CN103995731A

CN103995731A - Management center deployment method and virtual device

Info

Publication number: CN103995731A
Application number: CN201410195779.7A
Authority: CN
Inventors: 刘力力; 何嘉莹
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2014-05-09
Filing date: 2014-05-09
Publication date: 2014-08-20
Anticipated expiration: 2034-05-09
Also published as: CN103995731B

Abstract

The embodiment of the invention discloses a management center deployment method and a virtual device. The method comprises the steps that when a management center, deployed on a first computer, of a virtualization cluster where the first computer belongs fails, the target virtual device starts a pre-installed program of the management center so that the management center can operate on the target virtual device, wherein the target virtual device is a virtual device which is deployed on a second computer in the virtualization cluster and can directly get access to physical resources of the second computer; the target virtual device dispatches the physical resources of the second computer to the management center for use, wherein the management center operates on the target virtual device. According to the management center deployment method and the virtual device, the resources of the computers can be saved, and the management center of the virtualization cluster can be restored in time when the computers fail.

Description

A kind of administrative center's dispositions method and virtual bench

Technical field

The present invention relates to the communications field, relate in particular to a kind of administrative center dispositions method and virtual bench.

Background technology

Along with the develop rapidly of computer technology, Intel Virtualization Technology is used widely, and wherein, in Intel Virtualization Technology, virtual cluster application is very extensive.Virtual cluster is to comprise many computing machines that are deployed with virtual machine, can, by Intel Virtualization Technology by abstract the physical resource of these many computing machines resource pool for the various resource compositions such as storage, calculating, network, provide virtual machine to use to user by the mode of on-demand application resource at virtual cluster like this.Wherein, comprise administrative center at virtual cluster, this administrative center can manage all computing machines and virtual machine in this virtual cluster effectively, and corresponding virtualization services is externally provided, and can also reduce greatly the cost of virtual operation and maintenance.

And in current virtual cluster, be to have to be specifically designed to a computing machine of disposing administrative center, on this computing machine, only dispose administrative center.But the resource that administrative center is used in the time of this virtual cluster of management is in actual applications only a part for the resource of this computing machine, another part resource of this computing machine will be wasted like this.In addition, in the time that this computing machine breaks down, the service at the center of recovery management in time.

Summary of the invention

The embodiment of the present invention provides a kind of administrative center dispositions method and virtual bench, can save the resource of computing machine, and in the time that this computing machine breaks down, recovers in time the administrative center of virtual cluster.

First aspect, the invention provides a kind of administrative center dispositions method, comprising:

In the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, target virtual bench starts the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described target virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer;

The physical resource that described target virtual bench is dispatched described second computer uses to moving described administrative center on described target virtual bench.

In first aspect, in the possible implementation of the first, described target virtual bench starts the program of preassembled described administrative center, and with before realizing move described administrative center on described target virtual bench, described method also comprises:

Described target virtual bench acquisition unit is deployed in the logout of the described administrative center on described the first computing machine, and calculates the stock number of the needed physical resource of this logout;

The physical resource that described target virtual bench is dispatched described second computer uses to moving described administrative center on described target virtual bench, comprising:

The physical resource that is less than or equal to described stock number that described target virtual bench is dispatched described second computer uses to moving described administrative center on described target virtual bench.

In conjunction with first aspect, in first aspect in the possible implementation of the second, described target virtual bench starts the program of preassembled described administrative center, and with before realizing move described administrative center on described target virtual bench, described method also comprises:

The stock number of needed physical resource when what described target virtual bench received that described the first computing machine sends be deployed on described the first computing machine described administrative center action;

In conjunction with the possible implementation of the first of first aspect or the possible implementation of the second, in first aspect in the third possible implementation, the physical resource that is less than or equal to described stock number that described target virtual bench is dispatched described second computer uses to moving described administrative center on described target virtual bench, comprising:

Described target virtual bench is less than or equal to the physical resource of described stock number to the physical source distributing device application of described second computer, and the physical resource of dispatching described application is to moving the use of described administrative center on described target virtual bench; Or

The physical resource that is less than or equal to described stock number that described target virtual bench limits described second computer cannot be used by other virtual bench of described second computer, and the physical resource of dispatching described restriction uses to moving described administrative center on described target virtual bench, described other virtual bench is the arbitrary virtual bench except described target virtual bench in described second computer.

In conjunction with the possible implementation of the first of first aspect or first aspect or the possible implementation of the second, in first aspect in the 4th kind of possible implementation, described target virtual bench is dispatched the physical resource of described second computer to after moving the use of described administrative center on described target virtual bench, and described method also comprises:

Described target virtual bench upgrades the version number of described administrative center, and the version number after described renewal is sent to the computing machine in described virtual cluster.

In conjunction with the possible implementation of the first of first aspect or first aspect or the possible implementation of the second, in first aspect in the 5th kind of possible implementation, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, target virtual bench starts the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, comprising:

In the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, described target virtual bench judges whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, if, start the program of preassembled described administrative center, move described administrative center to realize on described target virtual bench.

In conjunction with the 5th kind of possible implementation of first aspect, in the 6th kind of possible implementation, described for representing the mark of carry load ability in first aspect, comprising:

F＝T-S×N-Δ×100/(H-L)

Wherein, F is described for representing the mark of carry load ability, described T is the reference mark of the described virtual cluster Computer preset, described N is the number of tasks of described second computer in special time operation, described S is the shared mark of each task, described Δ is the difference that E deducts L, and described E is greater than described L, described E equals the number percent that described second computer present load amount accounts for the high capacity that described second computer can carry and is multiplied by 100, described L equals predefined too low load threshold in described second computer and is multiplied by 100, described H equals the predefined high load threshold of crossing in described second computer and is multiplied by 100, or

F＝T-S×N-Δ×50/(H-L)

Wherein, F is described for representing the mark of carry load ability, described T is the reference mark of the described virtual cluster Computer preset, described N is the number of tasks of described second computer in special time operation, described S is the shared mark of each task, described Δ is the difference that L deducts E, and described L is greater than described E, described E equals the number percent that described second computer present load amount accounts for the high capacity that described second computer can carry and is multiplied by 100, described L equals predefined too low load threshold in described second computer and is multiplied by 100, described H equals the predefined high load threshold of crossing in described second computer and is multiplied by 100.

Second aspect, the invention provides a kind of administrative center dispositions method, comprising:

In the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the first virtual bench of the program of described administrative center, described the first virtual bench can directly be accessed the physical resource of described the first computing machine;

Described the first virtual bench judges whether described administrative center has operated on the computing machine of described virtual cluster, and if so, described the first virtual bench forbids that the program of described administrative center starts.

In the possible implementation of the first of second aspect, described the first virtual bench judges that whether described administrative center has operated on the computing machine of described virtual cluster, comprising:

Described the first virtual bench receives the current version number of the described administrative center of the computing machine transmission of described virtual cluster, and judge that whether described current version number is identical with the version number of the described administrative center of described the first virtual bench storage, if not, determine that described administrative center has operated on the computing machine of described virtual cluster, if so, determine on the current computing machine that does not operate in described virtual cluster of described administrative center.

In conjunction with the possible implementation of the first of second aspect or second aspect, in the possible implementation of the second of second aspect, before first virtual bench of program of described administrative center is installed in described the first computing machine of described recovery in advance, described method also comprises:

Described the first virtual bench sends to the computing machine of described virtual cluster the logout that described administrative center moves on described target virtual machine, described logout moves the stock number of the needed physical resource of described logout for calculating described administrative center, described stock number is greater than or equal to the stock number of the second virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described the second virtual bench is described virtual cluster; Or

The stock number of needed physical resource when described the first virtual bench sends the action of described administrative center to the computing machine of described virtual cluster, described stock number is greater than or equal to the stock number of the second virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described the second virtual bench is described virtual cluster.

The third aspect, the invention provides a kind of virtual bench, comprising: start unit and scheduling unit, wherein:

Described start unit, for in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, start the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer;

Described scheduling unit, uses to moving described administrative center on described target virtual bench for the physical resource of dispatching described second computer.

In the possible implementation of the first of the third aspect, described device also comprises:

Computing unit, is deployed in the logout of the described administrative center on described the first computing machine for acquisition unit, and calculates the stock number of the needed physical resource of this logout;

Described scheduling unit uses to moving described administrative center on described target virtual bench for the physical resource that is less than or equal to described stock number of dispatching described second computer.

In conjunction with the third aspect, in the possible implementation of the second of the third aspect, described device also comprises:

Receiving element, for receive that described the first computing machine sends be deployed in the described administrative center action on described the first computing machine time needed physical resource stock number;

In conjunction with the possible implementation of the second of the possible implementation of the first of the third aspect or the third aspect, in the third possible implementation of the third aspect, described scheduling unit is for being less than or equal to the physical resource of described stock number to the physical source distributing device application of described second computer, and the physical resource of dispatching described application is to moving the use of described administrative center on described target virtual bench; Or

Described scheduling unit cannot be used by other virtual bench of described second computer for the physical resource that is less than or equal to described stock number that limits described second computer, and the physical resource of dispatching described restriction uses to moving described administrative center on described target virtual bench, described other virtual bench is the arbitrary virtual bench except described target virtual bench in described second computer.

In conjunction with the possible implementation of the second of the possible implementation of the first of the third aspect or the third aspect or the third aspect, in the 4th kind of possible implementation of the third aspect, described device also comprises:

Updating block, for upgrading the version number of described administrative center, and sends to the computing machine in described virtual cluster by the version number after described renewal.

In conjunction with the possible implementation of the second of the possible implementation of the first of the third aspect or the third aspect or the third aspect, in the 5th kind of possible implementation of the third aspect, start unit is in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, judge whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, if, start the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize.

In conjunction with the 5th kind of possible implementation of the third aspect, in the 6th kind of possible implementation of the third aspect, described for representing the mark of carry load ability, comprising:

F＝T-S×N-Δ×100/(H-L)

F＝T-S×N-Δ×50/(H-L)

Fourth aspect, the invention provides a kind of virtual bench, comprising: recovery unit, judging unit and forbid unit, wherein:

Described recovery unit, for in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the described virtual bench of the program of described administrative center, described virtual bench can directly be accessed the physical resource of described the first computing machine;

Described judging unit, for judging whether described administrative center has operated in the computing machine of described virtual cluster;

Forbid unit, for when the judged result of described judging unit is when being, forbid that the program of described administrative center starts.

In the possible implementation of the first of fourth aspect, described judging unit is used for the current version number of the described administrative center of the computing machine transmission that receives described virtual cluster, and judge that whether described current version number is identical with the version number of the described administrative center of described the first virtual bench storage, if not, determine that described administrative center has operated on the computing machine of described virtual cluster, if so, determine on the current computing machine that does not operate in described virtual cluster of described administrative center.

In conjunction with the possible implementation of the first of fourth aspect or fourth aspect, in the possible implementation of the second of fourth aspect, described device also comprises:

The first transmitting element, for sending to the computing machine of described virtual cluster the logout that described administrative center moves on described virtual machine, described logout moves the stock number of the needed physical resource of described logout for calculating described administrative center, described stock number is greater than or equal to the stock number of target virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described target virtual bench is described virtual cluster; Or

The second transmitting element, the stock number of needed physical resource while action for send described administrative center to the computing machine of described virtual cluster, described stock number is greater than or equal to the stock number of target virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described target virtual bench is described virtual cluster.

In technique scheme, the target virtual bench that second computer is disposed is provided with the program of the administrative center of virtual batch of cluster in advance, in the time that the administrative center of the virtual cluster of the first computing machine deploy breaks down, above-mentioned target virtual bench just can start the program of above-mentioned administrative center, on this target virtual bench, move above-mentioned administrative center to realize, the physical resource that target virtual bench is dispatched described second computer again uses to moving described administrative center on described target virtual bench.Can realize like this while only having administrative center to break down, target virtual bench just starts the program of administrative center, while not breaking down in administrative center, target virtual bench can not start administrative center, thereby the program of the administrative center now starting on target virtual bench can not take the physical resource of second computer, thereby realize the resource of saving second computer.In addition, the program that only need to start administrative center in this technical method just can realize recovery management center, thereby can realize in the time that this computing machine breaks down, and recovers in time the administrative center of virtual cluster.

Brief description of the drawings

In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.

Fig. 1 is the schematic flow sheet of a kind of administrative center dispositions method of providing of the embodiment of the present invention;

Fig. 2 is the schematic flow sheet of the another kind of administrative center dispositions method that provides of the embodiment of the present invention;

Fig. 3 is the schematic flow sheet of the another kind of administrative center dispositions method that provides of the embodiment of the present invention;

Fig. 4 is the structural representation of a kind of virtual bench of providing of the embodiment of the present invention;

Fig. 5 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Fig. 6 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Fig. 7 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Fig. 8 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Fig. 9 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Figure 10 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Figure 11 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention;

Figure 12 is the structural representation of a kind of computing node of providing of the embodiment of the present invention;

Figure 13 is the structural representation of the another kind of computing node that provides of the embodiment of the present invention;

Figure 14 is the structural representation that the embodiment of the present invention also provides a kind of computer system.

Embodiment

Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.

In the embodiment of the present invention, virtual bench can be the virtual management system on computing machine, and for example: virtual bench can be the virtual management system Domain0 of Xen platform, or virtual bench can be the flat as middle virtual management system hostSytem of Kvm etc.In addition, above-mentioned virtual bench can directly be accessed the physical resource of the affiliated computing machine of this virtual bench.In addition, the computing machine in the embodiment of the present invention can be the smart machine that server, network equipment and user terminal etc. can be disposed virtual bench.

In addition, in the embodiment of the present invention, physical resource can be understood as hardware resource, for example: cpu resource and memory source etc.

Refer to Fig. 1, Fig. 1 is the schematic flow sheet of a kind of administrative center dispositions method of providing of the embodiment of the present invention, as shown in Figure 1, comprises the following steps:

101, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, target virtual bench starts the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described target virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer.

The administrative center of above-mentioned the first computing machine deploy breaks down, can refer to that the administrative center moving on the first computing machine breaks down, in addition, breaking down can be to be interpreted as that administrative center cannot provide service, for example: the first computing machine is delayed, and the virtual bench that moves described administrative center in machine, the first computer corruption, the first computing machine breaks down, the program of the described administrative center of the first computer run occurs that wrong or the first computing machine cannot communicate etc. with other computing machine of virtual cluster.In addition, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, can be, second computer detects that the administrative center of the first computing machine deploy breaks down, for example: the request that second computer sends to administrative center cannot be received response; Or second computer receive on the first computing machine, send for notifying notification message that administrative center breaks down etc.

Above-mentioned target virtual bench is provided with the program of the administrative center of virtual cluster in advance, in the time that the administrative center of the first computing machine deploy normally moves, the just program of operations control center not of above-mentioned target virtual bench, thereby now the physical resource on second computer can or calculate agency's use by the virtual machine of second computer deploy, thereby realizes the resource of saving second computer.In the time that the first computing machine deploy administrative center breaks down, above-mentioned target virtual bench just can start the program of administrative center, move on target virtual bench to realize administrative center, now the administrative center of virtual cluster is deployed on target virtual bench.

102, the physical resource that target virtual bench is dispatched described second computer is to moving the use of described administrative center on described target virtual bench.

In the time that administrative center moves on target virtual bench, the physical resource that target virtual bench just can call on second computer uses to administrative center, because target virtual bench can directly be accessed the physical resource of second computer, thereby the administrative center of target virtual bench deploy also can directly access the physical resource of second computer, administrative center just can be used the physical resource of second computer to manage the computing machine of virtual cluster like this, wherein, the computing machine of virtual cluster is managed and can comprise following at least one:

The virtual machine that physical resource to computing machine manages, computing machine is disposed manages, receive the virtual machine that computing machine disposes performance, virtual machine is carried out to alarm and event handling etc.This present embodiment is not construed as limiting.

Because above-mentioned target virtual bench had just been deployed in second computer before the administrative center of the first computing machine deployment breaks down, be that target virtual bench just moved before the administrative center of the first computing machine deployment breaks down, for example, and target virtual bench (: database has started some public services in the time of operation, device drives, network communication module), like this in the time starting the program of administrative center, this administrative center managing virtual cluster and service is outwards provided in time, thereby realize timely recovery section and be deployed in the administrative center on the first computing machine.

Refer to Fig. 2, Fig. 2 is the schematic flow sheet of the another kind of administrative center dispositions method that provides of the embodiment of the present invention, as shown in Figure 2, comprises the following steps:

201, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, target virtual bench starts the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described target virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer.

Optionally, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, the computing machine of virtual cluster can select in the computing machine of virtual cluster the computing machine of applicable operations control center by default election algorithm, thus this computer run administrative center.For example: in the time that the administrative center on the first computing machine breaks down, when in the computing machine of virtual cluster, the load of second computer operation is minimum, the target virtual bench of second computer just can start the program of administrative center, thus operations control center on target virtual bench.Wherein, the implementation procedure of above-mentioned election algorithm can be as follows: step 201 can comprise:

Wherein, target virtual bench judges whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, and can comprise:

In virtual cluster, each computing machine is shared current mark each other, when computing machine receives arbitrary mark when higher than the mark of itself, just itself be set to non-owner (Master) candidate pattern, when the mark receiving is during all lower than mark itself, just itself be set to Master candidate pattern.When the computing machine of Master candidate pattern does not receive higher than mark itself more like this, just can itself be set to Master pattern, wherein, Master pattern refers to the pattern of operations control center.

Optionally, above-mentioned for representing the mark of carry load ability, can represent to comprise by following formula:

F＝T-S×N-Δ×100/(H-L)

F＝T-S×N-Δ×50/(H-L)

Above-mentioned high load threshold excessively and too low load threshold are all the threshold values with the form of number percent, for example: cross high load threshold and too low load threshold and be respectively 80% and 20%, in addition, above-mentioned mistake when number percent that high load threshold represents the high capacity that accounts for when the present load amount of second computer that described second computer can carry is this threshold value represents that the load of second computer is overweight, above-mentioned too low load threshold represents to represent the underload of second computer in the time that the number percent that the present load amount of second computer accounts for the high capacity that described second computer can carry is this threshold value.Above-mentioned T can be 100, and above-mentioned S can be 2, and above-mentioned special time can be a period of time in the past, for example: the half an hour close with current time.

Below taking the concrete example of a tool as describing the mark of computing machine:

For example: the number of tasks that second computer moves within the half an hour close with current time is 5, in second computer, predefined too low load threshold is 20%, too low load threshold is 80%, present load amount accounts for 50% of high capacity that described second computer can carry, so, the current mark of second computer can be just 100-10-1500/60=65.

202, the physical resource that target virtual bench is dispatched the specific amount of resources of described second computer uses to moving described administrative center on described target virtual bench.

Optionally, above-mentioned specific amount of resources can be that target virtual bench calculates, for example: before step 201, described method can also comprise:

Target virtual bench acquisition unit is deployed in the logout of the described administrative center on described the first computing machine, and calculates the stock number of the needed physical resource of this logout.

Step 202 can comprise:

The physical resource that is less than or equal to described stock number that target virtual bench is dispatched described second computer uses to moving described administrative center on described target virtual bench.

Wherein, the stock number of the needed physical resource of this logout of above-mentioned calculating refers to, the administrative center of the first computing machine deploy moves the stock number of the needed physical resource of this logout.In addition, the administrative center that the above-mentioned stock number calculating can also be the first computing machine deploy moves the stock number of the needed greatest physical resource of this logout.

Optionally, above-mentioned specific amount of resources can be that target virtual bench receives the first computing machine transmission, for example: before step 201, described method can also comprise:

The stock number of needed physical resource when what target virtual bench received that described the first computing machine sends be deployed on described the first computing machine described administrative center action.

Step 202 can comprise:

The administrative center of above-mentioned the first computing machine can be in operational process, this administrative center can be periodically or interval certain hour monitor the demand stock number of this administrative center, or record the greatest requirements stock number of current administrative center, and the demand stock number that monitoring is obtained or greatest requirements stock number send to above-mentioned target virtual bench, wherein, the stock number that this demand stock number or greatest requirements stock number just can receive for above-mentioned target virtual bench.In addition, when the first computing machine sends after the demand stock number or greatest requirements stock number, and when the demand stock number of the administrative center on the first computing machine only changes within the specific limits, the first computing machine just does not need to send to above-mentioned target virtual bench the demand stock number of administrative center; In the time that the variation of the demand stock number of the administrative center on the first computing machine exceedes certain limit, the first computing machine just can send demand stock number or the default stock number after changing to above-mentioned target virtual bench.For example: the greatest requirements stock number of administrative center's last registration is N, current monitor demand stock number while being greater than N, the first computing machine just can send the stock number information for representing 125%N to above-mentioned target virtual bench, for example: the greatest requirements stock number of administrative center's last registration is N, current monitor demand stock number during lower than 80%N, the first computing machine just can send the stock number information for representing 75%N to above-mentioned target virtual bench.

Optionally, above-mentioned target virtual bench is dispatched the physical resource that is less than or equal to described stock number of described second computer to moving the step that described administrative center is used on described target virtual bench, can comprise:

Target virtual bench is less than or equal to the physical resource of described stock number to the physical source distributing device application of described second computer, and the physical resource of dispatching described application is to moving the use of described administrative center on described target virtual bench.

Be illustrated with cpu resource and internal memory below:

For cpu resource, this embodiment for example can arrange the cpu resource of above-mentioned target virtual bench, in advance by the CPU divider of second computer (: CPU Alloc) unified management, wherein, above-mentioned CPU divider can be managed all cpu resources on second computer; Like this in the time that above-mentioned target virtual bench does not have operations control center, CPU divider just can call less cpu resource and use to target virtual bench, for example: the calculating of a CPU divider invocation target virtual bench deploy is acted on behalf of needed cpu resource and used to target virtual bench.When on target virtual bench when operations control center, just can send to CPU divider the information of above-mentioned stock number, so that calling the cpu resource that is less than or equal to this stock number, CPU divider uses to the administrative center of target virtual bench.

For memory source, this embodiment can arrange in advance the memory source of above-mentioned target virtual bench and act on behalf of unified management by the memory management of second computer, and wherein, above-mentioned memory management agency can manage all memory sources on second computer; Like this in the time that above-mentioned target virtual bench does not have operations control center, memory management agency just can call less memory source and use to target virtual bench, for example: the calculating of a memory management agency invocation target virtual bench deploy is acted on behalf of needed memory source and used to target virtual bench.When on target virtual bench when operations control center, just can send to internal memory administration agent the information of above-mentioned stock number, so that being less than or equal to the memory source of this stock number, memory management proxy call uses to the administrative center of target virtual bench.

It should be noted that, above-mentioned stock number can comprise cpu resource amount and memory source amount, in addition, in this embodiment, the virtual management system Domain0 that above-mentioned target virtual bench can be Xen platform.

The physical resource that is less than or equal to described stock number that target virtual bench limits described second computer cannot be used by other virtual bench of described second computer, and the physical resource of dispatching described restriction uses to moving described administrative center on described target virtual bench, described other virtual bench is the arbitrary virtual bench except described target virtual bench in described second computer.

Be illustrated with cpu resource and internal memory below:

For cpu resource, target virtual bench (for example: Kvm is flat as middle virtual management system hostSytem) in this embodiment can be shared by efficient scheduling cpu resource itself, the physical resource that is less than or equal to described stock number that in this embodiment, target virtual bench only need to limit second computer like this cannot be used by other virtual bench of described second computer, limit the summation of the spendable stock number of other virtual bench on second computer, the total amount that this summation equals the CPU on second computer deducts above-mentioned calling to moving described administrative center use stock number on target virtual bench.

For memory source, in this embodiment, the memory source of above-mentioned target virtual bench is acted on behalf of unified management by the memory management of second computer, and wherein, above-mentioned memory management agency can manage all memory sources on second computer; Like this in the time that above-mentioned target virtual bench does not have operations control center, memory management agency just can call less memory source and use to target virtual bench, for example: the calculating of a memory management agency invocation target virtual bench deploy is acted on behalf of needed memory source and used to target virtual bench.When on target virtual bench when operations control center, just can send to internal memory administration agent the information of above-mentioned stock number, so that being less than or equal to the memory source of this stock number, memory management proxy call uses to the administrative center of target virtual bench.

It should be noted that, above-mentioned stock number can comprise cpu resource amount and memory source amount, and in addition, in this embodiment, above-mentioned target virtual bench can be that Kvm is flat as middle virtual management system hostSytem.

Optionally, after step 202, described method can also comprise:

Target virtual bench upgrades the version number of described administrative center, and the version number after described renewal is sent to the computing machine in described virtual cluster.

Like this when the computing machine in virtual cluster obtains above-mentioned version number, before just can comparing on computing machine, obtain the version number of former administrative center, if send the current version number obtaining higher than obtain before version number time, just know that the administrative center of virtual cluster has operated on above-mentioned second computer.

Technique scheme has increased the embodiment of plurality of optional on the basis of first embodiment, and can realize the resource of saving second computer, and the administrative center that can realize the virtual cluster of timely recovery.

Refer to Fig. 3, Fig. 3 is the schematic flow sheet of the another kind of administrative center dispositions method that provides of the embodiment of the present invention, as shown in Figure 3, comprises the following steps:

301, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the first virtual bench of the program of described administrative center, described the first virtual bench can directly be accessed the physical resource of described the first computing machine.

Above-mentioned the first virtual bench can be the virtual management system on the first computing machine.

302, the first virtual bench judges whether described administrative center has operated on the computing machine of described virtual cluster, and if so, described the first virtual bench forbids that the program of described administrative center starts.

Above-mentioned the first virtual bench forbids that the program startup of described administrative center can be understood as, do not start the program of administrative center, because the first virtual bench is not activated the program of administrative center, thereby the first virtual bench just does not need to take too much resource, for example, the first virtual bench only need to take the first virtual bench deploy calculating generation needed resource just.

Optionally, above-mentioned the first virtual bench judges that whether described administrative center has operated in the step on the computing machine of described virtual cluster, can comprise:

The first virtual bench receives the current version number of the described administrative center of the computing machine transmission of described virtual cluster, and judge that whether described current version number is identical with the version number of the described administrative center of described the first virtual bench storage, if not, determine that described administrative center has operated on the computing machine of described virtual cluster, if so, determine on the current computing machine that does not operate in described virtual cluster of described administrative center.

When on the current computing machine that does not operate in described virtual cluster of definite described administrative center, the first virtual bench can also start the program of default administrative center of installing, to realize recovery management center on the first virtual bench.

Optionally, before step 301, described method can also comprise:

The first virtual bench sends to the computing machine of described virtual cluster the logout that described administrative center moves on described target virtual machine, described logout moves the stock number of the needed physical resource of described logout for calculating described administrative center, described stock number is greater than or equal to the stock number of the second virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described the second virtual bench is described virtual cluster; Or

Above-mentioned logout can a certain special time period logout, for example: the logout of nearly half an hour.In addition, the first virtual bench of above-mentioned the first computing machine can be running affairs in the operational process of center, can be periodically or interval certain hour monitor the demand stock number of this administrative center, or record the greatest requirements stock number of current administrative center, and the demand stock number that monitoring is obtained or greatest requirements stock number send to the second virtual bench.In addition, when the first computing machine sends after the demand stock number or greatest requirements stock number, and when the demand stock number of the administrative center on the first computing machine only changes within the specific limits, the first computing machine does not just need to send to above-mentioned the second virtual bench the demand stock number of administrative center; In the time that the variation of the demand stock number of the administrative center on the first computing machine exceedes certain limit, the first computing machine just can send demand stock number or the default stock number after changing to above-mentioned the second virtual bench.For example: the greatest requirements stock number of administrative center's last registration is N, current monitor demand stock number while being greater than N, the first computing machine just can send the stock number information for representing 125%N to above-mentioned the second virtual bench, for example: the greatest requirements stock number of administrative center's last registration is N, current monitor demand stock number during lower than 80%N, the first computing machine just can send the stock number information for representing 75%N to above-mentioned the second virtual bench.

Above-mentioned the second virtual bench is appreciated that the target virtual bench in the embodiment shown in Fig. 1 and Fig. 2.

In technique scheme, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the first virtual bench of the program of described administrative center; Described the first virtual bench judges whether described administrative center has operated on the computing machine of described virtual cluster, and if so, described the first virtual bench forbids that the program of described administrative center starts.Can realize like this administrative center while breaking down, and administrative center has been while having operated on the computing machine of described virtual cluster, the first virtual bench does not start administrative center, thereby realizes the resource of saving the first computing machine.

Be apparatus of the present invention embodiment below, apparatus of the present invention embodiment is for carrying out the method for the inventive method embodiment mono-to three realization, for convenience of explanation, only show the part relevant to the embodiment of the present invention, concrete ins and outs do not disclose, and please refer to the embodiment of the present invention one, embodiment bis-and embodiment tri-.

Refer to Fig. 4, Fig. 4 is the structural representation of a kind of virtual bench of providing of the embodiment of the present invention, as shown in Figure 4, comprising: start unit 41 and scheduling unit 42, wherein:

Start unit 41, for in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, start the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer.

Scheduling unit 42, uses to moving described administrative center on described target virtual bench for the physical resource of dispatching described second computer.

Refer to Fig. 5, Fig. 5 is the structural representation of the another kind of virtual bench that provides of the embodiment of the present invention, as shown in Figure 5, and start unit 51 and scheduling unit 52, wherein:

Start unit 51, for in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, start the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer.

Optionally, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, the computing machine of virtual cluster can select in the computing machine of virtual cluster the computing machine of applicable operations control center by default election algorithm, thus this computer run administrative center.For example: in the time that the administrative center on the first computing machine breaks down, when in the computing machine of virtual cluster, the load of second computer operation is minimum, the target virtual bench of second computer just can start the program of administrative center, thus operations control center on target virtual bench.Wherein, the implementation procedure of above-mentioned election algorithm can be as follows: start unit 51 can be in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, judge whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, if, start the program of preassembled described administrative center, move described administrative center to realize on described target virtual bench.

Wherein, judge whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, and can comprise:

F＝T-S×N-Δ×100/(H-L)

F＝T-S×N-Δ×50/(H-L)

Above-mentioned high load threshold excessively and too low load threshold are all the threshold values with the form of number percent, for example: cross high load threshold and too low load threshold and be respectively 80% and 20%, above-mentioned T can be 100, above-mentioned S can be 2, above-mentioned special time can be a period of time in the past, for example: the half an hour close with current time.

Scheduling unit 52, uses to moving described administrative center on described target virtual bench for the physical resource of the specific amount of resources of dispatching described second computer.

Optionally, as shown in Figure 6, described device can also comprise:

Computing unit 53, is deployed in the logout of the described administrative center on described the first computing machine for acquisition unit, and calculates the stock number of the needed physical resource of this logout;

The physical resource that is less than or equal to described stock number that scheduling unit 52 can be stated second computer for dispatching office is to moving the use of described administrative center on described target virtual bench.

Optionally, as shown in Figure 7, described device can also comprise:

Receiving element 54, for receive that described the first computing machine sends be deployed in the described administrative center action on described the first computing machine time needed physical resource stock number;

Optionally, at the embodiment shown in Fig. 6 and Fig. 7, scheduling unit 52 can be less than or equal to the physical resource of described stock number for the physical source distributing device application to described second computer, and the physical resource of dispatching described application is to moving the use of described administrative center on described target virtual bench; Or

Scheduling unit 52 can cannot be used by other virtual bench of described second computer for the physical resource that is less than or equal to described stock number that limits described second computer, and the physical resource of dispatching described restriction uses to moving described administrative center on described target virtual bench, described other virtual bench is the arbitrary virtual bench except described target virtual bench in described second computer.

Optionally, as shown in Figure 8, described device can also comprise:

Updating block 55, for upgrading the version number of described administrative center, and sends to the computing machine in described virtual cluster by the version number after described renewal.

Technique scheme has increased the embodiment of plurality of optional, and can realize the resource of saving second computer on the basis of first device embodiment, and the administrative center that can realize the virtual cluster of timely recovery.

Refer to Fig. 9, the structural representation of the another kind of virtual bench that Fig. 9 embodiment of the present invention provides, as shown in Figure 9, comprising: recovery unit 91, judging unit 92 and forbid unit 93, wherein:

Recovery unit 91, for in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the described virtual bench of the program of described administrative center, described virtual bench can directly be accessed the physical resource of described the first computing machine.

Above-mentioned virtual bench can be the virtual management system on the first computing machine.

Judging unit 92, for judging whether described administrative center has operated in the computing machine of described virtual cluster.

Forbid unit 93, for when the judged result of judging unit 92 is when being, forbid that the program of described administrative center starts.

Optionally, the current version number of described administrative center that judging unit 92 can send for receiving the computing machine of described virtual cluster, and judge that whether described current version number is identical with the version number of the described administrative center of described the first virtual bench storage, if not, determine that described administrative center has operated on the computing machine of described virtual cluster, if so, determine on the current computing machine that does not operate in described virtual cluster of described administrative center.

When on the current computing machine that does not operate in described virtual cluster of definite described administrative center, described virtual bench can also start the program of default administrative center of installing, to realize recovery management center on described virtual bench.

Optionally, as shown in figure 10, described device can also comprise:

The first transmitting element 94, for sending to the computing machine of described virtual cluster the logout that described administrative center moves on described virtual machine, described logout moves the stock number of the needed physical resource of described logout for calculating described administrative center, described stock number is greater than or equal to the stock number of target virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described target virtual bench is described virtual cluster.

Above-mentioned logout can a certain special time period logout, for example: the logout of nearly half an hour.

Optionally, as shown in figure 11, described device can also comprise:

The second transmitting element 95, the stock number of needed physical resource while action for send described administrative center to the computing machine of described virtual cluster, described stock number is greater than or equal to the stock number of target virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described target virtual bench is described virtual cluster.

In technique scheme, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the virtual bench of the program of described administrative center; Described virtual bench judges whether described administrative center has operated on the computing machine of described virtual cluster, and if so, described virtual bench forbids that the program of described administrative center starts.Can realize like this administrative center while breaking down, and administrative center has been while having operated on the computing machine of described virtual cluster, virtual bench does not start administrative center, thereby realizes the resource of saving the first computing machine.

Please refer to Figure 12, Figure 12 is the structural representation of a kind of computing node of providing of the embodiment of the present invention, as shown in figure 12, this computing node comprises: at least one processor 121, for example CPU, at least one network interface 122 or other user interfaces 123, storer 125, at least one communication bus 122.Communication bus 122 is for realizing the connection communication between these assemblies.This computing node 120 optionally comprises user interface 123, comprises display, keyboard or pointing device (for example, mouse, trace ball (trackball), touch-sensitive plate or touch sensitive display screen).Storer 125 may comprise high-speed RAM storer, also may also comprise non-unsettled storer (non-volatile memory), for example at least one magnetic disk memory.Storer 605 optionally can comprise at least one and be positioned at the memory storage away from aforementioned processing device 121.

In some embodiments, storer 125 has been stored following element, executable module or data structure, or their subset, or their superset:

Operating system 1251, comprises various system programs, for realizing various basic businesses and processing hardware based task;

Application program module 1252, comprises various application programs, for realizing various applied business.

In application program module 1252, include but not limited to one or more vCPU61, vCPU61 comprises vAPIC611, and described vAPIC611 comprises virtual register 6111.

In application program module 1252 specific implementation of each module referring to Fig. 7 and embodiment illustrated in fig. 8 in corresponding module, be not repeated herein.

In embodiments of the present invention, program or the instruction of storing by calling storer 125, processor 121 for:

In the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, control the program that target virtual bench starts preassembled described administrative center, on described target virtual bench, move described administrative center to realize, described target virtual bench is on the second computer being deployed in described virtual cluster, and can directly access the virtual bench of the physical resource of described second computer;

The physical resource of dispatching described second computer uses to moving described administrative center on described target virtual bench.

In above-mentioned each embodiment, further, described processor 121 can also be used for:

Acquisition unit is deployed in the logout of the described administrative center on described the first computing machine, and calculates the stock number of the needed physical resource of this logout.

Optionally, the physical resource of the described second computer of scheduling that processor 121 is carried out is given on described target virtual bench and is moved the operation that described administrative center is used, and can comprise:

The physical resource that is less than or equal to described stock number of dispatching described second computer uses to moving described administrative center on described target virtual bench.

Receive that described the first computing machine sends be deployed in the described administrative center action on described the first computing machine time needed physical resource stock number.

In above-mentioned each embodiment, further, the physical resource that is less than or equal to described stock number of the described second computer of scheduling that processor 121 is carried out is given on described target virtual bench and is moved the operation that described administrative center is used, and can comprise:

Physical source distributing device application to described second computer is less than or equal to the physical resource of described stock number, and the physical resource of dispatching described application is to moving the use of described administrative center on described target virtual bench; Or

The physical resource that is less than or equal to described stock number that limits described second computer cannot be used by other virtual bench of described second computer, and the physical resource of dispatching described restriction uses to moving described administrative center on described target virtual bench, described other virtual bench is the arbitrary virtual bench except described target virtual bench in described second computer.

Upgrade the version number of described administrative center, and the version number after described renewal is sent to the computing machine in described virtual cluster.

Optionally, when the administrative center of the virtual cluster under described the first computing machine when the first computing machine deploy that processor 121 is carried out breaks down, control the program that target virtual bench starts preassembled described administrative center, to realize the operation that moves described administrative center on described target virtual bench, can comprise:

In the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, control target virtual bench and judge whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, if, start the program of preassembled described administrative center, move described administrative center to realize on described target virtual bench.

Optionally, above-mentioned for representing the mark of carry load ability, can comprise:

F＝T-S×N-Δ×100/(H-L)

F＝T-S×N-Δ×50/(H-L)

In technique scheme, the target virtual bench that second computer is disposed is provided with the program of the administrative center of virtual batch of cluster in advance, in the time that the administrative center of the virtual cluster of the first computing machine deploy breaks down, target virtual bench just can start the program of above-mentioned administrative center, on this target virtual bench, move above-mentioned administrative center to realize, the physical resource that target virtual bench is dispatched described second computer again uses to moving described administrative center on described target virtual bench.Can realize like this while only having administrative center to break down, target virtual bench just starts the program of administrative center, while not breaking down in administrative center, target virtual bench can not start administrative center, thereby the program of the administrative center now starting on target virtual bench can not take the physical resource of second computer, thereby realize the resource of saving second computer.In addition, the program that only need to start administrative center in this technical method just can realize recovery management center, thereby can realize in the time that this computing machine breaks down, and recovers in time the administrative center of virtual cluster.

Please refer to Figure 13, Figure 13 is the structural representation of the another kind of computing node that provides of the embodiment of the present invention, as shown in figure 13, this computing node comprises: at least one processor 131, for example CPU, at least one network interface 132 or other user interfaces 133, storer 135, at least one communication bus 132.Communication bus 132 is for realizing the connection communication between these assemblies.This computing node 130 optionally comprises user interface 133, comprises display, keyboard or pointing device (for example, mouse, trace ball (trackball), touch-sensitive plate or touch sensitive display screen).Storer 135 may comprise high-speed RAM storer, also may also comprise non-unsettled storer (non-volatile memory), for example at least one magnetic disk memory.Storer 605 optionally can comprise at least one and be positioned at the memory storage away from aforementioned processing device 131.

In some embodiments, storer 135 has been stored following element, executable module or data structure, or their subset, or their superset:

Operating system 1351, comprises various system programs, for realizing various basic businesses and processing hardware based task;

Application program module 1352, comprises various application programs, for realizing various applied business.

In application program module 1352, include but not limited to one or more vCPU61, vCPU61 comprises vAPIC611, and described vAPIC611 comprises virtual register 6111.

In application program module 1352 specific implementation of each module referring to Fig. 7 and embodiment illustrated in fig. 8 in corresponding module, be not repeated herein.

In embodiments of the present invention, program or the instruction of storing by calling storer 135, processor 131 for:

Judge whether described administrative center has operated on the computing machine of described virtual cluster, if so, forbid that described the first virtual bench starts the program of described administrative center.

In above-mentioned each embodiment, further, what described processor 131 was carried out judges that whether described administrative center has operated on the computing machine of described virtual cluster, comprising:

Receive the current version number of the described administrative center of the computing machine transmission of described virtual cluster, and judge that whether described current version number is identical with the version number of the described administrative center of described the first virtual bench storage, if not, determine that described administrative center has operated on the computing machine of described virtual cluster, if so, determine on the current computing machine that does not operate in described virtual cluster of described administrative center.

Optionally, processor 131 can also be used for:

Send to the computing machine of described virtual cluster the logout that described administrative center moves on described target virtual machine, described logout moves the stock number of the needed physical resource of described logout for calculating described administrative center, described stock number is greater than or equal to the stock number of the second virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described the second virtual bench is described virtual cluster; Or

The stock number of needed physical resource while sending the action of described administrative center to the computing machine of described virtual cluster, described stock number is greater than or equal to the stock number of the second virtual bench to the physical resource of the described administrative center scheduling of operation, and the virtual bench that has described administrative center is disposed and moved to the computing machine that described the second virtual bench is described virtual cluster.

In technique scheme, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, recover to be provided with in advance in described the first computing machine the first virtual bench of the program of described administrative center; Judge whether described administrative center has operated on the computing machine of described virtual cluster, if so, forbid that described the first virtual bench starts the program of described administrative center.Can realize like this administrative center while breaking down, and administrative center has been while having operated on the computing machine of described virtual cluster, the first virtual bench does not start administrative center, thereby realizes the resource of saving the first computing machine.

Refer to Figure 14, Figure 14 is the structural representation that the embodiment of the present invention also provides a kind of computer system, as shown in figure 14, can comprise: the computing node 130 shown in the computing node 120 shown at least one Figure 12 and at least one Figure 13.

The description of the computing node of the embodiment of the present invention can, with reference to previous embodiment, repeat no more here.

To sum up, in the embodiment of the present invention, the default program that administrative center is installed of a virtual bench (for example: virtual management system) in virtual cluster in each computing machine, in the time that the administrative center of a virtual bench deploy breaks down, the virtual bench of another computing machine just can start the program of administrative center in time, move on this virtual bench to realize administrative center, and the virtual bench of other computing machine can not start the program of administrative center, thereby this falseness device does not need to take too much physical resource, to realize the resource of saving computing machine.In addition, because above-mentioned virtual bench was just disposed on computers before administrative center breaks down, be that virtual bench just moved before administrative center breaks down, for example, and virtual bench (: database has started some public services in the time of operation, device drives, network communication module), like this in the time starting the program of administrative center, this administrative center managing virtual cluster and service is outwards provided in time, thus realize timely recovery management center.

One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, can carry out the hardware that instruction is relevant by computer program to complete, described program can be stored in a computer read/write memory medium, this program, in the time carrying out, can comprise as the flow process of the embodiment of above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random access memory (Random Access Memory is called for short RAM) etc.

Above disclosed is only preferred embodiment of the present invention, certainly can not limit with this interest field of the present invention, and the equivalent variations of therefore doing according to the claims in the present invention, still belongs to the scope that the present invention is contained.

Claims

1. administrative center's dispositions method, is characterized in that, comprising:

2. the method for claim 1, is characterized in that, described target virtual bench starts the program of preassembled described administrative center, and with before realizing move described administrative center on described target virtual bench, described method also comprises:

3. the method for claim 1, is characterized in that, described target virtual bench starts the program of preassembled described administrative center, and with before realizing move described administrative center on described target virtual bench, described method also comprises:

4. method as claimed in claim 2 or claim 3, is characterized in that, the physical resource that is less than or equal to described stock number that described target virtual bench is dispatched described second computer uses to moving described administrative center on described target virtual bench, comprising:

5. the method as described in any one in claim 1-3, is characterized in that, described target virtual bench is dispatched the physical resource of described second computer to after moving the use of described administrative center on described target virtual bench, and described method also comprises:

6. the method as described in any one in claim 1-3, it is characterized in that, in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, target virtual bench starts the program of preassembled described administrative center, on described target virtual bench, move described administrative center to realize, comprising:

7. method as claimed in claim 6, is characterized in that, described for representing the mark of carry load ability, comprising:

F＝T-S×N-Δ×100/(H-L)

F＝T-S×N-Δ×50/(H-L)

8. administrative center's dispositions method, is characterized in that, comprising:

9. method as claimed in claim 8, is characterized in that, described the first virtual bench judges that whether described administrative center has operated on the computing machine of described virtual cluster, comprising:

10. method as claimed in claim 8 or 9, is characterized in that, before first virtual bench of program of described administrative center is installed in described the first computing machine of described recovery in advance, described method also comprises:

11. 1 kinds of virtual benchs, is characterized in that, comprising: start unit and scheduling unit, wherein:

12. virtual benchs as claimed in claim 11, is characterized in that, described device also comprises:

13. virtual benchs as claimed in claim 11, is characterized in that, described device also comprises:

14. virtual benchs as described in claim 12 or 13, it is characterized in that, described scheduling unit is for being less than or equal to the physical resource of described stock number to the physical source distributing device application of described second computer, and the physical resource of dispatching described application is to moving the use of described administrative center on described target virtual bench; Or

15. virtual benchs as described in any one in claim 11-13, is characterized in that, described device also comprises:

16. virtual benchs as described in any one in claim 11-13, it is characterized in that, start unit is in the time that the administrative center of the virtual cluster under described first computing machine of the first computing machine deploy breaks down, judge whether the current mark for representing carry load ability of described second computer is described virtual all computing machine highest score of concentrating, if, start the program of preassembled described administrative center, move described administrative center to realize on described target virtual bench.

17. virtual benchs as claimed in claim 16, is characterized in that, described for representing the mark of carry load ability, comprising:

F＝T-S×N-Δ×100/(H-L)

F＝T-S×N-Δ×50/(H-L)

18. 1 kinds of virtual benchs, is characterized in that, comprising: recovery unit, judging unit and forbid unit, wherein:

19. virtual benchs as claimed in claim 18, it is characterized in that, described judging unit is used for the current version number of the described administrative center of the computing machine transmission that receives described virtual cluster, and judge that whether described current version number is identical with the version number of the described administrative center of described the first virtual bench storage, if not, determine that described administrative center has operated on the computing machine of described virtual cluster, if so, determine on the current computing machine that does not operate in described virtual cluster of described administrative center.

20. virtual benchs as described in claim 18 or 19, is characterized in that, described device also comprises: