CN113672382B

CN113672382B - Service resource allocation method and device, electronic equipment and storage medium

Info

Publication number: CN113672382B
Application number: CN202110820656.8A
Authority: CN
Inventors: 张伟; 宋泽辉; 辛文
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-07-20
Filing date: 2021-07-20
Publication date: 2024-03-26
Anticipated expiration: 2041-07-20
Also published as: CN113672382A

Abstract

The disclosure relates to a service resource allocation method, a device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring the resource characteristic data of the current online service, determining a mixed time period and mixed resources of the physical machines according to the load information in the resource characteristic data of the current online service, and distributing the offline service to a first physical machine corresponding to the current online service according to the mixed time period and the mixed resources, wherein the load resources of the first physical machine occupied by the offline service are smaller than the mixed resources, and the first physical machine jointly operates the offline service and the current online service in the mixed time period. The method can acquire the maximum limit and the operation time of the operation resources occupied by the offline service, so that the offline service can be distributed to the physical machine as much as possible under the condition of not influencing the online service, and the resource utilization rate of the physical machine is improved. The method can also set a service priority mechanism and a real-time detection mechanism, thereby improving the accuracy and the flexibility of resource allocation.

Description

Service resource allocation method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of cloud computing, and in particular relates to a service resource allocation method, a service resource allocation device, electronic equipment and a storage medium.

Background

The scale of modern internet data centers is larger and larger along with the increase of application service demands, but the low utilization rate of data center resources is gradually a constraint factor for further development of cloud computing. The mixed calculation realizes the multiplexing of online resources by the mixed deployment of offline service and online service, so that the mode of improving the overall utilization rate of resources is important to improve the utilization rate of resources of a data center.

In the related art, the hybrid deployment of the offline service and the online service is performed on the physical machine, and the method relies on a preset static resource template to acquire fixed hybrid resources in a specific time range, or relies on manual and past experience to perform judgment, and corresponding parameters such as an upper limit of resources are set, so that the accuracy of service resource allocation is reduced, and the resource utilization rate of the physical machine is reduced.

Disclosure of Invention

The disclosure provides a service resource allocation method, a device, an electronic device and a storage medium, so as to at least solve the problems of low accuracy of service resource allocation and low resource utilization rate of a physical machine in the related art. The technical scheme of the present disclosure is as follows:

According to a first aspect of an embodiment of the present disclosure, there is provided a service resource allocation method, including:

acquiring the resource characteristic data of the current online service running on each physical machine, wherein the resource characteristic data represents characteristic information related to the resource load of the current online service during running;

determining a mixed section time period and mixed section resources of each physical machine based on the resource characteristic data, wherein the mixed section time period represents a time period for the current online service and offline service to co-operate, and the mixed section resources represent available offline resources of the physical machine corresponding to the current online service in the mixed section time period;

and distributing the offline service to a first physical machine with the mixed time period and the mixed resources, so that the first physical machine runs the offline service by utilizing the mixed resources in the mixed time period.

As an alternative embodiment, the method further comprises:

acquiring a service priority corresponding to the current online service;

and under the condition that the service priority of the current online service is a first priority, acquiring the resource characteristic data of the current online service, wherein the first priority is the service priority corresponding to the non-load-sensitive online service, and a mixed time period exists between the non-load-sensitive online service and the offline service.

As an optional embodiment, the resource feature data includes a sensitive time period and a service resource threshold, the service resource threshold characterizes an upper limit threshold of a physical machine load resource when the current online service is operated, and determining, based on the resource feature data, a mixed time period and a mixed resource of each physical machine includes:

determining other time periods except the sensitive time period in a preset service period as the mixed time period;

determining a target service resource threshold corresponding to the current online service running in the mixed section time period from the service resource threshold;

acquiring the current load resource of each physical machine;

and determining the mixed part resources according to the target business resource threshold and the current load resources of the physical machine.

As an optional embodiment, the current online service includes a plurality of current online services, and determining the other time periods except the sensitive time period in the preset service period as the mixed time period includes:

determining a union time period among sensitive time periods of a plurality of current online services running on each physical machine;

determining other time periods except the union time period in the service period as the mixing section time period;

The determining, from the service resource thresholds, a target service resource threshold corresponding to the current online service running in the mixed section period includes:

determining a mixed operation business operated on each physical machine in the mixed time period;

acquiring a service resource threshold corresponding to the current online service of the mixed part operation from the service resource threshold;

and determining the minimum value in the service resource threshold corresponding to the mixed part operation service as the target service resource threshold.

As an alternative embodiment, the method further comprises:

acquiring a newly added online service corresponding to the first physical machine;

and under the condition that the service priority corresponding to the newly added online service is a second priority, distributing the offline service running on the first physical machine to a second physical machine, wherein the second priority represents the service priority corresponding to the load-sensitive online service, and a mixed section time period does not exist between the load-sensitive online service and the offline service.

As an optional embodiment, after the obtaining the newly added online service corresponding to the first physical machine, the method further includes:

acquiring resource characteristic data of the newly added online service under the condition that the service priority of the newly added online service is a first priority;

Updating the mixed part time period and the mixed part resources corresponding to the first physical machine according to the resource characteristic data of the newly-added online service;

comparing the updated mixed section time period with the mixed section time period corresponding to the first physical machine;

acquiring offline business load resources, wherein the offline business load resources represent load resources occupied by offline business running on the first physical machine;

comparing the updated mixed part resource with the offline business load resource;

and distributing the offline service running on the first physical machine to a third physical machine under the condition that the updated mixed section time period is smaller than the mixed section time period or the updated mixed section resource is smaller than the offline service load resource.

As an alternative embodiment, the method further comprises:

acquiring service portrait information of a preset service;

and determining the service priority, the sensitive time period and the service resource threshold of the preset service according to the service portrayal information.

According to a second aspect of embodiments of the present disclosure, there is provided a service resource allocation apparatus, the apparatus including:

the system comprises a feature data acquisition module, a feature data processing module and a feature data processing module, wherein the feature data acquisition module is configured to acquire resource feature data of a current online service running on each physical machine, and the resource feature data represents feature information related to a resource load when the current online service runs;

An online service resource determining module configured to determine a mixed time period and mixed resources of each physical machine based on the resource feature data, wherein the mixed time period represents a time period for the current online service to co-operate with an offline service, and the mixed resources represent available offline resources of the physical machine corresponding to the current online service in the mixed time period;

and the offline service allocation module is configured to perform the allocation of the offline service to the first physical machine with the mixed time period and the mixed resource, so that the first physical machine runs the offline service by using the mixed resource in the mixed time period.

As an alternative embodiment, the apparatus further comprises:

the service priority acquisition module is configured to acquire the service priority corresponding to the current online service;

the first priority determining module is configured to execute to obtain resource feature data of the current online service when the service priority of the current online service is a first priority, wherein the first priority is a service priority corresponding to a non-load-sensitive online service, and a mixed time period exists between the non-load-sensitive online service and the offline service.

As an alternative embodiment, the resource feature data includes a sensitive time period and a service resource threshold, the service resource threshold represents an upper threshold of a physical machine load resource when running a current online service, and the online service resource determining module includes:

a mixed section period acquisition unit configured to perform determination of other periods than the sensitive period in a preset service period as the mixed section period;

a target threshold value acquisition unit configured to perform determining a target service resource threshold value corresponding to a current online service running in the mixed time period from the service resource threshold values;

the current load acquisition unit is configured to acquire the current load resources of each physical machine;

and the mixed part resource determining unit is configured to determine the mixed part resource according to the target business resource threshold and the current load resource of the physical machine.

As an optional embodiment, the current online service includes a plurality of current online services, and the mixed period acquiring unit includes:

a union time period determination unit configured to perform determination of a union time period between sensitive time periods of each current online service;

A mixed section period determining unit configured to perform determination of other periods of the service period than the union period as the mixed section period;

the target threshold acquisition unit includes:

an operation service threshold value obtaining unit configured to obtain a service resource threshold value corresponding to each current online service operated in the mixed section time period from the service resource threshold values;

and a target threshold determining unit configured to perform determination of a minimum value of the corresponding service resource thresholds as the target service resource threshold.

As an alternative embodiment, the apparatus further comprises:

the new-added service acquisition module is configured to execute and acquire a new-added online service corresponding to the first physical machine;

the first offline service reassignment module is configured to execute the assignment of the offline service running on the first physical machine to the second physical machine under the condition that the service priority corresponding to the newly added online service is a second priority, wherein the second priority represents the service priority corresponding to the load-sensitive online service, and a mixed section time period does not exist between the load-sensitive online service and the offline service.

As an alternative embodiment, the apparatus further comprises:

the new feature acquisition module is configured to acquire resource feature data of the new online service under the condition that the service priority of the new online service is a first priority;

the data updating module is configured to execute updating the mixed time period and the mixed resource corresponding to the first physical machine according to the resource characteristic data of the newly added online service;

the time period comparison module is configured to execute comparison of the updated mixed time period and the mixed time period corresponding to the first physical machine;

the offline business resource acquisition module is configured to perform acquisition of offline business load resources, wherein the offline business load resources represent load resources occupied by offline business running on the first physical machine;

the resource comparison module is configured to compare the updated mixed part resource with the offline business load resource;

and the second offline service reassignment module is configured to execute the offline service running on the first physical machine to a third physical machine when the updated mixed time period is smaller than the mixed time period or the updated mixed resource is smaller than the offline service load resource.

As an alternative embodiment, the apparatus further comprises:

a service portrayal information acquisition module configured to perform acquisition of service portrayal information of a preset service;

and the preset feature acquisition module is configured to determine the service priority, the sensitive time period and the service resource threshold of the preset service according to the service portraits.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the service resource allocation method as described above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform a method of traffic resource allocation as described above.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer instructions, characterized in that the computer instructions, when executed by a processor, implement the above-mentioned service resource allocation method.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

acquiring the resource characteristic data of the current online service, determining a mixed time period and mixed resources of the current online service according to the load information in the resource characteristic data of the current online service, and distributing the offline service to a first physical machine corresponding to the current online service according to the mixed time period and the mixed resources, wherein the load resources of the first physical machine occupied by the offline service are smaller than the mixed resources, and the first physical machine jointly operates the offline service and the current online service in the mixed time period. The method can acquire the maximum limit and the operation time of the operation resources occupied by the offline service, so that the offline service can be distributed to the physical machine as much as possible under the condition of not influencing the online service, and the resource utilization rate of the physical machine is improved.

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

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 is a schematic view of an application scenario of a service resource allocation method according to an exemplary embodiment.

Fig. 2 is a schematic diagram illustrating a distributed block chain structure of a service resource allocation method according to an exemplary embodiment.

Fig. 3 is a flow chart illustrating a method of traffic resource allocation according to an exemplary embodiment.

Fig. 4 is a flowchart illustrating a method for determining whether to perform a service resource allocation task according to a service priority in a service resource allocation method according to an exemplary embodiment.

Fig. 5 is a flowchart illustrating a method for determining a mix period and mix resources of a current online service in a service resource allocation method according to an exemplary embodiment.

Fig. 6 is a flowchart illustrating a method for determining a mix period and mix resources of a current online service in the case of a plurality of current online services in a service resource allocation method according to an exemplary embodiment.

Fig. 7 is a schematic diagram illustrating determining a mix period and mix resources when the number of online traffic is a plurality in a traffic resource allocation method according to an exemplary embodiment.

Fig. 8 is a flowchart illustrating a method for offline task reassignment after adding an online service in a service resource assignment method according to an exemplary embodiment.

Fig. 9 is a block diagram illustrating a structure of a service resource allocation apparatus according to an exemplary embodiment.

Fig. 10 is a block diagram of an electronic device, according to an example embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

Fig. 1 is a schematic application scenario of a service resource allocation method according to an exemplary embodiment, as shown in fig. 1, where the application scenario may include a physical machine 110 and a resource allocation server 120, where the resource allocation server 120 obtains resource feature data of a current online service on the physical machine 110, the resource allocation server 120 determines a mixed time period and mixed resources of the physical machine 110 according to the resource feature data, and allocates a corresponding offline service to the physical machine 110 according to the mixed time period and the mixed resources, and the physical machine 110 operates the offline service in the mixed time period.

In the embodiment of the present disclosure, as shown in fig. 2, the physical machine 110 and the resource allocation server 120 may be a block chain structure, and the block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. The blockchain is essentially a decentralised database, the blockchain technology does not depend on an additional third party management mechanism or hardware facilities, the center control is not needed, and each node realizes information self-verification, transmission and management through distributed accounting and storage except the self-integrated blockchain.

Generally, blockchain systems consist of a data layer, a network layer, a consensus layer, an incentive layer, a contract layer, and an application layer. The data layer encapsulates the underlying data blocks and related basic data such as data encryption and time stamps and basic algorithms; the network layer comprises a distributed networking mechanism, a data transmission mechanism, a data verification mechanism and the like; the consensus layer mainly encapsulates various consensus algorithms of the network node; the incentive layer integrates economic factors into a blockchain technology system and mainly comprises an issuing mechanism, an allocation mechanism and the like of economic incentives; the contract layer mainly encapsulates various scripts, algorithms and intelligent contracts, and is the basis of programmable characteristics of the block chain; the application layer encapsulates various application scenarios and cases of the blockchain.

Fig. 3 is a flowchart illustrating a service resource allocation method according to an exemplary embodiment, which is used at a resource allocation server side, as shown in fig. 3, and includes the following steps.

S310, acquiring the resource characteristic data of the current online service running on each physical machine, wherein the resource characteristic data represents the characteristic information related to the resource load when the current online service runs;

as an alternative embodiment, referring to fig. 4, before acquiring the resource feature data of the current online service running on each physical machine, the method further includes:

s410, acquiring service priority corresponding to the current online service;

s420, judging whether the service priority corresponding to the current online service is a first priority;

s430, acquiring the resource characteristic data of the current online service under the condition that the service priority of the current online service is the first priority.

As an alternative embodiment, the resource allocation server obtains a service priority of a current online service on the first physical machine. The service priority may be a first priority, where the first priority is a service priority corresponding to a non-load-sensitive online service, a mixed time period exists between the non-load-sensitive online service and an offline service, and the current online service corresponding to the first priority includes a service that is sensitive to a CPU load and has a service low peak period and a service peak period, and may be deployed on the same physical machine as the offline service during the service low peak period; or the service is insensitive to CPU load, but has a requirement on the upper load limit of the physical machine, and the service can be deployed on the same physical machine as the offline service in the service period under the condition that the load of the physical machine does not reach the upper load limit; or the service is insensitive to CPU load and has no requirement on the upper limit of the load of the physical machine, and the service can be deployed on the same physical machine as the offline service in the service period.

At this time, the resource allocation server can continue to execute the service resource allocation task to acquire the resource characteristic data of the current online service. And according to the resource characteristic data, carrying out the subsequent steps of determining the mixed time period and the mixed resources, and distributing the offline service to the first physical machine.

Based on the service priority, whether the current online service can be operated on the same physical machine as the offline service is determined, and when the current online service can be operated together with the offline service, the offline service allocation task is continuously executed, so that the load resource utilization rate of the physical machine is improved, the operation efficiency of the physical machine is improved, and the operation cost of the physical machine is reduced.

As an alternative embodiment, after acquiring the service priority of the current online service, the method further includes:

s440, closing a service resource allocation task under the condition that the service priority corresponding to the current online service is the second priority, and not executing the step of acquiring the resource characteristic data of the current online service running on each physical machine to allocate the offline service to the first physical machine with the mixed time period and the mixed resource.

As an alternative embodiment, the resource allocation server obtains a service priority of a current online service on the first physical machine. The service priority may be a second priority, where the second priority characterizes a service priority corresponding to the load-sensitive online service, where there is no mixed time period between the load-sensitive online service and the offline service, and the current online service corresponding to the second priority is extremely sensitive to the load of the central processing unit (central processing unit, CPU), and cannot be deployed on the same physical machine as the offline service, so when the resource allocation server determines that the service priority corresponding to the current online service on the first physical machine is the second priority, the service resource allocation task is closed, and any offline service is not allocated to the first physical machine.

And determining whether the current online service can be operated on the same physical machine as the offline service or not based on the service priority, and ensuring the load resource required by the current online service corresponding to the second priority.

S320, determining a mixed part time period and mixed part resources of each physical machine based on the resource characteristic data, wherein the mixed part time period represents a time period for the current online service and the offline service to jointly operate, and the mixed part resources represent available offline resources of the physical machines corresponding to the current online service in the mixed part time period;

as an alternative embodiment, the method further comprises:

acquiring service portrait information of a preset service;

As an optional embodiment, the resource feature data characterizes load information corresponding to the preset service, where the load information includes load information of the preset service and load information of the physical machine, that is, the resource feature data includes a sensitive time period and a service resource threshold. The sensitive time period is a time period in which the preset service cannot co-operate with the offline service, for example, the preset service A cannot co-operate with the offline service from 7 pm to 1 am, and the sensitive time period from 7 pm to 1 am is the preset service. The service resource threshold represents an upper limit threshold of a physical machine load resource when the preset service is operated, for example, the service resource threshold of the preset service A is 30%, which indicates that the upper limit of the physical load resource is 30% when the preset service A is operated, and the operation of the preset service A is affected when the load resource exceeds 30%.

Acquiring service portrayal information of a preset service, acquiring a sensitive time period and a service resource threshold of the preset service according to the service portrayal information of the preset service, and determining a service priority corresponding to the preset service. The service portrayal information may be configuration information corresponding to a preset service. The service priority may include a first priority and a second priority, where the preset service corresponding to the second priority cannot be deployed on the same physical machine as the offline service, and a sensitive period of the preset service corresponding to the second priority is equal to a service period, for example, when the service period is 24 hours, the sensitive period of the preset service corresponding to the second priority is 24 hours, which may be represented as "sensitive period= [ 0:00-24:00 ]". The preset service corresponding to the second priority cannot be operated together with the offline service, and the service resource threshold is established on the basis that the preset service and the offline service can be operated together, and the load of a part of the physical machine is required to be used for operating the offline service, so that whether the service resource of the preset service corresponding to the second priority is limited by the threshold can be not considered.

The first priority may include a first preset priority, a second preset priority, and a third preset priority, and the preset service corresponding to the first preset priority, the preset service corresponding to the second preset priority, and the preset service corresponding to the third preset priority may be deployed on the same physical machine as the offline service. The preset service corresponding to the first preset priority may be deployed on the same physical machine during the service low peak period and the offline service, where the sensitive time period of the preset service corresponding to the first preset priority is the service peak period, for example, the service peak period of the preset service corresponding to the first preset priority is 18:00 to 24:00, 18:00 to 24:00 is a sensitive time period of the preset service, and can be expressed as "sensorperiod= [ 18:00-24:00 ]". Since the preset service corresponding to the first preset priority has a service peak period and a service low peak period, the physical machine running the preset service corresponding to the first preset priority is limited by a service resource threshold, and the service resource threshold may be expressed as "sendeuusagelimit=limit", that is, an upper limit exists in load resource usage.

The preset service corresponding to the second preset priority may be deployed on the same physical machine as the offline service in the service period, and the preset service insensitive time period corresponding to the second preset priority may be represented as "sensitive period= [ ]. The physical machine running the preset service corresponding to the second preset priority is limited by a service resource threshold, where the service resource threshold may be expressed as "sensorusagelimit=limit", that is, there is an upper limit for load resource usage.

The preset service corresponding to the third preset priority may be deployed on the same physical machine as the offline service in the service period, and the preset service insensitive time period corresponding to the third preset priority may be represented as "sensitive period= [ ]. And the physical machine running the preset service corresponding to the third preset priority is not limited by the service resource threshold, and the use of load resources is not limited.

The preset services are classified according to the service priorities, so that different strategies for running offline services at the mixed part can be formulated aiming at the preset services corresponding to different service priorities, and the accuracy of resource allocation is improved.

As an alternative embodiment, referring to fig. 5, determining the mix time period and the mix resource of the current online service according to the resource feature data includes:

S510, determining other time periods except a sensitive time period in a preset service period as mixed time periods;

s520, determining a target service resource threshold corresponding to the current online service running in the mixed section time period from service resource thresholds;

s530, acquiring current load resources of each physical machine;

s540, determining mixed part resources according to the target business resource threshold and the current load resources of the physical machine.

As an alternative embodiment, the sensitive time period and the service resource threshold of the current online service can be obtained according to the resource characteristic data of the current online service. And removing the sensitive time period from the preset service period, so as to obtain the mixed time period. For example, the sensitive period of current online service a is 18:00 to 24:00, service period is 0:00 to 24:00, the mixed period is 0:00 to 18:00, and the current online service can be operated together with the offline service in the mixed period.

And determining a target service resource threshold corresponding to the current online service running in the mixed time period from the service resource threshold of the current online service, wherein the target service resource threshold is the maximum load of a physical machine when the current online service is running in the mixed time period. And acquiring the current load resource of the physical machine, wherein the current load resource of the physical machine is the load resource occupied by the online service, and determining the mixed resource on the physical machine based on the target service resource threshold and the current load resource of the physical machine. For example, if the service resource threshold of the current online service a is that the physical machine load upper limit is 30%, the physical machine load upper limit is 30% as the maximum load of the physical machine when the current online service a is operated in the mixed period. And then obtaining the current load resource of the physical machine, and subtracting the current load resource of the physical machine from the target service resource threshold value to obtain the mixed resource. For example, in the mixed section period, the current load of the physical machine is 10%, the target service resource threshold value is subtracted by the current load resource of the physical machine, and the obtained mixed section resource is 20%, that is, the offline service running on the physical machine occupies no more than 20% of the physical machine load resource.

According to the sensitive time period and the service resource threshold, the mixed time period and the mixed resource are determined, and meanwhile, the requirements of two dimensions of the running time and the running resource are considered, so that the stability of the online service can be effectively ensured, and the offline service cannot influence the online service.

As an alternative embodiment, referring to fig. 6, the current online service includes a plurality of current online services, and determining a mixed time period and a mixed resource of the current online service according to the resource feature data includes:

s610, determining a union time period among sensitive time periods of a plurality of current online services running on each physical machine;

s620, determining other time periods except the union time period in the service period as mixed time periods;

determining a target traffic resource threshold corresponding to each current online traffic running in the mixed time period from the traffic resource thresholds comprises:

s630, determining mixed operation business operated on each physical machine in the mixed time period;

s640, acquiring a service resource threshold corresponding to the current online service of the mixed part operation from the service resource threshold;

s650, determining the minimum value in service resource thresholds corresponding to the mixed part operation service as a target service resource threshold.

As an alternative embodiment, when the number of the current online services is plural, please refer to fig. 7, which is a schematic diagram of determining the blending period and the blending resource when the number of the online services is plural, as shown in fig. 7. And according to the resource characteristic data of the current online service, a sensitive time period and a service resource threshold value of each current online service can be obtained. And determining a union time period among sensitive time periods of each current online service, removing the union time period from a preset service period, and obtaining the rest time period as a mixed time period. For example, the sensitive period of the current online service a is 18:00 to 24:00, the sensitive time period of the current online service B is 14:00 to 20:00, the union time period is taken to be 14:00 to 24:00. And when the preset service period is 0:00 to 24:00, the mixing period is 0:00 to 14:00, and the current online service can be operated together with the offline service in the mixing period.

And determining a mixed part operation service operated on each physical machine in the mixed part time period, determining a service resource threshold corresponding to the mixed part operation service from service resource thresholds of the current online service, and taking the minimum value in the target service resource thresholds as a target service resource threshold. And obtaining the current load resource of the physical machine, wherein the current load resource of the physical machine is the sum value of the resources occupied by a plurality of current online services, and subtracting the current load resource of the physical machine from the target service resource threshold value to obtain the mixed resource. For example, the current service resource threshold of the online service A is 30% of the physical machine load upper limit, the current service resource threshold of the online service B is 40% of the physical machine load upper limit, and the physical machine load upper limit is 30% as the target service resource threshold. And in the mixed section time period, the load resource of the physical machine occupied by the current online service A is 10%, the load resource of the physical machine occupied by the current online service B is 5%, and the current load resource of the physical machine is 15%. Subtracting the current load resource of the physical machine from the target service resource threshold to obtain 15% of mixed part resource, that is to say, the offline service running on the physical machine occupies no more than 20% of the load of the physical machine.

When the method has a plurality of current online services, the minimum value in the union of sensitive time periods and the service resource threshold can be obtained, the mixed time period and the mixed resource can be determined, and the operation requirements of the plurality of current online services can be met at the same time, so that the stability of the operation of the current online services is ensured.

S230, distributing the offline service to the first physical machine with the mixed time period and the mixed resources, so that the first physical machine runs the offline service by using the mixed resources in the mixed time period.

As an alternative embodiment, referring to fig. 8, the method further includes:

s810, acquiring a newly-added online service corresponding to a first physical machine;

s820, identifying service priority corresponding to the newly added online service;

s830, distributing the offline service running on the first physical machine to the second physical machine under the condition that the service priority of the newly-added online service is the second priority.

As an alternative embodiment, the offline service is allocated to the first physical machine according to the mix time period and the mix resource, and the first physical machine operates the offline service during the mix time period. The distribution of the offline service can be adjusted in real time according to the scheduling of the online service, when the newly added online service is scheduled to the first physical machine, the service priority corresponding to the task of the newly added online service is detected first, and when the service priority corresponding to the newly added online service is the second priority, the offline service running on the offline first physical machine is required because the newly added online service corresponding to the second priority cannot run together with the offline service, and the offline service on the first physical machine is distributed to the second physical machine. The second physical machine is a different physical machine from the first physical machine, the second physical machine is a physical machine which does not currently run the current online service corresponding to the second priority, and the load resource of the second physical machine can bear the offline service.

Detecting newly added online service on physical machine in real time, determining whether to redistribute offline service according to service priority corresponding to newly added online service, and improving real-time performance of service scheduling

As an optional embodiment, after obtaining the newly added online service corresponding to the first physical machine, the method further includes:

s840, acquiring resource characteristic data of the newly added online service under the condition that the service priority corresponding to the newly added online service is the first priority;

s850, updating the mixed part time period and the mixed part resources corresponding to the first physical machine according to the resource characteristic data of the newly added online service;

s860, comparing the updated mixed section time period with the mixed section time period corresponding to the first physical machine;

s870, acquiring offline service load resources, wherein the offline service load resources represent load resources occupied by offline service running on a first physical machine;

s880, comparing the updated mixed part resources with offline business load resources;

s880, distributing the offline service running on the first physical machine to the third physical machine under the condition that the updated mixed section time period is smaller than the mixed section time period or the updated mixed section resource is smaller than the offline service load resource.

As an optional embodiment, in the case that the service priority corresponding to the newly added online service is the first priority, the mixed time period and the mixed resource on the first physical machine after the newly added online service need to be recalculated. And acquiring the resource characteristic data of the newly-added online service to obtain a sensitive time period and a service resource threshold of the newly-added online service. And updating the mixed part time period corresponding to the first physical machine according to the sensitive time period of the newly-added online service, and updating the mixed part resources corresponding to the first physical machine according to the service resource threshold of the newly-added online service and the updated mixed part time period.

And comparing the updated mixed section time period with the mixed section time period corresponding to the first physical machine, and judging whether the updated mixed section time period is smaller than the mixed section time period corresponding to the first physical machine. And acquiring offline business load resources, wherein the offline business load resources represent load resources occupied by offline business running on the first physical machine. And comparing the updated mixed part resource with the offline business load resource of the first physical machine, and judging whether the updated mixed part resource is smaller than the mixed part resource corresponding to the first physical machine. If the updated mixed section time period is smaller than the original mixed section time period or the updated mixed section resource is smaller than the offline service load resource, the offline service running on the first physical machine needs to be adjusted.

And under the condition that the updated mixed section time period is smaller than the original mixed section time period, if the updated mixed section resource is larger than the offline service load resource, the offline service running on the first physical machine needs to be ended in advance based on the updated mixed section time period, and the offline service running on the first physical machine is distributed to other physical machines. If the updated hybrid resource is smaller than the offline service load resource, the offline service running on the first physical machine needs to be distributed to other physical machines. Under the condition that the updated mixed part resource is smaller than the offline business load resource, whether the updated mixed part time period is smaller than the original mixed part time period or not, the offline business running on the first physical machine is required to be distributed to other physical machines. When the offline service is redistributed, the offline service running on the first physical machine may be distributed to a third physical machine, which is a different physical machine than the first physical machine.

For example, the services running on the current physical machine include a current online service a, a current online service B and an offline service C, wherein the mixed time period is 0:00 to 14:00, and the mixed resource is 15%. The offline traffic load resource for offline traffic C is 7%. At this time, the newly added online service D is scheduled to the first physical machine, the service priority corresponding to the newly added online service D is the first priority, the resource characteristic data of the newly added online service D includes a sensitive time period of 7:00 to 14:00 and a service resource threshold of 10%, and the updated mixed time period is 0:00 to 7:00, and the mixed resource is 5%. The updated mixed time period and mixed resources are smaller than the original mixed time period and mixed resources, and the physical machine load resources occupied by the offline service C are larger than the mixed resources, so that the offline service C needs to be adjusted from the first physical machine at the moment so as to ensure the operation of the online service.

If the updated mixed time period is equal to the original mixed time period and the updated mixed resource is greater than or equal to the offline service load resource, the offline service running on the first physical machine may not be adjusted.

And detecting newly added online service on the physical machine in real time, and determining whether to redistribute the offline service according to the resource characteristic data of the newly added online service, thereby ensuring the running stability of the online service, rapidly detecting the physical machine capable of distributing the offline service, and improving the efficiency and the flexibility of service resource distribution.

As an optional embodiment, the resource allocation server may detect, in real time, a mixed time period and a mixed resource corresponding to the current online service according to the service priority and the resource feature data, so as to schedule the online service and the offline service in real time.

The resource allocation server acquires the service priority corresponding to the current online service on the first physical machine, and does not allocate the offline service to the first physical machine when the service priority corresponding to the current online service is the second priority. When the service priority corresponding to the current online service is the first priority, calculating the mixed time period and the mixed resource corresponding to the physical machine according to the sensitive time period and the service resource threshold in the resource characteristic data of the current online service. And distributing the offline service to the first physical machine in the mixed section time period, wherein the first physical machine simultaneously operates the current online service and the offline service, and the offline service operation resource of the offline service is smaller than the mixed section resource. When a plurality of offline services are distributed to the first physical machine, the sum of service operation resources of the plurality of offline services is smaller than the mixed part resources.

When the newly-added online service is scheduled to the first physical machine, the resource allocation server firstly acquires the service priority corresponding to the newly-added online service, and when judging that the service priority corresponding to the newly-added online service is the second priority, the resource allocation server downloads the offline service running on the first physical machine. And when judging that the service priority corresponding to the newly added online service is the first priority, updating the mixed part time period and the mixed part resource corresponding to the first physical machine according to the sensitive time period and the service resource threshold in the resource characteristic data of the newly added online service. And when the updated mixed section time period is smaller than the original mixed section time period or the updated mixed section resource is smaller than the offline service operation resource of the offline service, the offline service operated on the first physical machine is distributed to other physical machines. And when the updated mixed time period is equal to the original mixed time period or the updated mixed resource is greater than or equal to the offline service operation resource of the offline service, the offline service operated on the first physical machine is not adjusted.

When the current online service on the first physical machine is ended or the current online service is scheduled to other physical machines, updating the mixed part time period and the mixed part resources corresponding to the first physical machine according to the resource characteristic data of the current online service on the first physical machine, and scheduling a new offline task to the first physical machine when the updated mixed part time period is greater than the original mixed part time period or the updated mixed part resources are greater than the original mixed part resources.

The service resource allocation method provided by the embodiment of the disclosure comprises the following steps: the method comprises the steps of obtaining resource characteristic data of current online service running on each physical machine, determining a mixed time period and mixed resources of each physical machine according to the resource characteristic data of the current online service, distributing offline service to a first physical machine according to the mixed time period and the mixed resources, and running the offline service by the first physical machine in the mixed time period by utilizing the mixed resources and simultaneously running the current online service. The method can acquire the maximum limit and the operation time of the operation resources occupied by the offline service, so that the offline service can be distributed to the physical machine as much as possible under the condition of not affecting the online service, the resource utilization rate of the physical machine is improved, the method can also set the service priority, the corresponding offline service distribution mode can be customized for different online services, the accuracy of service resource distribution is improved, and the method can also adjust the distribution of the offline service in real time according to the actual task scheduling condition on the physical machine, and the flexibility of service resource distribution is improved.

Fig. 9 is a block diagram illustrating a traffic resource allocation apparatus according to an exemplary embodiment. Referring to fig. 9, the apparatus includes:

the feature data acquisition module is configured to acquire the resource feature data of the current online service running on each physical machine, wherein the resource feature data represents feature information related to the resource load of the current online service during running;

the online service resource determining module is configured to determine a mixed time period and mixed resources of each physical machine based on the resource characteristic data, wherein the mixed time period represents a time period for the current online service and the offline service to jointly operate, and the mixed resources represent available offline resources of the physical machine corresponding to the current online service in the mixed time period;

and the offline service allocation module is configured to perform the allocation of the offline service to the first physical machine with the mixed time period and the mixed resources, so that the first physical machine runs the offline service by using the mixed resources in the mixed time period.

As an alternative embodiment, the apparatus further comprises:

the first priority determining module is configured to obtain the resource characteristic data of the current online service under the condition that the service priority of the current online service is the first priority, wherein the first priority is the service priority corresponding to the non-load sensitive online service, and a mixed time period exists between the non-load sensitive online service and the offline service.

As an alternative embodiment, the resource feature data includes a sensitive time period and a service resource threshold, the service resource threshold characterizes an upper threshold of a physical machine load resource when running a current online service, and the online service resource determining module includes:

a mixed section period acquisition unit configured to perform determination of other periods than the sensitive period in the preset service period as mixed section periods;

a target threshold value acquisition unit configured to perform determination of a target service resource threshold value corresponding to the current online service running in the mixed section period from the service resource threshold values;

the current load acquisition unit is configured to perform acquisition of current load resources of each physical machine;

and the mixed part resource determining unit is configured to determine mixed part resources according to the target business resource threshold and the current load resources of the physical machine.

As an alternative embodiment, the current online service includes a plurality of current online services, and the mixed time period acquiring unit includes:

a mixed section period determination unit configured to perform determination of other periods except for the union period in the service period as mixed section periods;

The target threshold acquisition unit includes:

an operation service threshold value acquisition unit configured to perform acquisition of a service resource threshold value corresponding to each current online service operated in the mixed section period from the service resource threshold values;

and a target threshold determining unit configured to perform determination of a minimum value among the corresponding traffic resource thresholds as a target traffic resource threshold.

As an alternative embodiment, the apparatus further comprises:

the first offline service redistribution module is configured to distribute the offline service running on the first physical machine to the second physical machine under the condition that the service priority corresponding to the newly added online service is a second priority, wherein the second priority represents the service priority corresponding to the load-sensitive online service, and a mixed section time period does not exist between the load-sensitive online service and the offline service.

As an alternative embodiment, the apparatus further comprises:

the new-added-feature acquisition module is configured to acquire resource feature data of the new added online service under the condition that the service priority of the new online service is a first priority;

The data updating module is configured to execute updating the mixed part time period and the mixed part resource corresponding to the first physical machine according to the resource characteristic data of the newly added online service;

the offline service resource acquisition module is configured to acquire offline service load resources, wherein the offline service load resources represent load resources occupied by offline services running on the first physical machine;

and the second offline service reassignment module is configured to execute the offline service running on the first physical machine to the third physical machine when the updated mixed time period is smaller than the mixed time period or the updated mixed resource is smaller than the offline service load resource.

As an alternative embodiment, the apparatus further comprises:

the preset feature acquisition module is configured to determine the service priority, the sensitive time period and the service resource threshold of the preset service according to the service portraits.

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

Fig. 10 is a block diagram illustrating an electronic device, which may be a server, for performing a service resource allocation method according to an exemplary embodiment, and an internal structure diagram thereof may be as shown in fig. 10. The electronic device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of service resource allocation.

It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of a portion of the structure associated with the disclosed aspects and is not limiting of the electronic device to which the disclosed aspects apply, and that a particular electronic device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In an exemplary embodiment, a computer-readable storage medium is also provided, such as memory 1004, including instructions executable by processor 1020 of apparatus 1000 to perform the above-described method. Alternatively, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided, comprising computer instructions, characterized in that the computer instructions, when executed by a processor, implement the above-mentioned service resource allocation method.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for allocating service resources, the method comprising:

determining a mixed section time period and mixed section resources of each physical machine based on the resource characteristic data, wherein the mixed section time period represents a time period for the current online service and offline service to co-operate on the same physical machine, and the mixed section resources represent available offline resources of the physical machine corresponding to the current online service in the mixed section time period;

distributing the offline service to a first physical machine with the mixed time period and the mixed resources, so that the first physical machine runs the offline service by utilizing the mixed resources in the mixed time period;

the resource characteristic data comprises a sensitive time period and a service resource threshold, the sensitive time period is a time period in which a preset service cannot be operated together with an offline service, the service resource threshold represents an upper limit threshold of a physical machine load resource when the current online service is operated, and the determining the mixed time period and the mixed resource of each physical machine based on the resource characteristic data comprises the following steps:

acquiring the current load resource of each physical machine;

determining the mixed part resource according to the target service resource threshold and the current load resource of the physical machine;

the current online service comprises a plurality of current online services, and the determining of the other time periods except the sensitive time period in the preset service period as the mixed time period comprises the following steps:

2. The traffic resource allocation method according to claim 1, wherein the method further comprises:

acquiring a service priority corresponding to the current online service;

3. The traffic resource allocation method according to claim 1, wherein the method further comprises:

4. The service resource allocation method according to claim 3, wherein after the obtaining the newly added online service corresponding to the first physical machine, the method further comprises:

5. The traffic resource allocation method according to claim 1, wherein the method further comprises:

Acquiring service portrait information of the preset service;

6. A traffic resource allocation apparatus, the apparatus comprising:

an online service resource determining module configured to determine a mixed time period and mixed resources of each physical machine based on the resource feature data, wherein the mixed time period represents a time period for the current online service and offline service to co-operate on the same physical machine, and the mixed resources represent available offline resources of the physical machine corresponding to the current online service in the mixed time period;

an offline service allocation module configured to perform allocation of the offline service to a first physical machine having the hybrid time period and the hybrid resources such that the first physical machine runs the offline service using the hybrid resources during the hybrid time period;

The resource characteristic data comprises a sensitive time period and a service resource threshold value, the sensitive time period is a time period in which a preset service cannot be operated together with an offline service, the service resource threshold value represents an upper limit threshold value of a physical machine load resource when the current online service is operated, and the online service resource determining module comprises:

a mixed part resource determining unit configured to perform determining the mixed part resource according to the target service resource threshold and the current load resource of the physical machine;

the current online service includes a plurality of current online services, and the mixed section time period acquisition unit includes:

the target threshold acquisition unit includes:

7. The traffic resource allocation device according to claim 6, wherein said device further comprises:

8. The traffic resource allocation device according to claim 6, wherein said device further comprises:

9. The traffic resource allocation device according to claim 8, wherein said device further comprises:

10. The traffic resource allocation device according to claim 6, wherein said device further comprises:

11. An electronic device, the device comprising:

a processor;

a memory for storing the processor-executable instructions;

Wherein the processor is configured to execute the instructions to implement the traffic resource allocation method according to any of claims 1 to 5.

12. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the service resource allocation method according to any one of claims 1 to 5.

13. A computer program product comprising computer instructions which, when executed by a processor, implement the method of traffic resource allocation according to any of claims 1 to 5.