CN104735095A - Method and device for job scheduling of cloud computing platform - Google Patents
Method and device for job scheduling of cloud computing platform Download PDFInfo
- Publication number
- CN104735095A CN104735095A CN201310697757.6A CN201310697757A CN104735095A CN 104735095 A CN104735095 A CN 104735095A CN 201310697757 A CN201310697757 A CN 201310697757A CN 104735095 A CN104735095 A CN 104735095A
- Authority
- CN
- China
- Prior art keywords
- cloud computing
- resource
- computing platform
- job
- described operation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
Abstract
The invention discloses a method and a device for job scheduling of a cloud computing platform. The method comprises the steps of analyzing a received job to obtain characteristic parameters of the job, calculating the resource requirement of the job according to the characteristic parameters of the job, allocating resources to the job according to the resource requirement of the job and remaining resource information of the cloud computing platform, and sending a resource allocation result to the cloud computing platform to perform the job.
Description
Technical field
The present invention relates to technical field of computer information processing, particularly relate to a kind of cloud computing platform job scheduling method and device.
Background technology
Along with the continuous growth of userbase and improving constantly of lean operation management expectancy, the analytical system of mobile communication carrier inside, as the systems such as BASS, VGOP, FOS all face the impact of large data age, original system architecture can not meet the demand of business, problem below ubiquity: 1, handling property is not enough, cannot meet the handling property requirement of large data and unstructured data; 2, build maintenance cost high, original " minicomputer+high-end storage+relevant database " pattern, software and hardware buying and maintenance cost all very high; 3, system reliability is not high; 4, autgmentability is poor, cannot expand the requirement meeting data processing and increase by fast linear;
And take Hadoop as the appearance of the cloud computing technology of representative, preferably resolve these problems, therefore the analytical system of mobile communication carrier all progressively implements transition to cloud computing platform.But along with the scale of cloud computing platform constantly expands, must consider the most effectively to carry miscellaneous service under certain resource limit, therefore, the resource utilization how improving cloud computing platform becomes the key factor affecting cloud computing platform result of use, thus becomes us and need the urgent problem solved.
BASS(Business Analyse Support System) be mobile operator operation analysis system, refer to the intelligent supporting information system being supported for service goal with business decision-making support, market management analysis and a line marketing service; VGOP (Value-added Service General Operation Platform) is mobile operator value-added service comprehensive operation platform, is responsible for providing the data service support system unifying operation ability across business platform; FOS (data Flow Operation Management System) manages comprehensive operation managing system for mobile operator flow, provides the IT support system of analysis mining, accurate marketing and managerial ability.
Under existing framework, each operation system independently submit job, to cloud computing platform, and states resource requirement in advance.Cloud computing platform receives operation and puts into unified job queue, job scheduling module carries out job scheduling according to simple first in first out (fifo queue) dispatching algorithm, and carry out Resourse Distribute, First come first served according to the resource requirement that each operation proposes in advance.The resource requirement of All Jobs all needs to confirm in advance, the contention for resources between multitask and between operation dependence also need to plan in advance before submit job.
Existing framework has higher dispatching efficiency when using in single operation system, but under the complicated business environment of multisystem, exist resource use unbalanced, cannot react traffic performance, lack dynamic dispatching mechanism etc. problem, specific as follows:
(1) resource uses unbalanced
Cloud computing platform has the physical resource of 400 CPU core (CPU core).In a certain period, only have an operation ID be 2.1 BASS interface data processing operation run, the resource requirement of this operation is 100 CPU core, much smaller than the existing available resource of cloud computing platform, but cloud computing platform can only distribute 100 CPU core according to the resource requirement of this Hand up homework, more resource cannot be distributed to this operation, cause cloud computing platform resources idle, and the running time of this operation be also longer.If automatically increase the resource of distributing this operation, then the job run time significantly can be shortened.
(2) cannot dispatch according to job priority
Cloud computing platform has the physical resource of 400 CPU core.In a certain period, existing ID be 1.3 FOS system gather layer data processing operation and bring into operation, this operation takies 300 CPU core, and estimate that the Job execution time is 2 hours, priority level is low.If now have an ID be the multi-platform data statistics of 4.1 one-shot job submit to, this job priority rank be height, resource requirement is 200 CPUcore, and Estimated Time Of Operation is 10 minutes.According to the existing way to manage of cloud computing platform, ID be 4.1 operation need to wait in line ID be 1.3 operation all complete after releasing resource just can bring into operation, 2 hours need be waited for, the time requirement of high priority operation can not be met.If suspend ID be 1.3 operation excellent, preferentially first perform ID be the operation of 4.1, then only need within more than 10 minutes, high priority operation can be completed.
(3) cannot dispatch according to traffic performance and dependence
2 operation Existence dependency relationships of cloud computing platform, operation ID be 2.3 BASS system combined data processing operation depend on the result that operation ID is the slight combined data processing operation of BASS system of 2.2.Because of some reason (Hand up homework time delay, operation abnormal interruption, contention for resources etc.) cause ID in queue be 2.3 operation come before ID is the operation of 2.2 time, first existing way to manage will run the operation that ID is 2.3, cause this work data result abnormal.Under the complex environment of multiple operation system, between system and the operation Existence dependency of internal system and strict serial process order, existing framework can not process these relations automatically, more cannot ensure the process on time of critical path operation.
Summary of the invention
Cannot dispatch according to job priority to solve in prior art, cannot carry out job scheduling according to traffic performance and dependence, cloud computing platform resource uses unbalanced technical problem, and the present invention proposes a kind of cloud computing platform job scheduling method and device.
One aspect of the present invention, provides a kind of cloud computing platform job scheduling method, comprising:
The operation received is resolved, obtains the characteristic parameter of described operation;
The resource requirement of operation according to the calculation of characteristic parameters of described operation;
Be described operation Resources allocation according to the resource requirement of described operation and cloud computing platform resources left information;
Resource allocation result is sent to cloud computing platform and performs operation.
Another aspect of the present invention, provides a kind of cloud computing platform job scheduling device, comprising:
Operation parsing module, for resolving the operation received, obtains the characteristic parameter of described operation;
Resource Calculation module, for the resource requirement of operation according to the calculation of characteristic parameters of described operation;
Resource distribution module, for being described operation Resources allocation according to the resource requirement of described operation and cloud computing platform resources left information;
Job transfer module, performs operation for resource allocation result being sent to cloud computing platform.
Cloud computing platform job scheduling method of the present invention and device, by the estimation to operation resource requirement, in conjunction with cloud computing platform occupation condition, unified real-time dynamic scheduling is carried out to the operation of cloud computing platform, reach the target that resource automatic management distributes, balanced cloud computing platform load, improve the utilance of existing resource, ensure the order of Business Processing, realize Resourse Distribute automatically and reasonably.
Accompanying drawing explanation
Fig. 1 is the flow chart of cloud computing platform job scheduling method embodiment of the present invention;
Fig. 2 is the schematic diagram of the property list of operation of the present invention and system;
Fig. 3 is the structure chart of cloud computing platform job scheduling device embodiment of the present invention;
Fig. 4 is the flow chart of another embodiment of cloud computing platform job scheduling method of the present invention;
Fig. 5 is the flow chart of a cloud computing platform job scheduling method of the present invention embodiment again;
Fig. 6 is the job queue situation schematic diagram that resource distribution module of the present invention obtains from job transfer module;
Fig. 7 is the property list schematic diagram of another operation of the present invention and system.
Embodiment
The present invention by based on the stock assessment algorithm of traffic performance and dynamic dispatching mechanism, solves the problem of the resource management of cloud computing platform under the complicated business environment of multisystem.Below in conjunction with accompanying drawing, the present invention is described in detail.
As shown in Figure 1, the invention provides a kind of cloud computing platform job scheduling method embodiment, comprise the following steps:
Step 101, resolves the operation received, and obtains the characteristic parameter of operation;
Step 102, according to the resource requirement of the calculation of characteristic parameters operation of operation;
Step 103 is operation Resources allocation according to the resource requirement of operation and cloud computing platform resources left information;
Step 104, is sent to cloud computing platform and performs operation by resource allocation result.
Said method embodiment, by the estimation to operation resource requirement, in conjunction with cloud computing platform occupation condition, unified real-time dynamic scheduling is carried out to the operation of cloud computing platform, reach the target that resource automatic management distributes, balanced cloud computing platform load, improve the utilance of existing resource, ensure the order of Business Processing, realize Resourse Distribute automatically and reasonably.
In the present embodiment, the resource requirement of operation comprises capability requirement and/or storage demand.Above-mentioned steps 102 specifically comprises:
(1) according to the capability requirement of following formulae discovery operation:
Wherein, x
1for the capability requirement of operation, can represent by CPU core number;
N is the quantity of type of service corresponding to operation, and type of service corresponding to operation comprises: the interface data process of each operation system, slightly gather, aggregation process, application displaying, temporary statistics etc.; When calculating capability requirement, different types of service being calculated respectively, then gathering;
A is the data analysis flow process number of operation flow corresponding to operation;
B1 is Mean mapping (Map) number of single data stream;
C1 is the on average consuming time of Map task, and unit is second;
D1 is the Map task number of concurrent of single cpu kernel;
B2 is average stipulations (Reduce) number of single data stream;
C2 is the on average consuming time of Reduce task, and unit is second;
D2 is the Reduce task number of concurrent of single cpu kernel;
E is job run time requirement, and unit is second;
F is cloud computing platform ability redundancy coefficient, and this redundancy coefficient adopts empirical value, generally gets 10%.
(2) according to the storage demand of following formulae discovery operation:
Wherein, x
2for the storage demand of operation, unit is Gbit;
N ' is the quantity of data type corresponding to operation, and data type corresponding to operation comprises: interface data, slight combined data, combined data, application display data, temporary statistics data etc.; When calculating storage demand, different data types being calculated respectively, then gathering;
A ' is monocycle size of data, and unit is Gbit;
B ' is packing factor, adopts empirical value, generally gets 2;
C ' is data storage cycles, and unit is sky;
D ' is compression ratio, adopts empirical value, according to the concrete compress mode value selected;
E ', for storing utilization rate, stores utilization rate and adopts empirical value, generally get 10%;
The storage capacity that F ' is single device.
Cloud computing platform resource mainly refers to CPU, Memory, Disk and I/O of X86 server.Be distributed cloud computing platform based on Hadoop technology due to what adopt, Hadoop is a software frame that can carry out distributed treatment to mass data.Under normal circumstances, can not there is independent bottleneck in Memory and I/O, and the calculating of therefore resource requirement is mainly for computing capability and memory space.Based in the distributed cloud computing platform of Hadoop, its calculation task is that the MapReduce programming model provided according to Hadoop runs, the resource that operation consumes is decided by the scheduling of MapReduce on cloud computing platform, therefore by real-time job scheduling, optimum is assigned with MapReduce number of tasks, also just achieves the optimization of resource allocation management on whole cloud computing platform.
Preferably, step 103 comprises: be operation Resources allocation according to the capability requirement of operation and/or storage demand and cloud computing platform resources left information; Generate resource allocation result and comprise new job queue, business performs queue and comprises following information: the execution of the priority of Job execution statement/script, operation, operation relies on condition, the capability requirement of time requirement and operation and/or storage demand.
Preferably, step 103 also comprises: obtain characteristic information and active job queuing message that system is initiated in operation; The characteristic information that industry initiates system comprises: the job list, resource occupation, priority, scheduling frequency and the condition of dependence;
Further according to operation initiate system characteristic information and run in job queue information be operation Resources allocation.
In the present embodiment, the property list of an operation and system can be safeguarded, as shown in Figure 2, the key factors such as the job list corresponding to each operation system and resource occupation, priority, scheduling frequency and dependence are comprised, as the foundation of carrying out resource management based on traffic performance.In addition, the current job queue information run is obtained from cloud computing platform.The characteristic information of the operation system of operation will be initiated, the current job queue information run, and the capability requirement of operation that obtains of step and/or storage demand before and cloud computing platform resources left informix are to together, determine how to be as Resources allocation.Like this, owing to take into account between operation system and the priority of operation system each business inner and dependence, more reasonably the resource of cloud computing platform is distributed, improve the order of resource utilization and operation process further.
Preferably, above-mentioned steps 104 comprises:
Current work queue is upgraded according to new job queue;
Current work queue after renewal is submitted to cloud computing platform perform.
Also may there is due to current the job queue running and neutralize and wait in line, after carrying out Resourse Distribute to new operation, need to upgrade current job queue, the job queue after upgrading is brought up to cloud computing platform.
On the other hand, as shown in Figure 3, the present invention also provides a kind of cloud computing platform job scheduling device embodiment, comprising:
Operation parsing module 31, for resolving the operation received, obtains the characteristic parameter of operation;
Resource Calculation module 32, for the resource requirement of the calculation of characteristic parameters operation according to operation;
Resource distribution module 33, for being operation Resources allocation according to the resource requirement of operation and cloud computing platform resources left information;
Job transfer module 34, performs operation for resource allocation result being sent to cloud computing platform.
Preferably, the resource requirement of operation comprises capability requirement and/or storage demand, Resource Calculation module 32, the capability requirement for according to following formulae discovery operation:
Wherein, x
1for the capability requirement of operation; N is the quantity of type of service corresponding to operation; A is the data analysis flow process number of operation flow corresponding to operation; B1 is the average Map number of single data stream; C1 is the on average consuming time of Map task; D1 is the Map task number of concurrent of single CPU core; B2 is the average Reduce number of single data stream; C2 is the on average consuming time of Reduce task; D2 is the Reduce task number of concurrent of single CPU core; E is job run time requirement; F is cloud computing platform ability redundancy coefficient;
Storage demand according to following formulae discovery operation:
Wherein, x
2for the storage demand of operation; N ' is the quantity of data type corresponding to operation; A ' is monocycle size of data; B ' is packing factor; C ' is data storage cycles; D ' is compression ratio; E ' is for storing utilization rate; The storage capacity that F ' is single device.
Preferably, resource distribution module 33 comprises:
Distribution sub module 331, for being operation Resources allocation according to the capability requirement of operation and/or storage demand and cloud computing platform resources left information;
Generate submodule 332, comprise new job queue for generating resource allocation result, business performs queue and comprises following information: the execution of the priority of Job execution statement/script, operation, operation relies on condition, the capability requirement of time requirement and operation and/or storage demand.
Preferably, resource distribution module also comprises:
Obtaining submodule 333, initiating characteristic information and the active job queuing message of system for obtaining operation; The characteristic information that industry initiates system comprises: the job list, resource occupation, priority, scheduling frequency and the condition of dependence;
Distribution sub module 331, for further according to operation initiate system characteristic information and run in job queue information be operation Resources allocation.
Preferably, job transfer module 34, for upgrading current work queue according to new job queue; Current work queue after renewal is submitted to cloud computing platform perform.
For two typical flow processs, said method embodiment is described in detail below.
One, the operation that BASS system is initiated is dispatched
As shown in Figure 4, cloud computing platform job scheduling method embodiment flow process is as follows:
Step 401, BASS system to operation parsing module submit to an ID be 2.1 BASS interface data processing operation;
Step 402, after operation parsing module completes this operation parsing, by this job transfer to Resource Calculation module;
Step 403, Resource Calculation module calculates this operation resource requirement for being greater than 100 CPU core;
Step 404, resource distribution module obtains job queue from job transfer module, and existing job queue is empty, the operation not performing and queuing up;
Step 405, resource distribution module takies situation from cloud computing platform Gains resources, and existing 400 the CPU core of cloud computing platform are idle condition;
Step 406, ID is that the resource requirement of the operation of 2.1 is adjusted to 400 CPUcore by resource distribution module, and by this information transmission to job transfer module;
Step 407, job transfer module upgrades job queue, is that the Hand up homework of 2.1 runs to cloud computing platform by ID.
In the present embodiment, by the estimation to operation resource requirement, be that Resourse Distribute is carried out in operation in conjunction with cloud computing platform occupation condition, more reasonably the resource of cloud computing platform distributed, improve resource utilization further.
Two, the operation that other operation systems are initiated is dispatched
As shown in Figure 5, cloud computing platform job scheduling method embodiment flow process is as follows:
Step 501, other operation systems submit to an ID to be the one-shot job of the multi-platform data statistics of 4.1 to operation parsing module, and this job priority is high;
Step 502, after operation parsing module fulfils assignment and resolves, by this job transfer to Resource Calculation module;
Step 503, Resource Calculation module rule of thumb formula assesses resource requirement for being greater than 300 CPUcore;
Step 504, resource distribution module obtains job queue from job transfer module, and queue situation is as shown in Figure 6;
Step 505, resource distribution module takies situation from cloud computing platform Gains resources, and existing 400 the CPU core of cloud computing platform are using state, without remaining available resource;
Step 506, resource distribution module analyzes existing job queue and the new operation submitted to, the association attributes of each operation is inquired about in the property list of operation as shown in Figure 7 and system, resource distribution module analyzes cloud computing platform resources left situation, job queue situation, job priority and dependence, the operation of priority treatment high priority, and according to the dependence of high priority operation, jobs scheduling is adjusted: suspending ID is the operation of 2.5, according to operation ID 2.1,1.1, the order of 4.1 performs, and the job queue after adjustment is transferred to Job execution module;
Step 507, job transfer module upgrades job queue, and suspending ID is the operation of 2.5, is that the Hand up homework of 2.1 runs to cloud computing platform after releasing resource by ID.
In the present embodiment, by the estimation to operation resource requirement, in conjunction with between cloud computing platform occupation condition, operation system and the priority of operation system each business inner and dependence be that Resourse Distribute is carried out in operation, more reasonably the resource of cloud computing platform is distributed, balanced cloud computing platform load, improve the utilance of existing resource, ensure the order of Business Processing.
The above embodiment of the present invention, by the estimation to operation resource requirement, in conjunction with cloud computing platform occupation condition, carry out unified real-time dynamic scheduling to the operation of cloud computing platform, major advantage is as follows:
1, the characteristic of every business that cloud computing platform carries is associated with the resource management of cloud computing platform, with the priority of each business of internal system and dependence between embodiment system, Resourse Distribute automatically and reasonably can be realized;
2, can dispatch dynamically operation according to the real time resources service condition of cloud computing platform, balanced cloud computing platform load, realizes resource management and becomes more meticulous, and promotes the utilance of resource;
3, avoid occurring contention for resources.When resource is nervous, carries out dynamic dispatching by assessing the priority of operation, time requirement, dependence and resource consumption, making Business Processing rational and orderly;
It is noted that above embodiment is only in order to illustrate the present invention and unrestricted, the present invention is also not limited in above-mentioned citing, and all do not depart from technical scheme and the improvement thereof of the spirit and scope of the present invention, and it all should be encompassed in right of the present invention.
Claims (10)
1. a cloud computing platform job scheduling method, is characterized in that, comprising:
The operation received is resolved, obtains the characteristic parameter of described operation;
The resource requirement of operation according to the calculation of characteristic parameters of described operation;
Be described operation Resources allocation according to the resource requirement of described operation and cloud computing platform resources left information;
Resource allocation result is sent to cloud computing platform and performs operation.
2. method according to claim 1, is characterized in that, the resource requirement of described operation comprises capability requirement and/or storage demand; According to the calculation of characteristic parameters of described operation, the resource requirement of operation comprises:
The capability requirement of operation according to following formulae discovery:
Wherein, x
1for the capability requirement of described operation; N is the quantity of type of service corresponding to operation; A is the data analysis flow process number of operation flow corresponding to described operation; B1 is the Mean mapping Map number of single data stream; C1 is the on average consuming time of Map task; D1 is the Map task number of concurrent of single cpu kernel; B2 is average stipulations (Reduce) number of single data stream; C2 is the on average consuming time of Reduce task; D2 is the Reduce task number of concurrent of single cpu kernel; E is job run time requirement; F is cloud computing platform ability redundancy coefficient;
The storage demand of operation according to following formulae discovery:
Wherein, x
2for the storage demand of described operation; N ' is the quantity of type of service corresponding to operation; A ' is monocycle size of data; B ' is packing factor; C ' is data storage cycles; D ' is compression ratio; E ' is for storing utilization rate; The storage capacity that F ' is single device.
3. method according to claim 2, is characterized in that, is that described operation Resources allocation comprises according to the resource requirement of described operation and cloud computing platform resources left information:
Be described operation Resources allocation according to the capability requirement of described operation and/or storage demand and cloud computing platform resources left information;
Generate resource allocation result and comprise new job queue, described business performs queue and comprises following information: the execution of the priority of Job execution statement/script, described operation, described operation relies on condition, the capability requirement of time requirement and described operation and/or storage demand.
4. method according to claim 3, is characterized in that, described method also comprises:
Obtain characteristic information and active job queuing message that system is initiated in operation; The characteristic information that described industry initiates system comprises: the job list, resource occupation, priority, scheduling frequency and the condition of dependence;
Further according to described operation initiate system characteristic information and in running job queue information be described operation Resources allocation.
5. method according to claim 3, is characterized in that, resource allocation result is sent to cloud computing platform and carries out Job execution and comprise:
Current work queue is upgraded according to described new job queue;
Current work queue after renewal is submitted to cloud computing platform perform.
6. a cloud computing platform job scheduling device, is characterized in that, comprising:
Operation parsing module, for resolving the operation received, obtains the characteristic parameter of described operation;
Resource Calculation module, for the resource requirement of operation according to the calculation of characteristic parameters of described operation;
Resource distribution module, for being described operation Resources allocation according to the resource requirement of described operation and cloud computing platform resources left information;
Job transfer module, performs operation for resource allocation result being sent to cloud computing platform.
7. device according to claim 6, is characterized in that, the resource requirement of described operation comprises capability requirement and/or storage demand; Described Resource Calculation module, the capability requirement for operation according to following formulae discovery:
Wherein, x
1for the capability requirement of described operation; N is the quantity of type of service corresponding to operation; A is the data analysis flow process number of operation flow corresponding to described operation; B1 is the Mean mapping Map number of single data stream; C1 is the on average consuming time of Map task; D1 is the Map task number of concurrent of single cpu kernel; B2 is average stipulations (Reduce) number of single data stream; C2 is the on average consuming time of Reduce task; D2 is the Reduce task number of concurrent of single cpu kernel; E is job run time requirement; F is cloud computing platform ability redundancy coefficient;
The storage demand of operation according to following formulae discovery:
Wherein, x
2for the storage demand of described operation; N ' is the quantity of type of service corresponding to operation; A ' is monocycle size of data; B ' is packing factor; C ' is data storage cycles; D ' is compression ratio; E ' is for storing utilization rate; The storage capacity that F ' is single device.
8. device according to claim 7, is characterized in that, described resource distribution module comprises:
Distribution sub module, for being described operation Resources allocation according to the capability requirement of described operation and/or storage demand and cloud computing platform resources left information;
Generate submodule, comprise new job queue for generating resource allocation result, described business performs queue and comprises following information: the execution of the priority of Job execution statement/script, described operation, described operation relies on condition, the capability requirement of time requirement and described operation and/or storage demand.
9. device according to claim 8, is characterized in that, described resource distribution module also comprises:
Obtaining submodule, initiating characteristic information and the active job queuing message of system for obtaining operation; The characteristic information that described industry initiates system comprises: the job list, resource occupation, priority, scheduling frequency and the condition of dependence;
Described distribution sub module, for further according to described operation initiate system characteristic information and in running job queue information be described operation Resources allocation.
10. device according to claim 7, is characterized in that, described job transfer module, for upgrading current work queue according to described new job queue; Current work queue after renewal is submitted to cloud computing platform perform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310697757.6A CN104735095B (en) | 2013-12-18 | 2013-12-18 | A kind of cloud computing platform job scheduling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310697757.6A CN104735095B (en) | 2013-12-18 | 2013-12-18 | A kind of cloud computing platform job scheduling method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104735095A true CN104735095A (en) | 2015-06-24 |
| CN104735095B CN104735095B (en) | 2018-02-23 |
Family
ID=53458529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310697757.6A Active CN104735095B (en) | 2013-12-18 | 2013-12-18 | A kind of cloud computing platform job scheduling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104735095B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159782A (en) * | 2015-08-28 | 2015-12-16 | 北京百度网讯科技有限公司 | Cloud host based method and apparatus for allocating resources to orders |
| CN105516242A (en) * | 2015-11-23 | 2016-04-20 | 华为技术有限公司 | Storage resource distribution method and storage resource distribution system |
| CN105607955A (en) * | 2015-12-23 | 2016-05-25 | 浪潮集团有限公司 | Calculation task distribution method and apparatus |
| CN105824705A (en) * | 2016-04-01 | 2016-08-03 | 广州唯品会网络技术有限公司 | Task distribution method and electronic equipment |
| CN106484520A (en) * | 2016-10-17 | 2017-03-08 | 北京集奥聚合科技有限公司 | A kind of intelligent dispatching method based on data blood relationship and system |
| CN106657203A (en) * | 2015-11-02 | 2017-05-10 | 广达电脑股份有限公司 | Dynamic resource management system and method thereof |
| CN106776025A (en) * | 2016-12-16 | 2017-05-31 | 郑州云海信息技术有限公司 | A kind of computer cluster job scheduling method and its device |
| CN107038072A (en) * | 2016-02-03 | 2017-08-11 | 博雅网络游戏开发（深圳）有限公司 | Method for scheduling task and device based on Hadoop system |
| CN107454137A (en) * | 2017-06-16 | 2017-12-08 | 广州天宁信息技术有限公司 | A kind of method, apparatus and equipment in line service on-demand service |
| CN107885589A (en) * | 2017-11-22 | 2018-04-06 | 链家网（北京）科技有限公司 | A kind of job scheduling method and device |
| CN108960641A (en) * | 2018-07-10 | 2018-12-07 | 康成投资（中国）有限公司 | Electric business platform operations dispatching method and system |
| CN109710414A (en) * | 2018-12-29 | 2019-05-03 | 北京三快在线科技有限公司 | A kind of job scheduling method, device, equipment and storage medium |
| CN110012507A (en) * | 2019-04-02 | 2019-07-12 | 华南理工大学 | A kind of car networking resource allocation methods that user experience is preferential and system |
| CN110209645A (en) * | 2017-12-30 | 2019-09-06 | 中国移动通信集团四川有限公司 | Task processing method, device, electronic equipment and storage medium |
| CN116302447A (en) * | 2023-04-27 | 2023-06-23 | 云动时代科技股份有限公司 | Cloud platform-based method for managing software and software management system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110145415A1 (en) * | 2009-12-14 | 2011-06-16 | Hitachi, Ltd. | Information processor and resource scheduling method |
| CN102780759A (en) * | 2012-06-13 | 2012-11-14 | 合肥工业大学 | Cloud computing resource scheduling method based on scheduling object space |
| CN102902344A (en) * | 2011-12-23 | 2013-01-30 | 同济大学 | Method for optimizing energy consumption of cloud computing system based on random tasks |
-
2013
- 2013-12-18 CN CN201310697757.6A patent/CN104735095B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110145415A1 (en) * | 2009-12-14 | 2011-06-16 | Hitachi, Ltd. | Information processor and resource scheduling method |
| CN102902344A (en) * | 2011-12-23 | 2013-01-30 | 同济大学 | Method for optimizing energy consumption of cloud computing system based on random tasks |
| CN102780759A (en) * | 2012-06-13 | 2012-11-14 | 合肥工业大学 | Cloud computing resource scheduling method based on scheduling object space |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159782A (en) * | 2015-08-28 | 2015-12-16 | 北京百度网讯科技有限公司 | Cloud host based method and apparatus for allocating resources to orders |
| CN105159782B (en) * | 2015-08-28 | 2018-11-02 | 北京百度网讯科技有限公司 | Based on the method and apparatus that cloud host is Order splitting resource |
| CN106657203A (en) * | 2015-11-02 | 2017-05-10 | 广达电脑股份有限公司 | Dynamic resource management system and method thereof |
| CN106657203B (en) * | 2015-11-02 | 2019-12-06 | 广达电脑股份有限公司 | Dynamic resource management system and method thereof |
| CN105516242A (en) * | 2015-11-23 | 2016-04-20 | 华为技术有限公司 | Storage resource distribution method and storage resource distribution system |
| WO2017088717A1 (en) * | 2015-11-23 | 2017-06-01 | 华为技术有限公司 | Storage resource allocation method and system |
| CN105607955A (en) * | 2015-12-23 | 2016-05-25 | 浪潮集团有限公司 | Calculation task distribution method and apparatus |
| CN107038072A (en) * | 2016-02-03 | 2017-08-11 | 博雅网络游戏开发（深圳）有限公司 | Method for scheduling task and device based on Hadoop system |
| CN107038072B (en) * | 2016-02-03 | 2019-10-25 | 博雅网络游戏开发（深圳）有限公司 | Method for scheduling task and device based on Hadoop system |
| CN105824705B (en) * | 2016-04-01 | 2019-10-11 | 广州品唯软件有限公司 | A kind of method for allocating tasks and electronic equipment |
| CN105824705A (en) * | 2016-04-01 | 2016-08-03 | 广州唯品会网络技术有限公司 | Task distribution method and electronic equipment |
| CN106484520A (en) * | 2016-10-17 | 2017-03-08 | 北京集奥聚合科技有限公司 | A kind of intelligent dispatching method based on data blood relationship and system |
| CN106776025A (en) * | 2016-12-16 | 2017-05-31 | 郑州云海信息技术有限公司 | A kind of computer cluster job scheduling method and its device |
| CN107454137A (en) * | 2017-06-16 | 2017-12-08 | 广州天宁信息技术有限公司 | A kind of method, apparatus and equipment in line service on-demand service |
| CN107454137B (en) * | 2017-06-16 | 2020-09-15 | 广州天宁信息技术有限公司 | Method, device and equipment for on-line business on-demand service |
| CN107885589A (en) * | 2017-11-22 | 2018-04-06 | 链家网（北京）科技有限公司 | A kind of job scheduling method and device |
| CN110209645A (en) * | 2017-12-30 | 2019-09-06 | 中国移动通信集团四川有限公司 | Task processing method, device, electronic equipment and storage medium |
| CN108960641A (en) * | 2018-07-10 | 2018-12-07 | 康成投资（中国）有限公司 | Electric business platform operations dispatching method and system |
| CN108960641B (en) * | 2018-07-10 | 2021-07-02 | 康成投资（中国）有限公司 | E-commerce platform operation scheduling method and system |
| CN109710414A (en) * | 2018-12-29 | 2019-05-03 | 北京三快在线科技有限公司 | A kind of job scheduling method, device, equipment and storage medium |
| CN109710414B (en) * | 2018-12-29 | 2021-03-26 | 北京三快在线科技有限公司 | Job scheduling method, device, equipment and storage medium |
| CN110012507A (en) * | 2019-04-02 | 2019-07-12 | 华南理工大学 | A kind of car networking resource allocation methods that user experience is preferential and system |
| CN116302447A (en) * | 2023-04-27 | 2023-06-23 | 云动时代科技股份有限公司 | Cloud platform-based method for managing software and software management system |
| CN116302447B (en) * | 2023-04-27 | 2023-08-04 | 云动时代科技股份有限公司 | Cloud platform-based method for managing software and software management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104735095B (en) | 2018-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104735095A (en) | Method and device for job scheduling of cloud computing platform | |
| US8380557B2 (en) | Multi-tenant database management for service level agreement (SLA) profit maximization | |
| CN103092698B (en) | Cloud computing application automatic deployment system and method | |
| CN109034396B (en) | Method and apparatus for processing deep learning jobs in a distributed cluster | |
| CN109408205B (en) | Task scheduling method and device based on hadoop cluster | |
| CN101652750B (en) | Data processing device, distributed processing system and data processing method | |
| CN104092756A (en) | Cloud storage system resource dynamic allocation method based on DHT mechanism | |
| US20120215920A1 (en) | Optimized resource management for map/reduce computing | |
| CN102917077A (en) | Resource allocation method in cloud computing system | |
| CN104468407A (en) | Method and device for performing service platform resource elastic allocation | |
| CN103023980B (en) | A kind of method and system of cloud platform processes user service request | |
| CN103237037A (en) | Media format conversion method and system based on cloud computing architecture | |
| CN103297499A (en) | Scheduling method and system based on cloud platform | |
| CN105471985A (en) | Load balance method, cloud platform computing method and cloud platform | |
| CN105491150A (en) | Load balance processing method based on time sequence and system | |
| CN111427678A (en) | Virtualized resource scheduling system and method in automobile diagnosis cloud platform | |
| Al-Sinayyid et al. | Job scheduler for streaming applications in heterogeneous distributed processing systems | |
| CN104052677A (en) | Soft load balancing method and apparatus of single data source | |
| CN103186536A (en) | Method and system for scheduling data shearing devices | |
| CN106856441A (en) | VIM systems of selection and device in NFVO | |
| CN114138488A (en) | Cloud-native implementation method and system based on elastic high-performance computing | |
| CN116402318B (en) | Multi-stage computing power resource distribution method and device for power distribution network and network architecture | |
| CN107454137B (en) | Method, device and equipment for on-line business on-demand service | |
| US20220114188A1 (en) | Efficient Database Loading | |
| CN114237858A (en) | Task scheduling method and system based on multi-cluster network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |