WO2012100545A1 - 一种业务调度方法、系统及设备 - Google Patents

一种业务调度方法、系统及设备 Download PDF

Info

Publication number
WO2012100545A1
WO2012100545A1 PCT/CN2011/079773 CN2011079773W WO2012100545A1 WO 2012100545 A1 WO2012100545 A1 WO 2012100545A1 CN 2011079773 W CN2011079773 W CN 2011079773W WO 2012100545 A1 WO2012100545 A1 WO 2012100545A1
Authority
WO
WIPO (PCT)
Prior art keywords
service
server
module
computing
resource management
Prior art date
Application number
PCT/CN2011/079773
Other languages
English (en)
French (fr)
Inventor
陈佩文
姚志强
谢晓冬
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2012100545A1 publication Critical patent/WO2012100545A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition

Definitions

  • the present invention relates to the field of mobile communications, and in particular, to a service scheduling method, system and device. Background technique
  • TCO total cost of ownership
  • Figure 1 shows the architecture of the existing service platform.
  • the current service platform is usually shown in Figure 1.
  • the main ways in which such various business platforms are built independently are as follows:
  • the software and hardware modules such as billing, log, report, operation and maintenance, network management, storage devices, and network equipment are repeatedly constructed, resulting in great waste of hardware and software resources.
  • Each service platform must be repeatedly connected with some external network elements (billing, overhead, network management, etc.), and the workload is very large. Moreover, in the case of these external interface changes, all the connected service platforms will be changed.
  • each service platform is not balanced, resulting in low equipment utilization.
  • the processing power of the WAP (Wireless Application Protocol) service system reaches 2000 transactions per second (TPS, Transactions Per Second), but only 800TPS is used, and the processing capacity of the MMS service system is only 200/sec, but it actually needs 300/sec.
  • TPS Wireless Application Protocol
  • MMS Mobility Management Function
  • Figure 2 is a schematic diagram of the structure of the integrated service platform. As can be seen from the figure, in addition to the service processing cluster, all other parts of the integrated service platform are used together, which can solve the problem of device redundancy and interface duplication.
  • the current scheduling method usually adds an additional scheduling subsystem under the premise of adopting the integrated service platform solution.
  • the scheduling method has the following disadvantages:
  • the scheduling granularity is too large, and the current scheduling granularity is the physical server, and the service capacity is If the requirements are small, the device utilization rate is still not improved.
  • This problem is particularly acute when the processing power of the current physical server is gradually increasing. For example, a business system requires only 300 TPS of processing power, and a single server can handle up to 3000 TPS. In the case of scheduling granularity for the server, it is extremely wasteful.
  • the technical problem to be solved by the present invention is to provide a service scheduling method, system and device for solving the problem that the existing server resources cannot be fully utilized in the prior art.
  • a service scheduling method is provided in the embodiment of the present invention, where the method includes:
  • the service scheduling module receives the number of computing units of each server reported by each resource by the resource management module, and the computing processing capability of each server is composed of one or more computing units; the service scheduling module according to the number of computing units and the service state, according to the scheduling The algorithm determines, in units of computing units, the computing units that need to be added or released, and the services that need to be performed; The service scheduling module indicates a computing unit that the resource management module needs to add or release; the service scheduling module indicates the service that the automatic deployment module needs to perform.
  • the method further includes: the service scheduling module receives the service status information reported by each server by the resource management module, where the service status is a service status that is calculated by each server in units of the computing unit.
  • An embodiment of the present invention provides a service scheduling device, where the device includes:
  • the receiving module is configured to receive, by each server, the number of computing units provided by each server reported by the resource management module, and the computing processing capability of each server is composed of one or more computing units;
  • a scheduling module configured to determine, according to a number of computing units and a service state, a computing unit that needs to be added or released in units of computing units according to a scheduling algorithm, and a service that needs to be executed;
  • the resource indication module is configured to indicate a computing unit that the resource management module needs to add or release; the service indication module is configured to indicate a service that the automatic deployment module needs to perform.
  • the receiving module is further configured to receive service status information reported by each server by the resource management module, where the service status is a service status calculated by each server in units of computing units.
  • An embodiment of the present invention provides an integrated service platform system, where the system includes: a server, configured to report the number of computing units of the server to the resource management module, where the computing processing capability of the server is composed of one or more computing units ;
  • a resource management module configured to report the number of calculation units reported by the server to the service scheduling module
  • a service scheduling module configured to determine, according to a calculation unit, a calculation unit that needs to be added or released, and a service that needs to be executed, according to a calculation unit quantity and a service status; and indicate a calculation unit that the resource management module needs to add or release, And indicating the services that the automated deployment module needs to perform;
  • a resource management module configured to be a computing unit added or released according to an indication of a service scheduling module;
  • the automatic deployment module is configured to allocate the services performed by each server according to the instructions of the service scheduling module.
  • the server is further configured to report the service status information of the local server to the resource management module, where the service status is a service status that is calculated by each server by using a computing unit;
  • the resource management module is further configured to be a server The reported service status information is reported to the service scheduling module.
  • a server in an integrated service platform system where the server includes:
  • a resource determining module configured to determine the number of computing units that the server has, and the computing processing capability of the server is composed of one or more computing units;
  • the reporting module is configured to report the number of computing units of the server to the resource management module.
  • the server further includes:
  • a service determining module configured to determine service state information of the server, where the service state is a service state that is calculated by each server by using a computing unit;
  • the reporting module is further configured to report the service status information of the local server to the resource management module.
  • the embodiment of the present invention provides a resource management device in an integrated service platform system, where the device includes:
  • a receiving module configured to receive an indication of a computing unit added or released by the service scheduling module, where the computing processing capability of each server is composed of one or more computing units;
  • the execution module is set to a computing unit that is added or released according to the instructions of the service scheduling module.
  • the device further includes: a forwarding module, configured to connect each server The number of computing units and/or service status information of each reported server is forwarded to the service scheduling module.
  • the beneficial effects of the present invention are as follows:
  • the service scheduling module is also determined by the calculation unit according to the number of calculation units and the service state according to the scheduling algorithm.
  • the computing unit that needs to be added or released, and the service that needs to be executed, can achieve the purpose of making full use of the resources of each server by reducing the granularity of the schedulable resources.
  • Figure 1 is a schematic diagram of an existing service platform architecture
  • FIG. 2 is a schematic structural diagram of an existing integrated service platform
  • FIG. 3 is a schematic flowchart of an implementation process of a service scheduling method according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a system of an integrated service platform according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a server in an integrated service platform system according to an embodiment of the present invention
  • FIG. 6 is a schematic structural diagram of a service scheduling device according to an embodiment of the present invention
  • FIG. 7 is a schematic structural diagram of a resource management device in an integrated service platform system according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of a service scheduling implementation process according to an embodiment of the present invention. detailed description
  • the object of the present invention is to provide a better scheduling scheme, which can well solve the problem that the existing scheduling method can not fully utilize the resources of each server, thereby improving the utilization rate of the device.
  • FIG. 3 is a schematic diagram of a service scheduling method implementation process. As shown in FIG. 3, during the service scheduling process, the following steps may be included:
  • Step 301 The service scheduling module receives each server reported by each resource by the resource management module.
  • the number of computing units provided, the computing processing capacity of each server is composed of one or more computing units;
  • Step 302 The service scheduling module determines, according to the number of computing units and the service state, the computing unit that needs to be added or released, and the service that needs to be performed, in units of computing units.
  • Step 303 The service scheduling module indicates that the resource management module needs to be added or released. Computing unit;
  • Step 304 The service scheduling module indicates a service that the automatic deployment module needs to perform.
  • the virtual machine technology may be utilized to virtualize the physical server, and the physical server is cut into a smaller granular virtual computing unit; then, the resource management module increases the interface between the virtual machine and the virtual machine.
  • Manage virtual computing units may be utilized to virtualize the physical server, and the physical server is cut into a smaller granular virtual computing unit; then, the resource management module increases the interface between the virtual machine and the virtual machine.
  • the service scheduling module can periodically schedule the virtual computing unit resource status (CPU, memory usage, etc.) and service status (traffic volume, etc.), and the automatic deployment module also performs service deployment on the virtual computing resource.
  • virtual computing unit resource status CPU, memory usage, etc.
  • service status traffic volume, etc.
  • the method further includes: the service scheduling module receives the service status information reported by each server by the resource management module, where the service status is a service status calculated by each server by using a computing unit.
  • an embodiment of the present invention further provides an integrated service platform system, a service scheduling device, a server in an integrated service platform system, and a resource management device in an integrated service platform system.
  • the principle of the device to solve the problem is similar to the service scheduling method. Therefore, the implementation of these devices can be referred to the implementation of the method, and the repeated description will not be repeated.
  • FIG 4 is a schematic diagram of the system structure of the integrated service platform.
  • the integrated service platform system can include:
  • the server 401 is configured to report the number of computing units of the server to the resource management module, where the computing processing capability of the server is composed of one or more computing units;
  • the resource management module 402 is configured to report the number of calculation units reported by the server to the service scheduling Module
  • the service scheduling module 403 is configured to determine, according to the number of computing units and the service state, a computing unit that needs to be added or released in units of computing units according to a scheduling unit, and a service that needs to be executed; and instruct the computing unit that the resource management module needs to be added or released, And indicating the services that the automated deployment module needs to perform;
  • a resource management module 402 configured to be a computing unit added or released according to an indication of a service scheduling module
  • the automatic deployment module 404 is configured to allocate the services performed by each server according to the instructions of the service scheduling module.
  • the server may be further configured to report the service status information of the local server to the resource management module, where the service status is a service status calculated by each server by using a computing unit.
  • the resource management module may be further configured to report the service status information reported by the server to the service scheduling module.
  • FIG. 5 is a schematic structural diagram of a server in an integrated service platform system. As shown in FIG. 6, the server may include:
  • the resource determining module 501 is configured to determine the number of computing units that the server has, and the computing processing capability of the server is composed of one or more computing units;
  • the reporting module 502 is configured to report the number of computing units of the server to the resource management module.
  • the server may further include: a service determining module 503, configured to determine service state information of the server, where the service state is a service state that is calculated by each server by using a computing unit; Further, it is set to report the service status information of the local server to the resource management module.
  • a service determining module 503 configured to determine service state information of the server, where the service state is a service state that is calculated by each server by using a computing unit; Further, it is set to report the service status information of the local server to the resource management module.
  • FIG. 6 is a schematic structural diagram of a service scheduling device, as shown in FIG. 6, the service scheduling device may be To include:
  • the receiving module 601 is configured to receive, by each server, the number of computing units of each server reported by the resource management module, where the computing processing capability of each server is composed of one or more computing units;
  • the scheduling module 602 is configured to determine, according to the number of computing units and the service state, a computing unit that needs to be added or released in units of computing units according to a scheduling algorithm, and a service that needs to be performed;
  • a resource indication module 603, configured to indicate a computing unit that the resource management module needs to add or release;
  • the service indication module 604 is set to indicate the service that the automatic deployment module needs to perform.
  • the receiving module 601 may be further configured to receive service status information reported by each server by the resource management module, where the service status is a service status calculated by each server in units of computing units.
  • the resource management device may include:
  • the receiving module 701 is configured to receive an indication of a computing unit added or released by the service scheduling module, where the computing processing capability of each server is composed of one or more computing units;
  • the execution module 702 is configured to be a calculation unit that is added or released according to an indication of the service scheduling module.
  • the resource management device may further include: a forwarding module 803, configured to forward the number of computing units and/or service state information of each server reported by each server to the service scheduling module.
  • a forwarding module 803 configured to forward the number of computing units and/or service state information of each server reported by each server to the service scheduling module.
  • FIG. 8 is a schematic diagram of a service scheduling implementation process.
  • the virtualization module virtualizes all or part of the server into a computing unit according to a predetermined policy.
  • the flow of the service scheduling may be as follows:
  • Step 801 The server/computing unit that has deployed the service periodically reports the resource status and the service status to the resource management module. If it is an idle server/computing unit, only the resource status is reported.
  • Step 802 The resource management module further reports the foregoing information to the service scheduling module.
  • Step 803 The service scheduling module calculates resources that need to be increased/decreased according to the obtained information and a predefined algorithm.
  • Step 804 The service scheduling module applies for/releases resources to the resource management module according to the calculation result. After the application is successful, proceed to the next step.
  • Step 805 The service scheduling module issues an instruction to deploy/uninstall the service module to the automatic deployment module.
  • Step 806 The automatic deployment module executes the above instruction.
  • Step 807 The automatic deployment module notifies the service scheduling module of the execution result.
  • Step 808 In the case that the deployment/uninstallation is successful, the service scheduling module notifies the deployment change of the current service module of the service distribution module, so that the service classification device adjusts the policy of the service distribution.
  • the service module is a module that processes one or more services, and generally, one service corresponds to one service module.
  • the actual scheduling process may also include other steps such as abnormal process processing. It can be seen from the above embodiments that, in the technical solution provided by the embodiment of the present invention, the server is virtualized into a computing unit by adding a virtualization module, thereby reducing the granularity of the schedulable resource;
  • the resource management module increases the interface with the virtual machine, so that the virtual computing unit can be managed.
  • the resource management module further retains the original function of managing the server resources, so that the scheduling object can be either a server or a computing unit after virtualization;
  • the service scheduling module periodically schedules the resource status (CPU, memory usage, etc.) and service status (traffic volume, etc.) of the virtual computing unit or the server.
  • the automatic deployment module can perform service deployment on the virtual computing resource, or Business deployment on the server.
  • this scheme significantly improves equipment utilization.
  • the processing capacity of a certain service system is only 300 TPS, 400 TPS, 600 TPS, and 700 TPS, respectively, and the processing capacity of a single server can reach 3000 TPS.
  • the scheduling granularity can only be a server, deploying these services requires 4 servers, and with this solution, only one server is needed.
  • this solution provides the ability to schedule based on business capabilities compared to a pure virtual machine solution.
  • a simple virtual machine can only allocate resources based on server resources such as CPU and memory occupancy, and cannot be scheduled based on traffic. Therefore, the solution combines the scheduling function and the virtual machine technology, provides a more flexible scheduling granularity, and solves the problem of low equipment utilization.
  • embodiments of the present invention can be provided as a method, system, or computer program product.
  • the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware.
  • the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG.
  • the computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing device to produce a machine for generating settings by instructions executed by a processor of a computer or other programmable data processing device To implement one or more blocks in a process or multiple processes and/or block diagrams in the flowchart The device for the function specified in the box.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps that are set to implement the functions specified in one or more of the flow or in a block or blocks of the flowchart.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Debugging And Monitoring (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开了一种业务调度方法、系统及设备,包括:业务调度模块接收各服务器经资源管理模块上报的各服务器所具备的计算单元数量,每一服务器的计算处理能力由一个或多个计算单元构成;业务调度模块根据计算单元数量及业务状态,按调度算法以计算单元为单位确定需要增加或释放的计算单元、以及需要执行的业务;业务调度模块指示资源管理模块需要增加或释放的计算单元;业务调度模块指示自动部署模块需要执行的业务。本发明可以通过降低可调度资源的粒度,实现充分利用各服务器资源的目的。

Description

一种业务调度方法、 系统及设备 技术领域
本发明涉及移动通讯领域, 特别涉及一种业务调度方法、 系统及设备。 背景技术
金融危机背景下, 企业如何降低总所有成本 (TCO , Total cost of ownership ) 的问题被提高了前所未有的高度, 运营商当然也不例外。 而由 于当前业务平台存在软硬件型号不统一、 冗余模块多、 设备利用率低等特 点, 使得解决这个问题在业务平台领域有着更重要的意义。
图 1为现有业务平台架构示意图, 当前的业务平台通常如图 1所示。 这种各种业务平台独立建设的方式主要存在如下问题:
1、 计费、 日志、 报表、 运维、 网管、 存储设备、 网络设备等软硬件模 块重复建设, 造成软硬件资源极大浪费。
2、 各业务平台采用的外购软硬件类型、 实现的操作维护手段都有可能 不同, 会造成系统的维护成本成倍的增加。
3、 每个业务平台都要和某些外部网元(计费, 开销户, 网管等)进行 重复对接, 工作量很大。 并且, 在这些外部接口变更的情况下, 会造成所 有对接的业务平台都要改动。
4、 各业务平台处理能力不均衡造成设备利用率不高, 例如: 无线应用 协议 ( WAP, Wireless Application Protocol )业务系统的处理能力达到 2000 每秒事务数( TPS , Transactions Per Second ), 但实际只用到了 800TPS , 同 时彩信业务系统的处理能力只有 200条 /秒, 但实际需要 300条 /秒。 独立平 台情况下, 无法做到把 WAP系统空闲的处理能力共享给彩信系统使用。
针对软硬件型号不统一, 业界通常通过采用统一的刀片服务器、 并强 制统一外购系统软件的方法来有效解决。
针对设备冗余、 接口重复, 业界通常通过提取公共模块和接口, 提供 综合业务平台的方式来有效解决。 图 2为综合业务平台结构示意图, 从图 中可以看到, 综合业务平台中, 除了业务处理集群以外, 其他部分全部共 用, 从而可以很好的解决设备冗余和接口重复问题。
而针对设备利用率不高的问题, 通常还需要在采用综合业务平台方案 的前提下, 通过增加额外的调度子系统、 实现调度功能来实现各业务平台 间共享处理能力以及自动容灾, 从而提高设备利用率。
当前的调度方法通常是在采用综合业务平台方案的前提下, 增加额外 的调度子系统, 但是, 该调度方法存在的不足在于: 调度的粒度太大, 目 前的调度粒度为物理服务器, 在业务容量要求较小的情况下, 仍然不能很 好的提高设备利用率。 在当前物理服务器处理能力逐渐提升的情况下, 该 问题尤为突出。 例如, 某业务系统所需处理能力仅为 300TPS , 而单台服务 器的处理能力可达 3000TPS , 在调度粒度为服务器的情况下, 就会造成极 大的浪费。
因此, 即使增加了额外的调度子系统, 该调度方法仍然不能充分利用 各服务器资源, 也不能很好的提高设备利用率。 发明内容
本发明所解决的技术问题是提供了一种业务调度方法、 系统及设备, 用以解决现有技术中存在的不能充分利用各服务器资源的问题。
本发明实施例中提供了一种业务调度方法, 所述方法包括:
业务调度模块接收各服务器经资源管理模块上报的各服务器所具备的 计算单元数量, 每一服务器的计算处理能力由一个或多个计算单元构成; 业务调度模块根据计算单元数量及业务状态, 按调度算法以计算单元 为单位确定需要增加或释放的计算单元、 以及需要执行的业务; 业务调度模块指示资源管理模块需要增加或释放的计算单元; 业务调度模块指示自动部署模块需要执行的业务。
在上述方案中, 所述方法进一步包括: 业务调度模块接收各服务器经 资源管理模块上报的业务状态信息, 所述业务状态是各服务器以计算单元 为单位统计的业务状态。
本发明实施例中提供了一种业务调度设备, 所述设备包括:
接收模块, 设置为接收各服务器经资源管理模块上报的各服务器所具 备的计算单元数量, 每一服务器的计算处理能力由一个或多个计算单元构 成;
调度模块, 设置为根据计算单元数量及业务状态, 按调度算法以计算 单元为单位确定需要增加或释放的计算单元、 以及需要执行的业务;
资源指示模块, 设置为指示资源管理模块需要增加或释放的计算单元; 业务指示模块, 设置为指示自动部署模块需要执行的业务。
在上述方案中, 所述接收模块进一步设置为接收各服务器经资源管理 模块上报的业务状态信息, 所述业务状态是各服务器以计算单元为单位统 计的业务状态。
本发明实施例中提供了一种综合业务平台系统, 所述系统包括: 服务器, 设置为向资源管理模块上报本服务器所具备的计算单元数量 , 服务器的计算处理能力由一个或多个计算单元构成;
资源管理模块, 设置为将服务器上报的计算单元数量上报业务调度模 块;
业务调度模块, 设置为根据计算单元数量及业务状态, 按调度算法以 计算单元为单位确定需要增加或释放的计算单元、 以及需要执行的业务; 并指示资源管理模块需要增加或释放的计算单元, 以及指示自动部署模块 需要执行的业务; 资源管理模块, 设置为根据业务调度模块的指示增加或释放的计算单 元;
自动部署模块, 设置为根据业务调度模块的指示分配各服务器执行的 业务。
在上述方案中, 所述服务器进一步设置为向资源管理模块上报本服务 器的业务状态信息, 所述业务状态是各服务器以计算单元为单位统计的业 务状态; 所述资源管理模块进一步设置为将服务器上报的业务状态信息上 报业务调度模块。
本发明实施例中提供了一种综合业务平台系统中的服务器, 所述服务 器包括:
资源确定模块, 设置为确定本服务器所具备的计算单元数量, 服务器 的计算处理能力由一个或多个计算单元构成;
上报模块, 设置为向资源管理模块上报本服务器所具备的计算单元数 量。
在上述方案中, 所述服务器进一步包括:
业务确定模块, 设置为确定本服务器的业务状态信息, 所述业务状态 是各服务器以计算单元为单位统计的业务状态;
所述上报模块进一步设置为向所述资源管理模块上报本服务器的业务 状态信息。
本发明实施例中提供了一种综合业务平台系统中的资源管理设备, 所 述设备包括:
接收模块, 设置为接收业务调度模块增加或释放的计算单元的指示, 每一服务器的计算处理能力由一个或多个计算单元构成;
执行模块, 设置为根据业务调度模块的指示增加或释放的计算单元。 在上述方案中, 所述设备进一步包括: 转发模块, 设置为将各服务器 上报的各服务器所具备的计算单元数量和 /或业务状态信息转发给业务调度 模块。
本发明有益效果如下: 在本发明实施例提供的技术方案中, 由于各服 务器是按计算单元上报自身的处理能力, 业务调度模块也是根据计算单元 数量及业务状态按调度算法以计算单元为单位确定需要增加或释放的计算 单元, 以及需要执行的业务, 因此可以通过降低可调度资源的粒度, 从而 实现充分利用各服务器资源的目的。 附图说明
图 1为现有业务平台架构示意图;
图 2为现有综合业务平台结构示意图;
图 3为本发明实施例中业务调度方法实施流程示意图;
图 4为本发明实施例中综合业务平台系统结构示意图;
图 5为本发明实施例中综合业务平台系统中的服务器结构示意图; 图 6为本发明实施例中业务调度设备结构示意图;
图 7 为本发明实施例中综合业务平台系统中的资源管理设备结构示意 图;
图 8为本发明实施例中业务调度实施流程示意图。 具体实施方式
本发明的目的在于提出一种更好地调度方案, 可以很好的解决现有调 度方法不能充分利用各服务器资源的问题, 从而可以更好的提高设备利用 率。 下面结合附图对本发明的具体实施方式进行说明。
图 3为业务调度方法实施流程示意图, 如图 3所示, 进行业务调度过 程中, 可以包括如下步驟:
步驟 301、业务调度模块接收各服务器经资源管理模块上报的各服务器 所具备的计算单元数量, 每一服务器的计算处理能力由一个或多个计算单 元构成;
步驟 302、业务调度模块根据计算单元数量及业务状态按调度算法以计 算单元为单位确定需要增加或释放的计算单元, 以及需要执行的业务; 步驟 303、 业务调度模块指示资源管理模块需要增加或释放的计算单 元;
步驟 304、 业务调度模块指示自动部署模块需要执行的业务。
具体的, 在实施过程中, 可以利用虚拟机技术, 将物理服务器虚拟化, 将物理服务器切割成更小粒度的虚拟计算单元; 然后, 在资源管理模块增 加和虚拟机之间的接口, 从而可以管理虚拟计算单元;
业务调度模块则可以定期根据虚拟计算单元资源状态 (CPU、 内存占 用率等)和业务状态 (话务量等)进行调度, 自动部署模块也是在虚拟计 算资源上进行业务部署。
实施中, 还可以进一步包括: 业务调度模块接收各服务器经资源管理 模块上报的业务状态信息, 所述业务状态是各服务器以计算单元为单位统 计的业务状态。
基于同一发明构思, 本发明实施例中还提供了一种综合业务平台系统、 一种业务调度设备、 一种综合业务平台系统中的服务器、 一种综合业务平 台系统中的资源管理设备, 由于这些设备解决问题的原理与业务调度方法 相似, 因此这些设备的实施可以参见方法的实施, 重复之处不再赘述。
图 4为综合业务平台系统结构示意图, 如图 4所示, 综合业务平台系 统可以包括:
服务器 401 ,设置为向资源管理模块上报本服务器所具备的计算单元数 量, 服务器的计算处理能力由一个或多个计算单元构成;
资源管理模块 402,设置为将服务器上报的计算单元数量上报业务调度 模块;
业务调度模块 403 ,设置为根据计算单元数量及业务状态按调度算法以 计算单元为单位确定需要增加或释放的计算单元, 以及需要执行的业务; 并指示资源管理模块需要增加或释放的计算单元, 以及指示自动部署模块 需要执行的业务;
资源管理模块 402,设置为根据业务调度模块的指示增加或释放的计算 单元;
自动部署模块 404,设置为根据业务调度模块的指示分配各服务器执行 的业务。
实施中, 服务器还可以进一步设置为向资源管理模块上报本服务器的 业务状态信息, 所述业务状态是各服务器以计算单元为单位统计的业务状 态;
资源管理模块还可以进一步设置为将服务器上报的业务状态信息上报 业务调度模块。
图 5为综合业务平台系统中的服务器结构示意图, 如图 6所示, 所述 服务器可以包括:
资源确定模块 501 ,设置为确定本服务器所具备的计算单元数量,服务 器的计算处理能力由一个或多个计算单元构成;
上报模块 502,设置为向资源管理模块上报本服务器所具备的计算单元 数量。
实施中, 所述服务器还可以进一步包括: 业务确定模块 503 , 设置为确 定本服务器的业务状态信息, 所述业务状态是各服务器以计算单元为单位 统计的业务状态; 所述上报模块 502还可以进一步设置为向资源管理模块 上报本服务器的业务状态信息。
图 6为业务调度设备结构示意图, 如图 6所示, 所述业务调度设备可 以包括:
接收模块 601 ,设置为接收各服务器经资源管理模块上报的各服务器所 具备的计算单元数量, 每一服务器的计算处理能力由一个或多个计算单元 构成;
调度模块 602,设置为根据计算单元数量及业务状态按调度算法以计算 单元为单位确定需要增加或释放的计算单元, 以及需要执行的业务;
资源指示模块 603 ,设置为指示资源管理模块需要增加或释放的计算单 元;
业务指示模块 604, 设置为指示自动部署模块需要执行的业务。
实施中, 接收模块 601还可以进一步设置为接收各服务器经资源管理 模块上报的业务状态信息, 所述业务状态是各服务器以计算单元为单位统 计的业务状态。
图 7为综合业务平台系统中的资源管理设备结构示意图, 如图 7所示, 所述资源管理设备可以包括:
接收模块 701 , 设置为接收业务调度模块增加或释放的计算单元的指 示, 每一服务器的计算处理能力由一个或多个计算单元构成;
执行模块 702, 设置为根据业务调度模块的指示增加或释放的计算单 元。
实施中, 所述资源管理设备还可以进一步包括: 转发模块 803 , 设置为 将各服务器上报的各服务器所具备的计算单元数量和 /或业务状态信息转发 给业务调度模块。
为了描述的方便, 以上所述装置的各部分以功能分为各种模块或单元 分别描述。 当然, 在实施本发明时可以把各模块或单元的功能在同一个或 多个软件或硬件中实现。
为了更好的理解本发明的实施, 下面以实例进行说明。 图 8 为业务调度实施流程示意图, 首先, 虚拟化模块按预定的策略, 将服务器全部或部分的虚拟化成计算单元, 在此基础上, 则如图 8所示, 业务调度的流程可以如下:
步驟 801、 部署了业务的服务器 /计算单元定期上报资源状态和业务状 态给资源管理模块。 如果是空闲的服务器 /计算单元, 则只上报资源状态。
步驟 802、 资源管理模块进一步上报上述信息给业务调度模块。
步驟 803、业务调度模块根据获取的信息和预先定义好的算法,计算出 需要增加 /减少的资源。
步驟 804、 业务调度模块根据计算结果向资源管理模块申请 /释放资源。 申请成功以后, 进行下一步。
步驟 805、 业务调度模块下达部署 /卸载业务模块指令给自动部署模块。 步驟 806、 自动部署模块执行上述指令。
步驟 807、 自动部署模块把执行结果告知业务调度模块。
步驟 808、 在部署 /卸载成功的情况下, 业务调度模块通知业务分流模 块当前业务模块的部署变化情况, 以便于业务分类设备调整业务分流的策 略。
上述实施例中, 业务模块为处理一种或多种业务的模块, 一般, 一种 业务对应一个业务模块。
具体实施中, 实际调度流程中还可以包含异常流程处理等其它步驟。 由上述实施例可见, 在本发明实施例提供的技术方案中, 通过增加虚 拟化模块把服务器虚拟化为计算单元, 从而降低可调度资源的粒度;
同时在资源管理模块增加和虚拟机之间的接口, 从而可以管理虚拟计 算单元。 当然, 具体实施中资源管理模块还继续保留原先的管理服务器资 源的功能, 从而使得调度对象既可以是服务器, 也可以是虚拟化以后的计 算单元; 业务调度模块定期根据虚拟计算单元或者服务器的资源状态 ( CPU、 内存占用率等)和业务状态 (话务量等)进行调度, 自动部署模块既可以 在虚拟计算资源上进行业务部署, 也可以在服务器上进行业务部署。
该方案和原方案相比, 明显提高了设备利用率。 例如, 某几个业务系 统所需处理能力仅分别为 300TPS、 400TPS、 600TPS和 700TPS , 而单台服 务器的处理能力可达 3000TPS, 在调度粒度只能为服务器的情况下, 部署 这几个业务需要 4台服务器, 而采用本方案, 则仅需一台服务器即可。
此外, 和单纯的虚拟机方案相比, 本方案提供了根据业务能力进行调 度的功能。 单纯的虚拟机只能根据 CPU, 内存占有率等服务器资源来进行 资源分配, 无法根据业务量来进行调度。 因此, 本方案巧妙的结合了调度 功能和虚拟机技术, 提供了更灵活的调度粒度, 很好的解决了设备利用率 不高的问题。
本领域内的技术人员应明白, 本发明的实施例可提供为方法、 系统、 或计算机程序产品。 因此, 本发明可采用完全硬件实施例、 完全软件实施 例、 或结合软件和硬件方面的实施例的形式。 而且, 本发明可采用在一个 或多个其中包含有计算机可用程序代码的计算机可用存储介质 (包括但不 限于磁盘存储器、 CD-ROM、 光学存储器等) 上实施的计算机程序产品的 形式。
本发明是参照根据本发明实施例的方法、 设备(系统)、 和计算机程序 产品的流程图和 /或方框图来描述的。 应理解可由计算机程序指令实现流 程图和 /或方框图中的每一流程和 /或方框、 以及流程图和 /或方框图中 的流程和 /或方框的结合。 可提供这些计算机程序指令到通用计算机、 专 用计算机、 嵌入式处理机或其他可编程数据处理设备的处理器以产生一个 机器, 使得通过计算机或其他可编程数据处理设备的处理器执行的指令产 生设置为实现在流程图一个流程或多个流程和 /或方框图一个方框或多个 方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理 设备以特定方式工作的计算机可读存储器中, 使得存储在该计算机可读存 储器中的指令产生包括指令装置的制造品, 该指令装置实现在流程图一个 流程或多个流程和 /或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备 上, 使得在计算机或其他可编程设备上执行一系列操作步驟以产生计算机 实现的处理, 从而在计算机或其他可编程设备上执行的指令提供设置为实 现在流程图一个流程或多个流程和 /或方框图一个方框或多个方框中指定 的功能的步驟。
尽管已描述了本发明的优选实施例, 但本领域内的技术人员一旦得知 了基本创造性概念, 则可对这些实施例作出另外的变更和修改。 所以, 所 附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和 修改。
显然, 本领域的技术人员可以对本发明进行各种改动和变型而不脱离 本发明的精神和范围。 这样, 倘若本发明的这些修改和变型属于本发明权 利要求及其等同技术的范围之内, 则本发明也意图包含这些改动和变型在 内。

Claims

权利要求书
1、 一种业务调度方法, 其中, 所述方法包括:
业务调度模块接收各服务器经资源管理模块上报的各服务器所具备的 计算单元数量, 每一服务器的计算处理能力由一个或多个计算单元构成; 业务调度模块根据计算单元数量及业务状态, 按调度算法以计算单元 为单位确定需要增加或释放的计算单元、 以及需要执行的业务;
业务调度模块指示资源管理模块需要增加或释放的计算单元; 业务调度模块指示自动部署模块需要执行的业务。
2、 如权利要求 1所述的方法, 其中, 所述方法进一步包括:
业务调度模块接收各服务器经资源管理模块上报的业务状态信息, 所 述业务状态是各服务器以计算单元为单位统计的业务状态。
3、 一种业务调度设备, 其中, 所述设备包括:
接收模块, 设置为接收各服务器经资源管理模块上报的各服务器所具 备的计算单元数量, 每一服务器的计算处理能力由一个或多个计算单元构 成;
调度模块, 设置为根据计算单元数量及业务状态, 按调度算法以计算 单元为单位确定需要增加或释放的计算单元、 以及需要执行的业务;
资源指示模块, 设置为指示资源管理模块需要增加或释放的计算单元; 业务指示模块, 设置为指示自动部署模块需要执行的业务。
4、 如权利要求 3所述的业务调度设备, 其中, 所述接收模块进一步设 置为接收各服务器经资源管理模块上报的业务状态信息, 所述业务状态是 各服务器以计算单元为单位统计的业务状态。
5、 一种综合业务平台系统, 其中, 所述系统包括:
服务器, 设置为向资源管理模块上报本服务器所具备的计算单元数量 , 服务器的计算处理能力由一个或多个计算单元构成; 资源管理模块, 设置为将服务器上报的计算单元数量上报业务调度模 块;
业务调度模块, 设置为根据计算单元数量及业务状态, 按调度算法以 计算单元为单位确定需要增加或释放的计算单元、 以及需要执行的业务; 并指示资源管理模块需要增加或释放的计算单元, 以及指示自动部署模块 需要执行的业务;
资源管理模块, 设置为根据业务调度模块的指示增加或释放的计算单 元;
自动部署模块, 设置为根据业务调度模块的指示分配各服务器执行的 业务。
6、 如权利要求 5所述的系统, 其中, 所述服务器进一步设置为向资源 管理模块上报本服务器的业务状态信息, 所述业务状态是各服务器以计算 单元为单位统计的业务状态;
所述资源管理模块进一步设置为将服务器上报的业务状态信息上报业 务调度模块。
7、 一种综合业务平台系统中的服务器, 其中, 所述服务器包括: 资源确定模块, 设置为确定本服务器所具备的计算单元数量, 服务器 的计算处理能力由一个或多个计算单元构成;
上报模块, 设置为向资源管理模块上报本服务器所具备的计算单元数 量。
8、 如权利要求 5所述的服务器, 其中, 所述服务器进一步包括: 业务确定模块, 设置为确定本服务器的业务状态信息, 所述业务状态 是各服务器以计算单元为单位统计的业务状态;
所述上报模块进一步设置为向所述资源管理模块上报本服务器的业务 状态信息。
9、 一种综合业务平台系统中的资源管理设备, 其中, 所述设备包括: 接收模块, 设置为接收业务调度模块增加或释放的计算单元的指示, 每一服务器的计算处理能力由一个或多个计算单元构成;
执行模块, 设置为根据业务调度模块的指示增加或释放的计算单元。
10、 如权利要求 9所述的资源管理设备, 其中, 所述设备进一步包括: 转发模块, 设置为将各服务器上报的各服务器所具备的计算单元数量和 /或 业务状态信息转发给业务调度模块。
PCT/CN2011/079773 2011-01-24 2011-09-16 一种业务调度方法、系统及设备 WO2012100545A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201110025606.7 2011-01-24
CN2011100256067A CN102088719A (zh) 2011-01-24 2011-01-24 一种业务调度方法、系统及设备

Publications (1)

Publication Number Publication Date
WO2012100545A1 true WO2012100545A1 (zh) 2012-08-02

Family

ID=44100275

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2011/079773 WO2012100545A1 (zh) 2011-01-24 2011-09-16 一种业务调度方法、系统及设备

Country Status (2)

Country Link
CN (1) CN102088719A (zh)
WO (1) WO2012100545A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019006907A1 (en) * 2017-07-06 2019-01-10 Huawei Technologies Co., Ltd. SYSTEMS AND METHODS FOR ASSIGNING COMPUTER RESOURCES IN A DISTRIBUTED COMPUTER SYSTEM

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102088719A (zh) * 2011-01-24 2011-06-08 中兴通讯股份有限公司 一种业务调度方法、系统及设备
CN103491115A (zh) * 2012-06-12 2014-01-01 华为软件技术有限公司 资源调度方法、装置及系统
CN104426953A (zh) * 2013-08-28 2015-03-18 腾讯科技(深圳)有限公司 一种分配计算资源的方法及装置
CN107026802B (zh) * 2016-01-30 2020-12-15 华为技术有限公司 一种资源管理方法及设备
CN106358245B (zh) * 2016-11-07 2019-12-27 北京佰才邦技术有限公司 移动边缘计算应用负荷分担的方法和控制器
CN109992410B (zh) * 2018-11-28 2022-02-11 北京奥星贝斯科技有限公司 一种资源调度方法及系统、一种计算设备及存储介质
CN117194047B (zh) * 2023-04-13 2024-04-09 山东华科信息技术有限公司 基于数据协同的分布式系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004252812A (ja) * 2003-02-21 2004-09-09 Mitsubishi Electric Information Systems Corp 情報センタサーバシステム
CN101710301A (zh) * 2009-10-20 2010-05-19 中国电信股份有限公司 评估crm系统物理服务器虚拟化能力的方法及系统
CN101834851A (zh) * 2010-03-30 2010-09-15 中兴通讯股份有限公司 一种多媒体消息中心及调节其处理能力的方法
CN102088719A (zh) * 2011-01-24 2011-06-08 中兴通讯股份有限公司 一种业务调度方法、系统及设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004252812A (ja) * 2003-02-21 2004-09-09 Mitsubishi Electric Information Systems Corp 情報センタサーバシステム
CN101710301A (zh) * 2009-10-20 2010-05-19 中国电信股份有限公司 评估crm系统物理服务器虚拟化能力的方法及系统
CN101834851A (zh) * 2010-03-30 2010-09-15 中兴通讯股份有限公司 一种多媒体消息中心及调节其处理能力的方法
CN102088719A (zh) * 2011-01-24 2011-06-08 中兴通讯股份有限公司 一种业务调度方法、系统及设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019006907A1 (en) * 2017-07-06 2019-01-10 Huawei Technologies Co., Ltd. SYSTEMS AND METHODS FOR ASSIGNING COMPUTER RESOURCES IN A DISTRIBUTED COMPUTER SYSTEM
US10686728B2 (en) 2017-07-06 2020-06-16 Huawei Technologies Co., Ltd. Systems and methods for allocating computing resources in distributed computing

Also Published As

Publication number Publication date
CN102088719A (zh) 2011-06-08

Similar Documents

Publication Publication Date Title
WO2012100545A1 (zh) 一种业务调度方法、系统及设备
US11226846B2 (en) Systems and methods of host-aware resource management involving cluster-based resource pools
US10810052B2 (en) Methods and systems to proactively manage usage of computational resources of a distributed computing system
US11204811B2 (en) Methods and systems for estimating time remaining and right sizing usable capacities of resources of a distributed computing system
AU2011289734B2 (en) Methods and systems for platform optimized design
US10776166B2 (en) Methods and systems to proactively manage usage of computational resources of a distributed computing system
CN103793278B (zh) 一种基于虚拟器件运维规则的资源自动调整方法
US20210027401A1 (en) Processes and systems that determine sustainability of a virtual infrastructure of a distributed computing system
WO2016090181A1 (en) Vertical scaling of computing instances
US11080093B2 (en) Methods and systems to reclaim capacity of unused resources of a distributed computing system
CN102819465A (zh) 一种虚拟化环境中故障恢复的方法
CN110677274A (zh) 一种基于事件的云网络服务调度方法及装置
US10296411B1 (en) Endpoint call backoff in a computing service environment
CN102929769A (zh) 一种基于代理服务的虚拟机内部数据采集方法
US20230004414A1 (en) Automated instantiation and management of mobile networks
CN110727508A (zh) 一种任务调度系统和调度方法
Ferdaus et al. Multi-objective, decentralized dynamic virtual machine consolidation using aco metaheuristic in computing clouds
CN105302641A (zh) 虚拟化集群中进行节点调度的方法及装置
WO2021262332A1 (en) Rightsizing virtual machine deployments in a cloud computing environment
Pei et al. Asyfunc: A high-performance and resource-efficient serverless inference system via asymmetric functions
US9934268B2 (en) Providing consistent tenant experiences for multi-tenant databases
CN110868330B (zh) 云平台可划分cpu资源的评估方法、装置及评估系统
US20150373078A1 (en) On-demand helper operator for a streaming application
WO2019161172A1 (en) Systems and methods for improved management of virtual machine clusters
CN103562852B (zh) 一种保障云应用程序服务质量的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11856832

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 11856832

Country of ref document: EP

Kind code of ref document: A1