WO2016041446A1

WO2016041446A1 - Resource allocation method, apparatus and device

Info

Publication number: WO2016041446A1
Application number: PCT/CN2015/089050
Authority: WO
Inventors: 甘嘉栋
Original assignee: 华为技术有限公司
Priority date: 2014-09-17
Filing date: 2015-09-07
Publication date: 2016-03-24
Also published as: CN104301257A; CN104301257B

Abstract

Disclosed are a resource allocation method, apparatus and device. In the present invention, the life cycle attribute information of a service application is obtained, and the life cycle attribute information indicates the time information of the resource expected to be occupied by the service application; a reserve resource capable of optimizing the resource utilization rate within a subsequent predictable period is determined on the basis of the life cycle attribute information, and the reserve resource is reserved for the service application; upon reaching the starting time when the resource is expected to be occupied by the service application, the reserve resource is allocated to the service application. By the present invention, the resource utilization rate in an infrastructure management system could be optimized in a predictable period and maintain the optimized state.

Description

Resource allocation method, device and device

Technical field

The present invention relates to the field of resource allocation technologies, and in particular, to a resource allocation method, apparatus, and device.

Background technique

With the promotion of the cloud concept, the layered architecture of the business application layer and management layer is widely used in solutions that require dynamic resource allocation.

The business application sends a service resource request to the infrastructure management system to request the infrastructure resources needed to process a particular business to run its instance. The resource specification requested by the infrastructure management system for the service resource request sent by the service application (the resource specification may be, for example, a physical specification such as a CPU, a memory, and a network connection, or other quality attribute requirements), and a resource distribution available in the system. Situation, comprehensive analysis and allocation of resources.

At present, when the infrastructure management system allocates resources, it is preferred to select the enabled infrastructure resource entities for resource allocation, and try not to use the unenabled infrastructure resource entities and select the infrastructure resources. The resource resource entity with the least remaining resources is preferentially selected in the entity to allocate resources. After the time taken by the service application is reached, the resource is released.

The above process of resource allocation can improve resource utilization to a certain extent. However, different service applications occupy different resources at different times. For example, the resource (1/2) on the infrastructure resource entity 1 in FIG. 1 is after a short time. Released, however resources on infrastructure resource entity 1 (1/4) and resources on infrastructure resource entity 2 (1/2) need to be occupied for a long time, although resources (1/4) occupy resources of infrastructure resource entities There are fewer, but still need to run the infrastructure resource entity 1, so it is necessary to run the infrastructure resource entity 1 and the infrastructure resource entity 2 at the same time, and the resource utilization in the infrastructure management system is difficult to maintain an optimized state for a long time.

Summary of the invention

Embodiments of the present invention provide a resource allocation method, device, and device to optimize infrastructure management Resource utilization in the system.

In a first aspect, a resource allocation method is provided, including:

Obtaining lifecycle attribute information of the service application, where the lifecycle attribute information reflects time information that the service application expects to occupy resources;

Determining, according to the lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and scheduling the reserved resource for the service application;

The reservation resource is allocated to the service application when the start time of the service application expected to occupy resources is reached.

With reference to the first aspect, in a first implementation manner, before the reservation resource is reserved for the service application, the method further includes:

The reserved resources are re-subscribed under the premise that the resource utilization meets the further optimization conditions in the subsequent expected time.

With reference to the first aspect, or the first implementation manner of the first aspect, in the second implementation manner, the acquiring the lifecycle attribute information of the service application includes:

Invoking a service resource request interface to carry a service application lifecycle attribute information function;

The service resource request interface carries the service application lifecycle attribute information function to obtain the lifecycle attribute information of the service application.

With reference to any one of the foregoing implementation manners of the first aspect, in a third implementation manner, determining, according to the lifecycle attribute information, an reserved resource that can optimize resource utilization in a subsequent predictable time, including:

In the set partial resource set, based on the lifecycle attribute information, an reserved resource capable of optimizing resource utilization in a subsequent predictable time is preferentially selected.

In a second aspect, a resource allocation apparatus is provided, including an obtaining unit, a reservation unit, and an allocating unit, wherein:

The obtaining unit is configured to obtain lifecycle attribute information of the service application, where the lifecycle attribute information reflects time information that the service application expects to occupy resources;

The reservation unit is configured to determine, according to the lifecycle attribute information acquired by the acquiring unit, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the reserved resource for the service application;

The allocating unit is configured to allocate, by the reservation unit, the reserved resource to the service application when the start time of the service application expected to occupy the resource is reached.

In conjunction with the second aspect, in a first implementation, the apparatus further includes a re-subscribing unit, wherein:

And the re-subscribing unit is configured to re-subscribe the reserved resource before the reservation unit reserves the reserved resource for the service application, on the premise that the resource utilization meets the further optimization condition in the subsequent predictable time.

With reference to the second aspect or the first implementation manner of the second aspect, in the second implementation manner, the acquiring unit is specifically configured to obtain lifecycle attribute information of the service application as follows:

With reference to any implementation of the second aspect, in a third implementation manner, the scheduling unit is specifically configured to determine, according to the lifecycle attribute information, an appointment that can optimize resource utilization in a subsequent predictable time according to the following manner. Resources:

In a third aspect, a resource allocation device is provided, including a communication interface, a memory, and a processor, wherein:

The memory is configured to store program code executed by the processor;

The processor is configured to invoke the program code stored in the memory to implement the following functions:

The life cycle attribute information of the service application is obtained by using the communication interface, where the life cycle attribute information reflects time information that the service application expects to occupy the resource, and determines, according to the life cycle attribute information, the reserved resource that can optimize the resource utilization rate in the subsequent expected time. Dedicating the pre-order for the business application The resource is allocated to the service application when the start time of the resource occupied by the service application is reached.

With reference to the third aspect, in a first implementation manner, the processor is further configured to:

Under the premise that the resource utilization meets the further optimization condition in the subsequent expected time, the reserved resource is re-subscribed before the reserved resource is reserved for the service application.

The resource allocation method, device and device provided by the embodiment of the present invention obtain the life cycle attribute information of the service application, and the life cycle attribute information can reflect the time information of the expected resource occupation of the service application, so that the resource in the subsequent predictable time can be known in advance. The time taken. And determining, according to the acquired lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the reserved resource for the service application, and when the time at which the service application expects to occupy the resource is reached, the reserved resource is used. Assignment to business applications enables resource utilization in the infrastructure management system to be optimized for the expected time and maintained in an optimized state.

DRAWINGS

1 is a schematic diagram of resource allocation in the prior art;

2 is a system architecture diagram of an applicable embodiment of the present invention;

3 is a schematic structural diagram of a resource allocation device according to an embodiment of the present invention;

4 is a flowchart of a resource allocation method according to an embodiment of the present invention;

FIG. 5A is a schematic diagram of an existing resource allocation process; FIG.

FIG. 5B is a schematic diagram of a resource allocation process according to an embodiment of the present invention; FIG.

6A is a schematic structural diagram of a resource allocation apparatus according to an embodiment of the present invention;

FIG. 6B is a schematic structural diagram of another resource allocation apparatus according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, one of ordinary skill in the art does not create All other embodiments obtained under the premise of sexual labor are within the scope of protection of the present invention.

2 is a schematic diagram of a system architecture applicable to a resource allocation method according to an embodiment of the present invention. As shown in FIG. 2, a service resource request interface of an infrastructure management system has a service resource request function for acquiring a service application, and an infrastructure management system. The resource request and the management module obtain the service resource request of the service application, and the resource allocation and management module selects the resource for the service application in the resource pool based on the obtained service resource request. In the embodiment of the present invention, the function of the service resource requesting interface is extended to obtain the lifecycle attribute information of the service application, and the lifecycle attribute information of the service application is obtained, and the lifecycle attribute information reflects the time information of the expected resource occupation of the service application. . The resource allocation and management module performs resource allocation based on the acquired lifecycle attribute information to achieve the purpose of optimizing resource utilization in the infrastructure management system within an expected time.

It should be noted that the resource allocation method provided in the embodiment of the present invention is not limited to the system architecture diagram shown in FIG. 2, for example, the resource allocation function and the resource management function may be applied to two separate entities in the embodiment of the present invention. Module implementation.

The embodiment of the present invention provides a resource allocation device 300. As shown in FIG. 3, the resource allocation device 300 includes a communication interface 301, a memory 302, and a processor 303. Of course, the resource allocation device 300 provided in the embodiment of the present invention may further include a communication bus, which is not limited by the embodiment of the present invention.

In the embodiment of the present invention, the communication interface 301 communicates with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Networks (WLAN), etc., using devices such as transceivers.

The memory 302 in the embodiment of the present invention may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or a storable memory. Other types of dynamic storage devices for information and instructions, or Electro Scientific Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or Other disc storage, disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), disk storage media or other magnetic storage devices, or can be used for Any other medium that carries or stores the desired program code in the form of an instruction or data structure and that can be accessed by a computer, but is not limited thereto.

The processor 303 in the embodiment of the present invention may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more program programs for controlling the present invention. Execution of the integrated circuit.

The memory 302 is used to store the program code executed by the processor 303 in the embodiment of the present invention.

The processor 303 is configured to call the program code stored in the memory 302 to implement the following functions:

The life cycle attribute information of the service application is obtained through the communication interface 301, and the life cycle attribute information reflects time information that the service application expects to occupy the resource.

Determining, according to the acquired lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserves the determined reserved resource for the service application; when the start time of the service application is expected to occupy the resource, the determined reservation is determined. Resources are allocated to business applications.

In an implementation manner, the processor 303 is further configured to:

Under the premise that the resource utilization meets the further optimization condition in the subsequent expected time, the reserved resource is re-subscribed before the reserved resource is reserved for the service application; wherein the further optimization condition is that the subsequent candidate can be expected The resource allocation in the time is tuned, for example, the overall resource utilization can be maximized.

Specifically, in the embodiment of the present invention, the communication interface 301 may be a service resource request interface, where the service resource request interface has an extended function that carries the service application lifecycle attribute information, and the processor 303 may invoke the service resource request interface to carry the service application lifecycle attribute. The information function: the service resource request interface carries the service application life cycle attribute information function, and obtains the life cycle attribute information of the service application.

Specifically, in the embodiment of the present invention, the processor 303 may determine, according to the lifecycle attribute information, an reserved resource that can optimize resource utilization in a subsequent expected time period:

A: Determine that the infrastructure resource entity is enabled in the set resource collection.

The set resource set in the embodiment of the present invention may be all resources in the infrastructure management system, and also It can be part of the resources in the infrastructure management system.

In the embodiment of the present invention, part of the resources are preferably set in the infrastructure management system, and the resource allocation is performed based on the life cycle attribute information, so that the infrastructure management system can simultaneously support the original allocation mechanism (ie, the life cycle of the resource occupation is not considered). ), and mechanisms for resource allocation based on lifecycle information. In the embodiment of the present invention, the resource allocation is performed based on the lifecycle information, and the uncertainty of the original resource allocation mechanism may be avoided to affect the resource allocation based on the lifecycle attribute information.

B: In the set partial resource set, based on the life cycle attribute information, the reserved resource capable of optimizing resource utilization in the subsequent expected time is preferentially selected.

In the embodiment of the present invention, for example, the enabled infrastructure resource entity may be selected in the subsequent expected time when the resource occupation time is similar to the expected resource occupation time in the life cycle attribute information, and the unallocated resource meets the resource condition required by the service application. Resources as an appointment resource.

The resource allocation device 300 provided by the embodiment of the present invention may be an infrastructure management system or a component in the infrastructure management system, which is not limited in the embodiment of the present invention.

The resource allocation device 300 of the embodiment of the present invention obtains the life cycle attribute information of the service application, where the life cycle attribute information can reflect the time information of the expected resource occupation of the service application, so that the resource can be occupied in the expected expected time. time. And determining, according to the acquired lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the reserved resource for the service application, and when the time at which the service application expects to occupy the resource is reached, the reserved resource is used. Assignment to business applications enables resource utilization in the infrastructure management system to be optimized for the expected time and maintained in an optimized state.

Embodiments of the Present Invention A method for implementing a resource allocation method will be described in detail below.

FIG. 4 is a flowchart of a method for implementing a resource allocation method according to an embodiment of the present invention. The execution body of the method shown in FIG. 4 may be, for example, an infrastructure management system or a component of an infrastructure management system, which is not implemented in the embodiment of the present invention. limited. As shown in FIG. 4, the method includes:

S101: Obtain lifecycle attribute information of the service application.

In the embodiment of the present invention, the lifecycle attribute information reflects time information that the service application expects to occupy resources.

In the embodiment of the present invention, the scalable resource requesting interface has the function of carrying the service lifecycle attribute information of the service application, and the service resource requesting interface carries the service application lifecycle attribute information function to obtain the lifecycle attribute information of the service application.

The life cycle attribute information in the embodiment of the present invention may be represented by, for example, the structure shown in Table 1 below.

Table 1

It should be noted that the lifecycle attribute information in the embodiment of the present invention is not limited to several examples listed in Table 1, and should also include any manner that can be used to describe the time when the resource is expected to be occupied. For example, it can also be a time list for listing the expected usage time of each irregularity (non-repetitive period).

S102: Determine, according to the lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the determined reserved resource for the service application.

In the embodiment of the present invention, the reserved resource determined by the service application reservation is not actually allocated and occupied, but the reserved resource cannot be reserved or allocated to the current reserved time within the reserved time. Other business applications other than business applications.

In the embodiment of the present invention, in the process of determining the reserved resource that can optimize resource utilization in the subsequent expected time period based on the lifecycle attribute information, the resource resource fragmentation and the enabled infrastructure resource may be used. The at least one of the minimum number of entities and the optimized state for a long time is an optimization target, and the determination of the reserved resources is performed.

For example, in the embodiment of the present invention, the process of determining the reserved resource that can optimize the resource utilization rate in the subsequent expected time based on the lifecycle attribute information may be as follows:

Determines that the infrastructure resource entity is enabled in the set resource collection and determines when the allocated resources on the infrastructure resource entity and the resources expected by the reserved resources are enabled.

Preferentially selecting resources on the enabled infrastructure resource entity whose resource occupation time is similar to the expected resource occupation time in the life cycle attribute information, and the unallocated resource meets the resource condition required by the service application, as an appointment Resources.

S103: Allocate the reserved resource to the service application when the start time of the resource occupied by the service application is reached.

The resource allocation method provided by the embodiment of the present invention obtains the life cycle attribute information of the service application, where the life cycle attribute information can reflect the time information of the expected resource occupation of the service application, so that the time when the resource is occupied in the subsequent expected time can be known in advance. . And determining, according to the acquired lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the reserved resource for the service application, and when the time at which the service application expects to occupy the resource is reached, the reserved resource is used. Assignment to business applications enables resource utilization in the infrastructure management system to be optimized for the expected time and maintained in an optimized state.

In the embodiment of the present invention, the reservation resource based on the life cycle attribute information of the service application is reserved for the service application, and is not actually allocated and occupied. Therefore, in the embodiment of the present invention, another basis can be realized by changing the reservation information. The resource reservation of the facility resource entity is applied to the business application without any resource migration technology, and the technology implementation is simple and easy.

Optionally, in the embodiment of the present invention, in order to further achieve that the resources in the infrastructure management system are in an optimized state for a long time, that is, the resource utilization rate satisfies the further optimization condition, the reserved resources may be re-subscribed, wherein, further optimization is performed. Conditions, for example, can be to reduce resource fragmentation, minimize the number of enabled infrastructure resource entities, or enable the foundation in an infrastructure management system Facility resource entities can be optimized for a long time.

For example, in the embodiment of the present invention, the reserved resource may be on the current infrastructure resource entity, and the resource occupation time in the subsequent predictable time is similar to the time expected by the current service application, and the unallocated resource of the current infrastructure resource entity does not satisfy the current In the case of the resource required by the service application, the reserved resource on the current infrastructure resource entity is re-subscribed, and the reserved resource and the resource required by the current application are allocated to the same infrastructure resource entity to optimize resource utilization.

Embodiments of the Invention The process of resource allocation described above will be described in detail below in conjunction with actual applications.

In the embodiment of the present invention, it is assumed that the resource resource entities in the infrastructure management system have the same resource specifications, and the total resources are recorded as 1S, and the resources corresponding to the three infrastructure resource entities are Sn, n=1, 2, and 3. The resource specifications for business application applications are 0.25S, 0.5S, or 0.75S (the actual resource specifications are multi-dimensional). It is assumed that the infrastructure management system needs to process the resource requests rX (X=A, B, C, D, E) five times in sequence, and the requested resource specifications and timing relationships are as shown in FIG. 5A and FIG. 5B, wherein two adjacent moments are shown. The interval between the two is time T, and the resources corresponding to rA and rD are released after a period of use, and rB, rC and rE continue to occupy for a long time.

FIG. 5A is a schematic diagram of resource allocation according to an original allocation mechanism that does not consider lifecycle attribute information, and FIG. 5B is a schematic diagram of resource allocation based on lifecycle attribute information according to an embodiment of the present invention.

In FIG. 5A, in the case where it is impossible to predict the resource occupation time in the subsequent expected time, the resources are allocated on the infrastructure resource entity that is preferentially allocated from the existing partial resources, that is, the new infrastructure resource entity is enabled as much as possible. And, under the above conditions, the resource resource allocation is preferentially selected by the infrastructure resource entity with the least remaining resources and the least allocated business resources. The role of this is to avoid "fragmentation" of resources and improve resource utilization. According to the resource utilization=the total amount of resources allocated/the total amount of resources of the enabled infrastructure resource entity, the simple calculation can obtain the overall resource utilization rate during the period from t1 to t6 is only about 56%. If the allocation has not changed after t6, the utilization will remain at a low level of about 33% for a long time.

In FIG. 5B, the process of resource allocation based on lifecycle attribute information according to an embodiment of the present invention is as follows:

A: Before t1, rA and rC made resource reservations in advance. Although the expected resource occupation time of the two is very different, there is no other resource distribution that can be optimally allocated at the time, so they are all reserved to s1 (resources are not Really allocated occupancy, still in the power-off state).

B: At t1, rA allocates resources according to the original reservation, and s1 powers up. When processing rB, the system analyzes that rB and rC are basically the same in the expected long-term occupation of resources, and the allocation together can bring long-term resource optimization effects. Therefore, start s2 to allocate rB resources, and re-subscribe rC to s2.

C: The rE is processed at t4, and the s3 should be allocated according to the general policy without considering the lifecycle attribute information. However, since rE and rB, that is, rC, are expected to occupy resources in the same expected time, the time is basically the same (all long-running), so the allocation strategy is appropriately adjusted, and the allocation is specified by s2.

According to the above resource allocation method, according to the foregoing method for calculating the resource utilization rate, the result of the method of the present invention in the example is that the resource utilization rate is 67.5% (originally 56%) from t1 to t6; Long-running resource utilization is 100%.

The resource allocation method provided by the embodiment of the present invention obtains the life cycle attribute information of the service application, where the life cycle attribute information can reflect the time information of the expected resource occupation of the service application, so that the time when the resource is occupied in the subsequent expected time can be known in advance. . And determining, according to the acquired lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the reserved resource for the service application, and when the time at which the service application expects to occupy the resource is reached, the reserved resource is used. Assignment to business applications enables resource utilization in the infrastructure management system to be optimized for the expected time and maintained in an optimized state. Further, in the embodiment of the present invention, a simple risk-free "re-reservation" adjustment can be performed when necessary, and finally the use of the overall resource can be maintained in an optimized state for a predictable period of time, and the technical implementation is simple.

It should be noted that, in the embodiment of the present invention, the resource on the infrastructure resource entity in the infrastructure management system may be a resource or a group used by the upper layer service application managed by the infrastructure management system. For example, it may be network resources (network connection and communication bandwidth, etc.), storage resources, certain types of special processing capabilities (such as data encryption and decryption processing capabilities provided by special hardware), and the like. Moreover, the form of resource allocation is also diverse. For example, taking computing resources as an example (other types of resources are similar), the allocated resource forms are not limited to virtual machines using virtualization technology, and may include any part of physical resources or The overall form provided to the applicant, such as the CGroups technology provided by the Linux kernel, can divide an OS-managed resource (generally a physical server) into multiple entities with certain resources. Further, the infrastructure resource entity is also diverse. Taking computing resources as an example (other types of resources are similar), the physical resource entity does not necessarily refer to a physical server, but can provide any computing resource. Physical or logical collection. For example, it may be a plurality of blade servers in a chassis, a server in a machine room, or a server logically divided into a cluster, and the like.

Further, the resource allocation method provided by the foregoing embodiment of the present invention can flexibly apply the resource allocation method based on the lifecycle attribute information to the current infrastructure management system according to actual conditions, for example:

A: Lifecycle attribute information as a mandatory attribute

For example, in some enterprise or departmental infrastructure management systems, in order to maximize the effectiveness of the method of the present invention, users (such as personnel within the department) may be required to provide their corresponding estimated lifecycle information when requesting resources. .

Also for example, in some enterprises or departments, the infrastructure management system, in order to maximize the effect of the method of the present invention, will allocate resources in strict accordance with the life cycle specified by its users (such as personnel in the department) when requesting resources, ie The user cannot access the resource at a time outside the pre-specified lifecycle. Of course, in this way, the constraint needs to be notified to the user in advance by using, for example, a specification.

B: Lifecycle attribute information as an optional attribute

The method for resource allocation based on the lifecycle attribute information provided by the embodiment of the present invention may be applied only to the setting part of the infrastructure resource management entity in the infrastructure management system, and the original resource allocation method is applied in the remaining part. A typical example would be that the infrastructure management system is externally available. At the same time, the resource request carries or does not carry lifecycle information, but internally classifies the two types of requests, and uses the method of the present invention to allocate and optimize resources for the request carrying the lifecycle information, and assigns a dedicated one to it. The collection of resources; the remaining requests continue to use the original allocation mechanism (ie, regardless of the life cycle of resource occupancy), and specify another resource collection to assume resource allocation. The advantage of distinguishing the two is that the resource allocation of the former is analyzed and optimized based on the life cycle of the resource, which avoids the influence of the resource allocation and the uncertainty of the use of the latter (regardless of the life cycle of resource occupation) on the former. .

Based on the resource allocation method provided by the foregoing embodiment, the embodiment of the present invention further provides a resource allocation apparatus 600. As shown in FIG. 6A, the resource allocation apparatus 600 includes an obtaining unit 601, a reservation unit 602, and an allocating unit 603, where:

The obtaining unit 601 is configured to obtain lifecycle attribute information of the service application, where the lifecycle attribute information reflects time information that the service application expects to occupy the resource.

The reservation unit 602 is configured to determine, according to the lifecycle attribute information acquired by the obtaining unit 601, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve an reserved resource for the service application.

The allocating unit 603 is configured to allocate the reserved resource reserved by the reservation unit 602 to the service application when the start time of the service application expected resource occupation is reached.

In a first implementation, the resource allocation device 600 further includes a re-subscribing unit 604, as shown in FIG. 6B, in which:

The re-subscribing unit 604 is configured to re-subscribe the reserved resources before the reservation unit 602 reserves the reserved resources for the service application on the premise that the resource utilization meets the further optimization condition in the subsequent predictable time.

In the second implementation manner, the obtaining unit 601 is specifically configured to obtain lifecycle attribute information of the service application as follows:

The service resource request interface is invoked to carry the service application lifecycle attribute information function.

In a third implementation manner, the reservation unit 602 is specifically configured to determine, according to the lifecycle attribute information, an reserved resource that can optimize resource utilization in a subsequent predictable time according to the following manner:

In the set partial resource set, based on the life cycle attribute information, the reserved resource capable of optimizing resource utilization in the subsequent expected time is preferentially selected.

The resource allocation device 600 provided by the embodiment of the present invention may be an infrastructure management system or a component in the infrastructure management system, which is not limited in the embodiment of the present invention.

The resource allocation device 600 provided by the embodiment of the present invention obtains the life cycle attribute information of the service application, and the life cycle attribute information can reflect the time information of the expected resource occupation of the service application, so that the resource can be occupied in the expected expected time. time. And determining, according to the acquired lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and reserve the reserved resource for the service application, and when the time at which the service application expects to occupy the resource is reached, the reserved resource is used. Assignment to business applications enables resource utilization in the infrastructure management system to be optimized for the expected time and maintained in an optimized state. Further, in the embodiment of the present invention, a simple risk-free "re-reservation" adjustment can be performed when necessary, and finally the use of the overall resource can be maintained in an optimized state for a predictable period of time, and the technical implementation is simple.

It should be noted that the resource allocation apparatus 600 provided by the embodiment of the present invention can be used to implement the resource allocation method of FIG. 4 and FIG. 5B. Therefore, the resource allocation apparatus 600 is not described in detail in the embodiment of the present invention, and may refer to related manners. The description of the embodiments will not be repeated here.

It is apparent that those skilled in the art can make various modifications and variations to the invention without departing from the spirit and scope of the invention. Thus, it is intended that the present invention cover the modifications and modifications of the invention

Claims

A resource allocation method, comprising:

Obtaining lifecycle attribute information of the service application, where the lifecycle attribute information reflects time information that the service application expects to occupy resources;

Determining, according to the lifecycle attribute information, a reserved resource that can optimize resource utilization in a subsequent predictable time, and scheduling the reserved resource for the service application;

The reservation resource is allocated to the service application when the start time of the service application expected to occupy resources is reached.
The method of claim 1, wherein before the requesting the reserved resource for the service application, the method further comprises:

The reserved resources are re-subscribed under the premise that the resource utilization meets the further optimization conditions in the subsequent expected time.
The method of claim 1 or 2, wherein the obtaining the lifecycle attribute information of the service application comprises:

Invoking a service resource request interface to carry a service application lifecycle attribute information function;

The service resource request interface carries the service application lifecycle attribute information function to obtain the lifecycle attribute information of the service application.
The method according to any one of claims 1 to 3, wherein the predetermined resource capable of optimizing resource utilization in a subsequent predictable time period is determined based on the lifecycle attribute information, including:

In the set partial resource set, based on the lifecycle attribute information, an reserved resource capable of optimizing resource utilization in a subsequent predictable time is preferentially selected.
A resource allocation device, comprising:

An obtaining unit, configured to obtain lifecycle attribute information of the service application, where the lifecycle attribute information reflects time information that the service application expects to occupy resources;

a reservation unit, configured to determine, according to the lifecycle attribute information acquired by the acquiring unit, Optimizing a reserved resource of a resource utilization rate in a predetermined time period, and scheduling the reserved resource for the service application;

And an allocating unit, configured to allocate the reserved resource reserved by the reserved unit to the service application when a start time of the service application expected to occupy resources is reached.
The apparatus according to claim 5, wherein said apparatus further comprises a re-subscribing unit for providing said service in said reservation unit on the premise that resource utilization meets further optimization conditions in a subsequent predictable time Before the application reserves the reserved resources, the reserved resources are re-subscribed.
The device according to claim 5 or 6, wherein the obtaining unit is specifically configured to obtain lifecycle attribute information of the service application as follows:

Invoking a service resource request interface to carry a service application lifecycle attribute information function;

The service resource request interface carries the service application lifecycle attribute information function to obtain the lifecycle attribute information of the service application.
The method according to any one of claims 5 to 7, wherein the reservation unit is specifically configured to determine, according to the lifecycle attribute information, an appointment resource capable of optimizing resource utilization in a subsequent predictable time according to the following manner. :

In the set partial resource set, based on the lifecycle attribute information, an reserved resource capable of optimizing resource utilization in a subsequent predictable time is preferentially selected.
A resource allocation device, comprising: a communication interface, a memory, and a processor, wherein:

The memory is configured to store program code executed by the processor;

The processor is configured to invoke the program code stored in the memory to implement the following functions:

The life cycle attribute information of the service application is obtained by using the communication interface, where the life cycle attribute information reflects time information that the service application expects to occupy the resource, and determines, according to the life cycle attribute information, the reserved resource that can optimize the resource utilization rate in the subsequent expected time. And the reserved resource is reserved for the service application, and the reserved resource is allocated to the service application when a start time of the service application expected to occupy the resource is reached.
The device according to claim 9, wherein the processor is further configured to:

Under the premise that the resource utilization meets the further optimization condition in the subsequent expected time, the reserved resource is re-subscribed before the reserved resource is reserved for the service application.