CN104102523A - Method for migrating virtual machine and resource scheduling platform - Google Patents
Method for migrating virtual machine and resource scheduling platform Download PDFInfo
- Publication number
- CN104102523A CN104102523A CN201310115555.6A CN201310115555A CN104102523A CN 104102523 A CN104102523 A CN 104102523A CN 201310115555 A CN201310115555 A CN 201310115555A CN 104102523 A CN104102523 A CN 104102523A
- Authority
- CN
- China
- Prior art keywords
- physical machine
- machine
- virtual machine
- migrated
- target physical
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
- G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5019—Workload prediction
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Power Sources (AREA)
Abstract
The invention provides a method for migrating a virtual machine and a resource scheduling platform. The method comprises the following steps: determining a first target physical machine; determining a to-be-migrated virtual machine on the first target physical machine; determining a second target physical machine to which the to-be-migrated virtual machine needs to be migrated; predicting the load predicting condition of a frame on which the second target physical machine is positioned after the to-be-migrated virtual machine is migrated according to the parameter information of the to-be-migrated virtual machine; if the load predicting condition of a frame on which the second target physical machine is positioned exceeds a first threshold value, determining a third target physical machine to which the to-be-migrated virtual machine needs to be migrated once again, wherein the third target physical machine and the second target physical machine are not positioned on the same frame. According to the method for migrating the virtual machine and the resource scheduling platform provided by the invention, the situation of overload of the frames on which the target physical machines are positioned after the virtual machine is migrated to the target physical machines can be avoided.
Description
Technical field
The present invention relates to virtual machine technique, relate in particular to a kind of migration virtual machine method and scheduling of resource platform.Background technology
In cluster virtual machine, the load meeting of the quantity of virtual machine and virtual machine constantly changes in time, therefore needs to monitor in real time the load of all virtual machines and the load of the physical machine that migration virtual machine arrives.The in the situation that, load few in virtual machine quantity being low, virtual machine centralized dispatching, on physical machine still less, and is shut down a part of physical machine, to reach energy-conservation object; The in the situation that, load many in virtual machine quantity being high, wake a part of spare physical machine up, and carry out load balance; , carry out the optimization of virtual machine position and dispose during in laod unbalance state at different virtual machines, alleviate each virtual machine in same physical machine to CPU(Central Processing Unit, central processing unit) and the competition of the resource such as internal memory.Therefore, how to move virtual machine and become to need badly the problem of solution.
Summary of the invention
The invention provides a kind of migration virtual machine method and scheduling of resource platform, to realize the reasonable migration of virtual machine, avoid some frame to occur extra-heavy situation owing to newly increasing virtual machine.
First aspect present invention provides a kind of method of moving virtual machine, be applied to dummy machine system, described dummy machine system comprises physical equipment platform and scheduling of resource platform, described physical equipment platform comprises at least one frame, in each frame, comprise at least one physical machine, resource in described every physical machine is abstracted at least one virtual machine, and described method comprises:
Determine first object physical machine, wherein, described first object physical machine comprises heavily loaded physical machine or underloading physical machine;
Determine the virtual machine to be migrated in described first object physical machine;
Determine the second target physical machine that described virtual machine to be migrated need to move to;
According to the parameter information of described virtual machine to be migrated, the load estimation situation of the frame of predicting described the second target physical machine place after described virtual machine (vm) migration to be migrated;
If the load estimation situation of the frame at described the second target physical machine place exceeds first threshold, redefine the 3rd target physical machine that need to move to for described virtual machine to be migrated, wherein, described the 3rd target physical machine and described the second target physical machine be not in same frame.
According to first aspect, in the possible implementation of the first, described according to the parameter information of described virtual machine to be migrated, the load estimation situation of the frame of predicting described the second target physical machine place after described virtual machine (vm) migration to be migrated, comprising:
According to the parameter information of described virtual machine to be migrated, predict the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated;
Obtain the current realtime power of described the second target physical machine place frame;
According to the current realtime power of described power prediction recruitment and described the second target physical machine place frame, the predicted power of the frame of determining described the second target physical machine place after described virtual machine (vm) migration to be migrated;
Correspondingly, if the load estimation situation of the frame at described the second target physical machine place exceeds first threshold, redefine the 3rd target physical machine that need to move to for described virtual machine to be migrated, comprising:
If described predicted power is greater than the rated power of the frame at described the second target physical machine place, for redefining, described virtual machine to be migrated need to move to the 3rd target physical machine.
The implementation possible according to the first, in the possible implementation of the second, also comprises:
If described predicted power is less than or equal to the rated power of the frame at described the second target physical machine place, described virtual machine (vm) migration to be migrated is arrived to described the second target physical machine.
The implementation possible according to the first, in the third possible implementation, also comprises:
Set in advance the first parameter list, the increased power amount of described the second target physical machine that described the first parameter list comprises historical record after increasing the virtual machine of every type, or multiple virtual machine (vm) migrations of historical record are to the mean value of described the second target physical machine increased power amount afterwards;
, described according to the parameter information of described virtual machine to be migrated, predict the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated, comprising:
According to the parameter information of described virtual machine to be migrated, inquire about described the first parameter list, obtain the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated.
According to first aspect, in the 4th kind of possible implementation, described definite first object physical machine comprises:
Adopt underloading detection subalgorithm to obtain the first underloading value of each physical machine on described physical equipment platform, the physical machine that described the first underloading value is more than or equal to underloading threshold value is as described first object physical machine; Or
Adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on described physical equipment platform, the physical machine that described the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
In conjunction with first aspect or the possible four kinds of modes in the cards of implementation to the of the first, in the 5th kind of possible implementation, described the second target physical machine of determining that described virtual machine to be migrated need to move to, comprising:
According to the temperature information of each physical machine on described physical equipment platform, determine the second target physical machine that described virtual machine to be migrated need to move to.
According to the 5th kind of possible implementation, in the 6th kind of possible implementation, on described physical equipment platform, the temperature information of each physical machine comprises the combination in any of following information:
Described each physical machine is apart from the Current Temperatures of distance, refrigerating efficiency grade or the physical machine in air port.
Second aspect present invention provides a kind of scheduling of resource platform, comprising:
The first determining unit, for determining first object physical machine, wherein, described first object physical machine comprises heavily loaded physical machine or underloading physical machine;
The second determining unit, for determining the virtual machine to be migrated in described first object physical machine;
The 3rd determining unit, for the second target physical machine of determining that described virtual machine to be migrated need to move to;
Predicting unit, for according to the parameter information of described virtual machine to be migrated, the load estimation situation of the frame of predicting described the second target physical machine place after described virtual machine (vm) migration to be migrated;
The 4th determining unit, exceed first threshold if be used for the load estimation situation of the frame at described the second target physical machine place, redefine the 3rd target physical machine that need to move to for described virtual machine to be migrated, wherein, described the 3rd target physical machine and described the second target physical machine be not in same frame.
According to second aspect, in the possible implementation of the first, described predicting unit specifically for:
According to the parameter information of described virtual machine to be migrated, predict the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated;
Obtain the current realtime power of described the second target physical machine place frame;
According to the current realtime power of described power prediction recruitment and described the second target physical machine place frame, the predicted power of the frame of determining described the second target physical machine place after described virtual machine (vm) migration to be migrated;
Correspondingly, described the 4th determining unit specifically for:
If described predicted power is greater than the rated power of the frame at described the second target physical machine place, for redefining, described virtual machine to be migrated need to move to the 3rd target physical machine.
The implementation possible according to the first, in the possible implementation of the second, the described the 4th determine also for:
If described predicted power is less than or equal to the rated power of the frame at described the second target physical machine place, described virtual machine (vm) migration to be migrated is arrived to described the second target physical machine.
The implementation possible according to the first, in the third possible implementation, also comprises:
Setting unit, be used for setting in advance the first parameter list, the increased power amount of described the second target physical machine that described the first parameter list comprises historical record after increasing the virtual machine of every type, or multiple virtual machine (vm) migrations of historical record are to the mean value of described the second target physical machine increased power amount afterwards;
, described predicting unit specifically for:
According to the parameter information of described virtual machine to be migrated, inquire about described the first parameter list, obtain the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated.
According to second aspect, in the 4th kind of possible implementation, described the first determining unit specifically for:
Adopt underloading detection subalgorithm to obtain the first underloading value of each physical machine on described physical equipment platform, the physical machine that described the first underloading value is more than or equal to underloading threshold value is as described first object physical machine; Or
Adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on described physical equipment platform, the physical machine that described the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
In conjunction with second aspect or four kinds of modes in the cards of the first mode to the in the cards, in the 5th kind of possible implementation, described the 3rd determining unit specifically for:
According to the temperature information of each physical machine on described physical equipment platform, determine the second target physical machine that described virtual machine to be migrated need to move to.
The method of migration virtual machine provided by the invention and scheduling of resource platform, before by virtual machine (vm) migration to the second target physical machine to be migrated in first object physical machine, prejudge after virtual machine (vm) migration to the second target physical machine to be migrated, whether the load estimation situation of the second target physical machine place frame exceeds default first threshold, then determine whether virtual machine (vm) migration to the second target physical machine to be migrated according to judged result, to avoid after virtual machine (vm) migration to the second target physical machine to be migrated, the load upper limit that exceeds the frame at the second target physical machine place causes some equipment (for example power supply in this frame, fan, physical machine etc.) overwork, situation about even cannot normally work.
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 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 that moves according to an embodiment of the invention the method for virtual machine;
Fig. 2 is the schematic flow sheet that moves according to another embodiment of the present invention the method for virtual machine;
Fig. 3 is according to the schematic flow sheet of the method for the migration virtual machine of further embodiment of this invention;
Fig. 4 is the structural representation of scheduling of resource platform according to yet another embodiment of the invention;
Fig. 5 is the structural representation of scheduling of resource platform according to another embodiment of the present invention;
Fig. 6 is according to the structural representation of the scheduling of resource platform of further embodiment of this invention.
Embodiment
For making object, technical scheme and the advantage of the embodiment of the present invention clearer, 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 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.
Embodiment for a better understanding of the present invention, need to introduce the system architecture of the embodiment of the present invention, and system architecture can be divided into cloud application layer, cluster virtual machine, physical equipment platform, resource management platform:
Cloud application layer, for providing cloud application program to user, its medium cloud application program can comprise multiple processes, and process need to create on virtual machine, can be the corresponding virtual machine of a process, can be also the corresponding virtual machines of multiple processes;
Cluster virtual machine, is made up of virtual machine, serves a cluster virtual machine of virtual machine composition of an identical cloud application.Wherein, the resource of virtual machine is again to be provided by the physical machine on physical equipment platform, can be the corresponding physical machine of a virtual machine, can be also the corresponding physical machine of many virtual machines.
Physical equipment platform, comprises at least one physical machine, and for the physical resource of the required use of virtual machine is provided, for cloud application provides physical entity, the resource in every physical machine is abstracted at least one virtual machine.This physical equipment platform comprises at least one frame, and each frame comprises at least one physical machine, and a cluster virtual machine can be corresponding to the physical machine in one or more frame.
Resource management platform, the physical resource providing according to physical equipment platform is that each cloud application creates at least one virtual machine, is responsible for the scheduling of cluster virtual machine, the operation conditions of monitoring cloud application simultaneously.
Embodiment mono-
The present embodiment provides a kind of method of moving virtual machine, the method is applied to dummy machine system, dummy machine system comprises physical equipment platform and scheduling of resource platform, physical equipment platform comprises at least one frame, in each frame, comprise at least one physical machine, the resource in every physical machine is abstracted at least one virtual machine.The executive agent of the present embodiment is resource management platform.
As shown in Figure 1, for according to the schematic flow sheet of the method for the migration virtual machine of the present embodiment.
Step 101, determines first object physical machine, and wherein, first object physical machine comprises heavily loaded physical machine or underloading physical machine.
Heavy duty physical machine is the heavier physical machine of load, and underloading physical machine is the lighter physical machine of load.Specifically can set a threshold value and judge, in the time that the load of certain physical machine exceedes this threshold value, be called heavily loaded physical machine, in the time that the load of certain physical machine is less than or equal to this threshold value, be called underloading physical machine.
Step 102, determines the virtual machine to be migrated in first object physical machine.
The situation of migration virtual machine can be: when in the lower situation of virtual machine negligible amounts in a certain frame, load (Capacity), by the virtual machine (vm) migration in the first object physical machine in this frame on other physical machine, make electricity under this first object physical machine, this first object physical machine quits work; Or the load of working as a certain first object physical machine is larger, the load of another target physical machine hour, by the virtual machine (vm) migration in this first object physical machine to another target physical machine, so that the load of first object physical machine reduces, make the each virtual machine in first object physical machine obtain the resource increases such as CPU and internal memory.Certainly can also move according to actual needs virtual machine, specifically can set according to actual conditions.
Step 103, determines the second target physical machine that virtual machine to be migrated need to move to.
The second target physical machine can be predefined, also can according to predefined rules selection out, not limit at this.
Step 104, according to the parameter information of virtual machine to be migrated, the load estimation situation of the frame at prediction the second target physical machine place after virtual machine (vm) migration to be migrated.
The parameter information of virtual machine to be migrated can comprise the CPU(Central Processing Unit of virtual machine, central processing unit) quantity and dominant frequency, memory size, network interface card speed, CPU take up room, EMS memory occupation space, realtime power etc.Static parameter in parameter information can be pre-stored within first object physical machine, and dynamic parameter can Real-time Obtaining.
The load estimation situation of the present embodiment can be general power situation, air outlet temperature conditions, air intake vent temperature conditions of frame etc., does not limit at this.
It is pointed out that this step 104 is steps of a prediction, pre-estimate by after on virtual machine (vm) migration to the second target physical machine to be migrated the loading condition of the second target physical machine place frame according to virtual machine parameter information.For example, in the time that loading condition is general power situation, if predicted power is less than or equal to the rated power of the frame at the second target physical machine place, by virtual machine (vm) migration to be migrated to the second target physical machine.
Step 105, if the load estimation situation of the frame at the second target physical machine place exceeds first threshold, redefines the 3rd target physical machine that need to move to for virtual machine to be migrated.
Wherein, the 3rd target physical machine and the second target physical machine be not in same frame.
First threshold can be predefined according to actual needs.In the time that the loading condition of the frame at the second target physical machine place exceeds first threshold, need to find next target physical machine and move this virtual machine to be migrated, the 3rd target physical machine of being about to is as the second new target physical machine, and repeating step 104, until virtual machine (vm) migration to be migrated is complete or do not have the second target physical machine to meet transition condition.
According to the method for the migration virtual machine of the present embodiment, before by virtual machine (vm) migration to the second target physical machine to be migrated in first object physical machine, prejudge after virtual machine (vm) migration to the second target physical machine to be migrated, whether the load estimation situation of the second target physical machine place frame exceeds default first threshold, then determine whether virtual machine (vm) migration to the second target physical machine to be migrated according to judged result, to avoid after virtual machine (vm) migration to the second target physical machine to be migrated, the load upper limit that exceeds the frame at the second target physical machine place causes some equipment (for example power supply in this frame, fan, physical machine etc.) overwork, situation about even cannot normally work.
Embodiment bis-
The present embodiment provides a kind of method of moving virtual machine based on embodiment mono-.
As shown in Figure 2, for according to the schematic flow sheet of the method for the migration virtual machine of the present embodiment.
Step 200, adopts underloading detection subalgorithm to obtain the first underloading value of each physical machine on physical equipment platform, and the physical machine that the first underloading value is more than or equal to underloading threshold value is as first object physical machine; Or adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on physical equipment platform, the physical machine that the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
This step 200 is for determining the operation of first object physical machine.In the present embodiment, each target physical machine and virtual machine physical machine can have respectively identification information separately.
Underloading in the present embodiment detects subalgorithm and is called again underloading index computational algorithm, and heavy duty detects subalgorithm and is called again heavily loaded index computational algorithm.
Adopt following formula to obtain the first underloading value L of each physical machine in physical equipment platform
i:
wherein i physical machine in i represents physical equipment platform, total k physical machine in physical equipment platform, i and k are the integer that is more than or equal to 1.
Wherein, in the time that the utilization rate of i physical machine is less than default underloading threshold value, the utilization rate of default i the physical machine of underloading threshold value-the of S=; In the time that the utilization rate of i physical machine is more than or equal to default underloading threshold value, L=0.
In the present embodiment, the utilization rate of i physical machine can represent memory usage, CPU usage of i physical machine etc., and underloading threshold value can be set according to actual needs, and the default underloading threshold settings in the present embodiment is 45%.Underloading threshold value also can be set according to actual needs, for example, be 0.In practical operation, can calculate respectively memory usage and the CPU usage of i physical machine, in the time that internal memory underloading value corresponding to memory usage and CPU underloading value corresponding to CPU usage are all greater than underloading threshold value, judging this physical machine is first object physical machine, need the virtual machine in this first object physical machine of migration, now, the first underloading value comprises internal memory underloading value and CPU underloading value.In the time that the first underloading value in first object physical machine is more than or equal to underloading threshold value, illustrate that the virtual machine in this first object physical machine is less, virtual machine (vm) migration in this first object physical machine can be moved away completely, and by electricity under this first object physical machine.
Adopt following formula to obtain the first heavy duty value H of physical equipment platform
i:
wherein i physical machine in i represents physical equipment platform, total k physical machine in the first frame, i and k are the integer that is more than or equal to 1.
Wherein, in the time that the utilization rate of i physical machine is greater than default heavy load door limit value, utilization rate-heavy load door limit value of Y=i physical machine; In the time that the utilization rate of i physical machine is less than or equal to default heavy load door limit value, H=0.
In the present embodiment, the utilization rate of i physical machine can represent memory usage, CPU usage of i physical machine etc., and default heavy load door limit value can be set according to actual needs, and the default heavy load door limit value in the present embodiment is set as 81%.Heavy duty threshold value also can be set according to actual needs, for example, be 0.In practical operation, can calculate respectively memory usage and the CPU usage of i physical machine, in the time that internal memory corresponding to memory usage heavy duty value and the heavily loaded value of CPU corresponding to CPU usage are all greater than heavily loaded threshold value, judging this physical machine is first object physical machine, need the virtual machine in this first object physical machine of migration, now, the first heavy duty value comprises internal memory heavy duty value and CPU heavy duty value.In the time that the heavy duty of first in first object physical machine value is more than or equal to heavily loaded threshold value, illustrate that the virtual machine in this first object physical machine is more, virtual machine (vm) migration in this first object physical machine can be gone out to a part, alleviate the burden of this first object physical machine.
In the time that scheduling of resource platform finds that according to above-mentioned algorithm the first underloading value of first object physical machine is more than or equal to underloading threshold value, judge this first object physical machine underloading, can be by the virtual machine (vm) migration in this first object physical machine on other physical machine, and this first object physical machine is carried out to lower electricity operation.In the time that scheduling of resource platform finds that according to above-mentioned algorithm the first heavy duty value of first object physical machine is more than or equal to heavily loaded threshold value, judge this first object physical machine heavy duty, can carry out the operation that powers on to some physical machine in the cluster virtual machine at this first object physical machine place, in the physical machine that virtual machine (vm) migration in this first object physical machine is powered on to these, to alleviate the burden of this first object physical machine.
Step 201, determines the virtual machine to be migrated in first object physical machine.
Step 202, determines the second target physical machine.
This step can be specifically:
Obtain the second load value of each physical machine of the physical machine cluster at physical machine to be migrated place;
The physical machine that the second load value is less than or equal to Second Threshold is as target physical machine.
In the present embodiment, the second load value can be the realtime power of each physical machine.This step is in order to determine the second target physical machine.Realtime power taking the second load value as each physical machine is example, because the each physical machine in the physical machine cluster at physical machine to be migrated place all can be used as virtual machine (vm) migration physical machine extremely, now, can therefrom select physical machine that a load value is lighter as the second target physical machine.Specifically can obtain as the above-mentioned method of obtaining the first underloading value the realtime power of each physical machine, and using the physical machine that wherein realtime power is less than Second Threshold as the second target physical machine.Can ensure that like this virtual machine (vm) migration is to this second target physical machine, this second target physical machine can not exceed rated power as far as possible.
Step 203, according to the parameter information of virtual machine to be migrated, inquiry the first parameter list, obtains the power prediction recruitment of the second target physical machine after virtual machine (vm) migration to be migrated.
This first parameter list is the first parameter list setting in advance, the increased power amount of the second target physical machine that this first parameter list comprises historical record after increasing the virtual machine of every type, or the mean value of the increased power amount of multiple virtual machine (vm) migrations of historical record after the second target physical machine.
This first parameter list can be pre-stored in resource management platform, also can be stored in independent storer, as long as can be got by resource management platform.
Step 204, obtains the current realtime power of the second target physical machine place frame.
In the present embodiment, resource management platform obtains the realtime power of the frame at the second target physical machine place, concrete acquisition methods can be to send request by resource management platform to the each physical machine in the frame at the second target physical machine place, each physical machine in this frame receives the realtime power that returns to current the machine after this request to resource management platform, resource management platform just can obtain the realtime power of the frame at the second target physical machine place according to the realtime power of each physical machine in the frame at the second target physical machine place, the realtime power sum that is each physical machine is exactly the current realtime power of the frame at the second target physical machine place.
Particularly, the realtime power of the frame at the second target physical machine place equals the realtime power sum of each physical machine in the frame at the second target physical machine place.The obtain manner of the realtime power of the frame at the second target physical machine place can also be: to the controller switching equipment in the frame at the second target physical machine place, for example intelligent PDU(Protocol Data Unit, protocol Data Unit PDU), the current realtime power of the frame at inquiry the second target physical machine place.Controller switching equipment can be by inquiring about the realtime power of each physical machine and calculating the realtime power sum of each physical machine, thereby obtain the realtime power of the frame at the second target physical machine place.
Step 205, according to the current realtime power of power prediction recruitment and the second target physical machine place frame, the predicted power of the frame of determining the second target physical machine place after virtual machine (vm) migration to be migrated.
Current realtime power+power prediction recruitment of the predicted power=the second target physical machine place frame of the frame at the second target physical machine place after virtual machine (vm) migration to be migrated.
Step 206, whether the load estimation situation that judges the frame at the second target physical machine place has exceeded first threshold, if predicted power is greater than the rated power of the frame at the second target physical machine place, perform step 207, if predicted power is less than or equal to the rated power of the frame at the second target physical machine place, perform step 208.
Step 207, if predicted power is greater than the rated power of the frame at the second target physical machine place, redefine for virtual machine to be migrated the 3rd target physical machine that need to move to, next return to execution step 203, using the 3rd target physical machine as the second new target physical machine.
Step 208, by virtual machine (vm) migration to be migrated to the second target physical machine.
It is pointed out that in the present embodiment, in the time there is no virtual machine in first object physical machine, by electricity under first object physical machine.In the time that the number of first object physical machine electric under needs is greater than 1, preferentially by electricity under the physical machine that in first object physical machine, refrigerating efficiency is minimum., in the time not having the number of physical machine of virtual machine to be greater than 1, by electricity under physical machine minimum refrigerating efficiency.
According to the method for the migration virtual machine of the present embodiment, in the time judging the virtual machine that need move in first object physical machine, first calculate the second target physical machine that underloading value determines that virtual machine need migrate to, then the realtime power of the frame at this target physical machine place after predicting on virtual machine (vm) migration to the second target physical machine, and judge whether this realtime power exceeds the rated power of this frame, determine whether on virtual machine (vm) migration to the second target physical machine according to judged result, to ensure after the operation of carrying out on virtual machine (vm) migration to the second target physical machine, the frame at the second target physical machine place can overflow fixed load, and then ensure the normal work of this frame.
Embodiment tri-
The present embodiment provides a kind of schematic flow sheet of method of moving virtual machine.
As shown in Figure 3, for according to the schematic flow sheet of the method for the migration virtual machine of the present embodiment.
Step 300, adopts underloading detection subalgorithm to obtain the first underloading value of each physical machine on physical equipment platform, and the physical machine that the first underloading value is more than or equal to underloading threshold value is as first object physical machine; Or adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on physical equipment platform, the physical machine that the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
This step 300 is for determining the operation of first object physical machine.In the present embodiment, each target physical machine and virtual machine physical machine can have respectively identification information separately.This step is identical with step 200, does not repeat them here.
Step 301, determines the virtual machine to be migrated in first object physical machine.
Step 302, according to the temperature information of each physical machine on physical equipment platform, determines the second target physical machine that virtual machine to be migrated need to move to.
This step is the operation of determining the second target physical machine.This temperature information can comprise the combination in any of following information: each physical machine is apart from the Current Temperatures of distance, refrigerating efficiency grade or the physical machine in air port.
Wherein, judge the height of refrigerating efficiency, can judge according to the distance of physical machine and air outlet, be specially, with the nearest physical machine of air outlet be the physical machine that refrigerating efficiency is the highest, with air outlet distance physical machine be farthest the physical machine that refrigerating efficiency is minimum.
Alternatively, considering in temperature information, to it is also conceivable that the realtime power situation of the second target physical machine, realtime power is less than to physical machine that the 3rd threshold value and temperature be less than the 4th threshold value as the second target physical machine.
Step 303, according to the parameter information of virtual machine to be migrated, inquiry the first parameter list, obtains the temperature prediction recruitment of the second target physical machine after virtual machine (vm) migration to be migrated.
This first parameter list is the first parameter list setting in advance, the increased power amount of the second target physical machine that this first parameter list comprises historical record after increasing the virtual machine of every type, or the mean value of the increased power amount of multiple virtual machine (vm) migrations of historical record after the second target physical machine.
This first parameter list can be pre-stored in resource management platform, also can be stored in independent storer, as long as can be got by resource management platform.
Step 304, obtains the current realtime power of the second target physical machine place frame.
In the present embodiment, resource management platform obtains the realtime power of the frame at the second target physical machine place, concrete acquisition methods can be to send request by resource management platform to the each physical machine in the frame at the second target physical machine place, each physical machine in this frame receives the realtime power that returns to current the machine after this request to resource management platform, resource management platform just can obtain the realtime power of the frame at the second target physical machine place according to the realtime power of each physical machine in the frame at the second target physical machine place, the realtime power sum that is each physical machine is exactly the current realtime power of the frame at the second target physical machine place.
Particularly, the realtime power of the frame at the second target physical machine place equals the realtime power sum of each physical machine in the frame at the second target physical machine place.The obtain manner of the realtime power of the frame at the second target physical machine place can also be: to the controller switching equipment in the frame at the second target physical machine place, and for example intelligent PDU, the current realtime power of the frame at inquiry the second target physical machine place.Controller switching equipment can be by inquiring about the realtime power of each physical machine and calculating the realtime power sum of each physical machine, thereby obtain the realtime power of the frame at the second target physical machine place.
Step 305, according to the current realtime power of power prediction recruitment and the second target physical machine place frame, the predicted power of the frame of determining the second target physical machine place after virtual machine (vm) migration to be migrated.
Current realtime power+power prediction recruitment of the predicted power=the second target physical machine place frame of the frame at the second target physical machine place after virtual machine (vm) migration to be migrated.
Step 306, whether the load estimation situation that judges the frame at the second target physical machine place has exceeded first threshold, if predicted power is greater than the rated power of the frame at the second target physical machine place, perform step 307, if predicted power is less than or equal to the rated power of the frame at the second target physical machine place, perform step 308.
Step 307, if predicted power is greater than the rated power of the frame at the second target physical machine place, need to move to the 3rd target physical machine for virtual machine to be migrated redefines.
Step 308, by virtual machine (vm) migration to be migrated to the second target physical machine.
According to the method for the migration virtual machine of the present embodiment, in the time judging the virtual machine that need move in first object physical machine, first calculate the second target physical machine that temperature that underloading value determines that virtual machine need migrate to is less than Second Threshold, then the realtime power of the frame at this target physical machine place after predicting on virtual machine (vm) migration to the second target physical machine, and judge whether this realtime power exceeds the rated power of this frame, determine whether on virtual machine (vm) migration to the second target physical machine according to judged result, to ensure after the operation of carrying out on virtual machine (vm) migration to the second target physical machine, the frame at the second target physical machine place can overflow fixed load, and then ensure the normal work of this frame.
Embodiment tetra-
The present embodiment describes the method for above-mentioned migration virtual machine with a specific embodiment.
As shown in table 1, be the information of a physical machine cluster.
Table 1
Suppose, detect subalgorithm according to underloading and judge physical machine 1 for first object physical machine, judging physical machine 7 is the second target physical machine, the virtual machine VM0 on 1 physically can be moved in physical machine 7.First, obtain the realtime power 550W of frame 3, and to obtain the increased power amount that virtual machine VM0 migrates in physical machine 7 be 20W, the predicted power=550W+20W=570W of frame 3, it is less than the rated power 600W of frame 3, the VM0 in physical machine 1 can be migrated in physical machine 7.
Suppose, judge and the virtual machine VM0 in physical machine 1 can be migrated in physical machine 7, or the virtual machine VM1 in physical machine 2 can be migrated on virtual machine 7, according to the refrigerating efficiency in table 1, can first move the virtual machine VM1 in the physical machine 2 that refrigerating efficiency is lower, and after VM1 migrates in physical machine 7, physical machine 2 is carried out to lower electricity operation.
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can complete by the relevant hardware of programmed instruction, aforesaid program can be stored in a computer read/write memory medium, this program, in the time carrying out, is carried out the step that comprises said method embodiment; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CDs.
Embodiment five
The present embodiment provides a kind of scheduling of resource platform, for carrying out the method for migration virtual machine of embodiment mono-.
As shown in Figure 4, for according to the structural representation of the scheduling of resource platform of the present embodiment.This scheduling of resource platform 400 comprises the first determining unit 401, the second determining unit 402, the 3rd determining unit 403, predicting unit 404 and the 4th determining unit 405.
Wherein, the first determining unit 401 is for determining first object physical machine, and wherein, first object physical machine comprises heavily loaded physical machine or underloading physical machine; The second determining unit 402 is for determining the virtual machine to be migrated in the determined first object physical machine of the first determining unit 401; The second target physical machine of the 3rd determining unit 403 for determining that the determined virtual machine to be migrated of the second determining unit 402 need to move to; Predicting unit 404 is for according to the parameter information of virtual machine to be migrated, the load estimation situation of the frame at prediction the second target physical machine place after virtual machine (vm) migration to be migrated; If the 4th determining unit 405 exceeds first threshold for the load estimation situation of the frame at the second target physical machine place, redefine the 3rd target physical machine that need to move to for virtual machine to be migrated, wherein, the 3rd target physical machine and the second target physical machine be not in same frame.
The concrete operations mode of this scheduling of resource platform 400 is consistent with embodiment mono-, does not repeat them here.
According to the scheduling of resource platform 400 of the present embodiment, in the time judging the virtual machine that need move in first object physical machine, first calculate the target physical machine that underloading value determines that virtual machine need migrate to, then predict the realtime power of second frame at this target physical machine place after virtual machine (vm) migration is to target physical machine, and judge whether this realtime power exceeds the rated power of the second frame, determine whether virtual machine (vm) migration to target physical machine according to judged result, to ensure after carrying out the operation of virtual machine (vm) migration to target physical machine, second frame at target physical machine place can overflow fixed load, and then the normal work of guarantee the second frame.
Embodiment six
The present embodiment provides a kind of scheduling of resource platform based on embodiment five, for carrying out the method for migration virtual machine of embodiment bis-or embodiment tri-.
As shown in Figure 5, for according to the structural representation of the scheduling of resource platform of the present embodiment.This scheduling of resource platform 500 comprises the first determining unit 501, the second determining unit 502, the 3rd determining unit 503, predicting unit 504 and the 4th determining unit 505.
Predicting unit 504 in the present embodiment can be specifically for:
According to the parameter information of virtual machine to be migrated, the power prediction recruitment of prediction the second target physical machine after virtual machine (vm) migration to be migrated;
Obtain the current realtime power of the second target physical machine place frame;
According to the current realtime power of power prediction recruitment and the second target physical machine place frame, the predicted power of the frame of determining the second target physical machine place after virtual machine (vm) migration to be migrated.
Correspondingly, the 4th determining unit 505 specifically for:
If predicted power is greater than the rated power of the frame at the second target physical machine place, for redefining, virtual machine to be migrated need to move to the 3rd target physical machine.
Alternatively, the 4th determining unit 505 of the scheduling of resource platform 500 of the present embodiment also for: if predicted power is less than or equal to the rated power of the frame at the second target physical machine place, by virtual machine (vm) migration to be migrated to the second target physical machine.
Alternatively, the scheduling of resource platform 500 of the present embodiment also comprises setting unit 506, this setting unit 506 is for setting in advance the first parameter list, the increased power amount of the second target physical machine that the first parameter list comprises historical record after increasing the virtual machine of every type, or the mean value of the increased power amount of multiple virtual machine (vm) migrations of historical record after the second target physical machine., predicting unit 504 specifically for: according to the parameter information of virtual machine to be migrated, the first default parameter list of inquiry setting unit 506, obtains the power prediction recruitment of the second target physical machine after virtual machine (vm) migration to be migrated.
Alternatively, the first determining unit 501 specifically for:
Adopt underloading detection subalgorithm to obtain the first underloading value of each physical machine on physical equipment platform, the physical machine that the first underloading value is more than or equal to underloading threshold value is as first object physical machine; Or
Adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on physical equipment platform, the physical machine that the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
Alternatively, the 3rd determining unit 503 specifically for:
According to the temperature information of each physical machine on physical equipment platform, determine the second target physical machine that virtual machine to be migrated need to move to.
According to the scheduling of resource platform 500 of the present embodiment, in the time judging the virtual machine that need move in first object physical machine, first calculate the second target physical machine that underloading value and/or temperature determine that virtual machine need migrate to, then the realtime power of the frame at this second target physical machine place after predicting on virtual machine (vm) migration to the second target physical machine, and judge whether this realtime power exceeds the rated power of this frame, determine whether on virtual machine (vm) migration to the second target physical machine according to judged result, to ensure after the operation of carrying out on virtual machine (vm) migration to the second target physical machine, the frame at target physical machine place can overflow fixed load, and then ensure the normal work of this frame.
Embodiment seven
The present embodiment provides another kind of scheduling of resource platform, for carrying out the method for migration virtual machine of embodiment mono-to embodiment tetra-.
As shown in Figure 6, for according to the structural representation of the scheduling of resource platform of the present embodiment.This scheduling of resource platform 600 comprises at least one processor 601, communication bus 602, storer 603 and at least one communication interface 604.
Wherein, communication bus 602 is for realizing connection the communication between said modules, and communication interface 504 is for being connected with the network equipment and communicating by letter.This bus can be ISA(Industry Standard Architecture, industry standard architecture) bus, PCI(Peripheral Component, peripheral component interconnect) bus or EISA(Extended Industry Standard Architecture, extended industry-standard architecture) bus etc.Bus can be one or more physical circuit, in the time being many physical circuits, can be divided into address bus, data bus, control bus etc.
Wherein, storer 603 is for stores executable programs code, and wherein, processor 601 moves the program corresponding with executable program code by the executable program code of storage in read memory 603, for:
Determine first object physical machine, wherein, first object physical machine comprises heavily loaded physical machine or underloading physical machine;
Determine the virtual machine to be migrated in first object physical machine;
Determine the second target physical machine that virtual machine to be migrated need to move to;
According to the parameter information of virtual machine to be migrated, the load estimation situation of the frame at prediction the second target physical machine place after virtual machine (vm) migration to be migrated;
If the load estimation situation of the frame at the second target physical machine place exceeds first threshold, redefine the 3rd target physical machine that need to move to for virtual machine to be migrated, wherein, the 3rd target physical machine and the second target physical machine be not in same frame.
Alternatively, when processor 601 by read memory 603 in storage executable program code move the program corresponding with executable program code, for according to the parameter information of virtual machine to be migrated, when the load estimation situation of the frame of predicting the second target physical machine place after virtual machine (vm) migration to be migrated, can be specifically:
According to the parameter information of virtual machine to be migrated, the power prediction recruitment of prediction the second target physical machine after virtual machine (vm) migration to be migrated;
Obtain the current realtime power of the second target physical machine place frame;
According to the current realtime power of power prediction recruitment and the second target physical machine place frame, the predicted power of the frame of determining the second target physical machine place after virtual machine (vm) migration to be migrated;
Correspondingly, when processor 601 by read memory 603 in storage executable program code move the program corresponding with executable program code, if the load estimation situation for the frame at the second target physical machine place exceeds first threshold, while redefining the 3rd target physical machine that need to move to for virtual machine to be migrated, can be specifically:
If predicted power is greater than the rated power of the frame at the second target physical machine place, for redefining, virtual machine to be migrated need to move to the 3rd target physical machine.
Alternatively, processor 601 can also move the program corresponding with executable program code by the executable program code of storage in read memory 603, if be less than or equal to the rated power of the frame at the second target physical machine place for predicted power, by virtual machine (vm) migration to be migrated to the second target physical machine.
Alternatively, processor 601 also moves the program corresponding with executable program code by the executable program code of storage in read memory 603, for:
Set in advance the first parameter list, the increased power amount of the second target physical machine that the first parameter list comprises historical record after increasing the virtual machine of every type, or the mean value of the increased power amount of multiple virtual machine (vm) migrations of historical record after the second target physical machine;
; when processor 601 also by read memory 603 in storage executable program code move the program corresponding with executable program code; for according to the parameter information of virtual machine to be migrated; when the power prediction recruitment of the second target physical machine of predicting after virtual machine (vm) migration to be migrated, can be specifically:
According to the parameter information of virtual machine to be migrated, inquiry the first parameter list, obtains the power prediction recruitment of the second target physical machine after virtual machine (vm) migration to be migrated.
Alternatively, when processor 601 also by read memory 603 in the executable program code of storage move the program corresponding with executable program code, for determining when first object physical machine, can be specifically:
Adopt underloading detection subalgorithm to obtain the first underloading value of each physical machine on physical equipment platform, the physical machine that the first underloading value is more than or equal to underloading threshold value is as first object physical machine; Or
Adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on physical equipment platform, the physical machine that the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
Alternatively, the executable program code that processor 601 is stored in by read memory 603 move the program corresponding with executable program code for determine virtual machine to be migrated need to move to the second target physical machine time, can be specifically:
According to the temperature information of each physical machine on physical equipment platform, determine the second target physical machine that virtual machine to be migrated need to move to.
Wherein, on physical equipment platform, the temperature information of each physical machine comprises the combination in any of following information: each physical machine is apart from the Current Temperatures of distance, refrigerating efficiency grade or the physical machine in air port
According to the scheduling of resource platform 600 of the present embodiment, before by virtual machine (vm) migration to the second target physical machine to be migrated in first object physical machine, prejudge after virtual machine (vm) migration to the second target physical machine to be migrated, whether the load estimation situation of the second target physical machine place frame exceeds default first threshold, then determine whether virtual machine (vm) migration to the second target physical machine to be migrated according to judged result, to avoid after virtual machine (vm) migration to the second target physical machine to be migrated, the load upper limit that exceeds the frame at the second target physical machine place causes some equipment (for example power supply in this frame, fan, physical machine etc.) overwork, situation about even cannot normally work.
Finally it should be noted that: above embodiment only, in order to technical scheme of the present invention to be described, is not intended to limit; Although the present invention is had been described in detail with reference to previous embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement; And these amendments or replacement do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (13)
1. one kind is moved the method for virtual machine, it is characterized in that, be applied to dummy machine system, described dummy machine system comprises physical equipment platform and scheduling of resource platform, described physical equipment platform comprises at least one frame, in each frame, comprise at least one physical machine, the resource in described every physical machine is abstracted at least one virtual machine, and described method comprises:
Determine first object physical machine, wherein, described first object physical machine comprises heavily loaded physical machine or underloading physical machine;
Determine the virtual machine to be migrated in described first object physical machine;
Determine the second target physical machine that described virtual machine to be migrated need to move to;
According to the parameter information of described virtual machine to be migrated, the load estimation situation of the frame of predicting described the second target physical machine place after described virtual machine (vm) migration to be migrated;
If the load estimation situation of the frame at described the second target physical machine place exceeds first threshold, redefine the 3rd target physical machine that need to move to for described virtual machine to be migrated, wherein, described the 3rd target physical machine and described the second target physical machine be not in same frame.
2. the method for migration virtual machine according to claim 1, it is characterized in that, described according to the parameter information of described virtual machine to be migrated, the load estimation situation of the frame of predicting described the second target physical machine place after described virtual machine (vm) migration to be migrated, comprising:
According to the parameter information of described virtual machine to be migrated, predict the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated;
Obtain the current realtime power of described the second target physical machine place frame;
According to the current realtime power of described power prediction recruitment and described the second target physical machine place frame, the predicted power of the frame of determining described the second target physical machine place after described virtual machine (vm) migration to be migrated;
Correspondingly, if the load estimation situation of the frame at described the second target physical machine place exceeds first threshold, redefine the 3rd target physical machine that need to move to for described virtual machine to be migrated, comprising:
If described predicted power is greater than the rated power of the frame at described the second target physical machine place, for redefining, described virtual machine to be migrated need to move to the 3rd target physical machine.
3. the method for migration virtual machine according to claim 2, is characterized in that, also comprises:
If described predicted power is less than or equal to the rated power of the frame at described the second target physical machine place, described virtual machine (vm) migration to be migrated is arrived to described the second target physical machine.
4. the method for migration virtual machine according to claim 2, is characterized in that, also comprises:
Set in advance the first parameter list, the increased power amount of described the second target physical machine that described the first parameter list comprises historical record after increasing the virtual machine of every type, or multiple virtual machine (vm) migrations of historical record are to the mean value of described the second target physical machine increased power amount afterwards;
, described according to the parameter information of described virtual machine to be migrated, predict the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated, comprising:
According to the parameter information of described virtual machine to be migrated, inquire about described the first parameter list, obtain the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated.
5. the method for migration virtual machine according to claim 1, is characterized in that, described definite first object physical machine comprises:
Adopt underloading detection subalgorithm to obtain the first underloading value of each physical machine on described physical equipment platform, the physical machine that described the first underloading value is more than or equal to underloading threshold value is as described first object physical machine; Or
Adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on described physical equipment platform, the physical machine that described the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
6. according to the method for the migration virtual machine described in claim 1-5 any one, it is characterized in that, described the second target physical machine of determining that described virtual machine to be migrated need to move to, comprising:
According to the temperature information of each physical machine on described physical equipment platform, determine the second target physical machine that described virtual machine to be migrated need to move to.
7. the method for migration virtual machine according to claim 6, is characterized in that, on described physical equipment platform, the temperature information of each physical machine comprises the combination in any of following information:
Described each physical machine is apart from the Current Temperatures of distance, refrigerating efficiency grade or the physical machine in air port.
8. a scheduling of resource platform, is characterized in that, comprising:
The first determining unit, for determining first object physical machine, wherein, described first object physical machine comprises heavily loaded physical machine or underloading physical machine;
The second determining unit, for determining the virtual machine to be migrated in described first object physical machine;
The 3rd determining unit, for the second target physical machine of determining that described virtual machine to be migrated need to move to;
Predicting unit, for according to the parameter information of described virtual machine to be migrated, the load estimation situation of the frame of predicting described the second target physical machine place after described virtual machine (vm) migration to be migrated;
The 4th determining unit, exceed first threshold if be used for the load estimation situation of the frame at described the second target physical machine place, redefine the 3rd target physical machine that need to move to for described virtual machine to be migrated, wherein, described the 3rd target physical machine and described the second target physical machine be not in same frame.
9. scheduling of resource platform according to claim 8, is characterized in that, described predicting unit specifically for:
According to the parameter information of described virtual machine to be migrated, predict the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated;
Obtain the current realtime power of described the second target physical machine place frame;
According to the current realtime power of described power prediction recruitment and described the second target physical machine place frame, the predicted power of the frame of determining described the second target physical machine place after described virtual machine (vm) migration to be migrated;
Correspondingly, described the 4th determining unit specifically for:
If described predicted power is greater than the rated power of the frame at described the second target physical machine place, for redefining, described virtual machine to be migrated need to move to the 3rd target physical machine.
10. scheduling of resource platform according to claim 9, is characterized in that, described the 4th determining unit also for:
If described predicted power is less than or equal to the rated power of the frame at described the second target physical machine place, described virtual machine (vm) migration to be migrated is arrived to described the second target physical machine.
11. scheduling of resource platforms according to claim 9, is characterized in that, also comprise:
Setting unit, be used for setting in advance the first parameter list, the increased power amount of described the second target physical machine that described the first parameter list comprises historical record after increasing the virtual machine of every type, or multiple virtual machine (vm) migrations of historical record are to the mean value of described the second target physical machine increased power amount afterwards;
, described predicting unit specifically for:
According to the parameter information of described virtual machine to be migrated, inquire about described the first parameter list, obtain the power prediction recruitment of described the second target physical machine after described virtual machine (vm) migration to be migrated.
12. scheduling of resource platforms according to claim 8, is characterized in that, described the first determining unit specifically for:
Adopt underloading detection subalgorithm to obtain the first underloading value of each physical machine on described physical equipment platform, the physical machine that described the first underloading value is more than or equal to underloading threshold value is as described first object physical machine; Or
Adopt heavy duty detection subalgorithm to obtain the first heavy duty value of each physical machine on described physical equipment platform, the physical machine that described the first heavy duty value is more than or equal to heavily loaded threshold value is as first object physical machine.
Scheduling of resource platform in 13. according to Claim 8～12 described in any one, is characterized in that, described the 3rd determining unit specifically for:
According to the temperature information of each physical machine on described physical equipment platform, determine the second target physical machine that described virtual machine to be migrated need to move to.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310115555.6A CN104102523A (en) | 2013-04-03 | 2013-04-03 | Method for migrating virtual machine and resource scheduling platform |
| PCT/CN2014/072029 WO2014161391A1 (en) | 2013-04-03 | 2014-02-13 | Method for migrating virtual machine and resource scheduling platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310115555.6A CN104102523A (en) | 2013-04-03 | 2013-04-03 | Method for migrating virtual machine and resource scheduling platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104102523A true CN104102523A (en) | 2014-10-15 |
Family
ID=51657557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310115555.6A Pending CN104102523A (en) | 2013-04-03 | 2013-04-03 | Method for migrating virtual machine and resource scheduling platform |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104102523A (en) |
| WO (1) | WO2014161391A1 (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104461822A (en) * | 2014-11-12 | 2015-03-25 | 北京百度网讯科技有限公司 | Supervision method and device for capacity of data center |
| CN105045359A (en) * | 2015-07-28 | 2015-11-11 | 深圳市万普拉斯科技有限公司 | Heat dissipation control method and apparatus |
| CN105159751A (en) * | 2015-09-17 | 2015-12-16 | 河海大学常州校区 | Energy-efficient virtual machine migration method in cloud data center |
| CN105357292A (en) * | 2015-10-29 | 2016-02-24 | 北京汉柏科技有限公司 | Method and system for balancing dynamic load of cloud platform |
| WO2016078391A1 (en) * | 2014-11-21 | 2016-05-26 | 华为技术有限公司 | Virtual machine migration method, virtualized infrastructure manger and coordinator |
| CN105718310A (en) * | 2016-01-13 | 2016-06-29 | 上海应用技术学院 | Virtual machine scheduling method for IO dense application under cloud platform |
| CN105930202A (en) * | 2016-04-29 | 2016-09-07 | 合肥工业大学 | Migration policy for virtual machine with three thresholds |
| CN106445677A (en) * | 2015-08-06 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Load balancing method and device |
| CN107506233A (en) * | 2016-06-14 | 2017-12-22 | 深圳市深信服电子科技有限公司 | A kind of schedule virtual resources method, apparatus and server |
| CN108337179A (en) * | 2017-01-19 | 2018-07-27 | 华为技术有限公司 | Link flow control method and device |
| CN108804210A (en) * | 2018-04-23 | 2018-11-13 | 北京奇艺世纪科技有限公司 | A kind of resource allocation method and device of cloud platform |
| CN108984271A (en) * | 2018-07-20 | 2018-12-11 | 浪潮电子信息产业股份有限公司 | Load balancing method and related equipment |
| CN109358952A (en) * | 2018-10-30 | 2019-02-19 | 张家口浩扬科技有限公司 | A kind of virtual machine migration method and system |
| CN109857521A (en) * | 2019-01-23 | 2019-06-07 | 华为技术服务有限公司 | A kind of host conveying method and device |
| CN110727392A (en) * | 2018-07-17 | 2020-01-24 | 阿里巴巴集团控股有限公司 | Cloud storage data unit scheduling method and device |
| CN110955513A (en) * | 2018-09-27 | 2020-04-03 | 阿里巴巴集团控股有限公司 | Scheduling method and system of service resources |
| CN111831095A (en) * | 2019-04-16 | 2020-10-27 | 阿里巴巴集团控股有限公司 | Physical machine racking density optimization method, device and equipment |
| CN112433858A (en) * | 2020-12-17 | 2021-03-02 | 济南浪潮数据技术有限公司 | Load distribution method, device, equipment and readable storage medium |
| CN113626140A (en) * | 2021-06-30 | 2021-11-09 | 济南浪潮数据技术有限公司 | Virtual machine adjusting method and related device |
| WO2022048674A1 (en) * | 2020-09-07 | 2022-03-10 | 华为云计算技术有限公司 | Server cabinet-based virtual machine management method and apparatus |
| CN114237808A (en) * | 2020-09-07 | 2022-03-25 | 华为云计算技术有限公司 | Virtual machine management method and device based on server cabinet |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102016748A (en) * | 2008-04-21 | 2011-04-13 | 自适应计算企业股份有限公司 | System and method for managing energy consumption in a compute environment |
| CN102096601A (en) * | 2011-02-11 | 2011-06-15 | 浪潮(北京)电子信息产业有限公司 | Virtual machine migration management method and system |
| US20120023554A1 (en) * | 2010-07-21 | 2012-01-26 | Marco Murgia | Systems and methods for providing a smart group |
| US20120053925A1 (en) * | 2010-08-31 | 2012-03-01 | Steven Geffin | Method and System for Computer Power and Resource Consumption Modeling |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739287A (en) * | 2008-11-13 | 2010-06-16 | 国际商业机器公司 | Device, system and method for managing virtual machines |
| CN101504620A (en) * | 2009-03-03 | 2009-08-12 | 华为技术有限公司 | Load balancing method, apparatus and system of virtual cluster system |
-
2013
- 2013-04-03 CN CN201310115555.6A patent/CN104102523A/en active Pending
-
2014
- 2014-02-13 WO PCT/CN2014/072029 patent/WO2014161391A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102016748A (en) * | 2008-04-21 | 2011-04-13 | 自适应计算企业股份有限公司 | System and method for managing energy consumption in a compute environment |
| US20120023554A1 (en) * | 2010-07-21 | 2012-01-26 | Marco Murgia | Systems and methods for providing a smart group |
| US20120053925A1 (en) * | 2010-08-31 | 2012-03-01 | Steven Geffin | Method and System for Computer Power and Resource Consumption Modeling |
| CN102959510A (en) * | 2010-08-31 | 2013-03-06 | 阿沃森特公司 | Method and system for computer power and resource consumption modeling |
| CN102096601A (en) * | 2011-02-11 | 2011-06-15 | 浪潮(北京)电子信息产业有限公司 | Virtual machine migration management method and system |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104461822A (en) * | 2014-11-12 | 2015-03-25 | 北京百度网讯科技有限公司 | Supervision method and device for capacity of data center |
| CN104461822B (en) * | 2014-11-12 | 2019-01-15 | 北京百度网讯科技有限公司 | A kind of the capacity monitoring and managing method and device of data center |
| WO2016078391A1 (en) * | 2014-11-21 | 2016-05-26 | 华为技术有限公司 | Virtual machine migration method, virtualized infrastructure manger and coordinator |
| CN105677441A (en) * | 2014-11-21 | 2016-06-15 | 华为技术有限公司 | Migration method of virtual machines, manager of virtual facility and coordinator |
| CN105677441B (en) * | 2014-11-21 | 2019-07-09 | 华为技术有限公司 | Virtual machine migration method, virtual facility manager and coordinator |
| CN105045359A (en) * | 2015-07-28 | 2015-11-11 | 深圳市万普拉斯科技有限公司 | Heat dissipation control method and apparatus |
| CN106445677A (en) * | 2015-08-06 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Load balancing method and device |
| CN105159751B (en) * | 2015-09-17 | 2018-11-09 | 河海大学常州校区 | The virtual machine migration method of energy efficient in a kind of cloud data center |
| CN105159751A (en) * | 2015-09-17 | 2015-12-16 | 河海大学常州校区 | Energy-efficient virtual machine migration method in cloud data center |
| CN105357292A (en) * | 2015-10-29 | 2016-02-24 | 北京汉柏科技有限公司 | Method and system for balancing dynamic load of cloud platform |
| CN105718310A (en) * | 2016-01-13 | 2016-06-29 | 上海应用技术学院 | Virtual machine scheduling method for IO dense application under cloud platform |
| CN105718310B (en) * | 2016-01-13 | 2018-09-18 | 上海应用技术学院 | The dispatching method of virtual machine that I/O intensive type is applied under a kind of cloud platform |
| CN105930202A (en) * | 2016-04-29 | 2016-09-07 | 合肥工业大学 | Migration policy for virtual machine with three thresholds |
| CN105930202B (en) * | 2016-04-29 | 2019-03-08 | 合肥工业大学 | A kind of virtual machine migration method of three threshold values |
| CN107506233B (en) * | 2016-06-14 | 2020-12-01 | 深信服科技股份有限公司 | Virtual resource scheduling method, device and server |
| CN107506233A (en) * | 2016-06-14 | 2017-12-22 | 深圳市深信服电子科技有限公司 | A kind of schedule virtual resources method, apparatus and server |
| CN108337179A (en) * | 2017-01-19 | 2018-07-27 | 华为技术有限公司 | Link flow control method and device |
| CN108804210B (en) * | 2018-04-23 | 2021-05-25 | 北京奇艺世纪科技有限公司 | Resource configuration method and device of cloud platform |
| CN108804210A (en) * | 2018-04-23 | 2018-11-13 | 北京奇艺世纪科技有限公司 | A kind of resource allocation method and device of cloud platform |
| CN110727392A (en) * | 2018-07-17 | 2020-01-24 | 阿里巴巴集团控股有限公司 | Cloud storage data unit scheduling method and device |
| CN110727392B (en) * | 2018-07-17 | 2023-07-14 | 阿里巴巴集团控股有限公司 | Cloud storage data unit scheduling method and device |
| CN108984271A (en) * | 2018-07-20 | 2018-12-11 | 浪潮电子信息产业股份有限公司 | Load balancing method and related equipment |
| CN110955513A (en) * | 2018-09-27 | 2020-04-03 | 阿里巴巴集团控股有限公司 | Scheduling method and system of service resources |
| CN110955513B (en) * | 2018-09-27 | 2023-04-25 | 阿里云计算有限公司 | Service resource scheduling method and system |
| CN109358952A (en) * | 2018-10-30 | 2019-02-19 | 张家口浩扬科技有限公司 | A kind of virtual machine migration method and system |
| CN109857521B (en) * | 2019-01-23 | 2021-06-01 | 华为技术服务有限公司 | Host computer relocation method and device |
| CN109857521A (en) * | 2019-01-23 | 2019-06-07 | 华为技术服务有限公司 | A kind of host conveying method and device |
| CN111831095A (en) * | 2019-04-16 | 2020-10-27 | 阿里巴巴集团控股有限公司 | Physical machine racking density optimization method, device and equipment |
| WO2022048674A1 (en) * | 2020-09-07 | 2022-03-10 | 华为云计算技术有限公司 | Server cabinet-based virtual machine management method and apparatus |
| CN114237808A (en) * | 2020-09-07 | 2022-03-25 | 华为云计算技术有限公司 | Virtual machine management method and device based on server cabinet |
| CN112433858A (en) * | 2020-12-17 | 2021-03-02 | 济南浪潮数据技术有限公司 | Load distribution method, device, equipment and readable storage medium |
| CN113626140A (en) * | 2021-06-30 | 2021-11-09 | 济南浪潮数据技术有限公司 | Virtual machine adjusting method and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2014161391A1 (en) | 2014-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104102523A (en) | Method for migrating virtual machine and resource scheduling platform | |
| EP3606008B1 (en) | Method and device for realizing resource scheduling | |
| US20140082202A1 (en) | Method and Apparatus for Integration of Virtual Cluster and Virtual Cluster System | |
| CN106133693B (en) | Moving method, device and the equipment of virtual machine | |
| CN102096601A (en) | Virtual machine migration management method and system | |
| US20210105322A1 (en) | Distributed storage system and data migration method | |
| CN102508718A (en) | Method and device for balancing load of virtual machine | |
| CN102696000A (en) | Methods and apparatus for coordinated energy management in virtualized data centers | |
| CN112888268A (en) | Energy-saving control method, device and equipment for data center machine room and storage medium | |
| US20110161483A1 (en) | Virtual server system and physical server selection method | |
| CN103473139A (en) | Virtual machine cluster resource allocation and scheduling method | |
| CN104461673B (en) | A kind of virtual machine (vm) migration determination method and device | |
| CN107220108B (en) | Method and system for realizing load balance of cloud data center | |
| CN111953732B (en) | Resource scheduling method and device in cloud computing system | |
| TWI533146B (en) | Virtual resource adjusting method, device and computer readable storage medium for storing thereof | |
| CN107506233B (en) | Virtual resource scheduling method, device and server | |
| CN107220125A (en) | A kind of cloud resource dispatching method and device | |
| CN103037109A (en) | Multicore equipment energy consumption management method and device | |
| CN105893155B (en) | Virtual machine control method for equalizing load and device | |
| CN114048006A (en) | Virtual machine dynamic migration method and device and storage medium | |
| JP6750368B2 (en) | Virtual machine control program, virtual machine control method, and virtual machine control device | |
| CN103984588B (en) | Virtual machine migration method based on temperature and system thereof | |
| US11150932B2 (en) | Virtual disk management for virtual disks accessed from compute only nodes | |
| CN104866375A (en) | Virtual machine migration method and apparatus | |
| CN111104203A (en) | Virtual machine decentralized scheduling method and device, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141015 |
|
| RJ01 | Rejection of invention patent application after publication |