WO2018072708A1 - 一种云平台业务的缩容方法、装置及云平台 - Google Patents

一种云平台业务的缩容方法、装置及云平台 Download PDF

Info

Publication number
WO2018072708A1
WO2018072708A1 PCT/CN2017/106686 CN2017106686W WO2018072708A1 WO 2018072708 A1 WO2018072708 A1 WO 2018072708A1 CN 2017106686 W CN2017106686 W CN 2017106686W WO 2018072708 A1 WO2018072708 A1 WO 2018072708A1
Authority
WO
WIPO (PCT)
Prior art keywords
service
virtual machine
cloud platform
reduced
service system
Prior art date
Application number
PCT/CN2017/106686
Other languages
English (en)
French (fr)
Inventor
邓堪全
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 WO2018072708A1 publication Critical patent/WO2018072708A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/45562—Creating, deleting, cloning virtual machine instances
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/509—Offload

Definitions

  • the present disclosure relates to the field of cloud computing technologies, and in particular, to a method, an apparatus, a cloud platform, and a computer storage medium thereof.
  • Cloud computing is a computing model that distributes computing tasks across resource pools of large numbers of computers, enabling various business systems to acquire computing power, storage space, and information services as needed.
  • the basic characteristics of cloud computing are the use of resources on demand, the dynamic expansion of resources, the application of elastic computing, and the provision of service development to users through the network.
  • a cloud computing resource pool As a basic capability provider of cloud computing, a cloud computing resource pool, referred to as a cloud platform, is generally referred to as an IaaS (Infrastructure as a Service) platform, and multiple types of virtual resources are deployed in the resource pool. External customers choose to use.
  • the PaaS (Platform as a Service) layer can be deployed on the IaaS layer
  • the Software as a Service (SaaS) layer can be deployed on the PaaS layer.
  • SaaS can also be directly deployed.
  • PaaS is a platform on which software runs, such as databases, web containers, and so on. SaaS is a wide variety of business software, such as web portals, SMS bulkers, and more.
  • SaaS and PaaS are upper layers relative to IaaS.
  • the above two deployment relationships of IaaS, PaaS, and SaaS are shown in Figures 1(a) and (b). Because the PaaS and SaaS layers need to rely on IaaS operation, when the IaaS is expanded or reduced, the PaaS and SaaS layers need to be scaled accordingly to achieve balanced load balancing.
  • the existing cloud computing elastic scaling service includes two modules: a scaling decision module and a virtual machine management module.
  • the scaling decision module is generally used to dynamically adjust the load according to the load, and decide whether to expand or reduce the virtual machine in the scaling group.
  • the decision is sent to the virtual machine management module to notify the virtual machine management module to expand or reduce the capacity of the virtual machine.
  • the virtual machine management module is responsible for specifically creating and deleting virtual machines, and powering on and off the virtual machine.
  • the technical problem to be solved by the embodiments of the present invention is to provide a method and device for shrinking a cloud platform service, a cloud platform, and a computer storage medium thereof, which do not affect the security and stability of the entire service system when the virtual machine is deleted due to the shrinkage. Service capacity.
  • the cloud platform service shrinks the method and runs the service on the cloud platform.
  • System comprising:
  • the service being executed on the virtual machine to be contracted is transferred to another virtual machine in the service system, and the virtual machine to be indented is deleted.
  • the method further includes: before selecting a virtual machine to be reduced from the service system, detecting whether a performance indicator of the service on the cloud platform is lower than a first indicator threshold;
  • the performance indicators of the service include: an average value of traffic on each virtual machine.
  • selecting a virtual machine to be reduced from the business system includes:
  • a virtual machine is randomly selected from the service system as the virtual machine to be reduced.
  • the method further includes: running the virtual machine to be indented before transferring the service being executed on the virtual machine to be compacted to other virtual machines in the service system
  • the service query asks whether the virtual machine to be reduced is allowed to be deleted, and if so, the service being executed on the virtual machine to be reduced is transferred to other virtual machines in the service system.
  • the service being executed on the virtual machine to be reduced is transferred to other virtual machines in the service system, including:
  • transferring the service service instance data on the virtual machine to be reduced to other virtual machines in the service system includes:
  • the service service instance data includes: logical state information of a call, state control information of a call, and correspondence information of a call and an interface node; Performance metrics for the business, including: the average number of calls on each virtual machine;
  • the service service instance data includes: data information of the download request, download task completion degree information, download link information, and each download task respectively with the management node and the interface node. Mapping relationship information; performance indicators of the service, including: the number of download links on each virtual machine or the average of the network speed or traffic.
  • the embodiment of the present invention further provides a device for shrinking a cloud platform service, which is installed in a cloud platform, and runs a service system on the cloud platform, where the device includes:
  • a volume reduction module configured to transfer the service being executed on the virtual machine to be contracted to another virtual machine in the service system, and delete the virtual machine to be indented.
  • the apparatus further includes:
  • a determining module configured to: before the selecting the module selects a virtual machine to be reduced from the service system, whether the performance indicator of the service on the cloud platform is lower than the first indicator threshold; and when the performance indicator of the service is lower than the first When an indicator threshold is used, the virtual machine to be reduced is selected from the service system;
  • the performance indicators of the service include: an average value of traffic on each virtual machine.
  • the selection module is for:
  • a virtual machine is randomly selected from the service system as the virtual machine to be reduced.
  • the volume reduction module is further configured to: before the transfer of the service being executed on the virtual machine to be compacted to other virtual machines in the service system, to the to-be-reduced
  • the service running by the virtual machine asks whether the virtual machine to be retracted is allowed to be deleted, and if so, the service being executed on the virtual machine to be contracted is transferred to other virtual machines in the service system.
  • the volume reduction module is used to:
  • the volume reduction module is specifically configured to:
  • the service service instance data includes: logical state information of a call, state control information of a call, and correspondence information of a call and an interface node; Performance metrics for the business, including: the average number of calls on each virtual machine;
  • the service service instance data includes: data information of the download request, download task completion degree information, download link information, and each download task respectively with the management node and the interface node. Mapping relationship information; performance indicators of the service, including: the number of download links on each virtual machine or the average of the network speed or traffic.
  • An embodiment of the present invention further provides a cloud platform, where the cloud platform includes a main control unit, where the main control unit includes a processor and a memory storing the processor executable instructions, when the instructions are executed by the processor , do the following:
  • the service being executed on the virtual machine to be contracted is transferred to another virtual machine in the service system, and the virtual machine to be indented is deleted.
  • the operations performed by the processor specifically include:
  • the operations performed by the processor specifically include:
  • An embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores one or more programs executable by a computer, and when the one or more programs are executed by the computer, causing the computer to execute the foregoing The shrinking method of the cloud platform business.
  • the technical solution provided by the embodiment of the present invention has at least the following advantages:
  • the method, device, and cloud platform of the cloud platform service of the present invention when shrinking the service of the cloud platform, first perform some shrinkage preprocessing on the cloud platform service, including whether the application service deployed on the virtual machine is allowed to stop. , the ongoing transfer of business service instance data, etc., in order to achieve stable and secure release of virtual machine resources, improve resource utilization At the same time, ensuring that the virtual machine is down does not affect the security and stability of the entire service system, that is, effectively implementing the security and stability of the cloud platform business.
  • Figure 1 (a), (b) is a schematic diagram of two deployment relationships of IaaS, PaaS, and SaaS;
  • FIG. 2 is a flowchart of a method for shrinking a cloud platform service according to a first embodiment of the present invention
  • FIG. 3 is a flowchart of a method for shrinking a cloud platform service according to a second embodiment of the present invention.
  • FIG. 5 is a flowchart of step A2 of the third embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a component of a volume reduction device of a cloud platform service according to fourth and fifth embodiments of the present invention.
  • FIG. 7 is a schematic diagram of a service system framework diagram of a cloud platform according to an eighth embodiment of the present invention.
  • FIG. 8 is a flowchart of collecting performance indicators of a service according to an eighth embodiment of the present invention.
  • FIG. 9 is a flowchart of a shrinking operation of a service according to an eighth embodiment of the present invention.
  • FIG. 10 is a timing diagram of call switching transition of a SCP to be reduced in accordance with an eighth embodiment of the present invention.
  • a first embodiment of the present invention is a method for shrinking a cloud platform service, which runs a service system on a cloud platform. As shown in FIG. 2, the method includes the following specific steps:
  • step S201 it is determined whether the performance indicator of the service on the cloud platform is lower than the first indicator threshold.
  • the performance indicator of the service is lower than the first indicator threshold, the virtual machine to be reduced is selected from the service system.
  • the performance indicators of the service include: an average value of traffic on each virtual machine.
  • Step S202 Select a virtual machine to be reduced from the service system.
  • step S202 includes:
  • a virtual machine is randomly selected from the service system as the virtual machine to be reduced.
  • step S203 the service being executed on the virtual machine to be contracted is transferred to another virtual machine in the service system, and the virtual machine to be reduced is deleted.
  • the cloud platform when the discovery service is in a low load operation in the service system, the cloud platform performs a shrink operation on the service system, so that the service system is processed by the cloud platform under the control of the cloud platform, and the virtual machine is stable and secure. Release resources to improve resource utilization.
  • a second embodiment of the present invention is a method for shrinking a cloud platform service, which runs a service system on a cloud platform. As shown in FIG. 3, the method includes the following specific steps:
  • step S301 it is detected whether the performance indicator of the service on the cloud platform is lower than the first indicator threshold.
  • the performance indicator of the service is lower than the first indicator threshold, the virtual machine to be reduced is selected from the service system.
  • the performance indicators of the service include: an average value of traffic on each virtual machine.
  • Step S302 selecting a virtual machine to be reduced from the business system.
  • step S302 includes:
  • a virtual machine is randomly selected from the service system as the virtual machine to be reduced.
  • step S303 the service running to the virtual machine to be reduced is asked whether the virtual machine to be reduced is allowed to be deleted, and if yes, step S303 is performed.
  • step S304 the service being executed on the virtual machine to be contracted is transferred to another virtual machine in the service system, and the virtual machine to be reduced is deleted.
  • the difference between the embodiment of the present invention and the first embodiment is that, after the virtual machine to be reduced is selected in the embodiment, the service is also required to ask whether the virtual machine that is allowed to run the service is deleted, and the service is allowed. In this case, the capacity is reduced, and some services are not allowed to allow the virtual machine to be deleted.
  • a third embodiment of the present invention is a method for shrinking a cloud platform service.
  • the method in this embodiment is substantially the same as the first embodiment or the second embodiment. The difference is that the method in this embodiment introduces a method in detail. The method is used to implement the process of transferring the service in step S203 or step S304.
  • the service being executed on the virtual machine to be compacted is transferred to other virtual machines in the service system, including:
  • Step A1 Notifying the management node to stop managing the virtual machine to be reduced, notifying the interface node to stop the distribution of the service request for the virtual machine to be reduced; and deactivating the service being executed on the virtual machine to be stopped to stop receiving A new business service request for the business.
  • Step A2 Transfer the service service instance data in the memory of the virtual machine to be reduced to other virtual machines in the service system.
  • step A2 includes:
  • A21 serializing and encoding the service service instance data in the virtual machine memory to be reduced to obtain a sequence code, and saving the sequence code to a database of the service system;
  • A22 selecting, in the service system, a virtual machine with the lowest traffic load as the target virtual machine among the other virtual machines except the virtual machine to be reduced;
  • A23 The target virtual machine is notified to obtain the sequence code from the database, and the sequence code is decoded and restored to the memory of the target virtual machine.
  • Step A3 After the transfer succeeds, the service on the virtual machine to be reduced is stopped.
  • the services in the cloud platform are classified into two categories: call service and data download service.
  • the service service instance data includes: logical state information of the call, state control information of the call, and correspondence information of the call and the interface node.
  • the correspondence information between the call and the interface node refers to the correspondence relationship between the call and the SIU (Signaling Interface Unit), and the correspondence relationship between the call and the IMP (Interface Machine).
  • the call service is mainly implemented by the application node-SCP (Service Control Point) in the service system based on the cloud platform.
  • the management node is notified to the SMP (Service Management Point). Stop the management of the virtual machine to be shrinked, and notify the interface node that the SIU stops distributing the service request for the virtual machine to be compressed.
  • the performance indicators of the service include: an average of the number of calls on each virtual machine.
  • the service service instance data includes: data information of the download request, download task completion degree information, download link information, and each download task respectively with the management node and the interface node. Mapping relationship information.
  • the client connects to each server in the business system of the cloud platform through a switch, and each server can serve as an application node, wherein the application server: provides a data access application service to the client; and the data server: is responsible for the data flow. Codec, cache, and forwarding processing; central control management server: responsible for the operation and scheduling management of the entire data transmission system.
  • the switch can be used as an interface node, and the data downloading service is mainly implemented by an application node in the cloud platform-based business system—application server and data server.
  • the notification management node the central control management server stops processing
  • the virtual machine is managed to notify the interface node that the switch stops distributing the service request for the virtual machine to be reduced.
  • the performance indicators of the service include: the number of download links on each virtual machine or the average of the network speed or traffic.
  • the fourth embodiment of the present invention corresponds to the first embodiment.
  • the embodiment introduces a device for shrinking a cloud platform service, which is installed in a cloud platform, and runs a service system on the cloud platform, as shown in FIG.
  • the device comprises the following components:
  • the determining module 601 is configured to: before the selecting the module selects the virtual machine to be reduced from the service system, whether the performance indicator of the service on the cloud platform is lower than the first indicator threshold; and when the performance indicator of the service is When the threshold is lower than the first indicator, the virtual machine to be reduced is selected from the service system;
  • the performance indicators of the service include: an average value of traffic on each virtual machine.
  • a selection module 602 configured to select a virtual machine to be reduced from the service system
  • the selection module 602 is configured to:
  • a virtual machine is randomly selected from the service system as the virtual machine to be reduced.
  • the shrinking module 603 is configured to transfer the service being executed on the virtual machine to be contracted to other virtual machines in the service system, and delete the virtual machine to be reduced.
  • the cloud platform when the discovery service is in a low load operation in the service system, the cloud platform performs a shrink operation on the service system, so that the service system is processed by the cloud platform under the control of the cloud platform, and the virtual machine is stable and secure. Release resources to improve resource utilization.
  • the fifth embodiment of the present invention corresponds to the second embodiment, and the embodiment introduces a device for shrinking the cloud platform service.
  • the device includes the following components:
  • the determining module 601 is configured to: before the selecting the module selects the virtual machine to be reduced from the service system, whether the performance indicator of the service on the cloud platform is lower than the first indicator threshold; and when the performance indicator of the service is When the threshold is lower than the first indicator, the virtual machine to be reduced is selected from the service system;
  • the performance indicators of the service include: an average value of traffic on each virtual machine.
  • a selection module 602 configured to select a virtual machine to be reduced from the service system
  • the selection module 602 is configured to:
  • a virtual machine is randomly selected from the service system as the virtual machine to be reduced.
  • a shrinking module 603 configured to query, for the service running on the virtual machine to be retracted, whether to delete the virtual machine to be retracted, and if yes, execute the virtual machine to be indented The service is transferred to other virtual machines in the service system, and the virtual machine to be indented is deleted.
  • the difference between the embodiment of the present invention and the first embodiment is that, after the virtual machine to be reduced is selected in the embodiment, the service is also required to ask whether the virtual machine that is allowed to run the service is deleted, and the service is allowed. In this case, the capacity is reduced, and some services are not allowed to allow the virtual machine to be deleted.
  • the sixth embodiment of the present invention is a device for shrinking a cloud platform service.
  • the device in this embodiment is substantially the same as the fourth embodiment or the fifth embodiment. The difference is that the device in this embodiment describes a device in detail.
  • the method is used to implement the process of transferring the service in the volume reduction module 603.
  • the reduction module 603 is configured to:
  • the volume reduction module 603 is configured to:
  • the services in the cloud platform are classified into two categories: call service and data download service.
  • the service service instance data includes: logical state information of the call, state control information of the call, and correspondence information of the call and the interface node.
  • the correspondence information between the call and the interface node refers to the correspondence relationship between the call and the SIU (Signaling Interface Unit), and the correspondence relationship between the call and the IMP (Interface Machine).
  • the call service is mainly implemented by an application node-SCP (Service Control Point) in the cloud-based service system, and the shrink-capture module 603 specifically informs the management node—SMP (Service Management Point) Stop managing the virtual machine that is shrinking, and notify the interface node that the SIU stops distributing the service request to the virtual machine that is shrinking.
  • the performance indicators of the service include: an average of the number of calls on each virtual machine.
  • the service service instance data includes: data information of the download request, download task completion degree information, download link information, and each download task respectively with the management node and the interface node. Mapping relationship information.
  • the client connects to each server in the business system of the cloud platform through a switch, and each server can serve as an application node, wherein the application server: provides a data access application service to the client; and the data server: is responsible for the data flow. Codec, cache, and forwarding processing; central control management server: responsible for the operation and scheduling management of the entire data transmission system.
  • the switch can be used as an interface node, and the data downloading service is mainly implemented by an application node in the cloud platform-based business system, an application server and a data server, and the shrinking module 603 specifically notifies the management node that the central control management server stops processing.
  • the virtual machine is managed to notify the interface node that the switch stops distributing the service request for the virtual machine to be reduced.
  • the performance indicators of the service include: the number of download links on each virtual machine or the average of the network speed or traffic.
  • a seventh embodiment of the present invention is a cloud platform that can be understood as a physical device.
  • the cloud platform includes a main control unit, and the main control unit includes a processor and a memory storing executable instructions of the processor. When the instruction is executed by the processor, the following operations are performed:
  • the service being executed on the virtual machine to be contracted is transferred to another virtual machine in the service system, and the virtual machine to be indented is deleted.
  • the operations performed by the processor specifically include:
  • the operations performed by the processor specifically include:
  • the virtual load with the lowest traffic load is selected.
  • the virtual machine is the target virtual machine;
  • the eighth embodiment of the present invention is based on the foregoing embodiment, and an application example of the present invention is described by taking a call service as an example and referring to FIGS. 7-10.
  • the IaaS layer functional entity is represented by the cloud platform
  • the "PaaS and SaaS layer” functional entity is represented by the service system
  • the SaaS layer functional entity is represented in the absence of the PaaS layer.
  • the subsequent description of the interworking between the cloud platform and the business system may be the interworking between the IaaS layer and the PaaS and SaaS layers, or may be only the interworking of the IaaS layer and the PaaS layer, or only the IaaS layer and the SaaS layer. Intercommunication does not affect the essence of the invention.
  • a business system of a cloud platform is a cloud platform master unit of the IaaS layer and a service system of the SaaS layer.
  • the cloud platform-based business system the intelligent network is composed of multiple virtual machines that deploy different call services, respectively: the signaling interface unit SIU responsible for accessing the basic call from the SS7 network; together with the deployment
  • the service control point SCP of the SLP and the state machine is responsible for the logical flow of the call service in the intelligent network, the relevant protocol codec and call state control;
  • the database SDP is deployed to store the service data;
  • the service management point SMP and the service management access point SMAP is responsible for providing device management and service management functions for the entire business system.
  • the cloud platform main control unit is responsible for the creation, deletion, and scheduling management functions of the underlying physical entity virtual machine, and mainly includes: a performance data acquisition module, a volume reduction decision and a preprocessing module, and a virtual machine management module, and the performance data acquisition module is responsible for periodically collecting the SCP. Performance data, monitoring the traffic load situation, when the load reaches a preset threshold, triggering the shrinking operation, and then the shrinkage decision and preprocessing module is responsible for completing the selection of the SCP to be reduced, and performing a series of pre-processing
  • the processing includes notifying the SIU and the SMP that the local device will go offline, switching the currently existing call to another SCP, and continuing to complete the session task.
  • the virtual machine management module VNFM completes the deletion of the physical virtual machine resource.
  • the performance data acquisition module, the reduction capacity decision-making and pre-processing module, and the virtual machine management module in this embodiment have the same functions as the determination module, the selection module, and the reduction module in the fourth to sixth embodiments, and the difference is only in the function. The difference in the way of division.
  • the performance index collection process performed by the performance data acquisition module of the cloud platform main control unit in the embodiment of the present invention is as follows:
  • Step 301 Send a message to each SCP application at a frequency of once every minute, obtain the number of calls of the current application, and save the obtained number of calls on each SCP.
  • Step 302 Calculate an average value of the number of calls on each SCP.
  • Step 303 The average value is compared with a preset threshold. If the threshold is lower than the preset threshold, it is determined that the volume is required to be reduced. If the threshold is not lower than the preset threshold, step 305 is performed.
  • Step 304 Trigger the shrinking operation.
  • Step 305 The collection ends, waiting for the next indicator data acquisition.
  • the shrinking operation process of the shrinkage decision module of the cloud platform main control unit in the embodiment of the present invention is as follows:
  • Step 401 The shrinking operation is started.
  • Step 402 Select the SCP with the smallest number of calls to be the virtual machine to be reduced. If the number of calls of the current SCP is the same, randomly select an SCP as the virtual machine to be reduced.
  • Step 403 Send a message to the application process of the virtual machine to be reduced, and confirm whether the device is allowed to be retracted. If the service application of the SCP is pre-configured to prohibit offline, the shrink operation returns to step 402 to re-select another from the scaling group. A virtual machine to be reduced; if allowed to be reduced, step 404 is performed.
  • Step 404 Pre-processing before shrinking.
  • the specific work is as follows: sending a message to the SIU not to distribute a new call to the SCP to be reduced, sending a message to the SMP to remove the management of the SCP, then deactivating all the services on the SCP to be reduced, and stopping accessing the new service request, and Transfer the call instance data currently being executed by the SCP to other SCP nodes of the scaling group, continue to complete the existing call task in a continuous manner, and then compress and package the files such as bills and FTP backups to the pre-configured server directory, and finally stop shrinking.
  • the SCP application is loaded, and according to the above work completion situation, the pre-contraction pre-processing result is returned to the shrinkage decision processing module.
  • the implementation details of the handover to transfer the call of the current SCP to other SCP nodes described in step 404 are as shown in FIG. 10, and the SLP and the state machine are deployed together in the SCP; the DCACHE deployed in the SDP is based on Key/Value's cloud storage engine provides distributed storage with high capacity, high performance and high reliability.
  • the specific process is as follows:
  • the shrinkage preprocessing module in the cloud platform main control unit notifies the SLP module in the contracted SCP to switch the call operation; then 2) the SLP module traverses all session links to find all current online call instances; 3) Notifying the state machine to switch the call instance; then 4) the SLP serializes the service logic state information (including the service support data SSD, the call instance data CID) of the call into a unique ID, and saves it to the DCACHE; and 5) the state machine puts the call State control information, and serialization code of each call and SIU, IMP correspondence table information, saved to DCACHE; then 8) response shrinkage preprocessing module, call state storage saved successfully; afterwards, 9) in other SCP
  • the SCP with the smallest traffic volume and the lowest load is selected to recover the transferred call; after that, 10-14) is the deserialization process, and the SLP and the state machine restore the call information stored in the DCACHE as it is.
  • Step 405 If the shrinkage preprocessing is successful, go to step 406; if the shrinkage preprocessing fails, go to step 407.
  • Step 406 Delete the virtual machine to be reduced from the cloud platform resource pool, and then perform step 408.
  • Step 407 Roll back the data modified by the previous pre-processing operation, restore the SCP to the previous state, and notify the SIU and the SMP to re-enable the SCP to be re-enabled, and then return to step 402 to select another one from the scaling group.
  • the virtual machine continues to try to perform the shrinking task.
  • Step 408 The operation ends.
  • the ninth embodiment of the present invention the flow of the cloud platform to the business system in the present embodiment is the first, second, and third Or the eight embodiments are the same, the difference is that, in engineering implementation, the embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is a better implementation.
  • the method of the present invention can be embodied in the form of a computer software product stored in a storage medium (such as a ROM/RAM, a magnetic disk, an optical disk), including a number of instructions for causing a
  • the device (which may be a cloud platform main control unit or the like) performs the method described in the embodiment of the present invention.
  • the technical solution provided by the embodiment of the present invention can be applied to the field of the cloud computing technology.
  • the network platform service is first pre-processed, including Whether the application service deployed on the virtual machine is allowed to stop, the ongoing transfer of the service service instance data, etc., to achieve stable and secure release of virtual machine resources, improve resource utilization, and ensure that the virtual machine does not crash when the virtual machine is down. It affects the security and stability of the entire service system, which effectively realizes the security and stability of the cloud platform business.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer And Data Communications (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种云平台业务的缩容方法、装置及云平台，在云平台上运行业务系统，该方法包括：从业务系统中选择待缩容的虚拟机（S202）；将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机（S203）。对云平台的业务进行缩容时，先对云平台业务做一些缩容预处理，包括虚拟机上部署的应用服务是否准许停止，正在进行的业务服务实例数据的切换转移等，以实现稳定安全的将虚拟机资源释放，提高资源利用率的同时，保证该虚拟机宕机时也不影响整个业务系统对外提供安全稳定的服务能力，即有效的实现了云平台业务的安全稳定的缩容弹性管理。

Description

一种云平台业务的缩容方法、装置及云平台 技术领域
本公开涉及云计算技术领域，尤其涉及一种云平台业务的缩容方法、装置、云平台及其计算机存储介质。
背景技术
云计算是一种计算模式，它将计算任务分布在大量计算机构成的资源池上，使各种业务系统能够根据需要获取计算力、存储空间和信息服务。云计算基本特征为按需使用资源、资源可以动态扩展、应用弹性计算、通过网络以服务方式提供给业务开发用户。
作为云计算的基础能力提供商，会建立云计算资源池，简称云平台，一般称为IaaS(Infrastructure as a Service，基础设施即服务)平台，在资源池中部署多种类型的虚拟资源，供外部客户选择使用。按照逻辑功能划分，在IaaS层上可以部署PaaS(Platform as a Service，平台即服务)层，PaaS层之上再部署SaaS(Software as a Service，软件即服务)层，也可以直接将SaaS部署在IaaS上。PaaS为软件运行的平台，如数据库、web容器等。SaaS为各式各样的业务软件，如web门户网站、短信群发器等。一般来说，SaaS和PaaS相对于IaaS是上层。IaaS、PaaS和SaaS的上述两种部署关系如图1(a)、(b)所示。由于PaaS和SaaS层需要依赖于IaaS运行，当IaaS进行扩容或缩容时，需要PaaS和SaaS层也进行相应的伸缩，以实现业务负载的均衡适配。
现有云计算弹性伸缩服务包含两个模块：伸缩决策模块和虚拟机管理模块，伸缩决策模块一般用于根据负载的动态调整，决策是否要扩容或减容伸缩组内的虚拟机，并将伸缩决策发送给虚拟机管理模块通知虚拟机管理模块扩容或减容虚拟机，虚拟机管理模块负责具体的创建、删除虚拟机，虚拟机上电、下电等操作。
现有技术中，在云平台的业务缩容方面，还没有较好的缩容策略，现在大多关注的是被缩容的物理虚拟机处理，而缺少对虚拟机上的业务做一些缩容前的预处理，以保护该虚拟机宕机不影响整个业务系统对外提供安全稳定的服务能力。比如智能网场景中，在停止待缩容虚拟机上业务系统软件之前，需要对正在进行的呼叫进行切换转移到其他虚拟机继续处理，避免用户当前通话服务被中断的影响。
发明内容
本发明实施例要解决的技术问题是，提供一种云平台业务的缩容方法、装置、云平台及其计算机存储介质，在因缩容而删除虚拟机时不影响整个业务系统对外提供安全稳定的服务能力。
本发明实施例采用的技术方案是，所述云平台业务的缩容方法，在云平台上运行业务 系统，所述方法包括：
从业务系统中选择待缩容的虚拟机；
将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
根据一个示例性实施例，所述方法还包括：在从业务系统中选择待缩容的虚拟机之前，检测云平台上的业务的性能指标是否低于第一指标阈值；
当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机；
所述业务的性能指标，包括：各虚拟机上业务量的平均值。
根据一个示例性实施例，从业务系统中选择待缩容的虚拟机，包括：
从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
根据一个示例性实施例，所述方法还包括：在将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上之前，向所述待缩容的虚拟机运行的业务询问是否允许删除所述待缩容的虚拟机，若是，则将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上。
根据一个示例性实施例，将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，包括：
通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
转移成功后，停止所述待缩容的虚拟机上的所述业务。
根据一个示例性实施例，将所述待缩容的虚拟机上的业务服务实例数据转移到业务系统中的其他虚拟机上，包括：
将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
根据一个示例性实施例，在所述业务为呼叫业务的情况下，所述业务服务实例数据包括：呼叫的逻辑状态信息、呼叫的状态控制信息、以及呼叫与接口节点的对应关系信息；所述业务的性能指标，包括：各虚拟机上的呼叫数量的平均值；
在所述业务为数据下载业务的情况下，所述业务服务实例数据包括：下载请求的数据信息、下载任务传输完成度信息、下载链路信息、以及各下载任务分别与管理节点和接口节点的映射关系信息；所述业务的性能指标，包括：各虚拟机上的下载链接数量或者网速或者流量的平均值。
本发明实施例还提供一种云平台业务的缩容装置，设置于云平台中，在所述云平台上运行业务系统，所述装置包括：
选择模块，用于从业务系统中选择待缩容的虚拟机；
缩容模块，用于将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
根据一个示例性实施例，所述装置还包括：
判断模块，用于在所述选择模块从业务系统中选择待缩容的虚拟机之前，检测云平台上的业务的性能指标是否低于第一指标阈值；当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机；
所述业务的性能指标，包括：各虚拟机上业务量的平均值。
根据一个示例性实施例，所述选择模块用于：
从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
根据一个示例性实施例，所述缩容模块还用于：在将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上之前，向所述待缩容的虚拟机运行的业务询问是否允许删除所述待缩容的虚拟机，若是，则将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上。
根据一个示例性实施例，所述缩容模块用于：
通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
转移成功后，停止所述待缩容的虚拟机上的所述业务。
根据一个示例性实施例，所述缩容模块具体用于：
将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目 标虚拟机的内存中。
根据一个示例性实施例，在所述业务为呼叫业务的情况下，所述业务服务实例数据包括：呼叫的逻辑状态信息、呼叫的状态控制信息、以及呼叫与接口节点的对应关系信息；所述业务的性能指标，包括：各虚拟机上的呼叫数量的平均值；
在所述业务为数据下载业务的情况下，所述业务服务实例数据包括：下载请求的数据信息、下载任务传输完成度信息、下载链路信息、以及各下载任务分别与管理节点和接口节点的映射关系信息；所述业务的性能指标，包括：各虚拟机上的下载链接数量或者网速或者流量的平均值。
本发明实施例还提供一种云平台，所述云平台包括主控单元，所述主控单元包括处理器以及存储有所述处理器可执行指令的存储器，当所述指令被处理器执行时，执行如下操作：
从业务系统中选择待缩容的虚拟机；
将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
根据一个示例性实施例，所述处理器执行的操作具体包括：
通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
转移成功后，停止所述待缩容的虚拟机上的所述业务。
根据一个示例性实施例，所述处理器执行的操作具体包括：
将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
本发明实施例还提供一种计算机存储介质，所述计算机存储介质中存储有计算机可执行的一个或多个程序，所述一个或多个程序被所述计算机执行时使所述计算机执行上述任意云平台业务的缩容方法。
采用上述技术方案，本发明实施例提供的技术方案至少具有下列优点：
本发明所述云平台业务的缩容方法、装置及云平台，对云平台的业务进行缩容时，先对云平台业务做一些缩容预处理，包括虚拟机上部署的应用服务是否准许停止，正在进行的业务服务实例数据的切换转移等，以实现稳定安全的将虚拟机资源释放，提高资源利用 率的同时，保证该虚拟机宕机时也不影响整个业务系统对外提供安全稳定的服务能力，即有效的实现了云平台业务的安全稳定的缩容弹性管理。
附图说明
图1(a)、(b)为IaaS、PaaS和SaaS的两种部署关系示意图；
图2为本发明第一实施例的云平台业务的缩容方法流程图；
图3为本发明第二实施例的云平台业务的缩容方法流程图；
图4为本发明第三实施例中的业务转移过程的具体流程图；
图5为本发明第三实施例的步骤A2的流程图；
图6为本发明第四、五实施例的云平台业务的缩容装置组成结构示意图；
图7为本发明第八实施例的云平台的业务系统框架图示意图；
图8为本发明第八实施例的业务的性能指标采集流程图；
图9为本发明第八实施例的业务的缩容操作流程图；
图10为本发明第八实施例的待缩容SCP的呼叫切换转移的时序图。
具体实施方式
为更进一步阐述本发明为达成预定目的所采取的技术手段及功效，以下结合附图及较佳实施例，对本发明进行详细说明如后。
本发明第一实施例，一种云平台业务的缩容方法，在云平台上运行业务系统，如图2所示，所述方法包括以下具体步骤：
步骤S201，检测云平台上的业务的性能指标是否低于第一指标阈值；当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机。
具体的，所述业务的性能指标，包括：各虚拟机上业务量的平均值。
步骤S202，从业务系统中选择待缩容的虚拟机。
具体的，步骤S202包括：
从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
步骤S203，将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
本发明实施例中，云平台在发现业务在业务系统中处于低负载运行时，对业务系统执行缩容操作，使业务系统在云平台的控制下经过步骤S203处理后，稳定安全的将虚拟机资源释放，提高资源利用率。
本发明第二实施例，一种云平台业务的缩容方法，在云平台上运行业务系统，如图3所示，所述方法包括以下具体步骤：
步骤S301，检测云平台上的业务的性能指标是否低于第一指标阈值；当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机。
具体的，所述业务的性能指标，包括：各虚拟机上业务量的平均值。
步骤S302，从业务系统中选择待缩容的虚拟机。
具体的，步骤S302包括：
从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
步骤S303，向所述待缩容的虚拟机运行的业务询问是否允许删除所述待缩容的虚拟机，若是，则将执行步骤S303。
步骤S304，将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
本发明实施例与第一实施例的区别在于，本实施例中在选定了待缩容的虚拟机之后，还需要向业务询问是否允许运行该业务的虚拟机被删除，在得到业务的允许的情况下才进行缩容，避免有些业务不允许虚拟机被删除的情况下的缩容处理导致业务无法接续的损失。
本发明第三实施例，一种云平台业务的缩容方法，本实施例所述方法与第一实施例或第二实施例大致相同，区别在于，本实施例的所述方法详细介绍一种方式，用以实现步骤S203或步骤S304中的转移业务的过程。
在本实施例中，如图4所示，将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，包括：
步骤A1：通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求。
步骤A2：将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上。
具体的，如图5所示，步骤A2包括：
A21：将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
A22：在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
A23：通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
步骤A3：转移成功后，停止所述待缩容的虚拟机上的所述业务。
根据一个示例性实施例，云平台中的业务分为呼叫业务和数据下载业务这两大类。
在所述业务为呼叫业务的情况下，所述业务服务实例数据包括：呼叫的逻辑状态信息、呼叫的状态控制信息、以及呼叫与接口节点的对应关系信息。该呼叫与接口节点的对应关系信息指的是呼叫与SIU(信令接口单元)的对应关系信息、以及呼叫与IMP(接口机)的对应关系信息。在呼叫业务的场景下，呼叫业务主要是通过基于云平台的业务系统中的应用节点—SCP(业务控制点)来实现的，在上述步骤A1中具体是，通知管理节点—SMP(业务管理点)停止对待缩容的虚拟机进行管理，通知接口节点—SIU停止对待缩容的虚拟机进行业务请求的分发。所述业务的性能指标，包括：各虚拟机上的呼叫数量的平均值。
在所述业务为数据下载业务的情况下，所述业务服务实例数据包括：下载请求的数据信息、下载任务传输完成度信息、下载链路信息、以及各下载任务分别与管理节点和接口节点的映射关系信息。由于数据下载业务的场景下，客户端通过交换机连接云平台的业务系统中的各服务器，各服务器可以作为应用节点，其中，应用服务器：给客户提供数据访问应用服务；数据服务器：负责数据流的编解码、缓存、转发处理；中心控制管理服务器：负责整个数据传输系统的运行调度管理。交换机可以作为接口节点，数据下载业务主要是通过基于云平台的业务系统中的应用节点—应用服务器和数据服务器来实现的，上述步骤A1中具体是，通知管理节点—中心控制管理服务器停止对待缩容的虚拟机进行管理，通知接口节点—交换机停止对待缩容的虚拟机进行业务请求的分发。所述业务的性能指标，包括：各虚拟机上的下载链接数量或者网速或者流量的平均值。
本发明第四实施例，与第一实施例对应，本实施例介绍一种云平台业务的缩容装置，设置于云平台中，在所述云平台上运行业务系统，如图6所示，所述装置包括以下组成部分：
1)判断模块601，用于在所述选择模块从业务系统中选择待缩容的虚拟机之前，检测云平台上的业务的性能指标是否低于第一指标阈值；当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机；
具体的，所述业务的性能指标，包括：各虚拟机上业务量的平均值。
2)选择模块602，用于从业务系统中选择待缩容的虚拟机；
具体的，选择模块602，用于：
从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
3)缩容模块603，用于将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
本发明实施例中，云平台在发现业务在业务系统中处于低负载运行时，对业务系统执行缩容操作，使业务系统在云平台的控制下经过步骤S203处理后，稳定安全的将虚拟机资源释放，提高资源利用率。
本发明第五实施例，与第二实施例对应，本实施例介绍一种云平台业务的缩容装置， 设置于云平台中，在所述云平台上运行业务系统，如图6所示，所述装置包括以下组成部分：
1)判断模块601，用于在所述选择模块从业务系统中选择待缩容的虚拟机之前，检测云平台上的业务的性能指标是否低于第一指标阈值；当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机；
具体的，所述业务的性能指标，包括：各虚拟机上业务量的平均值。
2)选择模块602，用于从业务系统中选择待缩容的虚拟机；
具体的，选择模块602，用于：
从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
3)缩容模块603，用于向所述待缩容的虚拟机运行的业务询问是否允许删除所述待缩容的虚拟机，若是，则将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
本发明实施例与第一实施例的区别在于，本实施例中在选定了待缩容的虚拟机之后，还需要向业务询问是否允许运行该业务的虚拟机被删除，在得到业务的允许的情况下才进行缩容，避免有些业务不允许虚拟机被删除的情况下的缩容处理导致业务无法接续的损失。
本发明第六实施例，一种云平台业务的缩容装置，本实施例所述装置与第四实施例或第五实施例大致相同，区别在于，本实施例的所述装置详细介绍一种方式，用以实现缩容模块603中的转移业务的过程。
在本实施例中，缩容模块603，用于：
通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
转移成功后，停止所述待缩容的虚拟机上的所述业务。
根据一个示例性实施例，缩容模块603用于：
将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
根据一个示例性实施例，云平台中的业务分为呼叫业务和数据下载业务这两大类。
在所述业务为呼叫业务的情况下，所述业务服务实例数据包括：呼叫的逻辑状态信息、呼叫的状态控制信息、以及呼叫与接口节点的对应关系信息。该呼叫与接口节点的对应关系信息指的是呼叫与SIU(信令接口单元)的对应关系信息、以及呼叫与IMP(接口机)的对应关系信息。在呼叫业务的场景下，呼叫业务主要是通过基于云平台的业务系统中的应用节点—SCP(业务控制点)来实现的，缩容模块603具体是，通知管理节点—SMP(业务管理点)停止对待缩容的虚拟机进行管理，通知接口节点—SIU停止对待缩容的虚拟机进行业务请求的分发。所述业务的性能指标，包括：各虚拟机上的呼叫数量的平均值。
在所述业务为数据下载业务的情况下，所述业务服务实例数据包括：下载请求的数据信息、下载任务传输完成度信息、下载链路信息、以及各下载任务分别与管理节点和接口节点的映射关系信息。由于数据下载业务的场景下，客户端通过交换机连接云平台的业务系统中的各服务器，各服务器可以作为应用节点，其中，应用服务器：给客户提供数据访问应用服务；数据服务器：负责数据流的编解码、缓存、转发处理；中心控制管理服务器：负责整个数据传输系统的运行调度管理。交换机可以作为接口节点，数据下载业务主要是通过基于云平台的业务系统中的应用节点—应用服务器和数据服务器来实现的，缩容模块603具体是，通知管理节点—中心控制管理服务器停止对待缩容的虚拟机进行管理，通知接口节点—交换机停止对待缩容的虚拟机进行业务请求的分发。所述业务的性能指标，包括：各虚拟机上的下载链接数量或者网速或者流量的平均值。
本发明第七实施例，一种云平台，可以作为实体装置来理解，所述云平台包括主控单元，所述主控单元包括处理器以及存储有所述处理器可执行指令的存储器，当所述指令被处理器执行时，执行如下操作：
从业务系统中选择待缩容的虚拟机；
将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
具体的，所述处理器执行的操作具体包括：
通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
转移成功后，停止所述待缩容的虚拟机上的所述业务。
根据一个示例性实施例，所述处理器执行的操作具体包括：
将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚 拟机作为目标虚拟机；
通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
本发明第八实施例，本实施例是在上述实施例的基础上，以呼叫业务为例，结合附图7～10介绍一个本发明的应用实例。
为描述方便，后续以云平台表示IaaS层功能实体，以业务系统表示“PaaS和SaaS层”功能实体，或在不存在PaaS层的情况下，表示SaaS层功能实体。除非特别说明，后续描述云平台和业务系统之间的互通，可以是IaaS层与PaaS和SaaS层之间的互通，也可以仅仅是IaaS层和PaaS层的互通，或者仅仅是IaaS层和SaaS层之间的互通，不影响本发明的实质。
本发明实施例一种云平台的业务系统，如图7所示，分别为IaaS层的云平台主控单元，与SaaS层的业务系统两部分。
其中，基于云平台的业务系统—智能网由多台部署了不同呼叫业务的虚拟机组成，分别为：负责从七号信令网接入分发基本呼叫的信令接口单元SIU；一起合设部署了SLP和状态机的业务控制点SCP负责智能网中的呼叫业务的逻辑流程、相关协议编解码及呼叫状态控制；部署了数据库SDP负责业务数据的存储；业务管理点SMP和业务管理接入点SMAP负责提供用户对整个业务系统的设备管理、业务管理功能。
云平台主控单元负责系统底层物理实体虚拟机的创建、删除、调度管理功能，主要包含：性能数据获取模块、缩容决策及预处理模块和虚拟机管理模块，性能数据获取模块负责定期采集SCP的性能数据，监控业务负载情况，当负载较低达到预设阈值时，触发缩容操作，然后由缩容决策及预处理模块，负责完成待缩容SCP的选定，并对进行一系列预处理，包括通知SIU及SMP本机将下线，切换当前存在的呼叫到其他SCP已继续完成会话任务等，预处理完成后，由虚拟机管理模块VNFM完成物理虚拟机资源的删除工作。本实施例中的性能数据获取模块、缩容决策及预处理模块和虚拟机管理模块与第四～六实施例中的判断模块、选择模块和缩容模块所完成的功能相同，区别仅在功能划分方式上的不同。
如图8所示，本发明实施例的云平台主控单元的性能数据获取模块执行的性能指标采集流程，如下：
步骤301：每分钟一次的频率，向各个SCP应用发消息，获取当前应用的呼叫数caps并将获取的各SCP上的呼叫数保存。
步骤302：计算各SCP上的呼叫数的平均值。
步骤303：然后将该平均值跟预设的阈值做比较，若低于预设的阈值，则判断需要进行缩容；若不低于预设的阈值，则执行步骤305。
步骤304：触发缩容操作。
步骤305：本次采集结束，等待下次指标数据获取。
如图9所示，本发明实施例的云平台主控单元的缩容决策模块的缩容操作流程，如下：
步骤401：缩容操作启动。
步骤402：选取呼叫数caps最小的SCP为待缩容虚拟机，若当前SCP的呼叫数大小都相同，则随机选择一个SCP为待缩容虚拟机。
步骤403：向待缩容虚拟机的应用进程发消息，确认是否准许被缩容，若该SCP的业务应用预先配置了禁止下线，则缩容操作回到步骤402重新从伸缩组中选择另外一台待缩容虚拟机；若允许被缩容，则执行步骤404。
步骤404：缩容前预处理。具体工作如下：发消息通知SIU不在分发新的呼叫给待缩容SCP，发消息通知SMP去除对本SCP的管理，然后去激活待缩容SCP上的所有业务，停止接入新的服务请求，并转移当前SCP正在执行的呼叫实例数据到伸缩组其他SCP节点，以不断线方式继续完成已有呼叫任务，然后将话单等文件压缩打包并FTP备份上传到预先配置的服务器目录，最后停止待缩容SCP的应用程序，并根据上述工作完成情况，返回缩容前预处理结果给缩容决策处理模块。
根据一个示例性实施例，步骤404中所述的切换转移当前SCP的呼叫到其他SCP节点的实现细节如图10所示，SCP中一起部署了SLP和状态机；部署在SDP中的DCACHE是基于Key/Value的云存储引擎，提供大容量、高性能、高可靠性的分布式存储。具体流程如下：
1)由云平台主控单元中的缩容预处理模块，通知被缩容SCP中的SLP模块切换呼叫操作；然后2)SLP模块遍历所有会话链路，找到所有当前在线的呼叫实例；3)通知状态机切换上述呼叫实例；然后4)SLP把呼叫的业务逻辑状态信息(包括业务支撑数据SSD、呼叫实例数据CID)序列化编码为唯一ID，保存至DCACHE中；同时5)状态机把呼叫的状态控制信息，以及各个呼叫跟SIU、IMP的对应关系表信息序列化编码，保存至DCACHE中；然后8)响应缩容预处理模块，呼叫状态入库保存成功；之后，9)在其他SCP节点中，根据性能指标，选择话务量最小，负载最低的SCP来恢复上述转移的呼叫；之后，10—14)为反序列化过程，SLP和状态机把保存在DCACHE中的呼叫信息原样恢复至内存中；15)通知主控单元呼叫状态恢复成功。切换转移的呼叫实例，由新的SLP/状态机和原SIU/SDP/IMP继续执行，直至挂机释放，实现真正的零业务中断的缩容操作。
步骤405：若缩容预处理成功，则到执行步骤406；若缩容预处理失败，则到执行步骤407。
步骤406：从云平台资源池中删除待缩容虚拟机，然后执行步骤408。
步骤407：对之前预处理操作而修改的数据进行回滚，恢复SCP为之前的状态，并分别通知SIU和SMP重新启用待缩容SCP，然后操作回到步骤402从伸缩组中选择另外一台虚拟机继续尝试进行缩容任务。
步骤408：本次操作结束。
本发明第九实施例，本实施例的云平台对业务系统的缩容方法的流程与第一、二、三 或八实施例相同，区别在于，在工程实现上，本实施例可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的所述方法可以以计算机软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台设备(可以是云平台主控单元等设备)执行本发明实施例所述的方法。
通过具体实施方式的说明，应当可对本发明为达成预定目的所采取的技术手段及功效得以更加深入且具体的了解，然而所附图示仅是提供参考与说明之用，并非用来对本发明加以限制。
工业实用性
本发明实施例提供的技术方案可以应用于云计算技术领域，在本发明实施例提供的技术方案中，对云平台的业务进行缩容时，先对云平台业务做一些缩容预处理，包括虚拟机上部署的应用服务是否准许停止，正在进行的业务服务实例数据的切换转移等，以实现稳定安全的将虚拟机资源释放，提高资源利用率的同时，保证该虚拟机宕机时也不影响整个业务系统对外提供安全稳定的服务能力，即有效的实现了云平台业务的安全稳定的缩容弹性管理。

Claims (12)

  1. 一种云平台业务的缩容方法，在云平台上运行业务系统，所述方法包括：
    从业务系统中选择待缩容的虚拟机；
    将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
  2. 根据权利要求1所述的云平台业务的缩容方法，还包括：在从业务系统中选择待缩容的虚拟机之前，检测云平台上的业务的性能指标是否低于第一指标阈值；
    当所述业务的性能指标低于第一指标阈值时，从业务系统中选择待缩容的虚拟机；
    所述业务的性能指标，包括：各虚拟机上业务量的平均值。
  3. 根据权利要求1所述的云平台业务的缩容方法，其中，从业务系统中选择待缩容的虚拟机，包括：
    从业务系统中选择业务量负载最低的虚拟机作为待缩容的虚拟机；或者，
    在业务系统中所有的虚拟机的业务量负载均相同的情况下，从业务系统中随机选择一个虚拟机作为待缩容的虚拟机。
  4. 根据权利要求1所述的云平台业务的缩容方法，还包括：在将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上之前，向所述待缩容的虚拟机运行的业务询问是否允许删除所述待缩容的虚拟机，若是，则将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上。
  5. 根据权利要求1所述的云平台业务的缩容方法，其中，将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，包括：
    通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
    将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
    转移成功后，停止所述待缩容的虚拟机上的所述业务。
  6. 根据权利要求5所述的云平台业务的缩容方法，其中，将所述待缩容的虚拟机上的业务服务实例数据转移到业务系统中的其他虚拟机上，包括：
    将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
    在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
    通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
  7. 根据权利要求6所述的云平台业务的缩容方法，其中，在所述业务为呼叫业务的情况下，所述业务服务实例数据包括：呼叫的逻辑状态信息、呼叫的状态控制信息、以及呼叫与接口节点的对应关系信息；所述业务的性能指标，包括：各虚拟机上的呼叫数量的平均值；
    在所述业务为数据下载业务的情况下，所述业务服务实例数据包括：下载请求的数据信息、下载任务传输完成度信息、下载链路信息、以及各下载任务分别与管理节点和接口节点的映射关系信息；所述业务的性能指标，包括：各虚拟机上的下载链接数量的平均值或者网速的平均值或者流量的平均值。
  8. 一种云平台业务的缩容装置，设置于云平台中，在所述云平台上运行业务系统，所述装置包括：
    选择模块，设置为从业务系统中选择待缩容的虚拟机；
    缩容模块，设置为将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
  9. 一种云平台，其中，所述云平台包括主控单元，所述主控单元包括处理器以及存储有所述处理器可执行指令的存储器，当所述指令被处理器执行时，执行如下操作：
    从业务系统中选择待缩容的虚拟机；
    将所述待缩容的虚拟机上正在执行的业务转移到业务系统中的其他虚拟机上，删除所述待缩容的虚拟机。
  10. 根据权利要求9所述的云平台，其中，所述处理器执行的操作包括：
    通知管理节点停止对待缩容的虚拟机进行管理，通知接口节点停止对待缩容的虚拟机进行业务请求的分发；对待缩容的虚拟机上正在执行的业务进行去激活，以停止接收所述业务的新的业务服务请求；
    将所述待缩容的虚拟机内存中的业务服务实例数据转移到业务系统中的其他虚拟机上；
    转移成功后，停止所述待缩容的虚拟机上的所述业务。
  11. 根据权利要求10所述的云平台，其中，所述处理器执行的操作包括：
    将所述待缩容的虚拟机内存中的业务服务实例数据进行序列化编码后得到序列码，并将所述序列码保存到业务系统的数据库中；
    在业务系统中除所述待缩容的虚拟机之外的其他虚拟机中选择业务量负载最低的虚拟机作为目标虚拟机；
    通知目标虚拟机从所述数据库中获取所述序列码，并对所述序列码解码恢复到所述目标虚拟机的内存中。
  12. 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行的一个或多个程序，所述一个或多个程序被所述计算机执行时使所述计算机执行如根据权 利要求1-7中任一项所述的云平台业务的缩容方法。
PCT/CN2017/106686 2016-10-21 2017-10-18 一种云平台业务的缩容方法、装置及云平台 WO2018072708A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610921143.5 2016-10-21
CN201610921143.5A CN107977252A (zh) 2016-10-21 2016-10-21 一种云平台业务的缩容方法、装置及云平台

Publications (1)

Publication Number Publication Date
WO2018072708A1 true WO2018072708A1 (zh) 2018-04-26

Family

ID=62004503

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/106686 WO2018072708A1 (zh) 2016-10-21 2017-10-18 一种云平台业务的缩容方法、装置及云平台

Country Status (2)

Country Link
CN (1) CN107977252A (zh)
WO (1) WO2018072708A1 (zh)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109815092A (zh) * 2019-01-28 2019-05-28 中国工商银行股份有限公司 云平台自动伸缩方法及系统
CN110275776A (zh) * 2019-05-17 2019-09-24 平安科技（深圳）有限公司 容器应用的缩容方法、装置、计算机设备及存储介质
CN110874384A (zh) * 2018-09-03 2020-03-10 阿里巴巴集团控股有限公司 数据库集群扩缩容的方法、装置和系统
CN111597058A (zh) * 2020-04-17 2020-08-28 微梦创科网络科技（中国）有限公司 一种数据流处理方法及系统
CN111752695A (zh) * 2020-06-28 2020-10-09 北京百度网讯科技有限公司 下线方法、装置、设备以及存储介质
CN111953571A (zh) * 2020-07-29 2020-11-17 新华三技术有限公司 一种vBRAS、服务器和存储介质
CN112468310A (zh) * 2019-09-06 2021-03-09 杭州海康威视系统技术有限公司 流媒体集群节点管理方法、装置及存储介质
CN113296794A (zh) * 2021-05-25 2021-08-24 多点(深圳)数字科技有限公司 一种软件工程管理方法、装置、存储介质及电子设备
CN113434256A (zh) * 2021-07-05 2021-09-24 云宏信息科技股份有限公司 云资源横向扩展方法、可读存储介质及云资源管理系统
CN114615177A (zh) * 2022-03-03 2022-06-10 腾讯科技（深圳）有限公司 一种云平台的负载检测方法、装置、电子设备和存储介质
WO2023045515A1 (en) * 2021-09-27 2023-03-30 International Business Machines Corporation Centralized imposing of multi-cloud clock speeds
CN110275776B (zh) * 2019-05-17 2024-05-31 平安科技（深圳）有限公司 容器应用的缩容方法、装置、计算机设备及存储介质

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108847956B (zh) * 2018-05-08 2021-08-17 国家计算机网络与信息安全管理中心 一种电信网安全业务vnf的多维智能扩缩容方法和系统
CN109032788B (zh) * 2018-06-29 2019-09-20 北京百度网讯科技有限公司 预留资源池动态调度方法、装置、计算机设备及存储介质
CN109756366B (zh) * 2018-12-24 2022-02-11 上海欣方智能系统有限公司 基于caas的智能网scp云服务实现系统
CN110958311A (zh) * 2019-11-27 2020-04-03 北京大学 一种基于yarn的共享集群弹性伸缩系统及方法
CN111464616A (zh) * 2020-03-30 2020-07-28 招商局金融科技有限公司 自动调节应用负载服务数量的方法、服务器及存储介质
CN111796908B (zh) * 2020-06-18 2022-08-19 聚好看科技股份有限公司 一种资源自动弹性伸缩的系统、方法及云平台
CN112068934B (zh) * 2020-09-08 2023-02-10 广州汇智通信技术有限公司 一种容器云服务实例收缩的控制系统和方法
CN112422329B (zh) * 2020-11-05 2022-08-05 杭州米络星科技(集团)有限公司 流媒体服务器集群的管理方法、装置和电子设备
CN112698947B (zh) * 2020-12-31 2022-03-29 山东省计算中心（国家超级计算济南中心） 一种基于异构应用平台的gpu资源弹性调度方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120084254A1 (en) * 2010-10-05 2012-04-05 Accenture Global Services Limited Data migration using communications and collaboration platform
CN103177006A (zh) * 2011-12-21 2013-06-26 北京昆仑万维科技股份有限公司 一种数据存储系统及其更新存储容量的方法
CN103257683A (zh) * 2013-05-07 2013-08-21 华为技术有限公司 一种云计算业务伸缩的方法和装置
CN103530189A (zh) * 2013-09-29 2014-01-22 中国科学院信息工程研究所 一种面向流式数据的自动伸缩及迁移的方法及装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7818808B1 (en) * 2000-12-27 2010-10-19 Intel Corporation Processor mode for limiting the operation of guest software running on a virtual machine supported by a virtual machine monitor
US8805989B2 (en) * 2012-06-25 2014-08-12 Sungard Availability Services, Lp Business continuity on cloud enterprise data centers
CN103023969A (zh) * 2012-11-15 2013-04-03 北京搜狐新媒体信息技术有限公司 一种云平台调度方法及系统
CN104980297A (zh) * 2014-04-14 2015-10-14 中兴通讯股份有限公司 虚拟机资源的变更方法、装置及虚拟网络功能设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120084254A1 (en) * 2010-10-05 2012-04-05 Accenture Global Services Limited Data migration using communications and collaboration platform
CN103177006A (zh) * 2011-12-21 2013-06-26 北京昆仑万维科技股份有限公司 一种数据存储系统及其更新存储容量的方法
CN103257683A (zh) * 2013-05-07 2013-08-21 华为技术有限公司 一种云计算业务伸缩的方法和装置
CN103530189A (zh) * 2013-09-29 2014-01-22 中国科学院信息工程研究所 一种面向流式数据的自动伸缩及迁移的方法及装置

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110874384A (zh) * 2018-09-03 2020-03-10 阿里巴巴集团控股有限公司 数据库集群扩缩容的方法、装置和系统
CN110874384B (zh) * 2018-09-03 2023-05-02 阿里巴巴集团控股有限公司 数据库集群扩缩容的方法、装置和系统
CN109815092A (zh) * 2019-01-28 2019-05-28 中国工商银行股份有限公司 云平台自动伸缩方法及系统
CN110275776A (zh) * 2019-05-17 2019-09-24 平安科技（深圳）有限公司 容器应用的缩容方法、装置、计算机设备及存储介质
CN110275776B (zh) * 2019-05-17 2024-05-31 平安科技（深圳）有限公司 容器应用的缩容方法、装置、计算机设备及存储介质
CN112468310B (zh) * 2019-09-06 2023-04-07 杭州海康威视系统技术有限公司 流媒体集群节点管理方法、装置及存储介质
CN112468310A (zh) * 2019-09-06 2021-03-09 杭州海康威视系统技术有限公司 流媒体集群节点管理方法、装置及存储介质
CN111597058A (zh) * 2020-04-17 2020-08-28 微梦创科网络科技（中国）有限公司 一种数据流处理方法及系统
CN111597058B (zh) * 2020-04-17 2023-10-17 微梦创科网络科技（中国）有限公司 一种数据流处理方法及系统
CN111752695A (zh) * 2020-06-28 2020-10-09 北京百度网讯科技有限公司 下线方法、装置、设备以及存储介质
CN111953571B (zh) * 2020-07-29 2022-10-21 新华三技术有限公司 一种vBRAS、服务器和存储介质
CN111953571A (zh) * 2020-07-29 2020-11-17 新华三技术有限公司 一种vBRAS、服务器和存储介质
CN113296794A (zh) * 2021-05-25 2021-08-24 多点(深圳)数字科技有限公司 一种软件工程管理方法、装置、存储介质及电子设备
CN113434256A (zh) * 2021-07-05 2021-09-24 云宏信息科技股份有限公司 云资源横向扩展方法、可读存储介质及云资源管理系统
CN113434256B (zh) * 2021-07-05 2023-06-30 云宏信息科技股份有限公司 一种云资源横向扩展方法、可读存储介质
WO2023045515A1 (en) * 2021-09-27 2023-03-30 International Business Machines Corporation Centralized imposing of multi-cloud clock speeds
CN114615177A (zh) * 2022-03-03 2022-06-10 腾讯科技（深圳）有限公司 一种云平台的负载检测方法、装置、电子设备和存储介质
CN114615177B (zh) * 2022-03-03 2023-10-13 腾讯科技（深圳）有限公司 一种云平台的负载检测方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
CN107977252A (zh) 2018-05-01

Similar Documents

Publication Publication Date Title
WO2018072708A1 (zh) 一种云平台业务的缩容方法、装置及云平台
EP3547648B1 (en) Service processing and consensus method and device
CN105873114B (zh) 一种虚拟网络功能性能监控的方法及相应的系统
CN106817432B (zh) 云计算环境下虚拟资源弹性伸展的方法，系统和设备
CN108121511B (zh) 一种分布式边缘存储系统中的数据处理方法、装置及设备
US20190075084A1 (en) Distributed Lock Management Method, Apparatus, and System
CN105069152B (zh) 数据处理方法及装置
US20230367749A1 (en) Data migration method and apparatus, device, medium, and computer product
CN101477386B (zh) 一种定时器实现方法和装置
CN107423942B (zh) 一种业务流转的方法及装置
JP7103705B1 (ja) クラスタに基づく容量縮小処理方法及び装置
CN112231108A (zh) 任务处理方法、装置、计算机可读存储介质及服务器
WO2023071999A1 (zh) 一种用户匹配方法、装置、设备及存储介质
US11102284B2 (en) Service processing methods and systems based on a consortium blockchain network
CN109165112B (zh) 一种元数据集群的故障恢复方法、系统及相关组件
WO2017215408A1 (zh) 会话切换控制方法、装置及接入点设备
CN113010496A (zh) 一种数据迁移方法、装置、设备和存储介质
CN111311254A (zh) 一种基于区块链的业务处理方法、装置和系统
CN112988062B (zh) 一种元数据读取限制方法、装置、电子设备及介质
CN102185717A (zh) 业务处理设备、方法及系统
JP2018072944A (ja) プログラム、システム及び情報処理方法
CN116701063B (zh) 数联网数据语用内存状态数据的持久化方法、装置及系统
CN111008095A (zh) 一种面向边缘云的状态快照生成和恢复方法
CN107040388B (zh) 计费系统及方法
CN113630317A (zh) 一种数据传输方法、装置、非易失性存储介质及电子装置

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: 17863202

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: 17863202

Country of ref document: EP

Kind code of ref document: A1