Fault positioning method and device, storage medium and program product

Abstract

The embodiment of the invention provides a fault positioning method and device, a storage medium and a program product, relates to the technical field of communication, and can realize quick fault positioning and improve the fault positioning efficiency. The method comprises the steps that alarm information sent by first equipment is received, the first equipment comprises a plurality of ports, a first flow rate time sequence and a second flow rate time sequence of the flow rate of each port in a first time period are determined, and the first flow rate time sequence and the second flow rate time sequence are sent to the first equipment; and finally, based on the first flow rate time sequence and the second flow rate time sequence of each port in the plurality of ports, determining a port in a fault state in the first equipment. Wherein the first flow rate time sequence is used for representing the change condition of the actual flow rate of the port in the first time period, and the second flow rate time sequence is used for representing the change condition of the predicted flow rate of the port in the first time period.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a fault location method, device, storage medium and program product. Background Art

[0002] In order to meet the computing power requirements of large artificial intelligence (AI) models, the Intelligent Computing Center continues to expand the scale of high-performance network clusters to provide the required computing power resources for model training and reasoning in different application scenarios.

[0003] However, with the continuous expansion of network clusters and the increasing complexity of the intelligent computing center system, the operation and maintenance management of the intelligent computing center also faces many challenges. Specifically, when multiple network devices work together to process AI large model tasks, when a network device or link fails, the traditional fault location method needs to traverse a large number of network devices and links, which greatly increases the difficulty of the operation and maintenance personnel. At the same time, the diversity and complexity of faults also make fault location more difficult. Therefore, how to quickly locate faults in complex and large-scale intelligent computing center systems to ensure the efficient operation of the intelligent computing center and the stable advancement of AI large model tasks has become a key issue that needs to be solved urgently. Summary of the invention

[0004] The present application provides a fault location method, device, storage medium and program product, which can realize rapid fault location and improve fault location efficiency.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a fault location method, applied to a server, the method comprising:

[0007] Receive alarm information sent by a first device, wherein the first device includes multiple ports, then determine, for each port in the multiple ports, a first traffic rate time series and a second traffic rate time series of the traffic rate of the port within a first time period, and finally determine a port in the first device that is in a faulty state based on the first traffic rate time series and the second traffic rate time series of each port in the multiple ports.

[0008] The first flow rate time series is used to characterize the change of the actual flow rate of the port within the first time period, and the second flow rate time series is used to characterize the change of the predicted flow rate of the port within the first time period.

[0009] Based on the above technical solution, after the server receives the alarm information sent by the first device, for each of the multiple ports of the first device, it can first determine the first traffic rate time series and the second traffic rate time series of the port in the first time period, and then determine whether the port is in a fault state through the first traffic rate time series and the second traffic rate time series of the port, thereby achieving rapid fault location and improving fault location efficiency.

[0010] Optionally, the above-mentioned determining the port in the first device that is in a faulty state based on the first traffic rate time series and the second traffic rate time series of each port in the multiple ports may specifically include: for each port in the multiple ports, if the similarity between the first traffic rate time series and the second traffic rate time series of the port is less than a similarity threshold, determining that the port is in a faulty state.

[0011] Optionally, the first time period includes multiple sub-time periods, on this basis, the first traffic rate time series of the above-mentioned port can be determined in the following manner: determine the traffic rate of the port in each sub-time period, and then determine the first traffic rate time series of the port based on the traffic rate of the port in each sub-time period.

[0012] Optionally, the second traffic rate time series of the above-mentioned port can be determined by the following method: determining the third traffic rate time series of the port's traffic rate in the second time period, and then predicting the second traffic rate time series of the port based on the third traffic rate time series of the port.

[0013] The second time period is a period before the first time period. The third flow rate time series is used to characterize the change of the actual flow rate of the port in the second time period.

[0014] Optionally, the method may further include: if there is no port in a faulty state in the first device, determining a second device that performs the same task as the first device, and then determining the port in the faulty state in the second device.

[0015] Optionally, a similarity determination model can be deployed in the server, and on this basis, the similarity between the first traffic rate time series and the second traffic rate time series of the above-mentioned port can be determined in the following way: input the first traffic rate time series and the second traffic rate time series of the port into the similarity determination model, and obtain the similarity between the first traffic rate time series and the second traffic rate time series output by the model.

[0016] In a second aspect, the present application provides a fault location device, comprising:

[0017] The receiving unit is used to receive the alarm information sent by the first device, wherein the first device includes a plurality of ports.

[0018] The first determining unit is configured to determine, for each port among the plurality of ports, a first flow rate time series and a second flow rate time series of a flow rate of the port within a first time period.

[0019] The first flow rate time series is used to characterize the change of the actual flow rate of the port within the first time period, and the second flow rate time series is used to characterize the change of the predicted flow rate of the port within the first time period.

[0020] The second determining unit is configured to determine a port in a fault state in the first device based on the first traffic rate time series and the second traffic rate time series of each port in the plurality of ports.

[0021] Optionally, the second determination unit is further configured to, for each port among the multiple ports, determine that the port is in a fault state if the similarity between the first flow rate time series and the second flow rate time series of the port is less than a similarity threshold.

[0022] Optionally, the first determining unit is further configured to determine a flow rate of the port in each sub-period.

[0023] Optionally, the first determining unit is further configured to determine a first flow rate time series of the port based on the flow rate of the port in each sub-period.

[0024] Optionally, the first determining unit is further configured to determine a third flow rate time series of the flow rate of the port within the second time period.

[0025] The second time period is a period before the first time period. The third flow rate time series is used to characterize the change of the actual flow rate of the port in the second time period.

[0026] Optionally, the first determination unit is further configured to, if no port in a faulty state exists in the first device, determine a second device that performs the same task as the first device, and determine the port in the faulty state in the second device.

[0027] In a third aspect, the present application provides a fault location device, the device comprising: a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement a fault location method as described in any one of the first aspect and any possible implementation of the first aspect.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal, the terminal executes a fault location method as described in the first aspect and any possible implementation of the first aspect.

[0029] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes a fault location method as described in any one of the first aspect and any possible implementation of the first aspect.

[0030] It can be understood that the beneficial effects that can be achieved by the second to fifth aspects provided above can refer to the beneficial effects of any possible design method of the fault location method described in any one of the first aspect and any possible implementation method of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 An architectural diagram of a fault location system provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a flow chart of a fault location method provided in an embodiment of the present application;

[0033] Figure 3 An interactive flow chart of a fault location method provided in an embodiment of the present application;

[0034] Figure 4 A schematic diagram of a flow chart of determining a flow rate of a port within a first time period provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of the structure of a fault location device provided in an embodiment of the present application;

[0036] Figure 6 A schematic diagram of the structure of another fault locating device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] A fault location method, device, storage medium, and program product provided by an embodiment of the present application are described in detail below in conjunction with the accompanying drawings.

[0038] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0039] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0040] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0041] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0042] In today's digital age, AI technology is leading a new wave of global technological revolution. As the core driving force in this field, AI big models are gradually becoming an important force in promoting digital transformation in all walks of life with their powerful data processing capabilities and broad application prospects.

[0043] As a key infrastructure supporting the operation of large AI models, the Intelligent Computing Center continues to expand its scale and build more and more high-performance network clusters to meet the computing power requirements of large AI models. These network clusters can provide the required computing power resources for model training and reasoning in different application scenarios, ensuring that large AI models can operate efficiently and stably.

[0044] However, with the continuous expansion of network clusters and the increasing complexity of the intelligent computing center system, the operation and maintenance management of the intelligent computing center also faces many challenges. Specifically, when multiple network devices work together to process AI large model tasks, when a network device or link fails, the traditional fault location method needs to traverse a large number of network devices and links, which greatly increases the work cost of operation and maintenance personnel. At the same time, the diversity and complexity of faults also make fault location more difficult. Therefore, how to quickly locate faults in complex and large-scale intelligent computing center systems to ensure the efficient operation of the intelligent computing center and the stable advancement of AI large model tasks has become a key issue that needs to be solved urgently.

[0045] In order to solve the above technical problems, an embodiment of the present application provides a fault location method. After the server receives the alarm information sent by the first device, for each of the multiple ports of the first device, the first traffic rate time series and the second traffic rate time series of the port in the first time period can be determined first, and then the first traffic rate time series and the second traffic rate time series of the port can be used to determine whether the port is in a fault state, thereby achieving rapid fault location and improving fault location efficiency.

[0046] Figure 1 An architecture diagram of a fault location system provided in an embodiment of the present application, such as Figure 1 As shown, the system framework includes: a first device 101 and a server 102.

[0047] The first device 101 may be a server or a gateway device.

[0048] The server may be a high-performance server that provides various services online, an independent physical server, a server cluster consisting of multiple physical servers, or at least one of cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data or artificial intelligence platforms, etc., which are not limited in the embodiments of the present application. Of course, the server can also include other functions to provide more comprehensive and diverse services.

[0049] A gateway device may be a device that connects different networks and provides network communication and data transmission services for different networks. A gateway device may include, but is not limited to, a router, a switch, and a virtual private network (VPN) device.

[0050] The embodiment of the present application does not limit the number of the first devices 101 in the fault location system, and may include: Figure 1 More or less first devices 101.

[0051] Server 102 may be a server of the same type as the above-mentioned server and will not be introduced here.

[0052] In the embodiment of the present application, when the first device 101 fails in executing a task, it can send an alarm message to the server 102. Accordingly, after receiving the alarm message, the server 102 can determine the first flow rate time series and the second flow rate time series of the flow rate of each port in the first time period for each of the multiple ports of the first device 101. Finally, the server 102 can determine the port in the first device 101 that is in a faulty state based on the first flow rate time series and the second flow rate time series of each of the multiple ports of the first device 101.

[0053] Figure 2 A schematic diagram of a fault location method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, this method is Figure 1 The server shown executes the method, comprising:

[0054] S201: Receive alarm information sent by a first device.

[0055] S202: For each port among the plurality of ports, determine a first traffic rate time series and a second traffic rate time series of the port's traffic rate within a first time period.

[0056] The first device includes a plurality of ports.

[0057] The first traffic rate time series is used to characterize the change of the actual traffic rate of the port within the first time period, and the second traffic rate time series is used to characterize the change of the predicted traffic rate of the port within the first time period.

[0058] The embodiment of the present application does not limit the duration of the first time period. For example, the duration of the first time period may be 1 minute, 1 hour, 1 day, or 1 week.

[0059] Specifically, after the first device fails to perform a task, it can send an alarm message to the server. Accordingly, after receiving the alarm message, the server can determine the first flow rate time series and the second flow rate time series of each port in the first time period for each of the multiple ports of the first device.

[0060] For example, assuming that the first device sends the alarm information at 9:10 and the first time period is 10 minutes, after receiving the alarm information, the server can determine the first flow rate time series and the second flow rate time series of each port in the first device between 9:00 and 9:10.

[0061] S203: Determine a port in a fault state in the first device based on the first traffic rate time series and the second traffic rate time series of each port in the plurality of ports.

[0062] Specifically, for each of the multiple ports of the first device, the server can determine the similarity between the first traffic rate time series and the second traffic rate time series of the port. If the similarity between the first traffic rate time series and the second traffic rate time series is less than a similarity threshold, it can be determined that the port is in a faulty state.

[0063] The embodiment of the present application does not limit the value of the similarity threshold. For example, the similarity threshold may be 0.6, 0.7 or 0.8.

[0064] In some embodiments, a similarity determination model is deployed in the server, on the basis of which the server determines the similarity between the first flow rate time series and the second flow rate time series of the port, which may specifically include: for each of the multiple ports, after the server determines the first flow rate time series and the second flow rate time series of the port, the first flow rate time series and the second flow rate time series can be input into the similarity determination model to obtain the similarity between the first flow rate time series and the second flow rate time series output by the model.

[0065] The embodiment of the present application does not limit the type of similarity determination model. For example, the similarity determination model may be a dynamic time warping (DTW) model or a Euclidean distance model.

[0066] Based on the above technical solution, the server can determine the port in the first device that is in a faulty state by judging whether the similarity between the first traffic rate time series and the second traffic rate time series of each port in the first device is less than the similarity threshold, thereby achieving rapid fault location, thereby ensuring the stable advancement of large model tasks and improving the operating efficiency of the intelligent computing center.

[0067] In some embodiments, if there is no port in the first device that is in a faulty state, the server may determine a second device that performs the same task as the first device, and then determine the port in the second device that is in a faulty state.

[0068] Specifically, a plurality of tasks and the execution devices corresponding to each task are stored in the server. Accordingly, if there is no port in a faulty state in the first device, the server can determine the second device that performs the same task as the first device from the execution devices corresponding to each task according to the task performed by the first device. Afterwards, the server can refer to the above-mentioned determination method in S202-S203, first determine the first flow rate time series and the second flow rate time series of each port in the plurality of ports of the second device, and then determine the port in the second device that is in a faulty state based on the first flow rate time series and the second flow rate time series of each port in the plurality of ports.

[0069] The embodiment of the present application does not limit the task information of each task stored in the server. For example, the task may be an AI large model task. The task information of the AI ​​large model task may include information such as the task identifier, the task parameter amount (such as 7 billion), or the task segmentation method (such as data parallelism (DP) method, pipeline parallelism (PIPELINEPARALLELISM) method, or sequence parallelism (SP) method, etc.).

[0070] In some embodiments, the first time period includes multiple sub-time periods, on this basis, the first traffic rate time series of the above-mentioned port can be determined in the following manner: determine the traffic rate of the port in each sub-time period, and then determine the first traffic rate time series of the port based on the traffic rate of the port in each sub-time period.

[0071] Specifically, after receiving the alarm information sent by the first device, the server can send a port rate acquisition request to the first device, and the rate acquisition request includes an acquisition time (such as a first time period). Accordingly, after receiving the port rate acquisition request, the first device can calculate the flow rate of the port in each sub-time period in the first time period for each of the multiple ports, and send the flow rate of the port in each sub-time period to the server. For each of the multiple ports, after receiving the flow rate of the port in each sub-time period, the server can determine the first flow rate time series of the port.

[0072] Exemplarily, assume that the first time period is from 9:00 to 9:02, the duration of each sub-time period is 1 minute, and the first device includes port number 1. On this basis, after the first device receives the port rate acquisition request, it can calculate the flow rate d1 of port number 1 in the first sub-time period (9:00 to 9:01), and the flow rate d2 of the port in the second sub-time period (9:00 to 9:02), and send the flow rate d1 and the flow rate d2 to the server. Accordingly, after the server receives the flow rate d1 and the flow rate d2, it can determine that the first flow rate time series of port number 1 is [d1, d2].

[0073] In the above manner, the server can determine a first traffic rate time series of the port's traffic rate within a first time period, which can provide a basis for determining a port that is in a fault state.

[0074] In some embodiments, the second traffic rate time series of the above-mentioned port can be determined by: determining the third traffic rate time series of the port's traffic rate within the second time period, and then predicting the second traffic rate time series of the port based on the third traffic rate time series of the port.

[0075] The second time period is the period before the first time period. For example, assuming that the first time period is from 9:00 to 9:30, the second time period is from 8:30 to 9:00.

[0076] The third traffic rate time series is used to characterize changes in the actual traffic rate of the port within the second time period.

[0077] Specifically, a rate prediction model is deployed in the server. Accordingly, after receiving the alarm information sent by the first device, the server can determine the third flow rate time series of the port's flow rate in the second time period by referring to the above-mentioned method of determining the first flow rate time series of the port by the server. Afterwards, the server can input the third flow rate time series of the port into the rate prediction model to obtain the second flow rate time series of the port output by the rate prediction model.

[0078] Through the above method, for each port, the server can train the rate prediction model corresponding to the port, and predict the second flow rate time series of the port in the first time period through the rate prediction model and the third flow rate time series of the port in the second time period, so as to provide a basis for locating the faulty port and improve the accuracy of fault location. At the same time, by predicting the future flow rate through the historical flow rate, it can also provide support for flow simulation and global load balancing.

[0079] In some embodiments, the above-mentioned rate prediction model can be trained in the following manner: obtain the historical traffic rate time series of the port's traffic rate in multiple historical time periods, and use the multiple historical traffic rate time series of the port as training data, and then use the training data to train the original prediction model to obtain the rate prediction model.

[0080] The embodiment of the present application does not limit the type of the original prediction model. For example, the original prediction model may include but is not limited to: a Transformer model, a long-short term memory (LSTM) model, an autoregressive model, a Prophet model, or a deep state-space (Deep State) model.

[0081] The embodiment of the present application does not limit the amount of training data. For example, when the number of iterations of the rate prediction model is N, the training data M = N*10%.

[0082] Specifically, take the original prediction model as the model Transformer model as an example. The server can refer to the above method of obtaining the first traffic rate time series of the port to obtain multiple historical traffic rate time series of the port and use them as training data. Then, the server can input the training data into the Transformer model, train the Transformer model, and obtain the trained Transformer model. Afterwards, the server can use the online learning method to optimize the trained Transformer model to obtain the final rate prediction model.

[0083] In the embodiment of the present application, multiple rate prediction models may be deployed in the server, and each port corresponds to a different rate prediction model. For example, port No. 1 corresponds to rate prediction model A. When the server predicts the second flow rate time series of port No. 1, the third flow rate time series of port No. 1 may be input into rate prediction model A to obtain the second flow rate time series output by the model.

[0084] In some embodiments, the server is connected to a plurality of devices, and the plurality of devices include a first device and a second device. On this basis, for each port in each device, the server can also determine the similarity between the first flow rate time series and the second flow rate time series of the port within a preset period according to a preset period, and perform fault detection on the port when the similarity between the first flow rate time series and the second flow rate time series is less than a similarity threshold.

[0085] In an embodiment of the present application, the server stores port information of each port. The port information may include, but is not limited to: the port number, the device number to which the port belongs, and the port position. For example, assuming that the first device is a server, the device number to which port number one of the first device belongs may be the server number (such as server-1), and the port number may be the server network card number (such as server-1-network card number). For another example, assuming that the first device is a switch, the device described in port number one of the first device may be the switch number (such as the spine layer switch number, the leaf layer switch number), and the port number may be the port number of the switch.

[0086] Based on the above, assuming that the similarity between the first flow rate time series and the second flow rate time series of the port is less than the similarity threshold, the server can determine the location of the port based on the port information of the port. Afterwards, the server can perform fault detection on the port based on the location of the port.

[0087] Through the above method, the server can periodically inspect each port of each device, and perform fault detection on the port in advance when the similarity between the first traffic rate time series and the second traffic rate time series of the port is less than the similarity threshold, thereby ensuring the stable operation of the large model task.

[0088] The following will combine the above-mentioned various implementation modes to introduce the fault location method provided by the present application in detail. Figure 3 An interactive flow chart of a fault location method provided in an embodiment of the present application, such as Figure 3 As shown, the method includes:

[0089] S301, the first device sends an alarm message to the server.

[0090] S302: The server sends a port traffic rate acquisition request to the first device.

[0091] The port traffic rate acquisition request includes the acquisition time (ie, the first time period and the second time period).

[0092] S303: The first device determines the traffic rate of the port in each sub-time period in the first time period and the traffic rate of the port in each sub-time period in the second time period based on the port traffic rate acquisition request.

[0093] Specifically, each port of the first device corresponds to multiple work queues (queue pairs, QPs), and each QP can transmit multiple data packets simultaneously. Figure 4 As shown, determining the flow rate of the port in the first time period may specifically include:

[0094] Step 1: For each QP, the first device obtains the rate at which each data packet is transmitted by the QP in each sub-time period.

[0095] Specifically, the first device may obtain the rate at which each QP transmits each data packet in each sub-time period through an NVIDIA collective communications library (NCCL) tool.

[0096] Step 2: The first device uses the average value of the rate of each data packet in each sub-time period as the flow rate of QP.

[0097] Step 3: For each sub-time period, the first device uses the average value of the flow rate of each QP corresponding to the port in the sub-time period as the flow rate of the port in the sub-time period.

[0098] The first device may determine the flow rate of each port in each sub-time period in the second time period by referring to the above method.

[0099] S304: The first device sends to the server the flow rate of the port in the first time period and in each sub-time period in the second time period.

[0100] S305: The server determines a first traffic rate time series of the port based on the traffic rate of the port in each sub-period in the first time period.

[0101] S306: The server determines a third traffic rate time series of the port based on the traffic rate of the port in each sub-period in the second time period.

[0102] S307: The server inputs the third flow rate time series of the port into the rate prediction model to obtain the second flow rate time series of the port predicted by the model.

[0103] S308: The server determines the similarity between the first flow rate time series and the second flow rate time series of the port, and determines that the port is in a fault state when the similarity is less than a similarity threshold.

[0104] Figure 5 A schematic diagram of a fault location device provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the device comprises:

[0105] The receiving unit 501 is configured to receive alarm information sent by a first device.

[0106] The first determining unit 502 is configured to determine, for each port among the plurality of ports, a first traffic rate time series and a second traffic rate time series of the port's traffic rate within a first time period.

[0107] The first flow rate time series is used to characterize the change of the actual flow rate of the port within the first time period, and the second flow rate time series is used to characterize the change of the predicted flow rate of the port within the first time period.

[0108] The second determining unit 503 is configured to determine a port in a fault state in the first device based on the first traffic rate time series and the second traffic rate time series of each port in the plurality of ports.

[0109] Optionally, the second determining unit 503 is further configured to, for each port among the multiple ports, determine that the port is in a fault state if the similarity between the first flow rate time series and the second flow rate time series of the port is less than a similarity threshold.

[0110] Optionally, the first determining unit 502 is further configured to determine a flow rate of the port in each sub-period.

[0111] Optionally, the first determining unit 502 is further configured to determine a first traffic rate time series of the port based on the traffic rate of the port in each sub-period.

[0112] Optionally, the first determining unit 502 is further configured to determine a third traffic rate time series of the traffic rate of the port within the second time period.

[0113] The second time period is a period before the first time period. The third flow rate time series is used to characterize the change of the actual flow rate of the port in the second time period.

[0114] Optionally, the first determining unit 502 is further configured to, if no port in the first device is in a faulty state, determine a second device that performs the same task as the first device, and determine the port in the second device that is in a faulty state.

[0115] Figure 6 Another possible structural diagram of the fault location device involved in the above embodiment is shown. The fault location device includes: a processor 601 and a communication interface 602. The processor 601 is used to control and manage the actions of the fault location device, and the communication interface 602 is used to support the communication between the fault location device and other network entities. The fault location device may also include a memory 603 and a bus 604, and the memory 603 is used to store program codes and data of the fault location device.

[0116] Among them, the memory 603 can be a memory in a fault location device, etc. The memory can include a volatile memory, such as a random access memory; the memory can also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory can also include a combination of the above types of memory.

[0117] The processor 601 may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The processor may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0118] The bus 604 may be an extended industry standard architecture (EISA) bus, etc. The bus 604 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0119] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, 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 is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0120] An embodiment of the present application provides a computer program product including instructions. When the computer program product is run on a computer, the computer is enabled to execute the fault location method in the above method embodiment.

[0121] The embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the fault location method in the method flow shown in the above method embodiment.

[0122] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0123] An embodiment of the present invention provides a computer program product including instructions. When the instructions are executed on a computer, the computer executes the fault location method described in the embodiment of the present application.

[0124] Since the fault location device, computer-readable storage medium, and computer program product in the embodiments of the present invention can be applied to the above method, the technical effects that can be obtained can also refer to the above method embodiments, and the embodiments of the present invention will not be repeated here.

[0125] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A fault location method, characterized in that: Applied to a server, the method comprises: Receiving alarm information sent by a first device; the first device includes multiple ports; For each port of the plurality of ports, determining a first flow rate time series and a second flow rate time series of a flow rate of the port within a first time period; The first flow rate time series is used to characterize the actual change of the flow rate of the port within the first time period; the second flow rate time series is used to characterize the predicted change of the flow rate of the port within the first time period; A port in the first device that is in a fault state is determined based on the first traffic rate time series and the second traffic rate time series of each port in the plurality of ports.

2. The method according to claim 1, characterized in that: The determining, based on the first traffic rate time series and the second traffic rate time series of each port of the plurality of ports, a port in a fault state in the first device comprises: For each port of the plurality of ports, if the similarity between the first traffic rate time series and the second traffic rate time series of the port is less than a similarity threshold, it is determined that the port is in a fault state.

3. The method according to claim 1 or 2, characterized in that: The first time period includes a plurality of sub-time periods; The first flow rate time series of the port is determined by: Determine the flow rate of the port in each of the sub-time periods; The first traffic rate time series of the port is determined based on the traffic rate of the port in each of the sub-time periods.

4. The method according to claim 1 or 2, characterized in that: The second flow rate time series of the port is determined by: determining a third flow rate time series of the flow rate of the port within a second time period; The second time period is the period before the first time period; the third flow rate time series is used to characterize the change of the actual flow rate of the port in the second time period; Based on the third traffic rate time series of the port, the second traffic rate time series of the port is predicted to provide support for global load balancing.

5. The method according to claim 1, characterized in that The method further comprises: If there is no port in a faulty state in the first device, determining a second device that performs the same task as the first device; Determine a port in the second device that is in a faulty state.

6. The method according to claim 2, characterized in that The server is deployed with a similarity determination model, and the method further includes: The first flow rate time series and the second flow rate time series of the port are input into the similarity determination model to obtain the similarity between the first flow rate time series and the second flow rate time series output by the model.

7. A fault location device, characterized in that: The device comprises: A receiving unit, configured to receive alarm information sent by a first device; the first device includes a plurality of ports; A first determining unit, configured to determine, for each port of the plurality of ports, a first flow rate time series and a second flow rate time series of a flow rate of the port within a first time period; The first flow rate time series is used to characterize the actual change of the flow rate of the port within the first time period; the second flow rate time series is used to characterize the predicted change of the flow rate of the port within the first time period; The second determining unit is configured to determine a port in the first device that is in a fault state based on the first traffic rate time series and the second traffic rate time series of each port in the plurality of ports.

8. A fault location device, characterized in that: include: A processor and a communication interface; the communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement the fault location method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions. When a computer executes the instructions, the computer executes the fault location method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed on a computer, the computer is enabled to execute the fault location method according to any one of claims 1 to 6.

Images