WO2017152797A1 - Method and device for resource reservation - Google Patents
Method and device for resource reservation Download PDFInfo
- Publication number
- WO2017152797A1 WO2017152797A1 PCT/CN2017/075199 CN2017075199W WO2017152797A1 WO 2017152797 A1 WO2017152797 A1 WO 2017152797A1 CN 2017075199 W CN2017075199 W CN 2017075199W WO 2017152797 A1 WO2017152797 A1 WO 2017152797A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- reservation
- user
- resources
- data center
- server
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/72—Admission control; Resource allocation using reservation actions during connection setup
- H04L47/724—Admission control; Resource allocation using reservation actions during connection setup at intermediate nodes, e.g. resource reservation protocol [RSVP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/80—Actions related to the user profile or the type of traffic
- H04L47/805—QOS or priority aware
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Definitions
- network (Web) service provides an open platform that is independent of the operating system, independent of the programming language, independent of the machine type, and independent of the operating environment. With sharing.
- the resources integrated by the cloud computing platform are mostly provided to users in the form of Web services.
- Many computing tasks often require a large amount of computing resources (including Central Processing Unit (CPU) resources and memory resources) and storage resources to work together.
- QoS quality of service
- the method further includes:
- FIG. 2 is a schematic structural diagram of a system for implementing resource reservation according to an embodiment of the present invention
- Step 100 The federation server receives a reservation request from a user, and acquires one or more numbers. According to available resources in the center;
- the simple reservation request may include: a reservation start time, a reservation end time, a QoS requirement parameter, and a resource requested to be reserved.
- Requests and simple reservation requests corresponding to network resources and then, according to available resources in each data center, determine whether each data center has available requested computing resources, available requested storage resources, available requested network resources, if The available simple request resource, the available requested storage resource, or the available requested network resource are sent to the corresponding data center. For example, there are three data centers, data data 1, data center 2, and data center 3, if the data center 1 has available requested computing resources, the simple reservation request corresponding to the decomposed computing resources is sent to the data center 1; If the data center 2 has the requested storage resource available, the simple reservation request corresponding to the decomposed storage resource is sent to the data center 2; if the requested network resource is available in the data center 3, the decomposed network resource is used. The corresponding simple reservation request is sent to the data center 3.
- the joint server After the joint server returns the allocated resources to the user, the reservation message is generated and the reservation message is put into the reservation queue; when the reservation start time in the reservation message arrives, the joint server determines the reservation message. Whether the allocated resources are available, if the resources allocated in the reservation message are available, the user's early reservation status is changed to an active state, the user is notified that the required resources have been bound, and the server that allocates the resources is notified to be allocated to the The user's resources are made unavailable.
- the method further includes:
- the federation server determines that all available resources in the data center do not include all of the resources in the reservation request, the federation server returns a rejection message to the user.
- the method further includes:
- module 30 it is arranged to return to the user the resources allocated by the server from one or more data centers.
- the returning module 30 After the returning module 30 returns the allocated resource to the user, generating a reservation message and placing the reservation message into the reservation queue; when the reservation start time in the reservation message arrives And determining whether the resources allocated in the reservation message are all available, and if the resources allocated in the reservation message are available, changing the early reservation state of the user to an active state to notify the user that the required resources are bound,
- the data center that notifies the assigned resource sets the resource assigned to the user to be unavailable.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method and a device for resource reservation, the method comprising: a federation server receiving a reservation request from a user, acquiring available resources in one or more data centers; the federation server determining whether there is a data center meeting a preset condition, and if there is no data center meeting the preset condition, breaking down, according to the acquired available resources in the one or more data centers, the reservation request into a plurality of simple reservation requests corresponding to the data centers, the preset condition comprising: the available resources in the data centers comprising all the resources in the reservation request; the federation server sending each simple reservation request to a server of a corresponding data center; and the federation server returning to the user the received resources allocated by the servers of the one or more data centers. The described technical solution can reduce the rejection rate of the reservation request.
Description
本文涉及但不限于云计算技术和虚拟化技术,涉及一种实现资源预留的方法和装置。This document relates to, but is not limited to, cloud computing technology and virtualization technology, and relates to a method and apparatus for realizing resource reservation.
网络(Web)服务作为目前最流行的分布式计算方式之一,提供了一种与操作***无关、与程序设计语言无关、与机器类型无关、与运行环境无关的开放平台,实现网络资源的协作与共享。云计算平台集成的资源多以Web服务的形式向用户提供,许多计算任务往往需要大量的计算资源(包括中央处理器(CPU,Central Processing Unit)资源和内存资源)和存储资源协同工作来完成,有效地控制和保障这类计算任务的服务质量(QoS,Quality of Service)成为云计算面临的重要议题之一。由于云计算环境下资源的可获得性和性能的动态变化,未来预留时间段内资源的可获得性和性能难以得到保证,因此,将资源的提前预留作为一种QoS的保障机制引入到云计算环境下面临着挑战。全球网络论坛(GGF,Global Grid Forum)将资源提前预留定义为:用户与资源所有者经过协商,在指定时间段内获得的对资源的限制性访问权限。实际上,提前预留可以看作是云计算平台的一种承诺,在指定时间段内可以获得特定水平的服务。As one of the most popular distributed computing methods, network (Web) service provides an open platform that is independent of the operating system, independent of the programming language, independent of the machine type, and independent of the operating environment. With sharing. The resources integrated by the cloud computing platform are mostly provided to users in the form of Web services. Many computing tasks often require a large amount of computing resources (including Central Processing Unit (CPU) resources and memory resources) and storage resources to work together. Effectively controlling and guaranteeing the quality of service (QoS) of such computing tasks has become one of the important issues facing cloud computing. Due to the dynamic change of resources and performance in the cloud computing environment, the availability and performance of resources in the reserved time period are difficult to be guaranteed. Therefore, the early reservation of resources is introduced as a QoS guarantee mechanism. The challenge is in the cloud computing environment. The Global Grid Forum (GGF) defines resource reservation in advance as the restricted access rights to resources obtained by users and resource owners after negotiation within a specified time period. In fact, early reservation can be seen as a commitment of the cloud computing platform to obtain a certain level of service within a specified time period.
相关技术中,实现资源预留的方法大致包括:In the related art, the method for realizing resource reservation generally includes:
数据中心的管理服务器接收到来自用户的预留请求后,若判断出数据中心中的可用资源中存在预留请求中的全部资源,则从可用资源中为用户分配资源并向用户返回分配的资源。After receiving the reservation request from the user, the management server of the data center allocates resources for the user from the available resources and returns the allocated resources to the user if it is determined that all the resources in the reservation request exist in the available resources in the data center. .
相关技术中,当判断出数据中心中的可用资源中不存在预留请求中的全部资源时,管理服务器向用户返回拒绝消息,使得数据中心在资源不足时,预留请求的拒绝率较高。In the related art, when it is determined that all resources in the reservation request do not exist in the available resources in the data center, the management server returns a rejection message to the user, so that when the data center is insufficient, the rejection rate of the reservation request is high.
发明内容
Summary of the invention
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.
本发明实施例提出了一种实现资源预留的方法和装置,能够降低预留请求的拒绝率。The embodiment of the invention provides a method and a device for implementing resource reservation, which can reduce the rejection rate of the reservation request.
本发明实施例提出了一种实现资源预留的方法,所述方法包括:An embodiment of the present invention provides a method for implementing resource reservation, where the method includes:
联合服务器接收到来自用户的预留请求后,获取一个或多个数据中心中的可用资源;After receiving the reservation request from the user, the federation server acquires available resources in one or more data centers;
联合服务器判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将所述预留请求分解为多个与数据中心对应的简单预留请求;其中,所述预设条件包括:数据中心中的可用资源中包含预留请求中的全部资源;The joint server determines whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiples according to available resources in the obtained one or more data centers. a simple reservation request corresponding to the data center; wherein the preset condition includes: all resources in the reservation request are included in the available resources in the data center;
联合服务器将每一个简单预留请求分别发送给对应的数据中心的服务器;The federation server sends each simple reservation request to the server of the corresponding data center separately;
联合服务器向用户返回接收到的来自一个或多个数据中心的服务器分配的资源。The federated server returns to the user the resources allocated by the server from one or more data centers.
可选地,该方法还包括:Optionally, the method further includes:
若存在满足所述预设条件的多个数据中心,则所述联合服务器将所述预留请求发送给满足所述预设条件的数据中心中的服务器;If there are multiple data centers that satisfy the preset condition, the joint server sends the reservation request to a server in a data center that satisfies the preset condition;
所述联合服务器向所述用户返回接收到的来自所述其中一个满足预设条件的数据中心中的服务器分配的资源。The federation server returns to the user the resources allocated by the server in the data center that meets the preset condition.
可选地,所述联合服务器将所述预留请求发送给满足预设条件的数据中心中的服务器包括:Optionally, the sending, by the synchronizing server, the reservation request to the server in the data center that meets the preset condition includes:
所述联合服务器按照公式计算每一个数据中心的偏差程度,将所述预留请求发送给计算得到的偏差程度最小的数据中心的服务器;The federation server according to the formula Calculating the degree of deviation of each data center, and transmitting the reservation request to the server of the data center with the smallest degree of deviation obtained;
其中,ε为偏差程度,m为预留请求中的资源包含的需求参数的个数,qi为数据中心中的资源的第i个需求参数,ri为所述预留请求中的资源的第i个需求参数,i为大于零的正整数。Where ε is the degree of deviation, m is the number of demand parameters included in the resource in the reservation request, q i is the i-th demand parameter of the resource in the data center, and r i is the resource in the reservation request The i-th demand parameter, i is a positive integer greater than zero.
可选地,该方法还包括:
Optionally, the method further includes:
在所述联合服务器向用户返回分配的资源后,将所述用户的提前预留状态更改为预定状态。After the joint server returns the allocated resources to the user, the advanced reservation status of the user is changed to a predetermined state.
可选地,该方法还包括:Optionally, the method further includes:
所述联合服务器向所述用户返回所述分配的资源后,生成预留消息并将所述预留消息放入预留队列中;After the joint server returns the allocated resource to the user, generate a reservation message and put the reservation message into the reservation queue;
当所述预留消息中的预留开始时间到达时,所述联合服务器判断所述预留消息中分配的资源是否均可用,若所述预留消息中分配的资源均可用,则将所述用户的提前预留状态更改为活跃状态,通知用户已绑定所需资源,通知分配资源的数据中心将分配给所述用户的资源置为不可用。When the reservation start time in the reservation message arrives, the joint server determines whether resources allocated in the reservation message are all available, and if the resources allocated in the reservation message are available, the The user's early reservation status is changed to an active state, notifying the user that the required resources have been bound, and notifying the data center that allocates the resources that the resources allocated to the user are made unavailable.
可选地,该方法还包括:Optionally, the method further includes:
若所述预留消息中分配的资源中的部分或全部资源不可用,则所述联合服务器继续执行所述获取一个或多个数据中心中的可用资源的步骤。If some or all of the resources allocated in the reservation message are unavailable, the joint server continues to perform the step of acquiring available resources in one or more data centers.
可选地,该方法还包括:Optionally, the method further includes:
当所述预留消息中的预留结束时间到达时,所述联合服务器将所述用户的提前预留状态更改为完成状态,并通知分配资源的数据中心释放分配给所述用户的资源;When the reservation end time in the reservation message arrives, the joint server changes the early reservation status of the user to a completion status, and notifies the data center that allocates resources to release resources allocated to the user;
或者,当所述联合服务器判断出满足预设终止条件时,所述联合服务器将所述用户的提前预留状态更改为终止状态,并通知分配资源的数据中心释放分配给所述用户的资源。Alternatively, when the joint server determines that the preset termination condition is met, the joint server changes the early reservation state of the user to a termination state, and notifies the data center that allocates resources to release resources allocated to the user.
可选地,该方法还包括:Optionally, the method further includes:
所述联合服务器接收到来自所述用户的修改预留请求后,继续执行获取一个或多个数据中心中的可用资源的步骤。After receiving the modification reservation request from the user, the syndication server continues to perform the step of acquiring available resources in one or more data centers.
可选地,该方法还包括:Optionally, the method further includes:
所述联合服务器接收到来自所述用户的修改预留请求后,将所述用户的提前预留状态更改为预定重协商状态或活跃重协商状态;After receiving the modification reservation request from the user, the joint server changes the early reservation status of the user to a predetermined renegotiation status or an active renegotiation status;
所述联合服务器向所述用户返回重新协商后分配的资源后,将所述用户的提前预留状态更改为预定状态或活跃状态。
After the joint server returns the resources allocated after the renegotiation to the user, the advanced reservation state of the user is changed to a predetermined state or an active state.
可选地,该方法还包括:Optionally, the method further includes:
所述联合服务器接收到来自所述用户的撤销请求后,将所述用户的提前预留状态更改为撤销状态,并通知分配资源的数据中心释放分配给所述用户的资源。After receiving the revocation request from the user, the syndication server changes the early reservation status of the user to an revoked state, and notifies the data center that allocates resources to release resources allocated to the user.
本发明实施例还提出了一种实现资源预留的装置,包括:An embodiment of the present invention further provides an apparatus for implementing resource reservation, including:
获取模块,设置为接收到来自用户的预留请求,获取一个或多个数据中心中的可用资源;Obtaining a module, configured to receive a reservation request from a user, to obtain available resources in one or more data centers;
处理模块,设置为判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将预留请求分解为多个数据中心对应的简单预留请求;其中,所述预设条件包括:数据中心的可用资源中包含预留请求中的全部资源;将每一个简单预留请求分别发送给对应的数据中心的服务器;The processing module is configured to determine whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiple according to the available resources in the obtained one or more data centers. a simple reservation request corresponding to the data center; wherein the preset condition includes: all resources in the reservation request are included in the available resources of the data center; and each simple reservation request is separately sent to the server of the corresponding data center;
返回模块,设置为向用户返回接收到的来自一个或多个数据中心的服务器分配的资源。A return module, set to return to the user the resources allocated by the server from one or more data centers.
可选地,所述处理模块还设置为:Optionally, the processing module is further configured to:
若存在满足所述预设条件的多个数据中心,则将预留请求发送给其中一个满足所述预设条件的数据中心的服务器;If there are multiple data centers that satisfy the preset condition, send a reservation request to a server of one of the data centers that meets the preset condition;
所述返回模块还设置为:The return module is also set to:
向所述用户返回接收到的来自所述其中一个满足预设条件的数据中心的服务器分配的资源。Returning to the user the resources allocated by the server from the one of the data centers that satisfy the preset condition.
可选地,所述处理模块还设置为:Optionally, the processing module is further configured to:
在所述返回模块向用户返回分配的资源后,将所述用户的提前预留状态更改为预定状态。After the return module returns the allocated resources to the user, the advanced reservation state of the user is changed to a predetermined state.
可选地,所述处理模块还设置为:Optionally, the processing module is further configured to:
在所述返回模块向所述用户返回所述分配的资源后,生成预留消息并将所述预留消息放入预留队列中;当所述预留消息中的预留开始时间到达时,判断所述预留消息中分配的资源是否均可用,若所述预留消息中分配的资源
均可用,将所述用户的提前预留状态更改为活跃状态通知用户已绑定所需资源,通知分配资源的数据中心将分配给所述用户的资源置为不可用。After the returning module returns the allocated resource to the user, generating a reservation message and placing the reservation message into the reservation queue; when the reservation start time in the reservation message arrives, Determining whether resources allocated in the reserved message are all available, if resources allocated in the reserved message
Both are available, changing the early reservation state of the user to an active state to notify the user that the required resource has been bound, and notifying the data center that allocates the resource that the resource allocated to the user is made unavailable.
可选地,所述处理模块还设置为:Optionally, the processing module is further configured to:
若所述预留消息中分配的资源中的部分或全部资源不可用,则则调用获取模块获取一个或多个数据中心中的可用资源。If some or all of the resources allocated in the reservation message are unavailable, the acquisition module is invoked to acquire available resources in one or more data centers.
可选地,所述处理模块还设置为:Optionally, the processing module is further configured to:
当所述预留消息中的预留结束时间到达时,将所述用户的提前预留状态更改为完成状态,并通知分配资源的数据中心释放分配给所述用户的资源;When the reservation end time in the reservation message arrives, the early reservation state of the user is changed to a completion state, and the data center that allocates the resource is notified to release the resource allocated to the user;
或者,当所述联合服务器判断出满足预设终止条件时,将所述用户的提前预留状态更改为终止状态,并通知分配资源的数据中心释放分配给所述用户的资源。Alternatively, when the joint server determines that the preset termination condition is met, the early reservation state of the user is changed to a termination state, and the data center that allocates the resource is notified to release the resource allocated to the user.
可选地,所述获取模块还设置为:Optionally, the obtaining module is further configured to:
在接收到来自所述用户的修改预留请求后,则调用获取模块获取一个或多个数据中心中的可用资源。After receiving the modify reservation request from the user, the acquisition module is invoked to obtain available resources in one or more data centers.
可选地,Optionally,
所述处理模块还设置为:The processing module is further configured to:
在所述获取模块接收到来自所述用户的修改预留请求后,将所述用户的提前预留状态更改为预定重协商状态或活跃重协商状态;在所述返回模块向所述用户返回重新协商后分配的资源后,将所述用户的提前预留状态更改为预定状态或活跃状态。After the obtaining module receives the modification reservation request from the user, changing the early reservation state of the user to a predetermined renegotiation state or an active renegotiation state; and returning to the user in the returning module After the resources allocated after negotiation, the advanced reservation state of the user is changed to a predetermined state or an active state.
可选地,Optionally,
所述处理模块还设置为:The processing module is further configured to:
在所述获取模块接收到来自所述用户的撤销请求后,将所述用户的提前预留状态更改为撤销状态,并通知分配资源的数据中心释放分配给所述用户的资源。After the obtaining module receives the revocation request from the user, the pre-reservation state of the user is changed to the revocation state, and the data center that allocates the resource is notified to release the resource allocated to the user.
与相关技术相比,本发明实施例的技术方案包括:联合服务器接收到来自用户的预留请求后,获取一个或多个数据中心中的可用资源;联合服务器
判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将预留请求分解为多个与数据中心对应的简单预留请求;其中,预设条件包括:数据中心的可用资源中包含预留请求中的全部资源;联合服务器将每一个简单预留请求发送给对应的数据中心的服务器;联合服务器向用户返回接收到的来自多个数据中心的服务器的分配的资源。通过本发明实施例的方案,通过联合服务器实现多个数据中心的可用资源的请求,在一个数据中心资源不足时,从多个数据中心中为用户分配资源,降低了预留请求的拒绝率。本发明实施例还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有计算机可执行指令,所述计算机可执行指令被执行时实现一种实现资源预留的方法。Compared with the related art, the technical solution of the embodiment of the present invention includes: after receiving the reservation request from the user, the joint server acquires available resources in one or more data centers; the joint server
Determining whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiple data centers according to the available resources in the obtained one or more data centers. A simple reservation request; wherein the preset condition includes: all resources in the reservation request are included in the available resources of the data center; the federation server sends each simple reservation request to the server of the corresponding data center; the joint server returns to the user The allocated resources of the servers received from multiple data centers. Through the solution of the embodiment of the present invention, a request for available resources of multiple data centers is implemented by the joint server, and when a data center resource is insufficient, resources are allocated to users from multiple data centers, and the rejection rate of the reservation request is reduced. The embodiment of the invention further provides a computer readable storage medium, wherein the computer readable storage medium stores computer executable instructions, and when the computer executable instructions are executed, a method for realizing resource reservation is implemented.
在阅读并理解了附图和详细描述后,可以明白其它方面。Other aspects will be apparent upon reading and understanding the drawings and detailed description.
下面对本发明实施例中的附图进行说明,实施例中的附图是用于对本申请的进一步理解,与说明书一起用于解释本申请,并不构成对本申请保护范围的限制。The drawings in the embodiments of the present invention are described below, and the accompanying drawings are used to explain the present application, and the present invention is not to be construed as limiting the scope of the application.
图1为本发明实施例的实现资源预留的方法的流程图;FIG. 1 is a flowchart of a method for implementing resource reservation according to an embodiment of the present invention;
图2为本发明实施例的实现资源预留的***的结构组成示意图;2 is a schematic structural diagram of a system for implementing resource reservation according to an embodiment of the present invention;
图3为本发明实施例的用户的提前预留状态变化示意图;FIG. 3 is a schematic diagram of changes in an advanced reservation state of a user according to an embodiment of the present invention; FIG.
图4为本发明实施例的实现资源预留的装置的结构组成示意图。FIG. 4 is a schematic structural diagram of an apparatus for implementing resource reservation according to an embodiment of the present invention.
下面结合附图对本申请作进一步的描述,并不能用来限制本申请的保护范围。需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的各种方式可以相互组合。The present application is further described below in conjunction with the accompanying drawings, and is not intended to limit the scope of the application. It should be noted that the embodiments in the present application and the various manners in the embodiments may be combined with each other without conflict.
参见图1,本发明实施例提出了一种实现资源预留的方法,所述方法包括:Referring to FIG. 1, an embodiment of the present invention provides a method for implementing resource reservation, where the method includes:
步骤100、联合服务器接收到来自用户的预留请求,获取一个或多个数
据中心中的可用资源;Step 100: The federation server receives a reservation request from a user, and acquires one or more numbers.
According to available resources in the center;
本步骤中,预留请求可以包括:预留开始时间、预留结束时间、QoS需求参数、请求预留的资源。In this step, the reservation request may include: a reservation start time, a reservation end time, a QoS requirement parameter, and a resource requested to be reserved.
其中,QoS需求参数可以包括用户希望达到的服务水平,即每一种资源对应的需求参数。例如,虚拟CPU核数、内存大小、磁盘空间、网卡数、端口数、网络带宽、互联网协议(IP,Internet Protocol)地址、媒体访问控制(MAC,Media Access Control)地址等。The QoS requirement parameter may include a service level that the user desires to reach, that is, a demand parameter corresponding to each resource. For example, the number of virtual CPU cores, memory size, disk space, number of network cards, number of ports, network bandwidth, Internet Protocol (IP) address, and media access control (MAC) address.
其中,请求预留的资源可以包括以下的任意一种或多种:计算资源、存储资源、网络资源等。The resource that is requested to be reserved may include any one or more of the following: a computing resource, a storage resource, a network resource, and the like.
其中,计算资源可以包括中央处理器(CPU,Center Process Unit)资源和内存资源,网络资源包括网络带宽资源等。The computing resources may include a central processing unit (CPU) resource and a memory resource, and the network resource includes a network bandwidth resource.
图2为本发明实施例实现资源预留的***的结构组成示意图。如图2所示,联合服务器可以从全局信息中心中获取一个或多个数据中心中的可用资源,具体可以采用向全局信息中心发送查询可用资源的指令的方式来获取。其中,全局信息中心可以是一个服务器。FIG. 2 is a schematic structural diagram of a system for implementing resource reservation according to an embodiment of the present invention. As shown in FIG. 2, the federation server can obtain available resources in one or more data centers from the global information center, and can be obtained by sending an instruction for querying available resources to the global information center. Among them, the global information center can be a server.
联合服务器也可以从每一个数据中心中获取数据中心中的可用资源。具体可以采用向每一个数据中心发送查询可用资源的指令的方式来获取,并对每一个数据中心的可用资源进行整合。Federated servers can also get the resources available in the data center from each data center. Specifically, it can be obtained by sending an instruction for querying available resources to each data center, and integrating the available resources of each data center.
每一个数据中心可以包括服务器和一个或多个资源所在的设备。在每一个数据中心中,可以在数据中心的服务器中采用虚拟资源容器(VRC,Virtual Resource Container)将相同种类的资源进行归类,形成虚拟资源列表,虚拟资源列表中的每一个表项包括每一种资源的可用状态,即该种资源在当前是否可用。Each data center can include a server and one or more resources on which the device resides. In each data center, a virtual resource container (VRC) can be used to classify the same kinds of resources in a server in the data center to form a virtual resource list. Each entry in the virtual resource list includes each The available state of a resource, that is, whether the resource is currently available.
每一个数据中心能够自动检测资源的动态加入和退出,例如资源所在的设备的启动与关闭等。当检测到资源的动态加入和退出时,数据中心的服务器可以自动更新VRC中的虚拟资源列表。Each data center can automatically detect the dynamic joining and exiting of resources, such as the startup and shutdown of the device where the resource is located. When a dynamic join and exit of a resource is detected, the server of the data center can automatically update the virtual resource list in the VRC.
VRC通过提前预留接口接收来自联合服务器的查询可用资源的指令,并通过提前预留接口将自身的可用的资源返回给联合服务器。
The VRC receives an instruction from the federated server to query available resources through the advance reservation interface, and returns its available resources to the federated server through the advance reservation interface.
步骤101、联合服务器判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将预留请求分解为多个与数据中心对应的简单预留请求;Step 101: The joint server determines whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiple according to the available resources in the obtained one or more data centers. a simple reservation request corresponding to the data center;
本步骤中,预设条件可以包括:数据中心的可用资源中包含预留请求中的全部资源。In this step, the preset condition may include: all resources in the reservation request are included in the available resources of the data center.
本步骤中,简单预留请求可以包括:预留开始时间、预留结束时间、QoS需求参数、请求预留的资源。In this step, the simple reservation request may include: a reservation start time, a reservation end time, a QoS requirement parameter, and a resource requested to be reserved.
其中,简单预留请求中请求预留的资源为预留请求中请求预留的资源的一部分。The resource reserved for reservation in the simple reservation request is part of the resource reserved for the request in the reservation request.
本步骤中,在根据获得的一个或多个数据中心中的可用资源,将预留请求分解为多个与数据中心对应的简单预留请求时,可以根据预留请求中的资源的种类分别查看每一个数据中心中是否有可用资源。例如,若预留请求中包括计算资源、存储资源和网络资源,则可以将预留请求分解多三个简单预留请求,分别为计算资源对应的简单预留请求、存储资源对应的简单预留请求以及网络资源对应的简单预留请求,然后根据每一个数据中心中的可用资源判断每一个数据中心是否有可用的请求的计算资源、可用的请求的存储资源、可用的请求的网络资源,如果有可用的请求的计算资源、可用的请求的存储资源或者可用的请求的网络资源,则将分解后的简单预留请求发送给对应的数据中心。例如,有三个数据中心,数据中1、数据中心2以及数据中心3,若数据中心1有可用的请求的计算资源,则将分解后的计算资源对应的简单预留请求发送给数据中心1;若数据中心2有可用的请求的存储资源,则将分解后的存储资源对应的简单预留请求发送给数据中心2;若数据中心3有可用的请求的网络资源,则将分解后的网络资源对应的简单预留请求发送给数据中心3。In this step, when the reservation request is decomposed into multiple simple reservation requests corresponding to the data center according to the available resources in the obtained one or more data centers, the reservation may be separately viewed according to the types of resources in the reservation request. Is there any resources available in each data center? For example, if the reservation request includes the computing resource, the storage resource, and the network resource, the reservation request may be decomposed into three simple reservation requests, which are respectively a simple reservation request corresponding to the computing resource and a simple reservation corresponding to the storage resource. Requests and simple reservation requests corresponding to network resources, and then, according to available resources in each data center, determine whether each data center has available requested computing resources, available requested storage resources, available requested network resources, if The available simple request resource, the available requested storage resource, or the available requested network resource are sent to the corresponding data center. For example, there are three data centers, data data 1, data center 2, and data center 3, if the data center 1 has available requested computing resources, the simple reservation request corresponding to the decomposed computing resources is sent to the data center 1; If the data center 2 has the requested storage resource available, the simple reservation request corresponding to the decomposed storage resource is sent to the data center 2; if the requested network resource is available in the data center 3, the decomposed network resource is used. The corresponding simple reservation request is sent to the data center 3.
可选地,对于每一个简单预留请求中请求的资源,如果有多个数据中心均有可用的请求的资源,可以按照公式计算每一个数据中心的该资源的偏差程度;将简单预留请求发送给计算得到的偏差程度最小的数据中心。Optionally, for each resource requested in the simple reservation request, if there are multiple data centers available for the requested resource, the formula may be followed. Calculate the degree of deviation of the resource in each data center; send a simple reservation request to the calculated data center with the least degree of deviation.
其中,ε为偏差程度,m为预留请求中的一种资源包含的需求参数的个
数,qi为数据中心中的一种资源的第i个需求参数,ri为预留请求中的一种资源的第i个需求参数,i为大于零的正整数。Where ε is the degree of deviation, m is the number of demand parameters included in a resource in the reservation request, q i is the i-th demand parameter of a resource in the data center, and r i is in the reservation request The i-th demand parameter of a resource, i is a positive integer greater than zero.
例如,计算资源的需求参数包括CPU核数和内存大小,则m取2,存储资源的需求参数包括存储空间大小,则m取1。For example, if the demand parameter of the computing resource includes the CPU core number and the memory size, then m takes 2, and the demand parameter of the storage resource includes the storage space size, then m takes 1.
步骤102、联合服务器将每一个简单预留请求分别发送给对应的数据中心的服务器;Step 102: The joint server sends each simple reservation request to the server of the corresponding data center.
本步骤中,数据中心的服务器接收到简单预留请求后,为用户分配简单预留请求中请求预留的资源,将分配的资源返回给联合服务器。In this step, after receiving the simple reservation request, the server of the data center allocates the resource reserved for request in the simple reservation request, and returns the allocated resource to the joint server.
步骤103、联合服务器向用户返回接收到的来自一个或多个数据中心的服务器分配的资源。Step 103: The federation server returns the received resources allocated by the server from one or more data centers to the user.
本发明实施例的技术方案,通过联合服务器实现一个或多个数据中心的可用资源的请求,在一个数据中心资源不足时,从多个数据中心中为用户分配资源,降低了预留请求的拒绝率。The technical solution of the embodiment of the present invention implements a request for available resources of one or more data centers by using a joint server, and allocates resources for users from multiple data centers when a data center resource is insufficient, thereby reducing the rejection of the reservation request. rate.
可选的,该方法还包括:Optionally, the method further includes:
若存在满足预设条件的一个或多个数据中心,则联合服务器将所述预留请求发送给其中一个满足预设条件的数据中心的服务器;联合服务器向用户返回接收到的来自所述其中一个满足预设条件的数据中心的服务器分配的资源。If there is one or more data centers that meet the preset condition, the federation server sends the reservation request to one of the servers of the data center that meets the preset condition; the federation server returns the received one from the one of the received The resources allocated by the server in the data center that meet the preset conditions.
其中,可以将预留请求发送给满足预设条件的数据中心中的任意一个服务器,也可以将预留请求发送给满足预设条件的数据中心中空闲资源最多的一个数据中心。The reservation request may be sent to any one of the data centers that meet the preset condition, or the reservation request may be sent to one data center with the most idle resources in the data center that meets the preset condition.
可选地,联合服务器可以按照公式计算每一个数据中心的偏差程度,将所述预留请求发送给计算得到的偏差程度最小的数据中心的服务器;Optionally, the federation server can follow the formula Calculating the degree of deviation of each data center, and transmitting the reservation request to the server of the data center with the smallest degree of deviation obtained;
其中,ε为偏差程度,m为预留请求中的资源包含的需求参数的个数,qi为数据中心中的资源的第i个需求参数,ri为预留请求中的资源的第i个需求参数。Where ε is the degree of deviation, m is the number of demand parameters included in the resource in the reservation request, q i is the i-th demand parameter of the resource in the data center, and r i is the i-th resource of the reservation request Demand parameters.
可选的,该方法还包括:
Optionally, the method further includes:
在联合服务器接收到来自用户的预留请求后,将用户的提前预留状态设置为请求预留协商状态;在联合服务器向用户返回分配的资源后,将用户的提前预留状态更改为预定状态。After the joint server receives the reservation request from the user, the user's early reservation status is set to the request reservation negotiation status; after the joint server returns the allocated resources to the user, the user's early reservation status is changed to a predetermined status. .
图3为本发明实施例的用户的提前预留状态变化示意图。如图3所示,在联合服务器接收到来自用户的预留请求后,用户的提前预留状态为请求预留协商状态;在联合服务器向用户返回分配的资源后,即成功协商,用户的提前预留状态变更为预定状态。FIG. 3 is a schematic diagram of a user's advanced reservation state change according to an embodiment of the present invention. As shown in FIG. 3, after the joint server receives the reservation request from the user, the user's early reservation status is the request reservation negotiation status; after the joint server returns the allocated resources to the user, the negotiation is successful, and the user advances. The reservation status is changed to a predetermined status.
可选的,该方法还包括:Optionally, the method further includes:
联合服务器向用户返回分配的资源后,生成预留消息并将所述预留消息放入预留队列中;当预留消息中的预留开始时间到达时,联合服务器判断所述预留消息中分配的资源是否均可用,若预留消息中分配的资源均可用,则将用户的提前预留状态更改为活跃状态,通知用户已绑定所需资源,通知分配资源的服务器将分配给所述用户的资源置为不可用。After the joint server returns the allocated resources to the user, the reservation message is generated and the reservation message is put into the reservation queue; when the reservation start time in the reservation message arrives, the joint server determines the reservation message. Whether the allocated resources are available, if the resources allocated in the reservation message are available, the user's early reservation status is changed to an active state, the user is notified that the required resources have been bound, and the server that allocates the resources is notified to be allocated to the The user's resources are made unavailable.
可选的,所述方法还包括:Optionally, the method further includes:
当预留消息中的预留开始时间到达时,如果用户当前的提前预留状态为预定状态,则判断预留消息中分配的资源是否可用,并继续执行后续流程,例如该后续流程可以是根据资源可用情况将状态变更为活跃,或者预定重协商等。When the reservation start time in the reservation message arrives, if the current advance reservation status of the user is the predetermined status, it is determined whether the resource allocated in the reservation message is available, and the subsequent process is continued, for example, the subsequent process may be based on The resource availability changes the status to active, or scheduled renegotiation.
当预留消息中的预留开始时间到达时,如果判断出用户当前的提前预留状态为终止状态或撤销状态,则结束本流程。When the reservation start time in the reservation message arrives, if it is determined that the current advance reservation status of the user is the termination status or the revocation status, the process ends.
如图3所示,预留开始时间到达时,用户的提前预留状态变更为活跃状态。As shown in FIG. 3, when the reservation start time arrives, the user's early reservation state is changed to the active state.
其中,预留消息可以包括预留开始时间、预留结束时间、QoS需求参数、预留类型、预留标识、每一个数据中心分配的资源。The reservation message may include a reservation start time, a reservation end time, a QoS requirement parameter, a reservation type, a reservation identifier, and resources allocated by each data center.
其中,预留类型用于表示预留消息是简单预留消息还是联合预留消息,简单预留消息只需一个数据中心的资源即可完成,联合预留消息则需多个数据中心的资源协同完成。The reservation type is used to indicate whether the reservation message is a simple reservation message or a joint reservation message. The simple reservation message only needs to be completed by one data center resource, and the joint reservation message requires resource coordination of multiple data centers. carry out.
预留标识为联合服务器向用户返回分配的资源后为用户分配的标识。
The reservation identifier is an identifier assigned to the user after the federation server returns the allocated resources to the user.
在本实施例中,当预留消息中的预留开始时间到达时,联合服务器重新获取每一个数据中心可用的资源,根据重新获得的可用的资源判断分配的资源是否可用,即在重新获得的可用的资源中查找是否存在分配的资源。In this embodiment, when the reservation start time in the reservation message arrives, the joint server reacquires the resources available to each data center, and judges whether the allocated resources are available according to the re-acquired available resources, that is, in the regained Find available resources in the available resources.
通过上述技术方案,联合服务器可以采用并行的方法处理预留请求,提高处理速度,从而提高用户的体验度。Through the above technical solution, the federation server can process the reservation request in a parallel manner, thereby improving the processing speed, thereby improving the user experience.
可选的,该方法还包括:Optionally, the method further includes:
当联合服务器判断出预留消息中分配的资源中的部分或全部资源不可用时,联合服务器继续执行获取一个或多个数据中心中的可用资源的步骤。When the federation server determines that some or all of the resources allocated in the reservation message are unavailable, the federation server continues to perform the step of acquiring available resources in one or more data centers.
可选的,该方法还包括:Optionally, the method further includes:
当预留消息中的预留结束时间到达时,联合服务器将用户的提取预留状态更改为完成状态,并通知分配资源的数据中心释放分配给用户的资源;When the reservation end time in the reservation message arrives, the federation server changes the user's extraction reservation status to the completion status, and notifies the data center that allocates the resource to release the resource allocated to the user;
或者,当联合服务器判断出满足预设终止条件时,联合服务器将用户的提前预留状态更改为终止状态,并通知分配资源的数据中心释放分配给用户的资源。Alternatively, when the joint server determines that the preset termination condition is met, the federation server changes the user's early reservation state to the termination state, and notifies the data center that allocates the resource to release the resource allocated to the user.
在本实施例中,联合服务器判断出满足预设终止条件包括:联合服务器接收到来自用户的终止请求。In this embodiment, the determining, by the joint server, that the preset termination condition is met includes: the joint server receiving the termination request from the user.
在其他实施例中,还可以预先在联合服务器中设置终止条件,当满足所述设置的终止条件时,则将用户的提前预留状态更改为终止状态。终止条件可以是任意条件。In other embodiments, the termination condition may also be set in advance in the federation server, and when the set termination condition is satisfied, the user's advance reservation state is changed to the termination state. The termination condition can be any condition.
可选的,该方法还包括:Optionally, the method further includes:
联合服务器接收到来自用户的修改预留请求后,继续执行获取一个或多个数据中心中的可用资源的步骤。After the syndication server receives the modification reservation request from the user, it proceeds to perform the step of acquiring available resources in one or more data centers.
然后联合服务器判断是否存在满足预设条件的数据中心,在判断是否存在满足预设条件的数据中心时,应判断数据中心的可用资源中是否包括修改预留请求中的全部资源。Then, the joint server determines whether there is a data center that meets the preset condition. When determining whether there is a data center that satisfies the preset condition, it is determined whether the available resources in the data center include all the resources in the modification reservation request.
可选的,该方法还包括:Optionally, the method further includes:
联合服务器接收到来自用户的修改预留请求后,将用户的提前预留状态
更改为预定重协商状态或活跃重协商状态;联合服务器向用户返回重新协商后分配的资源后,将用户的提前预留状态更改为预定状态或活跃状态。After the syndication server receives the modification reservation request from the user, the advanced reservation status of the user is
Change to the scheduled renegotiation state or active renegotiation state; after the federation server returns the resources allocated after renegotiation to the user, the user's early reservation state is changed to a predetermined state or an active state.
在本实施例中,若用户的提前预留状态在联合服务器接收到来自用户的修改预留请求之前为预定状态,在联合服务器接收到来自用户的修改预留请求后,则将用户的提前预留状态更改为预定重协商状态;联合服务器向用户返回重新协商后分配的资源后,将用户的提前预留状态更改为预定状态。In this embodiment, if the advanced reservation status of the user is in a predetermined state before the joint server receives the modification reservation request from the user, after the joint server receives the modification reservation request from the user, the user advances in advance. The retention status is changed to the predetermined renegotiation status; after the federation server returns the resources allocated after the renegotiation to the user, the advanced reservation status of the user is changed to the predetermined status.
若用户的提前预留状态在联合服务器接收到来自用户的修改预留请求之前为活跃状态,在联合服务器接收到来自用户的修改预留请求后,则将用户的提前预留状态更改为活跃重协商状态;联合服务器向用户返回重新协商后分配的资源后,将用户的提前预留状态更改为活跃状态。If the advanced reservation status of the user is in an active state before the joint server receives the modify reservation request from the user, after the joint server receives the modify reservation request from the user, the advanced reservation status of the user is changed to active weight. Negotiation status; after the federation server returns the resources allocated after renegotiation to the user, the advanced reservation status of the user is changed to the active state.
可选的,该方法还包括:Optionally, the method further includes:
联合服务器接收到来自用户的撤销请求后,将用户的提前预留状态更改为撤销状态,并通知分配资源的数据中心释放分配给所述用户的资源。After receiving the revocation request from the user, the syndication server changes the user's early reservation status to the revocation status, and notifies the data center that allocates the resource to release the resources allocated to the user.
可选的,该方法还包括:Optionally, the method further includes:
当联合服务器判断出所有数据中心的可用资源不包括预留请求中的全部资源时,联合服务器向用户返回拒绝消息。When the federated server determines that all available resources in the data center do not include all of the resources in the reservation request, the federation server returns a rejection message to the user.
可选的,所述方法还包括:Optionally, the method further includes:
当联合服务器判断出所有数据中心的可用资源不包括预留请求中的全部资源时,联合服务器将用户的提前预留状态更改为拒绝状态。When the federation server determines that all available resources in the data center do not include all the resources in the reservation request, the federation server changes the user's early reservation status to the denied status.
参见图4,本发明实施例还提出了一种实现资源预留的装置,所述装置包括:Referring to FIG. 4, an embodiment of the present invention further provides an apparatus for implementing resource reservation, where the apparatus includes:
获取模块10,设置为接收到来自用户的预留请求,获取一个或多个数据中心中的可用资源;The obtaining module 10 is configured to receive a reservation request from a user, and acquire available resources in one or more data centers;
处理模块20,设置为判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将预留请求分解为多个数据中心对应的简单预留请求;其中,所述预设条件包括:数据中心的可用资源中包含预留请求中的全部资源;将每一个简单预
留请求分别发送给对应的数据中心的服务器;The processing module 20 is configured to determine whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiple according to the available resources in the obtained one or more data centers. a simple reservation request corresponding to the data center; wherein the preset condition includes: all resources in the reservation request are included in the available resources of the data center;
The leaving request is sent to the server of the corresponding data center separately;
返回模块30,设置为向用户返回接收到的来自一个或多个数据中心的服务器分配的资源。Returning to module 30, it is arranged to return to the user the resources allocated by the server from one or more data centers.
可选地,本发明实施例的装置中,所述处理模块20还设置为:Optionally, in the apparatus of the embodiment of the present invention, the processing module 20 is further configured to:
若存在满足所述预设条件的多个数据中心,则将预留请求发送给其中一个满足所述预设条件的数据中心的服务器;If there are multiple data centers that satisfy the preset condition, send a reservation request to a server of one of the data centers that meets the preset condition;
所述返回模块30还设置为:The return module 30 is further configured to:
向所述用户返回接收到的来自所述其中一个满足预设条件的数据中心的服务器分配的资源。Returning to the user the resources allocated by the server from the one of the data centers that satisfy the preset condition.
可选地,本发明实施例的装置中,所述处理模块20还设置为:Optionally, in the apparatus of the embodiment of the present invention, the processing module 20 is further configured to:
在所述返回模块30向用户返回分配的资源后,将所述用户的提前预留状态更改为预定状态。After the returning module 30 returns the allocated resources to the user, the advanced reservation state of the user is changed to a predetermined state.
可选地,本发明实施例的装置中,所述处理模块20还设置为:Optionally, in the apparatus of the embodiment of the present invention, the processing module 20 is further configured to:
在所述返回模块30向所述用户返回所述分配的资源后,生成预留消息并将所述预留消息放入预留队列中;当所述预留消息中的预留开始时间到达时,判断所述预留消息中分配的资源是否均可用,若所述预留消息中分配的资源均可用,将所述用户的提前预留状态更改为活跃状态通知用户已绑定所需资源,通知分配资源的数据中心将分配给所述用户的资源置为不可用。After the returning module 30 returns the allocated resource to the user, generating a reservation message and placing the reservation message into the reservation queue; when the reservation start time in the reservation message arrives And determining whether the resources allocated in the reservation message are all available, and if the resources allocated in the reservation message are available, changing the early reservation state of the user to an active state to notify the user that the required resources are bound, The data center that notifies the assigned resource sets the resource assigned to the user to be unavailable.
可选地,本发明实施例的装置中,所述处理模块20还设置为:Optionally, in the apparatus of the embodiment of the present invention, the processing module 20 is further configured to:
若所述预留消息中分配的资源中的部分或全部资源不可用,则则调用获取模块获取一个或多个数据中心中的可用资源。If some or all of the resources allocated in the reservation message are unavailable, the acquisition module is invoked to acquire available resources in one or more data centers.
可选地,本发明实施例的装置中,所述处理模块20还设置为:Optionally, in the apparatus of the embodiment of the present invention, the processing module 20 is further configured to:
当所述预留消息中的预留结束时间到达时,将所述用户的提前预留状态更改为完成状态,并通知分配资源的数据中心释放分配给所述用户的资源;When the reservation end time in the reservation message arrives, the early reservation state of the user is changed to a completion state, and the data center that allocates the resource is notified to release the resource allocated to the user;
或者,当所述联合服务器判断出满足预设终止条件时,将所述用户的提前预留状态更改为终止状态,并通知分配资源的数据中心释放分配给所述用户的资源。
Alternatively, when the joint server determines that the preset termination condition is met, the early reservation state of the user is changed to a termination state, and the data center that allocates the resource is notified to release the resource allocated to the user.
可选地,本发明实施例的装置中,所述获取模块10还设置为:Optionally, in the apparatus of the embodiment of the present invention, the acquiring module 10 is further configured to:
在接收到来自所述用户的修改预留请求后,则调用获取模块获取一个或多个数据中心中的可用资源。After receiving the modify reservation request from the user, the acquisition module is invoked to obtain available resources in one or more data centers.
可选地,本发明实施例的装置中,Optionally, in the apparatus of the embodiment of the present invention,
所述处理模块20还设置为:The processing module 20 is further configured to:
在所述获取模块10接收到来自所述用户的修改预留请求后,将所述用户的提前预留状态更改为预定重协商状态或活跃重协商状态;在所述返回模块30向所述用户返回重新协商后分配的资源后,将所述用户的提前预留状态更改为预定状态或活跃状态。After the obtaining module 10 receives the modification reservation request from the user, changing the early reservation state of the user to a predetermined renegotiation state or an active renegotiation state; at the returning module 30 to the user After returning the resources allocated after renegotiation, the advanced reservation status of the user is changed to a predetermined state or an active state.
可选地,本发明实施例的装置中,Optionally, in the apparatus of the embodiment of the present invention,
所述处理模块20还设置为:The processing module 20 is further configured to:
在所述获取模块10接收到来自所述用户的撤销请求后,将所述用户的提前预留状态更改为撤销状态,并通知分配资源的数据中心释放分配给所述用户的资源。After the obtaining module 10 receives the revocation request from the user, the pre-reservation state of the user is changed to the revocation state, and the data center that allocates the resource is notified to release the resource allocated to the user.
需要说明的是,以上所述的实施例仅是为了便于本领域的技术人员理解而已,并不用于限制本申请的保护范围,在不脱离本申请的发明构思的前提下,本领域技术人员对本申请所做出的任何显而易见的替换和改进等均在本申请的保护范围之内。It should be noted that the above-mentioned embodiments are only for the purpose of facilitating the understanding of those skilled in the art, and are not intended to limit the scope of the present application, and those skilled in the art will Any obvious substitutions and improvements made by the application are within the scope of the present application.
本发明实施例还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有计算机可执行指令,所述计算机可执行指令被执行时实现一种实现资源预留的方法。The embodiment of the invention further provides a computer readable storage medium, wherein the computer readable storage medium stores computer executable instructions, and when the computer executable instructions are executed, a method for realizing resource reservation is implemented.
本领域普通技术人员可以理解上述方法中的全部或部分步骤可通过程序来指令相关硬件(例如处理器)完成,所述程序可以存储于计算机可读存储介质中,如只读存储器、磁盘或光盘等。可选地,上述实施例的全部或部分步骤也可以使用一个或多个集成电路来实现。相应地,上述实施例中的各模块/单元可以采用硬件的形式实现,例如通过集成电路来实现其相应功能,也可以采用软件功能模块的形式实现,例如通过处理器执行存储于存储器中的程序/指令来实现其相应功能。本申请不限制于任何特定形式的硬件和软件的
结合。本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或者等同替换,而不脱离本申请技术方案的精神和范围,均应涵盖在本申请的权利要求范围当中。One of ordinary skill in the art will appreciate that all or a portion of the above steps may be performed by a program to instruct related hardware, such as a processor, which may be stored in a computer readable storage medium, such as a read only memory, disk or optical disk. Wait. Alternatively, all or part of the steps of the above embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the above embodiment may be implemented in the form of hardware, for example, by implementing an integrated circuit to implement its corresponding function, or may be implemented in the form of a software function module, for example, executing a program stored in the memory by a processor. / instruction to achieve its corresponding function. This application is not limited to any particular form of hardware and software.
Combine. A person skilled in the art should understand that the technical solutions of the present application can be modified or equivalent, without departing from the spirit and scope of the technical solutions of the present application, and should be included in the scope of the claims of the present application.
上述技术方案能够降低预留请求的拒绝率。
The above technical solution can reduce the rejection rate of the reservation request.
Claims (19)
- 一种实现资源预留的方法,所述方法包括:A method for implementing resource reservation, the method comprising:联合服务器接收到来自用户的预留请求后,获取一个或多个数据中心中的可用资源;After receiving the reservation request from the user, the federation server acquires available resources in one or more data centers;联合服务器判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将所述预留请求分解为多个与数据中心对应的简单预留请求;其中,所述预设条件包括:数据中心中的可用资源中包含预留请求中的全部资源;The joint server determines whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiples according to available resources in the obtained one or more data centers. a simple reservation request corresponding to the data center; wherein the preset condition includes: all resources in the reservation request are included in the available resources in the data center;联合服务器将每一个简单预留请求分别发送给对应的数据中心的服务器;The federation server sends each simple reservation request to the server of the corresponding data center separately;联合服务器向用户返回接收到的来自一个或多个数据中心的服务器分配的资源。The federated server returns to the user the resources allocated by the server from one or more data centers.
- 根据权利要求1所述的方法,该方法还包括:The method of claim 1 further comprising:若存在满足所述预设条件的多个数据中心,则所述联合服务器将所述预留请求发送给满足所述预设条件的数据中心中的服务器;If there are multiple data centers that satisfy the preset condition, the joint server sends the reservation request to a server in a data center that satisfies the preset condition;所述联合服务器向所述用户返回接收到的来自所述满足预设条件的数据中心中的服务器分配的资源。The federation server returns to the user the received resource allocated from the server in the data center that satisfies the preset condition.
- 根据权利要求2所述的方法,其中,所述联合服务器将所述预留请求发送给满足预设条件的数据中心中的服务器包括:The method according to claim 2, wherein the syndication server sends the reservation request to a server in a data center that satisfies a preset condition, including:所述联合服务器按照公式计算每一个数据中心的偏差程度,将所述预留请求发送给计算得到的偏差程度最小的数据中心的服务器;The federation server according to the formula Calculating the degree of deviation of each data center, and transmitting the reservation request to the server of the data center with the smallest degree of deviation obtained;其中,ε为偏差程度,m为预留请求中的资源包含的需求参数的个数,qi为数据中心中的资源的第i个需求参数,ri为所述预留请求中的资源的第i个需求参数,i为大于零的正整数。Where ε is the degree of deviation, m is the number of demand parameters included in the resource in the reservation request, q i is the i-th demand parameter of the resource in the data center, and r i is the resource in the reservation request The i-th demand parameter, i is a positive integer greater than zero.
- 根据权利要求1或2所述的方法,该方法还包括:The method of claim 1 or 2, further comprising:在所述联合服务器向用户返回分配的资源后,将所述用户的提前预留状态更改为预定状态。 After the joint server returns the allocated resources to the user, the advanced reservation status of the user is changed to a predetermined state.
- 根据权利要求1或2所述的方法,该方法还包括:The method of claim 1 or 2, further comprising:所述联合服务器向所述用户返回所述分配的资源后,生成预留消息并将所述预留消息放入预留队列中;After the joint server returns the allocated resource to the user, generate a reservation message and put the reservation message into the reservation queue;当所述预留消息中的预留开始时间到达时,所述联合服务器判断所述预留消息中分配的资源是否均可用,若所述预留消息中分配的资源均可用,则将所述用户的提前预留状态更改为活跃状态,通知用户已绑定所需资源,通知分配资源的数据中心将分配给所述用户的资源置为不可用。When the reservation start time in the reservation message arrives, the joint server determines whether resources allocated in the reservation message are all available, and if the resources allocated in the reservation message are available, the The user's early reservation status is changed to an active state, notifying the user that the required resources have been bound, and notifying the data center that allocates the resources that the resources allocated to the user are made unavailable.
- 根据权利要求5所述的方法,该方法还包括:The method of claim 5, further comprising:若所述预留消息中分配的资源中的部分或全部资源不可用,则所述联合服务器继续执行所述获取一个或多个数据中心中的可用资源的步骤。If some or all of the resources allocated in the reservation message are unavailable, the joint server continues to perform the step of acquiring available resources in one or more data centers.
- 根据权利要求5所述的方法,该方法还包括:The method of claim 5, further comprising:当所述预留消息中的预留结束时间到达时,所述联合服务器将所述用户的提前预留状态更改为完成状态,并通知分配资源的数据中心释放分配给所述用户的资源;When the reservation end time in the reservation message arrives, the joint server changes the early reservation status of the user to a completion status, and notifies the data center that allocates resources to release resources allocated to the user;或者,当所述联合服务器判断出满足预设终止条件时,所述联合服务器将所述用户的提前预留状态更改为终止状态,并通知分配资源的数据中心释放分配给所述用户的资源。Alternatively, when the joint server determines that the preset termination condition is met, the joint server changes the early reservation state of the user to a termination state, and notifies the data center that allocates resources to release resources allocated to the user.
- 根据权利要求1或2所述的方法,该方法还包括:The method of claim 1 or 2, further comprising:所述联合服务器接收到来自所述用户的修改预留请求后,继续执行获取一个或多个数据中心中的可用资源的步骤。After receiving the modification reservation request from the user, the syndication server continues to perform the step of acquiring available resources in one or more data centers.
- 根据权利要求8所述的方法,该方法还包括:The method of claim 8 further comprising:所述联合服务器接收到来自所述用户的修改预留请求后,将所述用户的提前预留状态更改为预定重协商状态或活跃重协商状态;After receiving the modification reservation request from the user, the joint server changes the early reservation status of the user to a predetermined renegotiation status or an active renegotiation status;所述联合服务器向所述用户返回重新协商后分配的资源后,将所述用户的提前预留状态更改为预定状态或活跃状态。After the joint server returns the resources allocated after the renegotiation to the user, the advanced reservation state of the user is changed to a predetermined state or an active state.
- 根据权利要求1或2所述的方法,该方法还包括:The method of claim 1 or 2, further comprising:所述联合服务器接收到来自所述用户的撤销请求后,将所述用户的提前 预留状态更改为撤销状态,并通知分配资源的数据中心释放分配给所述用户的资源。After the syndication server receives the revocation request from the user, the user is advanced The reservation state is changed to the revocation state, and the data center that allocates the resource is notified to release the resource allocated to the user.
- 一种实现资源预留的装置,所述装置包括:An apparatus for realizing resource reservation, the apparatus comprising:获取模块,设置为接收到来自用户的预留请求,获取一个或多个数据中心中的可用资源;Obtaining a module, configured to receive a reservation request from a user, to obtain available resources in one or more data centers;处理模块,设置为判断是否存在满足预设条件的数据中心,若不存在满足预设条件的数据中心,则根据获得的一个或多个数据中心中的可用资源,将预留请求分解为多个数据中心对应的简单预留请求;其中,所述预设条件包括:数据中心的可用资源中包含预留请求中的全部资源;将每一个简单预留请求分别发送给对应的数据中心的服务器;The processing module is configured to determine whether there is a data center that meets the preset condition. If there is no data center that meets the preset condition, the reservation request is decomposed into multiple according to the available resources in the obtained one or more data centers. a simple reservation request corresponding to the data center; wherein the preset condition includes: all resources in the reservation request are included in the available resources of the data center; and each simple reservation request is separately sent to the server of the corresponding data center;返回模块,设置为向用户返回接收到的来自一个或多个数据中心的服务器分配的资源。A return module, set to return to the user the resources allocated by the server from one or more data centers.
- 根据权利要求11所述的装置,其中,所述处理模块还设置为:The apparatus of claim 11 wherein said processing module is further configured to:若存在满足所述预设条件的多个数据中心,则将预留请求发送给其中一个满足所述预设条件的数据中心的服务器;If there are multiple data centers that satisfy the preset condition, send a reservation request to a server of one of the data centers that meets the preset condition;所述返回模块还设置为:The return module is also set to:向所述用户返回接收到的来自所述其中一个满足预设条件的数据中心的服务器分配的资源。Returning to the user the resources allocated by the server from the one of the data centers that satisfy the preset condition.
- 根据权利要求11或12所述的装置,其中,所述处理模块还设置为:The apparatus according to claim 11 or 12, wherein the processing module is further configured to:在所述返回模块向用户返回分配的资源后,将所述用户的提前预留状态更改为预定状态。After the return module returns the allocated resources to the user, the advanced reservation state of the user is changed to a predetermined state.
- 根据权利要求11或12所述的装置,其中,所述处理模块还设置为:The apparatus according to claim 11 or 12, wherein the processing module is further configured to:在所述返回模块向所述用户返回所述分配的资源后,生成预留消息并将所述预留消息放入预留队列中;当所述预留消息中的预留开始时间到达时,判断所述预留消息中分配的资源是否均可用,若所述预留消息中分配的资源均可用,将所述用户的提前预留状态更改为活跃状态通知用户已绑定所需资源,通知分配资源的数据中心将分配给所述用户的资源置为不可用。 After the returning module returns the allocated resource to the user, generating a reservation message and placing the reservation message into the reservation queue; when the reservation start time in the reservation message arrives, Determining whether the resources allocated in the reservation message are all available, and if the resources allocated in the reservation message are all available, changing the early reservation state of the user to an active state to notify the user that the required resources are bound, and notifying The data center that allocates the resource makes the resources assigned to the user unavailable.
- 根据权利要求14所述的装置,其中,所述处理模块还设置为:The apparatus of claim 14, wherein the processing module is further configured to:若所述预留消息中分配的资源中的部分或全部资源不可用,则则调用获取模块获取一个或多个数据中心中的可用资源。If some or all of the resources allocated in the reservation message are unavailable, the acquisition module is invoked to acquire available resources in one or more data centers.
- 根据权利要求14所述的装置,其中,所述处理模块还设置为:The apparatus of claim 14, wherein the processing module is further configured to:当所述预留消息中的预留结束时间到达时,将所述用户的提前预留状态更改为完成状态,并通知分配资源的数据中心释放分配给所述用户的资源;When the reservation end time in the reservation message arrives, the early reservation state of the user is changed to a completion state, and the data center that allocates the resource is notified to release the resource allocated to the user;或者,当所述联合服务器判断出满足预设终止条件时,将所述用户的提前预留状态更改为终止状态,并通知分配资源的数据中心释放分配给所述用户的资源。Alternatively, when the joint server determines that the preset termination condition is met, the early reservation state of the user is changed to a termination state, and the data center that allocates the resource is notified to release the resource allocated to the user.
- 根据权利要求11或12所述的装置,其中,所述获取模块还设置为:The apparatus according to claim 11 or 12, wherein the obtaining module is further configured to:在接收到来自所述用户的修改预留请求后,则调用获取模块获取一个或多个数据中心中的可用资源。After receiving the modify reservation request from the user, the acquisition module is invoked to obtain available resources in one or more data centers.
- 根据权利要求17所述的装置,其中,The device according to claim 17, wherein所述处理模块还设置为:The processing module is further configured to:在所述获取模块接收到来自所述用户的修改预留请求后,将所述用户的提前预留状态更改为预定重协商状态或活跃重协商状态;在所述返回模块向所述用户返回重新协商后分配的资源后,将所述用户的提前预留状态更改为预定状态或活跃状态。After the obtaining module receives the modification reservation request from the user, changing the early reservation state of the user to a predetermined renegotiation state or an active renegotiation state; and returning to the user in the returning module After the resources allocated after negotiation, the advanced reservation state of the user is changed to a predetermined state or an active state.
- 根据权利要求11或12所述的方法,其中,The method according to claim 11 or 12, wherein所述处理模块还设置为:The processing module is further configured to:在所述获取模块接收到来自所述用户的撤销请求后,将所述用户的提前预留状态更改为撤销状态,并通知分配资源的数据中心释放分配给所述用户的资源。 After the obtaining module receives the revocation request from the user, the pre-reservation state of the user is changed to the revocation state, and the data center that allocates the resource is notified to release the resource allocated to the user.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610127439.X | 2016-03-07 | ||
CN201610127439.XA CN107171976B (en) | 2016-03-07 | 2016-03-07 | Method and device for realizing resource reservation |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017152797A1 true WO2017152797A1 (en) | 2017-09-14 |
Family
ID=59788959
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2017/075199 WO2017152797A1 (en) | 2016-03-07 | 2017-02-28 | Method and device for resource reservation |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107171976B (en) |
WO (1) | WO2017152797A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110784335A (en) * | 2019-09-19 | 2020-02-11 | 烽火通信科技股份有限公司 | Network element resource reservation system under cloud scene |
CN113127185A (en) * | 2019-12-31 | 2021-07-16 | 北京懿医云科技有限公司 | Task execution queue processing method and device, storage medium and electronic equipment |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532092A (en) * | 2019-08-21 | 2019-12-03 | 云湾科技(嘉兴)有限公司 | Reso urce matching method, device and equipment |
CN115499388B (en) * | 2022-08-30 | 2024-04-12 | 阿里巴巴(中国)有限公司 | Virtual host resource allocation method, device, equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030154112A1 (en) * | 2002-02-08 | 2003-08-14 | Steven Neiman | System and method for allocating computing resources |
CN101783768A (en) * | 2010-03-08 | 2010-07-21 | 东南大学 | Quantity assurance method of grid service based on resource reservation |
CN102014159A (en) * | 2010-11-29 | 2011-04-13 | 华中科技大学 | Layered resource reservation system under cloud computing environment |
CN104301391A (en) * | 2014-09-19 | 2015-01-21 | 北京邮电大学 | Multi-domain optical network data center resource virtualization mapping method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1855424B1 (en) * | 2006-05-12 | 2013-07-10 | Panasonic Corporation | Reservation of radio resources for users in a mobile communications system |
CN102929687B (en) * | 2012-10-12 | 2016-05-25 | 山东省计算中心(国家超级计算济南中心) | A kind of energy-conservation cloud computing data center virtual machine laying method |
-
2016
- 2016-03-07 CN CN201610127439.XA patent/CN107171976B/en active Active
-
2017
- 2017-02-28 WO PCT/CN2017/075199 patent/WO2017152797A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030154112A1 (en) * | 2002-02-08 | 2003-08-14 | Steven Neiman | System and method for allocating computing resources |
CN101783768A (en) * | 2010-03-08 | 2010-07-21 | 东南大学 | Quantity assurance method of grid service based on resource reservation |
CN102014159A (en) * | 2010-11-29 | 2011-04-13 | 华中科技大学 | Layered resource reservation system under cloud computing environment |
CN104301391A (en) * | 2014-09-19 | 2015-01-21 | 北京邮电大学 | Multi-domain optical network data center resource virtualization mapping method |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110784335A (en) * | 2019-09-19 | 2020-02-11 | 烽火通信科技股份有限公司 | Network element resource reservation system under cloud scene |
CN113127185A (en) * | 2019-12-31 | 2021-07-16 | 北京懿医云科技有限公司 | Task execution queue processing method and device, storage medium and electronic equipment |
CN113127185B (en) * | 2019-12-31 | 2023-11-10 | 北京懿医云科技有限公司 | Task execution queue processing method and device, storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN107171976B (en) | 2022-03-25 |
CN107171976A (en) | 2017-09-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6751780B2 (en) | Acceleration resource processing method and equipment | |
US10122707B2 (en) | User impersonation/delegation in a token-based authentication system | |
US9967196B2 (en) | Systems and/or methods for resource use limitation in a cloud environment | |
WO2017152797A1 (en) | Method and device for resource reservation | |
US9307017B2 (en) | Member-oriented hybrid cloud operating system architecture and communication method thereof | |
US20180321974A1 (en) | Methods and systems for providing on-demand cloud computing environments | |
US11119813B1 (en) | Mapreduce implementation using an on-demand network code execution system | |
EP3479249B1 (en) | Technologies for managing application configurations and associated credentials | |
US9930138B2 (en) | Communicating with third party resources in cloud computing environment | |
WO2018176998A1 (en) | Data storage method and device | |
WO2015123999A1 (en) | Storage resource scheduling method and storage calculation system | |
WO2017035735A1 (en) | Method and apparatus for deploying network services | |
US20160105375A1 (en) | Device-to-device communication for resource sharing | |
EP3343364A1 (en) | Accelerator virtualization method and apparatus, and centralized resource manager | |
US9462068B2 (en) | Cross-domain inactivity tracking for integrated web applications | |
WO2020087948A1 (en) | Network slice template generation method, apparatus and device, and storage medium | |
WO2016070609A1 (en) | Method and system for implementing vnf instantiation, nfvo and vnfm | |
WO2013075446A1 (en) | Service processing method and system | |
CN103428198B (en) | network device, system and method | |
WO2016061935A1 (en) | Resource scheduling method, device and computer storage medium | |
WO2016145904A1 (en) | Resource management method, device and system | |
WO2018090191A1 (en) | Management method, management unit and system for network function | |
WO2016183799A1 (en) | Hardware acceleration method and relevant device | |
CN1918557A (en) | Systems and methods for creating time aware networks using independent absolute time values in network devices | |
WO2022267646A1 (en) | Pod deployment method and apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17762483 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17762483 Country of ref document: EP Kind code of ref document: A1 |