CN116089069A

CN116089069A - Partition management method and device of super fusion architecture, electronic equipment and storage medium

Info

Publication number: CN116089069A
Application number: CN202211665859.5A
Authority: CN
Inventors: 潘晓东; 陈丽娜
Original assignee: Tianyi Cloud Technology Co Ltd
Current assignee: Tianyi Cloud Technology Co Ltd
Priority date: 2022-12-23
Filing date: 2022-12-23
Publication date: 2023-05-09

Abstract

The embodiment of the application provides a partition management method and device of a super fusion architecture, electronic equipment and a storage medium. The method comprises the following steps: dividing a CPU system into a supporting area and a service area according to service properties; collecting node load data of the super-fusion nodes in the supporting area under multiple dimensions; dividing the supporting area into a shared supporting area and an unshared supporting area according to the node load data; and planning service resources of the supporting area and the service area according to the total amount of resources corresponding to the shared supporting area and the exclusive supporting area respectively. According to the embodiment of the application, the service of the supporting area and the service of the service area can be logically isolated, so that the service quality is ensured, and meanwhile, the resource management and control of the supporting area are thinned, and the service quality of the supporting service is improved.

Description

Partition management method and device of super fusion architecture, electronic equipment and storage medium

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a partition management method and apparatus for a super fusion architecture, an electronic device, and a storage medium.

Background

Under the great background of rapid development of cloud computing, cloud computing products in various forms are rapidly increased, and the cloud computing system has a large-scale full-stack cloud platform and a small-scale fusion version cloud platform. Cloud platforms can be generally classified into 5 major categories of management, computation, storage, network, cloud management, etc., wherein management, storage, network, cloud management do not directly provide computing power for services, i.e. support systems, and computation directly provides computing power for services, referred to herein as service systems. In some small-medium-scale cloud platforms, 5 kinds of components are often subjected to fusion deployment to reduce consumption of resources, and the architecture is called a super fusion cloud architecture. In the super-fusion cloud architecture, resources among all components are frequently contended, so that the quality of cloud service is reduced, and the service cannot stably run.

In the current super-fusion cloud architecture, in order to reduce the pressure of a supporting area (including management, network, storage and cloud management) on a service system, a cgroup method is generally adopted to limit the use of CPU (Central Processing Unit ) resources, the area of the CPU which actually runs is not bound (for example, CN110489232A only limits the size of a memory, and does not bind the area) or is statically limited, thus resources of the supporting system and the service system are still caused, the resources are not completely isolated, and as the pressure of the system increases, the resources contend for robbing, the service class level decreases, and the service delivery quality is influenced. The method of limiting the resources of each module generally adopts the following two modes:

1. the global sharing fusion mode prescribes management (4 cores), cloud management (4 cores), network (4 cores), storage (4 cores) and calculation (16 cores), and all resources are shared in the super fusion node;

2. the static partition fusion mode is that 4 CPUs are used by management service and are respectively 0-3, 4 CPUs are used by cloud management service and are distributed in 4-7, 4 cores of network service are distributed in 8-12, 4 cores of storage service are distributed in 12-15, 16 cores of computing service are distributed in 16-31, and each service has own CPU use resource and is independent of each other and is not interfered with each other.

The global sharing fusion mode limits the total amount of the used resources of each service, but the resources can be maximally utilized by global allocation, but the mutual interference between the services cannot be eliminated, and particularly when the pressure is high, the quality of the key service cannot be ensured. Meanwhile, the total use amount of resources of each service is limited, so that required resources cannot be adjusted according to the actual situation of no operation, and the flexibility is poor.

The static partition fusion mode limits the total amount of resources used by each service, and simultaneously runs on the corresponding CPU, so that running interference among components can be eliminated, but resources cannot be utilized to the maximum extent. Meanwhile, the total use amount of resources of each service is statically limited, the required resources cannot be adjusted according to the actual situation of no operation, and the flexibility is poor.

Disclosure of Invention

The technical problem to be solved by the embodiments of the present application is to provide a partition management method, apparatus, electronic device and storage medium of a super-fusion architecture, so as to realize logical isolation between service of a support area and service of a service area, ensure service quality, and meanwhile refine resource management and control of the support area, and improve service quality of support service.

In a first aspect, an embodiment of the present application provides a partition management method of a super fusion architecture, where the method includes:

dividing a CPU system into a supporting area and a service area according to service properties;

collecting node load data of the super-fusion nodes in the supporting area under multiple dimensions;

dividing the supporting area into a shared supporting area and an unshared supporting area according to the node load data;

and planning service resources of the supporting area and the service area according to the total amount of resources corresponding to the shared supporting area and the exclusive supporting area respectively.

Optionally, the collecting node load data of the super-fusion node in the supporting area in multiple dimensions includes:

and acquiring node load data of the super-fusion node in multiple dimensions according to a set data acquisition period.

Optionally, the collecting node load data of the super-fusion node in multiple dimensions according to a set data collection period includes:

acquiring node load data of the super-fusion node in multiple dimensions according to the set data acquisition period by adopting a probe acquisition mode; or alternatively

And acquiring node load data of the super fusion node in multiple dimensions according to the set data acquisition period by adopting a set script.

Optionally, the dividing the supporting area into a shared supporting area and an unshared supporting area according to the node load data includes:

acquiring weights corresponding to a plurality of dimensions;

calculating a superscore function corresponding to the super fusion node according to the weight and the corresponding node load data;

and dividing the supporting area into the shared supporting area and the unshared supporting area according to the superdivision function.

Optionally, the planning the service resources of the supporting area and the service area according to the total amount of resources corresponding to the shared supporting area and the exclusive supporting area respectively includes:

determining the resource allocation amount of each support service in the support area according to the superdivision function;

according to the resource allocation amount and the superdivision function of each supporting service, respectively merging service resources in the exclusive supporting area and the shared supporting area to obtain the total shared resources of the shared supporting area and the total exclusive resources of the exclusive supporting area;

and planning service resources of the supporting area and the service area according to the total shared resources and the total exclusive resources.

Optionally, the planning the service resources of the support area and the service area according to the total shared resources and the total exclusive resources includes:

Determining the total resource amount corresponding to the supporting area according to the total shared resource amount and the exclusive resource amount;

distributing the CPU core number matched with the total resource amount in the CPU to the supporting area;

and distributing the CPU core numbers in the CPU except the CPU core number corresponding to the total resource amount to the service area.

Optionally, the support service includes: management services, storage services, network services, and administration services.

Optionally, after the planning of the service resources of the support area and the service area according to the total amount of resources corresponding to the shared support area and the exclusive support area, the method further includes:

predicting predicted node load data of the CPU system in future time according to the node load data;

determining a resource adjustment function of the CPU system based on the predicted node load data;

and adjusting service resources of the supporting area and the service area according to the resource adjustment function.

In a second aspect, an embodiment of the present application provides a partition management apparatus of a super fusion architecture, where the apparatus includes:

the CPU system dividing module is used for dividing the CPU system into a supporting area and a service area according to service properties;

The node load acquisition module is used for acquiring node load data of the super-fusion nodes in the supporting area under multiple dimensions;

the support area dividing module is used for dividing the support area into a shared support area and an exclusive support area according to the node load data;

and the service resource planning module is used for planning service resources of the supporting area and the service area according to the total amount of resources respectively corresponding to the shared supporting area and the exclusive supporting area.

Optionally, the node load acquisition module includes:

the node load acquisition unit is used for acquiring the node load data of the super-fusion node in multiple dimensions according to a set data acquisition period.

Optionally, the node load acquisition unit includes:

the first node load acquisition subunit is used for acquiring node load data of the super-fusion node in multiple dimensions according to the set data acquisition period by adopting a probe acquisition mode;

and the second node load acquisition subunit is used for acquiring the node load data of the super fusion node in multiple dimensions according to the set data acquisition period by adopting a set script.

Optionally, the supporting region dividing module includes:

The dimension weight acquisition unit is used for acquiring weights corresponding to the plurality of dimensions;

the hyper-score function calculation unit is used for calculating the hyper-score function corresponding to the hyper-fusion node according to the weight and the corresponding node load data;

and the supporting area dividing unit is used for dividing the supporting area into the shared supporting area and the unshared supporting area according to the superdivision function.

Optionally, the service resource planning module includes:

the resource allocation amount determining unit is used for determining the resource allocation amount of each support service in the support area according to the superdistribution function;

the resource total amount obtaining unit is used for respectively merging the service resources in the exclusive supporting area and the shared supporting area according to the resource allocation amount and the superdistribution function of each supporting service to obtain the shared resource total amount of the shared supporting area and the exclusive resource total amount of the exclusive supporting area;

and the service resource planning unit is used for planning the service resources of the supporting area and the service area according to the total shared resources and the total exclusive resources.

Optionally, the service resource planning unit includes:

A total resource amount determining subunit, configured to determine a total resource amount corresponding to the supporting area according to the total shared resource amount and the total exclusive resource amount;

a first CPU core number allocation subunit, configured to allocate, to the support area, a CPU core number in the CPU that matches the total resource amount;

and the second CPU core number distribution subunit is used for distributing other CPU core numbers except the CPU core number corresponding to the total resource amount in the CPU to the service area.

Optionally, the apparatus further comprises:

the load data prediction module is used for predicting predicted node load data of the CPU system in future time according to the node load data;

the resource adjustment function determining module is used for determining a resource adjustment function of the CPU system based on the predicted node load data;

and the service resource adjusting module is used for adjusting the service resources of the supporting area and the service area according to the resource adjusting function.

In a third aspect, an embodiment of the present application provides an electronic device, including:

a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the partition management method of the super fusion architecture of any of the above when executing the program.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform a partition management method of the super fusion architecture described in any one of the above.

Compared with the prior art, the embodiment of the application has the following advantages:

in the embodiment of the application, the CPU system is divided into the supporting area and the service area according to the service property, the node load data of the super-fusion node in the supporting area under multiple dimensions is collected, the supporting area is divided into the shared supporting area and the unshared supporting area according to the node load data, and the service resources of the supporting area and the service area are planned according to the total amount of resources corresponding to the shared supporting area and the unshared supporting area respectively. According to the embodiment of the application, the problem of resource contention in the super fusion cloud architecture is effectively solved through the partition binding technology, and the service quality and the resource utilization rate of the super fusion cloud can be well solved through controllable engineering cost, so that the product quality and the service capacity are improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

FIG. 1 is a flowchart illustrating steps of a partition management method of a super-fusion architecture according to an embodiment of the present application;

fig. 2 is a flowchart of steps of a method for collecting node load data according to an embodiment of the present application;

fig. 3 is a flowchart of steps of another method for collecting node load data according to an embodiment of the present application;

FIG. 4 is a flowchart illustrating steps of a method for partitioning a support area according to an embodiment of the present disclosure;

fig. 5 is a flowchart of steps of a service resource planning method according to an embodiment of the present application;

FIG. 6 is a flowchart illustrating steps of a method for allocating CPU core numbers according to an embodiment of the present application;

fig. 7 is a flowchart of steps of a method for adjusting service resources according to an embodiment of the present application;

fig. 8 is a schematic diagram of a super-fusion cloud resource monitoring system architecture provided in an embodiment of the present application;

FIG. 9 is a schematic diagram of a partition isolation system according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of a web page information extracting device according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings.

The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

First, terms mentioned in the embodiments of the present application are explained as follows.

Super fusion cloud: the management, calculation, network, storage, cloud management and other resources are integrated and deployed in the same set of unit equipment, so that the efficient use of the resources is realized, and the method is commonly used for small-scale computing scenes such as edge calculation, expressways, hospitals, communities and the like.

Support service: services that do not directly provide computing power to the business include management services, storage services, web services, cloud management services, and the like.

Service services: the service directly provides computing power for the service, mainly refers to the computing service of the service, and provides services such as a virtual machine, a container and the like for the service through the computing service.

In order to solve the problem of resource contention in the super-fusion cloud, the embodiment of the application provides monitoring and analysis of the resource usage of each component, the components are classified differently according to the consumption conditions of the resource usage, different classification is isolated into different available areas, different available areas provide different quality assurance, and meanwhile, the size of the available areas is dynamically adjusted according to the load of the service, so that the quality assurance of the super-fusion cloud is realized.

Next, the technical solutions of the present application are described in detail below in connection with specific embodiments.

Referring to fig. 1, a step flowchart of a partition management method of a super fusion architecture provided in an embodiment of the present application is shown, and as shown in fig. 1, the partition management method of the super fusion architecture may include: step 101, step 102, step 103 and step 104.

Step 101: the CPU system is divided into a supporting area and a service area according to service properties.

In this embodiment, the CPU system may be divided into a support area and a service area according to service properties. Specifically, the partition technology can be adopted to divide the CPU system into a supporting area and a service area according to service properties, the supporting area and the service area can be isolated by adopting the technology of CPU binding, and the service of the supporting area and the service of the service area realize complete logic isolation so as to ensure the service quality.

After the CPU system is divided into a support area and a service area according to the service properties, step 102 is performed.

Step 102: and collecting node load data of the super-fusion nodes in the supporting area under multiple dimensions.

In the present embodiment, three systems are provided, respectively: the super fusion cloud resource monitoring system, the super fusion cloud partition isolation system and the super fusion cloud dynamic adjustment system are matched and cooperate with each other to jointly complete the automatic partition isolation function.

After the CPU system is divided into a supporting area and a service area according to service properties, the node load data of the super-fusion nodes in the supporting area under multiple dimensions can be acquired through the super-fusion cloud resource monitoring system. In this embodiment, when collecting node load data, each module in the super-fusion architecture, that is, management, cloud management, network, storage, and calculation, needs to be accurate, so as to facilitate subsequent statistics and analysis.

In a specific implementation, an acquisition period may be preset to acquire node load data at fixed time, and this implementation process may be described in detail below in connection with fig. 2.

Referring to fig. 2, a step flowchart of a method for collecting node load data according to an embodiment of the present application is shown, and as shown in fig. 2, the method for collecting node load data may include: step 201.

Step 201: and acquiring node load data of the super-fusion node in multiple dimensions according to a set data acquisition period.

In this embodiment, the set data acquisition period refers to a preset period for acquiring load data of the super-fusion node, and in this example, the set data acquisition period may be 30s, 50s, 1min, or the like, and specifically, specific values of the set data acquisition period may be determined according to service requirements, which is not limited in this embodiment.

The multiple dimensions may be dimensions of CPU, memory, disk operations, network traffic, etc.

When the super fusion node of the super fusion architecture is subjected to node load data acquisition, a set data acquisition period can be acquired, and then the node load data of the super fusion node in multiple dimensions is acquired according to the set data acquisition period.

In practical applications, the collection of node load data may be performed by means of a probe or script, and the implementation process may be described in detail below in conjunction with fig. 3.

Referring to fig. 3, a flowchart illustrating steps of another method for collecting node load data according to an embodiment of the present application is shown. As shown in fig. 3, the node load data acquisition method may include: step 301 and step 302.

Step 301: and acquiring node load data of the super-fusion node in multiple dimensions according to the set data acquisition period by adopting a probe acquisition mode.

Step 302: and acquiring node load data of the super fusion node in multiple dimensions according to the set data acquisition period by adopting a set script.

In this embodiment, the collection manner of the node load data may be: any one of the probe acquisition mode and the set script acquisition mode can be adopted to acquire the node load data of the super-fusion node in multiple dimensions according to the set data acquisition period when the node load data is acquired. Or, acquiring the node load data of the super-fusion node in multiple dimensions according to a set data acquisition period by adopting a set script.

In specific implementation, load data of the super-fusion node can be acquired by adopting modes such as probe SNMP/Shell script, the data of the probe can be periodically acquired by the acquisition device, the acquisition period can be adjusted as required by default to be once per minute, the acquisition period comprises a CPU (Central processing Unit), a memory, a disk operation, network flow and the like, the overall load condition of the system is calculated through weighting, and the acquisition needs to be accurate to each module (management, cloud management, network, storage and calculation), so that the follow-up statistics and analysis are convenient. The acquired data is stored using a time series database and provides access to the RESTful API. As shown in fig. 8, the process can be implemented by using a collector to collect node load data of a CPU (central processing unit), a Memory, a Network (Network traffic) and a Disk by using a probe collection mode. And then, storing the collected node load data into a time sequence database, and providing a RESTful interface for the outside so that other systems can conveniently inquire the corresponding node load data.

After collecting node load data of the super-fusion nodes in the supporting area in multiple dimensions, step 103 is performed.

Step 103: and dividing the supporting area into a shared supporting area and an unshared supporting area according to the node load data.

After collecting node load data of the super-fusion nodes in the supporting area in multiple dimensions, the supporting area can be divided into a shared supporting area and an exclusive supporting area according to the node load data of each super-fusion node. In this embodiment, the resources in the exclusive supporting area cannot be shared and only allowed to be used by themselves, and the resources in the shared supporting area can be shared by the nodes in the shared supporting area.

In a specific implementation, a superdivision function of the super-fusion node can be calculated according to the weight corresponding to each dimension and the corresponding node load data, and then the supporting area is divided into a shared supporting area and an unshared supporting area according to the superdivision function. This implementation may be described in detail below in conjunction with fig. 4.

Referring to fig. 4, a step flowchart of a supporting area dividing method provided in an embodiment of the present application is shown, and as shown in fig. 4, the supporting area dividing method may include: step 401, step 402 and step 403.

Step 401: and obtaining weights corresponding to the multiple dimensions.

In this embodiment, when performing the calculation of the super-division function, weights corresponding to a plurality of dimensions may be acquired. It will be appreciated that the multiple dimensions may be: the dimensions of CPU, memory, disk operation, network flow and the like, wherein the CPU dimension has larger influence on the calculation of the super-division function, and at the moment, a larger weight can be allocated to the CPU dimension, a smaller weight can be allocated to other dimensions, and the like.

After the weights corresponding to the multiple dimensions are obtained, step 402 is performed.

Step 402: and calculating a superscore function corresponding to the super fusion node according to the weight and the corresponding node load data.

After the weights corresponding to the multiple dimensions are obtained, the hyper-score function of the hyper-fusion node can be calculated according to the weights and the corresponding node load data.

In a specific implementation, the super-fusion cloud partition isolation system can logically isolate each service of the system according to the data of the resource monitoring system, so that the service quality of each service is ensured.

The super-fusion cloud partition isolation system can read load data of the resource monitoring system, comprises a CPU, a memory, a network, a disk and the like, calculates the load condition of the service through weighting, and the load is represented by load, and has the value of [0,1], for different load conditions, the system adopts different superdivision coefficients, the system with high load adopts low superdivision and even no superdivision, and the system with low load adopts high superdivision, so that the service quality of the system can be ensured, and meanwhile, the resource utilization rate of the system can be improved. To facilitate system implementation, the hyper-split function may be set to 2 gears: a low load gear and a high load gear, wherein load is more than 0.5 and equal to or less than 0.5, and a super-division function is set according to load data, as shown in the following formula (1):

In the above formula (1), load is the system load (0.ltoreq.load.ltoreq.1), k is a constant, and the recommended value is 1.

After the super-score function corresponding to the super-fusion node is calculated according to the weight and the corresponding node load data, step 403 is performed.

Step 403: and dividing the supporting area into the shared supporting area and the unshared supporting area according to the superdivision function.

After the super-division function corresponding to the super-fusion node is calculated according to the weight and the corresponding node load data, the supporting area can be divided into a shared supporting area and an unshared supporting area according to the super-division function. The division manner may be as follows:

(1) When load > 0.5, r=1/1=1, i.e. the superratio is 1, i.e. not superdivision, the distinction is called the exclusive supporting region.

(2) When load is less than or equal to 0.5, R=1/0.2=2, namely the super-ratio is 2, namely 2 times of super-division is started, and the regions are called shared supporting regions.

After the support area is divided into a shared support area and an unshared support area according to the node load data, step 104 is performed.

Step 104: and planning service resources of the supporting area and the service area according to the total amount of resources corresponding to the shared supporting area and the exclusive supporting area respectively.

After the supporting area is divided into the shared supporting area and the unshared supporting area according to the node load data, the service resources of the supporting area and the service area can be planned according to the total amount of resources corresponding to the shared supporting area and the unshared supporting area respectively. In a specific implementation, the resource allocation amount of each supporting service in the supporting area can be calculated according to the superdistribution function, and then the service resources of the supporting area and the service area are planned by combining the resource allocation amount and the superdistribution function. This implementation may be described in detail below in conjunction with fig. 5.

Referring to fig. 5, a flowchart illustrating steps of a service resource planning method provided in an embodiment of the present application is shown, and as shown in fig. 5, the service resource planning method may include: step 501, step 502 and step 503.

Step 501: and determining the resource allocation amount of each support service in the support area according to the superdivision function.

In this embodiment, the support service may include: management services, storage services, network services, and administration services.

After the superdistribution function is obtained, the resource allocation amount of each support service in the support area can be determined according to the superdistribution function.

In a specific implementation, the super-division ratio of the service of the supporting area (management, cloud management, network and storage) is calculated through a super-division function R (load), a resource function is designed as follows, taking the cloud management service as an example, assuming that the load of the cloud management service is 0.2, and the number of initially used CPUs is Cinit. For the use of a CPU, a certain water level is usually reserved for improving service experience, the CPU is not allowed to run 100%, the reserved water level is denoted by T, and T default is 0.7. The design resource function (i.e., the resource allocation amount in this example) is C (load), as shown in the following equation (2):

In the above formula (2), C _init The initial CPU resource occupation amount for service is 4 as default value, and the cloud management CPU resource number can be calculated as follows: c (0.2) = (4×0.2)/(0.7×2) =0.57 core.

After determining the resource allocation amount for each support service within the support zone according to the superallocation function, step 502 is performed.

Step 502: and respectively merging service resources in the exclusive supporting area and the shared supporting area according to the resource allocation amount and the superdivision function of each supporting service to obtain the total shared resources of the shared supporting area and the total exclusive resources of the exclusive supporting area.

After determining the resource allocation amount of each supporting service in the supporting area according to the superdistribution function, the service resources in the exclusive supporting area and the shared supporting area can be respectively combined according to the resource allocation amount of each supporting service and the superdistribution function, so as to obtain the total shared resources of the shared supporting area and the total exclusive resources of the exclusive supporting area.

Specifically, in the above process, the system is divided into the single-shared supporting area and the shared supporting area according to different loads, the single-shared supporting area and the shared supporting area are not necessarily continuous, in order to improve the system efficiency, the resources of the single-shared supporting area and the shared supporting area need to be combined, and meanwhile, logic isolation needs to be performed between the single-shared supporting area and the shared supporting area. The specific mode is to combine the service CPU resources with the same super-score value.

From this, the total resource function of the shared support area is shown in the following formula (3):

the total resource function of the exclusive supporting area is shown in the following formula (4):

in the above formulas (3) and (4), C _share (load) is the total amount of shared resources, C _monopoly (load) is the total amount of shared resources.

To ensure service operation, the results of the resource functions are rounded up, e.g. C _share (load)＝Γ5.1＝6。

After the service resources in the shared supporting area and the shared supporting area are respectively combined according to the resource allocation amount and the superdistribution function of each supporting service, and the total shared resources in the shared supporting area are obtained, step 503 is executed.

Step 503: and planning service resources of the supporting area and the service area according to the total shared resources and the total exclusive resources.

After the total shared resources of the shared supporting area and the total unshared resources of the unshared supporting area are obtained, the service resources of the supporting area and the service area can be planned according to the total shared resources and the total unshared resources. Specifically, the total resource amount required by the supporting area can be determined according to the total shared resource amount and the total exclusive resource amount, and then the service resource is allocated according to the total resource amount. This implementation may be described in detail below in conjunction with fig. 6.

Referring to fig. 6, a step flowchart of a method for allocating CPU core numbers according to an embodiment of the present application is shown, and as shown in fig. 6, the method for allocating CPU core numbers may include: step 601, step 602 and step 603.

Step 601: and determining the total resource amount corresponding to the supporting area according to the total shared resource amount and the exclusive resource amount.

In this embodiment, after the total shared resource and the total unshared resource are obtained, the total resource corresponding to the supporting area, that is, the total amount of resources required to be occupied by the supporting area, may be determined according to the total shared resource and the total unshared resource. I.e. total amount of resources = total amount of shared resources + total amount of exclusive resources.

After determining the total amount of resources corresponding to the support area according to the total amount of shared resources and the total amount of exclusive resources, steps 602 and 603 are performed.

Step 602: and distributing the CPU core number matched with the total resource amount in the CPU to the supporting area.

Step 603: and distributing the CPU core numbers in the CPU except the CPU core number corresponding to the total resource amount to the service area.

After determining the total resource amount corresponding to the supporting area according to the total shared resource amount and the exclusive resource amount, the CPU core number matched with the total resource amount in the CPU can be distributed to the supporting area. And allocating the CPU core numbers except the CPU core number corresponding to the total resource amount in the CPU to the service area.

In this embodiment, the service resources may be bound by using technologies such as cgroup, so as to form a logically independent shared area and a single shared area, thereby ensuring the operation quality of the service.

In this embodiment, the service resources of the support area and the service area may also be dynamically adjusted by the super-fusion cloud dynamic adjustment system. This implementation may be described in detail below in conjunction with fig. 7.

Referring to fig. 7, a flowchart illustrating steps of a service resource adjustment method provided in an embodiment of the present application is shown, and as shown in fig. 7, the service resource adjustment method may include: step 701, step 702 and step 703.

Step 701: and predicting the predicted node load data of the CPU system in future time according to the node load data.

In this embodiment, after obtaining the node load data, the predicted node load data of the CPU system in the future time may be predicted from the node load data.

In a specific implementation, the super-fusion cloud dynamic adjustment system can continuously check the current resource use condition of each service through the load data of the resource monitoring system, the current acquisition period is 1 minute, the system analyzes and predicts the load of the system through the comprehensive load use condition of the past time system, and the system predicts the load by adopting an LSTM neural network algorithm. The LSTM neural network algorithm is mainly based on relevant prediction of time sequences, in the embodiment, load values in a past period of time (default set to 3 days) are mainly utilized to predict future values, the load condition of the system is prejudged in advance, and the response speed and the service quality of the system are improved.

After the predicted node load data of the CPU system in the future time is predicted from the node load data, step 702 is performed.

Step 702: and determining a resource adjustment function of the CPU system based on the predicted node load data.

After the predicted node load data of the CPU system in the future time is predicted according to the node load data, a resource adjustment function of the CPU system may be determined based on the predicted node load data.

In this embodiment, a resource adjustment function is preset, specifically, the resource adjustment function of the shared supporting area is shown in the following formula (5):

the resource adjustment function of the exclusive supporting area is shown in the following formula (6):

in the above formulas (5) and (6), T is a pressure water line, generally set to 0.7, and may be adjusted according to the system requirement, and the load value in the last period of time (default set to 3 days) is input into the LSTM algorithm to obtain a predicted value, and the predicted value is used to adjust the boundary of the system partition. To guarantee service operation, the results of the resource adjustment function are rounded up, i.e. if cjshare=Γ5.1=6.

After determining the resource adjustment function of the CPU system based on the predicted node load data, step 703 is performed.

Step 703: and adjusting service resources of the supporting area and the service area according to the resource adjustment function.

After determining the resource adjustment function of the CPU system based on the predicted node load data, the service resources of the support area and the service area may be adjusted according to the resource adjustment function.

Under the strong background of the rapid development of cloud computing, various modes of the cloud computing are developed, and the super-fusion cloud architecture has great advantages in the aspects of resource use, deployment and implementation. The isolation problem and the resource contention problem of the super-fusion cloud architecture have been a problem which is difficult to solve for a long time. In the embodiment, the problem of resource contention in the super fusion cloud architecture is effectively solved through a partition binding technology and a dynamic adjustment technology, and the method can be realized through controllable engineering cost, so that the service quality and the resource utilization rate of the super fusion cloud can be well solved, and the product quality and the service capacity are improved. In the super fusion cloud architecture, the technical scheme of the embodiment plays a great role, can be rapidly popularized in scenes such as edge computing, mobile office, expressways, hospitals and communities, supplements short boards of super fusion cloud products, and remarkably improves product competitiveness.

The technical solution of the embodiments of the present application may be described in detail below with reference to fig. 9.

Referring to fig. 9, a schematic structural diagram of a partition isolation system according to an embodiment of the present application is shown. The partition isolation system can logically isolate each service of the system according to the data of the resource monitoring system, and ensure the service quality of each service. The logic of the partition isolation system may be:

step 1, storing and planning a network with higher load to a single-shared supporting area, isolating, and performing superdivision on a resource part through calculation of a superdivision function R;

step 2, carrying out region combination on management and management with lower load, distributing the management and management to a shared supporting region, and starting resource superdivision through superdivision function calculation;

and step 3, dividing all the remaining resources into service areas to provide the service with the largest resources.

According to the partition management method of the super-fusion architecture, a CPU system is divided into a supporting area and a service area according to service properties, node load data of super-fusion nodes in the supporting area under multiple dimensions are collected, the supporting area is divided into a shared supporting area and an exclusive supporting area according to the node load data, and service resources of the supporting area and the service area are planned according to total amounts of resources corresponding to the shared supporting area and the exclusive supporting area respectively. According to the embodiment of the application, the problem of resource contention in the super fusion cloud architecture is effectively solved through the partition binding technology, and the service quality and the resource utilization rate of the super fusion cloud can be well solved through controllable engineering cost, so that the product quality and the service capacity are improved.

Referring to fig. 10, a schematic structural diagram of a partition management device of a super fusion architecture according to an embodiment of the present application is shown, and as shown in fig. 10, a partition management device 1000 of a super fusion architecture may include the following modules:

a CPU system dividing module 1001, configured to divide a CPU system into a supporting area and a service area according to service properties;

the node load acquisition module 1002 is configured to acquire node load data of the super-fusion node in the support area under multiple dimensions;

a supporting area dividing module 1003, configured to divide the supporting area into a shared supporting area and an unshared supporting area according to the node load data;

and a service resource planning module 1004, configured to plan service resources of the support area and the service area according to the total amount of resources corresponding to the shared support area and the exclusive support area respectively.

Optionally, the node load acquisition module includes:

Optionally, the node load acquisition unit includes:

Optionally, the supporting region dividing module includes:

Optionally, the service resource planning module includes:

Optionally, the service resource planning unit includes:

Optionally, the apparatus further comprises:

According to the partition management device of the super-fusion framework, the CPU system is divided into the supporting area and the service area according to service properties, node load data of super-fusion nodes in the supporting area under multiple dimensions are collected, the supporting area is divided into the shared supporting area and the exclusive supporting area according to the node load data, and service resources of the supporting area and the service area are planned according to the total amount of resources corresponding to the shared supporting area and the exclusive supporting area respectively. According to the embodiment of the application, the problem of resource contention in the super fusion cloud architecture is effectively solved through the partition binding technology, and the service quality and the resource utilization rate of the super fusion cloud can be well solved through controllable engineering cost, so that the product quality and the service capacity are improved.

The embodiment of the application also provides electronic equipment, which comprises: the partition management system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the partition management method of the super fusion architecture when being executed by the processor.

Fig. 11 shows a schematic structural diagram of an electronic device 1100 according to an embodiment of the present invention. As shown in fig. 11, the electronic device 1100 includes a Central Processing Unit (CPU) 1101 that can perform various suitable actions and processes according to computer program instructions stored in a Read Only Memory (ROM) 1102 or computer program instructions loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM1103, various programs and data required for the operation of the electronic device 1100 can also be stored. The CPU1101, ROM1102, and RAM1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

A number of components in the electronic device 1100 are connected to the I/O interface 1105, including: an input unit 1106 such as a keyboard, mouse, microphone, etc.; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108, such as a magnetic disk, optical disk, etc.; and a communication unit 1109 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 1109 allows the electronic device 1100 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunications networks.

The various processes and treatments described above may be performed by the processing unit 1101. For example, the methods of any of the embodiments described above may be implemented as a computer software program tangibly embodied on a computer-readable medium, such as storage unit 1108. In some embodiments, some or all of the computer programs may be loaded and/or installed onto electronic device 1100 via ROM1102 and/or communication unit 1109. When the computer program is loaded into the RAM1103 and executed by the CPU1101, one or more actions of the methods described above may be performed.

Additionally, the embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the partition management method of the above super fusion architecture.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminals (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the present application.

Finally, it is further noted that relational terms such as first and second, and the like are 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. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal 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 terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal comprising the element.

The above description of the partition management method of the super fusion architecture, the partition management device of the super fusion architecture, the electronic device and the computer readable storage medium provided by the present application applies specific examples to illustrate the principles and embodiments of the present application, and the above description of the examples is only used to help understand the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims

1. A partition management method of a super fusion architecture, the method comprising:

2. The method of claim 1, wherein the acquiring node load data for the super-fusion node in the support zone in multiple dimensions comprises:

3. The method according to claim 2, wherein the collecting node load data of the super-fusion node in multiple dimensions according to a set data collection period includes:

4. The method of claim 1, wherein the dividing the support area into a shared support area and an unshared support area according to the node load data comprises:

acquiring weights corresponding to a plurality of dimensions;

5. The method of claim 4, wherein the planning the service resources of the support area and the service area according to the total amount of resources corresponding to the shared support area and the exclusive support area, respectively, comprises:

6. The method of claim 5, wherein the planning the service resources of the support zone and the service zone based on the total amount of shared resources and the total amount of exclusive resources comprises:

7. The method of claim 5, wherein the support service comprises: management services, storage services, network services, and administration services.

8. The method of claim 1, further comprising, after said planning of service resources for said support zone and said service zone based on said total amount of resources corresponding to said shared support zone and said exclusive support zone, respectively:

9. A partition management apparatus of a super-fusion architecture, the apparatus comprising:

10. The apparatus of claim 9, wherein the node load acquisition module comprises:

11. The apparatus of claim 10, wherein the node load acquisition unit comprises:

12. The apparatus of claim 9, wherein the support zone dividing module comprises:

13. The apparatus of claim 12, wherein the service resource planning module comprises:

14. An electronic device, comprising:

a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the partition management method of the super fusion architecture of any one of claims 1 to 8 when the program is executed.

15. A computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the partition management method of the super fusion architecture of any one of claims 1 to 8.