Scheduling method and system based on cloud resource computing power distribution

Abstract

The invention is applicable to the technical field of computing power scheduling, and particularly relates to a scheduling method and system based on cloud resource computing power allocation, and the method comprises the following steps: S100: obtaining a use object of cloud resource computing power, extracting common tasks, creating isolation containers in one-to-one correspondence with the common tasks, receiving a resource use request uploaded by a tenant, and sending the resource use request to the tenant; receiving a resource use request, accessing the resource use request to an isolation container, configuring resource limitation, and establishing a corresponding relation between the isolation container and the resource limitation; and S200, finding out a hardware unit for cloud resource computing power allocation. According to the method, the isolation containers are sorted according to the importance degree, normal operation of the isolation containers with high importance can be preferentially guaranteed, the abnormity of the isolation containers is reduced, the service quality of tenants is ensured, the remaining containers are reconstructed, loads can be balanced, single-point faults are effectively avoided, the response speed of hardware units is greatly increased, and the service quality of the tenants is improved. And efficient and stable operation of cloud resources is ensured.

Description

Technical Field

[0001] The present invention relates to the field of computing power scheduling technology, and in particular to a scheduling method and system based on cloud resource computing power allocation. Background Art

[0002] When allocating cloud resource computing power, the computing, storage and network resources between different tenants are usually isolated to ensure that the computing tasks of different tenants do not interfere with each other, and at the same time ensure that each tenant's computing environment, storage space, network bandwidth and other resources are logically separated; when allocating cloud resource computing power, resource balancing is also required. The goal of resource balancing is to maximize resource utilization and processing power, achieve load balancing through dynamic scheduling of resources, and avoid excessive concentration of resources, which may cause some tenants' resources to be idle or overloaded.

[0003] It can be seen that there is a contradiction between resource isolation and balancing; therefore, "how to isolate tasks and balance the loads among different tenants" is the technical problem that the present invention needs to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a scheduling method and system based on cloud resource computing power allocation to solve the problem of "how to isolate tasks and balance the load among different tenants" raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A scheduling method based on cloud resource computing power allocation, the method comprising: S100: Obtain the usage objects of cloud resource computing power, extract common tasks, create isolated containers corresponding to the common tasks, receive resource usage requests uploaded by tenants, connect the resource usage requests to the isolated containers, configure resource restrictions, and establish a corresponding relationship between the isolated containers and resource restrictions; S200: Find out the hardware units for cloud resource computing power allocation, build a virtualization management platform, connect the hardware units to the virtualization management platform, read out the resource consumption of the hardware units, and cluster the hardware units into fully loaded units and available units; S300: dividing the isolated container into a dormant container and a running container, and determining whether the available unit satisfies resource consumption of the dormant container; If not, configure the correspondence between the available units and the scheduling containers, activate the pre-built startup strategy, determine the importance of each of the isolated containers, sort all the dormant containers in descending order of importance, and connect the dormant containers to the available units in sequence according to the sorting results, find out the remaining containers, and reconstruct the remaining containers using the startup strategy.

[0006] Furthermore, the S100 includes: Embed a monitoring mechanism into the usage object to obtain a usage request uploaded by the usage object, wherein the usage request at least includes: an isolation container item and a time item; When the usage request is responded to, a record log is generated.

[0007] Furthermore, the S100 further includes: Creating a comparison table, wherein the comparison table includes: an isolation container item and a usage object item; A mapping between the tenant, the usage object and the hardware unit is established, a label is generated using the mapping, and the label is inserted into a comparison table.

[0008] Further, the S200 includes: Splitting the resource consumption to obtain a number of individual items, quantifying the individual items, and configuring weight values ​​corresponding to the individual items one by one; The quantified single items and weight values ​​are integrated to obtain a consumption score, the consumption score is compared with a preset score threshold, and the hardware units are clustered into fully loaded units and available units according to the comparison result.

[0009] Further, the S300 includes: Embed a load balancing strategy into the isolated container to determine a load threshold for each isolated container; When the consumption score is greater than a load threshold, the load balancing strategy is activated.

[0010] Furthermore, the S300 further includes: Creating a resource management pool, and mounting the hardware unit into the resource management pool; The change process of the resource management pool is recorded and a version snapshot is generated.

[0011] Furthermore, the S300 further includes: Determine the deployment location of the edge device and establish a communication link between the edge device and the resource management pool; The properties of the isolation container are configured, an edge container is selected based on the properties, and the edge container and the remaining containers are connected to the edge device.

[0012] Furthermore, the system comprises: Establish a module for obtaining the use objects of cloud resource computing power, extracting common tasks, creating isolated containers corresponding to the common tasks, receiving resource usage requests uploaded by tenants, and connecting the resource usage requests to the isolated containers, configuring resource restrictions, and establishing a corresponding relationship between the isolated containers and resource restrictions; The clustering module is used to find the hardware units for cloud resource computing power allocation, build a virtualization management platform, connect the hardware units to the virtualization management platform, read the resource consumption of the hardware units, and cluster the hardware units into fully loaded units and available units; A reconstruction module is used to divide the isolated container into a dormant container and a running container, determine whether the available unit meets the resource consumption of the dormant container, and if not, configure the correspondence between the available unit and the scheduling container, activate the pre-built startup strategy, determine the importance of each of the isolated containers, sort all the dormant containers in descending order of importance, and according to the sorting results, connect the dormant containers to the available units in turn, find out the remaining containers, and use the startup strategy to reconstruct the remaining containers.

[0013] Furthermore, the establishment module includes: An acquisition unit, configured to embed a monitoring mechanism into the usage object, and acquire a usage request uploaded by the usage object, wherein the usage request at least includes: an isolation container item and a time item; A generating unit, configured to generate a record log after the use request is responded to; A creating unit, used for creating a comparison table, wherein the comparison table includes: an isolation container item and a use object item; The insertion unit is used to establish a mapping between the tenant, the usage object and the hardware unit, generate a label using the mapping, and insert the label into the comparison table.

[0014] Furthermore, the clustering module includes: A configuration unit, used for splitting the resource consumption to obtain a plurality of individual items, quantifying the individual items, and configuring weight values ​​corresponding to the individual items one by one; The comparison unit is used to integrate the quantified single items and weight values ​​to obtain a consumption score, compare the consumption score with a preset score threshold, and cluster the hardware units into fully loaded units and available units according to the comparison result.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By identifying common tasks, data support can be provided for resource allocation and scheduling. By creating isolated containers, an independent operating environment can be provided for common tasks, minimizing the attack surface and greatly improving the security and stability of the operating environment for common tasks. By configuring resource restrictions, cloud resource contention can be effectively avoided, malicious behavior can be isolated and prevented, and the stability of common tasks can be further improved. By building a virtualization management platform, the utilization rate of hardware units can be maximized, thereby improving the overall resource utilization efficiency and flexibility. By sorting isolated containers according to their importance, the normal operation of isolated containers with higher importance can be prioritized, isolated container anomalies can be reduced, and the service quality of tenants can be ensured. By reconstructing the remaining containers, the load can be balanced, effectively avoiding single point failures, greatly improving the response speed of hardware units, and ensuring the efficient and stable operation of cloud resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention; Figure 2 A first sub-flow diagram of a scheduling method based on cloud resource computing power allocation provided in an embodiment of the present invention; Figure 3 A second sub-flow diagram of the scheduling method based on cloud resource computing power allocation provided in an embodiment of the present invention; Figure 4 A third sub-flow diagram of the scheduling method based on cloud resource computing power allocation provided in an embodiment of the present invention; Figure 5 A block diagram of the scheduling system based on cloud resource computing power allocation provided by an embodiment of the present invention; Figure 6 A block diagram of the components of the module in the scheduling system based on cloud resource computing power allocation provided by the embodiment of the present invention; Figure 7 A block diagram of the composition of a clustering module in a scheduling system based on cloud resource computing power allocation provided by an embodiment of the present invention; Figure 8 A block diagram of the composition of a reconstruction module in a scheduling system based on cloud resource computing power allocation provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] In Example 1, Figure 1The following is a flow chart of a scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention, which is described in detail as follows: S100: Obtain the usage objects of cloud resource computing power, extract common tasks, create isolated containers corresponding to the common tasks, receive resource usage requests uploaded by tenants, and connect the resource usage requests to the isolated containers, configure resource restrictions, and establish a corresponding relationship between the isolated containers and resource restrictions.

[0019] Determine the users of cloud resource computing power, where the users can be computing clusters, virtual machines, or other specific programs that use cloud resources; extract specific tasks from the users, determine the triggering frequency of the tasks, and divide the tasks into common tasks and uncommon tasks based on the triggering frequency; create a corresponding isolated container for each common task, receive resource usage requests uploaded by tenants, analyze the resource requirements in the resource usage requests (such as CPU, memory, storage, and network bandwidth requirements), and connect the resource usage requests to the corresponding isolated containers.

[0020] Resource limits are configured based on the resource requirements of each isolated container, such as setting the maximum number of CPU cores, memory limits, and storage space for the isolated container, to ensure that the isolated container does not exceed the predetermined resource range during operation and to avoid resource abuse or conflicts. Resource limits are set in advance by professionals.

[0021] S200: Find out the hardware units for cloud resource computing power allocation, build a virtualization management platform, connect the hardware units to the virtualization management platform, read out the resource consumption of the hardware units, and cluster the hardware units into fully loaded units and available units.

[0022] Find the hardware units for cloud resource computing power allocation, where the hardware units are the devices that run the usage objects. Integrate all the hardware units, build a virtualization management platform, and abstract the hardware units into virtual resources through software virtualization technology so that they can be flexibly allocated and scheduled to different usage objects. For example, computing resources such as CPU and memory can be divided into multiple virtual instances, and storage devices can be virtualized into multiple storage volumes. Integrate all virtual resources and generate a virtualization management platform.

[0023] Through the virtualization management platform, all hardware units are monitored in real time to obtain the resource consumption data of each hardware unit, including CPU usage, memory occupancy, and storage space usage. Based on the resource consumption data, it is possible to identify which hardware units are in a fully loaded state, that is, resource consumption is close to or has reached its maximum carrying capacity, and which hardware units are in an available state, that is, resource consumption is low and there is a certain margin, thereby determining the fully loaded units and available units.

[0024] S300: dividing the isolated container into a dormant container and a running container, and determining whether the available unit satisfies resource consumption of the dormant container; If not, configure the correspondence between the available units and the scheduling containers, activate the pre-built startup strategy, determine the importance of each of the isolated containers, sort all the dormant containers in descending order of importance, and connect the dormant containers to the available units in sequence according to the sorting results, find out the remaining containers, and reconstruct the remaining containers using the startup strategy.

[0025] According to the operation status of the isolated container, the isolated container is divided into dormant containers and running containers. If the available unit can meet the resource consumption of the dormant container, that is, the available unit can process all the dormant containers, the pre-built startup strategy is activated, where the startup strategy is: after the dormant container is started, according to the correspondence between the isolated container and the common tasks, the dormant container is connected to the corresponding available unit; the importance of each common task is determined, and all the common tasks are sorted in descending order of importance, and the sorting of the running container and the dormant container is determined at the same time; all the dormant containers are connected to the available units in descending order of importance.

[0026] After the access is completed, the remaining containers that have not been processed are found, and the load balancing strategy is integrated into the startup strategy. The startup strategy and all hardware units are used to process the remaining containers and balance the load.

[0027] If the available units can satisfy the resource consumption of the dormant container, upon receiving the resource usage request uploaded by the tenant, the corresponding dormant container is directly started and processed using the available units.

[0028] In Example 2, Figure 2 The implementation process of the scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and S100 is described in detail below, as follows: S101: Embed a monitoring mechanism into the usage object to obtain a usage request uploaded by the usage object, wherein the usage request at least includes an isolation container item and a time item.

[0029] A task monitoring tool is integrated in each usage object. The task monitoring tool can track and record the resource consumption, task execution status and system health status of the usage object in real time. After receiving the usage request uploaded by the usage object, the isolation container item and time item are split out. The isolation container item refers to the identifier corresponding to the isolation container that needs to be enabled, and the time item is the time generated by the usage request.

[0030] S102: After the use request is responded to, a record log is generated.

[0031] When the usage request is responded to by the hardware unit, a record log is generated to record the entire process of the usage request from generation, response and starting the corresponding isolated container.

[0032] In Example 3, Figure 2 The implementation process of the scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and S100 is further described in detail below, as follows: S103: Create a comparison table, wherein the comparison table includes: an isolation container item and a usage object item.

[0033] Create a comparison table to configure the correspondence between the isolated container and the object used. By building the correspondence, you can quickly determine the source corresponding to the ongoing task, thereby better performing load balancing and prediction.

[0034] S104: Establish a mapping between the tenant, the usage object and the hardware unit, generate a label using the mapping, and insert the label into a comparison table.

[0035] Determine the mapping between tenants, usage objects, and hardware units. By building the mapping, better resource management can be achieved and troubleshooting can be facilitated. Use the mapping to generate tags and insert the tags into the comparison table.

[0036] In Example 4, Figure 3 The implementation process of the scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and S200 is described in detail below, as follows: S201: split the resource consumption to obtain a number of individual items, quantify the individual items, and configure weight values ​​corresponding to the individual items one by one.

[0037] Resource consumption is broken down into CPU usage, memory usage, disk, and network bandwidth items. Each item is quantified and assigned a weight value.

[0038] S202: Integrate the quantified single items and weight values ​​to obtain a consumption score, compare the consumption score with a preset score threshold, and cluster the hardware units into fully loaded units and available units according to the comparison result.

[0039] The quantized value of each single item is multiplied by the weight value and weighted to obtain the consumption score of each hardware unit. If the consumption score is greater than the score threshold, the corresponding hardware unit is defined as a fully loaded unit, otherwise, it is defined as an available unit.

[0040] In Example 5, Figure 4The implementation process of the scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and S300 is described in detail below, as follows: S301: embed a load balancing strategy into the isolation container to determine a load threshold of each isolation container.

[0041] S302: When the consumption score is greater than a load threshold, activating the load balancing strategy.

[0042] A load threshold is set for each hardware unit, and the load balancing strategy is: if the consumption score is greater than the load threshold, the portion exceeding the load threshold is transferred to other hardware units.

[0043] In Example 6, Figure 4 The implementation process of the scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and S300 is further described in detail below, as follows: S303: Create a resource management pool, and mount the hardware unit into the resource management pool.

[0044] Integrate all cloud resource computing power to create a resource management pool, where the resource management pool is deployed in the virtualization management platform and is mainly used for unified management and allocation of all hardware units.

[0045] S304: Record the change process of the resource management pool and generate a version snapshot.

[0046] Record the change process of the resource management pool and embed a version control mechanism in the resource management pool, where the version control mechanism is mainly used to track and record status updates or configuration changes of the resource management pool; the resource management pool can monitor operations such as the addition, removal, status changes or attribute updates of hardware units in real time, record these operations in detail in the form of logs, and define the obtained logs as version snapshots.

[0047] In Example 7, Figure 4 The implementation process of the scheduling method based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and S300 is further described in detail below, as follows: S305: Determine the deployment location of the edge device and establish a communication link between the edge device and the resource management pool.

[0048] Determine the deployment location of the edge device, and after deployment, connect the edge device to the resource management pool.

[0049] S306: Configure the properties of the isolation container, select an edge container based on the properties, and connect the edge container and the remaining containers to the edge device.

[0050] Configure the properties of the isolation container, where the properties include task type, resource requirements, priority, data traffic characteristics, and delay sensitivity; and based on the properties, select the isolation container suitable for running in the edge device, determine it as the edge container, and connect the edge container and the remaining containers to the edge device; in other words, connect the tasks suitable for running in the edge device and the tasks that exceed the computing power of cloud resources to the edge device for processing.

[0051] Figure 5 The structure diagram of the scheduling system based on cloud resource computing power allocation provided by an embodiment of the present invention is shown. The scheduling system based on cloud resource computing power allocation 1 includes: Establish module 11, which is used to obtain the usage objects of cloud resource computing power, extract common tasks, create isolated containers corresponding to the common tasks, receive resource usage requests uploaded by tenants, and connect the resource usage requests to the isolated containers, configure resource restrictions, and establish a corresponding relationship between the isolated containers and resource restrictions; The clustering module 12 is used to find out the hardware units for cloud resource computing power allocation, build a virtualization management platform, connect the hardware units to the virtualization management platform, read out the resource consumption of the hardware units, and cluster the hardware units into fully loaded units and available units; The reconstruction module 13 is used to determine the ongoing real-time tasks based on the fully loaded units, divide the isolated containers into dormant containers and running containers, determine whether the available units meet the resource consumption of the dormant containers, and if not, configure the correspondence between the available units and the scheduling containers, and activate the pre-built startup strategy to determine the importance of each of the isolated containers, sort all the dormant containers in descending order of importance, and according to the sorting results, connect the dormant containers to the available units in turn, find out the remaining containers, and reconstruct the remaining containers using the startup strategy.

[0052] Figure 6 The structure diagram of the scheduling system based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and the establishment module 11 includes: An acquisition unit 111 is used to embed a monitoring mechanism into the usage object, and acquire a usage request uploaded by the usage object, wherein the usage request at least includes: an isolation container item and a time item; A generating unit 112, configured to generate a record log after the use request is responded to; A creating unit 113, used to create a comparison table, wherein the comparison table includes: an isolation container item and a use object item; The inserting unit 114 is used to establish a mapping between the tenant, the usage object and the hardware unit, generate a label using the mapping, and insert the label into the comparison table.

[0053] Figure 7 The structure diagram of the scheduling system based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and the clustering module 12 includes: A configuration unit 121 is used to split the resource consumption into several items, quantify the items, and configure weight values ​​corresponding to the items one by one; The comparison unit 122 is used to integrate the quantified single items and weight values ​​to obtain a consumption score, compare the consumption score with a preset score threshold, and cluster the hardware units into fully loaded units and available units according to the comparison result.

[0054] Figure 8 The structure diagram of the scheduling system based on cloud resource computing power allocation provided by an embodiment of the present invention is shown, and the reconstruction module 13 includes: A determination unit 131, configured to embed a load balancing strategy into the isolation container and determine a load threshold of each isolation container; An activation unit 132, configured to activate the load balancing strategy when the consumption score is greater than a load threshold; The mounting unit 133 is used to create a resource management pool and mount the hardware unit into the resource management pool; The recording unit 134 is used to record the change process of the resource management pool and generate a version snapshot; A building unit 135 is used to determine the deployment location of the edge device and build a communication link between the edge device and the resource management pool; The access unit 136 is used to configure the properties of the isolation container, select an edge container based on the properties, and access the edge container and the remaining containers to the edge device.

[0055] The establishment module 11 is mainly used to complete step S100, the clustering module 12 is mainly used to complete step S200, and the reconstruction module 13 is mainly used to complete step S300; The acquisition unit 111 is mainly used to complete step S101, the generation unit 112 is mainly used to complete step S102, the creation unit 113 is mainly used to complete step S103, and the insertion unit 114 is mainly used to complete step S104; The configuration unit 121 is mainly used to complete step S201, and the comparison unit 122 is mainly used to complete step S202; The determination unit 131 is mainly used to complete step S301, the activation unit 132 is mainly used to complete step S302, the mounting unit 133 is mainly used to complete step S303, the recording unit 134 is mainly used to complete step S304, the construction unit 135 is mainly used to complete step S305, and the access unit 136 is mainly used to complete step S306.

[0056] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0057] The functions that can be achieved by the scheduling method based on cloud resource computing power allocation are all completed by a computer device, and the computer device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the scheduling method based on cloud resource computing power allocation.

[0058] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory, which is used to store computer programs, and a protection device is provided outside the memory.

[0059] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0060] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.

[0061] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A scheduling method based on cloud resource computing power allocation, characterized in that: The method comprises: S100: Obtain the usage objects of cloud resource computing power, extract common tasks, create isolated containers corresponding to the common tasks, receive resource usage requests uploaded by tenants, connect the resource usage requests to the isolated containers, configure resource restrictions, and establish a corresponding relationship between the isolated containers and resource restrictions; S200: Find out the hardware units for cloud resource computing power allocation, build a virtualization management platform, connect the hardware units to the virtualization management platform, read out the resource consumption of the hardware units, and cluster the hardware units into fully loaded units and available units; S300: dividing the isolated container into a dormant container and a running container, and determining whether the available unit satisfies resource consumption of the dormant container; If not, configure the correspondence between the available units and the scheduling containers, activate the pre-built startup strategy, determine the importance of each of the isolated containers, sort all the dormant containers in descending order of importance, and connect the dormant containers to the available units in sequence according to the sorting results, find out the remaining containers, and reconstruct the remaining containers using the startup strategy.

2. The scheduling method based on cloud resource computing power allocation according to claim 1 is characterized in that: The S100 includes: Embed a monitoring mechanism into the usage object to obtain a usage request uploaded by the usage object, wherein the usage request at least includes: an isolation container item and a time item; When the usage request is responded to, a record log is generated.

3. The scheduling method based on cloud resource computing power allocation according to claim 1 is characterized in that: The S100 further includes: Creating a comparison table, wherein the comparison table includes: an isolation container item and a usage object item; A mapping between the tenant, the usage object and the hardware unit is established, a label is generated using the mapping, and the label is inserted into a comparison table.

4. The scheduling method based on cloud resource computing power allocation according to claim 1 is characterized in that: The S200 includes: Splitting the resource consumption to obtain a number of individual items, quantifying the individual items, and configuring weight values ​​corresponding to the individual items one by one; The quantified single items and weight values ​​are integrated to obtain a consumption score, the consumption score is compared with a preset score threshold, and the hardware units are clustered into fully loaded units and available units according to the comparison result.

5. The scheduling method based on cloud resource computing power allocation according to claim 4 is characterized in that: The S300 includes: Embed a load balancing strategy into the isolated container to determine a load threshold for each isolated container; When the consumption score is greater than a load threshold, the load balancing strategy is activated.

6. The scheduling method based on cloud resource computing power allocation according to claim 1 is characterized in that: The S300 further includes: Creating a resource management pool, and mounting the hardware unit into the resource management pool; The change process of the resource management pool is recorded, and a version snapshot is taken.

7. The scheduling method based on cloud resource computing power allocation according to claim 1 is characterized in that: The S300 further includes: Determine the deployment location of the edge device and establish a communication link between the edge device and the resource management pool; The properties of the isolation container are configured, an edge container is selected based on the properties, and the edge container and the remaining containers are connected to the edge device.

8. A scheduling system based on cloud resource computing power allocation, characterized in that: The system comprises: Establish a module for obtaining the use objects of cloud resource computing power, extracting common tasks, creating isolated containers corresponding to the common tasks, receiving resource usage requests uploaded by tenants, and connecting the resource usage requests to the isolated containers, configuring resource restrictions, and establishing a corresponding relationship between the isolated containers and resource restrictions; The clustering module is used to find the hardware units for cloud resource computing power allocation, build a virtualization management platform, connect the hardware units to the virtualization management platform, read the resource consumption of the hardware units, and cluster the hardware units into fully loaded units and available units; A reconstruction module is used to divide the isolated container into a dormant container and a running container, determine whether the available unit meets the resource consumption of the dormant container, and if not, configure the correspondence between the available unit and the scheduling container, activate the pre-built startup strategy, determine the importance of each of the isolated containers, sort all the dormant containers in descending order of importance, and according to the sorting results, connect the dormant containers to the available units in turn, find out the remaining containers, and use the startup strategy to reconstruct the remaining containers.

9. The scheduling system based on cloud resource computing power allocation according to claim 8, characterized in that: The establishment module includes: An acquisition unit, configured to embed a monitoring mechanism into the usage object, and acquire a usage request uploaded by the usage object, wherein the usage request at least includes: an isolation container item and a time item; A generating unit, configured to generate a record log after the use request is responded to; A creating unit, used for creating a comparison table, wherein the comparison table includes: an isolation container item and a use object item; The insertion unit is used to establish a mapping between the tenant, the usage object and the hardware unit, generate a label using the mapping, and insert the label into the comparison table.

10. The scheduling system based on cloud resource computing power allocation according to claim 8, characterized in that: The clustering module comprises: A configuration unit, used for splitting the resource consumption to obtain a plurality of individual items, quantifying the individual items, and configuring weight values ​​corresponding to the individual items one by one; The comparison unit is used to integrate the quantified single items and weight values ​​to obtain a consumption score, compare the consumption score with a preset score threshold, and cluster the hardware units into fully loaded units and available units according to the comparison result.

Images