CN104572308A - Computing resource distributing method, distributed type computing method and distributed type computing device - Google Patents
Computing resource distributing method, distributed type computing method and distributed type computing device Download PDFInfo
- Publication number
- CN104572308A CN104572308A CN201510069461.9A CN201510069461A CN104572308A CN 104572308 A CN104572308 A CN 104572308A CN 201510069461 A CN201510069461 A CN 201510069461A CN 104572308 A CN104572308 A CN 104572308A
- Authority
- CN
- China
- Prior art keywords
- computing
- computational resource
- pool
- resource
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The embodiment of the invention provides a computing resource distributing method, a distributed type computing method and a distributed type computing device which are applied to a distributed type system. The computing resource distributing method comprises the following steps: grouping computing resources of computing nodes of the distributed system according to a computing type; establishing a computing tool corresponding to the computing type, and distributing the computing resources in the computing nodes to the corresponding pool according to the computing type; and while performing computing task processing, firstly searching the computing pool corresponding to the computing type of the computing task, processing the computing task of the computing type through computing resources of the computing pool, so that the computing resources of the same computing type only process the computing task of the computing type. The computing resource distributing method is convenient for managing the computing resources, so that the computing resources are effectively utilized.
Description
Technical field
The application relates to field of computer technology, relates to a kind of computational resource allocation method, distributed computing method and device in particular.
Background technology
Distributed system comprises multiple interconnected computing node, has worked in coordination a common target between each computing node.Each computing node generally includes some computational resources, in order to the evaluation work carrying out data with computational resource.
In prior art, when utilizing distributed system to carry out Distributed Calculation, be that a calculation task is divided into multiple little subtask, calculated by the computational resource in multiple computing node respectively, then integrate according to the operation result of each computational resource and draw data conclusion.
Because the hardware configuration of different computing node may be different, therefore the computing power of computational resource is also different, and the type of service of different calculation tasks is different, also different to the requirement of computational resource, but, existing this distributed computing, just carry out task computation by the computational resource of current idle, and same computational resource may relate to the different calculation task of process, computational resource cannot unified management, makes effectively to utilize computational resource.
Summary of the invention
In view of this, this application provides a kind of computational resource allocation method, distributed computing method and device, make effective rate of utilization computational resource.
For achieving the above object, the application provides following technical scheme:
First aspect, provide a kind of computational resource allocation device, be applied in distributed system, described distributed system comprises multiple computing node, and described device comprises:
Computing pool control module, for receiving and RESPONSE CALCULATION pond steering order, sets up the computing pool of the compute type of corresponding described computing pool steering order instruction, and the computational resource information of described computing node;
Node control module, for receiving and responsive node steering order, determines the computing node that described node control instruction indicates;
Resource distribution module, for receiving and resource response distribution instruction, according to described compute type, the computational resource allocation in the computing node selecting described node control instruction to indicate gives corresponding computing pool; So that when receiving calculation task, the calculation task corresponding by the compute type of computing pool described in the computational resource process of described computing pool.
Preferably, also comprise:
Resource updates module, for receiving and resource response update instruction, upgrades the computational resource in the computing pool of described resource updates instruction instruction.
Preferably, also comprise:
Resource feedback module, for computing node sending controling instruction corresponding to the computational resource distributed or upgraded, so that described computing node responds described steering order, starts or closes corresponding computational resource.
Preferably, also comprise:
Resource adjusting module, for receiving and resource response adjustment instruction, idle computing resources in first computing pool of described resource adjustment instruction instruction is distributed to the second computing pool, and described resource adjustment instruction is generate when detecting that the computational resource of described first computing pool and described second computing pool meets pre-conditioned.
Second aspect, provides a kind of distributed computing devices, is applied in distributed system, and described distributed system comprises multiple computing node, and described device comprises:
Task determination module, for obtaining calculation task, and determines the compute type of described calculation task;
Computing pool searches module, for searching the computing pool of the compute type of corresponding described calculation task; Described computing pool is set up in advance for different compute type, and according to compute type, selects the computational resource allocation of each computing node in described distributed system to corresponding computing pool;
Resource determination module, for being retrieved as the computational resource that described computing pool is distributed;
Task processing module, for calculation task described in the described computational resource process that obtained by described resource determination module.
The third aspect, provide a kind of computational resource allocation method, be applied in distributed system, described distributed system comprises multiple computing node, and described method comprises:
Determine by RESPONSE CALCULATION pond steering order, the computing pool of the compute type of the described computing pool steering order instruction of correspondence of foundation;
Receive and responsive node steering order, determine the computing node in the described distributed system that described node control instruction indicates, and the computational resource information of described computing node;
Receive and resource response distribution instruction, according to described compute type, the computational resource allocation in the computing node selecting described node control instruction to indicate gives described computing pool; So that when receiving calculation task, the calculation task corresponding by the compute type of computing pool described in the computational resource process of described computing pool.
Preferably, described according to described compute type, after the computational resource allocation in the computing node selecting described node control instruction to indicate gives described computing pool, described method also comprises:
Receive and resource response update instruction, the computational resource in the computing pool of described resource updates instruction instruction is upgraded.
Preferably, after the computational resource in the described computing pool described resource updates instruction indicated upgrades, described method also comprises:
To the computing node sending controling instruction that the computational resource distributed or upgraded is corresponding, so that described computing node responds described steering order, start or close described computational resource.
Preferably, described according to described compute type, after the computational resource allocation in the computing node selecting described node control instruction to indicate gives described computing pool, described method also comprises:
Receive and resource response adjustment instruction, idle computing resources in first computing pool of described resource adjustment instruction instruction is distributed to the second computing pool, and described resource adjustment instruction is generate when detecting that the computational resource of described second computing pool meets pre-conditioned.
Fourth aspect, provides a kind of distributed computing method, is applied in distributed system, and described distributed system comprises multiple computing node, and described method comprises:
Obtain calculation task, and determine the compute type of described calculation task;
Search the computing pool of the compute type of corresponding described calculation task; Described computing pool is set up in advance for different compute type, and according to compute type, selects the computational resource allocation of each computing node in described distributed system to corresponding computing pool;
Be retrieved as the computational resource that described computing pool is distributed;
By calculation task described in the described computational resource process obtained.
Known via above-mentioned technical scheme, compared with prior art, this application provides a kind of computational resource allocation method, distributed computing method and device, computational resource is divided into groups according to compute type, by setting up the computing pool of corresponding compute type, by the computational resource in computing node, according to compute type, distribute to corresponding computing pool, when carrying out calculation task process, first the computing pool that the compute type of this calculation task is corresponding is searched, by the calculation task of this compute type of computational resource process of this computing pool, the computational resource belonging to same compute type is made only to process the calculation task of this compute type, facilitate Management Calculation resource, divide according to compute type, computational resource is made to obtain effective utilization.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present application or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only the embodiment of the application, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to the accompanying drawing provided.
The structural representation of a kind of computational resource allocation device embodiment that Fig. 1 provides for the embodiment of the present application;
The structural representation of a kind of another embodiment of computational resource allocation device that Fig. 2 provides for the embodiment of the present application;
The structural representation of a kind of another embodiment of computational resource allocation device that Fig. 3 provides for the embodiment of the present application;
The structural representation of a kind of distributed computing devices embodiment that Fig. 4 provides for the embodiment of the present application;
The process flow diagram of a kind of computational resource allocation method embodiment that Fig. 5 provides for the embodiment of the present application;
The process flow diagram of a kind of another embodiment of computational resource allocation method that Fig. 6 provides for the embodiment of the present application;
The process flow diagram of a kind of another embodiment of computational resource allocation method that Fig. 7 provides for the embodiment of the present application;
The process flow diagram of a kind of distributed computing method embodiment that Fig. 8 provides for the embodiment of the present application.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present application, be clearly and completely described the technical scheme in the embodiment of the present application, obviously, described embodiment is only some embodiments of the present application, instead of whole embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not making the every other embodiment obtained under creative work prerequisite, all belong to the scope of the application's protection.
Technical scheme is mainly used in distributed system, and distributed system is by comprising multiple interconnected computing node.Multiple computing node composition cluster, each computing node all can as the resource of Distributed Calculation, computational resource in each computing node characterizes the computing power of this computing node, and it is relevant with the hardware configuration of computing node, such as internal memory, CPU, hard disk etc.
The division of computational resource can divide according to hardware resource, and such as computing node comprises the CPU that has 32 threads, namely can using every 2 threads as a computational resource, and namely this computing node has 16 computational resources.
In prior art, be pre-configured by the computational resource number of each computing node in distributed system, fix, the adjustment of computational resource or change, need to restart distributed system, be unfavorable for management.And same computational resource may relate to the different calculation task of process, computational resource cannot unified management, makes effectively to utilize computational resource.
In the embodiment of the present application, computational resource is divided into groups according to compute type, by setting up the computing pool of corresponding compute type, by the computational resource in computing node, according to compute type, distribute to corresponding computing pool, when carrying out calculation task process, first the computing pool that the compute type of this calculation task is corresponding is searched, by the calculation task of this compute type of computational resource process of this computing pool, the computational resource belonging to same compute type is made only to process the calculation task of this compute type, facilitate Management Calculation resource, divide according to compute type, computational resource is made to obtain effective utilization.And the calculation task of different compute type processes in the computational resource of different computing pool, does not interfere with each other.
The structural representation of a kind of computational resource allocation device embodiment that Fig. 1 provides for the embodiment of the present application, this device is applied particularly in distributed system, described distributed system comprises multiple computing node, this device can be applied particularly in any one computing node, as the function that this computing node can realize, it can be integrated in the processor of this computing node, is connected with the processor of computing node as independently module.
Described device can comprise:
Computing pool control module 101, for receiving and RESPONSE CALCULATION pond steering order, sets up the computing pool of the compute type of corresponding described computing pool steering order instruction.
Node control module 102, for receiving and responsive node steering order, determines the computing node that described node control instruction indicates and the computational resource information of described computing node;
Resource distribution module 103, for receiving and resource response distribution instruction, according to compute type, the computational resource allocation in the computing node selecting described node control instruction to indicate gives corresponding computing pool; So that when receiving calculation task, the calculation task corresponding by the compute type of computing pool described in the computational resource process of described computing pool.
Wherein, computational resource information comprises the number and compute type etc. of computational resource.
The computing node of node control instruction instruction can comprise one or more, and the computational resource number of each computing node and the compute type of computational resource may be different.
The compute type of computing pool steering order instruction may comprise one or more, for each compute type, sets up the computing pool that each compute type is corresponding, and each computing pool is namely for the treatment of the calculation task of its compute type corresponding.
Instruction of resource allocation specifically may be used for one or more computational resource allocation identical with the compute type of computing pool in the one or more computing node of triggering selection to corresponding computing pool.
In the embodiment of the present application, by setting up computing pool, computational resource is divided into groups according to compute type, computing pool can identify the computational resource belonging to same compute type, when receiving calculation task, according to the compute type of calculation task, the computing pool of the compute type of corresponding calculation task can be selected, this calculation task of computational resource process identified by this computing pool, in a computing pool, computational resource only processes calculation task corresponding to its compute type, according to compute type, computational resource is carried out dividing and processing calculation task, computational resource is made to obtain effective utilization.And the calculation task of different compute type processes in the computational resource of different computing pool, does not interfere with each other, convenient management.
After resource distribution module distributes calculation resources, this device can also comprise:
Resource feedback module, for computing node sending controling instruction corresponding to the computational resource distributed, so that described computing node responds described steering order, starts corresponding computational resource.
Wherein, compute type can have multiple dividing mode.
In a kind of possible implementation, compute type can be determined according to the demand of hardware resource consumption, such as, can be divided into consumption internal memory type, consumption CPU type, consumption hard disk type etc.
And computing node is according to different hardware configuration (CPU, internal memory, hard disk etc.), all there is certain difference.If any the CPU of computing node very strong, its computational resource can process the calculation task of consumption CPU, and the internal memory of some computing nodes is very large, and its computational resource can process the calculation task of consumption internal memory, and the hard disk of some computing nodes is fine, its computational resource can handle the calculation task of hard disk well.
Therefore by setting up the computing pool of different compute type, the computational resource allocation in the computing node that CPU is very strong can be selected to the computing pool of consumption CPU type, select the computational resource allocation in the computing node that internal memory is very large to the computing pool of consumption internal memory type, select the computational resource allocation in the good computing node of hard disk in the computing pool of consumption hard disk type.
In same computing pool, same computational resource only can process the calculation task of its process the most applicable, makes computational resource can obtain fully effective utilization.
In the implementation that another kind is possible, compute type can divide according to the type of service of calculation task.
Such as type of service can comprise coding and decoding video process, large Data Analysis etc.
Thus the computing pool of corresponding different service types can be set up, and the computational resource allocation in seletion calculation node gives different computing pools, the calculation task of a computational resource process type of service of a computing pool, thus different service types calculation task can be separated process, do not interfere with each other, convenient statistics, fully, effectively can utilize computational resource.
It should be noted that, compute type can also adopt other modes to divide, and ensures the calculation task of computational resource process same type in a computing pool, computational resource can be made to obtain and fully, effectively utilize.
Wherein, as a kind of possible implementation, node control instruction can be trigger when detecting that distributed system increases computing node, thus can determine by node control instruction the computing node that distributed system increases, and the computational resource information of this computing node.
Instruction of resource allocation can trigger after node control module determines computing node, thus by resource response distribution instruction, the computational resource of computing node node control module can determined, according to compute type, distributes to different computing pools.
Computing pool steering order can be the compute type of computing node according to the computational resource in the computing node determined, or trigger generation according to the compute type pre-set, thus by this computing pool steering order of response, the computing pool of corresponding compute type can be set up.
As the implementation that another kind is possible, node control instruction can be triggered by user, user can select computing node, number and the computational resource compute type of the computational resource of this computing node can also be provided, thus trigger node steering order, thus by this node control instruction of response, the computing node that user selectes can be determined, and the information such as the computational resource number of this computing node and the compute type of computational resource.
Computing pool steering order also can be triggered by user, and user can provide the compute type of computing pool simultaneously, calculates the information such as title, thus by RESPONSE CALCULATION pond steering order, can set up the computing pool of the compute type that respective user provides.
Instruction of resource allocation also can be triggered by user, user can according to compute type, select for computing node corresponding to same compute type and computing pool, the computational resource allocation number of computing node is provided, thus by resource response distribution instruction, the number computing pool that user in computing node selects can be distributed to this computing pool.
Seen from the above description, as another embodiment, the computational resource allocation device in the embodiment of the present application can also comprise:
Display module, for display control panel, exports computing pool and sets up information, computing node information and Resourse Distribute information etc.
User can operation control panel, trigger node steering order, computing pool steering order and instruction of resource allocation etc.
The structural representation of a kind of another embodiment of resource allocation device that Fig. 2 provides for the embodiment of the present application, be with difference embodiment illustrated in fig. 1, the described resource allocation device in the present embodiment can also comprise:
Resource updates module 104, for receiving and resource response update instruction, upgrades the computational resource in the computing pool of described resource updates instruction instruction.
Wherein, renewal can refer to the operations such as deletion, time-out.
In the embodiment of the present application, for the computing pool of distributes calculation resources, the computational resource in computing pool can also be upgraded, such as, delete the computational resource etc. of some computing nodes in computing pool.
This resource updates instruction can be that user triggers, carry in this resource updates instruction user instruction one or more computing node and one or more computing node in need upgrade computational resource, thus by this resource updates instruction of response, can upgrade the computational resource of this one or more computing node in computing pool.
Such as, the computational resource of the first computing node in the first computing pool is closed 2 by this resource updates instruction instruction, then by response, the computational resource of the first computing node in this first computing pool is suspended 2.
In addition, this device can also comprise:
Upgrade feedback module 105, for computing node sending controling instruction corresponding to the computational resource distributed or upgraded, so that described computing node responds described steering order, start or close corresponding computational resource.
In addition, as another embodiment, as shown in Figure 3, described resource allocation device can also comprise:
Resource adjusting module 106, for receiving and resource response adjustment instruction, distributes to the second computing pool by the idle computing resources in the first computing pool of described resource adjustment instruction instruction.
Wherein, described resource adjustment instruction is generate when detecting that the computational resource of described first computing pool and described second computing pool meets pre-conditioned.
In task processes, for any two computing pools, if the computational resource of one of them computing pool is idle, and computational resource in another computing pool not enough time, instruction can be adjusted by triggers resource, by the computational resource allocation in the computing pool of computational resource free time to the not enough computing pool of computational resource, with can components utilising computational resource, ensure the treatment effeciency of calculation task.
Namely first computing pool can refer to the computing pool of computational resource free time, and namely the second computing pool refers to the computing pool that computational resource is not enough.
This pre-conditioned a kind of possible implementation, namely can refer to that computational resource in the first computing pool is idle, and computational resource in the second computing pool is not enough.
As the implementation that another kind is possible, if set up computing pool according to type of service, when calculation task is distinguished, this is pre-conditioned can refer to that the calculation task of the first computing pool all compares with the calculation task of the second computing pool and consume same hardware resource, now, the idle computing resources of the first computing pool can be distributed to the second computing pool, to make full use of computational resource.
If set up computing pool according to hardware resource consumption type, calculation task is distinguished, this is pre-conditioned can refer to that the calculation task of the first computing pool and the calculation task of the second computing pool are the calculation task processing same type of service, also the idle computing resources of the first computing pool can be distributed to the second computing pool, to facilitate, unified management be carried out to the calculation task of same type of service.
The embodiment of the present application carries out computational resource adjustment by resource adjusting module between computing pool, further increases the utilization factor of computational resource.
In addition, Fig. 3 shown device can also comprise resource updates module and resource feedback module.
The structural representation of a kind of distributed computing devices embodiment that Fig. 4 provides for the embodiment of the present application, this application of installation is in distributed system, described distributed system comprises multiple computing node, this device can be applied particularly in any one computing node, as the function that this computing node can realize, it can be integrated in the processor of this computing node, is connected with the processor of computing node as independently module.
Described device can comprise:
Task determination module 401, for obtaining calculation task, and determines the compute type of described calculation task.
Computing pool searches module 402, for searching the computing pool of the compute type of corresponding described calculation task.
Wherein, described computing pool is set up in advance for different compute type, and according to compute type, selects the computational resource allocation of each computing node in described distributed system to corresponding computing pool.
The foundation of computing pool and the distribution of computational resource can be carried out according to mode described in above-described embodiment.
Certainly, also can in advance according to the computational resource in the computing node in compartment system, these computational resources are divided by compute type, and set up the computing pool of corresponding different compute type, then in just described distributed system, the computational resource of each computing node distributes to corresponding computing pool according to different compute type.
Resource determination module 403, for being retrieved as the computational resource that described computing pool is distributed;
Task processing module 404, for calculation task described in the described computational resource process that obtained by described resource determination module.
In the embodiment of the present application, for the calculation task obtained, according to the compute type of this calculation task, can search should the computing pool of compute type, and the computational resource determined by the computing pool of this compute type can be determined.Can by calculation task described in this computational resource process.
Concrete, this calculation task can be decomposed into some subtasks, obtain subtask by the computational resource of this computing pool and to go forward side by side row operation.
In the embodiment of the present application, in a computing pool, computational resource only processes calculation task corresponding to its compute type, computational resource is obtained and fully, effectively utilizes.And the calculation task of different compute type processes in the computational resource of different computing pool, does not interfere with each other, convenient management.
The embodiment of the present application additionally provides a kind of computing node, and it can comprise the computational resource allocation device as described in Fig. 1 ~ Fig. 3, and distributed computing devices as shown in Figure 4.
The process flow diagram of a kind of computational resource allocation method embodiment that Fig. 5 provides for the embodiment of the present application, the method is applied particularly in distributed system, and described distributed system comprises multiple computing node.
Described method can comprise following step:
501: determine by RESPONSE CALCULATION pond steering order, the computing pool of the compute type of the described computing pool steering order instruction of correspondence of foundation.
This computing pool can be set up in advance, or set up in real time according to the actual conditions of Resourse Distribute.
502: receive and responsive node steering order, determine the computing node in the described distributed system that described node control instruction indicates, and the computational resource information of described computing node.
503: receive and resource response distribution instruction, according to described compute type, the computational resource allocation in the computing node selecting described node control instruction to indicate gives corresponding computing pool; So that when receiving calculation task, the calculation task corresponding by the compute type of computing pool described in the computational resource process of described computing pool.
Wherein, by computational resource allocation to after computing pool, computing node sending controling instruction that can also be corresponding to the computational resource distributed, so that described computing node responds described steering order, starts described computational resource.
In the embodiment of the present application, by setting up computing pool, computational resource is divided into groups according to compute type, computing pool can identify the computational resource belonging to same compute type, when receiving calculation task, according to the compute type of calculation task, the computing pool of the compute type of corresponding calculation task can be selected, this calculation task of computational resource process identified by this computing pool, in a computing pool, computational resource only processes calculation task corresponding to its compute type, according to compute type, computational resource is carried out dividing and processing calculation task, computational resource is made to obtain effective utilization.And the calculation task of different compute type processes in the computational resource of different computing pool, does not interfere with each other, convenient management.
As another embodiment, as shown in Figure 6, after the computational resource allocation in the computing node that step 503 selects described node control instruction to indicate gives corresponding computing pool, described method can also comprise:
504: receive and resource response update instruction, the computational resource in the computing pool of described resource updates instruction instruction is upgraded.
After being upgraded by computational resource, computing node sending controling instruction that can also be corresponding to the computational resource upgraded, so that described computing node responds described steering order, processes described computational resource.
Therefore, the method can also comprise:
505: to the computing node sending controling instruction that the computational resource distributed or upgraded is corresponding, so that described computing node responds described steering order, start or close described computational resource.
Wherein, renewal can refer to the operations such as deletion, time-out.
In the embodiment of the present application, for the computing pool of distributes calculation resources, the computational resource in computing pool can also be upgraded, such as, delete the computational resource etc. of some computing nodes in computing pool.
This resource updates instruction can be that user triggers, carry in this resource updates instruction user instruction one or more computing node and one or more computing node in need upgrade computational resource, thus by this resource updates instruction of response, can upgrade the computational resource of this one or more computing node in computing pool.
As another embodiment, as shown in Figure 7, after the computational resource allocation in the computing node that step 503 selects described node control instruction to indicate gives corresponding computing pool, described method can also comprise:
506: receive and resource response adjustment instruction, the idle computing resources in the first computing pool of described resource adjustment instruction instruction is distributed to the second computing pool.
Wherein, described resource adjustment instruction is generate when detecting that the computational resource of described second computing pool meets pre-conditioned.
In task processes, for any two computing pools, if the computational resource of one of them computing pool is idle, and computational resource in another computing pool not enough time, instruction can be adjusted by triggers resource, by the computational resource allocation in the computing pool of computational resource free time to the not enough computing pool of computational resource, with can components utilising computational resource, ensure the treatment effeciency of calculation task.
Namely first computing pool can refer to the computing pool of computational resource free time, and namely the second computing pool refers to the computing pool that computational resource is not enough.
This pre-conditioned a kind of possible implementation, namely can refer to that computational resource in the first computing pool is idle, and computational resource in the second computing pool is not enough.
As the implementation that another kind is possible, if set up computing pool according to type of service, when calculation task is distinguished, this is pre-conditioned can refer to that the calculation task of the first computing pool and the calculation task of the second computing pool consume same hardware resource, now, the idle computing resources of the first computing pool can be distributed to the second computing pool, to make full use of computational resource.
If set up computing pool according to hardware resource consumption type, calculation task is distinguished, this is pre-conditioned can refer to that the calculation task of the first computing pool and the calculation task of the second computing pool are the calculation task processing same type of service, also the idle computing resources of the first computing pool can be distributed to the second computing pool, to facilitate, unified management be carried out to the calculation task of same type of service.
The embodiment of the present application carries out computational resource adjustment by resource adjusting module between computing pool, further increases the utilization factor of computational resource.
The process flow diagram of a kind of distributed computing method embodiment that Fig. 8 provides for the embodiment of the present application, described method is applied particularly in distributed system, and described distributed system comprises multiple computing node, and described method can comprise following step:
801: obtain calculation task, and determine the compute type of described calculation task.
802: the computing pool of searching the compute type of corresponding described calculation task.
Described computing pool is set up in advance for different compute type, and according to compute type, selects the computational resource allocation of each computing node in described distributed system to corresponding computing pool.
The foundation of computing pool and the distribution of computational resource can be carried out according to mode described in above-described embodiment.
Certainly, also can in advance according to the computational resource in the computing node in compartment system, these computational resources are divided by compute type, and set up the computing pool of corresponding different compute type, then in just described distributed system, the computational resource of each computing node distributes to corresponding computing pool according to different compute type.
803: be retrieved as the computational resource that described computing pool is distributed.
804: by calculation task described in the described computational resource process obtained.
In the embodiment of the present application, for the calculation task obtained, according to the compute type of this calculation task, can search should the computing pool of compute type, and the computational resource determined by the computing pool of this compute type can be determined.Can by calculation task described in this computational resource process.
Concrete, this calculation task can be decomposed into some subtasks, obtain subtask by the computational resource of this computing pool and to go forward side by side row operation.
In the embodiment of the present application, in a computing pool, computational resource only processes calculation task corresponding to its compute type, computational resource is obtained and fully, effectively utilizes.And the calculation task of different compute type processes in the computational resource of different computing pool, does not interfere with each other, convenient management.
In this instructions, each embodiment adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar portion mutually see.For device disclosed in embodiment, because it corresponds to the method disclosed in Example, so description is fairly simple, relevant part illustrates see method part.
Finally, also it should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.
For convenience of description, various unit is divided into describe respectively with function when describing above device.Certainly, the function of each unit can be realized in same or multiple software and/or hardware when implementing the application.
As seen through the above description of the embodiments, those skilled in the art can be well understood to the mode that the application can add required general hardware platform by software and realizes.Based on such understanding, the technical scheme of the application can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product can be stored in storage medium, as ROM/RAM, magnetic disc, CD etc., comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform the method described in some part of each embodiment of the application or embodiment.
To the above-mentioned explanation of the disclosed embodiments, professional and technical personnel in the field are realized or uses the application.To be apparent for those skilled in the art to the multiple amendment of these embodiments, General Principle as defined herein when not departing from the spirit or scope of the application, can realize in other embodiments.Therefore, the application can not be restricted to these embodiments shown in this article, but will meet the widest scope consistent with principle disclosed herein and features of novelty.
Claims (10)
1. a computational resource allocation device, is characterized in that, is applied in distributed system, and described distributed system comprises multiple computing node, and described device comprises:
Computing pool control module, for receiving and RESPONSE CALCULATION pond steering order, sets up the computing pool of the compute type of corresponding described computing pool steering order instruction, and the computational resource information of described computing node;
Node control module, for receiving and responsive node steering order, determines the computing node that described node control instruction indicates;
Resource distribution module, for receiving and resource response distribution instruction, according to described compute type, the computational resource allocation in the computing node selecting described node control instruction to indicate gives corresponding computing pool; So that when receiving calculation task, the calculation task corresponding by the compute type of computing pool described in the computational resource process of described computing pool.
2. device according to claim 1, is characterized in that, also comprises:
Resource updates module, for receiving and resource response update instruction, upgrades the computational resource in the computing pool of described resource updates instruction instruction.
3. device according to claim 1 and 2, is characterized in that, also comprises:
Resource feedback module, for computing node sending controling instruction corresponding to the computational resource distributed or upgraded, so that described computing node responds described steering order, starts or closes corresponding computational resource.
4. device according to claim 1, is characterized in that, also comprises:
Resource adjusting module, for receiving and resource response adjustment instruction, idle computing resources in first computing pool of described resource adjustment instruction instruction is distributed to the second computing pool, and described resource adjustment instruction is generate when detecting that the computational resource of described first computing pool and described second computing pool meets pre-conditioned.
5. a distributed computing devices, is characterized in that, is applied in distributed system, and described distributed system comprises multiple computing node, and described device comprises:
Task determination module, for obtaining calculation task, and determines the compute type of described calculation task;
Computing pool searches module, for searching the computing pool of the compute type of corresponding described calculation task; Described computing pool is set up in advance for different compute type, and according to compute type, selects the computational resource allocation of each computing node in described distributed system to corresponding computing pool;
Resource determination module, for being retrieved as the computational resource that described computing pool is distributed;
Task processing module, for calculation task described in the described computational resource process that obtained by described resource determination module.
6. a computational resource allocation method, is characterized in that, is applied in distributed system, and described distributed system comprises multiple computing node, and described method comprises:
Determine by RESPONSE CALCULATION pond steering order, the computing pool of the compute type of the described computing pool steering order instruction of correspondence of foundation;
Receive and responsive node steering order, determine the computing node in the described distributed system that described node control instruction indicates, and the computational resource information of described computing node;
Receive and resource response distribution instruction, according to described compute type, the computational resource allocation in the computing node selecting described node control instruction to indicate gives described computing pool; So that when receiving calculation task, the calculation task corresponding by the compute type of computing pool described in the computational resource process of described computing pool.
7. method according to claim 6, is characterized in that, described according to described compute type, and after the computational resource allocation in the computing node selecting described node control instruction to indicate gives described computing pool, described method also comprises:
Receive and resource response update instruction, the computational resource in the computing pool of described resource updates instruction instruction is upgraded.
8. the method according to claim 6 or 7, is characterized in that, after the computational resource in the described computing pool described resource updates instruction indicated upgrades, described method also comprises:
To the computing node sending controling instruction that the computational resource distributed or upgraded is corresponding, so that described computing node responds described steering order, start or close described computational resource.
9. method according to claim 6, is characterized in that, described according to described compute type, and after the computational resource allocation in the computing node selecting described node control instruction to indicate gives described computing pool, described method also comprises:
Receive and resource response adjustment instruction, idle computing resources in first computing pool of described resource adjustment instruction instruction is distributed to the second computing pool, and described resource adjustment instruction is generate when detecting that the computational resource of described second computing pool meets pre-conditioned.
10. a distributed computing method, is characterized in that, is applied in distributed system, and described distributed system comprises multiple computing node, and described method comprises:
Obtain calculation task, and determine the compute type of described calculation task;
Search the computing pool of the compute type of corresponding described calculation task; Described computing pool is set up in advance for different compute type, and according to compute type, selects the computational resource allocation of each computing node in described distributed system to corresponding computing pool;
Be retrieved as the computational resource that described computing pool is distributed;
By calculation task described in the described computational resource process obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510069461.9A CN104572308A (en) | 2015-02-10 | 2015-02-10 | Computing resource distributing method, distributed type computing method and distributed type computing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510069461.9A CN104572308A (en) | 2015-02-10 | 2015-02-10 | Computing resource distributing method, distributed type computing method and distributed type computing device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104572308A true CN104572308A (en) | 2015-04-29 |
Family
ID=53088453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510069461.9A Pending CN104572308A (en) | 2015-02-10 | 2015-02-10 | Computing resource distributing method, distributed type computing method and distributed type computing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104572308A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105786622A (en) * | 2016-03-01 | 2016-07-20 | 国网安徽省电力公司 | Node selection method for real-time cooperative computing in cloud environment |
| CN107273179A (en) * | 2016-04-07 | 2017-10-20 | 中国移动通信有限公司研究院 | The dispatching method and device of a kind of hardware resource |
| WO2017206856A1 (en) * | 2016-05-31 | 2017-12-07 | 广东欧珀移动通信有限公司 | Method for allocating processor resources and mobile terminal |
| CN107633347A (en) * | 2017-08-22 | 2018-01-26 | 阿里巴巴集团控股有限公司 | A kind of data target statistical method and device |
| CN108228354A (en) * | 2017-12-29 | 2018-06-29 | 杭州朗和科技有限公司 | Dispatching method, system, computer equipment and medium |
| CN108848037A (en) * | 2018-05-31 | 2018-11-20 | 平安医疗科技有限公司 | Service request processing method, device, computer equipment and storage medium |
| CN108965380A (en) * | 2018-05-31 | 2018-12-07 | 平安医疗科技有限公司 | Service request processing method, device, computer equipment and storage medium |
| CN109274711A (en) * | 2018-08-13 | 2019-01-25 | 中兴飞流信息科技有限公司 | PC cluster method, apparatus and computer readable storage medium |
| CN109857550A (en) * | 2019-01-07 | 2019-06-07 | 平安科技（深圳）有限公司 | Resource allocation method, device, equipment and storage medium based on machine learning |
| CN110261392A (en) * | 2019-06-19 | 2019-09-20 | 北京百度网讯科技有限公司 | Quality determining method, device, electronic equipment and system |
| CN110995614A (en) * | 2019-11-05 | 2020-04-10 | 华为技术有限公司 | Computing power resource allocation method and device |
| CN112948104A (en) * | 2019-12-11 | 2021-06-11 | 中盈优创资讯科技有限公司 | Load balancing data acquisition method and device |
| CN113535405A (en) * | 2021-07-30 | 2021-10-22 | 上海壁仞智能科技有限公司 | Cloud service system and operation method thereof |
| CN113886094A (en) * | 2021-12-07 | 2022-01-04 | 浙江大云物联科技有限公司 | Resource scheduling method and device based on edge calculation |
| CN115328661A (en) * | 2022-09-09 | 2022-11-11 | 中诚华隆计算机技术有限公司 | Computing power balance execution method and chip based on voice and image characteristics |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102427473A (en) * | 2011-11-28 | 2012-04-25 | 中国联合网络通信集团有限公司 | Method and system for constructing cross-platform resource |
| CN103164283A (en) * | 2012-05-10 | 2013-06-19 | 上海兆民云计算科技有限公司 | Method and system for dynamic scheduling management of virtualized resources in virtualized desktop system |
| CN103197976A (en) * | 2013-04-11 | 2013-07-10 | 华为技术有限公司 | Method and device for processing tasks of heterogeneous system |
| CN103365713A (en) * | 2012-04-01 | 2013-10-23 | 华为技术有限公司 | Resource dispatch and management method and device |
| CN103782270A (en) * | 2013-10-28 | 2014-05-07 | 华为技术有限公司 | Method for managing stream processing system, and related apparatus and system |
| CN103812789A (en) * | 2013-09-18 | 2014-05-21 | 广东电网公司佛山供电局 | Cloud service resource automatic allocating method and system |
| CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
-
2015
- 2015-02-10 CN CN201510069461.9A patent/CN104572308A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102427473A (en) * | 2011-11-28 | 2012-04-25 | 中国联合网络通信集团有限公司 | Method and system for constructing cross-platform resource |
| CN103365713A (en) * | 2012-04-01 | 2013-10-23 | 华为技术有限公司 | Resource dispatch and management method and device |
| CN103164283A (en) * | 2012-05-10 | 2013-06-19 | 上海兆民云计算科技有限公司 | Method and system for dynamic scheduling management of virtualized resources in virtualized desktop system |
| CN103197976A (en) * | 2013-04-11 | 2013-07-10 | 华为技术有限公司 | Method and device for processing tasks of heterogeneous system |
| CN103812789A (en) * | 2013-09-18 | 2014-05-21 | 广东电网公司佛山供电局 | Cloud service resource automatic allocating method and system |
| CN103782270A (en) * | 2013-10-28 | 2014-05-07 | 华为技术有限公司 | Method for managing stream processing system, and related apparatus and system |
| CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105786622B (en) * | 2016-03-01 | 2018-12-28 | 国网安徽省电力公司 | A kind of node selecting method calculated under cloud environment for real-time collaborative |
| CN105786622A (en) * | 2016-03-01 | 2016-07-20 | 国网安徽省电力公司 | Node selection method for real-time cooperative computing in cloud environment |
| CN107273179A (en) * | 2016-04-07 | 2017-10-20 | 中国移动通信有限公司研究院 | The dispatching method and device of a kind of hardware resource |
| US10496440B2 (en) | 2016-05-31 | 2019-12-03 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for allocating processor resources and mobile terminal |
| WO2017206856A1 (en) * | 2016-05-31 | 2017-12-07 | 广东欧珀移动通信有限公司 | Method for allocating processor resources and mobile terminal |
| US20180365068A1 (en) | 2016-05-31 | 2018-12-20 | Guangdong Oppo Mobile Telecommunications Corp., Lt | Method for Allocating Processor Resources and Terminal Device |
| US10664313B2 (en) | 2016-05-31 | 2020-05-26 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for allocating processor resources and terminal device |
| CN107633347A (en) * | 2017-08-22 | 2018-01-26 | 阿里巴巴集团控股有限公司 | A kind of data target statistical method and device |
| CN108228354A (en) * | 2017-12-29 | 2018-06-29 | 杭州朗和科技有限公司 | Dispatching method, system, computer equipment and medium |
| CN108848037A (en) * | 2018-05-31 | 2018-11-20 | 平安医疗科技有限公司 | Service request processing method, device, computer equipment and storage medium |
| CN108965380A (en) * | 2018-05-31 | 2018-12-07 | 平安医疗科技有限公司 | Service request processing method, device, computer equipment and storage medium |
| CN109274711B (en) * | 2018-08-13 | 2021-05-25 | 中兴飞流信息科技有限公司 | Cluster computing method and device and computer readable storage medium |
| CN109274711A (en) * | 2018-08-13 | 2019-01-25 | 中兴飞流信息科技有限公司 | PC cluster method, apparatus and computer readable storage medium |
| CN109857550A (en) * | 2019-01-07 | 2019-06-07 | 平安科技（深圳）有限公司 | Resource allocation method, device, equipment and storage medium based on machine learning |
| CN110261392A (en) * | 2019-06-19 | 2019-09-20 | 北京百度网讯科技有限公司 | Quality determining method, device, electronic equipment and system |
| CN110995614A (en) * | 2019-11-05 | 2020-04-10 | 华为技术有限公司 | Computing power resource allocation method and device |
| CN110995614B (en) * | 2019-11-05 | 2022-04-05 | 华为技术有限公司 | Computing power resource allocation method and device |
| CN112948104A (en) * | 2019-12-11 | 2021-06-11 | 中盈优创资讯科技有限公司 | Load balancing data acquisition method and device |
| CN112948104B (en) * | 2019-12-11 | 2024-01-05 | 中盈优创资讯科技有限公司 | Load balancing data acquisition method and device |
| CN113535405A (en) * | 2021-07-30 | 2021-10-22 | 上海壁仞智能科技有限公司 | Cloud service system and operation method thereof |
| CN113886094A (en) * | 2021-12-07 | 2022-01-04 | 浙江大云物联科技有限公司 | Resource scheduling method and device based on edge calculation |
| CN113886094B (en) * | 2021-12-07 | 2022-04-26 | 浙江大云物联科技有限公司 | Resource scheduling method and device based on edge calculation |
| CN115328661A (en) * | 2022-09-09 | 2022-11-11 | 中诚华隆计算机技术有限公司 | Computing power balance execution method and chip based on voice and image characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104572308A (en) | Computing resource distributing method, distributed type computing method and distributed type computing device | |
| CN105049268B (en) | Distributed computing resource distribution system and task processing method | |
| US9491235B2 (en) | Method and apparatus to maximize return on investment in hybrid cloud environment | |
| CN105068874B (en) | A kind of on-demand dynamic allocation method of resource of combination Docker technology | |
| US10250451B1 (en) | Intelligent analytic cloud provisioning | |
| Zhu et al. | ANGEL: Agent-based scheduling for real-time tasks in virtualized clouds | |
| CN104038540A (en) | Method and system for automatically selecting application proxy server | |
| US20130290511A1 (en) | Managing a sustainable cloud computing service | |
| US20110258634A1 (en) | Method for Monitoring Operating Experiences of Images to Improve Workload Optimization in Cloud Computing Environments | |
| WO2016148963A1 (en) | Intelligent placement within a data center | |
| CN102929783A (en) | Data storage method, device and system | |
| CN107911399B (en) | Elastic expansion method and system based on load prediction | |
| US20150006734A1 (en) | System and method for performing customized resource allocation analyses for distributed computer systems | |
| CN104348881A (en) | Method and device for user resource partitioning in cloud management platform | |
| CN110347515B (en) | Resource optimization allocation method suitable for edge computing environment | |
| CN105488134A (en) | Big data processing method and big data processing device | |
| CN104639466A (en) | Dynamic priority safeguard method for application network bandwidth based on Storm real-time flow computing framework | |
| CN103942197A (en) | Data monitoring processing method and device | |
| Delavar et al. | A synthetic heuristic algorithm for independent task scheduling in cloud systems | |
| CN108961266A (en) | A kind of region partitioning method and device | |
| CN105760227A (en) | Method and system for resource scheduling in cloud environment | |
| CN104679444A (en) | Dynamic adjustment method and device for virtualized storage resources | |
| CN110941486A (en) | Task management method and device, electronic equipment and computer readable storage medium | |
| CN113014649B (en) | Cloud Internet of things load balancing method, device and equipment based on deep learning | |
| CN105487928A (en) | Control method and device and Hadoop system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150429 |
|
| RJ01 | Rejection of invention patent application after publication |