CN105094944A - Virtual machine migration method and apparatus - Google Patents
Virtual machine migration method and apparatus Download PDFInfo
- Publication number
- CN105094944A CN105094944A CN201510317273.3A CN201510317273A CN105094944A CN 105094944 A CN105094944 A CN 105094944A CN 201510317273 A CN201510317273 A CN 201510317273A CN 105094944 A CN105094944 A CN 105094944A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- migration
- virtual machine
- migrated
- main frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
Embodiments of the invention disclose a virtual machine migration method and apparatus, and relate to the field of communication technologies, so that a virtual machine migration strategy that is more accurate is generated. The method provided by the embodiment of the invention comprises: obtaining first power consumption that represents a to-be-migrated host before migration, a target host, and network device resource usage of east-to-west flow consumption between the to-be-migrated host before migration and the target host, obtaining second power consumption that represents a to-be-migrated host after a virtual machine migrates, a target host, and network device resource usage of east-to-west flow consumption between the to-be-migrated host after migration and the target host, obtaining third power consumption that represents power consumption of the network device connected to the to-be-migrated host and the target host in a virtual machine migration process, generating a corresponding virtual machine migration strategy, and performing virtual machine migration according to the strategy. The present invention is applicable to a method and a process of virtual machine migration.
Description
Technical field
The present invention relates to communication technical field, particularly relate to a kind of virtual machine migration method and device.
Background technology
At present, cloud computing technology has more and more become the IT (InternetTechnology of industry hot topic, Internet technology) technology, data center's cloud also becomes the large trend of data center's development, the data center of Yun Huahou how scheduling virtual machine, the power consumption how effectively reducing data center by the scheduling of virtual machine become industry must faced by major issue.
In the prior art, under the prerequisite of Deterministic service level agreement, only consider the virtual machine (vm) migration on main frame low for efficiency on the high main frame of efficiency, simultaneously, reduce the frequency of operation of the low main frame of load, thus improve the efficiency of data center on the whole, reduce power consumption of data center.But, when adopting prior art to move virtual machine, by means of only the power consumption of data center size compared before the power consumption of data center after migration and migration, generate corresponding virtual machine (vm) migration strategy, the virtual machine (vm) migration strategy adopting such method to generate is inaccurate, and really can not reach the object reducing power consumption of data center.
Summary of the invention
A kind of virtual machine migration method that the embodiment of the present invention provides and device, can generate virtual machine (vm) migration strategy more accurately, realizes the object reducing power consumption of data center.
A kind of virtual machine migration method, comprising:
Obtain the first power consumption, described first power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before main frame to be migrated, destination host and migration before representing virtual machine (vm) migration, and described virtual machine is the virtual machine in described main frame to be migrated;
Obtain the second power consumption, described second power consumption is for the total power consumption of the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described main frame to be migrated, described destination host and migration after representing virtual machine (vm) migration;
Obtain the 3rd power consumption, described 3rd power consumption is the power consumption of the network equipment connecting described main frame to be migrated and described destination host in described virtual machine (vm) migration process;
According to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy;
Virtual machine in main frame to be migrated according to described virtual machine (vm) migration policy migration.
A kind of virtual machine (vm) migration device, comprising:
First acquiring unit, for obtaining the first power consumption, described first power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before main frame to be migrated, destination host and migration before representing virtual machine (vm) migration, and described virtual machine is the virtual machine in described main frame to be migrated;
Second acquisition unit, for obtaining the second power consumption, described second power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described main frame to be migrated, described destination host and migration after representing virtual machine (vm) migration;
3rd acquiring unit, for obtaining the 3rd power consumption, described 3rd power consumption is the power consumption of the network equipment connecting described main frame to be migrated and described destination host in described virtual machine (vm) migration process;
Generation unit, for according to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy;
Migration units, for the virtual machine in main frame to be migrated according to described virtual machine (vm) migration policy migration.
Embodiments provide a kind of virtual machine migration method and device, the front main frame to be migrated of migration is represented by obtaining, first power consumption of destination host and the front resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and main frame to be migrated after acquisition expression virtual machine (vm) migration, second power consumption of destination host and the rear resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and obtain the 3rd power consumption representing and connect the power consumption of the network equipment of described main frame to be migrated and described destination host in virtual machine (vm) migration process, generate respective virtual machine migration strategy, and carry out virtual machine (vm) migration according to this strategy, compare and prior art, the present invention is when generating virtual machines migration strategy, also consider virtual machine from a host migration to the process of another main frame, connect the power consumption of the network equipment of described main frame to be migrated and described destination host, generate virtual machine (vm) migration strategy more accurately, although can avoid numerically, before migration, host power consumption is greater than the power consumption of migration aft engine energy, if but in fact add the power consumption of intermediary network device in transition process, before the migration likely occurred, power consumption is less than power consumption sum in the rear power consumption of migration and transition process, to such an extent as to the inaccurate problem of virtual machine (vm) migration strategy generated.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
A kind of virtual machine migration method process flow diagram that Fig. 1 provides for the embodiment of the present invention;
The another kind of virtual machine migration method process flow diagram that Fig. 2 provides for the embodiment of the present invention;
The another kind of virtual machine migration method process flow diagram that Fig. 3 provides for the embodiment of the present invention;
The another kind of virtual machine migration method process flow diagram that Fig. 4 provides for the embodiment of the present invention;
A kind of virtual machine (vm) migration device that Fig. 5 provides for the embodiment of the present invention forms schematic diagram;
The another kind of virtual machine (vm) migration device that Fig. 6 provides for the embodiment of the present invention forms schematic diagram;
The another kind of virtual machine (vm) migration device that Fig. 7 provides for the embodiment of the present invention forms schematic diagram;
The another kind of virtual machine (vm) migration device that Fig. 8 provides for the embodiment of the present invention forms schematic diagram;
The another kind of virtual machine (vm) migration device that Fig. 9 provides for the embodiment of the present invention forms schematic diagram.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
Embodiments provide a kind of virtual machine migration method, as shown in Figure 1, comprising:
101, the first power consumption is obtained.
Wherein, described first power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before main frame to be migrated, destination host and migration before representing virtual machine (vm) migration.Described first power consumption comprises: destination host power consumption before host power consumption to be migrated, migration before moving, and the power consumption of the front network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration.It should be noted that, East and West direction flow is the flow of generation when carrying out data interaction between main frame to be migrated and destination host.
The power consumption model of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before moving is set up in cloud data center policies scheduler, when this sets up this power consumption model, do not consider that an intermediary network device carries the situation that multiple stage has the main frame of associated services relation simultaneously.It should be noted that to there is the East and West direction flow of the main frame of associated services relation much larger than the East and West direction flow without associated services main frame, such as:
It is f that monitoring agent node obtains the front East and West direction flow between described main frame to be migrated and described destination host of migration, then the power consumption that connection and the network device processing flow f between main frame to be migrated and destination host produce is:
Wherein, F is the accessible network traffics of this network equipment.The span of F is from F
minto F
max, work as f<F
mintime, then when this network equipment is in light condition, E is unloaded constant, as f ∈ [F
min,f
max] time, this network equipment is in proper network load, μ
1for the power consumption under network equipment proper working load increases slope, work as f>F
maxtime, this network equipment is in operate in saturation load, μ
1' be the dissipation factor under network equipment operate in saturation load.According to the formula of the network equipment power consumption of East and West direction traffic consumes between main frame to be migrated described before above-mentioned migration and described destination host, the total power consumption that can obtain the network equipment of East and West direction traffic consumes between main frame to be migrated and destination host is:
Wherein, k ' is the network equipment quantity of the process that communicates between main frame to be migrated and destination host.
The power consumption e of the main frame to be migrated that monitoring agent monitoring nodes arrives
nwith the power consumption e of destination host
m.Therefore, obtaining the first power consumption is:
It should be noted that, monitoring agent node is the monitoring resource equipment be deployed in each main frame, for monitoring the resource service condition in each main frame.
102, the second power consumption is obtained.
Wherein, described second power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after main frame to be migrated, destination host and migration after representing virtual machine (vm) migration.Described second power consumption comprises: described destination host power consumption after described host power consumption to be migrated, migration after moving, and the power consumption of the rear network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration.
The power consumption e of the main frame to be migrated that cloud data center policies scheduler arrives according to monitoring agent monitoring nodes
nwith the power consumption e of destination host
m, predict the power consumption of main frame to be migrated and destination host after virtual machine (vm) migration respectively.
After completing virtual machine (vm) migration, the power consumption of destination host can be predicted as:
Wherein, e
m' be the prediction power consumption of destination host, e
mfor the current power consumption of the destination host that monitoring agent monitoring nodes arrives, ρ
mfor the power consumption rate of growth of destination host, k " be from host migration to be migrated to the virtual machine number destination host, v
i,n(cpu) be the virtual cpu quantity of virtual machine i on main frame to be migrated, u
i(cpu) be the average service rate of the unit interval of virtual machine i.According to above-mentioned formula, the measurable power consumption completing destination host after virtual machine (vm) migration.
After completing virtual machine (vm) migration, the power consumption of main frame to be migrated can be predicted as:
Wherein, e
n' be the prediction power consumption of main frame to be migrated, e
nfor the current power consumption of the main frame to be migrated that monitoring agent monitoring nodes arrives, ρ
nfor the power consumption rate of growth of main frame to be migrated.The definition of other parameters in this formula is identical with the definition in the power consumption of destination host after computation migration, does not do repeat specification at this.
According to the power consumption model setting up the rear network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration in cloud data center policies scheduler, it is f ' that monitoring agent node obtains the rear East and West direction flow between described main frame to be migrated and described destination host of migration, then calculate and connect and power consumption that network device processing flow f ' between main frame to be migrated and destination host produces, in its circular and step 101, between main frame to be migrated and destination host, the computing method of the total power consumption of the network equipment of East and West direction traffic consumes are similar, do not repeat at this, the total power consumption that then can obtain the network equipment of East and West direction traffic consumes between main frame to be migrated and destination host is:
In sum, obtaining the second power consumption is:
In the process of acquisition second power consumption, after main frame virtual machine to be migrated all moves to destination host, East and West direction flow in the middle of each virtual machine is all realized alternately by the bus of destination host and internal memory, therefore can think that now main frame to be migrated is 0 to the East and West direction flow of destination host, the power consumption then connecting the network equipment between main frame to be migrated and destination host is no-load power consumption E, now, the second power consumption is:
103, the 3rd power consumption is obtained.
Wherein, described 3rd power consumption is the power consumption of the network equipment connecting described main frame to be migrated and described destination host in virtual machine (vm) migration process, and described virtual machine is the virtual machine in described main frame to be migrated.
It should be noted that, cloud data center policies scheduler determines virtual machine from host migration to be migrated to destination host and quantity thereof according to the capacity of destination host.
When virtual machine (vm) migration, by the image file of the virtual machine in main frame to be migrated being moved to the method in destination host, realize the migration of virtual machine.The image file of usual virtual machine is comparatively large, so whole bandwidth that can take the network equipment when moving are to meet the transmission of the image file of virtual machine.Therefore, can think when virtual machine (vm) migration, the flow connecting the network equipment of described main frame to be migrated and described destination host is flow d when taking network equipment average outlet bandwidth, and now, the power consumption in virtual machine (vm) migration process is:
Monitoring agent monitoring nodes to the image file size of virtual machine i be g
i, then the transit time that can obtain virtual machine is:
Wherein, k ' and k " definition all identical with the definition in step 102 with above-mentioned steps 101, do not repeat at this.
According to the transit time of the power consumption in virtual machine (vm) migration process and virtual machine, the 3rd power consumption that the prediction of cloud data center policies scheduler connects the network equipment of described main frame to be migrated and described destination host is:
104, according to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy.
105, the virtual machine in main frame to be migrated according to described virtual machine (vm) migration policy migration.
Embodiments provide a kind of virtual machine migration method, the front main frame to be migrated of migration is represented by obtaining, first power consumption of destination host and the front resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and main frame to be migrated after acquisition expression virtual machine (vm) migration, second power consumption of destination host and the rear resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and obtain the 3rd power consumption representing and connect the power consumption of the network equipment of described main frame to be migrated and described destination host in virtual machine (vm) migration process, generate respective virtual machine migration strategy, and carry out virtual machine (vm) migration according to this strategy, compare and prior art, the present invention is when generating virtual machines migration strategy, also consider virtual machine from a host migration to the process of another main frame, connect the power consumption of the network equipment of described main frame to be migrated and described destination host, generate virtual machine (vm) migration strategy more accurately, although can avoid numerically, before migration, host power consumption is greater than the power consumption of migration aft engine energy, if but in fact add the power consumption of intermediary network device in transition process, before the migration likely occurred, power consumption is less than power consumption sum in the rear power consumption of migration and transition process, to such an extent as to the inaccurate problem of virtual machine (vm) migration strategy generated.
In another embodiment provided by the invention, as shown in Figure 2, describe the concrete grammar flow process according to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy in detail, comprising:
201, judge in a virtual machine life cycle, whether described first power consumption is greater than described second power consumption and described 3rd power consumption sum.
Wherein, if the life cycle of virtual machine is τ, it should be noted that, τ is the mean value of the life cycle of each virtual machine in this cloud data center, and cloud data center policies scheduler judges whether to satisfy condition: the first power consumption * τ > (the second power consumption * τ+the three power consumption).Owing to connecting the power consumption of the network equipment of each station server, proportion shared in heart power consumption in the data also can not be ignored, therefore, if in the process of carrying out virtual machine (vm) migration, do not consider the network equipment total power consumption in virtual machine (vm) migration process, before then likely there is migration, host power consumption is less than the network equipment total power consumption sum in the power consumption and virtual machine (vm) migration process of moving aft engine energy, if there is such situation, so the transition process of this virtual machine does not just reach the effect reducing power consumption of data center, does not meet the object of carrying out virtual machine (vm) migration.But by deterministic process, add network equipment total power consumption in virtual machine (vm) migration process as judging one of parameter, then can avoid the generation of above-mentioned situation, thus make the virtual machine (vm) migration strategy of generation more accurate, to meet the demand reducing power consumption of data center by carrying out virtual machine (vm) migration.
If 202 are greater than, then whether meet after judging described virtual machine (vm) migration by the service-level agreement of the application that the virtual machine that moves carries.
If 203 meet, then generate described virtual machine (vm) migration strategy.
In another embodiment provided by the invention, as shown in Figure 3, perform after step 105, also comprise:
301, determine to move the main frame that in rear each main frame, load is minimum.
Wherein, the minimum main frame of the load determined might not be main frame to be migrated, but the main frame that load is minimum in whole data center.
302, after judging to carry out frequency reducing to the main frame that described load is minimum, whether the application that the virtual machine that the main frame that described load is minimum carries is corresponding can violate the service-level agreement of the application that virtual machine carries.
Wherein, down conversion process is carried out to main frame and is specially the frequency of operation reducing main frame, minimum main frame is selected to carry out down conversion process, because if the load of a main frame is low, illustrate that this main frame needs task to be processed relatively less, if this main frame also carries out work with higher frequency of operation like this, power consumption is higher.Therefore, by down conversion process, the frequency of operation arranging this main frame just in time can be satisfied the demand the frequency of operation of Processing tasks, also can play the effect reducing host power consumption, thus reduce the power consumption of data center.
If 303 do not violate, then frequency reducing operation is carried out to the main frame that described load is minimum.
In another embodiment provided by the invention, as shown in Figure 4, before described first power consumption of acquisition, described second power consumption, described 3rd power consumption, also comprise:
401, the correlation parameter in cloud data center running environment is obtained.
Wherein, described correlation parameter at least comprises: each virtual machine power consumption, each host power consumption, the power consumption connecting the network equipment of each main frame, virtual machine East and West direction flow, virtual machine image file size, connect the outlet bandwidth of the network equipment of each main frame.
402, according to described correlation parameter, the virtual cpu quantity of virtual machine, the average service rate of the unit interval of each virtual machine and the efficiency of each main frame on the power consumption rate of growth of each main frame in described cloud data center, the unit interval average power consumption of each host-physical CPU, each main frame is obtained.
Wherein, according to the efficiency calculated, inquired about the Host List of cloud data center by cloud data center query analyzer, in Host List, pick out the highest main frame of efficiency as destination host, and the minimum main frame of efficiency is as main frame to be migrated.
It should be noted that, above-mentioned steps 401 to step 402 is the steps performed in the virtual machine (vm) migration cycle, after the virtual machine (vm) migration completing one-period, then can repeat above-mentioned steps 401 to step 402, according to the new parameter got, generate new virtual machine (vm) migration strategy.
Embodiments provide a kind of virtual machine migration method, the front main frame to be migrated of migration is represented by obtaining, first power consumption of destination host and the front resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and main frame to be migrated after acquisition expression virtual machine (vm) migration, second power consumption of destination host and the rear resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and obtain the 3rd power consumption representing and connect the power consumption of the network equipment of described main frame to be migrated and described destination host in virtual machine (vm) migration process, generate respective virtual machine migration strategy, and carry out virtual machine (vm) migration according to this strategy, compare and prior art, the present invention is when generating virtual machines migration strategy, also consider virtual machine from a host migration to the process of another main frame, connect the power consumption of the network equipment of described main frame to be migrated and described destination host, generate virtual machine (vm) migration strategy more accurately, although can avoid numerically, before migration, host power consumption is greater than the power consumption of migration aft engine energy, if but in fact add the power consumption of intermediary network device in transition process, before the migration likely occurred, power consumption is less than power consumption sum in the rear power consumption of migration and transition process, to such an extent as to the inaccurate problem of virtual machine (vm) migration strategy generated.
Embodiments provide a kind of virtual machine (vm) migration device, as shown in Figure 5, comprising: the first acquiring unit 51, second acquisition unit 52, the 3rd acquiring unit 53, generation unit 54, migration units 55.
First acquiring unit 51, for obtaining the first power consumption.
Wherein, described first power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before main frame to be migrated, destination host and migration before representing virtual machine (vm) migration, and described virtual machine is the virtual machine in described main frame to be migrated.
Second acquisition unit 52, for obtaining the second power consumption.
Wherein, described second power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after main frame to be migrated, destination host and migration after representing virtual machine (vm) migration.
3rd acquiring unit 53, for obtaining the 3rd power consumption.
Wherein, described 3rd power consumption is the power consumption of the network equipment connecting described main frame to be migrated and described destination host in described virtual machine (vm) migration process.
Generation unit 54, for according to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy.
Migration units 55, for the virtual machine in main frame to be migrated according to described virtual machine (vm) migration policy migration.
In the optional constituted mode of the another kind of this device, as shown in Figure 6, described generation unit 54, also comprises: the first judgment sub-unit 541, second judgment sub-unit 542, generation subelement 543.
First judgment sub-unit 541, for judging in a virtual machine life cycle, whether described first power consumption is greater than described second power consumption and described 3rd power consumption sum.
Whether the second judgment sub-unit 542, if when being greater than described second power consumption and described 3rd power consumption sum for described first power consumption, met service-level agreement by the application that the virtual machine that moves carries after judging described virtual machine (vm) migration.
Generate subelement 543, if when meeting the service-level agreement by application that the virtual machine that moves carries after described virtual machine (vm) migration, then generate described virtual machine (vm) migration strategy.
In the optional constituted mode of the another kind of this device, as shown in Figure 7, described first acquiring unit also comprises: first obtains subelement 511, first computation subunit 512.
First obtains subelement 511, moves front host power consumption to be migrated, the front destination host power consumption of migration for obtaining, and the power consumption of the front network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration.
First computation subunit 512, for according to destination host power consumption before host power consumption to be migrated before described migration, described migration, and the power consumption sum of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before described migration, obtain described first power consumption.
In the optional constituted mode of the another kind of this device, as shown in Figure 8, described second acquisition unit 52 also comprises: second obtains subelement 521, second computation subunit 522.
Second obtains subelement 521, for described destination host power consumption after described host power consumption to be migrated, migration after obtaining described migration, and the power consumption of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after migration.
Second computation subunit 522, for according to destination host power consumption described after described host power consumption to be migrated, described migration, and the power consumption sum of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described migration, obtain the second power consumption.
In the optional constituted mode of the another kind of this device, as shown in Figure 9, described 3rd acquiring unit 53 also comprises: the 3rd obtains subelement 531, the 3rd computation subunit 532.
3rd obtains subelement 531, for obtaining the transit time of power consumption in virtual machine (vm) migration process and virtual machine.
3rd computation subunit 532, for long-pending according to the transit time of the power consumption in described virtual machine (vm) migration process and described virtual machine, obtains described 3rd power consumption.
Embodiments provide a kind of virtual machine (vm) migration device, the front main frame to be migrated of migration is represented by obtaining, the resource service condition of destination host and the front network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and main frame to be migrated after acquisition expression virtual machine (vm) migration, the resource service condition of destination host and the rear network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration, and obtain the 3rd power consumption representing and connect the power consumption of the network equipment of described main frame to be migrated and described destination host in virtual machine (vm) migration process, generate respective virtual machine migration strategy, and carry out virtual machine (vm) migration according to this strategy, compare and prior art, the present invention is when generating virtual machines migration strategy, also consider virtual machine from a host migration to the process of another main frame, connect the power consumption of the network equipment of described main frame to be migrated and described destination host, generate virtual machine (vm) migration strategy more accurately, although can avoid numerically, before migration, host power consumption is greater than the power consumption of migration aft engine energy, if but in fact add the power consumption of intermediary network device in transition process, before the migration likely occurred, power consumption is less than power consumption sum in the rear power consumption of migration and transition process, to such an extent as to the inaccurate problem of virtual machine (vm) migration strategy generated.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, between each embodiment identical similar part mutually see, what each embodiment stressed is the difference with other embodiments.Especially, for apparatus embodiments, because it is substantially similar to embodiment of the method, so describe fairly simple, relevant part illustrates see the part of embodiment of the method.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-OnlyMemory, ROM) or random store-memory body (RandomAccessMemory, RAM) etc.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (10)
1. a virtual machine migration method, is characterized in that, comprising:
Obtain the first power consumption, described first power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before main frame to be migrated, destination host and migration before representing virtual machine (vm) migration, and described virtual machine is the virtual machine in described main frame to be migrated;
Obtain the second power consumption, described second power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described main frame to be migrated, described destination host and migration after representing virtual machine (vm) migration;
Obtain the 3rd power consumption, described 3rd power consumption is the power consumption of the network equipment connecting described main frame to be migrated and described destination host in described virtual machine (vm) migration process;
According to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy;
Virtual machine in main frame to be migrated according to described virtual machine (vm) migration policy migration.
2. method according to claim 1, is characterized in that, described according to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy, specifically comprises:
Judge in a virtual machine life cycle, whether described first power consumption is greater than described second power consumption and described 3rd power consumption sum;
If be greater than, then whether met service-level agreement by the application that the virtual machine that moves carries after judging described virtual machine (vm) migration;
If meet, then generate described virtual machine (vm) migration strategy.
3. method according to claim 1, is characterized in that, described acquisition first power consumption, specifically comprises:
Obtain host power consumption to be migrated before moving, the front destination host power consumption of migration, and the power consumption of the front network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration;
According to destination host power consumption before host power consumption to be migrated before described migration, described migration, and the power consumption sum of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before described migration, obtain described first power consumption.
4. method according to claim 1, is characterized in that, described acquisition second power consumption, specifically comprises:
Described destination host power consumption after described host power consumption to be migrated, migration after obtaining described migration, and the power consumption of the rear network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration;
According to destination host power consumption described after described host power consumption to be migrated, described migration, and the power consumption sum of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described migration, obtain the second power consumption.
5. method according to claim 1, is characterized in that, described acquisition the 3rd power consumption, specifically comprises:
Power consumption in acquisition virtual machine (vm) migration process and the transit time of virtual machine;
Long-pending according to the transit time of the power consumption in described virtual machine (vm) migration process and described virtual machine, obtain described 3rd power consumption.
6. a virtual machine (vm) migration device, is characterized in that, comprising:
First acquiring unit, for obtaining the first power consumption, described first power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before main frame to be migrated, destination host and migration before representing virtual machine (vm) migration, and described virtual machine is the virtual machine in described main frame to be migrated;
Second acquisition unit, for obtaining the second power consumption, described second power consumption is for the resource service condition of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described main frame to be migrated, described destination host and migration after representing virtual machine (vm) migration;
3rd acquiring unit, for obtaining the 3rd power consumption, described 3rd power consumption is the power consumption of the network equipment connecting described main frame to be migrated and described destination host in described virtual machine (vm) migration process;
Generation unit, for according to described first power consumption, described second power consumption and described 3rd power consumption generating virtual machines migration strategy;
Migration units, for the virtual machine in main frame to be migrated according to described virtual machine (vm) migration policy migration.
7. device according to claim 6, is characterized in that, described generation unit, also comprises:
First judgment sub-unit, for judging in a virtual machine life cycle, whether described first power consumption is greater than described second power consumption and described 3rd power consumption sum;
Whether the second judgment sub-unit, if when being greater than described second power consumption and described 3rd power consumption sum for described first power consumption, met service-level agreement by the application that the virtual machine that moves carries after judging described virtual machine (vm) migration;
Generate subelement, if when meeting the service-level agreement by application that the virtual machine that moves carries after described virtual machine (vm) migration, then generate described virtual machine (vm) migration strategy.
8. device according to claim 6, is characterized in that, described first acquiring unit, comprising:
First obtains subelement, moves front host power consumption to be migrated, the front destination host power consumption of migration for obtaining, and the power consumption of the front network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host of migration;
First computation subunit, for according to destination host power consumption before host power consumption to be migrated before described migration, described migration, and the power consumption sum of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host before described migration, obtain described first power consumption.
9. want the device described in 6 according to right, it is characterized in that, described second acquisition unit, comprising:
Second obtains subelement, for described destination host power consumption after described host power consumption to be migrated, migration after obtaining described migration, and the power consumption of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after migration;
Second computation subunit, for according to destination host power consumption described after described host power consumption to be migrated, described migration, and the power consumption sum of the network equipment of East and West direction traffic consumes between described main frame to be migrated and described destination host after described migration, obtain the second power consumption.
10. device according to claim 6, is characterized in that, described 3rd acquiring unit, comprising:
3rd obtains subelement, for obtaining the transit time of power consumption in virtual machine (vm) migration process and virtual machine;
3rd computation subunit, for long-pending according to the transit time of the power consumption in described virtual machine (vm) migration process and described virtual machine, obtains described 3rd power consumption.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510317273.3A CN105094944B (en) | 2015-06-10 | 2015-06-10 | A kind of virtual machine migration method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510317273.3A CN105094944B (en) | 2015-06-10 | 2015-06-10 | A kind of virtual machine migration method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105094944A true CN105094944A (en) | 2015-11-25 |
| CN105094944B CN105094944B (en) | 2018-06-29 |
Family
ID=54575453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510317273.3A Active CN105094944B (en) | 2015-06-10 | 2015-06-10 | A kind of virtual machine migration method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105094944B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375987A (en) * | 2018-10-30 | 2019-02-22 | 张家口浩扬科技有限公司 | A kind of method and system of virtual machine selection physical machine |
| CN111488053A (en) * | 2020-04-17 | 2020-08-04 | 苏州浪潮智能科技有限公司 | Power consumption adjusting method and device of network function virtualization system |
| CN112671586A (en) * | 2020-12-29 | 2021-04-16 | 中盈优创资讯科技有限公司 | Automatic migration and guarantee method and device for service configuration |
| CN112948057A (en) * | 2021-03-08 | 2021-06-11 | 中国联合网络通信集团有限公司 | Virtual machine migration control method, cloud management platform and SDN manager |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090327781A1 (en) * | 2008-06-30 | 2009-12-31 | Sun Microsystems, Inc. | Method and system for power management in a virtual machine environment without disrupting network connectivity |
| CN102082692A (en) * | 2011-01-24 | 2011-06-01 | 华为技术有限公司 | Method and equipment for migrating virtual machines based on network data flow direction, and cluster system |
| CN103455373A (en) * | 2013-09-18 | 2013-12-18 | 浪潮电子信息产业股份有限公司 | Dynamic migration security framework of virtual machine |
| CN104050038A (en) * | 2014-06-27 | 2014-09-17 | 国家计算机网络与信息安全管理中心 | Virtual machine migration method based on policy perception |
| US20150052254A1 (en) * | 2012-05-04 | 2015-02-19 | Huawei Technologies Co., Ltd. | Virtual Machine Live Migration Method, Virtual Machine Deployment Method, Server, and Cluster System |
-
2015
- 2015-06-10 CN CN201510317273.3A patent/CN105094944B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090327781A1 (en) * | 2008-06-30 | 2009-12-31 | Sun Microsystems, Inc. | Method and system for power management in a virtual machine environment without disrupting network connectivity |
| CN102082692A (en) * | 2011-01-24 | 2011-06-01 | 华为技术有限公司 | Method and equipment for migrating virtual machines based on network data flow direction, and cluster system |
| US20150052254A1 (en) * | 2012-05-04 | 2015-02-19 | Huawei Technologies Co., Ltd. | Virtual Machine Live Migration Method, Virtual Machine Deployment Method, Server, and Cluster System |
| CN103455373A (en) * | 2013-09-18 | 2013-12-18 | 浪潮电子信息产业股份有限公司 | Dynamic migration security framework of virtual machine |
| CN104050038A (en) * | 2014-06-27 | 2014-09-17 | 国家计算机网络与信息安全管理中心 | Virtual machine migration method based on policy perception |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375987A (en) * | 2018-10-30 | 2019-02-22 | 张家口浩扬科技有限公司 | A kind of method and system of virtual machine selection physical machine |
| CN111488053A (en) * | 2020-04-17 | 2020-08-04 | 苏州浪潮智能科技有限公司 | Power consumption adjusting method and device of network function virtualization system |
| CN112671586A (en) * | 2020-12-29 | 2021-04-16 | 中盈优创资讯科技有限公司 | Automatic migration and guarantee method and device for service configuration |
| CN112671586B (en) * | 2020-12-29 | 2023-04-21 | 中盈优创资讯科技有限公司 | Automatic migration and guarantee method and device for service configuration |
| CN112948057A (en) * | 2021-03-08 | 2021-06-11 | 中国联合网络通信集团有限公司 | Virtual machine migration control method, cloud management platform and SDN manager |
| CN112948057B (en) * | 2021-03-08 | 2023-07-21 | 中国联合网络通信集团有限公司 | Virtual machine migration control method, cloud management platform and SDN manager |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105094944B (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu | Multi-objective decision-making for mobile cloud offloading: A survey | |
| US20200104184A1 (en) | Accelerated resource allocation techniques | |
| US10884795B2 (en) | Dynamic accelerator scheduling and grouping for deep learning jobs in a computing cluster | |
| CN104252337B (en) | Task executing method, boundary means and grid service server in computing system | |
| CN102111337B (en) | Method and system for task scheduling | |
| CN103294521B (en) | A kind of method reducing data center's traffic load and energy consumption | |
| Kim et al. | Multi-agent reinforcement learning-based resource management for end-to-end network slicing | |
| CN104038540A (en) | Method and system for automatically selecting application proxy server | |
| CN105094944A (en) | Virtual machine migration method and apparatus | |
| Sampaio et al. | Towards high-available and energy-efficient virtual computing environments in the cloud | |
| Ren et al. | Collaborative edge computing and caching with deep reinforcement learning decision agents | |
| Babu et al. | Energy efficient scheduling algorithm for cloud computing systems based on prediction model | |
| Atanov et al. | Development an intelligent task offloading system for edge-cloud computing paradigm | |
| Kang et al. | Scheduling multiple divisible loads in a multi-cloud system | |
| Verma et al. | MADLVF: an energy efficient resource utilization approach for cloud computing | |
| Khanh et al. | Fuzzy-based mobile edge orchestrators in heterogeneous IoT environments: An online workload balancing approach | |
| Ni et al. | Priced timed petri nets based resource allocation strategy for fog computing | |
| CN116402318A (en) | Multi-stage computing power resource distribution method and device for power distribution network and network architecture | |
| CN115543626A (en) | Power defect image simulation method adopting heterogeneous computing resource load balancing scheduling | |
| Fang et al. | A Scheduling Strategy for Reduced Power Consumption in Mobile Edge Computing | |
| CN104052624A (en) | Configuration management method and device | |
| CN109788061B (en) | Computing task deployment method and device | |
| Peng et al. | Resource optimization strategy for CPU intensive applications in cloud computing environment | |
| Yan et al. | MP-DQN Based Task Scheduling for RAN QoS Fluctuation Minimizing in Public Clouds | |
| Jamali et al. | Energy efficient task assignment algorithm framework in mo-bile cloud computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |