CN113656292A - Multi-dimensional cross-space-time basic software performance bottleneck detection method - Google Patents
Multi-dimensional cross-space-time basic software performance bottleneck detection method Download PDFInfo
- Publication number
- CN113656292A CN113656292A CN202110893397.1A CN202110893397A CN113656292A CN 113656292 A CN113656292 A CN 113656292A CN 202110893397 A CN202110893397 A CN 202110893397A CN 113656292 A CN113656292 A CN 113656292A
- Authority
- CN
- China
- Prior art keywords
- bottleneck
- performance
- performance index
- mode
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 123
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 239000013598 vector Substances 0.000 claims description 36
- 238000007726 management method Methods 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 9
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000013523 data management Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 13
- 230000006978 adaptation Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The utility model relates to a multi-dimensional cross-space-time basic software performance bottleneck detection method, this method is applied to performance bottleneck diagnostic analysis tool, including: constructing a first performance index mode under an empty load operation system and a second performance index mode under different load operation systems; determining a similarity between the first performance indicator pattern and the second performance indicator pattern based on a common matching algorithm; according to the similarity comparison result, extracting a performance index mode with the similarity smaller than a preset similarity threshold from the first performance index mode and the second performance index mode, and taking the extracted performance index mode as a bottleneck correlation mode; and performing performance bottleneck analysis on the bottleneck correlation mode. The bottleneck analysis efficiency can be improved.
Description
Technical Field
The disclosure relates to the technical field of computers, in particular to a multi-dimensional cross-space-time basic software performance bottleneck detection method.
Background
It is known that the performance of a computer system is greatly influenced by the integrated adaptive optimization capability of basic software and hardware. At present, the optimization aiming at the integrated adaptation of basic software and hardware is very deficient, the ecological components of the domestic software and hardware are complex, and a part of ecological elements are not subjected to targeted optimization. Optimizing aiming at the type of the processor, not only compiler options need to be changed, but also performance bottlenecks need to be accurately positioned, optimization potential is found, an optimization scheme is formulated, and the task needs to deeply understand the performance characteristics of a processor architecture and the performance characteristics of application software.
With the development of software and hardware, the software and hardware respectively provide a plurality of operation modes to adapt to diversified operation scenes. The key software and hardware such as a processor, an operating system and a database provide a large amount of adjustable parameters, the combined space formed by the adjustable parameters is huge, and how to adjust various parameters to form an optimal adaptation scheme meeting specific services is a huge challenge.
At present, the performance optimization of key software and hardware mainly depends on the manual optimization of technicians with high technical level, and in the process of optimizing adaptation, information acquisition is usually carried out by utilizing some performance testing tools. The generation of the performance bottleneck analysis and optimization scheme is generally performed in a manual mode, the mode has low efficiency, various performance index data cannot be systematically and fully utilized, potential performance bottlenecks may be omitted, and the optimal optimization adaptation scheme cannot be found.
Disclosure of Invention
To solve the above technical problem or at least partially solve the above technical problem, the present disclosure provides a multi-dimensional cross-space-time base software performance bottleneck detection method.
The present disclosure provides a multi-dimensional cross-space-time basic software performance bottleneck detection method, which is applied to a performance bottleneck diagnostic analysis tool, and comprises:
constructing a first performance index mode under an empty load operation system and a second performance index mode under different load operation systems;
determining a similarity between the first and second performance indicator patterns based on a commonality matching algorithm;
according to the similarity comparison result, extracting a performance index mode with the similarity smaller than a preset similarity threshold from the first performance index mode and the second performance index mode, and taking the extracted performance index mode as a bottleneck correlation mode;
and performing performance bottleneck analysis on the bottleneck correlation mode.
Optionally, the constructing a first performance index mode under the empty load operation system includes:
under an air load carrying system, acquiring parameters of various performance indexes for multiple times according to a preset time step length, and storing acquired first performance index parameters according to a preset vector;
and sampling the first performance index parameter according to a time interval increasing mode to obtain a first performance index mode crossing a time domain.
Optionally, the constructing a second performance index mode under different load operating systems includes:
according to a preset load increasing mode, increasing different types of loads in an operating system one by one;
in the process that the operating system increases along with the load, multiple parameter acquisition is carried out on each performance index according to a preset time step length, and an acquired second performance index parameter is stored according to a preset vector;
and sampling the second performance index parameter according to a time interval increasing mode to obtain a second performance index mode crossing a time domain.
Optionally, the preset vector is a vector composed of a series of data pairs, where the data pairs include: the method comprises the steps of acquiring a parameter and a performance index parameter acquired at the parameter acquiring moment;
when all the parameter acquisition moments in the preset vectors are the same, the preset vectors represent multi-dimensional performance index vectors at the same moment;
and when at least two parameter acquisition moments in the preset vectors are different, the preset vectors represent multi-dimensional performance index vectors across time domains.
Optionally, the performing performance bottleneck analysis on the bottleneck association mode includes:
and performing bottleneck pattern matching and bottleneck main body analysis on the bottleneck correlation pattern by using a performance bottleneck analysis plug-in to obtain the performance bottleneck.
Optionally, the performance bottleneck diagnostic analysis tool includes: support layer, plug-in components layer and interface layer.
Optionally, the support layer includes a commonality management unit, a bottleneck mode management unit, and a bottleneck matching algorithm management unit; wherein,
the common management unit is used for providing a performance data retrieval function, bottleneck analysis plug-in management and a common data management function of bottleneck analysis;
the bottleneck mode management unit is used for providing functions of generating a performance index mode and retrieving the performance index mode;
and the bottleneck matching algorithm management unit is used for providing a common matching algorithm and a main body association algorithm of the performance index mode.
Optionally, the plug-in layer is used for providing the bottleneck analysis plug-in; the bottleneck analysis plug-in includes:
a bottleneck analysis plug-in for a first object, the first object comprising: CPU, memory, network and I/O; and a bottleneck analysis plug-in for a second object, the second object comprising: operating systems, databases, middleware, system architectures, and algorithms.
Optionally, the interface layer is used to provide an external interface for performance bottleneck analysis, and includes: the interface of strategy analysis management, the interface of bottleneck analysis result output presentation, and the interface of manual interactive operation.
The present disclosure provides a multidimensional cross-space-time basic software performance bottleneck detection device, which is applied to a performance bottleneck diagnosis analysis tool, and comprises:
the system comprises a construction module, a first performance index mode and a second performance index mode, wherein the construction module is used for constructing a first performance index mode under an empty load operation system and a second performance index mode under different load operation systems;
a matching module to determine a similarity between the first and second performance indicator patterns based on a commonality matching algorithm;
the extracting module is used for extracting a performance index mode with the similarity smaller than a preset similarity threshold from the first performance index mode and the second performance index mode according to a similarity comparison result, and taking the extracted performance index mode as a bottleneck correlation mode;
and the analysis module is used for performing performance bottleneck analysis on the bottleneck correlation mode.
The present disclosure provides an electronic device, the electronic device including:
a processor; a memory for storing the processor-executable instructions;
the processor is used for reading the executable instruction from the memory and executing the instruction to realize the multi-dimensional cross-space-time basic software performance bottleneck detection method.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
the multi-dimensional cross-space-time basic software performance bottleneck detection method provided by the embodiment of the disclosure comprises the steps of constructing a first performance index mode under a load operation system and a second performance index mode under different load operation systems by using a performance bottleneck diagnostic analysis tool, and determining the similarity between the first performance index mode and the second performance index mode based on a common matching algorithm; and extracting a bottleneck correlation mode from the first performance index mode and the second performance index mode according to the similarity comparison result, and performing performance bottleneck analysis on the bottleneck correlation mode. The method and the device can improve the bottleneck analysis efficiency, effectively analyze potential performance bottlenecks in the system, and provide better guidance value for optimizing the adaptation.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic structural diagram of a performance bottleneck diagnostic analysis tool according to an embodiment of the disclosure;
FIG. 2 is a flowchart illustrating a multi-dimensional cross-space-time basic software performance bottleneck detection method according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating an implementation process of the multi-dimensional cross-space-time basic software performance bottleneck detection method according to the embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of a multi-dimensional cross-space-time basic software performance bottleneck detection apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
The embodiment of the disclosure provides a multi-dimensional cross-space-time basic software performance bottleneck detection method, and for convenience of understanding, the embodiment of the disclosure is described in detail below.
Firstly, the embodiment of the disclosure introduces a multi-dimensional cross-space-time basic software performance bottleneck detection method, and the method is applied to a performance bottleneck diagnosis and analysis tool. Referring to fig. 1, the performance bottleneck diagnostic analysis tool includes a support layer, a plug-in layer, and an interface layer.
The support layer provides a generic function for performing performance bottleneck analysis, which includes: the system comprises a commonality management unit, a bottleneck mode management unit and a bottleneck matching algorithm management unit. And the common management unit is used for providing a performance data retrieval function, bottleneck analysis plug-in management and a common data management function of bottleneck analysis. And the bottleneck mode management unit is used for providing functions of generating the performance index mode and retrieving the performance index mode. And the bottleneck matching algorithm management unit is used for providing a common matching algorithm and a main body association algorithm of the performance index mode.
The plug-in layer is used for providing a specific type of bottleneck analysis plug-in; and the bottleneck analysis plug-in utilizes the data and algorithm provided by the supporting layer to carry out performance bottleneck analysis. The bottleneck analysis plug-in includes: a bottleneck analysis plug-in for a first object, the first object comprising: CPU, memory, network, I/O, etc.; and a bottleneck analysis plug-in for a second object, the second object comprising: operating systems, databases, middleware, system architectures and algorithms, and the like.
The interface layer is used for providing an external interface for performance bottleneck analysis and can provide an interface for controlling and data for a software and hardware system comprehensive adaptation optimization platform. The interface layer provides external interfaces such as: the interface of strategy analysis management, the interface of bottleneck analysis result output presentation, and the interface of manual interactive operation. The interface of the strategy analysis management is used for processing analysis requests sent by other tools and determining an analysis range and a method; and the bottleneck analysis result output presentation interface is used for providing analysis reports or result data of multiple modes to the comprehensive adaptation optimization platform and the intelligent solution recommendation tool. The interface of manual interactive operation is used for providing an operation mode of manual bottleneck analysis for an analyst, and the capabilities of interactive analysis and heuristic bottleneck discovery are realized.
By utilizing the performance bottleneck diagnosis and analysis tool provided by the embodiment, the embodiment provides a multi-dimensional cross-space-time basic software performance bottleneck detection method; referring to fig. 2, the method includes:
step S202, a first performance index mode under an empty load operation system and a second performance index mode under different load operation systems are constructed.
The embodiment may receive an analysis request through the interface layer in advance before the performance index mode is constructed. The analysis request can be an analysis request sent by other tools and received through an interface of the policy analysis management, and the analysis range and the method of the performance bottleneck can be determined through the analysis request; alternatively, the analysis request may be a request for a manual bottleneck analysis received through a manually interoperable interface.
In this embodiment, when the performance bottleneck analysis method is executed according to the analysis request, the first performance index mode and the second performance index mode may be constructed by the bottleneck mode management unit of the support layer. Specifically, a performance index pattern library may be constructed by using a bottleneck pattern editing tool and a bottleneck pattern learning tool provided by the bottleneck pattern management unit, where the performance index pattern library includes a large number of performance index patterns in different test scenarios. The process is continued from the development stage to the tool operation life cycle, so that the follow-up use is realized, the number of the bottleneck modes is gradually increased through knowledge accumulation, and the diagnosis rate of the bottleneck modes is improved. There are various implementations of the bottleneck pattern generation and learning, such as: an automatic learning mode, a manually assisted learning mode, and a manual editing mode.
The automatic learning mode is a performance index mode which is used for collecting performance index parameters according to performance indexes and extracting the performance index parameters under the normal operation of the system under a large amount of normal operation mode data. The artificial assistant learning mode is a performance index mode which is obtained by artificially constructing a typical performance bottleneck scene, collecting performance index parameters and excavating abnormal association through machine learning and an association index analysis method. The manual editing mode can support professionals to directly edit the bottleneck mode according to experience knowledge, and a new performance index mode is added at any time.
According to the above embodiment, there is provided a method for constructing a first performance index mode under an empty load operation system, including:
step 1, under an air load carrying system, multiple parameter acquisition is carried out on each performance index according to a preset time step t, and an acquired first performance index parameter is stored according to a preset vector. Each performance index may be all performance indexes in the system performance index set, such as CPU usage, memory usage, network occupied bandwidth, disk capacity, and disk read/write IO.
The preset vector is a vector composed of a series of data pairs, wherein the data pairs include: a parameter acquisition time t and a performance index parameter p acquired at the parameter acquisition time. The preset vector may specifically refer to the following: p1, p2, tz 3, …, tx, ty and tz represent the parameter acquisition time, and p1, p2, p3 and other acquired performance index parameters. When all the parameter acquisition moments in a preset vector are the same, the preset vector represents a multi-dimensional performance index vector at the same moment; when at least two parameter acquisition moments in the preset vector are different, the preset vector represents a multi-dimensional performance index vector across a time domain.
In this embodiment, the first performance index parameter acquired for multiple times is stored in the time sequence database according to the preset vector.
And 2, sampling the first performance index parameter according to a time interval increasing mode to obtain a time-domain-crossing first performance index mode. Specifically, the first performance index parameter is sampled according to a time interval increasing mode, and the starting time interval is 0, so that a multi-dimensional time-domain-crossing first performance index mode is obtained.
It is understood that a plurality of first performance index patterns may be constructed according to the above steps 1 and 2, and a normal performance index pattern sample library in the empty load system is formed by the plurality of first performance index patterns.
The embodiment provides a method for constructing a second performance index mode under different load operation systems, which includes:
(1) according to a preset load increasing mode, increasing different types of loads in an operating system one by one; and in the process that the operating system increases along with the load, acquiring parameters of each performance index for multiple times according to a preset time step, and storing the acquired second performance index parameters according to a preset vector.
According to the embodiment, loads of calculation, network, I/O, memory and other types can be increased in a mode of increasing 10% step by step, multiple parameter acquisition is carried out on each performance index according to the time step t, and second performance index parameters obtained through multiple acquisition are stored in a time sequence database according to the format of a preset vector (tx: p1, ty: p2, tz: p3, …).
(2) And sampling the second performance index parameter according to a time interval increasing mode to obtain a second performance index mode crossing the time domain. And sampling the second performance index parameters under different loads according to a time interval increasing mode, wherein the initial time interval is 0, so that the multi-dimensional time-domain-crossing second performance index modes of different loads are obtained.
It is understood that a plurality of second performance index modes can be constructed according to the above steps (1) and (2), and a performance index mode sample library under different load operation systems is formed by the plurality of second performance index modes.
Step S204, determining the similarity between the first performance index mode and the second performance index mode based on the common matching algorithm.
The embodiment may determine the similarity between the first performance index mode and the second performance index mode through a common matching algorithm provided by the bottleneck matching algorithm management unit in the support layer.
Step S206, according to the similarity comparison result, extracting the performance index mode with the similarity smaller than the preset similarity threshold from the first performance index mode and the second performance index mode, and taking the extracted performance index mode as the bottleneck association mode. The similarity threshold is 70%, for example.
The embodiment may extract the bottleneck correlation pattern from the first performance index pattern and the second performance index pattern through a subject correlation algorithm provided by the bottleneck matching algorithm management unit.
Step S208, performing performance bottleneck analysis on the bottleneck correlation mode.
The performance bottleneck analysis mainly utilizes a bottleneck correlation mode to diagnose the performance bottleneck existing in the current operating system and locate the bottleneck. The performance bottleneck analysis is a highly technology intensive task, and the present embodiment can provide two processes, namely, automatic bottleneck analysis and manual bottleneck analysis.
In the automatic bottleneck analysis process, a performance bottleneck analysis plug-in is used for performing bottleneck mode matching and bottleneck main body analysis on a bottleneck correlation mode to obtain a performance bottleneck. Specifically, in the performance bottleneck analysis plug-ins provided by the plug-in layer and aiming at four resource classes such as a CPU, a memory, a network and an I/O, and the specific performance bottleneck analysis plug-ins such as an operating system, a database, a middleware, a system architecture and an algorithm, the bottleneck pattern matching and the bottleneck body analysis are performed on the bottleneck association pattern by using all available or selected performance bottleneck analysis plug-ins, so as to obtain the confidence rate that each user-defined application method in the bottleneck association pattern becomes a performance bottleneck, and a method with a higher confidence rate is determined as a performance bottleneck.
In the manual bottleneck analysis process, a user interaction interface can be provided through a manual interaction interface in an interface layer, obvious abnormal indexes in the bottleneck association mode are displayed for an analyst, and information prompting the analyst of the next analysis direction is displayed, so that the analyst can select the next analysis operation, such as selecting a specific analysis plug-in.
According to the above embodiments, an embodiment of the present disclosure provides a method for detecting performance bottleneck of multidimensional cross-space-time basic software as shown in fig. 3, including:
a) and a generation and learning phase of the performance index mode. In a bottleneck mode management unit of a support layer, a performance index mode library is constructed through a generation method of at least one bottleneck mode of an automatic learning mode, a manual auxiliary learning mode and a manual editing mode.
b) An automatic bottleneck analysis stage. Receiving an analysis request through an interface layer, and determining an analysis range according to the analysis request; traversing a bottleneck analysis plug-in the plug-in layer; obtaining a performance index mode to be analyzed from a performance index mode library, such as a first performance index mode library and a second performance index mode library in the above embodiment; and performing bottleneck mode analysis on the performance index mode to be analyzed by using the bottleneck analysis plug-in obtained by traversing, and obtaining an analysis result report, wherein the analysis result report is used for representing the performance bottleneck in the performance index mode to be analyzed.
c) And (5) manually interacting with a bottleneck analysis stage. Receiving an analysis request through an interface of manual interactive operation, determining an analysis range and a used bottleneck analysis plug-in according to the analysis request, performing bottleneck mode analysis on a performance index mode to be analyzed obtained from a performance index mode library by using the bottleneck analysis plug-in, and obtaining an analysis result report.
In summary, according to the multi-dimensional cross-space-time basic software performance bottleneck detection method provided by the embodiment of the disclosure, a performance bottleneck diagnostic analysis tool is used to construct a first performance index mode under a load operation system and a second performance index mode under different load operation systems, and a similarity between the first performance index mode and the second performance index mode is determined based on a common matching algorithm; and extracting a bottleneck correlation mode from the first performance index mode and the second performance index mode according to the similarity comparison result, and performing performance bottleneck analysis on the bottleneck correlation mode. Aiming at the problem of insufficient optimization adaptation between software and hardware, the technical scheme effectively integrates scattered performance evaluation tools by using a performance bottleneck diagnosis analysis tool, and can improve the bottleneck analysis efficiency by performing performance bottleneck analysis in two different modes, namely a first performance index mode and a second performance index mode, effectively analyze potential performance bottlenecks in a system and provide better guidance value for optimization adaptation.
In particular, according to the technical scheme, the collected performance index parameters and the corresponding first performance index modes are stored in a preset vector format, so that bottleneck analysis can be performed by utilizing the spatial performance difference and the time sequence performance difference of the performance index parameters, and the bottleneck analysis rate is improved.
As shown in fig. 4, an embodiment of the present disclosure provides a multidimensional cross-spatiotemporal basic software performance bottleneck detection apparatus, which is applied to a performance bottleneck diagnostic analysis tool, and the apparatus includes:
a constructing module 402, configured to construct a first performance index mode in an empty load operating system and a second performance index mode in different load operating systems;
a matching module 404 for determining a similarity between the first performance indicator pattern and the second performance indicator pattern based on a commonality matching algorithm;
the extracting module 406 is configured to extract, according to the similarity comparison result, a performance index mode with a similarity smaller than a preset similarity threshold from the first performance index mode and the second performance index mode, and use the extracted performance index mode as a bottleneck association mode;
an analysis module 408 for performing a performance bottleneck analysis on the bottleneck correlation pattern.
In some embodiments, the building module 402 is specifically configured to:
under an air load carrying system, acquiring parameters of various performance indexes for multiple times according to a preset time step length, and storing acquired first performance index parameters according to a preset vector; and sampling the first performance index parameter according to a time interval increasing mode to obtain a first performance index mode crossing a time domain.
In some embodiments, the building module 402 is specifically configured to:
according to a preset load increasing mode, increasing different types of loads in an operating system one by one; in the process that the operating system increases along with the load, multiple parameter acquisition is carried out on each performance index according to a preset time step length, and the acquired second performance index parameter is stored according to a preset vector; and sampling the second performance index parameter according to a time interval increasing mode to obtain a second performance index mode crossing the time domain.
In some embodiments, the analysis module 408 is specifically configured to:
and performing bottleneck mode matching and bottleneck main body analysis on the bottleneck correlation mode by using the performance bottleneck analysis plug-in to obtain the performance bottleneck.
The device provided by the embodiment has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic device 500 includes one or more processors 501 and memory 502.
The processor 501 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.
Memory 502 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 501 to implement the multi-dimensional cross-spatiotemporal base software performance bottleneck detection method of the embodiments of the present disclosure described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 500 may further include: an input device 503 and an output device 504, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input device 503 may also include, for example, a keyboard, a mouse, and the like.
The output device 504 may output various information to the outside, including the determined distance information, direction information, and the like. The output devices 504 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 500 relevant to the present disclosure are shown in fig. 5, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 500 may include any other suitable components depending on the particular application.
Further, the present embodiment also provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is used to execute the above multi-dimensional cross-spatiotemporal basic software performance bottleneck detection method.
The method, the apparatus, the electronic device, and the computer program product of the medium for detecting performance bottleneck of multi-dimensional cross-space-time basic software provided in the embodiments of the present disclosure include a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, and thus, details are not described here.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (11)
1. A multi-dimensional cross-space-time basic software performance bottleneck detection method is applied to a performance bottleneck diagnostic analysis tool, and comprises the following steps:
constructing a first performance index mode under an empty load operation system and a second performance index mode under different load operation systems;
determining a similarity between the first and second performance indicator patterns based on a commonality matching algorithm;
according to the similarity comparison result, extracting a performance index mode with the similarity smaller than a preset similarity threshold from the first performance index mode and the second performance index mode, and taking the extracted performance index mode as a bottleneck correlation mode;
and performing performance bottleneck analysis on the bottleneck correlation mode.
2. The method of claim 1, wherein constructing the first performance indicator pattern for the empty load operating system comprises:
under an air load carrying system, acquiring parameters of various performance indexes for multiple times according to a preset time step length, and storing acquired first performance index parameters according to a preset vector;
and sampling the first performance index parameter according to a time interval increasing mode to obtain a first performance index mode crossing a time domain.
3. The method of claim 1, wherein constructing a second performance indicator model for the system operating at different loads comprises:
according to a preset load increasing mode, increasing different types of loads in an operating system one by one;
in the process that the operating system increases along with the load, multiple parameter acquisition is carried out on each performance index according to a preset time step length, and an acquired second performance index parameter is stored according to a preset vector;
and sampling the second performance index parameter according to a time interval increasing mode to obtain a second performance index mode crossing a time domain.
4. The method according to claim 2 or 3, wherein the predetermined vector is a vector consisting of a series of data pairs, wherein the data pairs comprise: the method comprises the steps of acquiring a parameter and a performance index parameter acquired at the parameter acquiring moment;
when all the parameter acquisition moments in the preset vectors are the same, the preset vectors represent multi-dimensional performance index vectors at the same moment;
and when at least two parameter acquisition moments in the preset vectors are different, the preset vectors represent multi-dimensional performance index vectors across time domains.
5. The method according to claim 1, wherein the performing a performance bottleneck analysis on the bottleneck correlation pattern comprises:
and performing bottleneck pattern matching and bottleneck main body analysis on the bottleneck correlation pattern by using a performance bottleneck analysis plug-in to obtain the performance bottleneck.
6. The method of claim 1, wherein the performance bottleneck diagnostic analysis tool comprises: support layer, plug-in components layer and interface layer.
7. The method according to claim 6, wherein the support layer comprises a commonality management unit, a bottleneck mode management unit, and a bottleneck matching algorithm management unit; wherein,
the common management unit is used for providing a performance data retrieval function, bottleneck analysis plug-in management and a common data management function of bottleneck analysis;
the bottleneck mode management unit is used for providing functions of generating a performance index mode and retrieving the performance index mode;
and the bottleneck matching algorithm management unit is used for providing a common matching algorithm and a main body association algorithm of the performance index mode.
8. The method of claim 6, wherein the plug-in layer is used to provide the bottleneck analysis plug-in; the bottleneck analysis plug-in includes:
a bottleneck analysis plug-in for a first object, the first object comprising: CPU, memory, network and I/O; and a bottleneck analysis plug-in for a second object, the second object comprising: operating systems, databases, middleware, system architectures, and algorithms.
9. The method of claim 6, wherein the interface layer is configured to provide an external interface for performance bottleneck analysis, comprising: the interface of strategy analysis management, the interface of bottleneck analysis result output presentation, and the interface of manual interactive operation.
10. A multi-dimensional cross-space-time basic software performance bottleneck detection device is applied to a performance bottleneck diagnostic analysis tool, and comprises:
the system comprises a construction module, a first performance index mode and a second performance index mode, wherein the construction module is used for constructing a first performance index mode under an empty load operation system and a second performance index mode under different load operation systems;
a matching module to determine a similarity between the first and second performance indicator patterns based on a commonality matching algorithm;
the extracting module is used for extracting a performance index mode with the similarity smaller than a preset similarity threshold from the first performance index mode and the second performance index mode according to a similarity comparison result, and taking the extracted performance index mode as a bottleneck correlation mode;
and the analysis module is used for performing performance bottleneck analysis on the bottleneck correlation mode.
11. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory for storing the processor-executable instructions;
the processor is used for reading the executable instructions from the memory and executing the instructions to realize the multi-dimensional cross-space-time base software performance bottleneck detection method of any one of the claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110893397.1A CN113656292B (en) | 2021-08-04 | 2021-08-04 | Multi-dimensional cross-space-time basic software performance bottleneck detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110893397.1A CN113656292B (en) | 2021-08-04 | 2021-08-04 | Multi-dimensional cross-space-time basic software performance bottleneck detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113656292A true CN113656292A (en) | 2021-11-16 |
CN113656292B CN113656292B (en) | 2022-05-17 |
Family
ID=78478382
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110893397.1A Active CN113656292B (en) | 2021-08-04 | 2021-08-04 | Multi-dimensional cross-space-time basic software performance bottleneck detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113656292B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114355171A (en) * | 2022-03-15 | 2022-04-15 | 江苏清微智能科技有限公司 | Reconfigurable chip performance bottleneck detection platform, detection method and electronic equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006527937A (en) * | 2003-06-18 | 2006-12-07 | コニンクリーケ・ケイピーエヌ・ナムローゼ・フェンノートシャップ | Method and system for analyzing data quality measurements in a wireless data communication network |
CN102981952A (en) * | 2012-11-06 | 2013-03-20 | 无锡江南计算技术研究所 | Procedure performance analysis method based on target machine |
US20150227446A1 (en) * | 2012-09-25 | 2015-08-13 | Nec Corporation | Bottleneck detection device, method and recording medium storing program |
CN109117354A (en) * | 2018-08-29 | 2019-01-01 | 郑州云海信息技术有限公司 | A kind of host side influence storage performance because of vegetarian refreshments automatic analysis method and device |
CN111143179A (en) * | 2019-12-24 | 2020-05-12 | 中信银行股份有限公司 | Method, device, storage medium and electronic equipment for positioning performance bottleneck |
CN111190832A (en) * | 2020-01-06 | 2020-05-22 | 成都库珀区块链科技有限公司 | Method, device and system for positioning and optimizing performance bottleneck |
CN112506754A (en) * | 2020-12-13 | 2021-03-16 | 国网河北省电力有限公司雄安新区供电公司 | System performance monitoring method and platform |
-
2021
- 2021-08-04 CN CN202110893397.1A patent/CN113656292B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006527937A (en) * | 2003-06-18 | 2006-12-07 | コニンクリーケ・ケイピーエヌ・ナムローゼ・フェンノートシャップ | Method and system for analyzing data quality measurements in a wireless data communication network |
US20150227446A1 (en) * | 2012-09-25 | 2015-08-13 | Nec Corporation | Bottleneck detection device, method and recording medium storing program |
CN102981952A (en) * | 2012-11-06 | 2013-03-20 | 无锡江南计算技术研究所 | Procedure performance analysis method based on target machine |
CN109117354A (en) * | 2018-08-29 | 2019-01-01 | 郑州云海信息技术有限公司 | A kind of host side influence storage performance because of vegetarian refreshments automatic analysis method and device |
CN111143179A (en) * | 2019-12-24 | 2020-05-12 | 中信银行股份有限公司 | Method, device, storage medium and electronic equipment for positioning performance bottleneck |
CN111190832A (en) * | 2020-01-06 | 2020-05-22 | 成都库珀区块链科技有限公司 | Method, device and system for positioning and optimizing performance bottleneck |
CN112506754A (en) * | 2020-12-13 | 2021-03-16 | 国网河北省电力有限公司雄安新区供电公司 | System performance monitoring method and platform |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114355171A (en) * | 2022-03-15 | 2022-04-15 | 江苏清微智能科技有限公司 | Reconfigurable chip performance bottleneck detection platform, detection method and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN113656292B (en) | 2022-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8315960B2 (en) | Experience transfer for the configuration tuning of large scale computing systems | |
CN105283851A (en) | Cost analysis for selecting trace objectives | |
CN105283866A (en) | Optimization analysis using similar frequencies | |
JP7000766B2 (en) | Training data selection program, training data selection method, and training data selection device | |
CN105283848A (en) | Application tracing by distributed objectives | |
He et al. | Parallel implementation of classification algorithms based on MapReduce | |
CN110727943B (en) | Intrusion detection method and device | |
JP7071624B2 (en) | Search program, search method and search device | |
Chen et al. | Experience transfer for the configuration tuning in large-scale computing systems | |
US20070233532A1 (en) | Business process analysis apparatus | |
US8245084B2 (en) | Two-level representative workload phase detection | |
Mohr et al. | The HOPSA workflow and tools | |
CN113656292B (en) | Multi-dimensional cross-space-time basic software performance bottleneck detection method | |
CN111768247A (en) | Order-placing rate prediction method, device and readable storage medium | |
CN108628678B (en) | Method, device and equipment for determining memory parameters | |
US7512519B2 (en) | Run-time characterization of on-demand analytical model accuracy | |
CN115147020B (en) | Decoration data processing method, device, equipment and storage medium | |
CN115629883A (en) | Resource prediction method, resource prediction device, computer equipment and storage medium | |
Ehrenstein | Scalability evaluation of explorviz with the universal scalability law | |
CN117716350A (en) | Linking Bloom filters to estimate the number of keys in a dataset that have low frequencies | |
CN113656391A (en) | Data detection method and device, storage medium and electronic equipment | |
JP2003196125A (en) | Performance evaluation information management device, performance evaluation device, performance evaluation information management method, performance evaluation method, storage medium and program | |
EP3671467A1 (en) | Gui application testing using bots | |
Vijayakumar et al. | Predicting jvm parameters for performance tuning using different regression algorithms | |
US8010477B2 (en) | Integrated problem solving system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |