CN105183588A - Rebuilding method and device of virtual machines - Google Patents
Rebuilding method and device of virtual machines Download PDFInfo
- Publication number
- CN105183588A CN105183588A CN201510642333.9A CN201510642333A CN105183588A CN 105183588 A CN105183588 A CN 105183588A CN 201510642333 A CN201510642333 A CN 201510642333A CN 105183588 A CN105183588 A CN 105183588A
- Authority
- CN
- China
- Prior art keywords
- cluster
- vim
- virtual machine
- server
- business cluster
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Abstract
The embodiment of the invention discloses a rebuilding method of virtual machines. The method comprises the steps that when a VIM detects that a source server in a service cluster breaks down, m virtual machines deployed by the source server are determined; the VIM rebuilds the m virtual machines in the service cluster; if rebuilding of the m virtual machines fails, the VIM searches for a redundant cluster associated with the service cluster; the VIM schedules n servers from the redundant cluster to the service cluster and rebuilds the m virtual machines again in the service cluster; or VIM schedules the m servers to the redundant cluster and rebuilds the m virtual machines again in the redundant cluster, wherein n is an integer larger than 1. The embodiment of the invention further discloses a rebuilding device of the virtual machine. By the adoption of the rebuilding method and device, the utilization rate of resources in the clusters can be improved.
Description
Technical field
The present invention relates to computer realm, particularly relate to a kind of method for reconstructing and device of virtual machine.
Background technology
In order to reduce operator's cost of telecom operators, propose the scheme of telecom cloud, such as NFV, NFV pass through the IT Intel Virtualization Technology of standard, in network equipment unification to the high-performance and jumbo server, switch and storage platform of industrialized standard.The network architecture of NFV is: nethermost is hardware resource (Hardwareresources), hardware resource is virtualization layer (VirtualizationLayer), for providing virtual computational resource, storage resources and Internet resources to network element, hardware resource and virtual machine layer are referred to as NFVI.NFVI is upper can support various virtual network function (VNF), by software simulating, is above EMS, EMS be OSS above VNF.VIM (VirtualizedInfrastructureManager, Virtual base infrastructure manager, be called for short VIM) for managing NFVI, VNFM (VirtualNetworkFunctionManager on it, virtual network function manager, be called for short VNFM) be used for the various Internet resources of layout for managing Orchestrator on various VNF, VNF, form a network.VIM, VNFM and VIM are referred to as MANO (ManagementandOrchestration)
Be the cluster of granularity with server by hardware resource division in the framework of cloud computing, the physical isolation of the hardware resource between different clusters.When finding the server failure in certain cluster, cloud management platform will move to the VM in failed server on other servers in this cluster, to improve virtual machine reliability of operation.But due to the difference that the hardware resource of different clusters distributes, the method Problems existing of this virtual machine (vm) migration is that the hardware resource in each cluster cannot be fully utilized.
Summary of the invention
Embodiment of the present invention technical matters to be solved is, provides a kind of method for reconstructing and device of virtual machine.The problem that the resource utilization of each cluster in prior art is not high can be solved.
In order to solve the problems of the technologies described above, embodiments provide a kind of method for reconstructing of virtual machine, comprising:
When the source server that VIM detects in business cluster breaks down, determine m the virtual machine that described source server is disposed;
Described VIM rebuilds a described m virtual machine in described business cluster;
If the idling-resource deficiency of described business cluster causes the reconstruction failure of a described m virtual machine, described VIM inquires about the redundant cluster associated with described business cluster;
Described VIM dispatches n server to described business cluster from described redundant cluster, and again rebuilds a described m virtual machine in described business cluster; Or
A described m scheduling virtual machine in described redundant cluster, and is again rebuild a described m virtual machine by described VIM in described redundant cluster; Wherein, n be greater than 1 integer.
In conjunction with first aspect, in the implementation that the first is possible, described VIM dispatches n server to described business cluster from described redundant cluster, and again rebuild a described m virtual machine in described business cluster after, also comprises:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM indicates described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described redundant cluster by described VIM; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described redundant cluster by described VIM.
In conjunction with first aspect, in the implementation that the second is possible, a described m scheduling virtual machine in described redundant cluster, and again rebuild a described m virtual machine in described redundant cluster after, also to comprise by described VIM:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM is by a described m scheduling virtual machine to described source server or on new server.
In conjunction with first aspect to any one in the possible implementation of the second of first aspect, in the implementation that the third is possible, when the described source server detected in business cluster as VIM breaks down, before determining m the virtual machine that described source server is disposed, also comprise:
Described business cluster and described redundant cluster are bound by the bind request that described VIM sends according to described VNFM, and preserve the incidence relation of described business cluster and described redundant cluster;
Described VIM returns the feedback message representing binding success to described VNFM.
In conjunction with first aspect, in the 4th kind of possible implementation, described redundant cluster comprises the business cluster being deployed with virtual machine or the cluster not disposing virtual machine.
Embodiment of the present invention second aspect provides a kind of method for reconstructing of virtual machine, comprising:
When the source server that VIM detects in the first business cluster breaks down, send fault notification message to VNFM;
According to described fault notification message, described VNFM determines that described source server breaks down, and determine m the virtual machine that described source server is disposed;
Described VNFM rebuilds a described m virtual machine in described first business cluster, sends reconstructed results to described VIM;
If the idling-resource deficiency of described first business cluster causes described m virtual machine reconstruction failure, described VIM inquires about the second business cluster associated with described first business cluster;
Described VIM indicates described VNFM to rebuild a described m virtual machine in described second business cluster; Or
Described VIM dispatches n server to described first business cluster from described second business cluster, and indicates described VNFM again in described second business cluster, to rebuild a described m virtual machine.
In conjunction with second aspect, in the implementation that the first is possible, described VIM indicates after described VNFM rebuilds a described m virtual machine in described second business cluster, also comprises:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM indicates described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described second business cluster by described VIM; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described second business cluster by described VIM.
In conjunction with second aspect, in the implementation that the second is possible, when the described source server detected in the first business cluster as VIM breaks down, before sending failure message to VNFM, also comprise:
Described first business cluster and the second cluster are bound by the bind request that described VIM sends according to described VNFM, and preserve the incidence relation of described first business cluster and described second cluster;
Described VIM returns the feedback message representing binding success to described VNFM.
The embodiment of the present invention third aspect provides a kind of device of virtual machine, and described device comprises VIM, and described VIM comprises:
Determination module, for when detecting that the source server in business cluster breaks down, determines m the virtual machine that described source server is disposed;
First rebuilds module, for rebuilding a described m virtual machine in described business cluster;
Enquiry module, if be unsuccessfully for the reconstructed results of a described m virtual machine, inquires about the redundant cluster associated with described business cluster;
Second rebuilds module, for dispatching n server to described business cluster from described redundant cluster, and again rebuilds a described m virtual machine in described business cluster; Or
By a described m scheduling virtual machine in described redundant cluster, and in described redundant cluster, again rebuild a described m virtual machine; Wherein, n be greater than 1 integer.
In conjunction with the third aspect, in the implementation that the first is possible, described VIM also comprises:
First recovers module, if for detecting that described source server recovers normal or is replaced by new server, indicate described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described redundant cluster; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described redundant cluster by described VIM.
In conjunction with the third aspect, in the implementation that the second is possible, described VIM also comprises:
Second recovers module, if for detecting that described source server recovers normal or is replaced by new server, described VIM is by a described m scheduling virtual machine to described source server or on new server.
In conjunction with the third aspect to any one in the possible implementation of the second, in the implementation that the third is possible, described VIM also comprises:
Binding module, binds described business cluster and described redundant cluster for the bind request sent according to described VNFM, and preserves the incidence relation of described business cluster and described redundant cluster; The feedback message representing binding success is returned to described VNFM.
Embodiment of the present invention fourth aspect provides a kind of reconstructing device of virtual machine, and described reconstructing device comprises VIM and VNFM, wherein,
When the source server that described VIM detects in the first business cluster breaks down, send fault notification message to described VNFM;
According to described fault notification message, described VNFM determines that described source server breaks down, and determine m the virtual machine that described source server is disposed;
Described VNFM rebuilds a described m virtual machine in described first business cluster, sends reconstructed results to described VIM;
If the idling-resource deficiency of described first business cluster causes described m virtual machine reconstruction failure, described VIM inquires about the second business cluster associated with described first business cluster;
Described VIM indicates described VNFM to rebuild a described m virtual machine in described second business cluster; Or
Described VIM dispatches n server to described first business cluster from described second business cluster, and indicates described VNFM again in described second business cluster, to rebuild a described m virtual machine.
In conjunction with fourth aspect, in the implementation that the first is possible, described VIM also for:
If detect, described source server recovers normal or is replaced by new server, indicate described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described second business cluster by described VIM; Or
If detect, described source server recovers normal or is replaced by new server, described source server or described new server scheduling is returned in described second business cluster.
In conjunction with fourth aspect, in the implementation that the second is possible, described VIM also for:
According to the bind request that described VNFM sends, described first business cluster and the second cluster are bound, and preserve the incidence relation of described first business cluster and described second cluster;
The feedback message representing binding success is returned to described VNFM.
Implement the embodiment of the present invention, there is following beneficial effect:
When source server in business cluster breaks down, in business cluster, rebuild the virtual machine that source server carries, if reconstruction failure, from business cluster, after dispatch server, again carry out the reconstruction of virtual machine.Such utilization factor that can improve virtual machine reliability of operation and raising hardware resource.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the method for reconstructing of a kind of virtual machine that first embodiment of the invention provides;
Fig. 2 is the schematic flow sheet of the method for reconstructing of a kind of virtual machine that second embodiment of the invention provides;
Fig. 3 is the principle schematic one of the method for reconstructing of the virtual machine that the embodiment of the present invention provides;
Fig. 4 is the principle schematic two of the method for reconstructing of the virtual machine that the embodiment of the present invention provides;
Fig. 5 is the schematic flow sheet of the method for reconstructing of a kind of virtual machine that third embodiment of the invention provides;
Fig. 6 is the principle schematic three of the method for reconstructing of the virtual machine that the embodiment of the present invention provides;
Fig. 7 is the principle schematic four of the method for reconstructing of the virtual machine that the embodiment of the present invention provides;
Fig. 8 is the principle schematic five of the method for reconstructing of the virtual machine that the embodiment of the present invention provides;
Fig. 9 is the structural representation of the reconstructing device of a kind of virtual machine that this aspect embodiment provides;
Figure 10 is another structural representation of the reconstructing device of a kind of virtual machine that the embodiment of the present invention provides.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The term " parts ", " module ", " system " etc. that use in this manual for represent computing machine and be correlated with entity, hardware, firmware, the combination of hardware and software, software or executory software.Such as, parts can be but be not limited to, the process run on a processor, processor, object, executable file, execution thread, program and/or computing machine.By diagram, the application run on the computing device and computing equipment can be parts.One or more parts can reside in process and/or execution thread, and parts and/or can be distributed on a computing machine between 2 or more computing machines.In addition, these parts can perform from the various computer-readable mediums storing various data structure above.Parts can such as be communicated by local and/or remote process according to the signal with one or more packet (such as from the data of two parts mutual with local system, distributed system and/or another parts internetwork, such as, by the internet of signal with other system interaction).
In addition, various aspects of the present invention or feature can be embodied as method, device or use the goods of standard program and/or engineering.The term " goods " used in the application is contained can from the computer program of any computer-readable device, carrier or medium access.Such as, computer-readable medium can comprise, but be not limited to: magnetic memory device is (such as, hard disk, floppy disk or tape etc.), CD (such as, CD (CompactDisk, compact disk), DVD (DigitalVersatileDisk, digital universal disc) etc.), smart card and flush memory device are (such as, EPROM (ErasableProgrammableRead-OnlyMemory, Erarable Programmable Read only Memory), card, rod or Keyed actuator etc.).In addition, various storage medium described herein can represent one or more equipment for storing information and/or other machine readable media.Term " machine readable media " can include but not limited to, wireless channel and other media various that can store, comprise and/or carry instruction and/or data.
See Fig. 1, the schematic flow sheet of the method for reconstructing of a kind of virtual machine provided for the embodiment of the present invention one, in embodiments of the present invention, described method comprises:
S101, when the source server that VIM detects in business cluster breaks down, determine m virtual machine of described source server deploy.
Concrete, business cluster is the set comprising multiple server, and the scheduling instruction that the quantity of the server comprised in business cluster can send according to cloud management platform changes.In VNF framework, the VIM in NFVO is in charge of the server in NFVI, the virtual machine in VNFM charge management server.VIM periodically can detect the running status of each server in business cluster, determines the source server broken down in business cluster according to running status; Or each server in business cluster when breaking down initiatively to VIM report and alarm information, VIM determines the source server broken down according to warning information; After source server breaks down, source server is deleted or is designated malfunction by VIM from business cluster.On the server of deploying virtual machine in business cluster, VNFM, according to the establishment of the virtual machine on business demand server, amendment and deletion, can know running status and the configuration parameter of the virtual machine of server deploy.
S102, described VIM rebuild a described m virtual machine in described business cluster.
Concrete, VIM creates m virtual machine according to hardware resource available quantity on the server in business cluster, if at least one virtual machine is not rebuild successfully in m virtual machine, then and m virtual machine reconstruction failure, if m virtual machine is all rebuild successfully, then m virtual machine is rebuild successfully.
If the idling-resource deficiency of S103 described business cluster causes the reconstruction failure of a described m virtual machine, inquire about the redundant cluster associated with described business cluster.
Wherein, if the idling-resource in business cluster does not meet the resource requirement of m virtual machine, m virtual machine can reconstruction failure.VIM stores the incidence relation of business cluster and redundant cluster, the redundant cluster that VIM associates according to incidence relation inquiry business cluster.Redundant cluster can have the business cluster of virtual machine for running or not run the blank cluster of virtual machine.
S104, VIM dispatch n server to described business cluster from described redundant cluster, and again rebuild a described m virtual machine in described business cluster; Or described VIM by a described m scheduling virtual machine in described redundant cluster, and in described redundant cluster, again rebuild a described m virtual machine.
Wherein, VIM dispatches n server to business cluster from redundant cluster, then the hardware resource available quantity of business cluster is increased, and again rebuilds m virtual machine in the business cluster of cloud management platform after scheduling.It should be noted that, in the hardware resource available quantity in n the server that cloud management platform is dispatched from redundant cluster and business cluster, hardware resource available quantity meets the hardware resource be greater than needed for m virtual machine; Or VIM by m scheduling virtual machine in the many redundant cluster of hardware resource available quantity, in redundant cluster, carry out the reconstruction of m virtual machine.
Implement embodiments of the invention, when source server in business cluster breaks down, the virtual machine that source server carries is rebuild in business cluster, if reconstruction failure, dispatch server or again carry out the reconstruction of virtual machine in redundant cluster from business cluster.Such utilization factor that can improve virtual machine reliability of operation and raising hardware resource.
See Fig. 2, the schematic flow sheet of the method for reconstructing of a kind of virtual machine provided for second embodiment of the invention, in embodiments of the present invention, described method comprises:
Business cluster and redundant cluster are bound by the bind request that S201, VIM send according to VNFM, and preserve the incidence relation of described business cluster and described redundant cluster.
Concrete, business cluster and redundant cluster are take server as the hardware resource set of granularity, comprise multiple server, comprise multiple server in redundant cluster in business cluster, and the server in business cluster and redundant cluster is a part for hardware resource pool.The virtual machine having bearer service is run in business cluster, server in redundant cluster can run or not run virtual machine, business cluster needs and certain redundant cluster in hardware resource pool when binding, VNFM sends the bind request of carrying the identify label of business cluster and the identify label of redundant cluster to VIM, after VIM receives bind request, the incidence relation of the identification presentation of both preservations, after binding success, VIM returns the feedback message of expression business cluster and redundant cluster binding success to VNFM.
S202, when the source server that described VIM detects in business cluster breaks down, determine m virtual machine of described source server deploy.
Concrete, when source server in business cluster breaks down, source server sends alarm event to VIM, by alarm event, VIM knows that source server breaks down, VIM can obtain the configuration information of the virtual machine of source server deploy from VNFM, configuration information comprises: the quantity of virtual machine, the hardware resource requirements amount of each virtual machine, the operating system of operation and the type etc. of business software.
S203, described VIM rebuild a described m virtual machine in described business cluster.
Wherein, in business cluster, the collocation strategy of virtual machine can be: reserved hardware resource on every station server, and reserved hardware resource does not allow to dispose virtual machine; Or reserved hardware resource on every station server, can hardware resource on the every station server of maximized use.When source server in business cluster breaks down, first the available hardware resource in business cluster is utilized to rebuild m virtual machine of source server deploy, wherein available in business cluster hardware resource at least will reach the hardware resource rebuild needed for m virtual machine, just possibility successful reconstitution m virtual machine; If the hardware resource of business cluster this locality is not enough, then rebuilding m virtual machine can lead to the failure.
S204, judge whether a described m virtual machine is rebuild successfully.
Concrete, if m virtual machine creating success, perform S205; If have a virtual machine creating failure in m virtual machine at least, perform S206.
S205, flow process terminate.
S206, described VIM obtain the hardware resource requirements amount of a described m virtual machine, and obtain the hardware resource available quantity in described business cluster.
Wherein, the reason of reconstruction failure is: the idling-resource in business cluster is not enough, cannot meet the demand of rebuilding m virtual machine.Described VIM obtains hardware resource requirements amount according to the configuration information of the virtual machine of m on source server, and hardware resource available quantity in the business of acquisition cluster, and hardware resource available quantity represents remaining not by the amount of hardware resource used.Hardware resource comprises: one or more in computational resource, storage resources and Internet resources.
S207, described VIM dispatch n server according to described hardware resource requirements amount and described hardware resource available quantity from described redundant cluster.
Wherein, in order to ensure that rebuilding m virtual machine has enough hardware resources, the hardware resource available quantity that n server is corresponding is more than or equal to the result that hardware resource requirements amount deducts the hardware resource available quantity of correspondence in business cluster.Dispatch after in n server to business cluster, the quantity of the server in business cluster increases n, and the hardware resource available quantity in the business cluster after simultaneously upgrading also increases, and enough rebuilds the hardware resource needed for m virtual machine.It should be noted that, n server of scheduling only allows to dispose the virtual machine in m virtual machine, when other virtual machines in business cluster need to dispose, the hardware resource of the server except n server can only be utilized to dispose.
A described m virtual machine is again rebuild in S208, the described VIM business cluster after scheduling.
Wherein, again rebuild m virtual machine in the business cluster of VIM after scheduling, now in business cluster, there is enough hardware resources, can a successful reconstitution m virtual machine.
If the described source server of S209 recovers normal or is replaced by new server, by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described redundant cluster; If or described VIM detects that described source server recovers normal or is replaced by new server, described VIM is by redundant cluster described in described source server or described new server scheduling meeting.
Wherein, source server recovers normal or when being replaced by new server; can to give notice message to VIM; according to notification message, VIM knows that source server recovers normal or is replaced by new server; the total amount of the hardware resource on new server is more than or equal to the total amount of the hardware resource of source server; m in a business cluster virtual machine moves on source server or new server by VIM successively; and discharge the hardware resource that m virtual machine take, and n server scheduling is returned in redundant cluster.Or VIM by source server or new server scheduling in redundant cluster.
Optionally, in some embodiments of the invention, a described m scheduling virtual machine in described redundant cluster, and again rebuild a described m virtual machine in described redundant cluster after, also to comprise by described VIM:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM is by a described m scheduling virtual machine to described source server or on new server.
Wherein, if the hardware resource available quantity in redundant cluster meets the requirement of rebuilding m virtual machine, rebuild successfully in redundant cluster, otherwise reconstruction failure.
See Fig. 3 and Fig. 4, be described with regard to the method for reconstructing of specific embodiment to the virtual machine of the embodiment of the present invention below, in embodiments of the present invention, business cluster and redundant cluster are all arranged in the hardware resource pool of NFVI, VIM is for managing the hardware resource in NFVI, VNFM is for the virtual machine of management operating on hardware resource, and VNFI is used for carrying out virtual to hardware resource, dispatches hardware resource for upper strata.Business cluster 1, business cluster 2 and a redundant cluster is had in hardware resource pool, wherein business cluster 1 comprises 4 servers, be respectively server 1, server 2, server 3 and server 4 from left to right, 4 servers are comprised in business cluster 2, be respectively server 1, server 2, server 3, server 4 from left to right, redundant cluster comprises 2 servers, and in business cluster 1, business cluster 2 and redundant cluster, each server has the hardware resource of 4 units.3 virtual machines are deployed with in the server 1 of business cluster 1, take the hardware resource of 4 units altogether, server 2 in business cluster 1 is deployed with 3 virtual machines, each virtual machine takies the hardware resource of 1 unit, the server 3 of business cluster 1 is deployed with 4 virtual machines, take the hardware resource of 4 units altogether, the server 4 of business cluster 1 is deployed with 3 virtual machines, takies the hardware resource of 3 units altogether.The server 1 of business cluster 2 is deployed with 4 virtual machines, and each virtual machine all takies the hardware resource of 1 unit, and the server 2 of business cluster 2, server 3 are all deployed with 3 virtual machines, and each virtual machine all takies the hardware resource of 1 unit; Be deployed with 2 virtual machines in the server 4 of business cluster 2, take 1 hardware resource and 2 hardware resources respectively.Any virtual machine is not disposed, the hardware resource of available 4 units in each server in redundant cluster.
Interaction flow is: VNFM sends the bind request of carrying the identify label of business cluster 1 and the identify label of redundant cluster to VIM, VIM is according to this bind request, the incidence relation of the identify label of both preservations, returns the acknowledge message representing binding success to VNFM after binding success.A redundant cluster can be bound with multiple business cluster, and shown in Fig. 3 is that business cluster 1 and business cluster 2 are bound with redundant cluster.
VNFM sends the bind request of carrying the identify label of business cluster 2 and the identify label of redundant cluster to VIM, VIM is according to bind request, and the incidence relation of the identify label of both preservations, returns the acknowledge message representing binding success to VNFM after binding success.
See Fig. 4, when VIM detects that the server 2 in business cluster 1 breaks down, determine that server 2 deploy has 3 virtual machines, the hardware resource of needs 3 units of inquiry 3 virtual machines, the hardware resource of residue 3 units simultaneously in inquiry business cluster 1, namely server 1 remains the hardware resource of 1 unit, the hardware resource of idle 1 unit of server 3, the hardware resource of idle 1 unit of server 4, VNFM rebuilds 3 virtual machines of server 2 deploy successively on above-mentioned three servers.
VIM detects that the server 4 in business cluster 2 breaks down, determine that server 2 deploy has 2 virtual machines, a virtual machine needs the hardware resource of 2 units, another virtual machine needs the hardware resource of 1 unit, inquiry business cluster 2 finds that remaining hardware resource is not enough to rebuild above-mentioned 2 virtual machines, from redundant cluster, dispatch a server joins in business cluster 2, there is in the server of scheduling the hardware resource of the free time of 4 units, in business cluster 2, the quantity of server becomes 5, above-mentioned 2 virtual machines are rebuild in the business cluster 2 of VIM after scheduling.
Wherein, when the server 4 in business cluster 2 recovers normal or is replaced by new server, by above-mentioned 2 virtual machine (vm) migrations in server 4 or new server, then the server scheduling originally belonging to redundant cluster can be returned redundant cluster; Or server 4 or new server scheduling are returned redundant cluster.
It should be noted that, the order of rebuilding or moving virtual machine can be determined according to the traffic load on virtual machine, the virtual machine that traffic load is little meets little virtual machine prior to business to carry out rebuilding or moving, or adopts other strategy rebuild or move virtual machine, and the present invention is not restricted.
See Fig. 5, the schematic flow sheet of the method that a kind of virtual machine provided for third embodiment of the invention is rebuild, in embodiments of the present invention, redundant cluster is the second business cluster, and described method comprises:
S501, when the source server that VIM detects in the first business cluster breaks down, send failure message to VNFM.
Concrete, the first business cluster is the set comprising multiple server, and the scheduling instruction (delete or add) that the quantity of the server that the first business cluster comprises can send according to cloud management platform changes.In VNF framework, cloud management platform is the server that the VIM in NFVO:NFVO is in charge of in NFVI, the virtual machine in VNFM charge management server.VIM periodically can detect the running status of each server in the first business cluster, determines the source server broken down in business cluster according to running status; Or first each server in business cluster when breaking down initiatively to VIM report and alarm information, VIM determines the source server broken down according to warning information; After source server breaks down, VIM sends fault notification message to VNFM, and fault notification message is source server for the server notifying VNFM and break down, and source server is deleted or is designated malfunction by VIM from the first business cluster.On the server of deploying virtual machine in the first business cluster, VNFM, according to the establishment of the virtual machine on business demand server, amendment and deletion, can know running status and the configuration parameter of the virtual machine of server deploy.
According to described fault notification message, S502, described VNFM determine that described source server breaks down, and determine m the virtual machine that described source server is disposed.
Wherein, can carry the identify label of source server in fault notification message, VNFM determines the source server broken down according to identify label, and VNFM obtains the quantity, operating system, application software etc. of the virtual machine disposed according to the configuration information of source server.
S503, described VNFM rebuild a described m virtual machine in described first business cluster, send reconstructed results to described VIM.
Wherein, VNFM creates m virtual machine according to the hardware resource available quantity of the first business cluster, if at least one virtual machine does not create successfully in m virtual machine, then and m virtual machine reconstruction failure; If m virtual machine is all rebuild successfully, then m virtual machine is rebuild successfully, and VNFM returns the reconstructed results of m virtual machine to VIM.
If the inadequate resource of the described first business cluster of S503 causes described m virtual machine reconstruction failure, described VIM inquires about the second business cluster associated with described first business cluster.
Concrete, VIM stores the incidence relation of the first business cluster and the second business cluster, inquires about the second business cluster of the first business cluster association according to incidence relation.Second business cluster comprises the set of multiple server, and server deploy has virtual machine, and the hardware resource on each server is available or reserved part hardware resource all.
S504, described VIM indicate described VNFM to rebuild a described m virtual machine in described second business cluster; Or described VIM dispatches n server to described first business cluster from described second business cluster, and described VNFM is indicated to rebuild a described m virtual machine in described second business cluster.
Wherein, VIM sends to VNFM and rebuilds Indication message, and VNFM triggers according to reconstruction Indication message and in the second business cluster, again rebuilds m virtual machine, if remaining hardware resource meets the hsrdware requirements of m virtual machine in the second business cluster, then rebuild successfully, otherwise reconstruction failure; Or VIM dispatches n server to the second business cluster according to the hsrdware requirements of hardware resource available quantity and m virtual machine in the first business cluster from second, then VIM sends to rebuild in the second business cluster of Indication message triggering VNFM after scheduling to VNFM and rebuilds m virtual machine.
Optionally, when the described source server detected in the first business cluster as VIM breaks down, before sending fault notification message to VNFM, also comprise:
Described first business cluster and described second business cluster are bound by the bind request that described VIM sends according to VNFM, and preserve the incidence relation of the first business cluster and described second business cluster; After binding success, described VIM returns the feedback message representing described first business cluster and described second business cluster binding success to VNFM.
Optionally, described VIM indicates after described VNFM rebuilds a described m virtual machine in described second business cluster, also comprises:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM indicates described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described second business cluster by described VIM; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described second business cluster by described VIM.
See Fig. 6 and Fig. 7, be described in detail with regard to the embodiment of a specific embodiment to Fig. 5 below, see Fig. 6, hardware resource pool comprises business cluster 1, business cluster 2 and business cluster 3, a business cluster can be bound with other business clusters multiple, and the cluster of business shown in Fig. 61 and business cluster 2 are bound with business cluster 3.Comprise 4 servers in business cluster 1, wherein, server 1 disposes 2 virtual machines, takies the hardware resource of 3 units altogether, and server 2 to server 3 is deployed with 3 virtual machines, and each virtual machine takies the hardware resource of 1 unit.Business cluster 2 comprises 4 servers, and server 1 to server 4 is deployed with 3 virtual machines respectively, and each virtual machine takies the hardware resource of 1 unit.Business cluster 3 comprises 2 servers, does not dispose any virtual machine.
Interaction flow is as follows: VIM utilizes the server in hardware resource pool to create business cluster 3, VNFM specified services cluster 3 is redundant cluster, VIM sends the bind request of carrying the identity information of business cluster 1, business cluster 2 and business cluster 3 to VNFM, the incidence relation of VNFM storage service cluster 1 and business cluster 3, and the incidence relation of storage service cluster 2 and business cluster 3.
See Fig. 7, the server 4 detected in business cluster 2 as VIM breaks down, send server 4 to VNFM and send fault notification message, VNFM breaks down according to fault notification message determination server 4, VNFM determines that server 4 deploy has 2 virtual machines, a virtual machine takies the hardware resource of 1 unit, another virtual machine takies the hardware resource of 2 units, in inquiry business cluster 2, remaining hardware resource finds the hardware resource of maximum residual 1 unit in individual server, another virtual machine cannot be rebuild, therefore virtual machine failure is rebuild, VNFM inquiry business cluster 2 management service cluster 3, above-mentioned 2 virtual machines are rebuild in business cluster 3, in business cluster 3, remaining hardware resource meets the hsrdware requirements of above-mentioned 2 virtual machines, rebuild successfully.
See Fig. 8, the server 4 detected in business cluster 2 as VIM breaks down, send server 4 to VNFM and send fault notification message, VNFM breaks down according to fault notification message determination server 4, VNFM determines that server 4 deploy has 2 virtual machines, a virtual machine takies the hardware resource of 1 unit, another virtual machine takies the hardware resource of 2 units, in inquiry business cluster 2, remaining hardware resource finds the hardware resource of maximum residual 1 unit in individual server, another virtual machine cannot be rebuild, therefore virtual machine failure is rebuild, VIM inquiry business cluster 2 associated services cluster 3, VIM dispatches 1 server in business cluster 2 from business cluster 3, business cluster 2 now comprises 5 servers, the hardware resource of residue 4 units in the server of scheduling, therefore the business cluster 2 after scheduling meets the demand of rebuilding above-mentioned 2 virtual machines, rebuild successfully.
Wherein, wherein, when the server 4 in business cluster 2 recovers normal or is replaced by new server, VNFM can by above-mentioned 2 virtual machine (vm) migrations in server 4 or new server, and then the server scheduling originally belonging to redundant cluster is returned business cluster 3 by VIM; Or server 4 or new server scheduling are returned business cluster 3 by VIM.
See Fig. 9, the structural representation of the reconstructing device of a kind of virtual machine provided for the embodiment of the present invention, the reconstructing device of the embodiment of the present invention is for realizing the method for reconstructing of the virtual machine of Fig. 1, in embodiments of the present invention, reconstructing device comprises: determination module 901, first rebuilds module 902, enquiry module 903 and second rebuilds module 904.
Determination module 901, for when detecting that the source server in business cluster breaks down, determines m the virtual machine that described source server is disposed.
First rebuilds module 902, for rebuilding a described m virtual machine in described business cluster.
Enquiry module 903, if the reconstruction failure causing a described m virtual machine for the inadequate resource of described business cluster, inquires about the redundant cluster associated with described business cluster.
Second rebuilds module 904, for dispatching n server to described business cluster from described redundant cluster, and again rebuilds a described m virtual machine in described business cluster; Or
By a described m scheduling virtual machine in described redundant cluster, and in described redundant cluster, again rebuild a described m virtual machine; Wherein, n be greater than 1 integer.
The embodiment of the present invention and embodiment of the method one are based on same design, and its technique effect brought is also identical, and concrete principle please refer to the description of embodiment of the method one, repeats no more herein.
Optionally, described VIM also comprises:
First recovers module, if for detecting that described source server recovers normal or is replaced by new server, indicate described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described redundant cluster; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described redundant cluster by described VIM.
Optionally, described VIM also comprises:
Second recovers module, if for detecting that described source server recovers normal or is replaced by new server, described VIM is by a described m scheduling virtual machine to described source server or on new server.
Optionally, described VIM also comprises:
Binding module, binds described business cluster and described redundant cluster for the bind request sent according to described VNFM, and preserves the incidence relation of described business cluster and described redundant cluster; The feedback message representing binding success is returned to described VNFM.
Optionally, described second rebuild module specifically for:
Obtain the hardware resource requirements amount of a described m virtual machine, and obtain the hardware resource available quantity in described business cluster;
From described redundant cluster, n server is dispatched according to described hardware resource requirements amount and described hardware resource available quantity; Wherein, hardware resource comprises one or more in storage resources, computational resource and Internet resources.
Optionally, described first rebuild module specifically for:
Obtain the traffic load state of each virtual machine in a described m virtual machine, in described business cluster, rebuild a described m virtual machine successively according to traffic load state; Wherein, the virtual machine that the virtual machine that traffic load is large is little prior to traffic load is rebuild.
The embodiment of the present invention and embodiment of the method two are based on same design, and its technique effect brought is also identical, and concrete principle please refer to the description of embodiment of the method two, repeats no more herein.
See Figure 10, be another structural representation of a kind of reconstructing device that the embodiment of the present invention provides, in embodiments of the present invention, reconstructing device 10 comprises processor 101, storer 103 and transceiver 102.Transceiver 102 is for communicating with external unit by communication interface.The quantity of the processor in reconstructing device 0 can be one or more.In some embodiments of the present invention, processor 101, storer 103 are connected by bus or other modes with transceiver 102.
Processor 101 may be used for the method shown in Fig. 1 that performs, and processor 101 comprises VIM, and VIM comprises: determination module, first rebuilds module, enquiry module and second rebuilds module.
Determination module, for when the source server in business cluster breaks down, determines m virtual machine of described source server deploy; M is the integer of large 1.
First rebuilds module, for rebuilding a described m virtual machine in described business cluster.
Enquiry module, if cause described m virtual machine reconstruction failure for the inadequate resource of described business cluster, inquires about the redundant cluster associated with described business cluster.
Second rebuilds module, for dispatching n server in described business cluster from described redundant cluster, and again rebuilds described m virtual machine in described business cluster; Wherein, n be greater than 1 integer.
Processor 101 may be used for the method shown in Fig. 1 that performs.The implication of the term related to about the present embodiment and citing, can the embodiment of reference diagram 1 correspondence.Repeat no more herein.
Further, the structural representation of the reconstructing device of a kind of virtual machine also provided for the embodiment of the present invention, in embodiments of the present invention, described reconstructing device is for realizing the method shown in Fig. 5, described reconstructing device comprises VIM and VNFM, wherein, when the source server that described VIM detects in the first business cluster breaks down, fault notification message is sent to described VNFM;
According to described fault notification message, described VNFM determines that described source server breaks down, and determine m the virtual machine that described source server is disposed;
Described VNFM rebuilds a described m virtual machine in described first business cluster, sends reconstructed results to described VIM;
If the inadequate resource of described first business cluster causes described m virtual machine reconstruction failure, described VIM inquires about the second business cluster associated with described first business cluster;
Described VIM indicates described VNFM to rebuild a described m virtual machine in described second business cluster; Or
Described VIM dispatches n server to described first business cluster from described second business cluster, and indicates described VNFM again in described second business cluster, to rebuild a described m virtual machine.
Optionally, described VIM also for:
If detect, described source server recovers normal or is replaced by new server, indicate described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described second business cluster by described VIM; Or
If detect, described source server recovers normal or is replaced by new server, described source server or described new server scheduling is returned in described second business cluster.
Optional described VIM also for:
According to the bind request that described VNFM sends, described first business cluster and the second cluster are bound, and preserve the incidence relation of described first business cluster and described second cluster;
The feedback message representing binding success is returned to described VNFM.
The embodiment of the present invention and embodiment of the method three are based on same design, and its technique effect brought is also identical, and concrete principle please refer to the description of embodiment of the method three, repeats no more herein.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in a computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-OnlyMemory, ROM) or random store-memory body (RandomAccessMemory, RAM) etc.
Above disclosedly be only a kind of preferred embodiment of the present invention, certainly the interest field of the present invention can not be limited with this, one of ordinary skill in the art will appreciate that all or part of flow process realizing above-described embodiment, and according to the equivalent variations that the claims in the present invention are done, still belong to the scope that invention is contained.
Claims (15)
1. a method for reconstructing for virtual machine, is characterized in that, comprising:
When the source server that Virtual base infrastructure manager VIM detects in business cluster breaks down, determine m the virtual machine that described source server is disposed;
Described VIM rebuilds a described m virtual machine in described business cluster;
If the not busy inadequate resource of described business cluster hollow causes described m virtual machine reconstruction failure, described VIM inquires about the redundant cluster associated with described business cluster;
Described VIM dispatches n server to described business cluster from described redundant cluster, and again rebuilds a described m virtual machine in described business cluster; Or
A described m scheduling virtual machine in described redundant cluster, and is again rebuild a described m virtual machine by described VIM in described redundant cluster; Wherein, n be greater than 1 integer.
2. the method for claim 1, is characterized in that, described VIM dispatches n server to described business cluster from described redundant cluster, and again rebuild a described m virtual machine in described business cluster after, also comprises:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM indicates described virtual network function manager VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described redundant cluster by described VIM; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described redundant cluster by described VIM.
3. the method for claim 1, is characterized in that, a described m scheduling virtual machine in described redundant cluster, and again rebuild a described m virtual machine in described redundant cluster after, also to comprise by described VIM:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM is by a described m scheduling virtual machine to described source server or on new server.
4. the method as described in claim 1-3 any one, is characterized in that, when the described source server detected in business cluster as VIM breaks down, before determining m the virtual machine that described source server is disposed, also comprises:
Described business cluster and described redundant cluster are bound by the bind request that described VIM sends according to described VNFM, and preserve the incidence relation of described business cluster and described redundant cluster;
Described VIM returns the feedback message representing binding success to described VNFM.
5. the method for claim 1, is characterized in that, described redundant cluster comprises the business cluster being deployed with virtual machine or the cluster not disposing virtual machine.
6. a method for reconstructing for virtual machine, is characterized in that, comprising:
When the source server that VIM detects in the first business cluster breaks down, send fault notification message to VNFM;
According to described fault notification message, described VNFM determines that described source server breaks down, and determine m the virtual machine that described source server is disposed;
Described VNFM rebuilds a described m virtual machine in described first business cluster, sends reconstructed results to described VIM;
If the not busy inadequate resource of described first business cluster hollow causes the reconstruction failure of a described m virtual machine, described VIM inquires about the second business cluster associated with described first business cluster;
Described VIM indicates described VNFM to rebuild a described m virtual machine in described second business cluster; Or
Described VIM dispatches n server to described first business cluster from described second business cluster, and indicates described VNFM again in described second business cluster, to rebuild a described m virtual machine.
7. method as claimed in claim 6, is characterized in that, described VIM indicates after described VNFM rebuilds a described m virtual machine in described second business cluster, also comprises:
If described VIM detects that described source server recovers normal or is replaced by new server, described VIM indicates described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described second business cluster by described VIM; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described second business cluster by described VIM.
8. method as claimed in claim 6, is characterized in that, when the described source server detected in the first business cluster as VIM breaks down, before sending failure message, also comprise to VNFM:
Described first business cluster and the second cluster are bound by the bind request that described VIM sends according to described VNFM, and preserve the incidence relation of described first business cluster and described second cluster;
Described VIM returns the feedback message representing binding success to described VNFM.
9. a device for virtual machine, is characterized in that, described device comprises VIM, and described VIM comprises:
Determination module, for when detecting that the source server in business cluster breaks down, determines m the virtual machine that described source server is disposed;
First rebuilds module, for rebuilding a described m virtual machine in described business cluster;
Enquiry module, if cause the reconstruction failure of a described m virtual machine, the redundant cluster that inquiry associates with described business cluster for the idling-resource deficiency of described business cluster;
Second rebuilds module, for dispatching n server to described business cluster from described redundant cluster, and again rebuilds a described m virtual machine in described business cluster; Or
By a described m scheduling virtual machine in described redundant cluster, and in described redundant cluster, again rebuild a described m virtual machine; Wherein, n be greater than 1 integer.
10. device as claimed in claim 9, it is characterized in that, described VIM also comprises:
First recovers module, if for detecting that described source server recovers normal or is replaced by new server, indicate described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described redundant cluster; Or
If described VIM detects that described source server recovers normal or is replaced by new server, described source server or described new server scheduling return in described redundant cluster by described VIM.
11. devices as claimed in claim 9, it is characterized in that, described VIM also comprises:
Second recovers module, if for detecting that described source server recovers normal or is replaced by new server, described VIM is by a described m scheduling virtual machine to described source server or on new server.
12. devices as described in claim 9-11 any one, it is characterized in that, described VIM also comprises:
Binding module, binds described business cluster and described redundant cluster for the bind request sent according to described VNFM, and preserves the incidence relation of described business cluster and described redundant cluster; The feedback message representing binding success is returned to described VNFM.
The reconstructing device of 13. 1 kinds of virtual machines, is characterized in that, described reconstructing device comprises VIM and VNFM, wherein,
When the source server that described VIM detects in the first business cluster breaks down, send fault notification message to described VNFM;
According to described fault notification message, described VNFM determines that described source server breaks down, and determine m the virtual machine that described source server is disposed;
Described VNFM rebuilds a described m virtual machine in described first business cluster, sends reconstructed results to described VIM;
If the idling-resource deficiency of described first business cluster causes described m virtual machine reconstruction failure, described VIM inquires about the second business cluster associated with described first business cluster;
Described VIM indicates described VNFM to rebuild a described m virtual machine in described second business cluster; Or
Described VIM dispatches n server to described first business cluster from described second business cluster, and indicates described VNFM again in described second business cluster, to rebuild a described m virtual machine.
14. devices as claimed in claim 13, is characterized in that, described VIM also for:
If detect, described source server recovers normal or is replaced by new server, indicate described VNFM by a described m virtual machine (vm) migration on described source server or described new server, and a described n server scheduling is returned described second business cluster by described VIM; Or
If detect, described source server recovers normal or is replaced by new server, described source server or described new server scheduling is returned in described second business cluster.
15. devices as claimed in claim 13, is characterized in that, described VIM also for:
According to the bind request that described VNFM sends, described first business cluster and the second cluster are bound, and preserve the incidence relation of described first business cluster and described second cluster;
The feedback message representing binding success is returned to described VNFM.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510642333.9A CN105183588B (en) | 2015-09-30 | 2015-09-30 | A kind of method for reconstructing and device of virtual machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510642333.9A CN105183588B (en) | 2015-09-30 | 2015-09-30 | A kind of method for reconstructing and device of virtual machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105183588A true CN105183588A (en) | 2015-12-23 |
| CN105183588B CN105183588B (en) | 2018-10-30 |
Family
ID=54905682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510642333.9A Active CN105183588B (en) | 2015-09-30 | 2015-09-30 | A kind of method for reconstructing and device of virtual machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105183588B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018023217A1 (en) * | 2016-07-30 | 2018-02-08 | 华为技术有限公司 | Method, device and system for establishing virtual machine |
| CN110990118A (en) * | 2019-11-24 | 2020-04-10 | 北京浪潮数据技术有限公司 | High-availability method, device and equipment for virtual machine |
| WO2020224421A1 (en) * | 2019-05-06 | 2020-11-12 | 中兴通讯股份有限公司 | Upgrade method, apparatus and system, and storage medium |
| CN113381887A (en) * | 2021-06-08 | 2021-09-10 | 中国工商银行股份有限公司 | Method and device for processing faults of computing nodes |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629941A (en) * | 2012-03-20 | 2012-08-08 | 武汉邮电科学研究院 | Caching method of a virtual machine mirror image in cloud computing system |
| CN104427002A (en) * | 2013-09-09 | 2015-03-18 | 三星Sds株式会社 | Cluster system and method for providing service availability in cluster system |
| US20150113529A1 (en) * | 2013-10-23 | 2015-04-23 | Huawei Technologies Co., Ltd. | Method, System and Apparatus for Creating Virtual Machine |
-
2015
- 2015-09-30 CN CN201510642333.9A patent/CN105183588B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102629941A (en) * | 2012-03-20 | 2012-08-08 | 武汉邮电科学研究院 | Caching method of a virtual machine mirror image in cloud computing system |
| CN104427002A (en) * | 2013-09-09 | 2015-03-18 | 三星Sds株式会社 | Cluster system and method for providing service availability in cluster system |
| US20150113529A1 (en) * | 2013-10-23 | 2015-04-23 | Huawei Technologies Co., Ltd. | Method, System and Apparatus for Creating Virtual Machine |
Non-Patent Citations (1)
| Title |
|---|
| 佚名: "VMware_虚拟机迁移", 《HTTP://WWW.360DCO.COM/CONTENT/14/0624/23/15328926_389484405.SHTML》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018023217A1 (en) * | 2016-07-30 | 2018-02-08 | 华为技术有限公司 | Method, device and system for establishing virtual machine |
| WO2020224421A1 (en) * | 2019-05-06 | 2020-11-12 | 中兴通讯股份有限公司 | Upgrade method, apparatus and system, and storage medium |
| CN110990118A (en) * | 2019-11-24 | 2020-04-10 | 北京浪潮数据技术有限公司 | High-availability method, device and equipment for virtual machine |
| CN113381887A (en) * | 2021-06-08 | 2021-09-10 | 中国工商银行股份有限公司 | Method and device for processing faults of computing nodes |
| CN113381887B (en) * | 2021-06-08 | 2023-04-07 | 中国工商银行股份有限公司 | Method and device for processing faults of computing nodes |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105183588B (en) | 2018-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106301876B (en) | Physical machine upgrade method, business migration method and device | |
| CN106528327B (en) | A kind of data processing method and backup server | |
| EP3200393B1 (en) | Method and device for virtual network function management | |
| CN105095317B (en) | Distributed data base service management system | |
| CN103778031A (en) | Distributed system multilevel fault tolerance method under cloud environment | |
| CN105933391A (en) | Node capacity expansion method, device and system | |
| CN105183588A (en) | Rebuilding method and device of virtual machines | |
| CN111506391B (en) | Container deployment method and device | |
| CN108804038A (en) | Method, apparatus, server and the computer-readable medium of daily record data migration | |
| CN106790092B (en) | Remote procedure call server control system and method | |
| CN106506186A (en) | The method and apparatus for rebuilding virtual network function | |
| CN103414712A (en) | Management system and method of distributed virtual desktop | |
| CN109274537B (en) | Continuous network virtualization platform system | |
| CN104023058A (en) | Method and system for managing and allocating storage resources | |
| CN108347339A (en) | A kind of service restoration method and device | |
| CN105635311A (en) | Method for synchronizing resource pool information in cloud management platform | |
| CN103634128B (en) | The collocation method and device of virtual machine Placement Strategy | |
| CN102088490A (en) | Data storage method, device and system | |
| CN109358967A (en) | A kind of ME platform APP instantiation moving method and server | |
| CN105740049B (en) | A kind of control method and device | |
| CN110932914A (en) | Deployment method, deployment device, hybrid cloud system architecture and computer storage medium | |
| CN106385330A (en) | Network function virtualization composer realization method and device | |
| CN107562519A (en) | Moving method, system and the server of virtual machine | |
| CN104517067A (en) | Method, device and system for data access | |
| CN110580198A (en) | Method and device for adaptively switching OpenStack computing node into control node |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |