Performance tuning methods and cloud management platforms for cloud services

Abstract

The present application provides a method for performance tuning of cloud services and a cloud management platform, the method comprising: a cloud management platform receives a performance tuning experience model for a first cloud service uploaded by a first tenant, the performance tuning experience model is used to indicate a corresponding relationship between a set of indicator types and a plurality of indicator alarm threshold ranges corresponding to each indicator type in the set of indicator types and the causes of performance problems and tuning solutions, the cloud management platform collects first operating indicator data of a second cloud service of a second tenant including each indicator type in the set of indicator types, the cloud management platform inputs the first operating indicator data into the performance tuning experience model of the first cloud service, obtains the causes of performance problems and tuning solutions for the second cloud service, and the cloud management platform provides the second tenant with the causes of performance problems and tuning solutions for the second cloud service. Tenants of the present application can share performance tuning experience models related to cloud services with each other.

Description

Technical Field

[0001] The present application relates to the field of cloud technology, and in particular to a method for performance tuning of cloud services and a cloud management platform. Background Art

[0002] With the widespread application of cloud technology, more and more corporate tenants have deployed their businesses on the cloud. The number of corporate tenants served by major cloud vendors continues to grow. The continuous expansion of corporate tenants' businesses has also led to a continuous improvement in the utilization rate of cloud resources.

[0003] When enterprise tenant businesses are running in the cloud, some performance issues may arise that require tuning. The same performance issues generated by various cloud businesses require repeated manual search for tuning solutions, which results in low tuning efficiency and affects the business operations of enterprise tenants. Summary of the invention

[0004] The present application provides a method for performance tuning of cloud services and a cloud management platform, where tenants can share performance tuning experience models related to cloud services with each other, thereby improving the tuning efficiency of similar performance issues of cloud services.

[0005] In a first aspect, the present application provides a method for performance tuning of a cloud service, which is applied to a cloud management platform, the cloud management platform is used to manage infrastructure, the infrastructure supports the operation of multiple cloud services, the multiple cloud services include a first cloud service and a second cloud service, the first cloud service belongs to a first tenant, and the second cloud service belongs to a second tenant, the method includes: the cloud management platform receives a performance tuning experience model for the first cloud service uploaded by the first tenant, the performance tuning experience model is used to indicate the correspondence between an indicator type set and a plurality of indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and the causes of performance problems and tuning solutions, the cloud management platform collects first operating indicator data of each indicator type in the indicator type set for the second cloud service of the second tenant, the cloud management platform inputs the first operating indicator data into the performance tuning experience model of the first cloud service, obtains the causes of performance problems and tuning solutions for the second cloud service, and the cloud management platform provides the causes of performance problems and tuning solutions for the second cloud service to the second tenant.

[0006] Based on the above method, the first tenant can upload the performance tuning experience model for the first cloud service to the cloud management platform. When the second tenant encounters a performance problem similar to that of the first tenant, the cloud management platform collects the operating indicator data of the second tenant's second cloud service and inputs it into the performance tuning experience model of the first cloud service. The cause of the performance problem and the tuning plan of the second cloud service can be quickly obtained. Tenants can share performance tuning experience models related to cloud services with each other, thereby improving the tuning efficiency of similar performance problems of cloud services.

[0007] In a possible implementation of the first aspect, before the cloud management platform collects the first operating indicator data of the second cloud service of the second tenant, including each indicator type in the indicator type set, the method also includes: the cloud management platform provides the second tenant with a performance tuning experience model of the first cloud service.

[0008] Based on the above method, the performance tuning experience model related to the first cloud business of the first tenant can be shared with the second tenant, so that the second tenant can find the cause of the performance problem and the tuning solution for the second cloud business.

[0009] In a possible implementation of the first aspect, the cloud management platform provides the performance tuning experience model of the first cloud service to the data trading market, and receives fee payment information for the performance tuning experience model of the first cloud service input by the second tenant, and the cloud management platform provides the performance tuning experience model of the first cloud service to the second tenant, including: the cloud management platform provides the performance tuning experience model of the first cloud service to the second tenant based on the fee payment information.

[0010] Based on the above method, the second tenant obtains the performance tuning experience model of the first tenant by paying a certain fee to the first tenant. The transaction can increase the enthusiasm of tenants to upload the performance tuning experience model.

[0011] In a possible implementation of the first aspect, the multiple cloud services also include a third cloud service, and the third cloud service belongs to a third tenant. The method also includes: the cloud management platform collects second operating indicator data of the third cloud service of the third tenant, including each indicator type in the indicator type set, the cloud management platform inputs the second operating indicator data into the performance tuning experience model of the first cloud service, obtains the causes of performance problems and tuning solutions of the third cloud service, and the cloud management platform provides the causes of performance problems and tuning solutions of the third cloud service to the third tenant.

[0012] Based on the above method, when the third tenant encounters a performance problem similar to that of the first tenant, the cloud management platform collects the operating indicator data of the third tenant's third cloud business and inputs it into the performance tuning experience model of the first cloud business. The cause of the performance problem and the tuning plan of the third cloud business can be quickly obtained. Tenants can share cloud business-related performance tuning experience models with each other, thereby improving the tuning efficiency of similar performance problems of cloud businesses.

[0013] In a possible implementation manner of the first aspect, the cloud management platform records the performance tuning experience model of the first cloud service in a knowledge base.

[0014] Based on the above method, the cloud management platform records the performance tuning experience model for the first cloud service uploaded by the first tenant in the knowledge base. Tenants can share performance tuning experience models of similar cloud services through the knowledge base without manual tuning, making cloud service performance tuning more convenient.

[0015] In a possible implementation of the first aspect, the multiple cloud services also include a fourth cloud service, and the fourth cloud service belongs to a fourth tenant. The method also includes: the cloud management platform receives a performance tuning experience model for the fourth cloud service uploaded by the fourth tenant, the cloud management platform records the performance tuning experience model for the fourth cloud service in a knowledge base, and the cloud management platform shares the performance tuning experience model in the knowledge base when preset conditions are met.

[0016] Based on the above method, the fourth tenant can upload the performance tuning experience model for the fourth cloud business to the cloud management platform. When other tenants encounter similar performance problems as the fourth tenant, they can refer to the performance tuning experience model of the fourth tenant, thereby achieving mutual learning of performance tuning experience among multiple tenants and improving the accuracy and speed of cloud business performance tuning.

[0017] In a possible implementation manner of the first aspect, the first cloud service includes an elastic cloud service, a cloud hard disk service, a virtual private cloud service, a cloud database service, or a distributed cache service.

[0018] Based on the above method, the performance tuning experience model involves a variety of cloud services, ensuring the comprehensive coverage of the cloud service performance tuning model.

[0019] In a possible implementation manner of the first aspect, the indicator type includes a hardware indicator, a virtual machine configuration indicator, a microarchitecture indicator, a kernel indicator, a resource occupancy rate indicator, or a typical application configuration indicator.

[0020] Based on the above method, the performance tuning experience model is used to indicate the correspondence between the indicator type set and the multiple indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and the causes of performance problems and tuning solutions. The performance tuning model involves multiple indicator types, which can quickly and accurately determine the causes of performance problems and their corresponding tuning solutions.

[0021] In the second aspect, the present application provides a cloud management platform, which is used to manage network infrastructure, and the infrastructure supports the operation of multiple cloud services, including a first cloud service and a second cloud service, and the cloud management platform includes: a model receiving module, a model transaction module, a model providing module, a data collection module, a solution acquisition module, and a solution providing module. Among them, the model receiving module is used to receive the performance tuning experience model for the first cloud service uploaded by the first tenant, the performance tuning experience model is used to indicate the corresponding relationship between the indicator type set and the multiple indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and the performance problem cause and the tuning solution, the data collection module is used to collect the first operation indicator data of the second cloud service of the second tenant, including each indicator type in the indicator type set, the solution acquisition module is used to input the first operation indicator data into the performance tuning experience model of the first cloud service, obtain the performance problem cause and the tuning solution of the second cloud service, and the solution providing module is used to provide the performance problem cause and the tuning solution of the second cloud service to the second tenant.

[0022] The second aspect or any implementation of the second aspect is an implementation of the device corresponding to the first aspect or any implementation of the first aspect. The description in the first aspect or any implementation of the first aspect is applicable to the second aspect or any implementation of the second aspect and will not be repeated here.

[0023] In a third aspect, the present application provides a computing device cluster, comprising at least one computing device, each computing device comprising a processor and a memory; the processor of at least one computing device is used to execute instructions stored in the memory of at least one computing device, so that the computing device cluster implements the method disclosed in the first aspect and any possible implementation manner of the first aspect.

[0024] In a fourth aspect, the present application provides a computer program product comprising instructions, which, when executed by a computer device cluster, enables the computer device cluster to implement the method disclosed in the first aspect and any possible implementation manner of the first aspect.

[0025] In a fifth aspect, the present application provides a computer-readable storage medium, comprising computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method disclosed in the first aspect and any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic diagram of the system architecture of a method for performance tuning of cloud services according to an embodiment of the present invention;

[0027] Figure 2 is a flow chart of a method for optimizing cloud service performance according to an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of a performance tuning process for cloud services according to an embodiment of the present invention;

[0029] Figure 4 It is a schematic diagram of the internal structure of the cloud management platform according to an embodiment of the present invention;

[0030] Figure 5 It is a schematic diagram of the computing device structure of the method for performance tuning of cloud services according to an embodiment of the present invention;

[0031] Figure 6 It is a structural diagram of a computing device cluster of a method for performance tuning of cloud services according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] In order to facilitate understanding of the embodiments of the present application, first, some terms involved in the present invention are explained.

[0034] Cloud management platform: The cloud management platform is used to manage multiple cloud data centers set up by cloud vendors in different regions. The cloud management platform can provide interfaces related to public cloud services, such as pages or application program interfaces (APIs) for tenants to remotely access public cloud services. Tenants can log in to the cloud management platform on the public cloud access page using a pre-registered account and password, and after a successful login, select and purchase public cloud services provided by the cloud data center in the area selected by the tenant on the public cloud access page, such as object storage services, virtual machine services, container services, etc.

[0035] Elastic Cloud Server: An Elastic Cloud Server (ECS) is a computing server that can be obtained at any time and can be elastically scalable on the cloud. In the embodiment of the present invention, the scheduling node is an elastic cloud server, which can be implemented by a virtual machine.

[0036] Cloud disk service: also known as Elastic Volume Service (EVS), is a service that provides persistent block storage for computing services. It provides high availability and persistence, as well as stable low-latency performance through multiple technologies such as data redundancy and cache acceleration. Tenants can format cloud disks, create file systems, and perform other operations on persistent data storage.

[0037] Virtual Private Cloud: Virtual Private Cloud (VPC) is an isolated, private virtual network environment applied by users on the cloud.

[0038] An embodiment of the present invention provides a method for performance tuning of a cloud service. The method is applied to a cloud management platform. The cloud management platform is used to manage an infrastructure. The infrastructure supports the operation of multiple cloud services. The multiple cloud services include a first cloud service and a second cloud service. The first cloud service belongs to a first tenant, and the second cloud service belongs to a second tenant. The method includes:

[0039] The cloud management platform receives a performance tuning experience model for the first cloud service uploaded by the first tenant, where the performance tuning experience model is used to indicate a corresponding relationship between an indicator type set and a plurality of indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and a performance problem cause and a tuning solution;

[0040] The cloud management platform collects first operating indicator data of each indicator type in the indicator type set for the second cloud service of the second tenant;

[0041] The cloud management platform inputs the first operating indicator data into the performance tuning experience model of the first cloud service, obtains the performance problem cause and tuning solution of the second cloud service, and provides the performance problem cause and tuning solution of the second cloud service to the second tenant.

[0042] Based on the above method, the first tenant can upload the performance tuning experience model for the first cloud service to the cloud management platform. When the second tenant encounters a performance problem similar to that of the first tenant, the cloud management platform collects the operating indicator data of the second tenant's second cloud service and inputs it into the performance tuning experience model of the first cloud service. The cause of the performance problem and the tuning plan of the second cloud service can be quickly obtained. Tenants can share performance tuning experience models related to cloud services with each other, thereby improving the tuning efficiency of similar performance problems of cloud services.

[0043] The above solution will be further explained below. It should be noted that the specific embodiments below are specific implementations based on the overall concept of the above solution.

[0044] See below Figure 1 , Figure 1It is a schematic diagram of the system architecture of a method for performance tuning of cloud services according to an embodiment of the present invention. Figure 1 In the illustrated embodiment, tenant A and tenant B access the cloud management platform 10 through client A and client B via the Internet 30, respectively. The cloud management platform 10 is used to manage infrastructure, and the infrastructure includes multiple regions: region 1, region 2...region N, and each regional center includes multiple cloud data centers: cloud data center A, cloud data center B, cloud data center C... The cloud system includes the cloud management platform 10 and multiple regions managed by the cloud management platform 10. Multiple cloud services run on multiple cloud data centers in multiple regions, for example: cloud service A belonging to tenant A and cloud service B belonging to tenant B run on cloud data center A in region 1 at the same time, or cloud service A belonging to tenant A runs on cloud data center A in region 1, and cloud service B belonging to tenant B runs on cloud data center B in region 1, and cloud service A belonging to tenant A runs on cloud data center A in region 1, and cloud service B belonging to tenant B runs on cloud data center A in region 2.

[0045] It should be noted that the above-mentioned types of cloud services include but are not limited to elastic cloud services, cloud hard disk services, virtual private cloud services, cloud database services or distributed cache services and other cloud services developed by cloud vendors.

[0046] Based on the above system architecture, the method for optimizing the performance of cloud services is further disclosed in the embodiment of the present invention. For details, see the following:

[0047] See below Figure 2 , Figure 2 1 is a flow chart of a method for optimizing cloud service performance according to an embodiment of the present invention. The method includes:

[0048] S101: Tenant A logs in to the cloud management platform 10 through client A and sends the cloud service A performance tuning experience model;

[0049] For example, tenant A registers an exclusive account on the cloud management platform 10 through client A, and then logs in to the cloud management platform 10 by logging in to the account. Tenant A can purchase cloud service A on the cloud management platform 10. During the operation of cloud service A, some problems may be encountered that require optimization and adjustment. These tuning experiences can be recorded in the form of models, and tenant A can upload the performance tuning experience model for cloud service A to the cloud management platform for storage.

[0050] For example, tenant A purchased a distributed cache service on the cloud management platform 10, which is mostly used in live broadcast services. During the live broadcast, tenant A encountered performance problems such as screen freeze, data loss, and connection timeout. By seeking help from professionals on the cloud management platform 10, the professionals found that the alarm indicators for the above performance problems include UDP receive errors (udp_recv_errors), UDP send errors (udp_send_errors), and UDP input errors (udp_in errors). At the same time, the data results of the two indicators, network traffic (network_pps) and network bandwidth (network_bandwidth), also show abnormalities. After analysis, the above performance problems are caused by User Datagram Protocol (UDP) buffer overflow. Therefore, the above tuning process forms a UDP tuning experience model in the live broadcast service. Tenant A can upload the UDP tuning experience model to the cloud management platform. When tenant A encounters the above performance problems again, he can directly enter the problem into the UDP tuning experience model to find a tuning solution without repeatedly requiring manual processing.

[0051] S102: The cloud management platform 10 receives the performance tuning experience model of cloud service A;

[0052] For example, the cloud management platform 10 receives a performance tuning experience model about cloud service A uploaded by tenant A, and with the authorization of tenant A, stores the performance tuning experience model in a knowledge base and provides it to the data trading market.

[0053] Specifically, the performance tuning experience model is used to indicate the relationship between the indicator type set and the multiple indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and the causes of performance problems and tuning solutions. Figure 3 As shown, Figure 3 FIG. 1 is a schematic diagram of a performance tuning process for cloud services according to an embodiment of the present invention. Figure 3As shown in the figure, during the performance tuning process, we first need to define the indicator type to form an indicator set (indicator 1, indicator 2…indicator 7). Secondly, we need to set the alarm threshold range for each indicator to form an alarm set (level 1 alarm, level 2 alarm, level 3 alarm). Then, we need to form a model set (model 1, model 2, model 3) based on different indicators and their alarm levels. Finally, we need to input the problem into the model to obtain a solution set (solution 1, solution 2, solution 3). For example, in response to the central processing unit (CPU) soft interrupt problem encountered by tenants, two indicator types, CPU soft interrupt occupancy rate and CPU soft interrupt inter-core balance, are defined. When the CPU soft interrupt occupancy rate is greater than 1, a level 1 alarm is generated; when the CPU soft interrupt occupancy rate is greater than 0.9, a level 2 alarm is generated; and when the CPU soft interrupt occupancy rate is greater than 0.8, a level 3 alarm is generated. The alarms generated for the CPU soft interrupt occupancy rate and the CPU soft interrupt inter-core balance are analyzed, and it is found that the cause of the performance problem is that the CPU interrupt imbalance causes a single-core soft interrupt surge. Finally, the solution is CPU interrupt balance optimization. If tenants encounter CPU soft interrupt problems in the future, they can directly input the CPU interrupt imbalance model to obtain a CPU interrupt balance tuning plan.

[0054] S103: Tenant B logs in to the cloud management platform 10 through client B and pays for the performance tuning experience model of cloud service A;

[0055] Similarly, tenant B registers an exclusive account on the cloud management platform 10 through client B, and then logs in to the cloud management platform 10 by logging in to the account. Tenant B can purchase cloud service B on the cloud management platform 10. During the operation of cloud service B, some problems are encountered that need to be optimized and adjusted. Tenant B can directly search for the same problem in the knowledge base provided on the cloud management platform 10. When the search results show that tenant A has uploaded a performance tuning experience model for the same problem, tenant B can purchase tenant A's performance tuning experience model for cloud service A in the data trading market.

[0056] S104: The cloud management platform 10 receives payment information for the cloud service A performance tuning experience model, and provides the cloud service A performance tuning experience model to tenant B;

[0057] The cloud management platform 10 receives the fee information paid by tenant B for the cloud service A performance tuning experience model, and displays the fee paid by tenant B in tenant A's account, and provides tenant B with the cloud service A performance tuning experience model in the knowledge base.

[0058] It should be noted that tenant A can arbitrarily set the price for obtaining the performance tuning experience model for cloud business A. When the price is set to 0, it means that tenant A is willing to provide the tuning experience model to the knowledge base for free for other tenants to use. At the same time, the fee paid by tenant B to tenant A can be real currency or virtual currency.

[0059] For example, tenant A sets the price for obtaining the performance tuning experience model of cloud service A to 50 cloud coins. Tenant B recharges 100 cloud coins on the cloud management platform 10 through client B. When tenant B purchases tenant A's performance tuning experience model for cloud service A, tenant B needs to pay 50 cloud coins to tenant A. The 50 cloud coins obtained by tenant A can be used to purchase tuning experience models of other users. Through the above transaction rules, the tuning experience models of multiple tenants can form a mechanism for mutual sharing.

[0060] S105: The cloud management platform 10 collects the operating indicator data of cloud service B and inputs it into the performance tuning model of cloud service A to obtain the cause of the performance problem of cloud service B and the tuning solution;

[0061] For example, since the cloud service B purchased by tenant B has the same problem as the cloud service A purchased by tenant A, the cloud management platform 10 can obtain the cause of the performance problem and the tuning plan of cloud service B by collecting the operating indicator data of cloud service B and inputting it into the performance tuning model of cloud service A. Tenant B does not need to seek help from professionals on the cloud management platform 10.

[0062] S106: The cloud management platform 10 provides tenant B with the causes of the performance issues of cloud service B and optimization solutions.

[0063] For example, the cloud management platform 10 obtains the cause of the performance problem of tenant B's cloud service B and the tuning solution by referring to tenant A's performance tuning model and provides it to tenant B.

[0064] Similarly, when tenant C encounters the same problem as cloud service A purchased by tenant A in cloud service C purchased on cloud management platform 10 through client C, tenant C can also purchase tenant A's performance tuning experience model on the trading platform provided by cloud management platform 10. Cloud management platform 10 obtains the cause of performance problem of tenant C's cloud service C and tuning solution by referring to tenant A's performance tuning model and provides them to tenant C. At the same time, tenant D can also upload performance tuning experience for cloud service D on cloud management platform 10 through client D, thereby realizing a mode of multi-tenant sharing of performance tuning models on the cloud management platform.

[0065] The knowledge base of performance tuning experience models in the cloud management platform 10 will become richer as tenants continue to share. At the same time, the cloud management platform 10 will continuously optimize the performance tuning experience models in the knowledge base, eliminate erroneous or outdated performance tuning experience models, and sort the performance tuning experience models according to the search frequency of tenants, put popular tuning experience models at the top, and label the tuning experience models shared by tenants for free to facilitate tenant searches.

[0066] It should be noted that when a tenant searches for an optimization experience model in the knowledge base, the search results may not exist. In this case, the tenant can still seek help from professionals on the cloud management platform 10 to perform manual tuning to ensure the normal operation of the cloud business.

[0067] The performance tuning method for cloud services disclosed in the embodiment of the present invention enables tenants to upload performance tuning experience models related to cloud services to a cloud management platform for sharing. Tenants can refer to each other's performance tuning experience models, and there is no need to repeatedly seek manual solutions to the same performance issues, thereby improving the tuning efficiency of the same performance issues of cloud services.

[0068] According to the above performance tuning method for cloud services, the embodiment of the present invention further discloses the internal structure of the cloud management platform, as shown below:

[0069] See below Figure 4 , Figure 4 1 is a schematic diagram of the internal structure of the cloud management platform of an embodiment of the present invention. The cloud management platform is used to manage network infrastructure, and the infrastructure supports the operation of multiple cloud services, and the multiple cloud services include a first cloud service and a second cloud service, and the first cloud service belongs to the first tenant, and the second cloud service belongs to the second tenant. The cloud management platform includes: a model receiving module 101, a model transaction module 102, a model providing module 103, a data collection module 104, a solution acquisition module 105, and a solution providing module 106. Among them:

[0070] The model receiving module 101 is used to receive a performance tuning experience model for a first cloud service uploaded by a first tenant, and record the performance tuning experience model of the first cloud service in a knowledge base, wherein the performance tuning experience model is used to indicate a corresponding relationship between an indicator type set and a plurality of indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and a performance problem cause and a tuning solution;

[0071] The model trading module 102 is used to provide the performance tuning experience model of the first cloud service to the data trading market, and receive the fee payment information of the performance tuning experience model for the first cloud service input by the second tenant;

[0072] A model providing module 103 is used to provide the second tenant with a performance tuning experience model of the first cloud service based on the fee payment information;

[0073] The data collection module 104 is used to collect the first operation indicator data of each indicator type in the indicator type set of the second cloud service of the second tenant;

[0074] Solution acquisition module 105, used for inputting the first operation indicator data into the performance tuning experience model of the first cloud service to obtain the performance problem cause and tuning solution of the second cloud service;

[0075] The solution providing module 106 is used to provide the second tenant with the cause of the performance problem of the second cloud service and a tuning solution.

[0076] At the same time, the multiple cloud services also include a third cloud service, which belongs to a third tenant. The data collection module 104 is also used to collect the second operating indicator data of the third cloud service of the third tenant, including each indicator type in the indicator type set; the solution acquisition module 105 is also used to input the second operating indicator data into the performance tuning experience model of the first cloud service to obtain the causes of performance problems and tuning solutions for the second cloud service; the solution providing module 106 is also used to provide the causes of performance problems and tuning solutions for the third cloud service to the third tenant.

[0077] In addition, the multiple cloud services also include a fourth cloud service, which belongs to a fourth tenant. The model receiving module 101 is also used to receive a performance tuning experience model for the fourth cloud service uploaded by the fourth tenant, and record the performance tuning experience model for the fourth cloud service in the knowledge base; the model providing module 103 is also used to share the performance tuning experience model in the knowledge base when preset conditions are met.

[0078] It should be noted that the model receiving module 101, the model transaction module 102, the model providing module 103, the data acquisition module 104, the solution acquisition module 105 and the solution providing module 106 can all be implemented by software, or can be implemented by hardware. Exemplarily, the implementation of the model receiving module 101 is introduced below by taking the model receiving module 101 as an example. Similarly, the implementation of the model transaction module 102, the model providing module 103, the data acquisition module 104, the solution acquisition module 105 and the solution providing module 106 can refer to the implementation of the model receiving module 101.

[0079] When implemented by software, the model receiving module 101 may be an application or a code block running on a computer device. The computer device may be at least one of a physical host, a virtual machine, a container, and other computing devices. Furthermore, the above-mentioned computer device may be one or more. For example, the model receiving module 101 may be an application running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the application may be distributed in the same availability zone (AZ) or in different AZs. The multiple hosts / virtual machines / containers used to run the application may be distributed in the same region or in different regions. Typically, a region may include multiple AZs.

[0080] Similarly, multiple hosts / virtual machines / containers for running the application can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Typically, a region can include multiple VPCs, and a VPC can include multiple AZs.

[0081] When implemented by hardware, the model receiving module 101 may include at least one computing device, such as a server, etc. Alternatively, the model receiving module 101 may also be a device implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), etc. The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0082] The multiple computing devices included in the model receiving module 101 can be distributed in the same AZ or in different AZs. The multiple computing devices included in the model receiving module 101 can be distributed in the same region or in different regions. Similarly, the multiple computing devices included in the model receiving module 101 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0083] It should be noted that any module among the model receiving module 101, the model trading module 102, the model providing module 103, the data collection module 104, the solution acquisition module 105 and the solution providing module 106 can be used to execute part or all of the steps in the configuration method of the cloud connection service based on the public cloud.

[0084] The various modules of the cloud management platform 10 disclosed in the embodiment of the present invention have clear division of labor and close cooperation. The various modules cooperate with each other to efficiently complete the performance tuning of cloud services.

[0085] The present invention also provides a computing device, see below Figure 5 , Figure 5 1 is a schematic diagram of the computing device structure of the method for performance tuning of cloud services according to an embodiment of the present invention. The computing device 100 includes: a bus 107, a processor 109, a memory 108, and a communication interface 110. The processor 109, the memory 108, and the communication interface 110 communicate with each other via the bus 107. The computing device 100 may be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computing device 100.

[0086] The bus 107 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus 107 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 107 may include a path for transmitting information between various components of the computing device 100 (eg, the memory 108, the processor 109, and the communication interface 110).

[0087] The processor 109 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0088] The memory 108 may include a volatile memory, such as a random access memory (RAM). The processor 109 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0089] The memory 108 stores executable program codes, and the processor 109 executes the executable program codes to respectively implement the functions of the aforementioned model receiving module 101, the model transaction module 102, the model providing module 103, the data acquisition module 104, the solution acquisition module 105, and the solution providing module 106, thereby implementing the configuration method of the cloud connection service based on the public cloud. That is, the memory 108 stores instructions for the cloud management platform to execute the configuration method of the cloud connection service based on the public cloud.

[0090] The communication interface 110 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 100 and other devices or a communication network.

[0091] An embodiment of the present invention further provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device may be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device may also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0092] See below Figure 6 , Figure 6 The present invention is a schematic diagram of a computing device cluster for a method for performance tuning of cloud services according to an embodiment of the present invention. The computing device cluster includes at least one computing device 100. The memory 108 in one or more computing devices 100 in the computing device cluster may store the same cloud management platform for executing instructions of a configuration method for a cloud connection service based on a public cloud.

[0093] In some possible implementations, one or more computing devices 100 in the computing device cluster may also be used to execute some instructions of the cloud management platform for executing the configuration method of the cloud connection service based on the public cloud. In other words, the combination of one or more computing devices 100 may jointly execute the instructions of the cloud management platform for executing the configuration method of the cloud connection service based on the public cloud.

[0094] It should be noted that the memory 108 in different computing devices 100 in the computing device cluster may store different instructions for executing some functions of the cloud management platform. That is, the instructions stored in the memory 108 in different computing devices 100 may implement the functions of one or more modules among the model receiving module 101, the model transaction module 102, the model providing module 103, the data collection module 104, the solution acquisition module 105 and the solution providing module 106.

[0095] The embodiment of the present invention also provides a computer program product including instructions. The computer program product may be software or a program product including instructions that can be run on a computing device or stored in any available medium. When the computer program product is run on at least one computer device, the at least one computer device executes the configuration method for the cloud management platform to execute a cloud connection service based on a public cloud.

[0096] An embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned configuration method applied to a cloud management platform for executing a cloud connection service based on a public cloud.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for performance tuning of cloud services, characterized in that: The method is applied to a cloud management platform, the cloud management platform is used to manage infrastructure, the infrastructure supports the operation of multiple cloud services, the multiple cloud services include a first cloud service and a second cloud service, the first cloud service belongs to a first tenant, and the second cloud service belongs to a second tenant, the method includes: The cloud management platform receives a performance tuning experience model for the first cloud service uploaded by the first tenant, where the performance tuning experience model is used to indicate a corresponding relationship between an indicator type set and a plurality of indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and a performance problem cause and a tuning solution; The cloud management platform collects first operation indicator data of each indicator type in the indicator type set of the second cloud service of the second tenant; The cloud management platform inputs the first operating indicator data into the performance tuning empirical model of the first cloud service to obtain the cause of the performance problem and the tuning solution of the second cloud service; The cloud management platform provides the second tenant with the cause of the performance problem of the second cloud service and a tuning solution.

2. The method according to claim 1, characterized in that Before the cloud management platform collects the first operating indicator data of each indicator type in the indicator type set for the second cloud service of the second tenant, the method further includes: The cloud management platform provides the second tenant with a performance tuning empirical model of the first cloud service.

3. The method according to claim 2, characterized in that The method further comprises: The cloud management platform provides the performance tuning experience model of the first cloud service to the data trading market, and receives the fee payment information for the performance tuning experience model of the first cloud service input by the second tenant; then The cloud management platform provides the second tenant with a performance tuning empirical model of the first cloud service, including: The cloud management platform provides the second tenant with a performance tuning empirical model of the first cloud service based on the fee payment information.

4. The method according to any one of claims 1 to 3, characterized in that: The multiple cloud services further include a third cloud service, and the third cloud service belongs to a third tenant. The method further includes: The cloud management platform collects second operation indicator data of each indicator type in the indicator type set of the third cloud service of the third tenant; The cloud management platform inputs the second operating indicator data into the performance tuning experience model of the first cloud service to obtain the cause of the performance problem and the tuning solution of the third cloud service; The cloud management platform provides the third tenant with the cause of the performance problem of the third cloud service and a tuning solution.

5. The method according to any one of claims 1 to 3, characterized in that: The method also includes: the cloud management platform recording the performance tuning experience model of the first cloud service in a knowledge base.

6. The method according to claim 5, characterized in that The plurality of cloud services further include a fourth cloud service, the fourth cloud service belongs to a fourth tenant, and the method further includes: The cloud management platform receives a performance tuning experience model for the fourth cloud service uploaded by the fourth tenant; The cloud management platform records the performance tuning experience model of the fourth cloud service in the knowledge base; The cloud management platform shares the performance tuning experience model in the knowledge base when preset conditions are met.

7. The method according to any one of claims 1 to 3, characterized in that: The first cloud service includes elastic cloud service, cloud hard disk service, virtual private cloud service, cloud database service or distributed cache service.

8. The method according to any one of claims 1 to 3, characterized in that: The indicator types include hardware indicators, virtual machine configuration indicators, micro-architecture indicators, kernel indicators, resource occupancy indicators or typical application configuration indicators.

9. A cloud management platform, characterized in that: The cloud management platform is used to manage a network infrastructure, the infrastructure supports the operation of multiple cloud services, the multiple cloud services include a first cloud service and a second cloud service, the first cloud service belongs to a first tenant, and the second cloud service belongs to a second tenant, and the cloud management platform includes: A model receiving module, the model receiving module is used to receive a performance tuning experience model for the first cloud service uploaded by the first tenant, the performance tuning experience model is used to indicate a corresponding relationship between an indicator type set and a plurality of indicator alarm threshold ranges corresponding to each indicator type in the indicator type set and a performance problem cause and a tuning solution; a data collection module, the data collection module being used to collect first operating indicator data of each indicator type in the indicator type set of the second cloud service of the second tenant; A solution acquisition module, the solution acquisition module is used to input the first operating indicator data into the performance tuning experience model of the first cloud service, and obtain the cause of the performance problem and the tuning solution of the second cloud service; A solution providing module is used to provide the second tenant with the cause of the performance problem of the second cloud service and a tuning solution.

10. The cloud management platform according to claim 9, characterized in that: Also includes: A model providing module is used to provide the performance tuning empirical model of the first cloud service to the second tenant before the data collection module collects the first operating indicator data of the second cloud service of the second tenant, including each indicator type in the indicator type set.

11. The cloud management platform according to claim 10, characterized in that: Also includes: The model trading module is used to provide the performance tuning experience model of the first cloud service to the data trading market, and receive the fee payment information for the performance tuning experience model of the first cloud service input by the second tenant; the model providing module is specifically used to provide the performance tuning experience model of the first cloud service to the second tenant based on the fee payment information.

12. The cloud management platform according to any one of claims 9 to 11, characterized in that: The multiple cloud services further include a third cloud service, and the third cloud service belongs to a third tenant, wherein: The data collection module is further used to collect second operation indicator data of each indicator type in the indicator type set of the third cloud service of the third tenant; The solution acquisition module is further used to input the second operation indicator data into the performance tuning experience model of the first cloud service to obtain the performance problem cause and tuning solution of the third cloud service; The solution providing module is also used to provide the third tenant with the cause of the performance problem of the third cloud service and a tuning solution.

13. The cloud management platform according to any one of claims 10-11, characterized in that: The model receiving module is further used to record the performance tuning experience model of the first cloud service in a knowledge base.

14. The cloud management platform according to claim 13, characterized in that: The plurality of cloud services further include a fourth cloud service, and the fourth cloud service belongs to a fourth tenant. The model receiving module is further used to receive a performance tuning experience model for the fourth cloud service uploaded by the fourth tenant; The model receiving module is further used to record the performance tuning experience model of the fourth cloud service in the knowledge base; The model providing module is also used to share the performance tuning experience model in the knowledge base when preset conditions are met.

15. The cloud management platform according to any one of claims 9 to 11, characterized in that: The first cloud service includes elastic cloud service, cloud hard disk service, virtual private cloud service, cloud database service or distributed cache service.

16. The cloud management platform according to any one of claims 9 to 11, characterized in that: The indicator types include hardware indicators, virtual machine configuration indicators, micro-architecture indicators, kernel indicators, resource occupancy indicators or typical application configuration indicators.

17. A computing device cluster, characterized in that: comprising at least one computing device, each computing device comprising a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method according to any one of claims 1 to 3.

18. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer device cluster, the computer device cluster executes the method according to any one of claims 1 to 3.

19. A computer-readable storage medium, characterized in that: The method comprises computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster performs the method according to any one of claims 1 to 3.

Images