CN104539708A - Capacity reduction method, device and system for cloud platform resources - Google Patents

Capacity reduction method, device and system for cloud platform resources Download PDF

Info

Publication number
CN104539708A
CN104539708A CN201410848185.1A CN201410848185A CN104539708A CN 104539708 A CN104539708 A CN 104539708A CN 201410848185 A CN201410848185 A CN 201410848185A CN 104539708 A CN104539708 A CN 104539708A
Authority
CN
China
Prior art keywords
example
virtual machine
described
quantity
target application
Prior art date
Application number
CN201410848185.1A
Other languages
Chinese (zh)
Other versions
CN104539708B (en
Inventor
叶会
王提政
Original Assignee
杭州华为数字技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 杭州华为数字技术有限公司 filed Critical 杭州华为数字技术有限公司
Priority to CN201410848185.1A priority Critical patent/CN104539708B/en
Publication of CN104539708A publication Critical patent/CN104539708A/en
Application granted granted Critical
Publication of CN104539708B publication Critical patent/CN104539708B/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network-specific arrangements or communication protocols supporting networked applications
    • H04L67/10Network-specific arrangements or communication protocols supporting networked applications in which an application is distributed across nodes in the network
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network-specific arrangements or communication protocols supporting networked applications
    • H04L67/16Service discovery or service management, e.g. service location protocol [SLP] or Web services

Abstract

The embodiment of the invention provides a capacity reduction method, device and system for cloud platform resources. The method includes the steps of receiving an example deleting request for a target application on a cloud platform, wherein the example deleting request carries application identification and number identification, and the number identification represents that the number of to-be-deleted examples of the target application is N; finding target virtual machines in the cloud platform according to the identification of the target application, wherein each target virtual machine comprises examples of the target application; obtaining the type of an application which each example in the target virtual machines belongs to and the number of examples of each type of application; deleting the N examples of the target application in the target virtual machines through preset capacity reduction strategies according to the type of the application which each example belongs to in the target virtual machines and the number of examples of each type of application. By means of the certain strategies, the probability that idle virtual machines may appear after capacity reduction is conducted is increased; meanwhile, the examples are concentrated in a small number of virtual machines as much as possible, and therefore the utilization rate of resources of the virtual machines is increased, and the operation cost is saved.

Description

A kind of capacity reduction method, equipment and system of cloud platform resource

Technical field

The present invention relates to communication technical field, particularly relate to a kind of capacity reduction method, equipment and system of cloud platform resource.

Background technology

Cloud computing is a kind of payment and using forestland of service, and calculation task is distributed on the resource pool of a large amount of computer formation by it, enables various application system obtain computing power, memory space and information service as required.Cloud computing essential characteristic for use as required resource, resource can dynamic expansion, application elastic calculation, be supplied to application and development user by network with method of service.In the cloud computing epoch, research and development of software platform is supplied to application and development user as one service by cloud platform, and the running environment of application and operation maintenance work are by cloud platform on behalf of completing, and application and development user only needs the logic realization paying close attention to application.

Determine according to the transient response speed of virtual machine when example starts in virtual machine, and each virtual machine is due to the difference of self-operating example quantity, kind, the response speed of each virtual machine is varied, for single virtual machine, due to the difference of its self-operating example, kind, same virtual machine is caused also to be not quite similar in the response speed of Different periods.Therefore the distribution of example in cloud platform on virtual machine is rambling.

Elastic calculation is one of essential characteristic of cloud computing, it refers to that application and development user is according to practical business or calculating needs, use computational resource neatly, and according to use resources of virtual machine on cloud platform number pay accordingly, really realize using as required, on-demand delivery and paying as required.Therefore when the external world reduces the access request of application, for avoiding the wasting of resources, saving the operation cost of application vendor, wishing that the example number reducing application carries out capacity reducing to the resources of virtual machine on cloud platform, thus the efficiency utilization of implementation platform resource.

Current in the application capacity reducing of cloud platform, do not have good capacity reducing strategy, the start-up time by the example to target application in the virtual machine of existing capacity reducing technology normally on cloud platform is deleted by order early in evening.

Because example in cloud platform, virtual machine is random distribution, therefore according to after deleting example start-up time, example distribution in virtual machine is still scattered unordered, integration and the distribution of virtual machine instance lack planning, not easily concentrate, virtual machine occurs that idle possibility is very little, especially when a large amount of external references applied are die-offed, the scattered distribution of example can waste the paying cost of unnecessary cloud platform resource, effectively can not carry out capacity reducing integration to the resources of virtual machine of cloud platform, thus cause resources of virtual machine utilance low.

Summary of the invention

In view of this, embodiments provide a kind of capacity reduction method, equipment and system of cloud platform resource, occur after making capacity reducing that example is empty virtual machine as much as possible, make example concentrate in several virtual machines of minority as far as possible, and the resources of virtual machine release that will free out completely, to improve the utilance of resources of virtual machine.

According to the first aspect of the embodiment of the present invention, provide a kind of capacity reduction method of cloud platform resource, cloud platform resource is the resources of virtual machine on cloud platform, and virtual machine comprises the example of application; It is characterized in that, said method comprises: receive the example removal request to target application on cloud platform, above-mentioned example removal request carries the mark of quantity identity and above-mentioned target application; Above-mentioned quantity identity represents the quantity of the example that above-mentioned target application needs are deleted to be N, N is the integer being greater than 0; Mark according to above-mentioned target application finds out target virtual machine from above-mentioned cloud platform, and above-mentioned target virtual machine is all virtual machines comprising the example of above-mentioned target application; Obtain the quantity of the kind of application belonging to each example in above-mentioned target virtual machine and the example of often kind of application; The quantity of the example of the kind applied belonging to example each in above-mentioned target virtual machine and often kind of application, adopts the capacity reducing strategy preset in above-mentioned target virtual machine, delete N number of example of above-mentioned target application.

In conjunction with first aspect, in the first possible implementation of first aspect, after the capacity reducing strategy that employing is default deletes N number of example of above-mentioned target application in above-mentioned target virtual machine, said method also comprises: check in above-mentioned target virtual machine whether occur free virtual machine, and the example quantity comprised in above-mentioned free virtual machine is zero; If be checked through in above-mentioned destination virtual and occur free virtual machine, discharge above-mentioned free virtual machine.。

In conjunction with first aspect, or in conjunction with the first possible implementation of first aspect, in the implementation that the second of first aspect is possible, above-mentioned target virtual machine comprises at least two special virtual machines, only comprise the example of above-mentioned target application in above-mentioned special virtual machine, the sum of the example comprised in all special virtual machines is more than or equal to N; N number of example that the capacity reducing strategy that above-mentioned employing is preset deletes above-mentioned target application in above-mentioned target virtual machine comprises: according to the example quantity order from less to more comprised in each special virtual machine, from least one special virtual machine above-mentioned, delete N number of example.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the third possible implementation of first aspect, the above-mentioned example quantity order from less to more according to comprising in each special virtual machine, from at least one special virtual machine above-mentioned, delete N number of example specifically comprise: if the example quantity comprised in the special virtual machine of the example minimum number comprised is more than or equal to N, in the special virtual machine of above-mentioned example minimum number, delete N number of example.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 4th kind of possible implementation of first aspect, the above-mentioned example quantity order from less to more according to comprising in each special virtual machine, from at least one special virtual machine above-mentioned, delete N number of example specifically comprise: if the example quantity comprised in the special virtual machine of the example minimum number comprised is less than N, in front M special virtual machine, all examples are deleted according to said sequence, delete quantity and be designated as N-X, the quantity of the example comprised in M+1 special virtual machine in said sequence is made to be more than or equal to X, X is that the residue of the example of above-mentioned target application deletes quantity, M and X is the integer being greater than 0, X example is deleted in M+1 special virtual machine in said sequence.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 5th kind of possible implementation of first aspect, above-mentioned target virtual machine comprises at least one special virtual machine, only comprise the example of above-mentioned target application in above-mentioned special virtual machine, in all special virtual machines, the sum of example is less than N; N number of example that the capacity reducing strategy that above-mentioned employing is preset deletes above-mentioned target application in above-mentioned target virtual machine comprises: delete examples all in all special virtual machines, has deleted quantity and has been designated as N-Y; According to the example sum order from less to more comprised in each residue target virtual machine, delete Y example of above-mentioned target application from least one residue target virtual machine, Y is the residue deletion quantity of the example of above-mentioned target application, Y be greater than 0 integer.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 6th kind of possible implementation of first aspect, the above-mentioned example sum order from less to more according to comprising in each residue target virtual machine, Y the example deleting above-mentioned target application from least one residue target virtual machine specifically comprises: if the example quantity comprising above-mentioned target application in the total minimum residue target virtual machine of the example comprised is more than or equal to Y, Y example of above-mentioned target application is deleted in the residue target virtual machine that the above-mentioned example sum comprised is minimum.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 7th kind of possible implementation of first aspect, the above-mentioned example sum order from less to more according to comprising in each residue target virtual machine, Y the example deleting above-mentioned target application from least one residue target virtual machine specifically comprises: if the example quantity comprising above-mentioned target application in the total minimum residue target virtual machine of the example comprised is less than Y, in front M1 residue target virtual machine, all examples of above-mentioned target application are deleted according to said sequence, delete quantity and be designated as Y-X1, the quantity comprising the example of above-mentioned target application in M1+1 residue target virtual machine in said sequence is made to be more than or equal to X1, above-mentioned X1 is that the residue of the example of above-mentioned target application deletes quantity, above-mentioned M1 and above-mentioned X1 is the integer being greater than 0, X1 example of above-mentioned target application is deleted in M1+1 residue target virtual machine in said sequence.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 8th kind of possible implementation of first aspect, N number of example that the capacity reducing strategy that above-mentioned employing is preset deletes above-mentioned target application in above-mentioned target virtual machine comprises: according to the example sum order from less to more comprised in each target virtual machine, delete N number of example of above-mentioned target application from least one target virtual machine.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 9th kind of possible implementation of first aspect, the above-mentioned example sum order from less to more according to comprising in each target virtual machine, the N number of example deleting above-mentioned target application from least one target virtual machine specifically comprises: if the example quantity comprising above-mentioned target application in the total minimum target virtual machine of the example comprised is more than or equal to N, deletes N number of example of above-mentioned target application in the target virtual machine that the above-mentioned example sum comprised is minimum.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the tenth kind of possible implementation of first aspect, the above-mentioned example sum order from less to more according to comprising in each target virtual machine, the N number of example deleting above-mentioned target application from least one target virtual machine specifically comprises: if the example quantity comprising above-mentioned target application in the total minimum target virtual machine of the example comprised is less than N, in a front M2 target virtual machine, all examples of above-mentioned target application are deleted according to said sequence, delete quantity and be designated as N-X2, the quantity comprising the example of above-mentioned target application in M2+1 target virtual machine in said sequence is made to be more than or equal to X2, X2 is that the residue of the example of above-mentioned target application deletes quantity, M2 and X2 is the integer being greater than 0, X2 example of above-mentioned target application is deleted in M2+1 target virtual machine in said sequence.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 11 kind of possible implementation of first aspect, said method also comprises: when self-contained example sum each in multiple target virtual machine is identical, the preferential example deleting the above-mentioned target application comprised in the minimum target virtual machine of application species number.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 12 kind of possible implementation of first aspect, said method also comprises: when self-contained example sum each in multiple target virtual machine is identical, and when each self-contained application species number is also identical, preferentially delete the example comprising the target application comprised in the target virtual machine of the example minimum number of above-mentioned target application.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 13 kind of possible implementation of first aspect, said method also comprises: when self-contained example sum each in multiple target virtual machine is identical, each self-contained application species number is also identical, and when the quantity of the example of each self-contained above-mentioned target application is also identical, the example of the target application comprised in the target virtual machine at the preferential deletion above-mentioned target application start-up time of example place the latest or the earliest, or in Stochastic choice any one virtual machine in above-mentioned multiple target virtual machine, delete the example of above-mentioned target application.

In conjunction with first aspect, or in conjunction with the implementation that the above-mentioned any one of first aspect is possible, in the 14 kind of possible implementation of first aspect, a special virtual machine is only included in above-mentioned target virtual machine, the example of above-mentioned target application is only comprised in above-mentioned special virtual machine, the sum of the example comprised in above-mentioned special virtual machine is more than or equal to N, and N number of example that the capacity reducing strategy that above-mentioned employing is preset deletes above-mentioned target application in above-mentioned target virtual machine comprises: in above-mentioned special virtual machine, delete N number of example.

According to the second aspect of the embodiment of the present invention, provide a kind of capacity reducing device of cloud platform resource, said apparatus comprises: receiver module, and for receiving the example removal request to target application on cloud platform, above-mentioned example removal request carries the mark of quantity identity and above-mentioned target application; Above-mentioned quantity identity represents the quantity of the example that above-mentioned target application needs are deleted to be N, N is the integer being greater than 0; Search module, find out target virtual machine for the mark receiving target application according to above-mentioned receiver module from above-mentioned cloud platform, above-mentioned target virtual machine is all virtual machines comprising the example of above-mentioned target application; Obtain module, for obtain above-mentioned search module searches to target virtual machine in the quantity of the kind applied belonging to each example and often kind of example applied; Policy module, for the quantity of the example according to the kind applied belonging to each example in the above-mentioned target virtual machine of above-mentioned acquisition module acquisition and often kind of application, adopts the capacity reducing strategy preset in above-mentioned target virtual machine, delete N number of example of above-mentioned target application.

In conjunction with second aspect, in the first possible implementation of second aspect, said apparatus also comprises checking module and release module, and above-mentioned checking module is for checking in above-mentioned target virtual machine whether occur free virtual machine, and the example quantity comprised in above-mentioned free virtual machine is zero; If above-mentioned checking module is checked through in above-mentioned destination virtual occur free virtual machine, above-mentioned release module is for discharging above-mentioned free virtual machine.

In conjunction with second aspect, or may implementation in conjunction with the first of second aspect, in the implementation that the second of second aspect is possible, above-mentioned policy module comprises counting unit and delete cells; Above-mentioned target virtual machine comprises at least one special virtual machine, only comprises the example of above-mentioned target application in above-mentioned special virtual machine; Above-mentioned counting unit is for judging the sum of example and the relation of N in all special virtual machines; If above-mentioned counting unit judges that the sum of example in all special virtual machines is more than or equal to N, then above-mentioned delete cells is used for according to the example quantity order from less to more comprised in each special virtual machine, from least one special virtual machine above-mentioned, delete N number of example.

In conjunction with second aspect, or in conjunction with the implementation that the above-mentioned any one of second aspect is possible, in the third possible implementation of first aspect, above-mentioned counting unit also for judge the example minimum number comprised special virtual machine in the quantity of example and the relation of N; If above-mentioned counting unit judges that the quantity of example in the special virtual machine of the example minimum number comprised is more than or equal to N, above-mentioned delete cells specifically for deleting N number of example in the special virtual machine of above-mentioned example minimum number.

In conjunction with second aspect, or in conjunction with the implementation that the above-mentioned any one of second aspect is possible, in the 4th kind of possible implementation of first aspect, above-mentioned counting unit also for judge the example minimum number comprised special virtual machine in the quantity of example and the relation of N; If above-mentioned counting unit judges that the quantity of example in the special virtual machine of the example minimum number comprised is less than N, above-mentioned delete cells specifically for: in front M special virtual machine, delete all examples according to said sequence, delete quantity and be designated as N-X, the quantity of the example comprised in M+1 special virtual machine in said sequence is made to be more than or equal to X, X is that the residue of the example of above-mentioned target application deletes quantity, M and X is the integer being greater than 0; X example is deleted in M+1 special virtual machine in said sequence.

In conjunction with second aspect, or in conjunction with the possible implementation of the above-mentioned any one of second aspect, in the 5th kind of possible implementation of first aspect, above-mentioned policy module comprises counting unit and delete cells; Above-mentioned target virtual machine comprises at least one special virtual machine, only comprises the example of above-mentioned target application in above-mentioned special virtual machine; Above-mentioned counting unit is for judging the sum of example and the relation of N in all special virtual machines; If above-mentioned counting unit judges that the sum of example in all special virtual machines is less than N, above-mentioned delete cells is used for: delete examples all in all special virtual machines, has deleted quantity and has been designated as N-Y; According to the example sum order from less to more comprised in each residue target virtual machine, delete Y example of above-mentioned target application from least one residue target virtual machine, Y is the residue deletion quantity of the example of above-mentioned target application, Y be greater than 0 integer.

In conjunction with second aspect, or in conjunction with the implementation that the above-mentioned any one of second aspect is possible, in the 6th kind of possible implementation of first aspect, above-mentioned counting unit is also for the relation of the example quantity and Y that judge the target application comprised in the residue target virtual machine of the example minimum number comprised; If above-mentioned counting unit judges that the quantity of the example of the target application comprised in the residue target virtual machine of the above-mentioned example minimum number comprised is more than or equal to Y, above-mentioned delete cells specifically for deleting Y example of above-mentioned target application in the special virtual machine of the above-mentioned example minimum number comprised.

In conjunction with second aspect, or in conjunction with the implementation that the above-mentioned any one of second aspect is possible, in the 7th kind of possible implementation of first aspect, above-mentioned counting unit is also for the relation of the example quantity and Y that judge the target application comprised in the residue target virtual machine of the example minimum number comprised;

If above-mentioned counting unit judges that the quantity of the example of the target application comprised in the residue target virtual machine of the above-mentioned example minimum number comprised is less than Y, above-mentioned delete cells specifically for: according to said sequence front M1 residue target virtual machine in delete all examples of above-mentioned target application, delete quantity and be designated as Y-X1, the quantity comprising the example of above-mentioned target application in M1+1 residue target virtual machine in said sequence is made to be more than or equal to X1, X1 is that the residue of the example of above-mentioned target application deletes quantity, M1 and X1 is the integer being greater than 0; X1 example of above-mentioned target application is deleted in M1+1 residue target virtual machine in said sequence.

In conjunction with second aspect, or in conjunction with the implementation that the above-mentioned any one of second aspect is possible, in the 8th kind of possible implementation of first aspect, above-mentioned policy module, specifically for according to the example sum order from less to more comprised in each target virtual machine, deletes N number of example of above-mentioned target application from least one target virtual machine.

In conjunction with second aspect, or in conjunction with the possible implementation of the above-mentioned any one of second aspect, in the 9th kind of possible implementation of first aspect, above-mentioned policy module comprises counting unit and delete cells; Above-mentioned counting unit is for the relation of the example quantity and N that judge the above-mentioned target application comprised in the target virtual machine of the example minimum number comprised; If above-mentioned counting unit judges that the example quantity comprising above-mentioned target application in the target virtual machine that the above-mentioned example sum comprised is minimum is more than or equal to N, above-mentioned delete cells specifically for deleting N number of example of above-mentioned target application in the target virtual machine that the above-mentioned example sum comprised is minimum.

In conjunction with second aspect, or in conjunction with the possible implementation of the above-mentioned any one of second aspect, in the tenth kind of possible implementation of first aspect, above-mentioned policy module comprises counting unit and delete cells; Above-mentioned counting unit is for the relation of the example quantity and N that judge the above-mentioned target application comprised in the target virtual machine of the example minimum number comprised; If above-mentioned counting unit judges that the example quantity comprising above-mentioned target application in the target virtual machine that the above-mentioned example sum comprised is minimum is less than N, above-mentioned delete cells specifically for: in a front M2 target virtual machine, delete all examples of above-mentioned target application according to said sequence, delete quantity and be designated as N-X2, the quantity comprising the example of above-mentioned target application in M2+1 target virtual machine in said sequence is made to be more than or equal to X2, X2 is that the residue of the example of above-mentioned target application deletes quantity, M2 and X2 is the integer being greater than 0; X2 example of above-mentioned target application is deleted in M2+1 target virtual machine in said sequence.

In conjunction with second aspect, or in conjunction with the possible implementation of the above-mentioned any one of second aspect, in the 11 kind of possible implementation of first aspect, above-mentioned policy module comprises counting unit and delete cells; Only include a special virtual machine in above-mentioned target virtual machine, in above-mentioned special virtual machine, only comprise the example of above-mentioned target application; Above-mentioned counting unit is for judging the sum of example and the relation of N in above-mentioned special virtual machine; If above-mentioned counting unit judges that the sum of example in above-mentioned special virtual machine is more than or equal to N, then above-mentioned delete cells is used for deleting N number of example from above-mentioned special virtual machine.

According to the third aspect of the embodiment of the present invention, provide a kind of capacity reducing system of cloud platform resource, said system comprises: user terminal and cloud platform; Above-mentioned user terminal is for sending the example removal request to target application on cloud platform to above-mentioned cloud platform, above-mentioned example removal request carries the mark of quantity identity and above-mentioned target application; Above-mentioned quantity identity represents the quantity of the example that above-mentioned target application needs are deleted to be N, N is the integer being greater than 0; Above-mentioned cloud platform is used for, and receives the example removal request that above-mentioned user terminal sends; Identifier lookup according to above-mentioned target application goes out target virtual machine, and above-mentioned target virtual machine is all virtual machines comprising the example of above-mentioned target application; Obtain the quantity of the kind of application belonging to each example in above-mentioned target virtual machine and the example of often kind of application; The quantity of the example of the kind applied belonging to example each in above-mentioned target virtual machine and often kind of application, adopts the capacity reducing strategy preset in above-mentioned target virtual machine, delete N number of example of above-mentioned target application.

According to the technical scheme that the embodiment of the present invention provides, when deleting example and carrying out capacity reducing, obtain kind and the quantity of running example in virtual machine, certain strategy is adopted according to this information, the virtual machine that prioritizing selection example is few carries out example deletion action, or first select the virtual machine of the example only the comprising target application virtual machine that prioritizing selection example is few to carry out example deletion action equally wherein, thus, the virtual machine that example is fewer, more selected when deleting example, make example after orderly deletion action concentrate in several virtual machines of minority as far as possible, and substantially increase the possibility occurring free virtual machine.Thus once there is free virtual machine, this virtual machine just can be released, improve cloud platform virtual machine resource utilization, reduce cloud platform energy consumption, the physical resource of release virtual machine effectively reduces the operation cost of cloud platform resource.

Accompanying drawing explanation

Fig. 1 is two kinds of mode configuration schematic diagrames of prior art medium cloud platform application;

Fig. 2 is the application scenarios schematic diagram of a kind of cloud platform resource capacity reducing in the embodiment of the present invention;

Fig. 3 is the flow chart of a kind of cloud platform resource capacity reduction method in the embodiment of the present invention;

Fig. 4 is the schematic diagram of example distributed intelligence in a kind of virtual machine in the embodiment of the present invention;

Fig. 5 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention;

Fig. 6 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention;

Fig. 7 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention;

Fig. 8 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention;

Fig. 9 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention;

Figure 10 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention;

Figure 11 is a kind of ordering rule application scenarios figure deleting example in virtual machine in the embodiment of the present invention;

Figure 12 is a kind of scheme schematic diagram moving example in integration virtual machine in the embodiment of the present invention;

Figure 13 is the schematic diagram of a kind of cloud platform resource capacity reducing device in the embodiment of the present invention;

Figure 14 is the schematic diagram of a kind of policy module in the embodiment of the present invention;

Figure 15 is the schematic diagram of a kind of cloud platform resource capacity reducing system in the embodiment of the present invention;

Figure 16 is the capacity reducing device structure schematic diagram of a kind of cloud platform resource in the embodiment of the present invention.

Embodiment

Embodiments provide a kind of capacity reduction method, equipment and system of cloud platform resource.

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 preferred embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.

Example (Instance) is the automatic expansion computing unit of application (Application), apply the most basic avatar, be the equal of application a kind of mirror image or copy, it provide all resources that can use needed for application.It comprises Language Runtime, application interface and the code applied and storage.Each example comprises a safe floor, to guarantee to be independent of each other between different instances.In any given time, an application may operate on one or more example.Example can be static, also can be dynamic, and dynamic instance can automatically start according to current demand and close, and static example is running always, and it can improve the performance of application.Example is different because of the difference of application, and the different instances under same application is identical, and they can provide a complete set for this application to use resource.Virtual machine is represented, the virtual machine that different numerals is different hereinafter with " VM numeral "; Represent application with " App numeral ", represent example, the application that different numerals is different or the different examples of application with " App digital-digital ".

At present, the application of cloud platform runs and mainly contains two kinds of ranks: virtual machine level and container rank.Virtual machine level refers to that a virtual machine runs an example, container rank refers to and a virtual machine starts multiple container, and between each container, resource is mutually isolated, runs an example in each container, as shown in Figure 1, Fig. 1 is two kinds of mode configuration schematic diagrames of prior art medium cloud platform application.

The present invention is based on the container rank at cloud platform, between each container, resource is mutually isolated, an example is run in each container, in each virtual machine, nearly tens to a hundreds of container, therefore the example of variety classes, varying number may to be run in each virtual machine, the all examples belonging to same application are called example of the same race, and the example belonging to different application is called example not of the same race.The distribution that the present invention is intended to how to carry out deleting and then make them in virtual machine according to certain strategic planning is more reasonable, and the resource of virtual machine is more reasonably utilized.

Refer to Fig. 2, Fig. 2 is the application scenarios schematic diagram of a kind of cloud platform resource capacity reducing in the embodiment of the present invention.

For the shopping website during two 11, due to advertising campaign, sizable external user can be had to access shopping website certain period, occupy Taobao, Jingdone district, cloud platform virtual machine resource when numerous application such as working as simultaneously, and movable once terminate, user's visit capacity then occurs significantly die-offing in pole.On the present cloud platform of this procedure body, it is exactly the example running a myriad of between active stage, and when activity end, most example does not need to rerun, but because example before is not deleted in time, a large amount of resources of virtual machine is taken without reason, cause the waste of resource and unreasonable distribution, application and development user owing to can not discharge more virtual machine, and adds operation cost.For addressing this problem the method, the equipment and system that the invention provides a kind of cloud platform resource capacity reducing.

Refer to Fig. 3, Fig. 3 is the flow chart of a kind of cloud platform resource capacity reduction method in the embodiment of the present invention, and the method comprises:

S101: receive the example removal request to target application on cloud platform, example removal request carries application identities and quantity identity; Application identities represents the application belonging to the example of target application; Quantity identity represents the quantity of the example of target application to be N, N is the integer being greater than 0.

Wherein the removal request of example can be that user sends in real time, also can be automatic telescopic service management system according in advance timed sending is set; Comprise specific application identities in the removal request of example, such as express by special field the example which kind of application software developer wants to delete, such as, delete the example that Sina is still deleted by Baidu; N represents that this operation of software developer wants to delete the quantity of example.

In specific implementation process, application identities and quantity identity are not limited to form separately, can be fields, can be a string character or numeral, also can be specific symbols, can also be combined fields; As long as it can represent unique application identities, maybe can indicate the deletion example quantity of specifying.

S102: the application identities according to target application finds out target virtual machine from cloud platform, target virtual machine is the virtual machine of the example comprising target application.

Such as when the developer of Taobao wants the example deleting Taobao, all virtual machines comprising Taobao's example can be found out with the unique ID number characterizing Taobao, they can be deleted as software developer the target virtual machine that example carries out capacity reducing.

S103: the quantity obtaining the kind of application belonging to each example in above-mentioned target virtual machine and the example of often kind of application.

Get distributed intelligence as shown in Figure 4, wherein Fig. 4 is the schematic diagram of example distributed intelligence in a kind of virtual machine, this distributed intelligence can clearly demonstrate each virtual machine VM comprises which application, each virtual machine VM respectively has each application in how many examples, each virtual machine VM to have how many examples, the example of a certain kind is distributed in the medium information of which virtual machine, on cloud platform, target virtual machine at least exists one, is certainly all far longer than one under normal circumstances.

S104: the quantity of the example of the kind applied belonging to example each in the target virtual machine obtained in S103 and often kind of application, adopts the capacity reducing strategy preset in target virtual machine, delete N number of example of described target application.

After the software developer of some application carries out a series of deletion action, the example distribution situation of cloud platform virtual machine can change, can by detecting the example distribution of virtual machine, especially detect target virtual machine, can search and whether there is the free virtual machine not comprising any example after deleting.The opportunity detected is relatively more flexible, and can carry out regular detection, detect after also often can deleting example in a virtual machine, after also N number of example all can being deleted, then unification detects.When described free virtual machine being detected, just by described free virtual machine release, operation cost can be reduced.

Wherein step S104 is in specific implementation, will follow certain capacity reducing strategy when deleting N number of example, optionally has several as follows.

The first capacity reducing strategy: filter out the virtual machine of the example only comprising target application as special virtual machine from all target virtual machine; According to the example distributed intelligence of each target virtual machine, when the sum obtaining example in all special virtual machines is more than or equal to N, then from less to more special virtual machine can be put in order according to the example quantity comprised, first the special virtual machine of example minimum number is selected, delete N number of example if can complete in the special virtual machine of this example minimum number, then delete termination.Wherein the most special situation is exactly that special virtual machine only has one, so can not sort in this situation, directly carry out the deletion of example wherein, if the example sum in this special virtual machine is more than or equal to N, so directly can complete deletion action; If be less than N, then can perform the 3rd kind of strategy.

For Fig. 5, Fig. 5 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention, can find by step S102 the virtual machine only comprising App1 and have VM1, VM2, VM3, known by step S103, the sum of the example that they comprise is respectively 5,3,1, therefore according to the example quantity that comprises from less to more virtual machine deletion order be arranged as VM3, VM2, VM1, first deletion action will be carried out in VM3, suppose that the developer of App1 wants the example of deletion 1 App1, so directly in VM3, carry out deletion can complete.

The second capacity reducing strategy: filter out the virtual machine of the example only comprising target application as special virtual machine from all target virtual machine; According to the example distributed intelligence of each target virtual machine, the sum obtaining example in all special virtual machines is more than or equal to N, then from less to more special virtual machine is put in order according to the example quantity comprised, examples all in M special virtual machine before deleting according to putting in order, delete quantity and be designated as N-X, the quantity comprising the example of target application in M+1 special virtual machine in sequence is made to be more than or equal to X, X is that the residue of the example of target application deletes quantity, M and X is the integer being greater than 0; X example of described target application is deleted in the ranking in M+1 special virtual machine.

For Fig. 6, Fig. 6 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention, can find by step S102 the virtual machine only comprising App1 and have VM1, VM2, VM3, known by step S103, the sum of the example that they comprise is respectively 5, 3, 1, therefore according to the example quantity that comprises from less to more virtual machine deletion order be arranged as VM3, VM2, VM1, first in VM3, deletion action is carried out, suppose that the developer of App1 wants the example of deletion 3 App1, but have in VM3 and only have the example of 1 App1, then first the App1 example of 1 in VM3 is deleted, due to also 2 App1 examples will be deleted again, therefore need in VM2, to carry out deletion action in order, and the example quantity of App1 in VM2 is greater than 2, therefore the App1 of 2 in VM2 is deleted, complete deletion task.

The third capacity reducing strategy: filter out the virtual machine of the example only comprising target application as special virtual machine from all target virtual machine, according to the example distributed intelligence of each target virtual machine, when the sum obtaining example in all special virtual machines is less than N, then first delete all examples in all special virtual machines, delete quantity and be designated as N-Y, from less to more residue target virtual machine is put in order according to the sum comprising all kinds of example again, first select to comprise the minimum target virtual machine of the sum of all kinds of example, if comprise in the minimum target virtual machine of the sum of all kinds of example and can complete at this example deleting Y target application, then delete termination, wherein Y is the residue deletion quantity of the example of target application, Y be greater than 0 integer.

For Fig. 7, Fig. 7 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention, can find by step S102 the virtual machine comprising App1 and have VM1, VM2, VM3, VM4, VM5, known by step S103, the virtual machine wherein only comprising App1 example has VM1, VM2, VM1, the quantity that VM2 comprises App1 example is respectively 4, 2, suppose that the developer of App1 wants deletion 7 App1 examples, the summation comprising App1 example due to VM1 and VM2 is 6, be less than 7, therefore first first totally 6 the App1 examples in VM1 and VM2 are all deleted, the virtual machine comprising App1 at present has VM3, VM4, VM5, their each self-contained all kinds of example sums are respectively 2,3,4, following basis comprises all kinds of example sum and from less to more virtual machine deletion order is arranged as VM3, VM4, VM5, first deletion action will be carried out in VM3, because remaining deletion quantity is 7-6=1, and in VM3, comprise an App1 example, therefore directly in VM3, carry out deletion can complete.

4th kind of capacity reducing strategy: filter out the virtual machine of the example only comprising target application as special virtual machine from all target virtual machine, according to the example distributed intelligence of each target virtual machine, the sum obtaining example in all special virtual machines is less than N, then first delete all examples in all special virtual machines, delete quantity and be designated as N-Y, from less to more residue target virtual machine is put in order according to the sum comprising all kinds of example again, the example of target application all in M target virtual machine before deleting according to putting in order, delete quantity and be designated as Y-X, the quantity comprising the example of target application in M+1 target virtual machine in sequence is made to be more than or equal to X, X is that the residue of the example of target application deletes quantity, M and X is the integer being greater than 0, the example of X target application is deleted in the ranking in M+1 target virtual machine.

For Fig. 8, Fig. 8 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention, can find by step S102 the virtual machine comprising App1 and have VM1, VM2, VM3, VM4, VM5, known by step S103, the virtual machine wherein only comprising App1 example has VM1, VM2, VM1, the quantity that VM2 comprises App1 example is respectively 4, 2, suppose that the developer of App1 wants deletion 9 App1 examples, the summation comprising App1 example due to VM1 and VM2 is 6, be less than 9, therefore first first totally 6 the App1 examples in VM1 and VM2 are all deleted, the virtual machine comprising App1 at present has VM3, VM4, VM5, their each self-contained all kinds of example sums are respectively 2, 3, 4, following basis comprises all kinds of example sum and from less to more virtual machine deletion order is arranged as VM3, VM4, VM5, first deletion action will be carried out in VM3, because remaining deletion quantity is 9-6=3, and in VM3, only comprise an App1 example, therefore first in VM3, an App1 example is deleted, next in VM4, deletion action is carried out according to putting in order, owing to having in VM4 and only having an App1 example, and now remaining deletion quantity is 9-6-1=2, therefore continue to continue to delete a central only App1 example in VM4, now remaining deletion quantity is 9-6-1-1=1, therefore continue in VM5, to carry out deletion action according to putting in order, owing to there being 2 App1 examples in VM5, therefore only need delete 1 App1 example in VM5 can delete complete.

5th kind of capacity reducing strategy: target virtual machine puts in order by sum according to all kinds of example from less to more, first select to comprise the minimum target virtual machine of the sum of all kinds of example, if the example deleting N number of target application can be completed in the target virtual machine that the sum comprising all kinds of example is minimum, then delete termination.

For Fig. 9, Fig. 9 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention, can find by step S102 the virtual machine comprising App1 and have VM1, VM2, VM3, known by step S103, the sum that they comprise various example is respectively 5,3,2, therefore using the target virtual machine of VM3 as preferential deletion example, suppose that the developer of App1 wants the example of deletion 1 App1, so direct carrying out in VM3 is deleted.

6th kind of capacity reducing strategy: target virtual machine puts in order by sum according to all kinds of example from less to more, according to the example deleting target application all in M target virtual machine that puts in order, delete quantity and be designated as N-X, the quantity comprising the example of target application in M+1 target virtual machine in sequence is made to be more than or equal to X, X is that the residue of the example of target application deletes quantity, M and X is the integer being greater than 0; The example of X target application is deleted in the ranking in M+1 target virtual machine.

For Figure 10, Figure 10 is a kind of scheme schematic diagram deleting example in virtual machine in the embodiment of the present invention, can find by step S102 the virtual machine comprising App1 and have VM1, VM2, VM3, the sum that they comprise various example is respectively 5,3,2, therefore according to example quantity sum, the order that virtual machine carries out deleting is arranged as VM3, VM2, VM1, suppose that the developer of App1 wants the example of deletion 4 App1, but have in VM3 and only have the example of 1 App1, then first the App1 example of 1 in VM3 being deleted; Due to also 3 App1 examples will be deleted again, therefore continue in order to perform deletion in VM2, owing to comprising 2 App1 in VM2, be less than 3, therefore the App1 of 2 in VM2 is all deleted, next VM1 to be carried out as the next one virtual machine deleting example, delete the start-up time of 1 the App1 example the latest in VM1.

In above six kinds of capacity reducing strategies, often run into some examples to distribute identical multiple virtual machines when sorting from less to more according to example quantity, in order to avoid conflict appears in sequence, therefore there is preference strategy in capacity reducing strategy, such as, can sets following several sequence priority rules:

Article 1, sort priority rule: if there is each self-contained example sum in multiple target virtual machine when putting in order identical, the minimum target virtual machine of the sample types so comprised is preferential when putting in order.

Article 2 sequence priority rule: if there is each self-contained example sum in multiple target virtual machine when putting in order identical, and each self-contained sample types number is also identical, and the target virtual machine so comprising the example minimum number of target application is preferential when putting in order.

Article 3 sequence priority rule: if there is each self-contained example sum in multiple target virtual machine when putting in order identical, each self-contained sample types number is also identical, and the example quantity of each self-contained target application is also identical, so start-up time target application the latest the target virtual machine at example place preferential when putting in order, or deleted by the order in morning and evening, or one of them virtual machine of Stochastic choice is deleted, or follow the arbitrary personalized priority rule of developer and carry out correspondingly deletion action.

It should be noted that, in each delet method above, when deleting the Multi-instance of same application in single virtual machine, especially, when the quantity of the example of the target application existed in this virtual machine is greater than the number of needs deletion, deleted by order early in evening start-up time according to the example of target application.

In specific implementation process, the example distribution situation of each virtual machine varies, in delete procedure, therefore guarantee the necessary condition being capacity reducing process and carrying out smoothly in good order that puts in order.

For Figure 11, Figure 11 is a kind of ordering rule application scenarios figure deleting example in virtual machine in the embodiment of the present invention, this scene may occur in the application scenarios of above-mentioned 4th kind and the 6th kind capacity reducing strategy, suppose that the numeral larger expression in " APP1-numeral " is more late for start-up time, according to the example sum in virtual machine, the preliminary priority that puts in order is: VM2, VM3 are better than VM4, VM5VM6 and are better than VM1, VM7; Be better than VM3 because Article 1 sequence priority rule can obtain VM2, VM4, VM5 are better than VM6; VM5 is better than because Article 2 sequence priority rule can obtain VM4; VM1 is better than because Article 3 sequence priority rule can obtain VM7.In sum, in the example in Figure 11, the virtual machine deleting example puts in order and is followed successively by VM2, VM3, VM4, VM5, VM6, VM7, VM1.

Except the capacity reducing strategy of above-mentioned 6 kinds of comparatively systems, also has a kind of supplementary prioritization scheme, after the example distributed intelligence that each target virtual machine of acquisition comprises, or after in the above-mentioned 6 kinds of capacity reducing strategies of experience, any one carries out deletion action, select a suitable virtual machine as host virtual machine according to the size of remaining space, by whole instance migration of comprising in the less target virtual machine of various example sum in this host virtual machine, and discharge those virtual machines freed out after migration.

For Figure 12, Figure 12 is a kind of scheme schematic diagram moving example in integration virtual machine in the embodiment of the present invention, the example distributed intelligence that the virtual machine obtained by S103 is comprised as shown in figure 12, after a series of deletion actions that experience is above-mentioned, App1-1 is contain in VM1, App1-2, App1-3, App2-3 is contains only in VM2, App2-1 is contains only in VM3, but VM2, but cannot discharge in time because there is example although VM3 is very easy to release, now can according to the computing function of cloud platform to virtual machine space size, the VM1 selecting example more is host virtual machine, by the App2-3 in VM2, App2-1 migration in VM3 is incorporated in VM1, VM2 and VM3 is left unused, VM2 and VM3 can be discharged by follow-up releasing operation.

In conjunction with more than the possibility discussed, the developer of application according to the demand of oneself by used in combination stage by stage for above 6 kinds of capacity reducing schemes, can also build personalized deletion scheme.Such as, can perform above-mentioned 1st kind or the 2nd kind of capacity reducing mode when performing first stage deletion, then after longer a period of time, then when performing the above-mentioned 5th or the 6th kind of capacity reducing scheme.

The technical scheme that the embodiment of the present invention provides, when applying capacity reducing, the removal request of example is utilized to carry application identities and quantity identity marks virtual machine, and get the example distributed intelligence of each target virtual machine, by adopting the strategy of capacity reducing further, the virtual machine that prioritizing selection example is few carries out example deletion action, or first select the virtual machine of the example only the comprising target application virtual machine that prioritizing selection example is few to carry out example deletion action equally wherein, thus, the virtual machine that example is fewer, more selected during capacity reducing, occur after making capacity reducing that the probability of free virtual machine improves greatly, also make example concentrate in several virtual machines of minority simultaneously as far as possible, improve the utilance of resources of virtual machine, reduce cloud platform energy consumption, energy-saving and emission-reduction.

Refer to Figure 13, Figure 13 is the schematic diagram of a kind of cloud platform resource capacity reducing device in the embodiment of the present invention.This device 200 comprises:

Receiver module 201, for receiving the example removal request to target application on cloud platform, this example removal request carries the mark of quantity identity and target application; Quantity identity represents the quantity of the example that target application needs are deleted to be N, N is the integer being greater than 0.

Application identities in the removal request of wherein example is determined by the developer applied, and the developer of an application can only delete the example of oneself application, and can determine the quantity N that deletes.

Search module 202, find out target virtual machine for the mark receiving target application according to receiver module 401 from cloud platform, target virtual machine is all virtual machines comprising the example of target application.

Obtain module 203, for obtaining the quantity of searching kind and the often kind of example applied applied belonging to each example in target virtual machine that module 202 obtains.Obtain module 203 and be specifically responsible for the example distribution situation of collecting each virtual machine and comprising, comprise each example of different App, and the VM at each example place, obtain the arrangement view as Fig. 4, the example containing which kind in each virtual machine can be known, the number of often kind of example.

Policy module 204, for the quantity of the example according to the kind applied belonging to each example in the target virtual machine of acquisition module 203 acquisition and often kind of application, adopts the capacity reducing strategy preset in target virtual machine, delete N number of example of target application.

In addition, this device 200 also comprises detection module 205, and whether there is for detecting the free virtual machine that instance number is zero, detection time is comparatively flexible, can perform in the process of deletion action in policy module 204 and detect, also can detect after completing deletion action; Also comprising release module 206, for when free virtual machine being detected, free virtual machine being discharged.Can be deleted the virtual machine of releasing idling herein by the order of calling cloud platform I layer, the api as openstack is /v2/:tenant_id/servers/:server_id.

In specific implementation process, above-mentioned policy module 204 can comprise screening unit 2041, counting unit 2042, sequencing unit 2043, delete cells 2044 and policy unit 2045; Refer to Figure 14, Figure 14 is the schematic diagram of a kind of policy module in the embodiment of the present invention.

Wherein screen unit 2041 for according to application identities and virtual machine instance distributed intelligence, from all target virtual machine, filter out the virtual machine of the example only comprising described target application as special virtual machine.Above-mentioned capacity reducing strategy the first to the four kind of scheme all relates to this module; Counting unit 2042 judges the sum of example and the relation of N in all special virtual machine that screening unit 2041 screens, if counting unit 2042 judges that the sum of example in all special virtual machines is more than or equal to N, then special virtual machine puts in order according to the example quantity comprised by sequencing unit 2043 from less to more; Delete cells 2044 is according to the example deleting N number of target application in the target virtual machine after sequence that puts in order.If counting unit 2042 judges that the sum of example in all special virtual machines is less than N, then first delete cells 2044 deletes all examples in all special virtual machines, and residue target virtual machine puts in order according to the sum comprising all kinds of example by sequencing unit 2043 from less to more; Delete cells 2044 according to the example deleting Y target application in the target virtual machine after sequence that puts in order, Y be the example of described target application residue delete quantity, Y be greater than 0 integer.

In the 5th kind of above-mentioned capacity reducing strategy and the 6th kind of scheme, policy module 204 only can comprise counting unit 2042, sequencing unit 2043, delete cells 2044 and policy unit 2045.Sequencing unit 2043 is for putting in order target virtual machine from less to more according to the sum of all kinds of example; Delete cells 2044 is for according to the example deleting N number of target application in the target virtual machine after sequence that puts in order.

The capacity reducing device 200 of above-mentioned cloud platform also comprises transferring module 207, for the whole instance migration comprised in the relatively less target virtual machine of various example sum being comprised in the relatively many virtual machines of various example sum to another one.After the example distributed intelligence that each target virtual machine of acquisition comprises, or in the above-mentioned 6 kinds of capacity reducing schemes of experience after any one deletion action, a host virtual machine is selected according to the size of free space or the example quantity that comprises, by whole instance migration of comprising in the few target virtual machine of various example sum in another host virtual machine, and the virtual machine that release frees out after migration.

In another kind of specific implementation, a large amount of policing rules is had in policy module 204, policy module 204 at least can comprise counting unit 2042 and delete cells 2044, and wherein counting unit 2042 and delete cells 2044 can perform the complete capacity reducing strategy of in embodiment corresponding to above-mentioned Fig. 5 to Figure 12 6 kinds.Row specific as follows 6 kinds of situations.

Situation 1: target virtual machine comprises at least one special virtual machine, only comprises the example of described target application in special virtual machine; Counting unit 2042 is for judging the sum of example and the relation of N in all special virtual machines; If counting unit 2042 judges that the sum of example in all special virtual machines is more than or equal to N, counting unit 2042 judges the quantity of example and the relation of N in the special virtual machine of the example minimum number comprised again, if the quantity of example is more than or equal to N in the special virtual machine of the example minimum number comprised, delete cells 2044 specifically for deleting N number of example in the special virtual machine of example minimum number.

Wherein there are a kind of special circumstances, if only have one in special virtual machine, so technical unit directly can judge the quantity of example and the relation of N in this special virtual machine, if the quantity of example is more than or equal to N in this special virtual machine, then in this special virtual machine, directly deletes N number of example; If the quantity of example is less than N in this special virtual machine, corresponding module performs as situation 3.

Situation 2: target virtual machine comprises at least one special virtual machine, only comprises the example of described target application in special virtual machine, counting unit 2042 is for judging the sum of example and the relation of N in all special virtual machines, if counting unit 2042 judges that the sum of example in all special virtual machines is more than or equal to N, counting unit 2042 judges the quantity of example and the relation of N in the special virtual machine of the example minimum number comprised again, if the quantity of example is less than N in the special virtual machine of the example minimum number comprised, delete cells 2044 is specifically for according to the example sum order from less to more comprised in each special virtual machine, all examples are deleted in front M special virtual machine, delete quantity and be designated as N-X, the quantity of the example comprised in M+1 special virtual machine in said sequence is made to be more than or equal to X, X is that the residue of the example of target application deletes quantity, M and X is the integer being greater than 0, delete cells 2044 deletes X example in M+1 special virtual machine in order.

Situation 3: target virtual machine comprises at least one special virtual machine, only comprises the example of described target application in special virtual machine; Counting unit 2042 is for judging the sum of example and the relation of N in all special virtual machines; If counting unit 2042 judges that the sum of example in all special virtual machines is less than N, delete cells 2044, for deleting examples all in all special virtual machines, has been deleted quantity and has been designated as N-Y; Counting unit 2042 is also for the relation of the example quantity and Y that judge the target application comprised in the residue target virtual machine of the example minimum number comprised; If counting unit 2042 judges that the quantity of the example of the target application comprised in the residue target virtual machine of the above-mentioned example minimum number comprised is more than or equal to Y, delete cells 2044 specifically for deleting Y example of target application in the special virtual machine of the above-mentioned example minimum number comprised.

Situation 4: target virtual machine comprises at least one special virtual machine, only comprises the example of described target application in special virtual machine, counting unit 2042 is for judging the sum of example and the relation of N in all special virtual machines, if counting unit 2042 judges that the sum of example in all special virtual machines is less than N, delete cells 2044, for deleting examples all in all special virtual machines, has been deleted quantity and has been designated as N-Y, counting unit 2042 is also for the relation of the example quantity and Y that judge the target application comprised in the residue target virtual machine of the example minimum number comprised, if counting unit 2042 judges that the quantity of the example of the target application comprised in the residue target virtual machine of the above-mentioned example minimum number comprised is less than Y, delete cells 2044 is specifically for remaining the example sum order from less to more comprised in target virtual machine according to each, the all examples of target application are deleted in front M1 residue target virtual machine, delete quantity and be designated as Y-X1, the quantity comprising the example of target application in M1+1 residue target virtual machine in order is made to be more than or equal to X1, X1 is that the residue of the example of target application deletes quantity, M1 and X1 is the integer being greater than 0, delete cells 2044 deletes X1 example of described target application in order in M1+1 residue target virtual machine.

Situation 5: counting unit 2042 is for the relation of the example quantity and N that judge the target application comprised in the target virtual machine of the example minimum number comprised; If counting unit 2042 judges that the example quantity comprising target application in the total minimum target virtual machine of example comprised is more than or equal to N, delete cells 2044 specifically for deleting N number of example of target application in the target virtual machine that the above-mentioned example sum comprised is minimum.

Situation 6: counting unit 2042 is for the relation of the example quantity and N that judge the target application comprised in the target virtual machine of the example minimum number comprised; If counting unit 2042 judges that the example quantity comprising target application in the total minimum target virtual machine of example comprised is less than N, delete cells 2044 is specifically for according to the example sum order from less to more comprised in each target virtual machine, the all examples of target application are deleted in a front M2 target virtual machine, delete quantity and be designated as N-X2, the quantity comprising the example of described target application in M2+1 target virtual machine in order is made to be more than or equal to X2, X2 is that the residue of the example of target application deletes quantity, M2 and X2 is the integer being greater than 0; Delete cells 2044 deletes X2 example of described target application in said sequence in M2+1 target virtual machine.

Also can comprise preference strategy in policy unit 2045, this preference strategy provides sort by for sequencing unit, occurs sequence conflict when avoiding putting in order, and specifically can comprise 3 the sequence priority rules mentioned in an embodiment.In addition can also comprise some ordering rules and migration strategy in policy module 204, can also comprise and formulate personalized deletion scheme according to demand by the developer applied, deletion action be carried out without any confusion, in target virtual machine, deletes N number of example; Removing module is according to the application identities in the removal request of example and the quantity of deleting example, one can be provided to apply capacity reducing API style command: DELETE/v2/apps/:guid/instance/:count) (wherein: guid is unique ID of mark application,: count needs the example number deleted): the application of the field references of guid is all different and unique.

Embodiments provide a kind of capacity reducing device of cloud platform, when applying capacity reducing, search the target virtual machine that application identities that module 202 can receive according to receiver module 201 finds the example comprising target application, the example distributed intelligence of each target virtual machine can be known by obtaining module 203, under the guidance of policy module 204, in target virtual machine, the deletion of example is carried out according to certain capacity reducing strategy, the virtual machine that prioritizing selection example is few carries out example deletion action, or first select the virtual machine of the example only the comprising target application virtual machine that prioritizing selection example is few to carry out example deletion action equally wherein, make the more few more single virtual machine of example, example is more selected, virtual machine is made more easily to occur the free time, thus be released module 206 and discharge, and example concentrates in several virtual machines of minority after capacity reducing as far as possible, cloud platform virtual machine resource utilization can be improved, reduce cloud platform energy consumption, for application developer saves expense.

Refer to Figure 15, Figure 15 is the schematic diagram of a kind of cloud platform resource capacity reducing system in the embodiment of the present invention.This device 300 comprises:

User terminal 301, for sending the removal request of the example for cloud platform.

In general, the developer of application has permission and holds user terminal, a kind of request mechanism be when developer by user terminal pre-set on cloud platform when capacity reducing, capacity reducing quantity and how capacity reducing time, complete and the automatic management of capacity reducing is arranged, user, without the need to operating in real time, just can complete capacity reducing operation by automatic telescopic service management system.

Another kind of request mechanism is user under special sight of special time, needs to carry out personalized capacity reducing operation according to the actual service condition of cloud platform, now can determine the removal request specifically sending what kind of example, have certain flexibility.

Under above two kinds of request mechanisms, the example removal request of user, all comprises application identities and quantity identity, and application identities represents the example needing to delete any application, and quantity identity represents that the example of this kind of application needs to delete how many.

Cloud platform 302, for:

Receive the example removal request that user terminal sends; Identifier lookup according to target application goes out target virtual machine, and target virtual machine is all virtual machines comprising the example of target application; Obtain the quantity of the kind of application belonging to each example in target virtual machine and the example of often kind of application; The quantity of the example of the kind applied belonging to example each in target virtual machine and often kind of application, adopts the capacity reducing strategy preset in target virtual machine, delete N number of example of target application.

In specific implementation process, if cloud platform 302 is after deletion action, detects idle virtual machine, then free virtual machine is discharged.

Embodiments provide a kind of capacity reducing system of cloud platform, cloud platform according to the removal request of the example of user terminal, can realize personalized capacity reducing operation, when carrying out the operation of deleting example, in target virtual machine, the deletion of example is carried out according to certain capacity reducing strategy, the virtual machine that prioritizing selection example is few carries out example deletion action, or first select the virtual machine of the example only the comprising target application virtual machine that prioritizing selection example is few to carry out example deletion action equally wherein, make the more few more single virtual machine of example, example is more selected, virtual machine is made more easily to occur the free time, thus be released, and example concentrates in several virtual machines of minority after capacity reducing as far as possible, cloud platform virtual machine resource utilization can be improved, reduce cloud platform energy consumption, for application developer saves expense.

Refer to Figure 16, Figure 16 is the capacity reducing device structure schematic diagram of a kind of cloud platform resource in the embodiment of the present invention.This equipment 400 comprises:

Processor 401, for generation of corresponding operating control signal, issue the corresponding parts of calculating treatmenting equipment, read and process software in data, especially the data read and process in memory 402 and program, to make wherein each functional module perform corresponding function, thus control corresponding parts and carry out action by the requirement of instruction.

Memory 402, for storage program and various data, the software units such as main storage operation system, application and function command or their subset or their superset.Operating system comprises various system program as windows series etc., for realizing various basic business and processing hardware based task device, nonvolatile RAM (NVRAM) can also be comprised, the hardware, software and the data resource that comprise in Management Calculation treatment facility are provided to processor 401, support comprising of control software design and application.

Transceiver 403, for gathering, obtaining or the information of transmission, can be used for transmission of information between the modules.

Each hardware cell above-mentioned can be communicated by bus connection.

Thus, by calling program or the instruction of memory 402 storage, transceiver 403 can receive the example removal request to target application on cloud platform, and processor 401 can search the virtual machine of the example comprising this target application according to the application identities in example removal request, i.e. target virtual machine; Processor 401 obtains the example distributed intelligence of each target virtual machine, next according to example removal request, call and be present in N number of example that capacity reducing strategy concrete in memory 402 goes to delete target application, and detect whether there is the virtual machine that instance number is zero after deletion, when detecting that instance number is the free virtual machine of zero, this free virtual machine discharges by processor 401.

Those of ordinary skill in the art are known, and all or part of step in said method can be completed by the hardware that program command is relevant, and this program can be stored in a computer-readable recording medium.Through the above description of the embodiments, those skilled in the art can be well understood to the present invention can use hardware implementing, or firmware realizes, or their compound mode realizes.

More than above are only the preferred embodiment of technical solution of the present invention, be not intended to limit protection scope of the present invention.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included in protection scope of the present invention.

Claims (28)

1. a capacity reduction method for cloud platform resource, described cloud platform resource is the resources of virtual machine on cloud platform, and virtual machine comprises the example of application, it is characterized in that, described method comprises:
Receive the example removal request to target application on cloud platform, described example removal request carries the mark of quantity identity and described target application; Described quantity identity represents the quantity of the example that described target application needs are deleted to be N, N is the integer being greater than 0;
Mark according to described target application finds out target virtual machine from described cloud platform, and described target virtual machine is all virtual machines comprising the example of described target application;
Obtain the quantity of the kind of application belonging to each example in described target virtual machine and the example of often kind of application;
The quantity of the example of the kind applied belonging to example each in described target virtual machine and often kind of application, adopts the capacity reducing strategy preset in described target virtual machine, delete N number of example of described target application.
2. method as claimed in claim 1, is characterized in that, adopting after the capacity reducing strategy preset deletes N number of example of described target application in described target virtual machine, described method also comprises:
Check in described target virtual machine and whether occur free virtual machine, the example quantity comprised in described free virtual machine is zero;
If be checked through in described destination virtual and occur free virtual machine, discharge described free virtual machine.
3. method as claimed in claim 1, it is characterized in that, a special virtual machine is only included in described target virtual machine, the example of described target application is only comprised in described special virtual machine, the sum of the example comprised in described special virtual machine is more than or equal to N, and N number of example that the capacity reducing strategy that described employing is preset deletes described target application in described target virtual machine comprises:
N number of example is deleted in described special virtual machine.
4. method as claimed in claim 1, it is characterized in that, described target virtual machine comprises at least two special virtual machines, only comprises the example of described target application in described special virtual machine, and the sum of the example comprised in all special virtual machines is more than or equal to N;
N number of example that the capacity reducing strategy that described employing is preset deletes described target application in described target virtual machine comprises:
According to the example quantity order from less to more comprised in each special virtual machine, from least one special virtual machine described, delete N number of example.
5. method as claimed in claim 4, is characterized in that the described example quantity order from less to more according to comprising in each special virtual machine is deleted N number of example and specifically comprised from least one special virtual machine described:
If the example quantity comprised in the special virtual machine of the example minimum number comprised is more than or equal to N, in the special virtual machine of described example minimum number, delete N number of example.
6. method as claimed in claim 4, is characterized in that the described example quantity order from less to more according to comprising in each special virtual machine is deleted N number of example and specifically comprised from least one special virtual machine described:
If the example quantity comprised in the special virtual machine of the example minimum number comprised is less than N, in front M special virtual machine, all examples are deleted according to described order, delete quantity and be designated as N-X, the quantity of the example comprised in M+1 special virtual machine in described order is made to be more than or equal to X, X is that the residue of the example of described target application deletes quantity, M and X is the integer being greater than 0;
X example is deleted in M+1 special virtual machine in described order.
7. method as claimed in claim 1, it is characterized in that, described target virtual machine comprises at least one special virtual machine, only comprises the example of described target application in described special virtual machine, and in all special virtual machines, the sum of example is less than N;
N number of example that the capacity reducing strategy that described employing is preset deletes described target application in described target virtual machine comprises:
Delete examples all in all special virtual machines, deleted quantity and be designated as N-Y;
According to the example sum order from less to more comprised in each residue target virtual machine, delete Y example of described target application from least one residue target virtual machine, Y is the residue deletion quantity of the example of described target application, Y be greater than 0 integer.
8. method as claimed in claim 7, is characterized in that, the described example sum order from less to more according to comprising in each residue target virtual machine, and Y the example deleting described target application from least one residue target virtual machine specifically comprises:
If the example quantity comprising described target application in the residue target virtual machine that the example sum comprised is minimum is more than or equal to Y, in the residue target virtual machine that the described example sum comprised is minimum, delete Y example of described target application.
9. method as claimed in claim 7, is characterized in that, the described example sum order from less to more according to comprising in each residue target virtual machine, and Y the example deleting described target application from least one residue target virtual machine specifically comprises:
If the example quantity comprising described target application in the residue target virtual machine that the example sum comprised is minimum is less than Y, in front M1 residue target virtual machine, all examples of described target application are deleted according to described order, delete quantity and be designated as Y-X1, the quantity comprising the example of described target application in M1+1 residue target virtual machine in described order is made to be more than or equal to X1, described X1 is that the residue of the example of described target application deletes quantity, and described M1 and described X1 is the integer being greater than 0;
X1 example of described target application is deleted in M1+1 residue target virtual machine in described order.
10. method as claimed in claim 1, it is characterized in that, N number of example that the capacity reducing strategy that described employing is preset deletes described target application in described target virtual machine comprises:
According to the example sum order from less to more comprised in each target virtual machine, from least one target virtual machine, delete N number of example of described target application.
11. methods as claimed in claim 10, is characterized in that, the described example sum order from less to more according to comprising in each target virtual machine, and the N number of example deleting described target application from least one target virtual machine specifically comprises:
If the example quantity comprising described target application in the target virtual machine that the example sum comprised is minimum is more than or equal to N, in the target virtual machine that the described example sum comprised is minimum, delete N number of example of described target application.
12. methods as claimed in claim 10, is characterized in that, the described example sum order from less to more according to comprising in each target virtual machine, and the N number of example deleting described target application from least one target virtual machine specifically comprises:
If the example quantity comprising described target application in the target virtual machine that the example sum comprised is minimum is less than N, in a front M2 target virtual machine, all examples of described target application are deleted according to described order, delete quantity and be designated as N-X2, the quantity comprising the example of described target application in M2+1 target virtual machine in described order is made to be more than or equal to X2, X2 is that the residue of the example of described target application deletes quantity, M2 and X2 is the integer being greater than 0;
X2 example of described target application is deleted in M2+1 target virtual machine in described order.
13. according to any one of claim 7-12 method, it is characterized in that, when self-contained example sum each in multiple target virtual machine is identical, the preferential example deleting the described target application comprised in the minimum target virtual machine of application species number.
14. according to any one of claim 7-12 method, it is characterized in that, when self-contained example sum each in multiple target virtual machine is identical, and when each self-contained application species number is also identical, preferentially delete the example comprising the target application comprised in the target virtual machine of the example minimum number of described target application.
15. as described in any one of claim 4-12 method, it is characterized in that, when self-contained example sum each in multiple target virtual machine is identical, each self-contained application species number is also identical, and when the quantity of the example of each self-contained described target application is also identical, the example of the target application comprised in the target virtual machine at the preferential deletion described target application start-up time of example place the latest or the earliest, or in Stochastic choice any one virtual machine in described multiple target virtual machine, delete the example of described target application.
The capacity reducing device of 16. 1 kinds of cloud platform resources, is characterized in that, described device comprises:
Receiver module, for receiving the example removal request to target application on cloud platform, described example removal request carries the mark of quantity identity and described target application; Described quantity identity represents the quantity of the example that described target application needs are deleted to be N, N is the integer being greater than 0;
Search module, find out target virtual machine for the mark receiving target application according to described receiver module from described cloud platform, described target virtual machine is all virtual machines comprising the example of described target application;
Obtain module, for search described in obtaining module searches to target virtual machine in the quantity of the kind applied belonging to each example and often kind of example applied;
Policy module, for the quantity of the example according to the kind applied belonging to each example in the described target virtual machine of described acquisition module acquisition and often kind of application, adopts the capacity reducing strategy preset in described target virtual machine, delete N number of example of described target application.
17. devices as claimed in claim 16, it is characterized in that, described device also comprises checking module and release module, and described checking module is for checking in described target virtual machine whether occur free virtual machine, and the example quantity comprised in described free virtual machine is zero;
If described checking module is checked through in described destination virtual occur free virtual machine, described release module is for discharging described free virtual machine.
18. devices as claimed in claim 16, it is characterized in that, described policy module comprises counting unit and delete cells; Only include a special virtual machine in described target virtual machine, in described special virtual machine, only comprise the example of described target application;
Described counting unit is for judging the sum of example and the relation of N in described special virtual machine;
If described counting unit judges that the sum of example in described special virtual machine is more than or equal to N,
Then described delete cells is used for deleting N number of example from described special virtual machine.
19. devices as claimed in claim 16, it is characterized in that, described policy module comprises counting unit and delete cells; Described target virtual machine comprises at least two special virtual machines, only comprises the example of described target application in described special virtual machine;
Described counting unit is for judging the sum of example and the relation of N in all special virtual machines;
If described counting unit judges that the sum of example in all special virtual machines is more than or equal to N,
Then described delete cells is used for according to the example quantity order from less to more comprised in each special virtual machine, from least one special virtual machine described, delete N number of example.
20. devices as claimed in claim 19, is characterized in that, described counting unit also for judge the example minimum number comprised special virtual machine in the quantity of example and the relation of N;
If described counting unit judges that the quantity of example in the special virtual machine of the example minimum number comprised is more than or equal to N, described delete cells specifically for deleting N number of example in the special virtual machine of described example minimum number.
21. devices as claimed in claim 19, is characterized in that, described counting unit also for judge the example minimum number comprised special virtual machine in the quantity of example and the relation of N;
If described counting unit judges that the quantity of example in the special virtual machine of the example minimum number comprised is less than N, described delete cells specifically for:
In front M special virtual machine, all examples are deleted according to described order, delete quantity and be designated as N-X, the quantity of the example comprised in M+1 special virtual machine in described order is made to be more than or equal to X, X is that the residue of the example of described target application deletes quantity, M and X is the integer being greater than 0;
X example is deleted in M+1 special virtual machine in described order.
22. devices as claimed in claim 16, it is characterized in that, described policy module comprises counting unit and delete cells; Described target virtual machine comprises at least one special virtual machine, only comprises the example of described target application in described special virtual machine;
Described counting unit is for judging the sum of example and the relation of N in all special virtual machines;
If described counting unit judges that the sum of example in all special virtual machines is less than N, described delete cells is used for: delete examples all in all special virtual machines, has deleted quantity and has been designated as N-Y;
According to the example sum order from less to more comprised in each residue target virtual machine, delete Y example of described target application from least one residue target virtual machine, Y is the residue deletion quantity of the example of described target application, Y be greater than 0 integer.
23. devices as claimed in claim 22, is characterized in that, described counting unit is also for the relation of the example quantity and Y that judge the target application comprised in the residue target virtual machine of the example minimum number comprised;
If the quantity of the example of the target application comprised in the residue target virtual machine of the example minimum number comprised described in described counting unit judges is more than or equal to Y, described delete cells specifically for deleting Y example of described target application in the special virtual machine of the described example minimum number comprised.
24. devices as claimed in claim 22, is characterized in that, described counting unit is also for the relation of the example quantity and Y that judge the target application comprised in the residue target virtual machine of the example minimum number comprised;
If described counting unit judge described in the quantity of the example of target application that comprises in the residue target virtual machine of example minimum number that comprises be less than Y, described delete cells specifically for:
In front M1 residue target virtual machine, all examples of described target application are deleted according to described order, delete quantity and be designated as Y-X1, the quantity comprising the example of described target application in M1+1 residue target virtual machine in described order is made to be more than or equal to X1, X1 is that the residue of the example of described target application deletes quantity, M1 and X1 is the integer being greater than 0;
X1 example of described target application is deleted in M1+1 residue target virtual machine in described order.
25. devices as claimed in claim 16, is characterized in that, described policy module, specifically for according to the example sum order from less to more comprised in each target virtual machine, deletes N number of example of described target application from least one target virtual machine.
26. devices as claimed in claim 25, it is characterized in that, described policy module comprises counting unit and delete cells; Described counting unit is for the relation of the example quantity and N that judge the described target application comprised in the target virtual machine of the example minimum number comprised;
If the example quantity comprising described target application in the target virtual machine that the example sum comprised described in described counting unit judges is minimum is more than or equal to N, described delete cells specifically for deleting N number of example of described target application in the target virtual machine that the described example sum comprised is minimum.
27. devices as claimed in claim 25, it is characterized in that, described policy module comprises counting unit and delete cells; Described counting unit is for the relation of the example quantity and N that judge the described target application comprised in the target virtual machine of the example minimum number comprised;
If described counting unit judge described in comprise described target application in the minimum target virtual machine of the example sum that comprises example quantity be less than N, described delete cells specifically for:
In a front M2 target virtual machine, all examples of described target application are deleted according to described order, delete quantity and be designated as N-X2, the quantity comprising the example of described target application in M2+1 target virtual machine in described order is made to be more than or equal to X2, X2 is that the residue of the example of described target application deletes quantity, M2 and X2 is the integer being greater than 0; X2 example of described target application is deleted in M2+1 target virtual machine in described order.
The capacity reducing system of 28. 1 kinds of cloud platform resources, is characterized in that, described system comprises:
User terminal and cloud platform;
Described user terminal is for sending the example removal request to target application on cloud platform to described cloud platform, described example removal request carries the mark of quantity identity and described target application; Described quantity identity represents the quantity of the example that described target application needs are deleted to be N, N is the integer being greater than 0;
Described cloud platform is used for:
Receive the example removal request that described user terminal sends;
Identifier lookup according to described target application goes out target virtual machine, and described target virtual machine is all virtual machines comprising the example of described target application;
Obtain the quantity of the kind of application belonging to each example in described target virtual machine and the example of often kind of application;
The quantity of the example of the kind applied belonging to example each in described target virtual machine and often kind of application, adopts the capacity reducing strategy preset in described target virtual machine, delete N number of example of described target application.
CN201410848185.1A 2014-12-29 2014-12-29 A kind of capacity reduction method, device and the system of cloud platform resource CN104539708B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410848185.1A CN104539708B (en) 2014-12-29 2014-12-29 A kind of capacity reduction method, device and the system of cloud platform resource

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410848185.1A CN104539708B (en) 2014-12-29 2014-12-29 A kind of capacity reduction method, device and the system of cloud platform resource

Publications (2)

Publication Number Publication Date
CN104539708A true CN104539708A (en) 2015-04-22
CN104539708B CN104539708B (en) 2018-01-23

Family

ID=52855175

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410848185.1A CN104539708B (en) 2014-12-29 2014-12-29 A kind of capacity reduction method, device and the system of cloud platform resource

Country Status (1)

Country Link
CN (1) CN104539708B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105740054A (en) * 2016-02-01 2016-07-06 浪潮软件股份有限公司 Virtual machine management method and device
CN106293868A (en) * 2015-05-15 2017-01-04 苏宁云商集团股份有限公司 In a kind of cloud computing environment, virtual machine expands capacity reduction method and scalable appearance system
WO2017041613A1 (en) * 2015-09-10 2017-03-16 华为技术有限公司 Mirror image deployment method and apparatus
CN107968810A (en) * 2016-10-20 2018-04-27 阿里巴巴集团控股有限公司 A kind of resource regulating method of server cluster, device and system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102236603A (en) * 2010-04-29 2011-11-09 国际商业机器公司 Garbage recycling method and system in virtual environment
CN103605575A (en) * 2013-11-18 2014-02-26 深圳市远行科技有限公司 Cloud Foundry platform application scheduling system and Cloud Foundry platform application scheduling method
US20140074973A1 (en) * 2012-09-07 2014-03-13 Oracle International Corporation System and method for orchestration of services for use with a cloud computing environment
US8706852B2 (en) * 2011-08-23 2014-04-22 Red Hat, Inc. Automated scaling of an application and its support components
CN103916396A (en) * 2014-04-10 2014-07-09 电子科技大学 Method for automatic expansion of application examples of cloud platform based on load self-adaption
US20140372984A1 (en) * 2013-06-18 2014-12-18 Disney Enterprises, Inc. Safe low cost web services software deployments

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102236603A (en) * 2010-04-29 2011-11-09 国际商业机器公司 Garbage recycling method and system in virtual environment
US8706852B2 (en) * 2011-08-23 2014-04-22 Red Hat, Inc. Automated scaling of an application and its support components
US20140074973A1 (en) * 2012-09-07 2014-03-13 Oracle International Corporation System and method for orchestration of services for use with a cloud computing environment
US20140372984A1 (en) * 2013-06-18 2014-12-18 Disney Enterprises, Inc. Safe low cost web services software deployments
CN103605575A (en) * 2013-11-18 2014-02-26 深圳市远行科技有限公司 Cloud Foundry platform application scheduling system and Cloud Foundry platform application scheduling method
CN103916396A (en) * 2014-04-10 2014-07-09 电子科技大学 Method for automatic expansion of application examples of cloud platform based on load self-adaption

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106293868A (en) * 2015-05-15 2017-01-04 苏宁云商集团股份有限公司 In a kind of cloud computing environment, virtual machine expands capacity reduction method and scalable appearance system
WO2017041613A1 (en) * 2015-09-10 2017-03-16 华为技术有限公司 Mirror image deployment method and apparatus
CN106528262A (en) * 2015-09-10 2017-03-22 华为技术有限公司 Image deployment method and device
CN106528262B (en) * 2015-09-10 2019-10-22 华为技术有限公司 Mirror image dispositions method, device
CN105740054A (en) * 2016-02-01 2016-07-06 浪潮软件股份有限公司 Virtual machine management method and device
CN107968810A (en) * 2016-10-20 2018-04-27 阿里巴巴集团控股有限公司 A kind of resource regulating method of server cluster, device and system

Also Published As

Publication number Publication date
CN104539708B (en) 2018-01-23

Similar Documents

Publication Publication Date Title
US20190258526A1 (en) Server consolidation using virtual machine resource tradeoffs
US10120726B2 (en) Hybrid virtual machine configuration management
US20180267837A1 (en) Central processing unit resource allocation method and computing node
US20200081731A1 (en) Method, system and apparatus for creating virtual machine
CN104937584B (en) Based on the quality of shared resource to the service quality of virtual machine and application program offer optimization through priority ranking
US9183016B2 (en) Adaptive task scheduling of Hadoop in a virtualized environment
US10387202B2 (en) Quality of service implementation in a networked storage system with hierarchical schedulers
Park et al. Locality-aware dynamic VM reconfiguration on MapReduce clouds
EP2715539B1 (en) Distributed computing framework
DE112011101633B4 (en) Reorganization of storage levels taking virtualization and dynamic resource allocation into account
US8631410B2 (en) Scheduling jobs in a cluster having multiple computing nodes by constructing multiple sub-cluster based on entry and exit rules
US20180367460A1 (en) Data flow processing method and apparatus, and system
US20150195416A1 (en) Optimizing storage between mobile devices and cloud storage providers
US9866450B2 (en) Methods and apparatus related to management of unit-based virtual resources within a data center environment
JP5939740B2 (en) Method, system and program for dynamically allocating resources
CN102724277B (en) The method of live migration of virtual machine and deployment, server and group system
DE112011100392B4 (en) Resource affinity by adding or removing queen card pairs for net adapter with software for receipt scale (rss)
US9274844B2 (en) Priority-based management of system load level
US8954487B2 (en) Management server and method for providing cloud computing service
JP6384877B2 (en) Streaming server session idle optimization
KR20170110708A (en) Opportunistic Resource Migration for Resource Deployment Optimization
US10412021B2 (en) Optimizing placement of virtual machines
CN103067293B (en) Method and system for multiplex and connection management of a load balancer
US9069465B2 (en) Computer system, management method of computer resource and program
EP2898410A1 (en) Automated profiling of resource usage

Legal Events

Date Code Title Description
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20180123

Termination date: 20181229