CN115801700A - Resource scheduling method and device, electronic equipment and readable storage medium - Google Patents

Abstract

The application discloses a resource scheduling method, a resource scheduling device, an electronic device and a readable storage medium, wherein the method comprises the following steps: receiving a request message from a system, wherein the system is one of a plurality of systems that commonly use a shared resource; determining the maximum available resource amount of the system in the shared resources, and sending the maximum available resource amount to the system; receiving the amount of required resources determined by the system according to the maximum available resource amount; and allocating resources to the system from the shared resources according to the amount of the resources required by the system, wherein the resources allocated to the system are less than or equal to the maximum available resource amount. The method and the device solve the problem that the system using the shared resource can not obtain the corresponding resource so as to influence the operation of the system when the shared resource is allocated in the prior art, improve the rationality of the allocation of the shared resource and further improve the operation stability of the system using the shared resource.

Description

Resource scheduling method, device, electronic device and readable storage medium

technical field

The present application relates to the field of network resources, in particular, to a resource scheduling method, device, electronic equipment and readable storage medium.

Background technique

With the development of network technology, more and more services are provided through the network. For example, live video service, web page service, etc. Different services are provided through different systems. The system mentioned here can be understood as a program that provides network-based services. This program can run on a server or cloud server and use the server to provide The resources provided by the provider provide services to users. For example, the system for providing the above-mentioned live video service may be called a live video system, and the system for increasing the speed of webpage access may be called a page acceleration system, and so on.

As more and more types of network services are provided to users, more and more types of systems are used. These systems are all based on the operation of the network, so these systems will use the same public resources, that is, these public resources can be used by multiple Therefore, these common resources are also called shared resources. In order to avoid conflicts when multiple systems use shared resources, it is necessary to schedule the use of shared resources in multiple systems to prevent conflicts caused by multiple systems using the same shared resources at the same time.

In the prior art, resources are locked to prevent other systems from using the resources to avoid resource usage conflicts. For example, when system A needs to use resources of A amount, system A first occupies A from the shared resources. number of resources, and then set flags for the occupied resources (this flag is used to indicate that the resources of A quantity have been used, that is, locked); when system B needs to use shared resources, it cannot use the resources with flags set, and can only use Other resources in the shared resources except the resources occupied by system A; after the system A has used up the resources of A amount, the set flag is canceled, and this part becomes a shared resource again. Although this method can solve the problem of conflicts in the use of shared resources, this method of resource allocation does not take into account the balance of resource use. For example, system A may occupy a large number of resources, resulting in less or no available resources for other systems. Resources are available. Therefore, the resource allocation method in the prior art may cause the system using the shared resource to fail to obtain the corresponding resource, thereby affecting the operation of the system.

Contents of the invention

Embodiments of the present application provide a resource scheduling method, device, electronic device, and readable storage medium to at least solve the problem that the system using the shared resource may not be able to obtain the corresponding resource when allocating shared resources in the prior art, thereby affecting the operation of the system The problem.

According to one aspect of the present application, a resource scheduling method is provided, including: receiving a request message from a system, wherein the system is one of multiple systems that jointly use a shared resource, and the request message is used to request The system allocates resources; determines the maximum amount of available resources of the system in the shared resources, and sends the maximum amount of available resources to the system; receives the required amount determined by the system according to the maximum amount of available resources Amount of resources: allocate resources to the system from the shared resources according to the amount of resources required by the system, wherein the resources allocated to the system are less than or equal to the maximum available resource amount.

According to another aspect of the present application, there is also provided a method for resource scheduling, including: sending a request message, wherein the request message is used to request resource allocation for a system, and the system is one of multiple systems that jointly use shared resources 1. Receive the maximum amount of available resources corresponding to the system; determine the amount of resources required by the system according to the actual resources required by the system and the maximum amount of available resources, wherein the amount of resources required by the system is less than or equal to The maximum amount of available resources; sending the amount of resources required by the system; receiving resources allocated for the system from the shared resources, wherein the resources allocated for the system are based on the resources required by the system distributed in quantity.

According to another aspect of the present application, there is also provided a resource scheduling device, including: a first receiving module, configured to receive a request message from a system, wherein the system is one of multiple systems that jointly use shared resources, The request message is used to request resource allocation for the system; the first determination module is configured to determine the maximum amount of available resources of the system in the shared resources, and send the maximum amount of available resources to the system The second receiving module is used to receive the amount of required resources determined by the system according to the maximum available resource amount; the allocation module is used to allocate resources from the shared resources according to the amount of resources required by the system. The system allocates resources, wherein the resources allocated to the system are less than or equal to the maximum available resource amount.

According to another aspect of the present application, there is also provided a resource scheduling device, including: a first sending module, configured to send a request message, wherein the request message is used to request resource allocation for a system, and the system is a shared One of multiple systems that share resources; a third receiving module, configured to receive the maximum amount of available resources corresponding to the system; a second determining module, configured to determine according to the actual resources required by the system and the maximum amount of available resources The amount of resources required by the system, wherein, the amount of resources required by the system is less than or equal to the maximum available resource amount; the second sending module is used to send the amount of resources required by the system; the third receiving module, It is used for receiving resources allocated for the system from the shared resources, wherein the resources allocated for the system are allocated according to the amount of resources required by the system.

According to another aspect of the present application, there is also provided an electronic device, including a memory and a processor; wherein, the memory is used to store one or more computer instructions, wherein the one or more computer instructions are stored by the The processor executes to implement the above method steps.

According to another aspect of the present application, there is also provided a readable storage medium on which computer instructions are stored, wherein the above-mentioned method steps are implemented when the computer instructions are executed by a processor.

In this embodiment of the present application, it is adopted to receive a request message from a system, wherein the system is one of multiple systems that jointly use a shared resource, and the request message is used to request resource allocation for the system; determine the The maximum amount of available resources of the system in the shared resources, and send the maximum amount of available resources to the system; receive the amount of required resources determined by the system according to the maximum amount of available resources; according to the system The amount of required resources allocates resources to the system from the shared resources, wherein the resources allocated to the system are less than or equal to the maximum available resource amount. This application solves the problem in the prior art that the system using the shared resource may not be able to obtain the corresponding resource when the shared resource is allocated, which affects the operation of the system, improves the rationality of the shared resource allocation, and further improves the use of the shared resource. system's operational stability.

Description of drawings

The drawings constituting a part of the application are used to provide further understanding of the application, and the schematic embodiments and descriptions of the application are used to explain the application, and do not constitute an improper limitation to the application. In the attached picture:

FIG. 1 is a flowchart 1 of a resource scheduling method according to an embodiment of the present application;

FIG. 2 is a schematic flow diagram of the summary management of shared resources according to an embodiment of the present application;

Fig. 3 is a schematic flow chart of summarizing shared resources with cost according to an embodiment of the present application;

FIG. 4 is a flowchart 2 of a resource scheduling method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of allocating shared resources for multiple systems according to an embodiment of the present application;

FIG. 6 is a schematic diagram of allocating resources according to priority order according to an embodiment of the present application; and,

Fig. 7 is a schematic diagram of a CDN network architecture according to an embodiment of the present application.

Detailed ways

It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

It should be noted that the steps shown in the flowcharts of the accompanying drawings may be performed in a computer system, such as a set of computer-executable instructions, and that although a logical order is shown in the flowcharts, in some cases, The steps shown or described may be performed in an order different than here.

Since the systems providing various services all run on the network, these systems inevitably use the same resources, including various computing resources and network resources, etc. The resource scheduling method provided in the following embodiments is not affected by resource types As long as it is necessary to schedule shared resources between multiple systems, the following implementation methods are applicable. The systems involved in the following embodiments may include systems that provide various services, for example, a video system for providing live video services, a webpage system for providing webpage services, a webpage acceleration system for providing webpage acceleration, and a webpage acceleration system for providing webpage acceleration. A big data service system that provides big data statistics and a streaming media system that provides streaming computing, etc. Because the services provided by these systems are different and the requirements of various services are also different. For example, the video system is used to provide video live broadcast, and the live broadcast has relatively high requirements for network delay; Its requirements for network delay are relatively low; another example is that big data service systems require more computing resources, while streaming media systems require more network resources and so on. Therefore, when performing shared resource scheduling, resource scheduling can be performed according to actual conditions of each system.

A resource scheduling method is provided in the following embodiments. FIG. 1 is a flow chart of the resource scheduling method according to an embodiment of the present application. As shown in FIG. 1 , the steps included in the method in FIG. 1 will be described below. .

Step S102, receiving a request message from a system, where the system is one of multiple systems that jointly use a shared resource, and the request message is used to request resource allocation for the system.

In an optional implementation, in order to better manage and schedule shared resources, a system for managing and scheduling shared resources can be set up. In order to distinguish this system from systems that use shared resources, consider The system is used for unified planning and orchestration of shared resources, so the system for managing and scheduling shared resources is referred to as a resource orchestration system in the following implementation manners. Fig. 2 is a schematic flow diagram of shared resource summary management according to an embodiment of the present application. As shown in Fig. 2, a system for resource summary, that is, the resource summary system in Fig. 2 may also be set up, and the resource summary system is used to complete the The summary of resources, that is, through the resource summary system, the input of resources can be completed and the input resources can be summarized into shared resources. The orchestration system is used to manage and schedule shared resources, and allocate shared resources to systems that use shared resources, thereby completing shared resources. Output. In actual application, the functions of the resource aggregation system and the resource orchestration system can also be completed through one system. All the steps shown in FIG. 1 can be executed by the resource orchestration system.

Step S104, determining the maximum amount of available resources of the system in the shared resources, and sending the maximum amount of available resources to the system.

In this step, the corresponding maximum amount of available resources of the system may be pre-configured, or as another optional implementation, the maximum amount of available resources of the system may also be based on the types of shared resources and the services provided by the system. It is generated by the demand level of this type of resources. For example, when the shared resources are bandwidth resources, the video live broadcast system has a greater demand for bandwidth resources than the big data processing system used for big data calculation and aggregation. Therefore, when allocating bandwidth resources, the maximum available resources of the video live broadcast system are greater than the maximum available resources of the big data processing system. For another example, when the shared resources are storage resources, compared with the big data processing system, the video live broadcast system has a greater demand for storage resources. Therefore, when allocating storage resources, the maximum of the big data processing system The amount of available resources is greater than the maximum amount of available resources of the video live broadcast system. In this optional implementation, when allocating different types of shared resources, the maximum amount of resources available to the system for this type of shared resources is determined according to the type of shared resources, so as to ensure that the system's requirements for different types of shared resources can be met. satisfy.

Step S106, receiving the amount of required resources determined by the system according to the maximum available resource amount, wherein the amount of required resources by the system is less than or equal to the maximum available resource amount.

In the above steps, the maximum amount of available resources that the system can use can be obtained. The maximum amount of available resources is not equal to the amount of resources required by the system. For example, a system determines that the maximum amount of available resources in the storage resources that it can use is 10G (1KB = 1024 bytes, 1MB = 1024KB, 1G = 1024MB), that is, the storage resources actually required by the system cannot exceed 10G. At this time, if the amount of resources required by the system is 8G, then 8G can be used as the The amount of resources required by the system.

Step S108, allocate resources to the system from the shared resources according to the amount of resources required by the system, wherein the resources allocated to the system are less than or equal to the maximum available resource amount.

This step involves resource allocation according to the amount of resources required by the system. As a simple implementation method, as many resources as the amount of resources required by the system can be allocated to the system, that is, in the above example, the system needs If the amount of storage resources is 8G, then 8G can be used as the resource allocated for the system. However, in the actual implementation process, the resources used by the system in the actual operation process are not necessarily a smooth process, and there may be short-term resource usage peaks (the peak may exceed the amount of resources required by the system calculated before) ), in order to solve this problem, as an optional implementation, some resources (for example, a predetermined percentage of resources) can be appropriately added to the amount of resources required by the system as the amount of resources allocated for the system, that is, from the Allocate resources that are equal to or greater than the amount of resources required by the system among the shared resources, and provide guarantees for the sudden increase in resources generated by the system during actual operation through this optional implementation . For the above example, 10% of resources can be added, that is, 8G*10%=0.8G of resources. At this time, the amount of resources required by the system is 8G, but the amount of resources allocated for the system is 8.8G. Note that What is more important is that the amount of resources finally allocated to the system is less than or equal to the corresponding maximum available resource amount of the system.

In this step, resources are allocated from the shared resources according to the amount of resources required by the system, and the resources allocated to the system will not exceed the corresponding maximum available resources of the system. If there are remaining resources, the remaining resources are put back into the shared resources for resource allocation for other systems.

In the above steps, the systems that need to use shared resources allocate resources within their corresponding maximum available resources, which ensures that there is an upper limit for the resources allocated by each system, and avoids unrestrained preemption of shared resources by some systems. The above steps solve the problem caused by the unbalanced allocation of shared resources in the prior art, improve the rationality of shared resource allocation to a certain extent, and further improve the operation stability of the system using shared resources.

The maximum available resources corresponding to different systems can be pre-configured, or can also be related to the priority of the system, that is, in an optional implementation, priorities can be introduced, and different priorities correspond to different maximum available resources When allocating shared resources, allocate them according to the maximum amount of available resources corresponding to the priority of the system, so as to meet the needs of each system for shared resources as much as possible. That is, determining the maximum amount of available resources of the system in the shared resources may include the following steps: obtaining the priority of the system; determining the maximum available resources of the system in the shared resources according to the priority of the system quantity.

The priority of the system can be pre-configured, or as another optional implementation, the priority of the system can also be generated according to the type of shared resource and the service provided by the system. When the shared resources are bandwidth resources, compared with the big data processing system used for big data calculation and summarization, the video live broadcast system has a greater demand for bandwidth resources. Therefore, when allocating bandwidth resources, the video live broadcast system The priority of the system is higher than that of the big data processing system. For another example, when the shared resources are storage resources, compared with the big data processing system, the video live broadcast system has a greater demand for storage resources. Therefore, when allocating storage resources, the priority of the big data processing system is The priority is higher than the priority of the live video system. In this optional implementation, the maximum amount of available resources corresponding to the system is related to its own priority. When allocating different types of shared resources, the priority of the system is determined according to the type of shared resources, so as to ensure that the system is The needs of shared resources can be met.

Among multiple systems using shared resources, the resources occupied by the system with high priority are larger than those occupied by the system with low priority, that is to say, the system with high priority occupies more resources during resource allocation. More initiative, this will produce another situation: the system with high priority may run out of resources during the process of using the resources allocated to it. At this time, if in order to ensure that the system with high priority can obtain Sufficient resources can allow high-priority systems to preempt resources from low-priority systems. Although this method can ensure that high-priority systems get sufficient resources in actual operation, resource preemption will make low-priority systems The operation of the system is greatly affected, and in severe cases, even the system with low priority cannot operate normally. In order to solve this problem, the maximum amount of available resources corresponding to the system priority is used as the upper limit of resource allocation for the system. In this way, high priority systems can avoid preempting resources of low priority systems. In the above embodiments, considering that the maximum amount of available resources of the system is the upper limit of the resources that the system can use, when determining the amount of resources required by the system, various situations can be fully considered, and the situation that can meet the maximum requirements of the system can be used as much as possible. down to determine the amount of resources required by the system. In an optional implementation manner, if resources are added to the amount of resources required by the system, and the amount after the increase in resources is used as the resource allocated to the system, the increase in resources can be determined according to the priority of the system The higher the priority of the system, the greater the amount of resources that can be added, but the resources finally allocated to the system cannot exceed the maximum available resources. Through this optional implementation, on the one hand, a certain amount of resource redundancy can be provided for the system to ensure the stability of system resource usage; on the other hand, the resources used by systems with high priority can be limited to ensure that All priority systems can obtain corresponding shared resources, which ensures the balance of resource allocation among systems.

The above optional implementation manner sets an upper limit for the use of shared resources by systems of each priority, which can ensure the balance of resource allocation to a certain extent. However, considering the complexity of the actual environment, there may still be insufficient resources allocated to the system. In order to solve this problem, as an optional implementation manner, this problem can be solved by resource reservation. That is, reserve a part of resources in advance, wherein the reserved resources do not participate in the resource allocation of the multiple systems; after allocating the resources for the multiple systems, receive a message sent by at least one of the multiple systems The second request message, wherein the second request message is used to indicate that the system sending the second request message needs to increase resources on the basis of allocated resources; send the second request message from the reserved resources to the Two request messages for the system to allocate resources. For example, the shared storage resources are 1000G in total. When allocating storage resources for multiple systems, reserve a certain proportion of resources from 1000G as reserved resources (5% to 10% can be reserved). If 10 % is used as a reserved resource, the storage resource of 1000G*10%=100G will not be allocated among multiple systems as a shared resource.

The reserved resources can be used as spare resources. For example, when a system using shared resources is newly added, the reserved resources can be allocated to the newly added system. Considering that new systems are not frequently added, the reserved resources are more used when the allocated resources are insufficient. At this time, if only one system requests to allocate additional resources from the reserved resources , resource allocation can be performed directly from the reserved resources according to the request. If multiple systems request resource allocation from the reserved resources, the allocation is performed according to the priority of the system. That is, allocating resources from the reserved resources to the system sending the second request message includes: in the case of receiving the second request message sent by at least two systems, according to the priorities of the at least two systems Allocating resources for the at least two systems from the reserved resources in descending order. In the above example, the reserved resource is 100G, and the second request message sent by the two systems is received, and the priority of system A is higher than that of system B. System A requests the allocation of 80G storage resources, and system B requests the allocation of 30G storage resources. For storage resources, at this time, 80G storage resources are allocated to system A first, and then the remaining storage resources of 100G-80G=20G are allocated to system B, and system B is notified that only 20G of resources remain.

When using shared resources, in terms of system speed and stability, each system hopes to obtain more resources, but resources are limited, so the resource orchestration system is based on the priority of the system to be allocated resources The maximum amount of available resources that the system can use is determined, and then the amount of resource allocation is finally determined according to the amount of required resources (the resources allocated for the system are also referred to as resources occupied by the system). It should be noted that considering that the use of resources also requires cost, the system using these shared resources hopes to have the autonomy of resource determination, that is, it is hoped that the system can determine the resources required by the system according to the cost of resources and the actual situation of the system amount. Fig. 3 is a schematic flow chart of sharing resource summarization with cost according to an embodiment of the present application. As shown in Fig. 3, after the resource summarization system summarizes resources to obtain shared resources, the billing rule system can import billing rules into the shared resources. resources, so that the cost of using shared resources can be obtained. In this way, the amount of resources required by each system can be determined by each system according to its own needs. FIG. 4 is the second flow chart of the resource scheduling method according to the embodiment of the present application. FIG. 4 is described from the perspective of a system using shared resources. As shown in FIG. 4 , the steps included in FIG. 4 will be described below.

Step S402, sending a request message, wherein the request message is used to request resource allocation for a system, and the system is one of multiple systems that jointly use shared resources;

Step S404, receiving the maximum amount of available resources corresponding to the system;

Step S406, determining the amount of resources required by the system according to the actual resources required by the system and the maximum amount of available resources, wherein the amount of resources required by the system is less than or equal to the maximum amount of available resources;

Step S408, sending the amount of resources required by the system;

Step S410, receiving resources allocated for the system from the shared resources, wherein the resources allocated for the system are allocated according to the amount of resources required by the system.

Through the above steps, the system can determine the amount of resources required by the system according to the amount of its own maximum available resources. On the one hand, the system has a certain autonomy to determine the amount of resources used for the use of shared resources. On the other hand, The resources used by the system are also limited by the maximum amount of available resources, thus ensuring the balance of resource allocation among the various systems and providing the stability of the operation of multiple systems.

In one embodiment, the above-mentioned resource orchestration system and multiple systems that share resources can be used as an overall resource scheduling system. In the resource scheduling system, the system to be allocated shared resources sends a request message; the resource orchestration system receives requests from A request message of a system sharing resources; the resource orchestration system obtains the priority of the system, and obtains the maximum amount of available resources corresponding to the system according to the priority of the system, and the resource orchestration system sends the maximum amount of available resources to The system; the system receives the maximum amount of available resources, and determines the amount of resources required by the system in the maximum amount of available resources; the system sends the amount of resources required by the system to the resource orchestration system The resource orchestration system receives the amount of resources required by the system, and allocates resources for the system from the maximum available resource amount according to the amount of resources required by the system; the system receives and uses the allocated resources for the system resource.

In the above steps, when allocating resources, the priorities in the multiple systems can be obtained, and then resources are allocated in sequence according to the priority. Among the multiple systems, the maximum amount of available resources that can be used by the system with the highest priority is all the shared resources. Except for the system with the highest priority, the maximum amount of available resources that can be used by systems with other priorities is all shared resources. The amount of remaining resources in the shared resources, where the remaining resources are the remaining resources after subtracting the resources occupied by other systems with a higher priority than the current system in the shared resources. Fig. 5 is a schematic diagram of allocating shared resources for multiple systems according to an embodiment of the present application. As shown in Fig. 5, the priority of system 1 is higher than that of system 2, the priority of system 2 is higher than that of system 3, and the priority of system 3 is higher than that of system 3. The priority of system 3 is higher than that of system 4. The resource orchestration system first takes all shared resources as the maximum available resources of system 1, and then system 1 allocates 30% of the shared resources as resources of system 1; the remaining shared resources are used as The maximum amount of available resources that can be used by System 2, and then System 2 allocates 30% of the remaining shared resources as the resources of System 2; the remaining shared resources allocated by System 2 are used as the maximum amount of available resources that can be used by System 3 , and then system 3 allocates 50% of the remaining shared resources as the resources of system 3; the remaining shared resources allocated by system 3 are taken as the maximum amount of available resources that can be used by system 4, and then system 4 allocates the remaining shared resources 30% as system 4 resources. After the four systems are allocated, the remaining resources can be used as reserved resources, and can be allocated from the reserved resources when a new system is added or the resources of the four systems are not enough.

Fig. 6 is a schematic diagram of allocating resources according to the order of priority according to the embodiment of the present application. As shown in Fig. 6, system A is the system with the highest priority, and its visible resources (that is, the maximum available resources) are all shared resources, and the resource arrangement The system allocates 60% of the visible resources to system A as the resources of system A; the priority of system B is lower than that of system A, but higher than that of system C, and its visible resources are the remaining resources after the resource orchestration system allocates resources for system A. The resource orchestration system allocates 60% of its visible resources to system B as the resources of system B; system C has the lowest priority, and no other system after system C has shared this resource, and the visible resources of system C are for system A and system For the remaining resources after allocation by B, since system C is the last system to allocate the shared resources, the resource orchestration system allocates all (ie 100%) of the visible resources to system C. It should be noted that the reserved resources in FIG. 6 have not participated in the allocation of shared resources. When system B in FIG. 6 determines the resources it needs, since system C has not allocated resources, it cannot monopolize all its visible resources. As an optional implementation, when allocating shared resources in sequence according to the system priority, each system may also consider systems that have not allocated resources when determining the amount of resources required by the system, for example, according to the actual resources of the system Determining the amount of resources required by the system includes: when the amount of resources actually required by the system is less than the maximum amount of available resources, combining the amount of resources actually required by the system The amount is used as the amount of resources required by the system; when the actual amount of resources required by the system is greater than or equal to the maximum available resource amount, and there are other systems with a lower priority than the system that have not yet allocated resources, from Obtain part of resources from the maximum amount of available resources as resources required by the system; wherein, the part of resources is determined according to the priority of the system and other systems whose priority is lower than that of the system, and the higher the priority The more resources are obtained from the maximum amount of available resources.

The resource allocation manner in the foregoing embodiments may be applied to various networks or to other various networks or scenarios. The following uses a content delivery network (Content Delivery Network, CDN for short) as an example for illustration. CDN is a network for content distribution built on the basis of existing networks. The content distribution network distributes content through technical means such as load balancing and resource scheduling, so that users can obtain the content they need nearby, reduce network congestion, and increase the speed at which users can obtain the content they need. Fig. 7 is a schematic diagram of the architecture of a CDN network according to an embodiment of the present application. As shown in Fig. 7, the origin site serves as the provider of the content, and it provides the content to the CDN node, so that users in different locations can choose the CDN closest to them Nodes to obtain the content, improving the speed of content acquisition. The CDN node is located at the edge of the network and is closer to the user. Therefore, the CDN node in FIG. 7 is also called an edge node. In addition to the edge node shown in FIG. 7, an intermediate node ( Not shown in FIG. 7 ), these intermediate nodes can acquire content from the source station, and distribute the acquired content to edge nodes. In the following embodiments, intermediate nodes and edge nodes are collectively referred to as nodes.

For a CDN network, each node is used to send and store content. Therefore, a node can also be regarded as a type of resource used in a CDN. Links are needed between nodes to transmit content. These Links can also be used as resources in CDN. It should be noted that each node can include multiple physical servers, and the physical servers can be divided into multiple groups, and different groups can provide different services, and these groups can also be regarded as a type of resource. A variety of content can be distributed using a CDN network. For example, a video system can use a CDN to distribute videos, and a webpage system can use a CDN to distribute web pages. When these systems use a CDN for content distribution, the shared resources are used in the content distribution network. Resources for content distribution, such as nodes, groups, and links. In this optional implementation manner, systems such as video systems and webpage systems that use CND for content distribution are called components.

It is not just video systems and webpage systems that use CDN for content distribution. In fact, CDN will have multiple components (that is, systems that use CDN for content distribution) to share resources. As the number of components (that is, the system) increases, if these components do not coordinate with each other when using resources, resources will conflict with each other. In this embodiment, a resource orchestration system is introduced to resolve conflicts caused by multiple components using shared resources. Due to the complexity of shared resources, the resource orchestration system can extract the shared resources that can be used for resource scheduling, realize the unified arrangement of shared resources (the shared resources can be CDN's entire network resources), and avoid conflicts between different components and resource waste .

In this optional implementation, the priorities of different types of resources used by each component are managed, and shared resources are allocated and controlled according to the priorities, and resource monitoring means can also be added to give an alarm when resources are used abnormally. For example, when assigning node resources to component 1, component 2, and component 3, the priority of component 1 is higher than that of component 2, and the priority of component 2 is higher than that of component 3. The edge node allocated to component 1 For node A, node B and node C, among them, the resources of node A are exclusively shared by component 3. For component 2, node B and node C are allocated, among which, node B is shared by component 1 and component 2; for component 3, resources are allocated Node B and node C, wherein node C is shared by component 1, component 2 and component 3. When monitoring the traffic of nodes A, B, and C, it is found that the traffic of component 1 in node C is greater than the traffic of component 1 in node A, which means that node A allocated for component 1 is not fully used. At this time Alerts can be raised.

When allocating shared resources, the component queries the maximum amount of available resources that the component can use according to the resource name (for example, the name of the node, the name of the group, the name of the link). The resource orchestration system obtains the maximum amount of available resources that the component can use in the shared resources queried by the component according to the identification information of the component, the priority of the component, and the resources queried by the component. The maximum amount of available resources that each component can use can be determined according to the component's The priority, the number of components using the shared resource, and the remaining resources are obtained, and the maximum available resource is returned to the component after obtaining the maximum available resource. The component performs resource planning according to the maximum amount of available resources, calculates the resources planned to be used on nodes, groups and links in this round of planning, and reports to the resource orchestration system (the reported message carries the component name and resource name). For each type of resource, a certain buffer can also be reserved. The resources in this buffer are used as reserved resources when the component resources are insufficient. If components of different priorities all request to use the reserved resources, the high priority High-level components preempt low-priority components to a certain extent (that is, satisfy the needs of high-priority components first).

When policy components with different priorities use resources at the same time, since high priority components have absolute priority in preempting shared resources, low priority components can only see the remainder of resources allocated by high priority components during planning. resource. If high-priority components preempt too much shared resources, it will affect low-priority components. In this optional implementation, for each component, you can configure a certain proportion of the upper limit of resource usage (that is, the maximum amount of available resources, which can also be called a quota), to achieve hard isolation of resources, and reduce or even eliminate high-priority resources through resource quotas. The impact of high-level components preempting resources on low-priority components, using the set priority and quota to allocate currently available resources to this component, increases the stability of the system.

It should be noted that the above resource orchestration system can only be used for the allocation of shared resources, that is, the resource orchestration system does not interfere with the services provided by each component. In this way, resource scheduling and service provision can be handed over to different systems. Execution, each component focuses on whether the services it provides are normal, and the resource scheduling part is executed by the resource orchestration system, which makes resource allocation clearer and is conducive to the stability of the CDN network. That is, the above-mentioned resource orchestration system coordinates various components, eliminates separate management of resource allocation among multiple components, removes complicated and chaotic resource reservation relationships, and unifies resource management.

In this embodiment, an electronic device is provided, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the methods in the above embodiments.

The above-mentioned program can run in the processor, or can also be stored in the memory (or called computer-readable medium), and the computer-readable medium includes permanent and non-permanent, removable and non-removable technology for information storage. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.

These computer programs can also be loaded onto a computer or other programmable data processing device, so that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device Steps are provided for realizing the functions specified in one or more processes of the flowchart and/or one or more blocks of the block diagram, and different corresponding steps may be implemented by different modules.

Such a device is provided in this embodiment. The device is called a resource scheduling device, and the modules in the device correspond to the steps shown in Fig. 1, and the device includes: a first receiving module, configured to receive a request message from a system, wherein the system is used in common One of multiple systems that share resources, the request message is used to request resource allocation for the system; the first determination module is used to determine the maximum amount of available resources of the system in the shared resources, and send the The maximum amount of available resources is sent to the system; the second receiving module is used to receive the amount of required resources determined by the system according to the maximum amount of available resources; the allocation module is used to receive the amount of resources required by the system according to the amount of resources required by the system Allocating resources for the system from the shared resources, wherein the resources allocated for the system are less than or equal to the maximum available resource amount.

Optionally, the allocation module is configured to allocate resources from the shared resources equal to or greater than the amount of resources required by the system.

Optionally, the first determining module is configured to obtain the priority of the system; determine the maximum amount of available resources of the system in the shared resources according to the priority of the system.

Optionally, the maximum amount of available resources that can be used by the system with the highest priority among the multiple systems is all the shared resources. Except for the system with the highest priority, the maximum amount of available resources that other priority systems can use The resource amount is the amount of remaining resources in the shared resources, and the remaining resources are the remaining resources after subtracting the resources occupied by other systems with higher priority than the current system in the shared resources.

Optionally, the first receiving module is further configured to receive a second request message sent by at least one of the multiple systems, where the second request message is used to indicate the sender of the second request message The system needs to increase resources on the basis of allocated resources; the allocating module is further configured to allocate resources from reserved resources to the system sending the second request message, wherein the reserved resources do not participate in Resource allocation for the plurality of systems.

Optionally, the allocating module is configured to, in the case of receiving the second request message sent by at least two systems, select from the reserved The resources are allocated to the at least two systems.

In another embodiment, another device for resource scheduling is provided, the modules in the device correspond to the steps shown in FIG. 4 , and the device includes: a first sending module, configured to send a request message, wherein the The request message is used to request resource allocation for a system, and the system is one of multiple systems that jointly use shared resources; the third receiving module is used to receive the maximum amount of available resources corresponding to the system; the second determining module uses Determining the amount of resources required by the system according to the actual resources required by the system and the maximum amount of available resources, wherein the amount of resources required by the system is less than or equal to the maximum amount of available resources; the second sending module, Used to send the amount of resources required by the system; a third receiving module, used to receive resources allocated for the system from the shared resources, wherein the resources allocated for the system are based on the resources required by the system The amount of resources allocated.

Optionally, the second determination module is configured to use the amount of resources actually required by the system as the amount of resources actually required by the system when the amount of resources actually required by the system is less than the maximum amount of available resources. The amount of resources; when the amount of resources actually required by the system is greater than or equal to the maximum amount of available resources, and there are other systems with a lower priority than the system that have not yet allocated resources, the resources from the maximum amount of available resources Obtain part of the resources as the resources required by the system; wherein, the part of the resources is determined according to the priority of the system and other systems whose priority is lower than that of the system, and the higher the priority, the greater the amount of available resources The more resources you get from it.

Optionally, the multiple systems are systems that use a content distribution network for content distribution, and the shared resources include resources used for content distribution in the content distribution network.

The above-mentioned device is used to implement the functions of the methods in the above-mentioned embodiments. Each module in the system or device corresponds to each step in the method. What has been described in the method will not be repeated here.

Through the above optional implementation mode, it solves the problem in the prior art that the system using the shared resource may not be able to obtain the corresponding resource when the shared resource is allocated, which affects the operation of the system, improves the rationality of the shared resource allocation, and further improves the This ensures the operational stability of systems using shared resources.

The above are only examples of the present application, and are not intended to limit the present application. For those skilled in the art, various modifications and changes may occur in this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims (13)

1. A resource scheduling method comprises the following steps:

receiving a request message from a system, wherein the system is one of a plurality of systems which commonly use shared resources, and the request message is used for requesting to allocate resources for the system;

determining a maximum available resource amount of the system in the shared resources and sending the maximum available resource amount to the system;

receiving the amount of required resources determined by the system according to the maximum available resource amount;

and allocating resources to the system from the shared resources according to the amount of the resources required by the system, wherein the resources allocated to the system are less than or equal to the maximum available resource amount.

2. The method of claim 1, wherein allocating resources for the system from the shared resources according to the amount of resources required by the system comprises:

allocating resources from the shared resources that are equal to or greater than the amount of resources required by the system.

3. The method of claim 1, wherein determining a maximum amount of resources available to the system in the shared resources comprises:

acquiring the priority of the system;

and determining the maximum available resource amount of the system in the shared resources according to the priority of the system.

4. The method according to claim 3, wherein the maximum available resource amount that can be used by the system with the highest priority among the plurality of systems is all the shared resources, the maximum available resource amount that can be used by the systems with other priorities except the system with the highest priority is the amount of the remaining resources in the shared resources, and the remaining resources are the resources remaining after the resources occupied by the systems with higher priorities than the system are subtracted from the shared resources.

5. The method of any of claims 1-4, wherein after allocating resources for the plurality of systems, the method further comprises:

receiving a second request message sent by at least one of the systems, wherein the second request message is used for indicating that the system sending the second request message needs to increase resources on the basis of the allocated resources;

allocating resources from reserved resources to a system that sent the second request message, wherein the reserved resources do not participate in resource allocation for the plurality of systems.

6. The method of claim 5, wherein allocating resources from the reserved resources to a system that transmitted the second request message comprises:

and in the case of receiving second request messages sent by at least two systems, allocating resources for the at least two systems from the reserved resources according to the order of the priorities of the at least two systems from high to low.

7. The method of any of claims 1-4, wherein the plurality of systems are systems for content distribution using a content distribution network, and the shared resources include resources in the content distribution network for content distribution.

8. A resource scheduling method comprises the following steps:

sending a request message, wherein the request message is used for requesting resource allocation for a system, and the system is one of a plurality of systems which commonly use shared resources;

receiving the maximum available resource amount corresponding to the system;

determining the amount of the resources required by the system according to the actual required resources of the system and the maximum available resource amount, wherein the amount of the resources required by the system is less than or equal to the maximum available resource amount;

transmitting an amount of resources required by the system;

receiving resources allocated to the system from the shared resources, wherein the resources allocated to the system are allocated according to the amount of resources required by the system.

9. The method of claim 8, wherein determining the amount of resources required by the system based on the actual resources required by the system and the maximum amount of available resources comprises:

taking the amount of the resource actually required by the system as the amount of the resource required by the system under the condition that the amount of the resource actually required by the system is smaller than the maximum available resource amount;

acquiring partial resources from the maximum available resource amount as the resources required by the system under the condition that the amount of the resources actually required by the system is greater than or equal to the maximum available resource amount and the resources are not allocated to other systems with priorities smaller than the priority of the resources; the partial resources are determined according to the system and the priority of other systems with the priority lower than that of the system, and the higher the priority is, the more resources are acquired from the maximum available resource amount.

10. A resource scheduling apparatus, comprising:

a first receiving module, configured to receive a request message from a system, where the system is one of multiple systems that share a shared resource, and the request message is used to request resource allocation for the system;

a first determining module, configured to determine a maximum available resource amount of the system in the shared resources, and send the maximum available resource amount to the system;

a second receiving module, configured to receive the amount of the required resource determined by the system according to the maximum available resource amount;

and the allocation module is used for allocating resources to the system from the shared resources according to the amount of the resources required by the system, wherein the amount of the resources allocated to the system is less than or equal to the maximum available resource amount.

11. A resource scheduling apparatus, comprising:

a first sending module, configured to send a request message, where the request message is used to request resource allocation for a system, and the system is one of multiple systems that share a shared resource;

a third receiving module, configured to receive a maximum available resource amount corresponding to the system;

a second determining module, configured to determine an amount of the resource required by the system according to the actual required resource of the system and the maximum available resource amount, where the amount of the resource required by the system is less than or equal to the maximum available resource amount;

a second sending module, configured to send the amount of resources required by the system;

a third receiving module, configured to receive a resource allocated to the system from the shared resources, where the resource allocated to the system is allocated according to an amount of a resource required by the system.

12. An electronic device comprising a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any one of claims 1 to 7 or the method steps of any one of claims 8 to 9.

13. A readable storage medium having stored thereon computer instructions, wherein the computer instructions, when executed by a processor, perform the method steps of any one of claims 1 to 7 or the method steps of any one of claims 8 to 9.

Images