WO2016058318A1 - Elastic virtual machine (vm) resource scaling method, apparatus and system - Google Patents

Elastic virtual machine (vm) resource scaling method, apparatus and system Download PDF

Info

Publication number
WO2016058318A1
WO2016058318A1 PCT/CN2015/073964 CN2015073964W WO2016058318A1 WO 2016058318 A1 WO2016058318 A1 WO 2016058318A1 CN 2015073964 W CN2015073964 W CN 2015073964W WO 2016058318 A1 WO2016058318 A1 WO 2016058318A1
Authority
WO
WIPO (PCT)
Prior art keywords
resource
node
vnfm
nfvo
elastic scaling
Prior art date
Application number
PCT/CN2015/073964
Other languages
French (fr)
Chinese (zh)
Inventor
陈露静
周智伟
刘磊
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 WO2016058318A1 publication Critical patent/WO2016058318A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/40Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities

Definitions

  • the present invention relates to the field of communications, and in particular to a virtual machine VM resource elastic scaling processing method, apparatus, and system.
  • VMs virtual machines
  • Point monitoring is the main method, in which the monitoring nodes are mostly placed upstream, and most of them are based on Network Functions Virtualisation Orchestrator (NFVO). This situation is too big for NFVO. If there is a problem with the upstream node, It is easy to cause a single point of failure.
  • NFVO Network Functions Virtualisation Orchestrator
  • the current monitoring mode generally uses a virtual machine to periodically report the indicator information of the local device to an upstream node, and then the upstream node determines whether the threshold of the scaling rule is reached.
  • the message will not be monitored in real time when there is packet loss or network congestion during transmission.
  • the invention provides a virtual machine VM resource elastic scaling processing method, device and system, so as to at least solve the problem that the NFVO information interaction is excessive and the impact is large in the related art.
  • a virtual machine VM resource elastic scaling processing method including: determining, by a first node or a neighboring upstream node of a first node, according to indicator information of a VM in the first node, The first node reaches a predetermined threshold for performing the VM resource elastic scaling process; and the VM node elastic scaling process is performed on the first node by using the upstream node of the first node.
  • the indicator information of the VM includes at least one of the following information: memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
  • performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: sending, by the VM, a virtualized network function VNF And requesting to perform the first request message of the VM resource elastic scaling process; the VNF sends, according to the first request message, a second request message for requesting a global resource access interface to pre-apply resources to the virtualized network function management VNFM.
  • the VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; and the NFVO performs the VM resource elastic scaling process on the VM according to the VM resource change request.
  • performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: the VNF to a virtualized network function
  • the management VNFM sends a second request message for requesting the global resource access interface to pre-apply the resource; the VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the NFVO is according to the The VM resource change request performs the VM resource elastic scaling process on the VNF.
  • performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: the VNFM virtualizing to a network function
  • the NFVO sends a third request message for requesting the global resource access interface to pre-apply the resource; if the pre-application resource application is successful, the VNFM sends a VM resource change request to the NFVO;
  • the NFVO performs the VM resource elastic scaling process on the VNFM according to the VM resource change request.
  • a virtual machine VM resource elastic scaling processing apparatus including: a determining module, located in a first node or an adjacent upstream node of a first node, configured to be according to the first node
  • the indicator information of the VM determines that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing; and the processing module is located in each upstream node of the first node, and is configured to perform the VM on the first node.
  • the processing module includes: a first sending unit, located in the VM, configured to send, when the first node is the VM, a request for performing the VM resource elastic scaling processing to the virtualized network function VNF
  • the first request message is located in the VNF, and is configured to send, according to the first request message, a second request for requesting a global resource access interface to pre-apply resources to the virtualized network function management VNFM.
  • a third sending unit located in the VNFM, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the first processing unit is located in the NFVO, and is set according to the The VM resource change request is performed on the VM by the VM resource change request.
  • the processing module includes: a fourth sending unit, located in the virtualized network function VNF, configured to send, by using the VNF, the virtualized network function management VNFM when the first node is the VNF Requesting a global resource access interface to perform a second request message for pre-applying resources; a fifth sending unit, located in the VNFM, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message;
  • the second processing unit, located in the NFVO is configured to perform the VM resource elastic scaling process on the VNF according to the VM resource change request.
  • the processing module includes: a sixth sending unit, located in the virtualized network function management VNFM, configured to use the VNFM to virtualize the NFVO transmission to the network function when the first node is the VNFM a third request message for requesting a resource for requesting a global resource access interface; a seventh sending unit, located in the VNFM, configured to send a VM resource to the NFVO if the pre-application resource application is successful a change request; the third processing unit, located in the NFVO, is configured to perform the VM resource elastic scaling process on the VNFM according to the VM resource change request.
  • a sixth sending unit located in the virtualized network function management VNFM, configured to use the VNFM to virtualize the NFVO transmission to the network function when the first node is the VNFM a third request message for requesting a resource for requesting a global resource access interface
  • a seventh sending unit located in the VNFM, configured to send a VM resource to the NFVO if the pre-application resource application
  • a system comprising the virtual machine VM resource elastic scaling processing device according to any of the above aspects is provided.
  • the first node or the neighboring upstream node of the first node determines that the first node has reached a predetermined threshold for performing VM resource elastic scaling processing according to the indicator information of the VM in the first node;
  • the upstream node of the first node performs the VM resource elastic scaling process on the first node, which solves the problem that the NFVO information interaction is too much and the impact is large in the related art, thereby reducing the information interaction with the NFVO. , the effect of reducing the impact on the NFVO.
  • FIG. 2 is a flowchart of a virtual machine VM resource elastic scaling processing method according to an embodiment of the present invention
  • FIG. 3 is a structural block diagram of a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention.
  • FIG. 4 is a structural block diagram 1 of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention
  • FIG. 5 is a second structural block diagram of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention
  • FIG. 6 is a third structural block diagram of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention.
  • Figure 7 is a block diagram showing the structure of a system in accordance with an embodiment of the present invention.
  • FIG. 8 is a diagram showing a process of VM elastic expansion according to an embodiment of the present invention.
  • Figure 9 is a diagram showing the VNF elastic shrinkage process according to an embodiment of the present invention.
  • FIG. 10 is a diagram showing a VNFM elastic expansion process according to an embodiment of the present invention.
  • FIG. 2 is a flowchart of a virtual machine VM resource elastic scaling processing method according to an embodiment of the present invention. As shown in FIG. 2, the process includes the following steps. :
  • step S202 the first node or the adjacent upstream node of the first node determines, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing the VM resource elastic scaling process;
  • Step S204 Performing VM resource elastic scaling processing on the first node by using the upstream node of the first node.
  • the first node or the adjacent upstream node of the first node determines, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing; and uses the upstream node of the first node.
  • Performing VM resource elastic scaling processing on the first node to implement neighboring by the node itself or the node The upstream node monitors the status of the node, reduces the impact on the NFVO node, and solves the problem of excessive interaction and large impact on the NFVO information in the related art, thereby reducing the information interaction with the NFVO and reducing the NFVO. The effect of the impact.
  • the indicator information of the VM includes at least one of the following information: memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
  • performing VM resource elastic scaling processing on the first node by using the upstream node of the first node includes: sending, by the VM to the virtualized network function VNF, requesting VM resource resiliency The first request message of the telescoping process; the VNF sends a second request message for requesting the global resource access interface for pre-applying resources to the virtualized network function management VNFM according to the first request message; the VNFM virtualizes to the network function according to the second request message.
  • the NFVO sends a VM resource change request; the NFVO performs VM resource elastic scaling processing on the VM according to the VM resource change request. Therefore, when the VM resource elastic scaling processing is performed on the VM, the information interaction with the NFVO is greatly reduced, and the impact on the NFVO is reduced.
  • performing the VM resource elastic scaling process on the first node by using the upstream node of the first node includes: sending the VNF to the virtualized network function management VNFM for Requesting a global resource access interface to perform a second request message for pre-applying resources; the VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; and the NFVO performs VM resource elastic scaling processing on the VNF according to the VM resource change request. Therefore, when the VM resource elastic scaling processing is performed on the VNF, the information interaction with the NFVO is greatly reduced, and the impact on the NFVO is reduced.
  • the VM node elastic scaling processing of the first node by using the upstream node of the first node includes: VNFM arranging NFVO for network function virtualization scheduling
  • the third request message of the pre-applied resource is requested by the global resource access interface; when the pre-application resource application is successful, the VNFM sends a VM resource change request to the NFVO; and the NFVO performs the VM resource elastic expansion on the VNFM according to the VM resource change request. deal with. Therefore, when the VM resource elastic scaling processing is performed on the VNFM, the information interaction with the NFVO is greatly reduced, and the impact on the NFVO is reduced.
  • a virtual machine VM resource resiliency processing device is also provided, which is used to implement the foregoing embodiments and preferred embodiments, and has not been described again.
  • the term "module” may implement a combination of software and/or hardware of a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • FIG. 3 is a structural block diagram of a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention. As shown in FIG. 3, the apparatus includes a determining module 32 and a processing module 34. The device will be described below.
  • the determining module 32 is located in the first node or the adjacent upstream node of the first node, and is configured to determine, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing; and the processing module 34 And being located in each of the upstream nodes of the first node, and connected to the determining module 32, configured to perform VM resource elastic scaling processing on the first node.
  • the indicator information of the VM may include at least one of the following information: memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
  • FIG. 4 is a structural block diagram 1 of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention.
  • the processing module 34 includes a first sending unit 42 and a second sending unit 44.
  • the processing module 34 will be described below.
  • the first sending unit 42 is located in the VM, and is configured to send a first request message for requesting VM resource elastic scaling processing to the virtualized network function VNF when the first node is a VM; the second sending unit 44 is located at the VNF.
  • the first sending unit 42 is configured to send, according to the first request message, a second request message for requesting the global resource access interface to pre-apply resources to the virtualized network function management VNFM;
  • the third sending unit 46 Located in the VNFM, connected to the foregoing second sending unit 44, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the first processing unit 48, located in the NFVO, connected to the third sending unit 46.
  • FIG. 5 is a structural block diagram 2 of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention.
  • the processing module 34 includes a fourth sending unit 52, a fifth sending unit 54, and Second processing unit 56.
  • the processing module 34 will be described below.
  • the fourth sending unit 52 is located in the virtualized network function VNF, and is configured to use the VNF to send a second request for requesting the global resource access interface for pre-applying resources to the virtualized network function management VNFM by using the VNF.
  • the fifth sending unit 54 located in the VNFM, is connected to the fourth sending unit 52, and configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the second processing unit 56 is located in the NFVO.
  • the fifth transmitting unit 54 is connected to the fifth transmitting unit 54 and configured to perform VM resource elastic scaling processing on the VM according to the VM resource change request.
  • FIG. 6 is a third structural block diagram of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention.
  • the processing module 34 includes a sixth sending unit 62, a seventh sending unit 64, and Third processing unit 66.
  • the processing module 34 will be described below.
  • the sixth sending unit 62 is located in the virtualized network function management VNFM, and is configured to use the VNFM to send the NFVO to the network function virtualization scheduling NFVO to request the global resource access interface to perform the pre-applied resource when the first node is the VNFM.
  • a request message the seventh sending unit 64, located in the VNFM, connected to the sixth sending unit 62, configured to send a VM resource change request to the NFVO if the pre-application resource application is successful; the third processing unit 66 is located
  • the NFVO is connected to the seventh transmitting unit 64, and is configured to perform VM resource elastic scaling processing on the VM according to the VM resource change request.
  • FIG. 7 is a structural block diagram of a virtual machine VM resource elastic scaling processing system according to an embodiment of the present invention.
  • the virtual machine VM resource elastic scaling processing system 72 includes the virtual machine VM resource elastic scaling processing of any of the above.
  • Device 74 includes the virtual machine VM resource elastic scaling processing of any of the above.
  • a method for resource on-demand provisioning and dynamic management is also provided in the embodiment of the present invention, which can be mitigated by the method in the embodiment of the present invention.
  • the impact on the upstream node NFVO effectively eliminates single points of failure, reduces message interaction, and makes the collected indicator information more accurate, thus achieving the purpose of constructing an efficient, secure and reliable elastic extension service.
  • the NFVO node that originally manages the virtual resource is sunk, and the NFVO impact is reduced by the privilege decentralized layer management, and the resource management interface is provided to the VNFM so that it can also access the preemption.
  • Global virtual resource information such as resources, VM state, and VM used resources, so that it does not need to be accessed through NFVO every time.
  • the VM resource elastic scaling process is performed:
  • the VMs are bundled together by the Server Load Balancing (SLB).
  • SLB Server Load Balancing
  • the VM monitoring indicators here mainly include system information such as memory, CPU, hard disk, and bandwidth.
  • the real-time status monitoring is performed by each VM itself, and it is judged by itself whether or not the elastic scaling condition is reached. If the VM itself cannot determine whether the elastic scaling rule is met, the monitored information data is transferred to the upstream VNF node. Judge.
  • the first request message is sent to the VNF for elastic scaling processing, and the request is sent to the Virtualised Network Function Manager (VNFM).
  • VNFM Virtualised Network Function Manager
  • the VNF sends the second request message to the VNFM, and triggers the elastic scalability request.
  • the VNFM sends the VM resource request change message to the NFVO, performs a series of state migration operations on the VM, releases the VM resources, and then performs the VNF.
  • SLB processing reducing the total cost of ownership (TCO); when the overall system load is high, such as If the capacity expansion condition is reached, the VNF sends a second request message to the VNFM, and the VNFM sends a VM resource request change message to the NFVO, and according to the VM configuration bound by the VNF, the VM is started by performing a series of state transition operations on the VM. Then, SLB processing is performed on the VNF to expand and expand the system processing capability.
  • TCO total cost of ownership
  • FIG. 8 is a diagram of a VM elastic scaling process according to an embodiment of the present invention. As shown in FIG. 8, the process includes the following steps:
  • Step S802 The cloud data center platform is deployed, the VM resources are created with elastic scaling rules, the virtual network deployment is completed, and the VM information collection is completed.
  • Step S804 The VM itself performs state monitoring and elastic determination. If the VM itself cannot determine whether the elastic scaling rule is met, the monitored information data is submitted to the upstream VNF node for judgment;
  • Step S806 If the scaling condition is reached, the VM sends a first request message to the VNF for elastic scaling processing.
  • Step S808 The VNF sends an elastic scaling request requesting elastic scaling processing of the VM resource to the VNFM;
  • Step S810 The VNFM sends a VM resource change request to the NFVO, where the VNFM parses the VNF-initiated VM request request, the request carries the VM name and operation, and the number of VMs created:
  • the VNFM starts the VM to the normal running state, and then reports success;
  • the VNFM requests the NFVO to request the resource from the global resource access interface, and the resource application successfully reports the message and proceeds to the next step. If the NFVO has no response timeout, the process terminates and reports an error; if the pre-requested resource fails, the report fails and the process terminates; the VNFM sends a resource allocation request to the NFVO, the resource allocation successfully reports the message and proceeds to the next step; if the NFVO has no response timeout, The process is terminated and an error is reported; if the resource allocation fails, the report fails and the process terminates;
  • Step S812 The NFVO successfully creates the VM, and finally causes the VM to reach the initial state.
  • the VNFM lifecycle service sends the VM that is created and created to the VNF. If the VM fails to be sent, the error is reported; the VNFM report message returns the VNF creation result, and carries the operation action and the VM name. And the result of each VM operation; VNF performs SLB processing on the newly added VM.
  • Preferred Embodiment 2 VM resource elastic scaling processing when the first node is a VNF
  • the VNF node In addition to the possibility of determining the downstream VM index information, the VNF node needs to simultaneously judge and monitor its own indicator information.
  • the monitoring indicators here mainly involve system information such as memory, CPU, hard disk, and bandwidth, and service indicators carried by the NE side. Information, such as the number of transactions per second (Transactions Per Second, TPS for short), the load situation of a certain service, etc. If the VNF itself cannot judge whether the elastic scaling rule is met, all the information data monitored is handed over to The upstream VNFM node performs the judgment. If the scaling condition is reached, the VNF performs elastic scaling processing and sends a related request to the VNFM. When the overall system load is low, if the shrinking condition is reached, the second request message is sent.
  • TPS Transactions Per Second
  • the VNFM sends a VM resource change request to the NFVO, performs a series of state migration operations on the VM, releases the VM resources, and then performs SLB processing on the VNF to reduce the system TCO; when the overall system load is high In the case that the capacity expansion condition is reached, the second request message is sent to the VNFM, VN.
  • the FM then sends a VM resource change request to the NFVO, and according to the VM configuration bound by the VNF, the VM is subjected to a series of state transition operations, the corresponding VM is started, and then the VNF is processed by the VNF, thereby expanding and expanding the system processing capability.
  • NFVO cooperates with VNFM to complete the elastic expansion and contraction of the VM.
  • the process is initiated by the VM.
  • the VNFM calculates the resource list to be modified, allocates resources to the NFVO application, completes the resource preemption and allocation, and the VNFM starts to add the VM and notifies the VNF.
  • 9 is a diagram showing a VNF elastic contraction process according to an embodiment of the present invention. As shown in FIG. 9, the process includes the following steps:
  • Step S902 The cloud data center platform is deployed, the VNF resource is created with elastic scaling rules, the virtual network deployment is completed, and the VNF information collection is completed.
  • Step S904 The VNF itself determines whether the VNF itself cannot determine whether the elastic scaling rule is met, and then the monitored information data is sent to the upstream VNFM node for judgment;
  • Step S906 If the scaling condition is reached, the VNF sends an elastic scaling processing message requesting the VM resource elastic scaling processing to the VNFM;
  • Step S908 The VNFM parses the VNF-created VM request, and the request carries the VM name and operation, and the number of VMs created:
  • the VNFM starts the VM to the normal running state, and then reports success;
  • the VNFM sends a second request message to the NFVO, requesting the global resource access interface to pre-apply the resource, and the resource application successfully reports the message and proceeds to the next step; if the NFVO has no response timeout, the process terminates and reports an error; if the pre-application resource fails, The report failed and the process was terminated.
  • the VNFM sends a VM resource change request to the NFVO, and the resource allocation successfully reports the message and proceeds to the next step. If the NFVO has no response timeout, the process terminates and an error is reported; if the resource allocation fails, the report fails and the process terminates;
  • Step S910 The NFVO successfully creates the VM, and finally causes the VM to reach the initial state.
  • the VNFM lifecycle service sends the VM that is created and created to the VNF. If the VM fails to be sent, the error is reported; the VNFM report message returns the VNF creation result, and carries the operation action and the VM name. And the result of each VM operation; VNF performs SLB processing on the newly added VM.
  • the VM resource elastic scaling process is performed:
  • the VNFM node In addition to the possibility of judging the downstream VNF indicator information, the VNFM node needs to simultaneously judge and monitor its own indicator information.
  • the monitoring indicators here mainly involve system information such as memory, CPU, hard disk, bandwidth, and network element processing capability. If the condition is low, if the overall load is low, if the shrinkage condition is reached, the elastic scalability request is triggered, and the VM resource request change message is sent to the NFVO, and a series of state transition operations are performed on the VM. The VM resource is released, and then the SLB processing is performed on the VNFM to reduce the system TCO.
  • the elastic scalability request is triggered, the resource request change message is sent to the NFVO, and the VNFM is bound according to the VNFM.
  • the VM configuration expands and expands the system processing capability by performing a series of state migration operations on the VM, starting the corresponding VM, and then performing SLB processing on the VNFM.
  • FIG. 10 is a schematic diagram of a VNFM elastic stretching process according to an embodiment of the present invention. As shown in FIG. 10, the process includes the following steps:
  • Step S1002 The cloud data center platform is deployed, the VNFM resource is created with elastic scaling rules, the virtual network deployment is completed, and the VNFM information collection is completed.
  • Step S1004 The VNFM itself judges flexibly. If the VNFM cannot judge whether the elastic scaling rule is met, the monitored information data is sent to the upstream NFVO node for determination; if the scaling condition is reached, the VNFM sends the request for the request. Performing an elastic scaling processing message of the VM resource elastic scaling process to the NFVO;
  • Step S1006 The VNFM parses the VM creation request initiated by itself, and the request carries the VM name and operation, and the number of VMs created:
  • the VNFM starts the VM to the normal running state, and then reports success;
  • the VNFM sends a third request message to the NFVO, requesting the global resource access interface to pre-apply the resource, and the resource application successfully reports the message and proceeds to the next step; if the NFVO has no response timeout, the process terminates and reports an error; if the pre-application resource fails, If the resource fails to be sent, the process is terminated and the error is reported.
  • Step S1008 The NFVO successfully creates the VM, and the report message returns the VNFM creation result, carries the operation action and the VM name, and the operation result of each VM; the VNFM performs SLB processing on the newly added VM.
  • the VMs of each level judge the frequent real-time information interaction of each level by real-time monitoring and elastic scalability of the own and the upstream nodes, and more accurately check and monitor the VM status indicators in real time, and check if the elastic state is achieved.
  • the condition triggers the elastic scaling action, automatically performs state transition on the VM, adjusts the state of the VM, and operates VM resources such as memory, CPU, hard disk, and bandwidth through the cloud data center to achieve extended network element capability or lower TCO.
  • the elastic extension state migration method under the telecommunication device virtualization technology proposed in the embodiment of the present invention can not only mitigate the impact on the upstream, but also effectively eliminate single point failure, reduce message interaction, and allow the collected indicators. More accurate information, while improving the security of flexible telescopic services, and reducing equipment resources The cost of the source, and a variety of customized services, including virtual service dynamic migration, VM on-demand allocation. In turn, the goal of safer, more reliable, flexible, and efficient information operation is achieved.
  • modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein.
  • the steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module.
  • the invention is not limited to any specific combination of hardware and software.
  • the above embodiments and preferred embodiments solve the problem of excessive interaction and large impact on the NFVO information in the related art, thereby achieving the effect of reducing the information interaction with the NFVO and reducing the impact on the NFVO. .

Abstract

The present invention provides an elastic virtual machine (VM) resource scaling method, apparatus and system. The method comprises: determining, by a first node or an upstream node adjacent to the first node according to VM index information in the first node, that the first node reaches a predetermined threshold for performing elastic VM resource scaling; and performing elastic VM resource scaling on the first node by using the upstream node of the first node. The problem in the related art of excessive information exchange with an NFVO and high impact on the NFVO is solved, thereby achieving the effect of reducing the information exchange with the NFVO and lowering the impact on the NFVO.

Description

虚拟机VM资源弹性伸缩处理方法、装置及系统Virtual machine VM resource elastic scaling processing method, device and system 技术领域Technical field
本发明涉及通信领域,具体而言,涉及一种虚拟机VM资源弹性伸缩处理方法、装置及系统。The present invention relates to the field of communications, and in particular to a virtual machine VM resource elastic scaling processing method, apparatus, and system.
背景技术Background technique
在当前通讯领域,如何在电信设备中构建高效可靠的弹性伸缩服务是业内面临的重要问题和核心难题。In the current communication field, how to build efficient and reliable elastic telescopic services in telecommunication equipment is an important problem and core problem facing the industry.
目前大多数的解决方案在安全性和可靠性上均不是很完善,特别是虚拟机(Virtual Machine,简称VM)的弹性伸缩指标监控部分,目前对虚拟机指标信息的监控多以集中式的单点监控方式为主,其中监控节点多放在上游,多以网络功能虚拟化编排(Network Functions Virtualisation Orchestrator,简称NFVO)为主,这种情况对NFVO的冲击过大,要是上游节点出现问题,就很容易会引发单点故障。At present, most of the solutions are not perfect in terms of security and reliability, especially the monitoring of the elastic scalability indicators of virtual machines (VMs). Currently, the monitoring of virtual machine indicator information is mostly centralized. Point monitoring is the main method, in which the monitoring nodes are mostly placed upstream, and most of them are based on Network Functions Virtualisation Orchestrator (NFVO). This situation is too big for NFVO. If there is a problem with the upstream node, It is easy to cause a single point of failure.
图1是相关技术中的资源控制结构图,并且,目前的监控方式一般都是虚拟机将本机的指标信息定时采集上报给上游节点,然后由上游节点判断是否达到了伸缩规则的阀值,此种方式的优点是对集中式的批量管理等比较方便,但是缺点也很明显,比如:1 is a resource control structure diagram in the related art, and the current monitoring mode generally uses a virtual machine to periodically report the indicator information of the local device to an upstream node, and then the upstream node determines whether the threshold of the scaling rule is reached. The advantage of this method is that it is convenient for centralized batch management, but the disadvantages are also obvious, such as:
1、消息在传送过程中出现丢包或者网络阻塞时将无法进行实时监控。1. The message will not be monitored in real time when there is packet loss or network congestion during transmission.
2、将本机采集的指标信息交由上游节点进行伸缩判断的话,在精确性上也会有问题。2. If the index information collected by this machine is submitted to the upstream node for telescopic judgment, there will be problems in accuracy.
针对相关技术中存在的对NFVO信息交互过多,冲击大的问题,目前尚未提出有效的解决方案。In view of the problem of excessive interaction and large impact on NFVO information existing in related technologies, no effective solution has been proposed yet.
发明内容Summary of the invention
本发明提供了一种虚拟机VM资源弹性伸缩处理方法、装置及系统,以至少解决相关技术中存在的对NFVO信息交互过多,冲击大的问题。 The invention provides a virtual machine VM resource elastic scaling processing method, device and system, so as to at least solve the problem that the NFVO information interaction is excessive and the impact is large in the related art.
根据本发明的一个方面,提供了一种虚拟机VM资源弹性伸缩处理方法,包括:由第一节点或第一节点的相邻上游节点根据所述第一节点中的VM的指标信息确定所述第一节点达到了进行VM资源弹性伸缩处理的预定阈值;利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理。According to an aspect of the present invention, a virtual machine VM resource elastic scaling processing method is provided, including: determining, by a first node or a neighboring upstream node of a first node, according to indicator information of a VM in the first node, The first node reaches a predetermined threshold for performing the VM resource elastic scaling process; and the VM node elastic scaling process is performed on the first node by using the upstream node of the first node.
优选地,所述VM的指标信息包括以下信息至少之一:内存信息、中央处理器CPU信息、硬盘信息、宽带信息、所述VM所承载的业务指标信息、所述VM的处理能力。Preferably, the indicator information of the VM includes at least one of the following information: memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
优选地,当所述第一节点为VM时,利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理包括:所述VM向虚拟化网络功能VNF发送用于请求进行所述VM资源弹性伸缩处理的第一请求消息;所述VNF根据所述第一请求消息向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;所述VNFM根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;所述NFVO根据所述VM资源变更请求对所述VM进行所述VM资源弹性伸缩处理。Preferably, when the first node is a VM, performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: sending, by the VM, a virtualized network function VNF And requesting to perform the first request message of the VM resource elastic scaling process; the VNF sends, according to the first request message, a second request message for requesting a global resource access interface to pre-apply resources to the virtualized network function management VNFM. The VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; and the NFVO performs the VM resource elastic scaling process on the VM according to the VM resource change request.
优选地,当所述第一节点为虚拟化网络功能VNF时,利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理包括:所述VNF向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;所述VNFM根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;所述NFVO根据所述VM资源变更请求对所述VNF进行所述VM资源弹性伸缩处理。Preferably, when the first node is a virtualized network function VNF, performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: the VNF to a virtualized network function The management VNFM sends a second request message for requesting the global resource access interface to pre-apply the resource; the VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the NFVO is according to the The VM resource change request performs the VM resource elastic scaling process on the VNF.
优选地,当所述第一节点为虚拟化网络功能管理VNFM时,利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理包括:所述VNFM向网络功能虚拟化编排NFVO发送用于请求全局的资源访问接口进行预申请资源的第三请求消息;在进行所述预申请资源申请成功的情况下,所述VNFM向所述NFVO发送VM资源变更请求;所述NFVO根据所述VM资源变更请求对所述VNFM进行所述VM资源弹性伸缩处理。Preferably, when the first node is a virtualized network function management VNFM, performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: the VNFM virtualizing to a network function The NFVO sends a third request message for requesting the global resource access interface to pre-apply the resource; if the pre-application resource application is successful, the VNFM sends a VM resource change request to the NFVO; The NFVO performs the VM resource elastic scaling process on the VNFM according to the VM resource change request.
根据本发明的另一方面,提供了一种虚拟机VM资源弹性伸缩处理装置,包括:确定模块,位于第一节点或第一节点的相邻上游节点中,设置为根据所述第一节点中的VM的指标信息确定所述第一节点达到了进行VM资源弹性伸缩处理的预定阈值;处理模块,位于所述第一节点的各个上游节点中,设置为对所述第一节点进行所述VM资源弹性伸缩处理。 According to another aspect of the present invention, a virtual machine VM resource elastic scaling processing apparatus is provided, including: a determining module, located in a first node or an adjacent upstream node of a first node, configured to be according to the first node The indicator information of the VM determines that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing; and the processing module is located in each upstream node of the first node, and is configured to perform the VM on the first node. Resource elastic scaling processing.
优选地,所述处理模块包括:第一发送单元,位于VM中,设置为当所述第一节点为所述VM时,向虚拟化网络功能VNF发送用于请求进行所述VM资源弹性伸缩处理的第一请求消息;第二发送单元,位于所述VNF中,设置为根据所述第一请求消息向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;第三发送单元,位于所述VNFM中,设置为根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;第一处理单元,位于所述NFVO中,设置为根据所述VM资源变更请求对所述VM进行所述VM资源弹性伸缩处理。Preferably, the processing module includes: a first sending unit, located in the VM, configured to send, when the first node is the VM, a request for performing the VM resource elastic scaling processing to the virtualized network function VNF The first request message is located in the VNF, and is configured to send, according to the first request message, a second request for requesting a global resource access interface to pre-apply resources to the virtualized network function management VNFM. a third sending unit, located in the VNFM, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the first processing unit is located in the NFVO, and is set according to the The VM resource change request is performed on the VM by the VM resource change request.
优选地,所述处理模块包括:第四发送单元,位于虚拟化网络功能VNF中,设置为当所述第一节点为所述VNF时,利用所述VNF向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;第五发送单元,位于所述VNFM中,设置为根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;第二处理单元,位于所述NFVO中,设置为根据所述VM资源变更请求对所述VNF进行所述VM资源弹性伸缩处理。Preferably, the processing module includes: a fourth sending unit, located in the virtualized network function VNF, configured to send, by using the VNF, the virtualized network function management VNFM when the first node is the VNF Requesting a global resource access interface to perform a second request message for pre-applying resources; a fifth sending unit, located in the VNFM, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; The second processing unit, located in the NFVO, is configured to perform the VM resource elastic scaling process on the VNF according to the VM resource change request.
优选地,所述处理模块包括:第六发送单元,位于虚拟化网络功能管理VNFM中,设置为当所述第一节点为所述VNFM时,利用所述VNFM向网络功能虚拟化编排NFVO发送用于请求全局的资源访问接口进行预申请资源的第三请求消息;第七发送单元,位于所述VNFM中,设置为在进行所述预申请资源申请成功的情况下,向所述NFVO发送VM资源变更请求;第三处理单元,位于所述NFVO中,设置为根据所述VM资源变更请求对所述VNFM进行所述VM资源弹性伸缩处理。Preferably, the processing module includes: a sixth sending unit, located in the virtualized network function management VNFM, configured to use the VNFM to virtualize the NFVO transmission to the network function when the first node is the VNFM a third request message for requesting a resource for requesting a global resource access interface; a seventh sending unit, located in the VNFM, configured to send a VM resource to the NFVO if the pre-application resource application is successful a change request; the third processing unit, located in the NFVO, is configured to perform the VM resource elastic scaling process on the VNFM according to the VM resource change request.
根据本发明的再一方面,提供了一种系统,包括上述任一项所述的虚拟机VM资源弹性伸缩处理装置。According to still another aspect of the present invention, a system comprising the virtual machine VM resource elastic scaling processing device according to any of the above aspects is provided.
通过本发明,采用由第一节点或第一节点的相邻上游节点根据所述第一节点中的VM的指标信息确定所述第一节点达到了进行VM资源弹性伸缩处理的预定阈值;利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理,解决了相关技术中存在的对NFVO信息交互过多,冲击大的问题,进而达到了减少与NFVO的信息交互,降低对该NFVO的冲击的效果。According to the present invention, the first node or the neighboring upstream node of the first node determines that the first node has reached a predetermined threshold for performing VM resource elastic scaling processing according to the indicator information of the VM in the first node; The upstream node of the first node performs the VM resource elastic scaling process on the first node, which solves the problem that the NFVO information interaction is too much and the impact is large in the related art, thereby reducing the information interaction with the NFVO. , the effect of reducing the impact on the NFVO.
附图说明DRAWINGS
此处所说明的附图用来提供对本发明的进一步理解,构成本申请的一部分,本发明的示意性实施例及其说明用于解释本发明,并不构成对本发明的不当限定。在附图中: The drawings described herein are intended to provide a further understanding of the invention, and are intended to be a part of the invention. In the drawing:
图1是相关技术中的资源控制结构图;1 is a resource control structure diagram in the related art;
图2是根据本发明实施例的虚拟机VM资源弹性伸缩处理方法的流程图;2 is a flowchart of a virtual machine VM resource elastic scaling processing method according to an embodiment of the present invention;
图3是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置的结构框图;3 is a structural block diagram of a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention;
图4是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置中处理模块34的结构框图一;4 is a structural block diagram 1 of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention;
图5是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置中处理模块34的结构框图二;FIG. 5 is a second structural block diagram of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention;
图6是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置中处理模块34的结构框图三;FIG. 6 is a third structural block diagram of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention;
图7是根据本发明实施例的系统的结构框图;Figure 7 is a block diagram showing the structure of a system in accordance with an embodiment of the present invention;
图8是根据本发明实施例的VM弹性伸缩过程图;FIG. 8 is a diagram showing a process of VM elastic expansion according to an embodiment of the present invention; FIG.
图9是根据本发明实施例的VNF弹性收缩过程图;Figure 9 is a diagram showing the VNF elastic shrinkage process according to an embodiment of the present invention;
图10是根据本发明实施例的VNFM弹性伸缩过程图。FIG. 10 is a diagram showing a VNFM elastic expansion process according to an embodiment of the present invention.
具体实施方式detailed description
下文中将参考附图并结合实施例来详细说明本发明。需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互组合。The invention will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.
在本实施例中提供了一种虚拟机VM资源弹性伸缩处理方法,图2是根据本发明实施例的虚拟机VM资源弹性伸缩处理方法的流程图,如图2所示,该流程包括如下步骤:In this embodiment, a virtual machine VM resource elastic scaling processing method is provided. FIG. 2 is a flowchart of a virtual machine VM resource elastic scaling processing method according to an embodiment of the present invention. As shown in FIG. 2, the process includes the following steps. :
步骤S202,由第一节点或第一节点的相邻上游节点根据第一节点中的VM的指标信息确定第一节点达到了进行VM资源弹性伸缩处理的预定阈值;In step S202, the first node or the adjacent upstream node of the first node determines, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing the VM resource elastic scaling process;
步骤S204,利用第一节点的上游节点对第一节点进行VM资源弹性伸缩处理。Step S204: Performing VM resource elastic scaling processing on the first node by using the upstream node of the first node.
通过上述步骤,由第一节点或第一节点的相邻上游节点根据第一节点中的VM的指标信息确定第一节点达到了进行VM资源弹性伸缩处理的预定阈值;利用第一节点的上游节点对第一节点进行VM资源弹性伸缩处理,实现了由节点本身或节点的相邻 上游节点对节点进行状态监控,减少了对NFVO节点的冲击,解决了相关技术中存在的对NFVO信息交互过多,冲击大的问题,进而达到了减少与NFVO的信息交互,降低对该NFVO的冲击的效果。Through the above steps, the first node or the adjacent upstream node of the first node determines, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing; and uses the upstream node of the first node. Performing VM resource elastic scaling processing on the first node to implement neighboring by the node itself or the node The upstream node monitors the status of the node, reduces the impact on the NFVO node, and solves the problem of excessive interaction and large impact on the NFVO information in the related art, thereby reducing the information interaction with the NFVO and reducing the NFVO. The effect of the impact.
其中,上述VM的指标信息包括以下信息至少之一:内存信息、中央处理器CPU信息、硬盘信息、宽带信息、VM所承载的业务指标信息、VM的处理能力。The indicator information of the VM includes at least one of the following information: memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
在一个优选的实施例中,当第一节点为VM时,利用第一节点的上游节点对第一节点进行VM资源弹性伸缩处理包括:VM向虚拟化网络功能VNF发送用于请求进行VM资源弹性伸缩处理的第一请求消息;VNF根据第一请求消息向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;VNFM根据第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;NFVO根据VM资源变更请求对VM进行VM资源弹性伸缩处理。从而实现了在对VM进行VM资源弹性伸缩处理时,极大的减少了和NFVO之间的信息交互,降低了对NFVO的冲击。In a preferred embodiment, when the first node is a VM, performing VM resource elastic scaling processing on the first node by using the upstream node of the first node includes: sending, by the VM to the virtualized network function VNF, requesting VM resource resiliency The first request message of the telescoping process; the VNF sends a second request message for requesting the global resource access interface for pre-applying resources to the virtualized network function management VNFM according to the first request message; the VNFM virtualizes to the network function according to the second request message. The NFVO sends a VM resource change request; the NFVO performs VM resource elastic scaling processing on the VM according to the VM resource change request. Therefore, when the VM resource elastic scaling processing is performed on the VM, the information interaction with the NFVO is greatly reduced, and the impact on the NFVO is reduced.
在一个优选的实施例中,当第一节点为虚拟化网络功能VNF时,利用第一节点的上游节点对第一节点进行VM资源弹性伸缩处理包括:VNF向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;VNFM根据第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;NFVO根据VM资源变更请求对VNF进行VM资源弹性伸缩处理。从而实现了在对VNF进行VM资源弹性伸缩处理时,极大的减少了和NFVO之间的信息交互,降低了对NFVO的冲击。In a preferred embodiment, when the first node is the virtualized network function VNF, performing the VM resource elastic scaling process on the first node by using the upstream node of the first node includes: sending the VNF to the virtualized network function management VNFM for Requesting a global resource access interface to perform a second request message for pre-applying resources; the VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; and the NFVO performs VM resource elastic scaling processing on the VNF according to the VM resource change request. Therefore, when the VM resource elastic scaling processing is performed on the VNF, the information interaction with the NFVO is greatly reduced, and the impact on the NFVO is reduced.
在一个优选的实施例中,当第一节点为虚拟化网络功能管理VNFM时,利用第一节点的上游节点对第一节点进行VM资源弹性伸缩处理包括:VNFM向网络功能虚拟化编排NFVO发送用于请求全局的资源访问接口进行预申请资源的第三请求消息;在进行预申请资源申请成功的情况下,VNFM向NFVO发送VM资源变更请求;NFVO根据VM资源变更请求对VNFM进行VM资源弹性伸缩处理。从而实现了在对VNFM进行VM资源弹性伸缩处理时,极大的减少了和NFVO之间的信息交互,降低了对NFVO的冲击。In a preferred embodiment, when the first node is a virtualized network function management VNFM, the VM node elastic scaling processing of the first node by using the upstream node of the first node includes: VNFM arranging NFVO for network function virtualization scheduling The third request message of the pre-applied resource is requested by the global resource access interface; when the pre-application resource application is successful, the VNFM sends a VM resource change request to the NFVO; and the NFVO performs the VM resource elastic expansion on the VNFM according to the VM resource change request. deal with. Therefore, when the VM resource elastic scaling processing is performed on the VNFM, the information interaction with the NFVO is greatly reduced, and the impact on the NFVO is reduced.
在本实施例中还提供了一种虚拟机VM资源弹性伸缩处理装置,该装置用于实现上述实施例及优选实施方式,已经进行过说明的不再赘述。如以下所使用的,术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现,但是硬件,或者软件和硬件的组合的实现也是可能并被构想的。 In this embodiment, a virtual machine VM resource resiliency processing device is also provided, which is used to implement the foregoing embodiments and preferred embodiments, and has not been described again. As used below, the term "module" may implement a combination of software and/or hardware of a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
图3是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置的结构框图,如图3所示,该装置包括确定模块32和处理模块34。下面对该装置进行说明。FIG. 3 is a structural block diagram of a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention. As shown in FIG. 3, the apparatus includes a determining module 32 and a processing module 34. The device will be described below.
确定模块32,位于第一节点或第一节点的相邻上游节点中,设置为根据第一节点中的VM的指标信息确定第一节点达到了进行VM资源弹性伸缩处理的预定阈值;处理模块34,位于第一节点的各个上游节点中,连接至上述确定模块32,设置为对第一节点进行VM资源弹性伸缩处理。其中,上述VM的指标信息可以包括以下信息至少之一:内存信息、中央处理器CPU信息、硬盘信息、宽带信息、VM所承载的业务指标信息、VM的处理能力。The determining module 32 is located in the first node or the adjacent upstream node of the first node, and is configured to determine, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing; and the processing module 34 And being located in each of the upstream nodes of the first node, and connected to the determining module 32, configured to perform VM resource elastic scaling processing on the first node. The indicator information of the VM may include at least one of the following information: memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
图4是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置中处理模块34的结构框图一,如图4所示,该处理模块34包括第一发送单元42、第二发送单元44、第三发送单元46和第一处理单元48。下面对该处理模块34进行说明。FIG. 4 is a structural block diagram 1 of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention. As shown in FIG. 4, the processing module 34 includes a first sending unit 42 and a second sending unit 44. The third transmitting unit 46 and the first processing unit 48. The processing module 34 will be described below.
第一发送单元42,位于VM中,设置为当第一节点为VM时,向虚拟化网络功能VNF发送用于请求进行VM资源弹性伸缩处理的第一请求消息;第二发送单元44,位于VNF中,连接至上述第一发送单元42,设置为根据第一请求消息向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;第三发送单元46,位于VNFM中,连接至上述第二发送单元44,设置为根据第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;第一处理单元48,位于NFVO中,连接至上述第三发送单元46,设置为根据VM资源变更请求对VM进行VM资源弹性伸缩处理。The first sending unit 42 is located in the VM, and is configured to send a first request message for requesting VM resource elastic scaling processing to the virtualized network function VNF when the first node is a VM; the second sending unit 44 is located at the VNF. The first sending unit 42 is configured to send, according to the first request message, a second request message for requesting the global resource access interface to pre-apply resources to the virtualized network function management VNFM; the third sending unit 46, Located in the VNFM, connected to the foregoing second sending unit 44, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the first processing unit 48, located in the NFVO, connected to the third sending unit 46. Set to perform VM resource elastic scaling processing on the VM according to the VM resource change request.
图5是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置中处理模块34的结构框图二,如图5所示,该处理模块34包括第四发送单元52、第五发送单元54、和第二处理单元56。下面对该处理模块34进行说明。5 is a structural block diagram 2 of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention. As shown in FIG. 5, the processing module 34 includes a fourth sending unit 52, a fifth sending unit 54, and Second processing unit 56. The processing module 34 will be described below.
第四发送单元52,位于虚拟化网络功能VNF中,设置为当第一节点为VNF时,利用VNF向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;第五发送单元54,位于VNFM中,连接至上述第四发送单元52,设置为根据第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;第二处理单元56,位于NFVO中,连接至上述第五发送单元54,设置为根据VM资源变更请求对VM进行VM资源弹性伸缩处理。The fourth sending unit 52 is located in the virtualized network function VNF, and is configured to use the VNF to send a second request for requesting the global resource access interface for pre-applying resources to the virtualized network function management VNFM by using the VNF. The fifth sending unit 54, located in the VNFM, is connected to the fourth sending unit 52, and configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message; the second processing unit 56 is located in the NFVO. The fifth transmitting unit 54 is connected to the fifth transmitting unit 54 and configured to perform VM resource elastic scaling processing on the VM according to the VM resource change request.
图6是根据本发明实施例的虚拟机VM资源弹性伸缩处理装置中处理模块34的结构框图三,如图6所示,该处理模块34包括第六发送单元62、第七发送单元64、和第三处理单元66。下面对该处理模块34进行说明。 FIG. 6 is a third structural block diagram of a processing module 34 in a virtual machine VM resource elastic scaling processing apparatus according to an embodiment of the present invention. As shown in FIG. 6, the processing module 34 includes a sixth sending unit 62, a seventh sending unit 64, and Third processing unit 66. The processing module 34 will be described below.
第六发送单元62,位于虚拟化网络功能管理VNFM中,设置为当第一节点为VNFM时,利用VNFM向网络功能虚拟化编排NFVO发送用于请求全局的资源访问接口进行预申请资源的第三请求消息;第七发送单元64,位于VNFM中,连接至上述第六发送单元62,设置为在进行预申请资源申请成功的情况下,向NFVO发送VM资源变更请求;第三处理单元66,位于NFVO中,连接至上述第七发送单元64,设置为根据VM资源变更请求对VM进行VM资源弹性伸缩处理。The sixth sending unit 62 is located in the virtualized network function management VNFM, and is configured to use the VNFM to send the NFVO to the network function virtualization scheduling NFVO to request the global resource access interface to perform the pre-applied resource when the first node is the VNFM. a request message, the seventh sending unit 64, located in the VNFM, connected to the sixth sending unit 62, configured to send a VM resource change request to the NFVO if the pre-application resource application is successful; the third processing unit 66 is located The NFVO is connected to the seventh transmitting unit 64, and is configured to perform VM resource elastic scaling processing on the VM according to the VM resource change request.
图7是根据本发明实施例的虚拟机VM资源弹性伸缩处理系统的结构框图,如图7所示,该虚拟机VM资源弹性伸缩处理系统72包括上述任一项的虚拟机VM资源弹性伸缩处理装置74。FIG. 7 is a structural block diagram of a virtual machine VM resource elastic scaling processing system according to an embodiment of the present invention. As shown in FIG. 7, the virtual machine VM resource elastic scaling processing system 72 includes the virtual machine VM resource elastic scaling processing of any of the above. Device 74.
为了解决相关技术中存在的对NFVO信息交互过多,冲击大的问题,在本发明实施例中还提供了一种资源按需供给和动态管理的方法,通过本发明实施例中的方法可以减轻对上游节点NFVO的冲击,有效消除单点故障,并减少消息交互,同时让采集的指标信息更加精确,从而实现了构建高效、安全可靠的弹性伸缩服务的目的。In order to solve the problem of excessive NFVO information interaction and large impact in the related art, a method for resource on-demand provisioning and dynamic management is also provided in the embodiment of the present invention, which can be mitigated by the method in the embodiment of the present invention. The impact on the upstream node NFVO effectively eliminates single points of failure, reduces message interaction, and makes the collected indicator information more accurate, thus achieving the purpose of constructing an efficient, secure and reliable elastic extension service.
在该实施例中通过使原来统一管理虚拟资源的NFVO节点下沉,通过权限下放分层管理的方式,来减小对NFVO的冲击,并提供资源管理接口给VNFM,使其也能访问预占资源、VM状态、VM已使用资源等全局虚拟资源信息,从而不用每次都通过NFVO访问。In this embodiment, the NFVO node that originally manages the virtual resource is sunk, and the NFVO impact is reduced by the privilege decentralized layer management, and the resource management interface is provided to the VNFM so that it can also access the preemption. Global virtual resource information such as resources, VM state, and VM used resources, so that it does not need to be accessed through NFVO every time.
优选实施例一当上述第一节点为VM时的VM资源弹性伸缩处理:In the first embodiment, when the first node is a VM, the VM resource elastic scaling process is performed:
最下游的VM资源创建好弹性伸缩规则后,各个VM是通过服务器负载均衡(Server Load Balancing,简称为SLB)的方式绑定在一起组成的虚拟化网络功能(Virtualised Network Function,简称为VNF),多指网元侧,相对于监控VNF层级的指标信息而言,监控VNF下每个VM的指标信息显得更为精确和及时,这里的VM监控指标主要由内存、CPU、硬盘、带宽等系统信息组成,通过每个VM自身进行实时状态监控,并由自身判断是否达到弹性伸缩条件,若是VM自身无法进行判断是否达到了弹性伸缩规则的条件,则将监控的信息数据交由上游的VNF节点进行判断。若是达到伸缩条件,则发送第一请求消息给VNF进行弹性伸缩处理,并发送请求给虚拟化网络功能管理(Virtualised Network Function Manager,简称为VNFM),当系统整体负荷较低的情况下,如果达到了缩容条件,则由VNF发送第二请求消息给VNFM,并触发弹性伸缩请求,VNFM发送VM资源请求变更消息给NFVO,通过对VM进行一系列状态迁移操作,释放VM资源,然后对VNF进行SLB处理,降低系统总体拥有成本(Total Cost of Ownership,简称为TCO);当系统整体负荷较高的情况下,如 果达到了扩容条件,则由VNF发送第二请求消息给VNFM,VNFM发送VM资源请求变更消息给NFVO,并根据VNF绑定的VM配置,通过对VM进行一系列状态迁移操作,启动相应的VM,然后对VNF进行SLB处理,以此扩展、扩大系统处理能力。After the most downstream VM resources are created with the elastic scaling rules, the VMs are bundled together by the Server Load Balancing (SLB). On the multi-finger network element side, compared with the indicator information of monitoring the VNF level, it is more accurate and timely to monitor the indicator information of each VM under the VNF. The VM monitoring indicators here mainly include system information such as memory, CPU, hard disk, and bandwidth. The real-time status monitoring is performed by each VM itself, and it is judged by itself whether or not the elastic scaling condition is reached. If the VM itself cannot determine whether the elastic scaling rule is met, the monitored information data is transferred to the upstream VNF node. Judge. If the scaling condition is reached, the first request message is sent to the VNF for elastic scaling processing, and the request is sent to the Virtualised Network Function Manager (VNFM). When the overall system load is low, if In the case of the contraction condition, the VNF sends the second request message to the VNFM, and triggers the elastic scalability request. The VNFM sends the VM resource request change message to the NFVO, performs a series of state migration operations on the VM, releases the VM resources, and then performs the VNF. SLB processing, reducing the total cost of ownership (TCO); when the overall system load is high, such as If the capacity expansion condition is reached, the VNF sends a second request message to the VNFM, and the VNFM sends a VM resource request change message to the NFVO, and according to the VM configuration bound by the VNF, the VM is started by performing a series of state transition operations on the VM. Then, SLB processing is performed on the VNF to expand and expand the system processing capability.
综上可知,NFVO配合VNFM、VNF完成VM的弹性伸缩。该过程由VM发起,VNFM收到VNF的创建请求后,计算所需修改的资源列表,向NFVO申请分配资源,完成资源的预占和分配,VNFM启动新增VM并向VNF通知完成。图8是根据本发明实施例的VM弹性伸缩过程图,如图8所示,该过程包括如下步骤:In summary, NFVO cooperates with VNFM and VNF to complete the elastic expansion and contraction of VM. The process is initiated by the VM. After receiving the VNF creation request, the VNFM calculates the resource list to be modified, allocates resources to the NFVO application, completes the resource preemption and allocation, and the VNFM starts to add the VM and notifies the VNF. FIG. 8 is a diagram of a VM elastic scaling process according to an embodiment of the present invention. As shown in FIG. 8, the process includes the following steps:
步骤S802:云数据中心平台部署完成,VM资源创建好弹性伸缩规则,虚拟网络部署完成,VM信息采集完成;Step S802: The cloud data center platform is deployed, the VM resources are created with elastic scaling rules, the virtual network deployment is completed, and the VM information collection is completed.
步骤S804:VM自身进行状态监控以及弹性判断,若VM自身无法进行判断是否达到了弹性伸缩规则的条件,则将监控的信息数据交由上游的VNF节点进行判断;Step S804: The VM itself performs state monitoring and elastic determination. If the VM itself cannot determine whether the elastic scaling rule is met, the monitored information data is submitted to the upstream VNF node for judgment;
步骤S806:若达到伸缩条件,则由VM发送第一请求消息给VNF进行弹性伸缩处理;Step S806: If the scaling condition is reached, the VM sends a first request message to the VNF for elastic scaling processing.
步骤S808:VNF发送请求对VM资源进行弹性伸缩处理的弹性伸缩请求给VNFM;Step S808: The VNF sends an elastic scaling request requesting elastic scaling processing of the VM resource to the VNFM;
步骤S810:VNFM向NFVO发送VM资源变更请求,其中,VNFM解析VNF发起的创建VM请求,请求中携带VM名称和操作、以及创建VM的个数:Step S810: The VNFM sends a VM resource change request to the NFVO, where the VNFM parses the VNF-initiated VM request request, the request carries the VM name and operation, and the number of VMs created:
如果VM已经存在,当VM处于异常状态时,直接上报错误;If the VM already exists, when the VM is in an abnormal state, the error is directly reported;
如果VM已经存在,当VM处于运行状态时,直接上报成功;If the VM already exists, the report is successfully reported when the VM is running.
如果VM已经存在,VM处于其他正常状态,则VNFM启动VM到正常运行状态,然后上报成功;If the VM already exists and the VM is in another normal state, the VNFM starts the VM to the normal running state, and then reports success;
如果VM不存在,则进入下一步;If the VM does not exist, go to the next step;
VNFM向NFVO请求全局的资源访问接口进行预申请资源,资源申请成功上报消息并进入下一步。若NFVO无应答超时,则流程终止并上报错误;如果预申请资源失败,则上报失败,流程终止;VNFM发送资源分配请求给NFVO,资源分配成功上报消息并进入下一步;若NFVO无应答超时,则流程终止并上报错误;如果资源分配失败,则上报失败,流程终止; The VNFM requests the NFVO to request the resource from the global resource access interface, and the resource application successfully reports the message and proceeds to the next step. If the NFVO has no response timeout, the process terminates and reports an error; if the pre-requested resource fails, the report fails and the process terminates; the VNFM sends a resource allocation request to the NFVO, the resource allocation successfully reports the message and proceeds to the next step; if the NFVO has no response timeout, The process is terminated and an error is reported; if the resource allocation fails, the report fails and the process terminates;
步骤S812:NFVO成功创建VM,最终使VM达到初始状态,VNFM生命周期业务向VNF发送启动创建的VM;若启动VM失败,则上报错误;VNFM上报消息返回VNF创建结果,携带操作动作和VM名称,以及每个VM的操作结果;VNF对新增VM进行SLB处理。Step S812: The NFVO successfully creates the VM, and finally causes the VM to reach the initial state. The VNFM lifecycle service sends the VM that is created and created to the VNF. If the VM fails to be sent, the error is reported; the VNFM report message returns the VNF creation result, and carries the operation action and the VM name. And the result of each VM operation; VNF performs SLB processing on the newly added VM.
优选实施例二当上述第一节点为VNF时的VM资源弹性伸缩处理Preferred Embodiment 2: VM resource elastic scaling processing when the first node is a VNF
VNF节点除了有可能需要判断下游的VM指标信息外,还需要同时判断并监控自身的指标信息,这里的监控指标主要涉及内存、CPU、硬盘、带宽等系统信息以及网元侧所承载的业务指标信息,比如每秒事务处理次数(Transactions Per Second,简称为TPS),某种业务的负荷情况等,若是VNF自身无法进行判断是否达到了弹性伸缩规则的条件,则将监控的所有信息数据交由上游的VNFM节点进行判断,若是达到伸缩条件,则由VNF进行弹性伸缩处理,并发送相关请求给VNFM,当系统整体负荷较低的情况下,如果达到了缩容条件,则发送第二请求消息给VNFM,并触发弹性伸缩请求,VNFM发送VM资源变更请求给NFVO,通过对VM进行一系列状态迁移操作,释放VM资源,然后对VNF进行SLB处理,降低系统TCO;当系统整体负荷较高的情况下,如果达到了扩容条件,则发送第二请求消息给VNFM,VNFM然后发送VM资源变更请求给NFVO,并根据VNF绑定的VM配置,通过对VM进行一系列状态迁移操作,启动相应的VM,然后对VNF进行SLB处理,以此扩展、扩大系统处理能力。In addition to the possibility of determining the downstream VM index information, the VNF node needs to simultaneously judge and monitor its own indicator information. The monitoring indicators here mainly involve system information such as memory, CPU, hard disk, and bandwidth, and service indicators carried by the NE side. Information, such as the number of transactions per second (Transactions Per Second, TPS for short), the load situation of a certain service, etc. If the VNF itself cannot judge whether the elastic scaling rule is met, all the information data monitored is handed over to The upstream VNFM node performs the judgment. If the scaling condition is reached, the VNF performs elastic scaling processing and sends a related request to the VNFM. When the overall system load is low, if the shrinking condition is reached, the second request message is sent. To the VNFM, and trigger the elastic scaling request, the VNFM sends a VM resource change request to the NFVO, performs a series of state migration operations on the VM, releases the VM resources, and then performs SLB processing on the VNF to reduce the system TCO; when the overall system load is high In the case that the capacity expansion condition is reached, the second request message is sent to the VNFM, VN. The FM then sends a VM resource change request to the NFVO, and according to the VM configuration bound by the VNF, the VM is subjected to a series of state transition operations, the corresponding VM is started, and then the VNF is processed by the VNF, thereby expanding and expanding the system processing capability.
由上述可知,NFVO配合VNFM完成VM的弹性伸缩。该过程由VM发起,VNFM收到VNF的创建请求后,计算所需修改的资源列表,向NFVO申请分配资源,完成资源的预占和分配,VNFM启动新增VM并向VNF通知完成。图9是根据本发明实施例的VNF弹性收缩过程图,如图9所示,该过程包括如下步骤:It can be seen from the above that NFVO cooperates with VNFM to complete the elastic expansion and contraction of the VM. The process is initiated by the VM. After receiving the VNF creation request, the VNFM calculates the resource list to be modified, allocates resources to the NFVO application, completes the resource preemption and allocation, and the VNFM starts to add the VM and notifies the VNF. 9 is a diagram showing a VNF elastic contraction process according to an embodiment of the present invention. As shown in FIG. 9, the process includes the following steps:
步骤S902:云数据中心平台部署完成,VNF资源创建好弹性伸缩规则,虚拟网络部署完成,VNF信息采集完成;Step S902: The cloud data center platform is deployed, the VNF resource is created with elastic scaling rules, the virtual network deployment is completed, and the VNF information collection is completed.
步骤S904:VNF自身弹性判断,若VNF自身无法进行判断是否达到了弹性伸缩规则的条件,则将监控的信息数据交由上游的VNFM节点进行判断;Step S904: The VNF itself determines whether the VNF itself cannot determine whether the elastic scaling rule is met, and then the monitored information data is sent to the upstream VNFM node for judgment;
步骤S906:若达到伸缩条件,则由VNF发送请求进行VM资源弹性伸缩处理的弹性伸缩处理消息给VNFM;Step S906: If the scaling condition is reached, the VNF sends an elastic scaling processing message requesting the VM resource elastic scaling processing to the VNFM;
步骤S908:VNFM解析VNF发起的创建VM请求,请求中携带VM名称和操作、以及创建VM的个数: Step S908: The VNFM parses the VNF-created VM request, and the request carries the VM name and operation, and the number of VMs created:
如果VM已经存在,当VM处于异常状态时,直接上报错误;If the VM already exists, when the VM is in an abnormal state, the error is directly reported;
如果VM已经存在,当VM处于运行状态时,直接上报成功;If the VM already exists, the report is successfully reported when the VM is running.
如果VM已经存在,VM处于其他正常状态,则VNFM启动VM到正常运行状态,然后上报成功;If the VM already exists and the VM is in another normal state, the VNFM starts the VM to the normal running state, and then reports success;
如果VM不存在,则进入下一步;If the VM does not exist, go to the next step;
VNFM向NFVO发送第二请求消息,请求全局的资源访问接口进行预申请资源,资源申请成功上报消息并进入下一步;若NFVO无应答超时,则流程终止并上报错误;如果预申请资源失败,则上报失败,流程终止;The VNFM sends a second request message to the NFVO, requesting the global resource access interface to pre-apply the resource, and the resource application successfully reports the message and proceeds to the next step; if the NFVO has no response timeout, the process terminates and reports an error; if the pre-application resource fails, The report failed and the process was terminated.
VNFM发送VM资源变更请求给NFVO,资源分配成功上报消息并进入下一步。若NFVO无应答超时,则流程终止并上报错误;如果资源分配失败,则上报失败,流程终止;The VNFM sends a VM resource change request to the NFVO, and the resource allocation successfully reports the message and proceeds to the next step. If the NFVO has no response timeout, the process terminates and an error is reported; if the resource allocation fails, the report fails and the process terminates;
步骤S910:NFVO成功创建VM,最终使VM达到初始状态,VNFM生命周期业务向VNF发送启动创建的VM;若启动VM失败,则上报错误;VNFM上报消息返回VNF创建结果,携带操作动作和VM名称,以及每个VM的操作结果;VNF对新增VM进行SLB处理。Step S910: The NFVO successfully creates the VM, and finally causes the VM to reach the initial state. The VNFM lifecycle service sends the VM that is created and created to the VNF. If the VM fails to be sent, the error is reported; the VNFM report message returns the VNF creation result, and carries the operation action and the VM name. And the result of each VM operation; VNF performs SLB processing on the newly added VM.
优选实施例三当上述第一节点为VNFM时的VM资源弹性伸缩处理:In the third embodiment, when the first node is a VNFM, the VM resource elastic scaling process is performed:
VNFM节点除了有可能需要判断下游的VNF指标信息外,还需要同时判断并监控自身的指标信息,这里的监控指标主要涉及内存、CPU、硬盘、带宽等系统信息以及网元处理能力,若是达到伸缩条件,则进行弹性伸缩处理,当系统整体负荷较低的情况下,如果达到了缩容条件,则触发弹性伸缩请求,发送VM资源请求变更消息给NFVO,通过对VM进行一系列状态迁移操作,释放VM资源,然后对VNFM进行SLB处理,降低系统TCO;当系统整体负荷较高的情况下,如果达到了扩容条件,则触发弹性伸缩请求,发送资源请求变更消息给NFVO,并根据VNFM绑定的VM配置,通过对VM进行一系列状态迁移操作,启动相应的VM,然后对VNFM进行SLB处理,以此扩展、扩大系统处理能力。In addition to the possibility of judging the downstream VNF indicator information, the VNFM node needs to simultaneously judge and monitor its own indicator information. The monitoring indicators here mainly involve system information such as memory, CPU, hard disk, bandwidth, and network element processing capability. If the condition is low, if the overall load is low, if the shrinkage condition is reached, the elastic scalability request is triggered, and the VM resource request change message is sent to the NFVO, and a series of state transition operations are performed on the VM. The VM resource is released, and then the SLB processing is performed on the VNFM to reduce the system TCO. When the overall load of the system is high, if the expansion condition is reached, the elastic scalability request is triggered, the resource request change message is sent to the NFVO, and the VNFM is bound according to the VNFM. The VM configuration expands and expands the system processing capability by performing a series of state migration operations on the VM, starting the corresponding VM, and then performing SLB processing on the VNFM.
综上可知,NFVO配合完成VNFM的弹性伸缩。该过程由VM发起,VNFM收到VNF的创建请求后,计算所需修改的资源列表,向NFVO申请分配资源,完成资源的预占和分配,VNFM启动新增VM并向VNF通知完成。图10是根据本发明实施例的VNFM弹性伸缩过程图,如图10所示,该过程包括如下步骤: In summary, NFVO cooperates to complete the elastic expansion of VNFM. The process is initiated by the VM. After receiving the VNF creation request, the VNFM calculates the resource list to be modified, allocates resources to the NFVO application, completes the resource preemption and allocation, and the VNFM starts to add the VM and notifies the VNF. FIG. 10 is a schematic diagram of a VNFM elastic stretching process according to an embodiment of the present invention. As shown in FIG. 10, the process includes the following steps:
步骤S1002:云数据中心平台部署完成,VNFM资源创建好弹性伸缩规则,虚拟网络部署完成,VNFM信息采集完成;Step S1002: The cloud data center platform is deployed, the VNFM resource is created with elastic scaling rules, the virtual network deployment is completed, and the VNFM information collection is completed.
步骤S1004:VNFM自身弹性判断,若VNFM自身无法进行判断是否达到了弹性伸缩规则的条件,则将监控的信息数据交由上游的NFVO节点进行判断;若达到伸缩条件,则由VNFM发送用于请求进行VM资源弹性伸缩处理的弹性伸缩处理消息给NFVO;Step S1004: The VNFM itself judges flexibly. If the VNFM cannot judge whether the elastic scaling rule is met, the monitored information data is sent to the upstream NFVO node for determination; if the scaling condition is reached, the VNFM sends the request for the request. Performing an elastic scaling processing message of the VM resource elastic scaling process to the NFVO;
步骤S1006:VNFM解析自身发起的创建VM请求,请求中携带VM名称和操作、以及创建VM的个数:Step S1006: The VNFM parses the VM creation request initiated by itself, and the request carries the VM name and operation, and the number of VMs created:
如果VM已经存在,当VM处于异常状态时,直接上报错误;If the VM already exists, when the VM is in an abnormal state, the error is directly reported;
如果VM已经存在,当VM处于运行状态时,直接上报成功;If the VM already exists, the report is successfully reported when the VM is running.
如果VM已经存在,VM处于其他正常状态,则VNFM启动VM到正常运行状态,然后上报成功;If the VM already exists and the VM is in another normal state, the VNFM starts the VM to the normal running state, and then reports success;
如果VM不存在,则进入下一步;If the VM does not exist, go to the next step;
VNFM向NFVO发送第三请求消息,请求全局的资源访问接口进行预申请资源,资源申请成功上报消息并进入下一步;若NFVO无应答超时,则流程终止并上报错误;如果预申请资源失败,则上报失败,流程终止;VNFM发送VM资源变更请求给NFVO,资源分配成功上报消息并进入下一步;若NFVO无应答超时,则流程终止并上报错误;如果资源分配失败,则上报失败,流程终止;The VNFM sends a third request message to the NFVO, requesting the global resource access interface to pre-apply the resource, and the resource application successfully reports the message and proceeds to the next step; if the NFVO has no response timeout, the process terminates and reports an error; if the pre-application resource fails, If the resource fails to be sent, the process is terminated and the error is reported.
步骤S1008:NFVO成功创建VM,上报消息返回VNFM创建结果,携带操作动作和VM名称,以及每个VM的操作结果;VNFM对新增VM进行SLB处理。Step S1008: The NFVO successfully creates the VM, and the report message returns the VNFM creation result, carries the operation action and the VM name, and the operation result of each VM; the VNFM performs SLB processing on the newly added VM.
在上述各实施例中,各个层级的VM通过自身及上游节点的实时监控及弹性伸缩判断,尽量减少各层级的频繁实时信息交互,更加精确的实时检查并监控VM状态指标,检查如果达到弹性伸缩的条件,触发弹性伸缩动作,对VM自动进行状态迁移,调整VM的状态,通过云数据中心操作内存、CPU、硬盘、带宽等VM资源,达到扩展网元能力或者降低TCO。In each of the above embodiments, the VMs of each level judge the frequent real-time information interaction of each level by real-time monitoring and elastic scalability of the own and the upstream nodes, and more accurately check and monitor the VM status indicators in real time, and check if the elastic state is achieved. The condition triggers the elastic scaling action, automatically performs state transition on the VM, adjusts the state of the VM, and operates VM resources such as memory, CPU, hard disk, and bandwidth through the cloud data center to achieve extended network element capability or lower TCO.
相对于相关技术,本发明实施例中提出的电信设备虚拟化技术下的弹性伸缩状态迁移方法,不仅能减轻对上游的冲击,还能有效消除单点故障,减少消息交互,同时让采集的指标信息更加精确,在提升弹性伸缩服务安全性的同时,而且能降低设备资 源的使用成本,而且可以得到各种定制化的服务,包括虚拟服务动态迁移、VM按需分配。进而实现了更加安全、可靠、灵活、高效的信息运作的目的。Compared with the related art, the elastic extension state migration method under the telecommunication device virtualization technology proposed in the embodiment of the present invention can not only mitigate the impact on the upstream, but also effectively eliminate single point failure, reduce message interaction, and allow the collected indicators. More accurate information, while improving the security of flexible telescopic services, and reducing equipment resources The cost of the source, and a variety of customized services, including virtual service dynamic migration, VM on-demand allocation. In turn, the goal of safer, more reliable, flexible, and efficient information operation is achieved.
显然,本领域的技术人员应该明白,上述的本发明的各模块或各步骤可以用通用的计算装置来实现,它们可以集中在单个的计算装置上,或者分布在多个计算装置所组成的网络上,可选地,它们可以用计算装置可执行的程序代码来实现,从而,可以将它们存储在存储装置中由计算装置来执行,并且在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤,或者将它们分别制作成各个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样,本发明不限制于任何特定的硬件和软件结合。It will be apparent to those skilled in the art that the various modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein. The steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module. Thus, the invention is not limited to any specific combination of hardware and software.
以上所述仅为本发明的优选实施例而已,并不用于限制本发明,对于本领域的技术人员来说,本发明可以有各种更改和变化。凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。The above description is only the preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes can be made to the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention.
工业实用性Industrial applicability
如上所述,通过上述实施例及优选实施方式,解决了相关技术中存在的对NFVO信息交互过多,冲击大的问题,进而达到了减少与NFVO的信息交互,降低对该NFVO的冲击的效果。 As described above, the above embodiments and preferred embodiments solve the problem of excessive interaction and large impact on the NFVO information in the related art, thereby achieving the effect of reducing the information interaction with the NFVO and reducing the impact on the NFVO. .

Claims (10)

  1. 一种虚拟机VM资源弹性伸缩处理方法,包括:A virtual machine VM resource elastic scaling processing method includes:
    由第一节点或第一节点的相邻上游节点根据所述第一节点中的VM的指标信息确定所述第一节点达到了进行VM资源弹性伸缩处理的预定阈值;Determining, by the first node or the adjacent upstream node of the first node, that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing according to the indicator information of the VM in the first node;
    利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理。Performing the VM resource elastic scaling process on the first node by using an upstream node of the first node.
  2. 根据权利要求1所述的方法,其中,所述VM的指标信息包括以下信息至少之一:The method of claim 1, wherein the indicator information of the VM comprises at least one of the following information:
    内存信息、中央处理器CPU信息、硬盘信息、宽带信息、所述VM所承载的业务指标信息、所述VM的处理能力。Memory information, central processor CPU information, hard disk information, broadband information, service indicator information carried by the VM, and processing capability of the VM.
  3. 根据权利要求1所述的方法,其中,当所述第一节点为VM时,利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理包括:The method according to claim 1, wherein when the first node is a VM, performing the VM resource elastic scaling process on the first node by using an upstream node of the first node comprises:
    所述VM向虚拟化网络功能VNF发送用于请求进行所述VM资源弹性伸缩处理的第一请求消息;Sending, by the VM, a first request message for requesting the VM resource elastic scaling process to the virtualized network function VNF;
    所述VNF根据所述第一请求消息向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;Transmitting, by the VNF, the second request message for requesting the global resource access interface to pre-apply resources according to the first request message to the virtualized network function management VNFM;
    所述VNFM根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;The VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message;
    所述NFVO根据所述VM资源变更请求对所述VM进行所述VM资源弹性伸缩处理。The NFVO performs the VM resource elastic scaling process on the VM according to the VM resource change request.
  4. 根据权利要求1所述的方法,其中,当所述第一节点为虚拟化网络功能VNF时,利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理包括:The method according to claim 1, wherein when the first node is a virtualized network function VNF, performing the VM resource elastic scaling process on the first node by using an upstream node of the first node comprises:
    所述VNF向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;Transmitting, by the VNF, a second request message for requesting a global resource access interface to pre-apply resources to the virtualized network function management VNFM;
    所述VNFM根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求; The VNFM sends a VM resource change request to the network function virtualization orchestration NFVO according to the second request message;
    所述NFVO根据所述VM资源变更请求对所述VNF进行所述VM资源弹性伸缩处理。The NFVO performs the VM resource elastic scaling process on the VNF according to the VM resource change request.
  5. 根据权利要求1所述的方法,其中,当所述第一节点为虚拟化网络功能管理VNFM时,利用所述第一节点的上游节点对所述第一节点进行所述VM资源弹性伸缩处理包括:The method according to claim 1, wherein when the first node is a virtualized network function management VNFM, performing the VM resource elastic scaling process on the first node by using an upstream node of the first node includes: :
    所述VNFM向网络功能虚拟化编排NFVO发送用于请求全局的资源访问接口进行预申请资源的第三请求消息;The VNFM sends a third request message for requesting a global resource access interface to pre-apply resources to the network function virtualization orchestration NFVO;
    在进行所述预申请资源申请成功的情况下,所述VNFM向所述NFVO发送VM资源变更请求;And when the pre-application resource application is successful, the VNFM sends a VM resource change request to the NFVO;
    所述NFVO根据所述VM资源变更请求对所述VNFM进行所述VM资源弹性伸缩处理。The NFVO performs the VM resource elastic scaling process on the VNFM according to the VM resource change request.
  6. 一种虚拟机VM资源弹性伸缩处理装置,包括:A virtual machine VM resource elastic scaling processing device includes:
    确定模块,位于第一节点或第一节点的相邻上游节点中,设置为根据所述第一节点中的VM的指标信息确定所述第一节点达到了进行VM资源弹性伸缩处理的预定阈值;a determining module, located in the first node or the adjacent upstream node of the first node, configured to determine, according to the indicator information of the VM in the first node, that the first node reaches a predetermined threshold for performing VM resource elastic scaling processing;
    处理模块,位于所述第一节点的各个上游节点中,设置为对所述第一节点进行所述VM资源弹性伸缩处理。The processing module is located in each of the upstream nodes of the first node, and is configured to perform the VM resource elastic scaling process on the first node.
  7. 根据权利要求6所述的装置,其中,所述处理模块包括:The apparatus of claim 6 wherein said processing module comprises:
    第一发送单元,位于VM中,设置为当所述第一节点为所述VM时,向虚拟化网络功能VNF发送用于请求进行所述VM资源弹性伸缩处理的第一请求消息;The first sending unit is located in the VM, and is configured to send, when the first node is the VM, a first request message for requesting the VM resource elastic scaling process to the virtualized network function VNF;
    第二发送单元,位于所述VNF中,设置为根据所述第一请求消息向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;a second sending unit, located in the VNF, configured to send, according to the first request message, a second request message for requesting a global resource access interface to pre-apply resources to the virtualized network function management VNFM;
    第三发送单元,位于所述VNFM中,设置为根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;a third sending unit, located in the VNFM, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message;
    第一处理单元,位于所述NFVO中,设置为根据所述VM资源变更请求对所述VM进行所述VM资源弹性伸缩处理。The first processing unit, located in the NFVO, is configured to perform the VM resource elastic scaling process on the VM according to the VM resource change request.
  8. 根据权利要求6所述的装置,其中,所述处理模块包括: The apparatus of claim 6 wherein said processing module comprises:
    第四发送单元,位于虚拟化网络功能VNF中,设置为当所述第一节点为所述VNF时,利用所述VNF向虚拟化网络功能管理VNFM发送用于请求全局的资源访问接口进行预申请资源的第二请求消息;The fourth sending unit is located in the virtualized network function VNF, and is configured to use the VNF to send a request for requesting a global resource access interface for pre-application to the virtualized network function management VNFM when the first node is the VNF. a second request message of the resource;
    第五发送单元,位于所述VNFM中,设置为根据所述第二请求消息向网络功能虚拟化编排NFVO发送VM资源变更请求;a fifth sending unit, located in the VNFM, configured to send a VM resource change request to the network function virtualization orchestration NFVO according to the second request message;
    第二处理单元,位于所述NFVO中,设置为根据所述VM资源变更请求对所述VNF进行所述VM资源弹性伸缩处理。The second processing unit is located in the NFVO, and is configured to perform the VM resource elastic scaling process on the VNF according to the VM resource change request.
  9. 根据权利要求6所述的装置,其中,所述处理模块包括:The apparatus of claim 6 wherein said processing module comprises:
    第六发送单元,位于虚拟化网络功能管理VNFM中,设置为当所述第一节点为所述VNFM时,利用所述VNFM向网络功能虚拟化编排NFVO发送用于请求全局的资源访问接口进行预申请资源的第三请求消息;The sixth sending unit is located in the virtualized network function management VNFM, and is configured to use the VNFM to send a NFVO to the network function virtualization to request a global resource access interface for pre-processing when the first node is the VNFM. Third request message for applying for resources;
    第七发送单元,位于所述VNFM中,设置为在进行所述预申请资源申请成功的情况下,向所述NFVO发送VM资源变更请求;a seventh sending unit, located in the VNFM, configured to send a VM resource change request to the NFVO if the pre-application resource application is successful;
    第三处理单元,位于所述NFVO中,设置为根据所述VM资源变更请求对所述VNFM进行所述VM资源弹性伸缩处理。The third processing unit, located in the NFVO, is configured to perform the VM resource elastic scaling process on the VNFM according to the VM resource change request.
  10. 一种虚拟机VM资源弹性伸缩处理系统,包括权利要求6至9中任一项所述的装置。 A virtual machine VM resource elastic scaling processing system, comprising the apparatus of any one of claims 6 to 9.
PCT/CN2015/073964 2014-10-17 2015-03-10 Elastic virtual machine (vm) resource scaling method, apparatus and system WO2016058318A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410555238.0 2014-10-17
CN201410555238.0A CN105577414A (en) 2014-10-17 2014-10-17 Elastically telescopic processing method, device and system for VM (Virtual Machine) resources

Publications (1)

Publication Number Publication Date
WO2016058318A1 true WO2016058318A1 (en) 2016-04-21

Family

ID=55746044

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/073964 WO2016058318A1 (en) 2014-10-17 2015-03-10 Elastic virtual machine (vm) resource scaling method, apparatus and system

Country Status (2)

Country Link
CN (1) CN105577414A (en)
WO (1) WO2016058318A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10826789B2 (en) 2018-12-27 2020-11-03 At&T Intellectual Property I, L.P. Adjusting triggers for automatic scaling of virtual network functions
CN112291078A (en) * 2020-09-11 2021-01-29 苏州浪潮智能科技有限公司 Subnet network resource management method and system based on virtualization platform
US11388109B2 (en) 2019-12-05 2022-07-12 At&T Intellectual Property I, L.P. Hierarchical capacity management in a virtualization environment
CN114785793A (en) * 2022-03-15 2022-07-22 浪潮云信息技术股份公司 Elastic expansion load balancing method and system

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170373938A1 (en) * 2016-06-27 2017-12-28 Alcatel-Lucent Usa Inc. Predictive auto-scaling of virtualized network functions for a network
WO2018000129A1 (en) * 2016-06-27 2018-01-04 华为技术有限公司 Policy management method, and nfv entity
CN107770067B (en) * 2016-08-23 2021-05-11 中兴通讯股份有限公司 Message sending method and device
CN106534307B (en) * 2016-11-14 2019-07-16 青岛银行股份有限公司 Cloud environment elastic load equalization methods based on load balancing dynamic configuration plug-in unit
CN108632049B (en) * 2017-03-15 2020-08-25 华为机器有限公司 Method and device for virtual network function expansion
CN111352767B (en) * 2018-12-24 2023-07-18 中国电信股份有限公司 Network function virtualization platform resource management method, backup platform and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101488098A (en) * 2009-02-13 2009-07-22 华中科技大学 Multi-core computing resource management system based on virtual computing technology
CN102646062A (en) * 2012-03-20 2012-08-22 广东电子工业研究院有限公司 Flexible capacity enlargement method for cloud computing platform based application clusters
US20130047158A1 (en) * 2011-08-16 2013-02-21 Esds Software Solution Pvt. Ltd. Method and System for Real Time Detection of Resource Requirement and Automatic Adjustments
CN103678251A (en) * 2013-11-30 2014-03-26 成都天志大行信息科技有限公司 Automatic information management system
CN104050045A (en) * 2014-06-27 2014-09-17 华为技术有限公司 Method and device for distributing virtual resources based on disk IO

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103248659B (en) * 2012-02-13 2016-04-20 北京华胜天成科技股份有限公司 A kind of cloud computing resource scheduling method and system
US8856339B2 (en) * 2012-04-04 2014-10-07 Cisco Technology, Inc. Automatically scaled network overlay with heuristic monitoring in a hybrid cloud environment
CN103716406A (en) * 2013-12-27 2014-04-09 汉柏科技有限公司 Method and system for improving operation resource of cloud computing network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101488098A (en) * 2009-02-13 2009-07-22 华中科技大学 Multi-core computing resource management system based on virtual computing technology
US20130047158A1 (en) * 2011-08-16 2013-02-21 Esds Software Solution Pvt. Ltd. Method and System for Real Time Detection of Resource Requirement and Automatic Adjustments
CN102646062A (en) * 2012-03-20 2012-08-22 广东电子工业研究院有限公司 Flexible capacity enlargement method for cloud computing platform based application clusters
CN103678251A (en) * 2013-11-30 2014-03-26 成都天志大行信息科技有限公司 Automatic information management system
CN104050045A (en) * 2014-06-27 2014-09-17 华为技术有限公司 Method and device for distributing virtual resources based on disk IO

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10826789B2 (en) 2018-12-27 2020-11-03 At&T Intellectual Property I, L.P. Adjusting triggers for automatic scaling of virtual network functions
US11356336B2 (en) 2018-12-27 2022-06-07 At&T Intellectual Property I, L.P. Adjusting triggers for automatic scaling of virtual network functions
US11671332B2 (en) 2018-12-27 2023-06-06 At&T Intellectual Property I, L.P. Adjusting triggers for automatic scaling of virtual network functions
US11388109B2 (en) 2019-12-05 2022-07-12 At&T Intellectual Property I, L.P. Hierarchical capacity management in a virtualization environment
CN112291078A (en) * 2020-09-11 2021-01-29 苏州浪潮智能科技有限公司 Subnet network resource management method and system based on virtualization platform
CN112291078B (en) * 2020-09-11 2022-12-27 苏州浪潮智能科技有限公司 Subnet network resource management method and system based on virtualization platform
CN114785793A (en) * 2022-03-15 2022-07-22 浪潮云信息技术股份公司 Elastic expansion load balancing method and system

Also Published As

Publication number Publication date
CN105577414A (en) 2016-05-11

Similar Documents

Publication Publication Date Title
WO2016058318A1 (en) Elastic virtual machine (vm) resource scaling method, apparatus and system
US10708149B2 (en) Context-aware virtualized control decision support system for providing quality of experience assurance for internet protocol streaming video services
US11301342B2 (en) Methods, systems, and computer readable storage devices for managing faults in a virtual machine network
CN108039964B (en) Fault processing method, device and system based on network function virtualization
US20190081879A1 (en) Auto-Scaling Software-Defined Monitoring Platform for Software-Defined Networking Service Assurance
US8856339B2 (en) Automatically scaled network overlay with heuristic monitoring in a hybrid cloud environment
CN108429631B (en) Method and device for instantiating network service
CN110677305B (en) Automatic scaling method and system in cloud computing environment
US20170046204A1 (en) Application Scaling Management Method and Apparatus
US10990435B2 (en) Virtual redundancy for active-standby cloud applications
TW201535266A (en) Resource adjustment methods and systems for virtual machines
US10642640B2 (en) Data-driven feedback control system for real-time application support in virtualized networks
CN106134141A (en) A kind of method and device updating network service describer NSD
CN105991458B (en) Load balancing method and load balancing device
CN109074280B (en) Network function virtualization
US20160048407A1 (en) Flow migration between virtual network appliances in a cloud computing network
CN112948063B (en) Cloud platform creation method and device, cloud platform and cloud platform implementation system
US20160203030A1 (en) Load calculation method, load calculation program, and load calculation apparatus
WO2016155291A1 (en) Method and apparatus for managing virtualized network function scaling
WO2018166366A1 (en) Method and device for volume expansion of virtual network function
CN106959885A (en) A kind of virtual machine High Availabitity realizes system and its implementation
WO2015117458A1 (en) Fault information collection method, device and system
CN115827148A (en) Resource management method and device, electronic equipment and storage medium
US11571618B1 (en) Multi-region game server fleets
CN113872997B (en) Container group POD reconstruction method based on container cluster service and related equipment

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: 15851365

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: 15851365

Country of ref document: EP

Kind code of ref document: A1