with the highest number of packet losses from multiple micro-bursts in the third period and report it to the network analysis device; or, the forwarding device can identify the micro-burst with the highest peak queue depth or the top few micro-bursts with the highest peak queue depth from multiple micro-bursts in the third period and report it to the network analysis device.

[0145] For example, the comparison of the processing of target data sent from the two types of forwarding devices to the network device is shown in Table 2 below.

[0146]

[0147] Table 2

[0148] For example, when a forwarding device reports target data to a network analysis device, the forwarding device monitors queue changes in real time, obtains micro-burst data for each queue within the first period, caches the micro-burst data for each queue within the first period, samples the micro-burst data of queues with packet loss according to the third period, and records the micro-burst data with the largest number of packet losses or the top few in terms of packet loss. Then, it encapsulates the micro-burst data and the first statistical data according to the message format shown in Table 1 to obtain the target data in the message format. The forwarding device can send the target data according to the first period and stop reporting the target data to the network analysis device after the reporting duration has elapsed. This method can minimize the amount of data transmitted while ensuring that the micro-burst data to be analyzed is comprehensive and sufficient.

[0149] In one possible implementation, the forwarding device, in response to detecting a second micro-burst event in the second queue, acquires second micro-burst data, which is used to characterize the changes in data of the second queue in the forwarding dimension; or, the forwarding device, in response to detecting a second micro-burst event in the first queue, acquires second micro-burst data, which is used to characterize the changes in data of the first queue in the forwarding dimension. The second queue can be any queue in the forwarding device other than the first queue.

[0150] In other words, after a second micro-burst event occurs in any queue of the forwarding device according to the second cycle, the forwarding device can obtain the corresponding second micro-burst data.

[0151] After the forwarding device executes S303, the network analysis device can process the received target data; or after the forwarding device executes S304, the network analysis device can process the received second statistical data. Specifically, Figure 6 A schematic flowchart of a data transmission method provided in an embodiment of this application is shown. This data transmission method is applicable to... Figure 2 or Figure 3 The network analysis device shown. The data transmission method includes the following steps:

[0152] S401, the network analysis device receives target data sent by the forwarding device.

[0153] In this embodiment, the network analysis device can receive target data sent by the forwarding device according to a first cycle. The target data may include first micro-burst data and first statistical data within the first cycle. The first statistical data can be used to characterize the occurrence frequency of the first micro-burst event, and the first micro-burst data can be used to characterize the data change of the first queue in the forwarding dimension. The first micro-burst data is the micro-burst data of the first queue obtained by the forwarding device when it detects the occurrence of the first micro-burst event in the first queue. The process of the forwarding device obtaining the first micro-burst data and the first statistical data is as shown in S301 and S302, and will not be described again here.

[0154] Optionally, after the forwarding device executes S303, the network analysis device can execute S401 and then S402, or after the forwarding device executes S304, the network analysis device can execute S403.

[0155] S402, the network analysis device outputs and displays the target data.

[0156] In this embodiment of the application, after receiving the target data, the network analysis device can output and display the target data so that professionals can analyze the target data sent by the forwarding device and determine the situation of micro-burst events in the queue of the forwarding device.

[0157] In one possible implementation, the network analysis device displays first statistical data within a first period through a first graphical output of a first display interface; and displays first micro-burst data within the first period through a second graphical output of the first display interface. After receiving target data, the network analysis device can display the first display interface, which can be used to distinguish and display the first statistical data and the first micro-burst data on the first display interface according to the target data of the first period, using different graphics.

[0158] Figure 7 This is a schematic diagram of a first display interface according to an embodiment of this application. Figure 7 As shown, in the form of a bar chart, each bar represents a first statistical statistic. If the first period is 1 second, Figure 7 The output shows the first statistics obtained in the first three periods, respectively. Figure 7 In the image, three bars are displayed at positions 1s, 2s, and 3s. The first statistical data corresponding to each bar represents the total number of occurrences of the first micro-burst event. For example... Figure 7 As shown, the second graph is in tabular form, meaning that the first micro-burst data can be displayed on the first display interface through tabular output.

[0159] In another possible implementation, after the user selects a first graph corresponding to a certain period (e.g., 3 seconds), the network analysis device outputs and displays the first micro-burst data corresponding to 3 seconds in a table on the first display interface. That is, the first micro-burst data displayed in the table corresponds to the period of a certain bar in the histogram. The first micro-burst data output in tabular form may include data such as the queue identifier, start time, end time, peak time, peak queue depth, and packet loss rate of the first micro-burst event.

[0160] Specifically, the first graphic may include, but is not limited to, bar charts, sector charts, dots, tables, waveforms, and other forms that can be used to represent numerical values; the second shape may include, but is not limited to, tables.

[0161] Since the first statistical data can be used to characterize not only the frequency of the first micro-burst event but also the frequency of the first micro-burst event with packet loss, the network analysis device can simultaneously output and display both the frequency of the first micro-burst event and the frequency of the first micro-burst event with packet loss.

[0162] In one possible implementation, if the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss, the specific parameters included in the first statistical data can be represented by different colors of the first graph. The total frequency of occurrence of the first micro-burst event within the first period is output and displayed through the first graph with the first color in the first display interface; if the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss, the frequency of occurrence of the first micro-burst event with packet loss within the first period is output and displayed through the first graph with the second color in the first display interface.

[0163] In other words, the first display interface distinguishes the total frequency of the first micro-burst event within the first cycle and the frequency of the first micro-burst event with packet loss within the first cycle by different colors of the same graphic.

[0164] For example, Figure 8 This is a schematic diagram of a first display interface according to an embodiment of this application. Figure 8 As shown, in the form of a bar chart, each bar can identify the first statistical data. If the first period is 1 second, Figure 8 The output shows the first statistics obtained in the first three periods, respectively. Figure 8 In the diagram, six bars are displayed at positions 1s, 2s, and 3s. Two bars are displayed at each position, and the two bars at each position have different colors. The first statistical data corresponding to the bars colored white is used to represent the total number of occurrences of the first micro-burst event within that second, while the first statistical data corresponding to the bars colored black is used to represent the number of occurrences of the first micro-burst event of packet loss within that second.

[0165] Similarly, the first micro-burst data can still be directly output and displayed on the first display interface via a second graph, such as a table. Alternatively, after the network analysis device receives a selection operation for a first graph with a certain color corresponding to a certain period (e.g., 3 seconds), it can output and display the first micro-burst data corresponding to the first colored first graph within the first period corresponding to 3 seconds on the first display interface, displaying the first micro-burst data in a table. Specifically, if the first micro-burst data includes data such as the queue identifier, start time, end time, peak time, peak queue depth, and packet loss rate for each first micro-burst event, a table can be displayed on the first display interface, containing data such as the queue identifier, start time, end time, peak time, peak queue depth, and packet loss rate for each first micro-burst event.

[0166] In one possible implementation, the network analysis device outputs the total frequency of occurrence of the first micro-burst event within a first period through a first colored first graphic in a first display interface; if the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event where the peak queue depth exceeds a threshold, the device outputs the frequency of occurrence of the first micro-burst event where the peak queue depth exceeds a threshold through a third colored first graphic in the first display interface.

[0167] In other words, the first display interface distinguishes the total frequency of the first micro-burst event within the first cycle and the frequency of the first micro-burst event where the peak queue depth exceeds the threshold within the first cycle by different colors of the same graphic in the first display interface.

[0168] In addition, the first statistical data may also include the third statistical data and the third micro-burst data under the third period, or the first statistical data may also include the fourth statistical data and the fourth micro-burst data under the third period.

[0169] In one possible implementation, the output displays the third statistical data and the third micro-burst data within the first period; the third statistical data includes the number of occurrences of the third micro-burst event, which is the first micro-burst event with packet loss, and the third micro-burst data is used to characterize the changes in the data of the first queue where the third micro-burst event occurred in the forwarding dimension; or, the output displays the fourth statistical data and the fourth micro-burst data within the first period; the fourth statistical data includes the number of occurrences of the fourth micro-burst event, which is the first micro-burst event where the peak queue depth exceeds a threshold, and the fourth micro-burst data is used to characterize the changes in the data of the first queue where the fourth micro-burst event occurred in the forwarding dimension.

[0170] For example, the network analysis device can directly output and display the third statistical data and the third micro-burst data for each first period, or output and display the fourth statistical data and the fourth micro-burst data for each first period. The output display can be in the form of a table; specifically, the third micro-burst data for each first period can be shown in Table 3 below.

[0171]

[0172]

[0173] Table 3

[0174] The packet loss information or packet transmission information can be the number of packets lost, the number of bytes lost, or the number of packets transmitted or transmitted during the third micro-burst event. Other indicator data may include the maximum inbound rate, maximum latency, and other indicators during the third micro-burst event.

[0175] Similarly, the third statistical data within each first period, or the fourth statistical data or fourth micro-burst data within each first period, can be output and displayed in the form of the table above.

[0176] Optionally, the network analysis device can execute S402 and S403 in any order. It can execute S402 after S403, or S403 before S402, or S402 and S403 at the same time.

[0177] S403, the network analysis device receives the second statistical data sent by the forwarding device and outputs and displays the second statistical data.

[0178] Among them, the network analysis device can obtain the second statistical data according to the second period. The second statistical data can be used to characterize the frequency of the second micro-burst event. The second period is longer than the first period. The second statistical data includes the first statistical data. The second micro-burst data is used to characterize the changes in the data of the queue where the second micro-burst event occurred in the forwarding dimension.

[0179] Optionally, the second statistical data includes the number of times the second micro-burst event occurred within the second period. The second statistical data may also include the number of times a second micro-burst event with packet loss occurred within the second period, or it may further include the number of times a second micro-burst event with a queue depth peak exceeding a threshold occurred within the second period.

[0180] In one possible implementation, the network analysis device can receive second statistical data sent by the forwarding device. The second statistical data characterizes the frequency of the second micro-burst event; the second micro-burst event is a micro-burst event detected by the forwarding device within a second period; the second period is longer than the first period. Specifically, the content of the second statistical data sent by the forwarding device to the network analysis device is as shown in S304 above, and will not be repeated here.

[0181] Since the analysis needs for micro-burst data under different conditions are different, the second statistical data can be displayed by different coloring of the same graph to distinguish the number of occurrences of the second micro-burst event in the second period and the number of occurrences of the second micro-burst event with packet loss in the second period; or, the second statistical data can be displayed by different coloring of the same graph to distinguish the number of occurrences of the second micro-burst event in the second period and the number of occurrences of the second micro-burst event with queue depth peak exceeding the threshold in the second period.

[0182] In one possible implementation, the network analysis device can display second statistical data within a second period via a third graphical output of a second display interface.

[0183] Optionally, before displaying the target data, the network analysis device receives and displays the second statistical data sent by the forwarding device. Alternatively, there may be no direct order between displaying the target data and displaying the second statistical data; they can be displayed simultaneously or sequentially, without any restriction.

[0184] In other words, the first display interface and the second display interface can be the same interface or different interfaces; there is no restriction here.

[0185] In one possible implementation, the network analysis device can output the total frequency of the second micro-burst event within the second period through the third graphic with fourth coloring in the second display interface; if the second statistical data is also used to characterize the frequency of the second micro-burst event with packet loss, the frequency of the second micro-burst event with packet loss within the second period can be output through the third graphic with fifth coloring in the second display interface.

[0186] In another possible implementation, the total frequency of the second micro-burst event within each second period is output through the third graphic with the fourth coloring in the second display interface; if the second statistical data is also used to characterize the frequency of the first micro-burst event where the peak queue depth exceeds the threshold, the frequency of the second micro-burst event where the peak queue depth exceeds the threshold within the second period is output through the third graphic with the sixth coloring in the second display interface.

[0187] For example, Figure 9 This is a schematic diagram of a second display interface according to an embodiment of this application. Figure 9 As shown, in the form of a bar chart, each bar can identify a second statistical data point. If the second period is 5 minutes, Figure 9 The output shows the second statistics obtained in the third period, which are respectively Figure 9 In the table, six bars are displayed at 5 min, 10 min, and 15 min. Two bars are displayed at each position, and the two bars at each position have different colors. The second statistical data corresponding to the bars colored white is used to represent the total number of occurrences of the first micro-burst event within that 5 min. The second statistical data corresponding to the bars colored black is used to represent the number of occurrences of the first micro-burst event with packet loss within that 5 min.

[0188] In one possible implementation, in response to receiving a selection operation on a third graphic, the target data within each of the first cycles in the second cycle corresponding to the third graphic is output and displayed.

[0189] In other words, after the network analysis device outputs and displays the second statistical data, the network analysis device determines which target data from each of the first periods within the second period will be displayed in the subsequent output by selecting the third graph corresponding to the second statistical data.

[0190] For example, after receiving a selection operation on a third graphic in a second display interface, the network analysis device can switch to displaying a first display interface and output the target data in each first cycle of the second cycle corresponding to the selected third graphic on the first display interface. Figure 8 as well as Figure 9 As shown, if a selection operation is received for the third graphic of the fifth color corresponding to 15 minutes on the second display interface, the network analysis device can display the first display interface, and the output of the first display interface is the first shape of the first appearance and the first shape of the second appearance corresponding to each second within 10 minutes to 15 minutes, which are used to characterize the total number of micro-burst events per second and the number of micro-burst events with packet loss.

[0191] In addition, taking the first and third figures as examples, Figure 10 This is a schematic diagram illustrating how, in an embodiment of this application, target data is output and displayed after the second statistical data is displayed. Figure 10 As shown, when the network analysis device outputs and displays the second statistical data through the second display interface, specifically as follows: Figure 10 As shown, six dots are displayed at the 5-minute, 10-minute, and 15-minute positions. Two dots are displayed at each position, and the two dots at each position have different colors. The white-colored dots correspond to the second statistical data representing the total number of occurrences of the first micro-burst event within that 5-minute period, while the black-colored dots correspond to the second statistical data representing the number of occurrences of the first micro-burst event with packet loss within that 5-minute period. If the network analysis device receives a selection operation for the black-colored dot at the 10-minute position, the network analysis device can output and display the first statistical data acquired in the first period through the second display interface, which are respectively... Figure 10 In the diagram, six dots are displayed at positions 1s, 2s, and 3s. At each position, two dots are displayed with different colors. The white dots correspond to the first statistical data representing the total number of occurrences of the first micro-burst event within that second, while the black dots correspond to the first statistical data representing the number of occurrences of the first micro-burst event with packet loss within that second. For example... Figure 10As shown, the second graph is in tabular form, meaning that the first micro-burst data can be displayed on the first display interface through tabular output. Specifically, it can display the first micro-burst data of the queues that experienced the first micro-burst event, sorted by packet loss rate. The first micro-burst data output in tabular form can include data such as the queue identifier, start time, end time, peak time, peak queue depth, and packet loss rate of the first micro-burst event.

[0192] The foregoing mainly describes the solutions of the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, the data transmission device includes at least one of the hardware structures and software modules corresponding to each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0193] This application embodiment can divide the data transmission device into functional units according to the above method example. For example, each function can be divided into separate functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. The unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0194] For example, Figure 11 A schematic diagram of a data transmission apparatus 500 provided in an exemplary embodiment of this application is shown. The data transmission apparatus 500 is deployed in a forwarding device, which may be... Figure 2 Any of the forwarding devices 10 shown. The data transmission apparatus 500 includes:

[0195] The acquisition module 510 is used to acquire the first micro-burst data of the first queue in response to the detection of the first micro-burst event in the first queue. The first micro-burst data is used to characterize the changes in the data of the first queue in the forwarding dimension.

[0196] The determination module 520 is used to obtain target data within a first period based on the first micro-burst data. The target data includes the first micro-burst data and a first statistical data, wherein the first statistical data is used to characterize the occurrence frequency of the first micro-burst event.

[0197] The sending module 530 is used to send the target data to the network analysis device.

[0198] In one possible implementation, the first micro-burst data includes the identifier of the first queue, the start time of the first micro-burst event, and the end time of the first micro-burst event.

[0199] For example, combining Figure 4 The acquisition module 510 can be used to perform actions such as... Figure 4 As shown in S301, the determination module 520 can be used to perform, for example... Figure 4 As shown in S302, the transmitting module 530 can be used to perform, for example... Figure 4 S303 is shown.

[0200] In one possible implementation, the first micro-burst data further includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

[0201] In one possible implementation, the first micro-burst data further includes the peak queue depth and the time when the peak queue depth occurs, and the first statistical data is also used to characterize the frequency of the first micro-burst event when the peak queue depth exceeds a threshold.

[0202] In one possible implementation, the acquisition module 510 is further configured to acquire second statistical data within a second period based on the second micro-burst data. The second statistical data is used to characterize the frequency of the occurrence of the second micro-burst event. The second period is greater than the first period. The second statistical data includes the first statistical data. The second micro-burst data is used to characterize the changes in data of the queue where the second micro-burst event occurred under the forwarding dimension.

[0203] The sending module 530 is also used to send the second statistical data to the network analysis device.

[0204] In one possible implementation, the acquisition module 510 is further configured to acquire the second micro-burst data in response to detecting the second micro-burst event occurring in the second queue, the second micro-burst data being used to characterize the changes in the data of the second queue in the forwarding dimension; or to acquire the second micro-burst data in response to detecting the second micro-burst event occurring in the first queue, the second micro-burst data being used to characterize the changes in the data of the first queue in the forwarding dimension.

[0205] In one possible implementation, the determining module 520 is further configured to acquire first target data within a third period, wherein the first period is longer than the third period, the first target data includes third micro-burst data and third statistical data, wherein the third micro-burst data is used to characterize the changes in data of the first queue where the third micro-burst event occurred in the forwarding dimension, the third micro-burst event is the first micro-burst event with packet loss, and the third statistical data includes the number of times the third micro-burst event occurred; and based on the first target data, acquire the target data within the first period, wherein the target data also includes the first target data.

[0206] In one possible implementation, the determining module 520 is further configured to acquire second target data within a third period, wherein the first period is longer than the third period, the second target data includes fourth micro-burst data and fourth statistical data, wherein the fourth micro-burst data is used to characterize the changes in data of the first queue where the fourth micro-burst event occurred in the forwarding dimension, the fourth micro-burst event is the first micro-burst event where the peak queue depth exceeds a threshold, and the fourth statistical data includes the number of times the fourth micro-burst event occurs; and based on the second target data, acquire the target data within the first period, wherein the target data also includes the second target data.

[0207] As an example, combined Figure 2 The functions implemented by some or all of the acquisition module 510, determination module 520, and transmission module 530 in the data transmission device can be achieved through... Figure 2 Execute on any of the forwarding devices 10.

[0208] For example, Figure 12 A schematic diagram of a data transmission apparatus 600 provided in an exemplary embodiment of this application is shown. The data transmission apparatus 600 is deployed in a network analysis device. The network analysis device may be... Figure 2 or Figure 3 The network analysis device 20 shown, the data transmission device 600 includes:

[0209] The receiving module 610 is used to receive target data sent by the forwarding device. The target data includes first micro-burst data and first statistical data within a first period. The first statistical data is used to characterize the occurrence frequency of the first micro-burst event. The first micro-burst data is used to characterize the data change of the first queue in the forwarding dimension. The first micro-burst data is the micro-burst data of the first queue obtained by the forwarding device when it detects the occurrence of the first micro-burst event in the first queue.

[0210] The output display module 620 is used to output and display the target data.

[0211] For example, combining Figure 6 The receiving module 610 can be used to perform, for example... Figure 6 As shown in S401, the output display module 620 can be used to perform, for example... Figure 6 S402 is shown.

[0212] In one possible implementation, the first micro-burst data includes the identifier of the first queue, the start time of the first micro-burst event, and the end time of the first micro-burst event.

[0213] In one possible implementation, the first micro-burst data further includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

[0214] In one possible implementation, the first micro-burst data further includes the peak queue depth and the time when the peak queue depth occurs, and the first statistical data is also used to characterize the frequency of the first micro-burst event when the peak queue depth exceeds a threshold.

[0215] In one possible implementation, the output display module 620 is further configured to display the first statistical data within each first cycle through a first shape output of the first display interface; and to display the first micro-burst data within each first cycle through a second shape output of the first display interface.

[0216] In one possible implementation, the output display module 620 is further configured to output the total occurrence frequency of the first micro-burst event within each first period through the first shape of the first appearance in the first display interface; if the first statistical data is further used to characterize the occurrence frequency of the first micro-burst event with packet loss, the first shape of the second appearance in the first display interface is used to output the occurrence frequency of the first micro-burst event with packet loss within each first period.

[0217] In one possible implementation, the output display module 620 is further configured to output the total occurrence frequency of the first micro-burst event within each first period through the first shape of the first appearance in the first display interface; if the first statistical data is further used to characterize the occurrence frequency of the first micro-burst event where the queue depth peak exceeds a threshold, the first shape of the third appearance in the first display interface is used to output the occurrence frequency of the first micro-burst event where the queue depth peak exceeds a threshold within each first period.

[0218] In one possible implementation, the output display module 620 is further configured to output and display a third statistical data and a third micro-burst data for each first period; the third statistical data includes the number of occurrences of the third micro-burst event, the third micro-burst event being a first micro-burst event with packet loss, and the third micro-burst data being used to characterize the data change of the first queue in the forwarding dimension for which the third micro-burst event occurred; or, output and display a fourth statistical data and a fourth micro-burst data for each first period; the fourth statistical data includes the number of occurrences of the fourth micro-burst event, the fourth micro-burst event being a first micro-burst event where the queue depth peak exceeds a threshold, and the fourth micro-burst data being used to characterize the data change of the first queue in the forwarding dimension for which the fourth micro-burst event occurred.

[0219] In one possible implementation, the output display module 620 is further configured to receive a second statistical data sent by the forwarding device; the second statistical data is used to characterize the frequency of the occurrence of the second micro-burst event; the second micro-burst event is a micro-burst event detected by the forwarding device in the queue within the second period; the second period is greater than the first period; and the second statistical data is output and displayed.

[0220] In one possible implementation, the output display module 620 is also used to display the second statistical data within each second cycle via a third shape output of the second display interface.

[0221] In one possible implementation, the output display module 620 is further configured to output the total occurrence frequency of the second micro-burst event within each second period through the third shape of the fourth appearance in the second display interface; if the second statistical data is further used to characterize the occurrence frequency of the second micro-burst event with packet loss, the occurrence frequency of the second micro-burst event with packet loss within each second period is output through the third shape of the fifth appearance in the second display interface.

[0222] In one possible implementation, the output display module 620 is further configured to output the total frequency of occurrence of the second micro-burst event within each second period through the third shape of the fourth appearance in the second display interface; if the second statistical data is further configured to characterize the frequency of occurrence of the first micro-burst event where the queue depth peak exceeds a threshold, the frequency of occurrence of the second micro-burst event where the queue depth peak exceeds a threshold within each second period is output through the third shape of the sixth appearance in the second display interface.

[0223] In one possible implementation, the output display module 620 is further configured to, in response to receiving a selection operation on the third shape, output and display the target data within each of the first cycles in the second cycle corresponding to the third shape.

[0224] As an example, combined Figure 2 or Figure 3 The functions implemented by some or all of the receiving module 610 and the output display module 620 in the data transmission device can be achieved through... Figure 2 or Figure 3 The network analysis device 20 in the middle is executed.

[0225] This application also provides a computer program product containing instructions. The computer program product may be a software or program product containing instructions, capable of running on a forwarding device or stored on any available medium. When the computer program product runs on at least one forwarding device, it causes the at least one forwarding device to perform a data transmission method.

[0226] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that the forwarding device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the forwarding device to perform a data transmission method, or instruct the forwarding device to perform a data transmission method.

[0227] In some embodiments, the methods shown in this application can be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of art.

[0228] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0229] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0230] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0231] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0232] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0233] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0234] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data transmission method, characterized in that, The method is performed by a forwarding device, and the method includes: In response to detecting a first micro-burst event in the first queue, the first micro-burst data of the first queue is obtained, and the first micro-burst data is used to characterize the changes in the data of the first queue in the forwarding dimension. Based on the first micro-burst data, target data within a first period is obtained. The target data includes the first micro-burst data and a first statistical data, which is used to characterize the frequency of occurrence of the first micro-burst event. The target data is sent to the network analysis device.

2. The method according to claim 1, characterized in that, The first micro-burst data includes the identifier of the first queue, the start time of the first micro-burst event, and the end time of the first micro-burst event.

3. The method according to claim 2, characterized in that, The first micro-burst data also includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

4. The method according to claim 2 or 3, characterized in that, The first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs. The first statistical data is also used to characterize the frequency of the first micro-burst event when the peak queue depth exceeds a threshold.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: The second statistical data within the second period is obtained based on the second micro-burst data. The second statistical data is used to characterize the frequency of the second micro-burst event. The second period is longer than the first period. The second statistical data includes the first statistical data. The second micro-burst data is used to characterize the changes in the data of the queue where the second micro-burst event occurred under the forwarding dimension. The second statistical data is sent to the network analysis device.

6. The method according to claim 5, characterized in that, The method further includes: In response to detecting the second micro-burst event in the second queue, the second micro-burst data is acquired, which is used to characterize the changes in data of the second queue in the forwarding dimension; or In response to detecting the second micro-burst event in the first queue, the second micro-burst data is acquired, which is used to characterize the changes in the data of the first queue in the forwarding dimension.

7. The method according to claim 3, characterized in that, The acquisition of target data within the first period includes: Acquire the first target data within the third period, where the first period is longer than the third period. The first target data includes third micro-burst data and third statistical data. The third micro-burst data is used to characterize the changes in the data of the first queue where the third micro-burst event occurred in the forwarding dimension. The third micro-burst event is the first micro-burst event with packet loss. The third statistical data includes the number of times the third micro-burst event occurred. Based on the first target data, the target data within the first period is obtained, and the target data further includes the first target data.

8. The method according to claim 4, characterized in that, The acquisition of target data within the first period includes: Acquire second target data within the third period, where the first period is longer than the third period. The second target data includes fourth micro-burst data and fourth statistical data. The fourth micro-burst data is used to characterize the changes in the data of the first queue where the fourth micro-burst event occurred in the forwarding dimension. The fourth micro-burst event is the first micro-burst event where the peak queue depth exceeds a threshold. The fourth statistical data includes the number of times the fourth micro-burst event occurred. Based on the second target data, the target data within the first period is obtained, and the target data further includes the second target data.

9. A data transmission method, characterized in that, The method is performed by a network analysis device, and the method includes: The system receives target data sent by a forwarding device. The target data includes first micro-burst data and first statistical data within a first period. The first statistical data is used to characterize the frequency of occurrence of the first micro-burst event. The first micro-burst data is used to characterize the changes in data of the first queue in the forwarding dimension. The first micro-burst data is the micro-burst data of the first queue obtained by the forwarding device when it detects the occurrence of the first micro-burst event in the first queue. The output displays the target data.

10. The method according to claim 9, characterized in that, The first micro-burst data includes the identifier of the first queue, the start time of the first micro-burst event, and the end time of the first micro-burst event.

11. The method according to claim 10, characterized in that, The first micro-burst data also includes at least one of packet loss information and packet gain information, and the first statistical data is also used to characterize the frequency of occurrence of the first micro-burst event with packet loss.

12. The method according to claim 10 or 11, characterized in that, The first micro-burst data also includes the peak queue depth and the time when the peak queue depth occurs. The first statistical data is also used to characterize the frequency of the first micro-burst event when the peak queue depth exceeds a threshold.

13. The method according to any one of claims 9 to 12, characterized in that, The output displays the target data, including: The first statistical data within the first period is displayed through the first graphical output of the first display interface; The first micro-burst data within the first period is displayed through the second graphical output of the first display interface.

14. The method according to any one of claims 9 to 13, characterized in that, The method further includes: The system receives a second statistical data point sent by the forwarding device; the second statistical data point is used to characterize the frequency of the occurrence of a second micro-burst event; the second micro-burst event is a micro-burst event detected by the forwarding device in the queue within a second period; the second period is longer than the first period; The output displays the second statistical statistic.

15. The method according to claim 14, characterized in that, The output displays the second statistical data, including: The second statistical data within the second period is displayed through a third graphical output on the second display interface.

16. A data transmission device, characterized in that, The device is applied to a forwarding device, and the device includes a module for implementing the function corresponding to the method of any one of claims 1 to 8.

17. A data transmission device, characterized in that, The apparatus is applied to a network analysis device, and the apparatus includes modules for implementing the functions corresponding to the method of any one of claims 9 to 15.

Images