Computing device performance analysis method and computing device

Abstract

The application provides a computing device performance analysis method and a computing device. In an embodiment, the method comprises: obtaining a performance feature to be analyzed of the computing device and an operating environment of the computing device; searching for a feature collection tool based on the performance feature to be analyzed and the operating environment by using a first AI tool, the first AI tool being used to search for a feature collection tool suitable for the operating environment; running the searched feature collection tool based on a search result returned by the first AI tool, and collecting feature data of the performance feature to be analyzed by using the feature collection tool; and determining a performance analysis result of the computing device based on the feature data. According to different performance features and operating environments of the computing device, the feature collection tool can be flexibly selected, and the convenience of feature collection is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of servers, and particularly relates to a computing device performance analysis method and a computing device. BACKGROUND

[0002] Performance optimization is an indispensable part of a high-performance computing (HPC) system, and performance optimization helps to improve task completion time, saves power, space and other resources consumed by system operation, improves system reliability and security, and maximizes the use of existing hardware resources.

[0003] For an HPC system, feature analysis is a necessary step for performance optimization; therefore, in the HPC system, it is crucial to collect feature analysis data and analyze HPC system bottlenecks for performance optimization.

[0004] The performance analysis process of the current HPC system is relatively complex, and therefore, a more convenient performance analysis method is urgently needed. SUMMARY

[0005] Embodiments of the present application provide a computing device performance analysis method and a computing device, according to performance characteristics and a running environment of the computing device, an AI tool can be used to flexibly search for a feature collection tool that is suitable for the running environment and the performance characteristics, improve the convenience and accuracy of selection of the feature collection tool, and subsequently perform performance analysis based on feature data collected by the feature collection tool; the AI tool can be used to flexibly select various feature collection tools to collect feature data for various performance characteristics, thereby improving the convenience of performance analysis.

[0006] In a first aspect, embodiments of the present application provide a computing device performance analysis method, the method comprising:

[0007] obtaining performance characteristics to be analyzed of a computing device and a running environment of the computing device; based on the performance characteristics to be analyzed and the running environment, searching for a feature collection tool by a first AI tool; wherein the AI tool is used to search for a feature collection tool suitable for the running environment; based on a search result returned by the first AI tool, running the searched feature collection tool, and collecting feature data of the performance characteristics to be analyzed by using the feature collection tool; and based on the feature data, determining a performance analysis result of the computing device.

[0008] In the scheme, according to the performance characteristics and the running environment of the computing device, the AI tool can flexibly search for a feature collection tool that is suitable for the running environment and the performance characteristics, improve the convenience and accuracy of the selection of the feature collection tool, and perform performance analysis based on the feature data collected by the feature collection tool subsequently; the AI tool can flexibly select various feature collection tools to collect feature data for various performance characteristics, thereby improving the convenience of performance analysis.

[0009] In a possible implementation, the performance characteristics of the computing device to be analyzed are acquired, including: acquiring, based on a human-computer interaction interface, performance characteristics of the computing device to be analyzed set by a user.

[0010] In the scheme, the user only needs to input the performance characteristics related to the performance of the computing device, without needing to care about the feature collection tool, thereby reducing the participation of the user in performance analysis and improving user experience. It should be noted that the user can input various performance characteristics related to the performance of the computing device according to actual needs.

[0011] In a possible implementation, the first AI tool is used to search for the feature collection tool based on the performance characteristics to be analyzed and the running environment, including: sending a search request to the first AI tool; the search request includes the performance characteristics and the running environment, and the search request is used to request to search for the feature collection tool for the performance characteristics in the running environment;

[0012] Based on the search result returned by the first AI tool, the searched feature collection tool is run, including: in the case that the search result of the first AI tool responding to the search request is accurate, the feature collection tool indicated by the search result is run on the computing device.

[0013] In a possible implementation, the method further includes: in the case that the search result is incorrect, sending the search request to a second AI tool.

[0014] In a possible implementation, the success times of the first AI tool are higher than those of the second AI tool, and / or the search time of the first AI tool is lower than that of the second AI tool, the success times are used to indicate the number of times of accurate search results for different search requests, and the search time is used to indicate the time consumed for responding to different search requests, the performance characteristics and / or the running environment in the different search requests are different.

[0015] In the scheme, the AI tool with accurate search and / or fast search is considered first, thereby improving the efficiency of searching for the feature collection tool.

[0016] In a possible implementation, the search result includes a download link of the feature collection tool, a compilation method of the feature collection tool, an installation method of the feature collection tool, and a running method of the feature collection tool.

[0017] Based on the search result returned by the first AI tool, the searched feature collection tool is run, including:

[0018] Based on the download link, the feature collection tool is downloaded; based on the compiling method, the feature collection tool is compiled into an executable file; based on the installation method, the executable file is installed in the running environment; and based on the running method, the executable file is run in the running environment.

[0019] In a possible implementation, before the feature data of the performance feature to be analyzed is collected by the feature collection tool, the method further includes: obtaining a running method of the business software; and based on the running method, the business software is run.

[0020] In a possible implementation, the running environment of the computing device includes an architecture of a central processing unit and a version of an operating system.

[0021] In a possible implementation, the computing device performance analysis method is executed by the computing device.

[0022] The first AI tool searches for the feature collection tool by executing other devices other than the computing device.

[0023] In a second aspect, the embodiments of the present application provide a computing device performance analysis apparatus. The computing device performance analysis apparatus includes a plurality of modules, and each module is configured to perform each step of the computing device performance analysis method provided in the first aspect of the embodiments of the present application. The division of the modules is not limited herein. For the specific functions performed by each module of the computing device performance analysis apparatus and the beneficial effects achieved, reference can be made to the functions of each step of the computing device performance analysis method provided in the first aspect of the embodiments of the present application, which will not be described herein again.

[0024] For example, the computing device performance analysis apparatus includes:

[0025] The obtaining module is configured to obtain the performance feature to be analyzed of the computing device and the running environment of the computing device.

[0026] The searching module is configured to search for the feature collection tool by using the first AI tool based on the performance feature to be analyzed and the running environment. The AI tool is configured to search for the feature collection tool suitable for the running environment.

[0027] The collecting module is configured to run the searched feature collection tool based on the search result returned by the first AI tool, and collect the feature data of the performance feature to be analyzed by using the feature collection tool.

[0028] The analyzing module is configured to determine the performance analysis result of the computing device based on the feature data.

[0029] In a possible implementation, the acquisition module is configured to acquire, based on the human-computer interaction interface, a performance feature to be analyzed of the computing device set by the user.

[0030] In a possible implementation, the search module is configured to send a search request to the first AI tool, the search request comprising the performance feature and the running environment, and the search request being used to request description information of the feature collection tool for the performance feature in the running environment.

[0031] The collection module is configured to run, on the computing device, the feature collection tool indicated by the search result of the first AI tool in a case where the search result of the first AI tool is accurate.

[0032] In a possible implementation, the search module is configured to send the search request to the second AI tool in a case where the search result is incorrect.

[0033] In a possible implementation, the success number of the first AI tool is higher than that of the second AI tool, and / or the search time of the first AI tool is lower than that of the second AI tool, the success number being used to indicate the number of times of accurate search results for different search requests, and the search time being used to indicate the time consumed for responding to different search requests, the performance feature and / or the running environment in the different search requests being different.

[0034] In a possible implementation, the search result comprises a download link of the feature collection tool, a compilation method of the feature collection tool, an installation method of the feature collection tool, and a running method of the feature collection tool.

[0035] The collection module is configured to download the feature collection tool based on the download link, compile the feature collection tool into an executable file based on the compilation method, install the executable file in the running environment based on the installation method, and run the executable file in the running environment based on the running method.

[0036] In a possible implementation, before the feature data of the performance feature to be analyzed is collected by using the feature collection tool, the collection module is further configured to acquire a running method of the business software, and run the business software based on the running method.

[0037] In a possible implementation, the running environment of the computing device comprises an architecture of a central processing unit and a version of an operating system.

[0038] In a possible implementation, the computing device performance analysis method is executed by the computing device.

[0039] The first AI tool searches for the feature collection tool by using another device other than the computing device.

[0040] In a third aspect, the embodiments of the present application provide a computing device performance analysis apparatus, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory, and when the programs stored in the memory are executed, the processor is configured to execute the method provided in the first aspect.

[0041] In a fourth aspect, the embodiments of the present application provide a computing device performance analysis apparatus, wherein the apparatus runs computer program instructions to execute the method provided in the first aspect. For example, the apparatus can be a chip or a processor.

[0042] In one example, the apparatus can include a processor which can be coupled with a memory, read instructions in the memory and execute the method provided in the first aspect according to the instructions. The memory can be integrated in the chip or the processor, or can be independent of the chip or the processor.

[0043] In a fifth aspect, the embodiments of the present application provide a computer storage medium, and the computer storage medium stores instructions, when the instructions are run on a computer, the computer executes the method provided in the first aspect.

[0044] In a sixth aspect, the embodiments of the present application provide a computer program product containing instructions, when the instructions are run on a computer, the computer executes the method provided in the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 FIG. 1 is a system architecture diagram of a feature collection system provided by the embodiments of the present application;

[0046] Figure 2 FIG. 2 is another system architecture diagram of a feature collection system provided by the embodiments of the present application;

[0047] Figure 3 FIG. 3 is a flow diagram of a computing device performance analysis method provided by the embodiments of the present application;

[0048] Figure 4 FIG. 4 is a schematic diagram of a first AI tool search provided by the embodiments of the present application;

[0049] Figure 5 FIG. 5 is a schematic diagram of n AI tool sequential search provided by the embodiments of the present application;

[0050] Figure 6a FIG. 6 is a schematic diagram of search result accuracy of a first AI tool provided by the embodiments of the present application;

[0051] Figure 6b FIG. 7 is another schematic diagram of search result accuracy of a first AI tool provided by the embodiments of the present application;

[0052] Figure 7 is a schematic diagram of starting a second AI tool search provided by an embodiment of the present application;

[0053] Figure 8a is a schematic diagram of starting a second AI tool search provided by an embodiment of the present application;

[0054] Figure 8b is a schematic diagram of another starting a second AI tool search provided by an embodiment of the present application;

[0055] Figure 9 is a schematic diagram of n AI tools parallel search provided by an embodiment of the present application;

[0056] Figure 10a is a schematic diagram of determining a performance analysis result of the computing device 102 provided by an embodiment of the present application;

[0057] Figure 10b is a schematic diagram of determining a performance adjustment suggestion of the computing device 102 provided by an embodiment of the present application;

[0058] Figure 10c is a schematic diagram of determining a performance analysis result and a performance adjustment suggestion of the computing device 102 provided by an embodiment of the present application;

[0059] Figure 10d is a schematic diagram of generating a document provided by an embodiment of the present application;

[0060] Figure 11 is a schematic diagram of the first AI tool running in the management device 103 provided by an embodiment of the present application;

[0061] Figure 12 is a schematic diagram of a software module in a feature acquisition system provided by an embodiment of the present application;

[0062] Figure 13 is a schematic diagram of the AI search module and the AI analysis module located in the management device 103 provided by an embodiment of the present application;

[0063] Figure 14 is a schematic diagram of another computing device performance analysis method provided by an embodiment of the present application;

[0064] Figure 15 is a structural schematic diagram of a computing device performance analysis apparatus provided by an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below with reference to the drawings.

[0066] In the description of the embodiments of the present application, the words "exemplary", "for example", or "e.g." are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary", "for example", or "e.g." should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the exemplary or illustrative embodiments are presented as examples to provide a clear and thorough understanding of the present application. The elements, acts, or devices illustrated in the figures, which have the same function in all or some embodiments, are not necessarily labeled in all figures.

[0067] In the description of the embodiments of the present application, the term "and / or", merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B, which can represent three cases of A alone, B alone, and A and B together. In addition, unless otherwise specified, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple terminals refer to two or more terminals.

[0068] In addition, the terms "first", "second", etc. are used only for descriptive purposes and should not be construed as indicating or implying relative importance or implying the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more features. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0069] In the following, some terms in the embodiments are explained. It should be noted that these explanations are for the convenience of those skilled in the art to understand, and do not constitute a limitation on the scope of protection required by the present application.

[0070] High-performance computing (HPC): A computer cluster specially designed for high-performance computing scenarios such as scientific computing and engineering simulation. It consists of a highly parallel computing platform with a large number of high-performance processors, high-speed networks, and high-capacity storage. It provides massive data processing capabilities, ultra-high computing performance, and ultra-long running capabilities to solve complex problems that cannot be solved by traditional single machines.

[0071] Artificial Intelligence (AI): An important driving force for the new round of technological revolution and industrial transformation. It is a new technical science that studies, develops, and applies systems for simulating, extending, and expanding human intelligence.

[0072] x86: Refers to a series of central processor instruction set architectures based on Intel 8086 and backward compatible.

[0073] ARM architecture: Once known as Advanced RISC Machine, and earlier as Acorn RISC Machine, is a 32-bit RISC processor architecture.

[0074] Regular expression: Also known as regular expression, (Regular Expression, commonly abbreviated as regex, regexp or RE in code), it is a text pattern, but also a concept of computer science, which includes ordinary characters (such as letters between a and z) and special characters (called "metacharacters"). Regular expressions use a single string to describe, match a series of strings that match a certain syntax rule, and are usually used to retrieve, replace those texts that meet a certain pattern (rule).

[0075] Next, the feature collection system to which the computing device performance analysis method provided by the embodiment of the application can be applied is introduced. Figure 1 An architecture example diagram of a feature collection system provided by an embodiment of the application is shown. The computing device performance analysis method provided by the embodiment of the application can be applied to the system architecture diagram shown in Figure 1 As shown in Figure 1 The feature collection system includes a terminal 101 and a computing device 102. The terminal 101 communicates with the computing device 102 through a network. The network can be a wired network and / or a wireless network. It can be understood that the network can use any known network communication protocol to realize different communication, and the above network communication protocol can be various wired and / or wireless communication protocols.

[0076] The terminal 101 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The exemplary embodiments of the terminal 101 involved in the present solution include, but are not limited to, electronic devices running iOS, android, Windows, Harmony OS or other operating systems. The type of electronic device is not limited in the embodiment of the application.

[0077] The computing device 102 can be used to provide services such as HPC services and cloud services, which can be a server or a super terminal that can establish a communication connection with other devices and provide computing and / or storage functions for other devices. In addition, the computing device 102 can also be a server cluster formed by multiple servers. The server involved in the present solution can be a hardware server, or can be implanted in a virtualization environment, for example, the server involved in the present solution can be a virtual machine executed on a hardware server including one or more other virtual machines.

[0078] The computing device 102 can be a single-node server, such as a rack server, or one computing node in a multi-node server, which can be a blade server, a high-density server, or a rack-mounted server (a stand-alone product formed by fusing the original rack and machine, such as a server node, into an architecture).

[0079] As shown in the example, Figure 1 The computing device 102 can include a power supply 121 and a mainboard 110, the power supply 121 being electrically connected to the mainboard 110 to supply power to devices connected to the mainboard 110.

[0080] In some possible embodiments, the devices connected to the mainboard 110 can include a processor 111, a memory 112, and a network card 122.

[0081] The processor 111 can be a central processing unit (CPU), and can also be another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or another programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. The general-purpose processor can be a microprocessor or any conventional processor, or the like. The processor 111 can also be a controller with computing capability.

[0082] The memory 112 can be inserted into a memory slot to be connected to the mainboard 110. The memory 112 can be a random access memory (RAM). By way of example but not limitation, many forms of RAM are available. The memory 112 can include at least two types of memory, such as a random access memory (RAM) and a read only memory (ROM). For example, the RAM can include a dynamic random access memory (DRAM), a storage class memory (SCM), or the like.

[0083] The network card 122 is configured to communicate with other devices, such as the terminal 101 or the management device 102 shown in Figure 2

[0084] It should be noted that,​Figure 1 Just as an example of the computing device 102, without specific limitation, more or less devices can be included in actual applications. For example, the feature collection system only includes the computing device 102. Figure 1

[0085] In some possible cases, as shown in FIG. 1, the feature collection system can further include a management device 103, which is configured to manage the computing device 102, such as providing one or more AI tools to the computing device 102, and the like. The details of the AI tools are described below, and will not be described herein again. The structure of the management device 103 can refer to the description of the computing device 102 above, and will not be described herein again. Figure 2

[0086] Next, in combination with the feature collection system provided above, a computing device performance analysis method provided by an embodiment of the present application is described in detail.

[0087] Figure 3 FIG. 1 is a flow diagram of a computing device performance analysis method provided by an embodiment of the present application. The embodiment can be applied to the feature collection system. As shown in FIG. 1, the computing device performance analysis method provided by the embodiment of the present application at least includes the following steps: Figure 3

[0088] Step 301: The computing device 102 acquires performance features to be analyzed of the computing device 102.

[0089] The performance features are used to describe the features related to the performance of the computing device 102 that need to be analyzed. For example, disk I / O (Input / Output), memory or processor related features. Disk I / O refers to the data reading and writing operations involving the disk in the computer system. Disk I / O is an important way for data exchange between the computer and the storage device. When the computer needs to read data from the disk, it initiates a read request, and the disk finds and transmits the data to the memory of the computer; when the computer needs to write data to the disk, it initiates a write request, and the data is written from the memory to the disk. In the embodiment of the present application, the performance features can describe several features, such as one feature or multiple features.

[0090] For example, for disk I / O, the features described by the performance features can include one or more of the following: input / output per second (IOPS), data throughput, type of IO request (such as read / write request), size of request, pattern of request (continuous or random), physical characteristics of the disk (such as rotation speed, cache size, etc.).

[0091] ​​​For example, for memory, the features of the performance feature description can include one or more of the following: memory capacity, memory transfer speed (in units of megabytes per second (MB / s) or gigabytes per second (GB / s)), memory latency (refers to the time required to obtain a response from the processor to request data), memory bandwidth (refers to the maximum amount of data that the memory can transfer), memory channel (refers to the number of connections between the memory module and the processor), memory frequency (represents the highest working frequency that the memory can reach, in units of MHz), and timing of the memory (refers to the timing characteristics of the memory interface signals, including Tras, Trp, Trcd, and other indicators, which are all indicators of the delay time of the memory interface transmission signals. The smaller the timing, the better the performance of the memory).

[0092] For example, for CPU, the features of the performance feature description can include one or more of the following: frequency (the number of instructions executed by the CPU per second, in units of hertz. The higher the frequency, the faster the CPU executes instructions), number of CPU cores (CPU core is the main computing unit of the processor, multi-core CPU can execute multiple tasks at the same time, improving processing power), CPU cache size (CPU cache is a high-speed memory located inside the CPU, used to temporarily store data and instructions), instruction set (instruction set is the set of instructions supported by the CPU, different instruction sets can provide different instructions and functions, affecting the function and performance of the CPU), floating point operation performance (refers to the ability of the CPU to perform floating point number operations), instructions per cycle (IPC, represents the number of instructions that the CPU can complete per clock cycle).

[0093] There can be various ways for the computing device 102 to obtain the performance features to be analyzed of the computing device 102.

[0094] In some possible implementations, the computing device 102 can provide an interface such as an application programming interface (API), and the user can operate the terminal 101 to access the interface to input the performance features to be analyzed of the computing device 102. Subsequently, the terminal 101 sends the performance features input by the user to the computing device 102.

[0095] In other possible implementations, the computing device 102 can provide a human-computer interaction interface, and the user can operate the terminal 101 to display the human-computer interaction interface to input the performance features to be analyzed of the computing device 102. Subsequently, the terminal 101 sends the performance features input by the user to the computing device 102.

[0096] In some possible implementation manners, the management device 103 can provide a human-computer interaction interface or an interface, and the user can operate the terminal 101 to access the interface or display the human-computer interaction interface to input the performance feature to be analyzed for the computing device 102. For example, it is assumed that the management device 103 manages a plurality of computing devices 102, and the user can input the model of the computing device 102 and the performance feature to be analyzed corresponding to the model. Subsequently, the management device 103 can send the performance feature to be analyzed to each computing device 102 of the model.

[0097] In step 302, the computing device 102 acquires the running environment of the computing device 102.

[0098] In the embodiment of the present application, the running environment of the computing device 102 is used to illustrate the hardware environment and the software environment of the computing device 102. For example, the running environment of the computing device 102 can include the processor architecture of the CPU and the operating system version. The processor architecture can be x86 or ARM, and the operating system version is used to illustrate the type and version number of the operating system, for example, the version of windows, and for example, the version of linux.

[0099] It should be noted that the execution sequence of step 301 and step 302 is not limited, and step 302 can be executed before, after or at the same time as step 301.

[0100] In step 303, the computing device 102 searches for the feature collection tool based on the performance feature and the running environment by using the first AI tool. The AI tool is used to search for the feature collection tool suitable for the running environment.

[0101] In some possible embodiments, as shown in FIG. 3, the computing device 102 determines a search request based on the performance feature and the running environment. The search request includes the performance feature and the running environment, and the search request is used to request the description information of the feature collection tool for the performance feature in the running environment. The computing device 102 sends the search request to the first AI tool. The first AI tool searches for the description information of the feature collection tool in response to the search request and returns a search result. Figure 4

[0102] ​The AI tool refers to various software and applications developed using artificial intelligence technology, which can simulate and learn human behavior and thinking, and use this information to achieve task automation or improve existing business processes. In the embodiments of the application, the first AI tool is a tool with search function, which is used for searching according to user requirements. For example, the first AI tool can be chatgpt or Baidu Wenxin, which has a search function. The first AI tool can use an open source tool or can be customized and developed. The specific design can be combined with the actual demand. It should be noted that the first AI tool can search for feature collection tools in the following way: based on the performance characteristics, running environment and description information of the feature collection tool in the search request, the server is requested to search for the feature collection tool, and the search result returned by the server is received; for example, the first AI tool is Baidu Wenxin, and the first AI tool can request the server of Baidu Wenxin to search for the feature collection tool based on the performance characteristics, running environment and description information of the feature collection tool in the search request. The server of Baidu Wenxin searches for the feature collection tool under the running environment for the performance characteristics and returns the search result to the first AI tool. In some possible implementation manners, the first AI tool can include a request template, and the request template includes a first blank field, a second blank field and a third blank field. The first blank field is used to fill in the performance characteristics, the second blank field is used to fill in the running environment, and the third blank field is used to fill in the description information of the feature collection tool. Subsequently, the first AI tool fills the performance characteristics, the running environment and the description information of the feature collection tool into the first blank field, the second blank field and the third blank field based on the search request, obtains a request under the request template, and sends the request under the request template to the server. The server is used to search for the feature collection tool to obtain the search result and feed back the search result to the first AI tool. For example, the first AI tool is Baidu Wenxin, and the first AI tool can fill the performance characteristics, the running environment and the description information of the feature collection tool in the search request into the request module to obtain a request under the request template. The request is sent to the server of Baidu Wenxin, and the server of Baidu Wenxin searches based on the request and feeds back the search result to the first AI tool. Therefore, in the embodiments of the application, the search process of the AI tool does not need human intervention, and the feature collection tool under the running environment of the computing device 102 for the performance characteristics can be automatically searched, thereby improving the convenience of selecting the feature collection tool.

[0103] In the embodiments of the application, the description information of the feature collection tool can be the download link, the compilation method, the installation method and the running method of the feature collection tool. Therefore, the search request can be used to request to search the download link, the compilation method, the installation method and the running method of the feature collection tool. Correspondingly, Figure 4As shown, the search result can include a download link of the feature collection tool, a compilation method, an installation method, and a running method. It should be noted that the description information of the feature collection tool is user-defined; and the actual requirements can be flexibly designed, and the embodiments of the present application do not make specific limitations. It should be noted that the first AI tool can include a request template, and the format of the filled content of the third blank field can be flexibly designed according to the actual request, for example, the key-value form can be used, and the third blank field can be "download link: ; compilation method: ; installation method: ; running method: " for example.

[0104] In some possible cases, the first AI tool is any one of n (greater than or equal to 2) AI tools; in some optional examples, the computing device 102 includes an order of n AI tools; assuming that the order of n AI tools is: AI tool 1, AI tool 2, …, AI tool n, in some possible scenarios, the computing device 102 searches for the feature collection tool according to the order of n AI tools, and the specific implementation is as follows:

[0105] As shown in Figure 5 , the computing device 102 can first send a search request to the AI tool 1 located at the first position according to the order of n AI tools, and in the case that the search result returned by the AI tool 1 in response to the search request is accurate, the search is ended, and in the case that the search result returned by the AI tool 1 in response to the search request is incorrect, the search request is sent to the AI tool 2 located at the second position, and in the case that the search result returned by the AI tool 2 in response to the search request is accurate, the search is ended, and in the case that the search result returned by the AI tool 2 in response to the search request is incorrect, the search request is sent to the AI tool 3 located at the second position, and the cycle is repeated.

[0106] As shown in Figure 6a , the accurate search result can be that the search result is successfully parsed, the download link of the feature collection tool in the search result can successfully download the feature collection tool, the compilation method of the feature collection tool in the search result can successfully compile the feature collection tool into an executable file, the installation method of the feature collection tool in the search result can successfully install the executable file after the feature collection tool is compiled, and the running method of the feature collection tool in the search result can successfully run the executable file after the feature collection tool is compiled. The successful parsing of the search result can be understood as that the key content in the search result: the download link of the feature collection tool, the compilation method, the installation method, and the running method can be extracted.

[0107] The search result error can be a failure to parse the search result, a failure of the feature collection tool download link in the search result to download the feature collection tool, a failure of the feature collection tool compilation method in the search result to compile the feature collection tool into an executable file, a failure of the feature collection tool installation method in the search result to install the executable file of the compiled feature collection tool, and / or a failure of the feature collection tool running method in the search result to run the executable file of the compiled feature collection tool. The failure to parse the search result can be understood as a failure to extract the key content in the search result: the feature collection tool download link, the compilation method, the installation method, and the running method.

[0108] It should be noted that the manner of parsing the search result can be regular expression parsing; in the embodiment of the present application, the regular expression uses a string to match a string in the search result, and the string is used to represent the feature collection tool download link, the compilation method, the installation method, and the running method.

[0109] In Figure 5 In the scenario shown, the computing device 102 determines the first AI tool in the following manner: based on the order of the n AI tools and the number of AI tools that have responded to the search request in the case of searching for the feature collection tool in the order of the n AI tools, the computing device 102 determines the first AI tool from the n AI tools; for example, the computing device 102 determines the number of AI tools that have responded to the search request as the target order position, and the AI tool at the next order position of the target order position in the order of the n AI tools as the first AI tool; for example, when the target order position is 0, the first AI tool is the AI tool at the first position in the n AI tools.

[0110] The order of the n AI tools can be a pre-set order, or can be determined based on the success number and / or the search time. The success number is used to indicate the number of times that the search result of the AI tool is accurate for different search requests, that is, the search result of the AI tool is accurate, and the search is counted as a success; the search time is used to indicate the time consumed in responding to different search requests, for example, the average of the total time consumed in responding to different search requests, the performance characteristics and / or the running environment in different search requests are different; for example, the time consumed in responding to the search request can be the time length from receiving the search request to obtaining the search result. For example, the order of the n AI tools can be obtained by sorting the n AI tools in descending order of the success number; for example, the order of the n AI tools can be obtained by sorting the n AI tools in ascending order of the search time; for example, for each AI tool, an evaluation value of the AI tool can be determined based on the success number and the search time, for example, weighting; the order of the n AI tools can be obtained by sorting the n AI tools in descending order of the evaluation value.

[0111] Step 304, the computing device 102 runs the searched feature collection tool based on the search result returned by the first AI tool, and collects feature data of the performance feature to be analyzed by using the feature collection tool.

[0112] In the embodiment of the present application, in the case that the search result of the first AI tool responding to the search request is accurate, the feature collection tool searched by the first AI tool can be successfully run based on the search result of the first AI tool responding to the search request. The feature collection tool can be understood as various software and applications with feature collection function.

[0113] Exemplarily, as shown in Figure 6a , the search request can be used to request to search the download link, compilation method, installation method and running method of the feature collection tool; correspondingly, the search result can include the download link, installation method, compilation method and running method of the feature collection tool; the computing device 102 successfully parses the search result, successfully downloads the feature collection tool based on the download link of the feature collection tool, successfully compiles the feature collection tool into an executable file based on the compilation method, successfully installs the executable file after the feature collection tool is compiled in the running environment of the computing device 102 based on the installation method, successfully runs the executable file after the feature collection tool is compiled in the running environment of the computing device 102 based on the running method of the feature collection tool, so as to determine that the search result of the first AI tool responding to the search request is accurate; subsequently, the feature data of the performance feature to be analyzed is collected by directly using the running feature collection tool.

[0114] It is worth noting that the search request can be a plurality of requests arranged in sequence, each request in the plurality of requests is used to request part of the download link, installation method, compilation method and running method of the feature collection tool, and the content requested by the plurality of requests arranged in sequence is in the order of the download link, installation method, compilation method and running method of the feature collection tool. In actual application, the computing device 102 can send the request located in the first position to the first AI tool according to the plurality of requests arranged in sequence, send the request located in the second position to the first AI tool in the case that the search result returned by the first AI tool is accurate, and repeat the cycle until the search result returned by the first AI tool responding to the request located in the last position is accurate. Exemplarily, as shown in Figure 6bAs shown, the computing device 102 determines a first request based on the performance characteristics to be analyzed of the computing device 102 and the running environment of the computing device 102, and the first request can be used to request a download link, a compilation method, and an installation method of the search feature collection tool. Correspondingly, the search result 11 of the first AI tool in response to the first request can include the download link, the compilation method, and the installation method of the feature collection tool. Then, the computing device 102 successfully parses the search result 11, successfully downloads the feature collection tool based on the download link, successfully compiles the feature collection tool into an executable file based on the compilation method, and successfully installs the executable file of the feature collection tool after compilation in the running environment of the computing device 102 based on the installation method. Then, it can be determined that the search content 11 of the first AI tool in response to the first request is accurate, and it is determined that the feature collection tool is successfully installed. Subsequently, the computing device 102 can determine a second request based on the running environment of the computing device 102 and the feature collection tool indicated by the feedback result 11, and the second request can be used to request a running method of the feature collection tool in the running environment of the computing device 102. Correspondingly, the search result 12 of the first AI tool in response to the second request can include the running method of the feature collection tool, and the computing device 102 successfully runs the executable file of the feature collection tool after compilation in the running environment based on the running method. Then, it is determined that the search result 12 of the first AI tool in response to the second request is accurate. Subsequently, the feature data of the performance characteristics to be analyzed is collected directly using the running feature collection tool.

[0115] In addition, in Figure 5 As shown in the scenario, as Figure 7 As shown, in the case where the search result of the first AI tool in response to the search request (for the sake of description and distinction, it can be referred to as search result 1) is incorrect, the search request is sent to the second AI tool. Exemplarily, the success times of the first AI tool are higher (greater than or equal to) than those of the second AI tool, and / or the search time of the first AI tool is lower (less than or equal to) than that of the second AI tool. The AI tool with accurate search and fast search is considered first, thereby improving the efficiency of searching for the feature collection tool. Subsequently, in the case where the search result 2 of the second AI tool in response to the search request is accurate, the feature collection tool is determined based on the second search result. For details, refer to the related description of the first AI tool, which will not be described herein again. It should be noted that the first AI tool and the second AI tool are different, for example, the first AI tool is chatgpt, and the second AI tool is Baidu Wenxin. In the case where the search result of the first AI tool in response to the search request is incorrect, the search request is continuously sent to other AI tools in a loop, thereby integrating multiple search results and improving the probability of searching for the feature collection tool that adapts to the performance characteristics and the running environment of the computing device 102.

[0116] It should be noted that, in Figure 6bThe search request is the first request and the second request in the scenario. In one possible scenario, as shown in Figure 8a If the first AI tool makes an error in the search result 11 for the first request, the computing device 102 sends the first request to the second AI tool, and the second AI tool returns the search result 21 in response to the first request. If the search result 21 returned by the second AI tool in response to the first request is accurate, the computing device 102 sends the second request to the second AI tool. If the search result 22 returned by the second AI tool in response to the second request is inaccurate, the computing device 102 continues to send the first request and the second request to other AI tools in the aforementioned manner, and the process is repeated. In one possible scenario, as shown in Figure 8b If the first AI tool makes an error in the search result 11 for the first request, the computing device 102 sends the first request to the second AI tool, and the second AI tool returns the search result 21 in response to the first request. If the search result 21 returned by the second AI tool in response to the first request is accurate, the computing device 102 sends the second request to the second AI tool. If the search result 22 returned by the second AI tool in response to the second request is inaccurate, the computing device 102 continues to send the first request and the second request to other AI tools in the aforementioned manner, and the process is repeated.

[0117] It should be noted that in actual applications, in the embodiments of the present application, the computing device 102 runs the feature collection tool based on the search request and the search result returned by at least part of the n (greater than or equal to 2) AI tools in response to the search request.

[0118] In some possible implementation manners, as shown in Figure 5 The computing device 102 can sequentially send the search request to the n AI tools in the order of the n AI tools.

[0119] It should be noted that the above-described manner of determining the feature collection tool is merely an example and does not constitute a specific limitation. In another possible implementation manner, as shown in Figure 9 The computing device 102 can send the search request to each of the n AI tools, and then run the searched feature collection tool based on the search results of the n AI tools.

[0120] In a possible example, the computing device 102 determines the search result to be processed currently based on the order of the received search results and the number of processed search results, judges whether the search result to be processed currently is accurate, ends if the search result to be processed currently is accurate, runs the feature collection tool indicated by the accurate search result, and otherwise, continues to determine the search result to be processed currently, and repeats the above process. For example, the computing device 102 takes the number of processed search results as a target order position, and takes the search result at a next order position of the target order position as the search result to be processed currently.

[0121] In another possible example, the computing device 102 determines the feature collection tool with the highest occurrence frequency based on all the n received search results, takes the feature collection tool with the highest occurrence frequency as the final running feature collection tool if the feature collection tool with the highest occurrence frequency can be run based on the search result, and otherwise, takes the feature collection tool with the second highest occurrence frequency, judges whether the feature collection tool with the second highest occurrence frequency can be run according to the above method, and repeats the above process.

[0122] In a specific implementation, the computing device 102 needs to run the business software, and in the case of running the business software, the feature collection tool is used to collect the feature data of the performance feature to be analyzed.

[0123] The business software can be software for implementing a business for a user, for example, HPC software, and the HPC software is software for using high-performance computing, for example, software for implementing weather forecasting, scientific research, engineering calculation, and simulation. In addition, the feature collection tool is used to collect the feature value of the feature of the characteristic type description. It should be noted that the business software uses the hardware resources of the computing device 102, such as CPU, memory, and disk, during running. The performance feature is used to describe the performance-related features of the computing device 102, and therefore, the running of the searched feature collection tool can collect the usage of the hardware resources of the computing device 102 during the running of the business software. In addition, the business software needs to run together with the feature collection tool or run before the running of the feature collection tool.

[0124] It should be noted that some business software is developed by the user, and the running method of the business software needs to be provided by the user. In this scenario, the computing device 102 needs to obtain the running method of the business software from the user in advance, and runs the business software based on the running method of the business software. There are various ways for the computing device 102 to obtain the running method of the business software.

[0125] In some possible implementation manners, the computing device 102 can provide an interface, the user can operate the terminal 101 to access the interface, and input the running method of the business software deployed on the computing device 102. Subsequently, the terminal 101 sends the running method of the business software input by the user to the computing device 102.

[0126] In some possible implementation, the computing device 102 can provide a human-computer interaction interface, the terminal 101 can display the human-computer interaction interface, and the user can input the running method of the deployed business software of the computing device 102 in the human-computer interaction interface. Subsequently, the terminal 101 can send the running method of the deployed business software input by the user to the computing device 102.

[0127] In some possible implementation, the management device 103 can provide a human-computer interaction interface or an interface, the terminal 101 can display the human-computer interaction interface or access the interface, and the user can input the running method of the deployed business software of the computing device 102. For example, assuming that the management device 103 manages a plurality of computing devices 102, the user can input the model of the computing device 102 and the running method of the business software corresponding to the model. Subsequently, the management device 103 can send the running method of the business software to each computing device 102 that deploys the business software under the model.

[0128] In step 305, the computing device 102 determines the performance analysis result of the computing device 102 based on the feature data.

[0129] In a specific implementation, as shown in Figure 10a The computing device 102 can determine a feature analysis request (for requesting to analyze the feature data) based on the feature data, send the feature analysis request to a feature analysis tool, and the feature analysis tool determines the performance analysis result of the computing device 102 and feeds back to the computing device 102.

[0130] The performance analysis result is used to describe the result of the performance analysis of the computing device 102, and can include a chart and a performance analysis conclusion. The performance analysis conclusion can include that the business software is read-write intensive software, the CPU usage rate (representing the CPU resource occupied by the business software) of the business software, and the memory usage rate (the ratio of the used memory to the total memory) of the business software.

[0131] Further, the computing device 102 can also determine the performance adjustment suggestion of the computing device 102 based on the feature data.

[0132] The performance adjustment suggestion can include the specification of the used disk, the specification of the used CPU, the size of the used memory, modification of the compilation parameter, modification of the multi-process communication mode, and modification of the start task number.

[0133] In some possible implementation, as shown in Figure 10bAs shown, the computing device 102 can determine a performance adjustment suggestion request (for requesting a performance adjustment suggestion of the computing device 102 based on the feature data) based on the feature data, send the performance adjustment suggestion request to the feature analysis tool, and the feature analysis tool determines the performance analysis result and the performance adjustment suggestion of the computing device 102 and feeds back to the computing device 102.

[0134] In some possible implementation manners, as shown in Figure 10c As shown, the computing device 102 can determine a feature analysis request (for requesting analysis of the feature data) based on the feature data, send the feature analysis request to the feature analysis tool, and the feature analysis tool determines the performance analysis result and the performance adjustment suggestion of the computing device 102 and feeds back to the computing device 102.

[0135] In addition, the performance analysis result of the computing device 102 can also be carried by a document, which can include the performance analysis result (which can include a chart and a performance analysis conclusion) of the computing device 102, and further can include the feature data, the computing device performance analysis method (describing steps 301-305) and / or the performance adjustment suggestion of the computing device 102.

[0136] In specific implementation, as shown in Figure 10c As shown, the computing device 102 can determine a feature analysis request (for requesting analysis of the feature data) based on the feature data, send the feature analysis request to the feature analysis tool, and the feature analysis tool determines the performance analysis result and the performance adjustment suggestion of the computing device 102 and feeds back to the computing device 102. Figure 10d As shown, the computing device 102 can determine a document generation request based on the feature data, the performance analysis result of the computing device 102, the performance adjustment suggestion of the computing device 102, and the computing device performance analysis method (describing steps 301-305), send the document generation request to the document generation tool, and the document generation tool generates a document based on the feature data, the performance analysis result of the computing device 102, the performance adjustment suggestion of the computing device 102, and the computing device performance analysis method (describing steps 301-305), and feeds back the generated document to the computing device 102, and the computing device 102 displays the document.

[0137] In this scheme, the feature collection tool can be flexibly selected according to the performance features selected by the user, and diversified user needs can be met.

[0138] It should be noted that in the embodiments of the present application, the first AI tool can be located in the computing device 102, as shown in Figure 11The first AI tool can also be located in the management device 103; in the case where the first AI tool is any one of the n AI tools, the n AI tools can be located in the computing device 102 and can also be located in the management device 103. It is worth noting that when the AI tool is located in the management device 103, the resource consumption of the computing device 102 can be reduced, and the impact on the business can be reduced.

[0139] It is worth noting that the above description of the first AI tool in the embodiments is only an example and does not constitute a specific limitation. In some possible implementations, in the case where the computing device 102 searches for the feature collection tool in the order of the n AI tools, the first AI tool can be the AI tool whose search result is accurate in the first search among the n AI tools. For example, in the scenario shown in Figure 5 In the scenario shown, the computing device 102 searches for the feature collection tool in the order of AI tool 1, AI tool 2, …, and AI tool n. Assuming that the search results of AI tool 1, …, and AI tool (i-1) in response to the search request are incorrect, and the search result of AI tool i in response to the search request is accurate, AI tool i is the first AI tool, and the computing device 102 runs the feature collection tool searched by the first AI tool based on the search result of the first AI tool in response to the search request. In other possible implementations, in the case where the computing device 102 searches for the feature collection tool in the parallel manner of the n tools, the first AI tool can be the n AI tools. For example, in the scenario shown in Figure 9 In the scenario shown, the computing device 102 runs the searched feature collection tool based on the n search results of the n AI tools in response to the search request.

[0140] Based on the above-provided computing device performance analysis method, the specific application of the computing device performance analysis method is described.

[0141] As shown in Figure 12 In the embodiments of the present application, the feature data collection system can include a feature collection module, a business software, an AI search module, an AI analysis module, and a feature display module. The AI search module can include a plurality of AI tools.

[0142] In actual applications, a user can install a feature collection module and a business software in the computing device 102. If the feature analysis to be performed involves multiple nodes, the feature collection module can obtain information of other nodes, for example, through / etc / hosts. The AI search module is used for information search, and the AI analysis module is used for analyzing the search result returned by the AI search module.

[0143] For the feature collection module: the module is used to read the performance characteristics of the computing device 102 to be analyzed input by the user, such as IO, memory, etc., in addition, the running method of the business software input by the user is also read. Then, according to the obtained performance characteristics, the related information of the computing device 102 (used to describe the running environment of the computing device 102) is read, and then a search request is sent to the AI search module. The AI search module searches the download link of the feature collection tool software, the compilation method, the installation method, the running method, etc. of the performance characteristics to be analyzed in the running environment of the computing device 102, obtains the search result, and parses the search result through the AI analysis module; according to the parsed search result returned by the AI analysis module, the searched feature collection tool is run on the computing device 102 to obtain the feature data of the performance characteristics of the computing device 102 in the running process of the business software. The feature data is sent to the AI search module, the AI search module determines the performance analysis result of the computing device 102 and the performance adjustment suggestion for the computing device 102, obtains the search result, and parses the search result through the AI analysis module. According to the parsed search result returned by the AI analysis module, the performance analysis result of the computing device 102 and the performance adjustment suggestion for the computing device 102 are obtained.

[0144] For the feature display module: the steps executed by the feature collection module, the feature data, the performance analysis result of the computing device 102 and the performance adjustment suggestion for the computing device 102 are sent to the AI search module, the AI search module determines the document, obtains the search result, and parses the search result through the AI analysis module. According to the parsed search result returned by the AI analysis module, the document is generated and presented to the user.

[0145] It should be noted that in the embodiments of the present application, the AI search module and the AI analysis module can be located in the computing device 102, and can also be located in the management device 103 (see Figure 13 ).

[0146] As Figure 14 shown, another specific embodiment of the computing device performance analysis method provided by the embodiments of the present application is provided. The embodiments are based on the foregoing embodiments, and the computing device performance optimization process is described more specifically and optimized to a certain extent in combination with the feature data collection system. In this embodiment, the computing device 102 is taken as an example of a server, and the server runs a main program, runs an AI search module, runs an AI analysis module, and installs business software. The main program can be the program of the feature collection module. As Figure 14 shown, the method in the embodiments includes:

[0147] 1. The main program reads the performance characteristics to be analyzed input by the user.

[0148] 2. The main program determines the performance characteristics to be analyzed and server information.

[0149] By way of example, the server information is used to describe the running environment of the server, such as the version of the operating system and the processor architecture.

[0150] 3. The main program sends a first request to the AI search request, and the first request is used to request a download link, a compilation method, and an installation method of the feature collection tool.

[0151] For example, assuming that the processor architecture of the server is x86 and the operating system is Linux, the search request is used to obtain the feature collection tool corresponding to the performance characteristics determined by the user under the x86 architecture and Linux, and return the relevant information of the feature collection tool.

[0152] 4. The AI search module searches for the download link, the compilation method, and the installation method of the feature collection tool in response to the first request to obtain a first response result and return.

[0153] It should be noted that the first response result can also be referred to as a search result.

[0154] 5. The AI analysis module analyzes the first response result returned by the AI search module.

[0155] In a specific implementation, the AI analysis module analyzes the first response result returned by the AI search module through a regular expression, and extracts the download link, the compilation method, and the installation method of the feature collection tool.

[0156] 6. The main program installs the feature collection tool on the server based on the parsed first response result.

[0157] The main program can download the feature collection tool based on the download link, compile the feature collection tool into an executable file based on the compilation method, and install the executable file based on the installation method.

[0158] In actual application, the AI search module can include multiple AI tools, and the search request is an http request. The main program can implement the following two steps:

[0159] Step 1. Call the calling order file of the multiple AI tools stored locally, such as the first order is chatgpt and the second order is baidu wenxin, send an http request to the AI tool, and parse the response result returned by the AI tool through a format, such as a regular expression, to obtain the download link, the compilation method, and the installation method of the feature collection tool.

[0160] Step 2. After the main program downloads the feature collection tool, install the feature collection tool on the server; if the main program fails to install the feature collection tool, return to step 1 and send an http request to the next AI tool in sequence.

[0161] Wherein, the main program has a default calling sequence for AI tools, and in the process of updating the AI tool calling sequence, the success times and time consumption are sorted, the earlier the sorting, the higher the priority of the call, when there are multiple types of AI tools with the same success times and time consumption, the types of these AI tools are randomly sorted. It should be noted that the higher the success times and the shorter the time consumption, the higher the sorting of the AI tool.

[0162] 7. The main program sends a second request to the AI search module, and the second request is used to request the running method of the feature collection tool.

[0163] 8. The AI search module searches the running method of the feature collection tool in response to the second search request to obtain a second response result and return.

[0164] 9. The AI analysis module analyzes the second response result returned by the AI search module.

[0165] In specific implementation, the AI analysis module analyzes the second response result returned by the AI search module through regular expression, and extracts the running method of the feature collection tool.

[0166] 10. The main program runs the business software on the server, and runs the feature collection tool on the server based on the parsed second response result.

[0167] In specific implementation, after the main program installs the feature collection tool, it sends an http request to the AI tool, and after the response result returned by the AI tool is parsed in a format such as regular expression, the running method of the feature collection tool is obtained; the main program executes the business software and the feature collection tool on the server using shell execution instructions.

[0168] 11. The main program acquires feature data through the feature collection tool.

[0169] 12. The main program sends a third request to the AI search request, and the third request is used to request to determine the performance analysis result and performance adjustment suggestion of the server according to the feature data.

[0170] 13. The AI search module determines the performance analysis result and performance adjustment suggestion of the server according to the feature data in response to the third request, obtains a third response result and returns.

[0171] 14. The AI analysis module analyzes the third response result returned by the AI search module.

[0172] In a specific implementation, the AI analysis module parses the third response result returned by the AI search module through a regular expression, and extracts the performance analysis result and performance adjustment suggestion of the server.

[0173] 15. The main program sends a fourth request to the AI search request, and the fourth request is used to request to generate a document based on the performance analysis step, the feature data, the performance analysis result and the performance adjustment suggestion of the server.

[0174] The performance analysis step can be steps 1 to 14 described above.

[0175] 16. The AI search module generates the content and format of the document according to the performance analysis step, the feature data, the performance analysis result and the performance adjustment suggestion of the server in response to the fourth request, obtains a fourth response result and returns.

[0176] 17. The AI analysis module parses the fourth response result returned by the AI search module.

[0177] In a specific implementation, the AI analysis module parses the fourth response result returned by the AI search module through a regular expression, and extracts the content and format of the server document.

[0178] The content of the document is: performance analysis step, feature data, performance analysis result of the server, performance adjustment suggestion, title, content layout (position of performance analysis step, feature data, performance analysis result of the server, performance adjustment suggestion), font, font size, color, alignment, etc. The format of the document is used to indicate that the format of the document refers to a special coding method of information used for information storage.

[0179] 18. The main program generates a document according to the parsed fourth response result.

[0180] Based on the same idea as the method embodiments of the present application, the embodiments of the present application further provide a computing device performance analysis apparatus. The computing device performance analysis apparatus comprises a plurality of modules, each module being configured to perform each step of the computing device performance analysis method provided by the embodiments of the present application. The division of the modules is not limited herein. Those skilled in the art can clearly understand that, in actual applications, each step of the computing device performance analysis method provided by the embodiments of the present application can be completed by different modules according to needs, i.e., the internal structure of the apparatus is divided into different modules to complete all or part of the functions described above. Each module in the embodiments can be integrated in one processing unit, or each unit can be physically present separately, or two or more modules can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific names of the modules are only for the purpose of mutual distinction, and do not limit the protection scope of the present application. The specific working process of the modules in the apparatus can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0181] For example, the computing device performance analysis apparatus is configured to perform the computing device performance analysis method provided by the embodiments of the present application. Figure 15 FIG. 1 is a structural schematic diagram of a computing device performance analysis apparatus provided by an embodiment of the present application. As shown in FIG. 1, the computing device performance analysis apparatus provided by the embodiments of the present application comprises: Figure 15

[0182] The acquisition module 1501 is configured to acquire the performance characteristics to be analyzed of the computing device and the running environment of the computing device.

[0183] The request module 1502 is configured to request a first AI tool to search for a feature collection tool based on the performance characteristics to be analyzed and the running environment. The first AI tool is configured to search for a feature collection tool suitable for the running environment.

[0184] The collection module 1503 is configured to run the searched feature collection tool based on the search result returned by the first AI tool, and collect feature data of the performance characteristics to be analyzed by using the feature collection tool.

[0185] The analysis module 1504 is configured to determine the performance analysis result of the computing device based on the feature data.

[0186] ​Based on the same idea as the method embodiments of the present application, the embodiments of the present application also provide a computing device. In a specific application, the computing device can include a memory, which can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a hard disk 123. The volatile memory can be a memory 112. Specifically, the memory of the computing device, such as the hard disk and the memory 112, can store a computer program. When the computing device is running, the processor 111 can read the computer program stored in the memory, such as reading the computer program stored in the hard disk to the memory 112, and reading the computer program from the memory 112, to implement the steps in the above computer performance test method, for example Figure 3 steps 301 to 305 in the method 300.

[0187] For example, the computer program can be divided into one or more modules / units, which can be a series of computer program instruction segments capable of completing a specific function, and the one or more modules / units are stored in the hard disk and executed by the CPU 111 to complete the present application. For example, the computer program can be divided into an acquisition module 1501, a request module 1502, a collection module 1503, and an analysis module 1504. The specific functions of each module are described above.

[0188] In addition to the above method, device and computing device, the embodiments of the present application can also provide a computer program product, which includes computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the computing device performance analysis method of various embodiments of the present application described in the above "method" part of the present specification. Among them, the computer program product can be written in one or more program design languages in any combination to execute the computer program code for performing the operations of the embodiments of the present application, which includes object-oriented program design languages such as Java, C++, etc., and conventional procedural program design languages such as "C" language or similar program design languages. Among them, the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer program code can be completely executed on the user computing device, partially executed on the user device, executed as an independent software package, partially executed on the user computing device and partially on a remote computing device, or completely executed on a remote computing device or server.

[0189] Moreover, embodiments of the present application can also provide a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, enable the processor to carry out the steps described in the above method part of the specification as related to the method of analyzing performance of a computing device according to various embodiments of the present disclosure. The computer readable storage medium can take the form of one or more combinations of any type of computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. It is noted that the computer readable medium contains content that can be appropriate for software that is in compliance with the requirements of the legislation and patent practice in the jurisdiction, and the computer readable medium can be appropriately added or reduced, for example, in some jurisdictions, according to the legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0190] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0191] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0192] The basic principles of the present application are described above in combination with specific embodiments, but it should be noted that the advantages, advantages, effects and the like mentioned in the present application are only examples and not limitations, and these advantages, advantages, effects and the like cannot be considered as the must-have of each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of example and for the purpose of understanding, and the above details do not limit the present disclosure to the must-use specific details.

[0193] The block diagrams of the devices, apparatuses, equipment, systems involved in the present disclosure are only as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be as shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have", and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0194] It should also be noted that in the devices, apparatuses and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present disclosure.

[0195] The above description has been given for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

[0196] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and do not limit the scope of the embodiments of the present application.

Claims

1. A method of performance analysis of a computing device, the method comprising: The method comprises: obtaining performance characteristics to be analyzed of a computing device and a running environment of the computing device; searching, based on the performance characteristics to be analyzed and the running environment, a feature collection tool by a first AI tool; wherein the first AI tool is used to search a feature collection tool suitable for the running environment; based on the search result returned by the first AI tool, running the searched feature collection tool, and collecting feature data of the performance characteristics to be analyzed by using the feature collection tool; based on the feature data, determining a performance analysis result of the computing device.

2. The method of claim 1, wherein, The obtaining of the performance characteristics to be analyzed of the computing device comprises: based on a human-computer interaction interface, obtaining performance characteristics to be analyzed of the computing device set by a user.

3. The method according to claim 1 or 2, characterized in that, The searching, based on the performance characteristics to be analyzed and the running environment, a feature collection tool by a first AI tool comprises: sending a search request to the first AI tool; the search request comprises the performance characteristics and the running environment, and the search request is used to request to search a feature collection tool for the performance characteristics under the running environment; The running, based on the search result returned by the first AI tool, the searched feature collection tool comprises: in the case that the search result of the first AI tool responding to the search request is accurate, running the feature collection tool indicated by the search result on the computing device.

4. The method of claim 3, wherein, The method further comprises: in the case that the search result is wrong, sending the search request to a second AI tool.

5. The method of claim 4, wherein, The success times of the first AI tool are higher than those of the second AI tool, and / or the search time of the first AI tool is lower than that of the second AI tool, the success times are used to indicate the number of times of accurate search results for different search requests, and the search time is used to indicate the time consumed in responding to the different search requests, the performance characteristics and / or the running environment in the different search requests are different.

6. The method according to claim 4 or 5, characterized in that, The search result comprises a download link of the feature collection tool, a compilation method of the feature collection tool, an installation method of the feature collection tool, and a running method of the feature collection tool; The running, based on the search result returned by the first AI tool, the searched feature collection tool comprises: downloading the feature collection tool based on the download link; compiling the feature collection tool into an executable file based on the compilation method; installing the executable file in the running environment based on the installation method; running the executable file in the running environment based on the running method.

7. The method of claim 1, 2, 4, or 5, wherein, Before collecting the feature data of the performance characteristics to be analyzed by using the feature collection tool, the method further comprises: obtaining a running method of a business software; based on the running method, running the business software.

8. The method of claim 1, 2, 4, or 5, wherein, The running environment of the computing device comprises the architecture of a central processing unit and the version of an operating system.

9. The method of claim 1, 2, 4, or 5, wherein, The computing device performance analysis method is executed by the computing device; The first AI tool searching the feature collection tool is executed by other devices other than the computing device.

10. A computing device, comprising: comprises a processor and a memory; wherein, the memory is used to store a program; The illustrated processor is configured to execute a program stored by the memory, wherein the program, when executed by the processor, implements the method of any one of claims 1 to 9.

Images