CN116346932A

CN116346932A - Resource scheduling method, equipment and system for network service

Info

Publication number: CN116346932A
Application number: CN202310274974.8A
Authority: CN
Inventors: 卢玥锟
Original assignee: Alibaba China Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2023-03-17
Filing date: 2023-03-17
Publication date: 2023-06-27

Abstract

The application provides a resource scheduling method, equipment and a system for network services. The method is applied to the NFV system and comprises the following steps: acquiring a first bandwidth of a network service and performance parameters of M resource pools, wherein the first bandwidth is a bandwidth required to be occupied by the network service or the first bandwidth is a bandwidth variation for running the network service, the resource pools comprise at least one resource, the performance parameters of the resource pools are used for indicating network calculation bandwidths and network forwarding bandwidths included by the resources in the resource pools, and M is an integer larger than 1; according to the first bandwidth and the performance parameters of the M resource pools, N resources to be scheduled in the M resource pools are determined, wherein N is smaller than or equal to a positive integer of M; the N resources are scheduled as resources running the network service. The N resources can bear the first bandwidth of the network service, and flexible scheduling of the virtual network resources in the heterogeneous resource pool scene is realized.

Description

Resource scheduling method, equipment and system for network service

Technical Field

The present disclosure relates to the field of cloud computing technologies, and in particular, to a method, an apparatus, and a system for scheduling resources of a network service.

Background

Currently, in the application scenario of network function virtualization (Network Functions Virtualization, NFV), an NFV system may provide network services to users through virtual network resources provided by a resource pool, where the resource pool is used to provide network services to a fixed user or user group, that is, the NFV system may provide network services to a corresponding user or user group by running different resource pools. When the amount of resources required by the network service operation changes, the amount of resources in the resource pool can be increased or reduced, so that the flexible expansion of the resource pool is realized.

However, NFV systems cannot schedule another resource pool (or referred to as a heterogeneous resource pool) for resource scheduling through a network service provided by one resource pool, reducing flexibility of resource scheduling.

Disclosure of Invention

The resource scheduling method, device and system for the network service are provided, so that flexibility of resource scheduling is improved in an NFV application scene.

In a first aspect, an embodiment of the present application provides a resource scheduling method for a network service, which is applied to an NFV system, including: acquiring a first bandwidth of a network service and performance parameters of M resource pools, wherein the first bandwidth is a bandwidth required to be occupied by the network service or the first bandwidth is a bandwidth variation for running the network service, the resource pools comprise at least one resource, the performance parameters of the resource pools are used for indicating network calculation bandwidths and network forwarding bandwidths included by the resources in the resource pools, and M is an integer larger than 1; according to the first bandwidth and the performance parameters of the M resource pools, N resources to be scheduled in the M resource pools are determined, wherein N is smaller than or equal to a positive integer of M; the N resources are scheduled as resources running the network service.

In a second aspect, an embodiment of the present application provides an electronic device, including: at least one processor and memory; the memory stores computer-executable instructions; the at least one processor executes computer-executable instructions stored in the memory, causing the at least one processor to perform the method as in the first aspect.

In a third aspect, embodiments of the present application provide an NFV system, including: a resource pool scheduling device and an NFV processing device, the resource pool scheduling device being communicatively connected to the NFV processing device; the resource pool scheduling device is used for: acquiring a first bandwidth of a network service and performance parameters of M resource pools, wherein the first bandwidth is a bandwidth required to be occupied by the network service or the first bandwidth is a bandwidth variation when the network service is operated, the resource pools comprise at least one resource, the performance parameters of the resource pools are used for indicating network calculation bandwidth and network forwarding bandwidth provided by the resources in the resource pools, and M is an integer greater than 1; according to the first bandwidth and the performance parameters of the M resource pools, N resources to be scheduled in the M resource pools are determined, wherein N is smaller than or equal to M, and N is a positive integer; the NFV processing means is configured to schedule the N resources as resources for running the network service.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, implement a method as provided in the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program product comprising computer instructions which, when executed by a processor, implement the method provided in the first aspect.

In the embodiment of the application, the NFV system determines N resources to be scheduled in the M resource pools based on performance parameters of each resource pool in the M resource pools in a heterogeneous resource pool scenario, so that the N resources can bear a first bandwidth of a network service, and flexible scheduling of virtual network resources in the heterogeneous resource pool scenario is realized.

Drawings

Fig. 1 is a schematic diagram of an NFV application scenario 100 provided in an embodiment of the present application;

fig. 2 is an interactive flow diagram of a resource scheduling method 200 of network service according to an embodiment of the present application;

FIG. 3 is a schematic block diagram of an apparatus 300 provided in an embodiment of the present application;

fig. 4 is a schematic structural diagram of an electronic device 400 according to an exemplary embodiment of the present application.

Detailed Description

The embodiment of the application can be applied to any network service scene realized by adopting the NFV architecture. The NFV architecture is different from the relation of strong binding between software and hardware in the traditional physical device, and in the NFV architecture, various network function standard software can be applied to the same hardware device.

When the NFV system based on the NFV architecture provides network services, in some scenarios, network services are provided for different users or user groups through different resource pools, for example, the users or user groups served by each resource pool belong to the same cloud service manufacturer or belong to service objects of the same cloud service manufacturer, and for example, the types of network services provided by each resource pool are different; in other scenarios, the implementation manners of the resource pools are different, for example, one resource pool is implemented by a cloud resource (such as a cloud virtual machine), and the other resource pool is implemented by a non-cloud resource (such as a physical server resource of a bare metal server), so as to meet the requirement that vendors provide network services for users with small flow and rapid change through the cloud resource, reduce cost, and provide network services for users with large flow and needs important guarantee through the non-cloud resource, so as to realize rapid network forwarding. It should be understood that different resource pools in embodiments of the present application may be referred to as heterogeneous resource pools. In order to solve the above problem, the embodiments of the present application determine at least one resource to be scheduled in different resource pools based on performance parameters of the different resource pools, so as to implement flexible call of the resource.

The following describes an exemplary embodiment of the present application with reference to the drawings.

Fig. 1 is a schematic diagram of an NFV application scenario 100 provided in an embodiment of the present application.

As shown in connection with fig. 1, NFV system 110 may be a software implementation built under an NFV network architecture. NFV system 110 may include NFV processing means 111, resource pool scheduling means 112, and resource pool monitoring means 113. The resource pool scheduling device 112 is communicatively connected to the NFV processing device 111 and the resource pool monitoring device 113, respectively.

NFV system 110 may be communicatively coupled to heterogeneous resource pool 120 (e.g., including resource pools 120-1 through 120-M) to obtain parameters or traffic data for the resource pool. The resource pools 120-1 to 120-M may include cloud resources and non-cloud resources, and when the resource pools are cloud resources, network resources may be provided for the virtual machine, where the network resources may include network computing bandwidth and network forwarding bandwidth. For ease of description, both the virtual machines that provide the resources and the physical servers will be referred to hereinafter as compute nodes. A resource provided by a computing node. Operations on a resource, such as determining a resource, creating a resource, deleting a resource, etc., referred to hereinafter are understood to be operations on a computing node that provides the resource, such as determining a computing node, creating a computing node, deleting a computing node, etc.

In one aspect, the resource pool scheduler 112 may obtain a performance parameter for each of M resource pools, where M is an integer greater than 1, where the performance parameter of the resource pool is used to indicate a network computation bandwidth and a network forwarding bandwidth provided by resources in the resource pool. Alternatively, the resource pool scheduling device 112 may obtain the traffic data (such as the bandwidth occupied by running the corresponding network service) collected by the resource pool monitoring device 113. The resource pool monitoring device 113 may comprise a plurality of resource pool monitoring sub-devices, each for monitoring a corresponding one of the resource pools.

Further, the resource pool scheduling device 112 may determine the bandwidth variation of the network service according to the traffic data collected by the resource pool monitoring device 113, and determine N resources to be scheduled in the M resource pools according to the respective performance parameters of the M resource pools, where N is a positive integer less than or equal to M.

The resource pool scheduler 112 may generate a scheduling request (or referred to as a scheduling event) of N resources and send the scheduling request to the NFV processing apparatus 111, so that the NFV processing apparatus 111 performs resource scheduling for a network service to use the N resources for running the network service.

The NFV processing apparatus 111 may include: NFV controller (controller) 1111, network function virtualization orchestration (Network Functions Virtualization Orchestrator, NFVO) 1112, and underlying network function virtualization architecture (Network Functions Virtualization Infrastructure, NFVI) 1113. Wherein the NFV controller 1111 is communicatively coupled to the NFVO 1112 and a plurality of NFVI components 1113 (e.g., including 1113-1 to 1113-M), respectively, and the NFVO 1112 is communicatively coupled to the resource pool scheduler 112.

Wherein NFV controller 111 is configured to manage scheduling NFVI component 1113; NFVO 1112 is used to orchestrate and manage the infrastructure, resources, network services of NFV system 110; NFVI component 1113 is configured to manage the resource pools, such as resource pools 120-1 through 120-M, required for NFV to operate network services, providing an operating environment for NFV system 110. NFVI 1113-1 to 1113-M corresponds one-to-one to resource pools 120-1 to 120-M, e.g., NFVI 1113-1 corresponds to resource pool 120-1, and NFVI 1113-1 is used to invoke an interface of resource pool 120-1 to implement resource scheduling.

Illustratively, the resource pool scheduler 112 may generate a scheduling request (or referred to as a scheduling event) for N resources and send the scheduling request to the NFVO 1112. After NFVO 1112 receives the scheduling request, the scheduling request may be orchestrated and sent to NFV controller 1111. After receiving the scheduled scheduling request, the NFV controller 1111 requests NFVI corresponding to each resource pool to which the N resources belong, and the NFVI invokes an interface of the corresponding resource pool to schedule the resources, so that the N resources are used to run the corresponding network service, and a resource scheduling process for the network service is completed.

It should be understood that NFV system 110 may include more or fewer components than the architecture shown in fig. 1, or that some of the components in the architecture shown in fig. 1 may be combined to implement corresponding functions, or that some of the components in the architecture shown in fig. 1 may be split into smaller components to implement corresponding functions, which is not limited in this application. For example, in a network service creation scenario, embodiments of the present application do not require monitoring of real-time traffic of a resource pool, and thus may not include resource pool scheduler 114.

It should be understood that the following details of the method provided in the embodiments of the present application are given by taking the NFV system as an execution body for convenience of understanding and description. The NFV system may be the NFV system 110 shown in fig. 1, which may be implemented as a hardware device or as a software program, which is not limited in this application.

It should be understood that this should not constitute any limitation as to the subject matter of the method provided herein. The method provided in the embodiment of the present application may be executed as a main body of execution of the method provided in the embodiment of the present application, as long as the method provided in the embodiment of the present application can be implemented by executing a program in which a code of the method provided in the embodiment of the present application is recorded. For example, the NFV system in the following embodiments may be implemented as an electronic device, or may be implemented as a chip, a system-on-chip, or other functional modules capable of calling a program and executing the program. The electronic device may be a server, such as a cloud server.

The resource scheduling method of the network service provided by the embodiment of the application can be applied to at least two of the following scenes:

scene one, creation phase of network service.

In scenario one above, the NFV system may trigger resource scheduling by a creation request of a network service, creating resources for the network service in M resource pools.

Scene two, the running phase of the network service.

In the second scenario, the NFV system may trigger resource scheduling by using a real-time state of a resource pool used for running a network service, create resources for the network service in M resource pools, to implement capacity expansion, or delete resources corresponding to the network service in M resource pools, to implement capacity reduction.

In scenario two, in the creation phase of network operation, the NFV system may use the default resource pool of the network service to operate the network service, for example, use the resource pool corresponding to vendor a to operate the network service serving the user of vendor a; or the NFV system may run the network service in accordance with the scene one determined resource.

The resource scheduling method of the network service provided in the embodiment of the present application will be described below in conjunction with the two possible scenarios.

Fig. 2 is an interactive flow diagram of a resource scheduling method 200 of network service according to an embodiment of the present application. As shown in fig. 2, the method 200 includes some or all of the following:

S210, acquiring a first bandwidth of a network service and performance parameters of M resource pools, wherein the resource pools comprise at least one resource, the performance parameters of the resource pools are used for indicating network calculation bandwidths and network forwarding bandwidths provided by the resources in the resource pools, and M is an integer greater than 1;

s220, determining N resources to be scheduled in the M resource pools according to the first bandwidth and the performance parameters of the M resource pools, wherein N is smaller than or equal to a positive integer of M;

and S230, scheduling the N resources as the resources for running the network service.

In the first scenario, the first bandwidth of the network service may be a bandwidth that is required to be occupied by the network service; in the second scenario described above, the first bandwidth of the network service may be a bandwidth variation amount of running the network service, and the bandwidth variation amount may be a bandwidth increase amount or may be a bandwidth decrease amount. Therefore, the embodiment of the application needs to determine N resources to be scheduled for the first bandwidth, so as to implement the bearer of the first bandwidth, thereby ensuring the normal and temperature operation of the network service.

The NFV system may determine N resources carrying a first bandwidth of the network service according to performance parameters of the M resource pools. It should be noted that the resources of N may belong to the same resource pool or belong to different resource pools, which is not limited in this application.

The performance parameters of the resource pool may include performance parameters of each computing node, where the performance parameters of the computing nodes are attribute values of the computing nodes, and the NFV system may read the performance parameters of the computing nodes from the resource pool. The performance parameters of the computing nodes corresponding to the resources in one resource pool may be the same or different, which is not limited in this application. The performance parameters of the compute node may include, but are not limited to:

network card processing capability: t (T) _n (b/s)

Core processor [ ]Central Processing Unit, CPU) dominant frequency: f (F) _c (Hz)

Network card queue: q (Q) _n (A)

Packet average processing clock period: c (C) _P (A)

System processing coefficients: k (K) _s

Wherein K is _s For balancing the impact of software capabilities under the resource pool on network forwarding. The performance parameter may reflect a network computing bandwidth and a network forwarding bandwidth that the computing node has. Exemplary, network computing bandwidth B of a computing node ₁ And network forwarding bandwidth B ₂ The following equations (1) and (2) may be satisfied, respectively.

B ₁ ＝F _c *Q _n /C _P (1)

B ₂ ＝T _n (2)

Assuming that the specifications of the computing nodes in one resource pool are the same, and the number of the computing nodes in the resource pool is N _s Then the resource pool can provide the maximum network bandwidth B for the outside _s Satisfy the following formula (3)

B _s ＝min(B ₂ ,B ₁ )*N _s *K _s (3)

Wherein N is _s Is the number of resources in the resource pool. It should be appreciated that the algorithm (3) may be replaced by the algorithm when the performance parameters of the computing nodes corresponding to different resources in the resource pool are different

i is a positive integer less than or equal to x, and x is a positive integer.

The above formula (3) is a network capability model of a heterogeneous resource pool constructed in the embodiment of the present application. Based on the capability model, network capabilities of heterogeneous resource pools that can be employed by the NFV system can be determined.

In S220 above, the NFV system determines N resources capable of carrying the first bandwidth in the M resource pools. In the capacity expansion scenario in the scenario one and the scenario two, the N resources are resources to be created, and in the capacity reduction scenario in the scenario two, the N resources are created resources in a resource pool that has participated in running the network service.

The bandwidth carrying capacity of the N resources may be determined based on performance parameters of the M resource pools. Assuming that the network computing bandwidth and the network forwarding bandwidth included in each resource in one resource pool are the same, the number of resources bearing the first bandwidth, i.e., N, may be determined according to the first bandwidth and the network computing bandwidth, the network forwarding bandwidth. Further, the N resources are determined from the M resource pools. For example, in the capacity expansion scenario of the first scenario or the second scenario, the M resource pools may be ordered in order of low bandwidth occupancy rate of the resource pools from low to high, and the N resources to be scheduled may be determined preferentially in the resource pool with low bandwidth occupancy rate, e.g. the N resources may be determined from the resource pool with the lowest bandwidth occupancy rate, or the previous K may be determined from low bandwidth occupancy rate to high ₁ And determining partial resources in the N resources respectively in the resource pools. For another example, in the second scenario, the M resource pools may be ordered according to the order of the bandwidth occupancy rates of the resource pools from high to low, and the N resources to be scheduled may be determined preferentially in the resource pool with higher bandwidth occupancy rate, e.g., the N resources may be determined from the resource pool with the highest bandwidth occupancy rate, or the first K from high to low bandwidth occupancy rate ₂ And determining partial resources in the N resources respectively in the resource pools.

Illustratively, each of the N resources includes a network computing bandwidth and a network forwarding bandwidth. At least one of a network computing bandwidth and a network forwarding bandwidth included in the N resources is greater than or equal to the first bandwidth; or the maximum value of the network calculation bandwidth and the network forwarding bandwidth included in the N resources is greater than or equal to the first bandwidth.

In the capacity expansion scenarios of the first scenario and the second scenario, the NFV system in S230 may create the N resources in at least one resource pool of the M resource pools; in the second scenario, the NFV system in S230 may delete the N resources in at least one of the M resource pools. It should be appreciated that for each of the N resources, the NFV system creates the resource or deletes the resource in the resource pool to which the resource corresponds.

Illustratively, the S210 and S220 may be performed by a resource pool scheduling device in the NFV system (e.g., the resource pool scheduling device 112 in fig. 1), and the S230 may be performed by an NFV processing device in the NFV system (e.g., the NFV processing device 111 in fig. 1), for example, implemented by interaction between the NFVO, the NFV controller, and the NFVI.

Therefore, in the embodiment of the present application, in the scenario of heterogeneous resource pools, the NFV system determines N resources to be scheduled in the M resource pools based on performance parameters of each resource pool in the M resource pools, so that the N resources can carry the first bandwidth of the network service, thereby implementing flexible scheduling of virtual network resources in the scenario of heterogeneous resource pools.

In some implementations of S220 above, the NFV system may determine the target parameter according to performance parameters of the M resource pools; and under the target network calculation bandwidth indicated by the target parameter, determining the number N of resources bearing the first bandwidth ₁ And determining the number N of resources carrying the first bandwidth under the target network forwarding bandwidth indicated by the target parameter ₂ The method comprises the steps of carrying out a first treatment on the surface of the Further, according to N ₁ And N ₂ Determining the number N of resources which finally bear the first bandwidth; and finally, determining N resources to be scheduled in the M resource pools.

The target parameters comprise target network calculation bandwidth and target network forwarding bandwidth.

In one example, the target network computing bandwidth is a mean of network computing bandwidths included by the resources in the M resource pools, and the target network forwarding bandwidth is a mean of network forwarding bandwidths included by the resources in the M resource pools.

In another example, the target parameter is a performance parameter of one of the M resource pools. In this case, if the performance parameters of the computing nodes in the one resource pool are the same, the target network computing bandwidth is a network computing bandwidth included in any resource in the one resource pool, and the target network forwarding bandwidth is a network forwarding bandwidth included in any resource in the one resource pool; if the performance parameters of at least two computing nodes in the resource pool are different, the target network computing bandwidth is the average value of the network computing bandwidths of all the resources in the resource pool, and the target network forwarding bandwidth is the average value of the network forwarding bandwidths of all the resources in the resource pool.

The present application is not limited to the determination method of the target parameter, for example, the target parameter may be determined by means of averaging, or the target parameter may be determined by means of variance.

In yet another embodiment, the target parameters include a network computation bandwidth and a network forwarding bandwidth for each resource in the M resource pools, the NFV system may determine the bandwidth carrying capacity of each resource one by one, and add the bandwidth carrying capacities of the plurality of resources to be able to carry the first bandwidth, and determine the N resources. It should be appreciated that the bandwidth carrying capacity of each resource may be determined one by one in the NFV system according to the priority of the resources in the M resource pools. The priority of a resource may be related to the bandwidth occupancy of the resource pool in which the resource is located. The bandwidth carrying capacity of the resource may be determined by the network computing bandwidth and the network forwarding bandwidth of the resource, and may be, for example, a larger value of the network computing bandwidth and the network forwarding bandwidth.

Assuming that the performance parameters of the M resource pools are the same, in the above embodiment, the NFV system may determine N according to the following formula (4);

N＝max(ΔB/B ₂ ,ΔB/B ₁ ) / K _s (4)

where Δb is the first bandwidth. DeltaB/B ₂ /K _s Representing the number N of resources carrying a first bandwidth under the forwarding bandwidth of the target network indicated by the target parameter ₂ ，ΔB/B ₁ /K _s Representing the number N of resources carrying a first bandwidth under the target network calculation bandwidth indicated by the target parameter ₁ 。

In some embodiments, the NFV system will N ₁ And N ₂ The larger value of the number N of resources occupied by cross-resource pool call ₃ The sum is taken as the number N of the resources which finally bear the first bandwidth; wherein the number N of occupied resources is called across resource pools ₃ Based on cross-resource poolsIs used for bandwidth determination. The larger the bandwidth across the resource pool, the more resources are occupied by the cross-resource pool call, i.e., N ₃ The larger. The bandwidth across the resource pool may be less than or equal to the first bandwidth.

Still assuming that the performance parameters of the M resource pools are the same, in the above embodiment, the NFV system may determine N according to the following formula (5):

N＝max(ΔB/B ₂ ,ΔB/B ₁ )/K _s +N _c *B _d (5)

wherein N is _c Network consumption required for transmission across resource pools for unit bandwidth, B _d For bandwidth across resource pools, i.e. N ₃ ＝N _c *B _d 。

In some embodiments, the NFV system determines N resources from the M resource pools based on the first bandwidth, the performance parameters of the M resource pools, and the cost parameters of the M resource pools. Based on the embodiment, the network service cost is reduced under the condition of realizing flexible scheduling of the resources of the heterogeneous resource pool.

Illustratively, the NFV system may determine multiple sets of resources in the M resource pools, each set of resources may include the same or different numbers of resources, based on the first bandwidth and the performance parameters of the M resource pools. And determining a group of resources with the lowest cost from the plurality of groups of resources, and scheduling N resources in the group of resources. Of course, the NFV system may also determine N resources by combining the first bandwidth, the performance parameters of the M resource pools, and the cost parameters of the M resource pools. The cost parameters for the resources in each resource pool may be the same.

Still assuming that the performance parameters of the M resource pools are the same, in the above embodiment, the NFV system may solve the number N of resources that can be expanded or contracted by the resource pool B according to the following equation (6) _i ：

Wherein N is _max The maximum number of resources that can be created for resource pool B. The resource pool B is at least one of N resourcesA pool of resources to which the individual resources belong. In the first scenario, the resource pool B is a resource pool determined by the NFV system from M resource pools and used for providing the first bandwidth bearing capability for the network service, which is an understanding that, in the network service creation stage, it is determined that the resource of the network service may be a capacity expansion of the resource; in the capacity expansion scene of the scene two, the resource pool B is a resource pool for capacity expansion determined by the NFV system from M resource pools in the process of running network services through the resource pool A, and in the capacity reduction scene of the scene two, the resource pool B is a resource pool for capacity reduction determined by the NFV system from M resource pools.

Further, the NFV system may determine N from at least one of the M resource pools, respectively, according to the following equation set (7) _i And resources such that the resources determined from each of the at least one resource pool are a union of N resources and at a minimum cost:

Wherein C is _i A node cost is calculated for one of the resource pools.

In the following, an exemplary description is made of a trigger condition for implementing resource scheduling in the embodiment of the present application in combination with the above two scenarios.

In the first scenario, the NFV system may receive a request for establishing a network service, where the request for establishing a network service may be input by a user operation, or may be sent by an external device, which is not limited in this application. The network service request is used for requesting the NFV system to provide the network service, and the NFV system may take, as the first bandwidth, an initial bandwidth of a corresponding resource pool of the network service according to the establishment request. As mentioned above, the resource pool corresponding to the network service may be a resource pool previously bound to the network service, that is, a default resource pool, or the NFV system may determine the resource pool of the network service from the M resource pools.

In the second scenario, the NFV system may detect an occupied bandwidth of a resource pool used for running the network service, determine a bandwidth occupancy rate of the resource pool according to the occupied bandwidth, and determine a bandwidth variation according to the occupied bandwidth and a preset value when the bandwidth occupancy rate is greater than or equal to an upper threshold or the bandwidth occupancy rate is less than or equal to a lower threshold, where the preset value indicates a desired bandwidth occupancy rate of the resource pool used for running the network service.

The NFV system may detect the occupied bandwidth of a resource pool employed for running the network service by the resource pool monitoring means and send the occupied bandwidth of the resource pool to the resource pool scheduling means, which may be configured to determine the occupied bandwidth B of the resource pool _now And the maximum network bandwidth B of the resource pool _s Determining the bandwidth occupancy T of a resource pool _now ＝B _now /B _s . At bandwidth occupancy T _now Greater than or equal to the upper threshold T _max When triggering a resource capacity expansion event, the first bandwidth Δb=b needing capacity expansion _now /T _exp -B _s Wherein T is _exp A desired bandwidth occupancy for the resource pool; at bandwidth occupancy T _now Less than or equal to the lower threshold T _min When triggering a resource capacity reduction event, a first bandwidth delta B=B requiring capacity reduction _s -B _now /T _exp Wherein T is _exp Desired bandwidth occupancy for the resource pool

The NFV system may also detect an occupied bandwidth of an unused resource pool of the running network service, so as to select a resource pool from which to implement cross-resource expansion based on the occupied bandwidth of the unused resource pool in the process of resource expansion.

It should be noted that, in this embodiment of the present application, when the NFV provides a network service through a resource pool a in M resource pools, expansion or contraction of a cross-resource pool may be implemented in other resource pools in the M resource pools, or expansion or contraction may be implemented in the resource pool a, or both may be implemented, that is, expansion or contraction is implemented when in the resource pool a, and expansion or contraction of a cross-resource pool is implemented in other resource pools in the M resource pools.

It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different bandwidths, data, etc., and do not represent the sequence, and are not limited to the "first" and "second" being different types.

Fig. 3 is a schematic block diagram of an apparatus 300 provided in an embodiment of the present application. As shown in fig. 3, the apparatus 300 may include an acquisition unit 310, a processing unit 320, and a scheduling unit 330.

The obtaining unit 310 may be configured to obtain a first bandwidth of a network service and performance parameters of M resource pools, where the first bandwidth is a bandwidth required to be occupied by the network service, or the first bandwidth is a bandwidth variation for running the network service, the resource pools include at least one resource, and the performance parameters of the resource pools are used to indicate a network computing bandwidth and a network forwarding bandwidth included by the resources in the resource pools, and M is an integer greater than 1; the processing unit 320 may be configured to determine N resources to be scheduled in the M resource pools according to the first bandwidth and performance parameters of the M resource pools, where N is less than or equal to a positive integer of M; the scheduling unit 330 may be configured to schedule the N resources as resources for running the network service.

In some embodiments, the maximum of the network computing bandwidth and the network forwarding bandwidth provided by the N resources is greater than or equal to the first bandwidth.

In some embodiments, the processing unit 320 is specifically configured to: determining target parameters according to the performance parameters of the M resource pools; the target parameters comprise target network calculation bandwidths and target network forwarding bandwidths, the target network calculation bandwidths are the average value of network calculation bandwidths included by resources in the M resource pools, and the target network forwarding bandwidths are the average value of network forwarding bandwidths included by the resources in the M resource pools; or, the target parameter is a performance parameter of one resource pool in the M resource pools; determining the number N of the resources carrying the first bandwidth under the target network calculation bandwidth indicated by the target parameter ₁ And determining the number N of the resources carrying the first bandwidth under the target network forwarding bandwidth indicated by the target parameter ₂ The method comprises the steps of carrying out a first treatment on the surface of the According to the N ₁ And the N is ₂ Determining the number N of resources which finally bear the first bandwidth; determining to-be-determined in the M resource poolsThe N resources scheduled.

In some embodiments, the processing unit 320 is specifically configured to: putting the N into ₁ And the N is ₂ The larger value of the number N of resources occupied by cross-resource pool call ₃ The sum of the two is taken as the number N of the resources which finally bear the first bandwidth; the number of resources occupied by the cross-resource pool call is determined based on the bandwidth of the cross-resource pool.

In some embodiments, the processing unit 320 is specifically configured to: and determining N resources from the M resource pools according to the first bandwidth, the performance parameters of the M resource pools and the cost parameters of the M resource pools.

In some embodiments, the scheduling unit 330 is specifically configured to: the first bandwidth is the bandwidth increment when the network service is operated, and the resource is established in a resource pool corresponding to each resource in the N resources; or, the first bandwidth is a bandwidth reduction amount when the network service is operated, and the resource is deleted for each resource in the N resources.

In some embodiments, the obtaining unit 330 is specifically configured to: receiving an establishment request of the network service; and taking the initial bandwidth of the resource pool corresponding to the network service as the first bandwidth.

In some embodiments, the obtaining unit 330 is specifically configured to: detecting the occupied bandwidth of a resource pool adopted for running the network service; determining the bandwidth occupancy rate of the resource pool according to the occupied bandwidth; and when the bandwidth occupancy rate is greater than or equal to an upper threshold value or the bandwidth occupancy rate is less than or equal to a lower threshold value, determining the bandwidth variation according to the occupied bandwidth and a preset value, wherein the preset value represents the expected bandwidth occupancy rate of a resource pool used for running the network service.

It should be understood that the specific process of each unit performing the corresponding steps has been described in detail in the above method embodiments, and is not described herein for brevity.

Fig. 4 is a schematic structural diagram of an electronic device 400 according to an exemplary embodiment of the present application. The electronic device 400 may be one implementation of the NFV system in the method embodiment above. As shown in fig. 4, the electronic device 400 includes: a memory 410 and a processor 420.

Memory 410 is used to store computer programs and may be configured to store various other data to support operations on the electronic device. The memory 410 may be an object store (Object Storage Service, OSS).

A processor 420, coupled to the memory 410, is for executing the computer program in the memory 410 for implementing the method implemented by the NFV system in the method embodiments above.

Further, as shown in fig. 4, when the electronic device is implemented as a cloud server, the method may further include: firewall 430, load balancer 440, communication component 450, power component 460, and other components. Only some of the components are schematically shown in fig. 4, which does not mean that the electronic device only comprises the components shown in fig. 4.

It should be appreciated that the electronic device 400 shown in fig. 4 is capable of implementing the various processes related to the NFV system in the method embodiments above. The operations and/or functions of the respective modules in the electronic device 400 are respectively for implementing the respective flows in the above-described method embodiments. Reference is specifically made to the description in the above method embodiments, and detailed descriptions are omitted here as appropriate to avoid repetition.

The application also provides a processing device, which comprises at least one processor, wherein the at least one processor is used for executing the computer program stored in the memory, so that the processing device executes the method executed by the NFV system in the method embodiment.

The embodiment of the application also provides a processing device which comprises a processor and an input/output interface. The input-output interface is coupled with the processor. The input/output interface is used for inputting and/or outputting information. The information includes at least one of instructions and data. The processor is configured to execute a computer program, so that the processing device executes a method executed by the NFV system in the method embodiment described above.

The embodiment of the application also provides a processing device, which comprises a processor and a memory. The memory is used for storing a computer program, and the processor is used for calling and running the computer program from the memory, so that the processing device executes the method executed by the NFV system in the method embodiment.

It should be understood that the processing means described above may be one or more chips. For example, the processing device may be a field programmable gate array (field programmable gate array, FPGA), an application specific integrated chip (application specific integrated circuit, ASIC), a system on chip (SoC), a processor (central processor unit, CPU), a network processor (network processor, NP), a digital signal processing circuit (digital signal processor, DSP), a microcontroller (micro controller unit, MCU), a programmable controller (programmable logic device, PLD) or other integrated chip.

In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.

It should be noted that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capability. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, or discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It will be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

According to the method provided by the embodiment of the application, the application further provides a computer program product, which comprises: computer program code which, when run on a computer, causes the computer to perform the method performed by the NFV system in the method embodiment described above.

According to the method provided in the embodiment of the present application, there is further provided a computer readable storage medium storing a program code, which when executed on a computer, causes the computer to perform the method performed by the NFV system in the embodiment of the method.

The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A resource scheduling method for network services, which is applied to a network function virtualization NFV system, comprising:

acquiring a first bandwidth of a network service and performance parameters of M resource pools, wherein the first bandwidth is a bandwidth required to be occupied by the network service or the first bandwidth is a bandwidth variation for running the network service, the resource pools comprise at least one resource, the performance parameters of the resource pools are used for indicating network calculation bandwidth and network forwarding bandwidth included by the resources in the resource pools, and M is an integer greater than 1;

According to the first bandwidth and the performance parameters of the M resource pools, N resources to be scheduled in the M resource pools are determined, wherein N is smaller than or equal to a positive integer of M;

and scheduling the N resources as the resources for running the network service.

2. The method of claim 1, wherein a maximum of the network computing bandwidth and the network forwarding bandwidth provided by the N resources is greater than or equal to the first bandwidth.

3. The method of claim 2, wherein the determining N resources to be scheduled in the M resource pools according to the first bandwidth and the performance parameters of the M resource pools comprises:

determining target parameters according to the performance parameters of the M resource pools; the target parameters comprise target network calculation bandwidths and target network forwarding bandwidths, wherein the target network calculation bandwidths are the average value of network calculation bandwidths of the M resource pools, and the target network forwarding bandwidths are the average value of network forwarding bandwidths of the M resource pools; or the target parameter is a performance parameter of one resource pool in the M resource pools;

determining the number N of resources bearing the first bandwidth under the target network calculation bandwidth indicated by the target parameter ₁ And determining the number N of resources carrying the first bandwidth under the target network forwarding bandwidth indicated by the target parameter ₂ ；

According to the N ₁ And said N ₂ Determining the number N of resources which finally bear the first bandwidth;

and determining the N resources to be scheduled in the M resource pools.

4. A method according to claim 3, wherein said step of determining said N ₁ And said N ₂ Determining the number N of resources that ultimately carry the first bandwidth, including:

the N is set to ₁ And said N ₂ The larger value of the number N of resources occupied by cross-resource pool call ₃ And, as the number N of resources which finally bear the first bandwidth; wherein,,

the number of resources occupied by the cross-resource pool call is determined based on the bandwidth of the cross-resource pool.

5. The method according to any one of claims 1 to 4, wherein determining N resources to be scheduled in the M resource pools according to the first bandwidth and the performance parameters of the M resource pools comprises:

and determining N resources from the M resource pools according to the first bandwidth, the performance parameters of the M resource pools and the cost parameters of the M resource pools.

6. The method of any of claims 1 to 4, wherein the first bandwidth is a bandwidth variance of operating the network service, the method further comprising:

if the first bandwidth is the bandwidth increment when the network service is operated, establishing the resource in a resource pool corresponding to each resource in the N resources; or,

and if the first bandwidth is the bandwidth reduction amount when the network service is operated, deleting the resource for each resource in the N resources.

7. The method according to any one of claims 1 to 4, wherein the first bandwidth is a bandwidth required to be occupied by the network service, and the obtaining the first bandwidth of the network service includes:

receiving an establishment request of the network service;

and taking the initial bandwidth of the resource pool corresponding to the network service as the first bandwidth.

8. The method according to any one of claims 1 to 4, wherein the first bandwidth is a bandwidth variation for running the network service, and the obtaining the first bandwidth sum of the network service includes:

detecting the occupied bandwidth of a resource pool adopted for running the network service;

Determining the bandwidth occupancy rate of the resource pool according to the occupied bandwidth;

and when the bandwidth occupancy rate is greater than or equal to an upper threshold value or the bandwidth occupancy rate is less than or equal to a lower threshold value, determining the bandwidth variation according to the occupied bandwidth and a preset value, wherein the preset value represents the expected bandwidth occupancy rate of a resource pool adopted for running the network service.

9. An electronic device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the method of any one of claims 1 to 8.

10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 9.

11. An NFV system, comprising: the system comprises a resource pool scheduling device and an NFV processing device, wherein the resource pool scheduling device is in communication connection with the NFV processing device;

The resource pool scheduling device is used for:

acquiring a first bandwidth of a network service and performance parameters of M resource pools, wherein the first bandwidth is a bandwidth required to be occupied by the network service or the first bandwidth is a bandwidth variation when the network service is operated, the resource pools comprise at least one resource, the performance parameters of the resource pools are used for indicating network calculation bandwidth and network forwarding bandwidth provided by the resources in the resource pools, and M is an integer greater than 1;

according to the first bandwidth and the performance parameters of the M resource pools, N resources to be scheduled in the M resource pools are determined, wherein N is smaller than or equal to M, and N is a positive integer;

the NFV processing means is configured to schedule the N resources as resources for running the network service.

12. The system of claim 11, further comprising: the resource pool monitoring device is in communication connection with the resource pool scheduling device;

the resource pool monitoring device is used for detecting occupied bandwidth of a resource pool adopted by running the network service;

the resource pool scheduling device is further configured to determine the bandwidth variation according to the occupied bandwidth and a preset value when the occupied bandwidth is greater than or equal to an upper threshold or the occupied bandwidth is less than or equal to a lower threshold, where the preset value represents an expected bandwidth occupation amount of a resource pool used for running the network service.