CN102567080A - Virtual machine position selection system facing load balance in cloud computation environment - Google Patents
Virtual machine position selection system facing load balance in cloud computation environment Download PDFInfo
- Publication number
- CN102567080A CN102567080A CN2012100013159A CN201210001315A CN102567080A CN 102567080 A CN102567080 A CN 102567080A CN 2012100013159 A CN2012100013159 A CN 2012100013159A CN 201210001315 A CN201210001315 A CN 201210001315A CN 102567080 A CN102567080 A CN 102567080A
- Authority
- CN
- China
- Prior art keywords
- module
- node
- load
- virtual machine
- host
- 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
Images
Abstract
The invention discloses a virtual machine position selection system facing load balance in a cloud computation environment, which comprises a front end module and a rear end module, wherein the front end module comprises a comprehensive load computation module and a host selection module, and the rear end module comprises a plurality of distributed node agent modules in an integrated manner. Each node agent module comprises a node load collection module, a node load predication module and a node load incremental computation module. Cloud computation serving as a novel computation and service method is put forward and is increasingly widely paid attention to, popularized and applied, and the virtual machine position selection system serves as a vital module in resource allocation of cloud computation, so that the virtual machine position selection system has the advantages that the virtual machine network throughput rate in the cloud computation environment is increased, the resource preemption probability of virtual machines is decreased, the service quality of a virtual host is improved, and the load balance of a distributed system in the cloud computation environment is enhanced. Hence, the virtual machine position selection system is wide in application range and capable of generating remarkable economic benefit.
Description
Technical field
The invention discloses a kind of virtual machine and select a system, the virtual machine towards load balancing that relates in particular in a kind of cloud computing environment is selected a system.Belong to field of computer technology.
Background technology
In recent years, the feasible demand to computing power of the develop rapidly of network application constantly increases, and is accompanied by the development of grid computing, parallel computation, Distributed Calculation, and cloud computing is arisen at the historic moment.Definition according to National Institute of Standards and Technology (NIST); Current cloud computing service can be divided into 3 levels; Be respectively: (1) infrastructure is promptly served (IaaS); Calculate cloud (elastic compute cloud is called for short EC2), the blue cloud (blue cloud) of IBM and the cloud Infrastructure platform (IAAS) of Sun etc. like the elasticity of Amazon; (2) platform is promptly served (PaaS), like the Google App Engine of Google and the Azure platform of Microsoft etc.; (3) software is promptly served (SaaS), like CRM service of Salesforce company etc.Cloud computing is classified as the technique direction that each country will give priority to future as a kind of emerging commercial computation schema, and becomes the hot research problem of computer nowadays research circle and industry member
, resource extent more and more along with the application kind in the cloud computing environment increasing, the difficulty of resource management is also in remarkable increase in the cloud computing environment.Especially revive once more along with Intel Virtualization Technology in recent years, virtual resource is as a kind of keystone resources form arena of history in the secondary again, obtained paying close attention to more widely towards the virtual data center of cloud computing.So-called virtual data center; The foreign scholar is called Virtual Datacenter; Be meant and utilize the server virtualization technology, adopt fictitious host computer (abbreviation virtual machine) independent mutually, that isolate that the function that is equal to physical host is provided, and its cost will be lower than physical data center.So-called virtual machine is exactly a computer software, runs on physical hardware or the physical computer, and it can operation system (being called client operating system) and application program, and the virtual hardware of oneself is arranged.Virtual machine is not emulator and simulator, and they are real computing machines, can realize identical with physical computer even surpasses the function of physical computer.Seeing that virtual machine is easy-to-use flexibly, the function of physical machine will transfer to and hold the virtual machine that these services are provided from service (application program, database etc.) is provided, just the host (host) of relative virtual machine.Along with the development of cloud computing, at present large-scale IT company such as IBM, HP, Amazon, Google, Microsoft and data center are all actively setting up and are externally providing various virtual data centers towards the cloud computing service.It is thus clear that; The virtual data center technology has become the hot research problem of current domestic and international research circle and industry member; And the management of resource virtualizing and virtual resource has also become one of important channel that solves system resource utilization bottleneck in the cloud computing, has important Research Significance and using value.
At Intel Virtualization Technology is that the utilization of resources in the cloud computing environment brings convenience; Be that the associating of physical machine and Intel Virtualization Technology will be when externally will provide the independent fictitious host computer considerably beyond physical host quantity; Also bring virtual machine to select the difficult problem of position, promptly how to have selected host for virtual machine rightly.To this problem, it is following that the virtual machine in the cloud computing environment is selected the progress and the case study of method for position and product:
Some Virtual Machine Manager products of knowing clearly have been researched and developed both at home and abroad; As the OpenNebula that increases income; Systems such as Eucalyptus; The Virtual Machine Manager 2008 and the VMware ESX Server of industrial community, virtual machine is selected the position and is embedded wherein as subfunction, and it is a core subsystem that visible virtual machine is selected the position.See from the architecture aspect, existing select a system and can be divided into 1) centralized, as virtual machine quantity on the physical host at most or load the maximum preferential; 2) distributing, preferential like virtual machine minimum number on the physical host or load reckling.See from implementation, existing select a system and can be divided into two types, the one, manually select the position, be that virtual machine is selected host by the keeper perceptually, exist to depend on keeper's subjective factor, the high inadequately shortcoming of robotization; The 2nd, select the position automatically, select host by background process based on the virtual machine that is thought of as to physical host environmental information, resource utilization etc.Select an implementation algorithm from core and see, the robotization virtual machine of current main flow is selected a core algorithm and is mainly contained packing (Packing) method, itemize (Striping) method, and load perception (Load-aware) method, internal memory is got close to (Memory Buddies) method.
● the basic thought of packing (Packing) method is to use node to be target less to the greatest extent, virtual machine to be concentrated on the node in the part cloud computing move.On the implementation, adopt the maximum priority principles of virtual machine operation number, promptly when needs are selected host for newly-built virtual machine, select to have the host of maximum quantity virtual machine operations.Realized in the Scheduler program of OpenNebula platform that this virtual machine selects method for position, its configuration file is labeled as " RANK=RUNNING_VMS ".The advantage of packaging method is that this method can make a large amount of virtual machines concentrate on the minority physical nodes to move, can reduce the physical server cost.The deficiency of packaging method is that virtual machine is too concentrated, and it is excessive to cause resources of virtual machine to seize probability, and for guaranteeing the service quality of virtual server, a large amount of virtual machine (vm) migrations and resource adjustment behavior are essential, can produce a large amount of expenses like this.
● itemize (Striping) method basic thought is to be target with maximization individual server node available resources, virtual machine is dispersed on all nodes moves.On the implementation, adopt virtual machine operation minimum number priority principle, promptly when needs are selected host for newly-built virtual machine, select to have the host of minimum number virtual machine operation.Realized also in the Scheduler program of OpenNebula platform that this virtual machine selects method for position, its configuration file is labeled as " RANK=-RUNNING_VMS ".Its basic ideas are inspired by group of planes load balancing, and virtual machine is evenly distributed by quantity, reduce resources of virtual machine and seize probability.Its shortcoming is to select the position according to virtual machine quantity; Virtual machine quantity only abstract be load value on the node, too single, and can't distinguish different resource (like CPU; Internal memory; The actual loading that the virtual machine of disk etc.) asking causes node, not enough refinement is difficult to realize more fine granularity and accurate resources allocation demand.
● the target of load perception (Load-aware) method is identical with itemize (Striping) method, makes every effort to maximize the available resources on the single node.Basic mentality of designing is to receive the node load minimum and inspire, and newly-built virtual machine is placed on the node with minimum load moves.On the implementation, adopt maximum CPU idleness priority principle, promptly when needs are selected host for newly-built virtual machine, select the maximum host of CPU idleness.Also realized this method in the Scheduler program of OpenNebula platform, its configuration file is labeled as " RANK=FREECPU ".It is identical with the itemize method that its advantage comprises, inspired by load balancing, owing to consider the cpu resource operating position on the node, can reach the cpu resource load balancing in the distributed computing system scope.Its shortcoming comprises that this method only considered cpu resource, and the important composition to the group of planes node loads such as internal memory, network and disk operating position of node lacks and considers.
● internal memory (Memory Buddies) method of getting close to is to select a system by a kind of virtual machine based on memory shared perception (memory sharing-aware) that Timothy doctor Wood proposes; Comprise an internal memory recognition system (memory fingerprinting system); Can effectively judge one group of memory shared potential (sharing potential) between the virtual machine, and calculate more effective modes of emplacement.In addition, along with load variations, system also will utilize online migration (live migration) to optimize virtual machine and place.Its advantage is to seek the identical virtual machine of virtual memory page from group of planes scope, makes them move to same group of planes node, shares virtual memory, can improve the physical memory utilization factor, save memory, and the virtual machine that promotes a group of planes holds quantity.Its shortcoming is that procedure is complicated, and too much if share the virtual machine of virtual memory owing to need realize selecting the position through virtual machine (vm) migration, can't guarantee the service quality of virtual server.
Sum up existing virtual machine and select method for position and can know, bolus dressing is to select method for position with the virtual machine that to take minimum group of planes node be target, causes resources of virtual machine to seize the probability problems of too, and the service quality of virtual server also can reduce greatly; Itemize method and load perception method are target with group of planes load balancing all; What consider respectively is virtual machine number and the group of planes node cpu resource utilization factor of moving on the group of planes node; Ignored the influence of together different and other resource operating positions such as node internal memory, network of each virtual machine request resource to the node load; Only considered promptly that also cpu resource utilizes situation, lacked the consideration of comprehensive resources utilization factor situation; The internal memory method of getting close to is to be shared as target with virutal machine memory in the maximization group of planes scope, though promoted the open ended virtual machine quantity of a group of planes, selects virtual machine (vm) migration of a process need, and has the loss of virtual server service quality.
Summing up existing invention present situation can know; Cloud computing is as emerging in recent years service mode; All obtained increasingly extensive attention in research circle and industry member in recent years; Yet because cloud computing is newer, still lack the invention of a system of selecting towards the virtual machine of cloud computing environment at present, the virtual machine towards load balancing that especially lacks in the cloud computing environment is selected the invention of a system.
Therefore, the present invention promptly is to this emerging Development Technology of cloud computing, and existing above problem of selecting position technology existence, and the virtual machine of having invented in a kind of cloud computing environment towards load balancing is selected a system.
Summary of the invention
1, purpose
The objective of the invention is problems such as appropriate distribution to virtual resource in the cloud computing environment; Especially select the problem of position (promptly how selecting host for virtual machine rightly) to virtual machine; Towards the balancing resource load target; The virtual machine of inventing in a kind of cloud computing environment towards load balancing is selected a system; The final virtual machine network throughput that promotes in the cloud computing environment, the resource race to control probability of reduction virtual machine improves the service quality of fictitious host computer and improves system load balancing property in the cloud computing environment.
2, technical scheme
Technical scheme of the present invention is following: the virtual machine towards load balancing in a kind of cloud computing environment is selected a system, on module constitutes, mainly is made up of front-end module and rear module.
1) front-end module: front-end module further comprises sub-function module: the integrated load computing module, host is selected module.
2) rear module: run on each distributed rear end child node, mainly carry out the load information work of treatment of each distributed node.Rear module is made up of a plurality of distributed node proxy module set.The node proxy module is made up of node load collection module, node load estimation module, node incremental loading computing module again.
Shown in wherein the function be responsible for of each module and deployed position are described below:
● front-end module: play comprehensive management role, be responsible for accepting newly-built virtual machine request and responding.Run on the preceding leaf.
● the integrated load computing module: the integrated load that carries out cloud computing system calculates, and with the integrated load result transmission.Run on the preceding leaf.
● host is selected module: with integrated load value vector is input, in available resources satisfy the node scope of request, carries out the linear search algorithm, according to the load balancing principle, selects the minimum node of integrated load value, as the target host of newly-built virtual machine.
● rear module: run on each distributed rear end child node, mainly carry out the load information work of treatment of each distributed node.Rear module is made up of a plurality of distributed node proxy module set.
● node proxy module: as the agency of each distributed physical nodes.Comprise that mainly node load collection module, node incremental loading computing module three sub-module constitute.Be deployed on each node in the cloud computing environment.
● node load collection module: each node obtains the load information on this node.Like CPU idleness, memory usage etc.
● node load estimation module: each node is by next original load information constantly of current and original load information prediction previous moment.
● node incremental loading computing module: each node at first carries out incremental computations to load; Node compares the load data and the previous moment load information of prediction then; Carry out following selection operation then: if increment is greater than threshold value; Predict the outcome and be transmitted to the front-end module of preceding leaf as this node load information, simultaneously with the original load information of current original load information replacement previous moment on this node.If increment is not more than threshold value, the front-end module of leaf does not transmit load information before a group of planes, directly on this node, current original load information is replaced with the original load information of previous moment.
Based on constituting with upper module, on core algorithm, the present invention has announced that the virtual machine towards load balancing in a kind of cloud computing environment selects an algorithm.The basic procedure of this algorithm is:
S1: front-end module is accepted a new request instruction of selecting.
S2: front-end module triggers each node proxy module.
S3: each node proxy module calls node load collection module: each node proxy module is accepted the request instruction of selecting from front-end module, calls node load collection module, carries out the node load and collects.
S4: each node proxy module calls node load estimation module, carries out the node load estimation.
S5:S5 mainly is made up of three sub-steps, i.e. S5:S51: each node proxy module calls node incremental loading computing module, S5:S52: judge whether load changes S5:S53: node incremental computations module loads to front-end module with transmission.Carrying out the node incremental loading calculates.
S6: front-end module calls the integrated load computing module, carries out integrated load and calculates.
S7: front-end module calls host and selects module, accomplishes host and selects.
3, advantage and effect
The virtual machine towards load balancing in a kind of cloud computing environment that the present invention announced is selected a system; It compared with prior art; Its main advantage is: host is just selected according to the load balancing principle in the initial virtual machine creating phase in (1); Can reduce the later stage well owing to each node load in the cloud computing is unbalanced, need carry out the possibility that virtual machine (vm) migration and resource are redistributed, promote the load balancing property and the fault-tolerance of cloud computing system.(2) be suggested as novel calculating and method of servicing owing to cloud computing in recent years; And it is increasingly extensive to have obtained industry member (finance, government, enterprise or the like); Promotion and application; And virtual machine to select a system be the vital module in its resources allocation, so the present invention has very strong practicality and very wide range of application.
Description of drawings
The virtual machine towards load balancing in Fig. 1 cloud computing environment of the present invention is selected an overall system framework synoptic diagram
The virtual machine towards load balancing in Fig. 2 cloud computing environment of the present invention is selected a system flow synoptic diagram
Embodiment
For making the object of the invention, technical scheme and advantage express clearlyer, the present invention is remake further detailed explanation below in conjunction with accompanying drawing and specific embodiment.As shown in Figure 2, the virtual machine towards load balancing in the cloud computing environment is selected a system, and the practical implementation step is following:
The virtual machine towards load balancing in a kind of cloud computing environment is selected a system, on module constitutes, mainly is made up of front-end module MF1 and rear module ME1.
1) front-end module MF1: front-end module further comprises sub-function module: integrated load computing module MF11, host is selected module MF12.Run on the front terminal node of cloud computing system.
2) rear module ME1: rear module ME1 is made up of a plurality of distributed node proxy module ME2 set.The node proxy module is made up of load collection module ME211, load estimation module ME212, incremental computations module ME213 again.Run on each distributed rear end child node, mainly carry out the load information work of treatment of each distributed node.
Shown in wherein the function be responsible for of each module and deployed position are described below:
3) front-end module MF1: play comprehensive management role, be responsible for accepting newly-built virtual machine request and responding.Run on the preceding leaf.
4) integrated load computing module MF11: the integrated load that carries out cloud computing system calculates, and with the integrated load result transmission.Run on the preceding leaf.
5) host is selected module MF13: with integrated load value vector is input; In available resources satisfy the node scope of request, carry out the linear search algorithm, according to the load balancing principle; Select the minimum node of integrated load value, as the target host of newly-built virtual machine.
6) rear module ME1: run on each distributed rear end child node, mainly carry out the load information work of treatment of each distributed node.Rear module ME1 is made up of a plurality of distributed node proxy module ME2 set.
7) node proxy module ME2: as the agency of each distributed physical nodes.Comprise that mainly node load collection module ME211, node incremental loading computing module ME213 three sub-module constitute.Be deployed on each node in each cloud computing environment.
8) node load collection module ME211: each node obtains the load information on this node.Like CPU idleness, memory usage etc.
9) node load estimation module ME212: each node is by next original load information constantly of current and original load information prediction previous moment.
10) node incremental loading computing module ME213: each node at first carries out incremental computations to load; Node compares the load data and the previous moment load information of prediction then; Carry out following selection operation then: if increment is greater than threshold value; Predict the outcome and be transmitted to the front-end module (MF1) of preceding leaf as this node load information, simultaneously with the original load information of current original load information replacement previous moment on this node.If increment is not more than threshold value, the front-end module MF1 of leaf does not transmit load information before a group of planes, directly on this node, current original load information is replaced with the original load information of previous moment.
Based on constituting with upper module, on core algorithm, the virtual machine towards load balancing in a kind of cloud computing environment that the present invention announces is selected an algorithm.The basic implementing procedure and the instance of this algorithm are:
S1: front-end module MF1 accepts a new request instruction of selecting, and instruction is exemplified as " virtual machine creating " and " virtual machine is selected the position " in this instance.
S2: front-end module MF1 triggers each node proxy module ME2, does not have password through leaf user before being provided with in this instance and logins other nodes and long-range run time version realization " triggering ".
S3: each node proxy module ME2 calls node load collection module ME211.In this instance, each node proxy module ME2 call and accept from front-end module MF1 select a request instruction (" virtual machine creating " and " virtual machine select position "), call node load collection module ME211 then, carry out the node load and collect.Concrete collection method is ME2 obtains node through multithread mode and SAR instrument, IOSTAT method a load information.Load information comprises the CPU idleness, memory usage, and disk read-write speed, network receives and transmission rate.
S4: each node proxy module ME2 calls node load estimation module ME212, carries out the node load estimation.
In this example, at first with the load information normalization that obtains among the S3, derive CPU usage (α
CR), memory usage (α
MR), network utilization (α
NR) and disk transfer rate (P).Wherein CPU usage, memory usage are got actual numerical value, and network utilization is network receiving velocity (v
NRS), transmission rate (v
NSS) sum and transmission network maximum rate (v
MNS) ratio since this instance in platform adopt hundred Broadcoms, so v
MNS=100Mbps, and α
NR=(v
NRS+ v
NSS)/v
MNSDisk transfer rate (P) is similarly, adopts disk read-write speed (v
DRS, v
DWS) sum is divided by disk optimal transmission rate (v
MDS), wherein can obtain the disk iptimum speed through the hdparm order.Through repeatedly test to 3 station servers in this instance; Find that the Timing cached reads speed that hdparm order test is returned is no more than 4170MB/s; Timing buffered disk reads speed is no more than 92Mbps, therefore adopts 92Mbps as the disk iptimum speed.Then, confirm the block size BLKS (block size) of server disk.Through checking that the disk unit order obtains the details of subregion, confirms that experiment porch server B lock size is 4KB for 4096B.Can confirm according to above information
P＝(v
DRS+v
DWS)B×8/v
MDS。
(α
CR,α
MR,α
NR,P)
tBe expressed as current (t constantly) load data, node is preserved previous moment (t simultaneously
0Load data (α constantly)
CR0,α
MR0,α
NR0,P
0) t
0, through the linear prediction model of two groups of data, we can know that next constantly (is defined as next second according to load data ageing here, is designated as n constantly) load data (α
CRn,α
MRn,α
NRn,Pn)
nWith the t moment, t
0There is following relation in load data constantly:
Can know that by n-t=1 separating by following system of equations of aforesaid equation obtains
Above-mentioned solution of equations is exactly next moment node load data of prediction.
S5: each node proxy module ME2 calls node incremental loading computing module ME213, carries out the node incremental loading and calculates.
In this instance, this step mainly need be calculated n load constantly (α
CRn,α
MRn,α
NRn,Pn) whether with respect to t
0(the α of load constantly
CR0,α
MR0,α
NR0,P
0) significant change is arranged, if each item variable quantity all then is designated as no change less than threshold value, node need not the forward end node and sends the prediction load data, to reduce the network overhead in the cloud computing system, simultaneously with t moment load data (α
CR,α
MR,α
NR,P) compose to t
0Constantly, preserve by the node module; Otherwise, the relative t of definition predicted data
0Load constantly changes, and the node module answers the forward end module to send the prediction load data, and with t moment load data (α
CR,α
MR,α
NR,P) compose to t
0Constantly, preserve by the node module.In this instance according to keeping the 2 significant digits significant figure and round up principle, when each item load data variable quantity less than 0.05 (being that threshold setting is 0.05), can think the load data no change.So, if the relative t of predicted data
0The no change of load constantly adopts following inequality group
S6: front-end module MF1 calls integrated load computing module MF11, carries out integrated load and calculates.Because the maximally related part of the web of virtual server service performance is CPU; Next is an internal memory; Be network interface card again; Be disk at last, so each item load information weight can confirm as 30, percent 20 and 10 40 percent, percent successively in this instance, the integrated load value is produced by cpu busy percentage, memory usage, network utilization and the weighting of disk transmission utilization ratio.In this example, each the node load data weighting respectively to preserving calculates each node integrated load value.According to the reasoning in the S1-S5 formula, the integrated load information weight of CPU usage, memory usage, network utilization, disk transfer rate each item is followed successively by 0.4,0.3,0.2 and 0.1.So node integrated load value is designated as LV, satisfy
LV＝0.4×α
CR+0.3×α
MR+0.2×α
NR+0.1×P. (4)
At last, will send host according to each node integrated load value that above formula calculates to and select module MF12.
S7: front-end module MF1 calls host and selects module MF12, accomplishes host and selects.
Main in this example according to the computation structure among the S6, according to the load balancing principle, in available resources satisfy the node scope of virtual machine request, select the minimum node of integrated load value (LV), as the target host of newly-built virtual machine.So far, accomplish virtual machine and selected the bit stream journey.
It should be noted last that: above embodiment is the unrestricted technical scheme of the present invention in order to explanation only; Although the present invention is specified with reference to the foregoing description; Those of ordinary skill in the art is to be understood that: still can make amendment or be equal to replacement the present invention; And replace any modification or the part that do not break away from the spirit and scope of the present invention, and it all should be encompassed in the middle of the claim scope of the present invention.
Claims (2)
1. the virtual machine towards load balancing in the cloud computing environment is selected a system, on module constitutes, mainly is made up of front-end module (MF1) and rear module (ME1);
1) front-end module (MF1): front-end module further comprises sub-function module: integrated load computing module (MF11), and host is selected module (MF12);
2) rear module (ME1): run on each distributed rear end child node, mainly carry out the load information work of treatment of each distributed node; Rear module (ME1) is made up of a plurality of distributed node proxy modules (ME2) set; The node proxy module is made up of node load collection module (ME211), node load estimation module (ME212), node incremental loading computing module (ME213) again;
Wherein, shown in the function be responsible for of each module and deployed position are described below:
● front-end module (MF1): play comprehensive management role, be responsible for accepting newly-built virtual machine request and responding; Run on the preceding leaf;
● integrated load computing module (MF11): the integrated load that carries out cloud computing system calculates, and with the integrated load result transmission; Run on the preceding leaf;
● host is selected module (MF13): with integrated load value vector is input; In available resources satisfy the node scope of request, carry out the linear search algorithm, according to the load balancing principle; Select the minimum node of integrated load value, as the target host of newly-built virtual machine;
● rear module (ME1): run on each distributed rear end child node, mainly carry out the load information work of treatment of each distributed node; Rear module (ME1) is made up of a plurality of distributed node proxy modules (ME2) set;
● node proxy module (ME2): as the agency of each distributed physical nodes; Comprise that mainly node load collection module (ME211), node incremental loading computing module (ME213) three sub-module constitute; Be deployed on each node in the cloud computing environment;
● node load collection module (ME211): each node obtains the load information on this node;
● node load estimation module (ME212): each node is by next original load information constantly of current and original load information prediction previous moment;
● node incremental loading computing module (ME213): each node at first carries out incremental computations to load; Node compares the load data and the previous moment load information of prediction then; Carry out following selection operation then: if increment is greater than threshold value; Predict the outcome and be transmitted to the front-end module (MF1) of preceding leaf as this node load information, simultaneously with the original load information of current original load information replacement previous moment on this node; If increment is not more than threshold value, the front-end module of leaf (MF1) does not transmit load information before a group of planes, directly on this node, current original load information is replaced with the original load information of previous moment.
2. the virtual machine of selecting in a kind of cloud computing environment of a system based on claim 1 towards load balancing is selected method for position, and basic procedure is:
S1: front-end module (MF1) is accepted a new request instruction of selecting;
S2: front-end module (MF1) triggers each node proxy module (ME2);
S3: each node proxy module (ME2) calls node load collection module (ME211): each node proxy module (ME2) is accepted the request instruction of selecting from front-end module (MF1), calls node load collection module (ME211), carries out the node load and collects;
S4: each node proxy module (ME2) calls node load estimation module (ME212), carries out the node load estimation;
S5:S5 mainly is made up of three sub-steps; Be S5:S51: each node proxy module (ME2) calls node incremental loading computing module (ME213); S5:S52: judge whether load changes S5:S53: node incremental computations module (ME213) loads to front-end module (MF1) with transmission; Carrying out the node incremental loading calculates;
S6: front-end module (MF1) calls integrated load computing module (MF11), carries out integrated load and calculates;
S7: front-end module (MF1) calls host and selects module (MF12), accomplishes host and selects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210001315.9A CN102567080B (en) | 2012-01-04 | 2012-01-04 | Virtual machine position selection system facing load balance in cloud computation environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210001315.9A CN102567080B (en) | 2012-01-04 | 2012-01-04 | Virtual machine position selection system facing load balance in cloud computation environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102567080A true CN102567080A (en) | 2012-07-11 |
| CN102567080B CN102567080B (en) | 2015-03-04 |
Family
ID=46412578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210001315.9A Active CN102567080B (en) | 2012-01-04 | 2012-01-04 | Virtual machine position selection system facing load balance in cloud computation environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102567080B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473113A (en) * | 2013-09-04 | 2013-12-25 | 国云科技股份有限公司 | Universal virtual-machine adopting method |
| CN103595763A (en) * | 2013-10-15 | 2014-02-19 | 北京航空航天大学 | Resource scheduling processing method and device |
| CN103885831A (en) * | 2012-12-19 | 2014-06-25 | 中国电信股份有限公司 | Host machine selecting method and device of virtual machine |
| CN104133727A (en) * | 2014-08-08 | 2014-11-05 | 成都致云科技有限公司 | Load distribution method based on real-time resources |
| CN104750541A (en) * | 2015-04-22 | 2015-07-01 | 成都睿峰科技有限公司 | Virtual machine migration method |
| WO2016037344A1 (en) * | 2014-09-12 | 2016-03-17 | Intel Corporation | Memory and resource management in a virtual computing environment |
| WO2018027449A1 (en) * | 2016-08-08 | 2018-02-15 | 深圳秦云网科技有限公司 | Private cloud management platform |
| CN108536525A (en) * | 2017-03-02 | 2018-09-14 | 北京金山云网络技术有限公司 | A kind of host dispatching method and device |
| US10129769B2 (en) | 2015-12-31 | 2018-11-13 | Affirmed Networks, Inc. | Adaptive peer overload control in mobile networks |
| US10154087B2 (en) | 2016-01-15 | 2018-12-11 | Affirmed Networks, Inc. | Database based redundancy in a telecommunications network |
| CN109710269A (en) * | 2018-09-07 | 2019-05-03 | 天翼电子商务有限公司 | A kind of list application discrete type clustered deploy(ment) device and method |
| CN110058966A (en) * | 2018-01-18 | 2019-07-26 | 伊姆西Ip控股有限责任公司 | Method, equipment and computer program product for data backup |
| CN112764918A (en) * | 2020-12-29 | 2021-05-07 | 重庆真逆思维科技有限公司 | Working method for carrying out space search on available area by cloud platform |
| US11005773B2 (en) | 2015-12-10 | 2021-05-11 | Microsoft Technology Licensing, Llc | Data driven automated provisioning of telecommunication applications |
| US11121921B2 (en) | 2019-01-15 | 2021-09-14 | Microsoft Technology Licensing, Llc | Dynamic auto-configuration of multi-tenant PaaS components |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593133A (en) * | 2009-06-29 | 2009-12-02 | 北京航空航天大学 | Load balancing of resources of virtual machine method and device |
| CN102004671A (en) * | 2010-11-15 | 2011-04-06 | 北京航空航天大学 | Resource management method of data center based on statistic model in cloud computing environment |
| CN102195890A (en) * | 2011-06-03 | 2011-09-21 | 北京大学 | Internet application dispatching method based on cloud computing |
-
2012
- 2012-01-04 CN CN201210001315.9A patent/CN102567080B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593133A (en) * | 2009-06-29 | 2009-12-02 | 北京航空航天大学 | Load balancing of resources of virtual machine method and device |
| CN102004671A (en) * | 2010-11-15 | 2011-04-06 | 北京航空航天大学 | Resource management method of data center based on statistic model in cloud computing environment |
| CN102195890A (en) * | 2011-06-03 | 2011-09-21 | 北京大学 | Internet application dispatching method based on cloud computing |
Non-Patent Citations (1)
| Title |
|---|
| 刘媛媛等: "《虚拟计算环境下虚拟机资源负载均衡方法》", 《计算机工程》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103885831A (en) * | 2012-12-19 | 2014-06-25 | 中国电信股份有限公司 | Host machine selecting method and device of virtual machine |
| CN103885831B (en) * | 2012-12-19 | 2017-06-16 | 中国电信股份有限公司 | The system of selection of virtual machine host machine and device |
| CN103473113B (en) * | 2013-09-04 | 2017-02-08 | 国云科技股份有限公司 | Universal virtual-machine adopting method |
| CN103473113A (en) * | 2013-09-04 | 2013-12-25 | 国云科技股份有限公司 | Universal virtual-machine adopting method |
| CN103595763B (en) * | 2013-10-15 | 2016-08-24 | 北京航空航天大学 | resource scheduling processing method and device |
| CN103595763A (en) * | 2013-10-15 | 2014-02-19 | 北京航空航天大学 | Resource scheduling processing method and device |
| CN104133727A (en) * | 2014-08-08 | 2014-11-05 | 成都致云科技有限公司 | Load distribution method based on real-time resources |
| WO2016037344A1 (en) * | 2014-09-12 | 2016-03-17 | Intel Corporation | Memory and resource management in a virtual computing environment |
| CN106575235B (en) * | 2014-09-12 | 2020-10-23 | 英特尔公司 | Memory and resource management in a virtualized computing environment |
| CN106575235A (en) * | 2014-09-12 | 2017-04-19 | 英特尔公司 | Memory and resource management in a virtual computing environment |
| US10216532B2 (en) | 2014-09-12 | 2019-02-26 | Intel Corporation | Memory and resource management in a virtual computing environment |
| CN104750541A (en) * | 2015-04-22 | 2015-07-01 | 成都睿峰科技有限公司 | Virtual machine migration method |
| US11005773B2 (en) | 2015-12-10 | 2021-05-11 | Microsoft Technology Licensing, Llc | Data driven automated provisioning of telecommunication applications |
| US10129769B2 (en) | 2015-12-31 | 2018-11-13 | Affirmed Networks, Inc. | Adaptive peer overload control in mobile networks |
| US10154087B2 (en) | 2016-01-15 | 2018-12-11 | Affirmed Networks, Inc. | Database based redundancy in a telecommunications network |
| WO2018027449A1 (en) * | 2016-08-08 | 2018-02-15 | 深圳秦云网科技有限公司 | Private cloud management platform |
| CN108536525A (en) * | 2017-03-02 | 2018-09-14 | 北京金山云网络技术有限公司 | A kind of host dispatching method and device |
| CN110058966A (en) * | 2018-01-18 | 2019-07-26 | 伊姆西Ip控股有限责任公司 | Method, equipment and computer program product for data backup |
| CN110058966B (en) * | 2018-01-18 | 2023-11-14 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer program product for data backup |
| CN109710269A (en) * | 2018-09-07 | 2019-05-03 | 天翼电子商务有限公司 | A kind of list application discrete type clustered deploy(ment) device and method |
| US11121921B2 (en) | 2019-01-15 | 2021-09-14 | Microsoft Technology Licensing, Llc | Dynamic auto-configuration of multi-tenant PaaS components |
| CN112764918A (en) * | 2020-12-29 | 2021-05-07 | 重庆真逆思维科技有限公司 | Working method for carrying out space search on available area by cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102567080B (en) | 2015-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102567080B (en) | Virtual machine position selection system facing load balance in cloud computation environment | |
| Ge et al. | GA-based task scheduler for the cloud computing systems | |
| Lee et al. | Topology-aware resource allocation for data-intensive workloads | |
| CN103713956B (en) | Method for intelligent weighing load balance in cloud computing virtualized management environment | |
| US9785472B2 (en) | Computing cluster performance simulation using a genetic algorithm solution | |
| Raghava et al. | Comparative study on load balancing techniques in cloud computing | |
| Ibrahim et al. | Handling partitioning skew in mapreduce using leen | |
| KR101578177B1 (en) | Method and system for migration based on resource utilization rate in cloud computing | |
| CN102236582A (en) | Method for balanced distribution of virtualization cluster load in a plurality of physical machines | |
| CN103401939A (en) | Load balancing method adopting mixing scheduling strategy | |
| Li et al. | An effective scheduling strategy based on hypergraph partition in geographically distributed datacenters | |
| Tao et al. | Load feedback-based resource scheduling and dynamic migration-based data locality for virtual hadoop clusters in openstack-based clouds | |
| CN102710779A (en) | Load balance strategy for allocating service resource based on cloud computing environment | |
| Rashmi et al. | Enhanced load balancing approach to avoid deadlocks in cloud | |
| CN105760227B (en) | Resource regulating method and system under cloud environment | |
| Chaudhary et al. | An analysis of the load scheduling algorithms in the cloud computing environment: A survey | |
| Biswas et al. | A novel resource aware scheduling with multi-criteria for heterogeneous computing systems | |
| Kumar et al. | A priority based dynamic load balancing approach in a grid based distributed computing network | |
| Shi et al. | Energy-efficient scheduling algorithms based on task clustering in heterogeneous spark clusters | |
| Lukashin et al. | Resource scheduler based on multi-agent model and intelligent control system for openstack | |
| Zhao et al. | A holistic cross-layer optimization approach for mitigating stragglers in in-memory data processing | |
| Jurgelevicius et al. | Application of a task stalling buffer in distributed hybrid cloud computing | |
| Xu et al. | Boosting mapreduce with network-aware task assignment | |
| Li et al. | Two-stage selection of distributed data centers based on deep reinforcement learning | |
| Tom et al. | Dynamic Task scheduling Based on Burst Time requirement for cloud environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210220 Address after: Room 203-204, building Y2, 112 liangxiu Road, Pudong New Area, Shanghai, 201203 Patentee after: SHANGHAI ZHIRUI ELECTRONIC TECHNOLOGY Co.,Ltd. Address before: 100191 No. 37, Haidian District, Beijing, Xueyuan Road Patentee before: BEIHANG University |
|
| TR01 | Transfer of patent right |