CN108446174A - Multinuclear job scheduling method based on pre-allocation of resources and public guiding agency - Google Patents
Multinuclear job scheduling method based on pre-allocation of resources and public guiding agency Download PDFInfo
- Publication number
- CN108446174A CN108446174A CN201810182628.6A CN201810182628A CN108446174A CN 108446174 A CN108446174 A CN 108446174A CN 201810182628 A CN201810182628 A CN 201810182628A CN 108446174 A CN108446174 A CN 108446174A
- Authority
- CN
- China
- Prior art keywords
- resource
- job
- guiding
- scheduling
- information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/48—Indexing scheme relating to G06F9/48
- G06F2209/484—Precedence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5011—Pool
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5021—Priority
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is the multinuclear job scheduling method based on pre-allocation of resources and public guiding agency, essential information, resource requirement and the state conversion of different type of being standardized by the way of unified operation；Website resource allocation information is obtained, is classified to site resource information according to different levels；According to the site resource service condition that Current resource management system provides, the demand type of user job is obtained；It using website job scheduling queuing message, the submissions quantity that guides proxy job, guides the operation share directory of the size of proxy job, the authentication information of user and operation as parameter, submits to guide proxy job and occupy to the job scheduling queue of user's specified sites and act on behalf of the identical computing resource of size with guiding；According to the identification information of operation, creates scheduling process and execute user job.The computational resource allocation mode of the present invention is simple, it is short to take, and the scheduling of multinuclear operation is realized with the side of public guiding agency, greatly reduced the consumption problem of memory source.
Description
Technical field
The present invention relates to high-energy physics experiment fields, and in particular to it is a kind of based on pre-allocation of resources and public guiding agency
Multinuclear job scheduling method.
Background technology
In order to handle and analyze the reconstruction data that high energy physics laboratory generates analogue data, data processing generates, and it is
Physicist provides good analysis computing environment, and Distributed Calculation is exactly the necessarily knot of computer aided calculation technology development
Fruit.Distributed computing technology is the Heterogeneous Computing resource consolidation strange land using network, forms a virtual super meter
Calculation machine, and provide powerful computing capability for large-scale calculating operation.Wherein, it is representative have middleware, point-to-point transmission,
Web service, grid and cloud computing technology.
Multinuclear job scheduling Model Design and resource allocation techniques of the external high-energy physics field to distributed computing system
Research it is more early, the work such as the distribution of structure, job scheduling pattern and multi-core resource to testing operation have been done largely
It explores and studies, representative is exactly European Large Hadron Collider CMS (compact muon solenoid, compact
Miao Zi solenoids detector) and ATLAS (AToroidal LHC Apparatus, annular LHC devices) experiment operation processing systems
System.Relative to foreign countries, JUNO (Jiangmen Underground Neutrino Observatory, Jiangmen neutrino experiment)
Research of the job processing system in terms of multi-core parallel concurrent it is relatively fewer, most representational is exactly that Chinese Academy of Sciences's high-energy physics is ground
Study carefully JUNO parallel artificial frames.
The operation processing procedure of high-energy physics experiment mainly includes the submission of operation, the place of distribution and the operation of resource
Reason, and the functions such as processing scheduling, execution and output of result comprising operation of operation, this is also high-energy physics distribution
The core of computing system.Under situation now, as experimental data amount and event complexity constantly increase, it will cause each
The processing time of operation is elongated, greatly increases the consumption of memory source, and mould is handled so as to cause existing monokaryon operation is tested
Formula will be difficult to meet the memory requirements of each monokaryon operation.One of the object of the invention is to propose a kind of time-consuming short and simple resource
Allocation strategy；Another object of the present invention is intended to the access for optimizing user to distributed computing resource, realizes multinuclear operation
Scheduling is executed with parallelization.
Invention content
The object of the present invention is to overcome the problems of the prior art, provides one kind and is drawn with public based on pre-allocation of resources
The multinuclear job scheduling method for leading agency can avoid the memory source under Distributed Calculation monokaryon tupe insufficient existing
As, and improve the utilization rate and job processing efficiency of distributed computing resource.
To realize above-mentioned technical purpose and the technique effect, the invention is realized by the following technical scheme：
A kind of multinuclear job scheduling method based on pre-allocation of resources and public guiding agency, this approach includes the following steps：
Step 1）User job is classified
Standardized the essential information of different type operation, resource requirement and state conversion with unified mode, and passes through to analyze and use
The user job of same characteristic features is included into same job queue, forms normalized operation by the demand characteristic of family operation；
Step 2）Resource status acquires
Website resource allocation information is obtained, is classified to site resource information according to different levels, monokaryon and multinuclear are obtained
The resource status of queue show that each queue is supported according to the site resource service condition that Current resource management system provides
User job demand type, resource information and job queue demand are subjected to matching detection, record the queue of meet demand
Resource characteristic；
Step 3）Distributed resource allocation
The job processing environment of user job specified sites is detected, according to the source demand of current work waiting list, profit
With the operating status for the current guiding agency that resource management system provides, with website job scheduling queuing message, guide agency's
It is parameter to submit quantity, the size of guiding agency, the authentication information of user and the operation share directory of operation, passes through resource public affairs
Access interface altogether is submitted guiding proxy job and is occupied and acts on behalf of size phase with guiding to the job scheduling queue of user's specified sites
Same computing resource, to facilitate pulling for user job；
Step 4）Job scheduling
Detection meets the operation waiting list of resource requirement, according to testing result, based on currently available computing resource,
Random fit meets the user job of resource requirement in operation waiting list, and the operation of successful match is added to execution queue,
And the essential information needed for executing is provided for operation, monitor job run situation and resource status, the shape of real-time update operation
The available resources number of state and guiding agency；
Step 5）Job parallelismization executes
The resource-sharing pond of initialization guiding proxy job is obtained according to the identification information of the operation from resource management system
The input file of operation, the configuration information of output journal and fileinfo obtain the available resources number within Current resource, and
According to the resource type of site-local scheduling queue, computational resource allocation is given to active user's operation, create and adjust in resource pool
Degree process executes user job, and monitors the operating condition of operation in real time.
Step 6）It obtains operation and exports destination file, journal file and error message.
Further, the step 1）In normalized operation include following three parts：
A. essential information
The essential attribute of operation described, including job number, homework type, owning user, operation group, job priority and associated
Fileinfo；
B. demand information
The information of storage, memory and cpu resource needed for describing job scheduling and executing, including performing environment, specified sites, institute
Need cpu resource, memory space, memory requirements and CPU run times；
C. status information
The information of state and resource actual use of the description user job in life cycle, including the basic status of operation,
Creation time, Starting Executing Time, deadline, residing nodal information, memory actual consumption, CPU actual run times.
Further, the step 3）It is middle to use pre-allocation of resources strategy, hold guiding proxy job as resource reservation
Device is sent to the specified sites of Distributed Computing Platform, and guiding, which acts on behalf of size and is designated as the scheduling queue, can support maximum operation
The minimum value of both check figure and current maximum operation demand check figure, it is then by resource status and operation to guide the quantity of proxy job
What queuing message codetermined, calculation formula is：
PilotsToSubmit=max (0, min (totalSlots, totalTQJobs-totalWaitingPilots)),
Wherein, pilotsToSubmit is that website acts on behalf of the quantity that guiding proxy job is submitted under one cycle, totalSlots
For the site resource quantity, totalTQJobs is the operation waiting number of current queue, and totalWaitingPilots is current
The guiding for occupying resource is waited for act on behalf of quantity.
Further, the step 4）To step 5）It is to complete multinuclear operation under public guiding scheduling agent pattern
Scheduling and execution, the scheduling of operation is moved to from calculating website guides agency internal, it is assumed that existing M mixture operation waiting tune
Degree,It is the check figure of i-th of operation, i ∈ [1, M] are acted on behalf of if website is guided there are N cores, when+...+When≤N, wherein 1≤k≤m≤M, then operation...It can be guided to act on behalf of while dispatch execution, if+...+=N, then it represents that guiding proxy resources are on the contrary then will produce resource fragmentation without the free time；
Under the scheduling and executive condition of multi-user's different type operation, using the performance of operation and resource utilization as system
The evaluation index for performance of uniting, the calculation formula of operation resource utilization are represented by：
,
Wherein, website available resources number is N, and it is n that number is completed in operation,For the check figure of i-th of operation,For the operation
Run time.
Further, the basic status of the operation includes waiting, matching, operation, end and failure.
The beneficial effects of the invention are as follows:
The present invention can avoid the phenomenon of the memory source deficiency under Distributed Calculation monokaryon tupe, and improve distribution
The utilization rate and job processing efficiency of computing resource, and computational resource allocation mode is simple, it is short to take, and is acted on behalf of with public guiding
Side realize the scheduling of multinuclear operation, greatly reduced the consumption problem of memory source.
Description of the drawings
Fig. 1 is that the present invention is based on the pre-allocation of resources strategies of guiding agency；
Fig. 2 is the job scheduling pattern of the public guiding agency of the present invention；
Fig. 3 is the particular flow sheet of multinuclear job scheduling method of the present invention.
Specific implementation mode
It is below with reference to the accompanying drawings and in conjunction with the embodiments, next that the present invention will be described in detail.
A kind of multinuclear job scheduling method based on pre-allocation of resources and public guiding agency, this method includes following step
Suddenly：
Step 1）User job is classified
Standardized the essential information of different type operation, resource requirement and state conversion with unified mode, and passes through to analyze and use
The user job of same characteristic features is included into same job queue, forms normalized operation by the demand characteristic of family operation；
Step 2）Resource status acquires
Website resource allocation information is obtained, is classified to site resource information according to different levels, monokaryon and multinuclear are obtained
The resource status of queue show that each queue is supported according to the site resource service condition that Current resource management system provides
User job demand type, resource information and job queue demand are subjected to matching detection, record the queue of meet demand
Resource characteristic；
Step 3）Distributed resource allocation
The job processing environment of user job specified sites is detected, according to the source demand of current work waiting list, profit
With the operating status for the current guiding agency that resource management system provides, with website job scheduling queuing message, guide agency's
It is parameter to submit quantity, the size of guiding agency, the authentication information of user and the operation share directory of operation, passes through resource public affairs
Access interface altogether is submitted guiding proxy job and is occupied and acts on behalf of size phase with guiding to the job scheduling queue of user's specified sites
Same computing resource, to facilitate pulling for user job；
Step 4）Job scheduling
Detection meets the operation waiting list of resource requirement, according to testing result, based on currently available computing resource,
Random fit meets the user job of resource requirement in operation waiting list, and the operation of successful match is added to execution queue,
And the essential information needed for executing is provided for operation, monitor job run situation and resource status, the shape of real-time update operation
The available resources number of state and guiding agency；
Step 5）Job parallelismization executes
The resource-sharing pond of initialization guiding proxy job is obtained according to the identification information of the operation from resource management system
The input file of operation, the configuration information of output journal and fileinfo obtain the available resources number within Current resource, and
Resource type according to site-local scheduling queue（Single or multiple core）, give computational resource allocation to active user's operation, providing
Scheduling process is created in the pond of source and executes user job, and monitors the operating condition of operation in real time.
Step 6）It obtains operation and exports destination file, journal file and error message.
The step 1）In normalized operation include following three parts：
A. essential information
The essential attribute of operation described, including job number, homework type, owning user, operation group, job priority and associated
Fileinfo；
B. demand information
The information of storage, memory and cpu resource needed for describing job scheduling and executing, including performing environment, specified sites, institute
Need cpu resource, memory space, memory requirements and CPU run times；
C. status information
The information of state and resource actual use of the description user job in life cycle, including the basic status of operation,
Creation time, Starting Executing Time, deadline, residing nodal information, memory actual consumption, CPU actual run times.
The step 3）Middle to use pre-allocation of resources strategy, specific design will be as shown in Figure 1, proxy job conduct will be guided
Resource reservation container is sent to the specified sites of Distributed Computing Platform, wherein it is point to guide the size and number of proxy job
The key factor that cloth computing resource utilization rate influences, guiding, which acts on behalf of size and is designated as the scheduling queue, can support maximum operation
The minimum value of both check figure and current maximum operation demand check figure, it is then by resource status and operation to guide the quantity of proxy job
What queuing message codetermined, calculation formula is：
PilotsToSubmit=max (0, min (totalSlots, totalTQJobs-totalWaitingPilots)),
Wherein, pilotsToSubmit is that website acts on behalf of the quantity that guiding proxy job is submitted under one cycle, totalSlots
For the site resource quantity, totalTQJobs is the operation waiting number of current queue, and totalWaitingPilots is current
The guiding for occupying resource is waited for act on behalf of quantity.
The step 4）To step 5）Be under public guiding scheduling agent pattern, complete multinuclear operation scheduling with hold
The scheduling of row, operation is moved to guiding agency inside from website is calculated, and specific ideograph is as illustrated in fig. 2, it is assumed that existing M mixed
Cooperation industry waits for scheduling,It is the check figure of i-th of operation, i ∈ [1, M] are acted on behalf of if website is guided there are N cores, when+...+When≤N, wherein 1≤k≤m≤M, then operation...It can be guided agency simultaneously
Scheduling executes, if+...+=N, then it represents that guiding proxy resources are on the contrary then will produce money without the free time
Source fragment；
Under the scheduling and executive condition of multi-user's different type operation, using the performance of operation and resource utilization as system
The evaluation index for performance of uniting, the calculation formula of operation resource utilization are represented by：
,
Wherein, website available resources number is N, and it is n that number is completed in operation,For the check figure of i-th of operation,For the operation
Run time.
The basic status of the operation includes waiting, matching, operation, end and failure.
In the present embodiment, refer to the attached drawing 3, next the present invention will be described in detail：
1) initialization procedure queue, according to operation set Job={ job1 , job2 , ..., jobi , ... ,jobnIn
The resource requirement of operation and User Priority classify and job queue are added；
2) using circulation time as time interval, set of sites S is traversed, the resource status of S is detected and count；
3) according to the resource requirement of operation in job queue, pre-allocation of resources strategy using the present invention will guide proxy job
Collect P={ pt1,pt2 ,..., pti ,...,ptnIt is submitted to the working node WN in specified sites collection Sj；
4) working node WNjTo guide proxy job ptiDistribute computing resource, ptiInitiating task is acted on behalf of, and initializes remaining money
Source；
5) it is serviced by matching, operation is waited for according in available resources number Dynamic Matching job queue；
If 6) operation jobkSuccessful match, resource pool can active obtaining operation jobkParameter information, execute operation jobk, and more
New surplus resources；
7) operation jobkAfter running succeeded, surplus resources are updated, and feed back job information；If there is mistake, pt in operationiTerminate
And discharge computing resource；
If 8) ptiLife cycle is reached, then ptiTerminate and actively discharge the computing resource of working node, and guiding agency's letter
Breath feeds back to monitoring system.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (5)
1. based on pre-allocation of resources and public guiding agency multinuclear job scheduling method, which is characterized in that this method include with
Lower step：
Step 1）User job is classified
Standardized the essential information of different type operation, resource requirement and state conversion with unified mode, and passes through to analyze and use
The user job of same characteristic features is included into same job queue, forms normalized operation by the demand characteristic of family operation；
Step 2）Resource status acquires
Website resource allocation information is obtained, is classified to site resource information according to different levels, monokaryon and multinuclear are obtained
The resource status of queue show that each queue is supported according to the site resource service condition that Current resource management system provides
User job demand type, resource information and job queue demand are subjected to matching detection, record the queue of meet demand
Resource characteristic；
Step 3）Distributed resource allocation
The job processing environment of user job specified sites is detected, according to the source demand of current work waiting list, profit
With the operating status for the current guiding agency that resource management system provides, with website job scheduling queuing message, guide agency's
It is parameter to submit quantity, the size of guiding agency, the authentication information of user and the operation share directory of operation, passes through resource public affairs
Access interface altogether is submitted guiding proxy job and is occupied and acts on behalf of size phase with guiding to the job scheduling queue of user's specified sites
Same computing resource, to facilitate pulling for user job；
Step 4）Job scheduling
Detection meets the operation waiting list of resource requirement, according to testing result, based on currently available computing resource,
Random fit meets the user job of resource requirement in operation waiting list, and the operation of successful match is added to execution queue,
And the essential information needed for executing is provided for operation, monitor job run situation and resource status, the shape of real-time update operation
The available resources number of state and guiding agency；
Step 5）Job parallelismization executes
The resource-sharing pond of initialization guiding proxy job is obtained according to the identification information of the operation from resource management system
The input file of operation, the configuration information of output journal and fileinfo obtain the available resources number within Current resource, and
According to the resource type of site-local scheduling queue, computational resource allocation is given to active user's operation, create and adjust in resource pool
Degree process executes user job, and monitors the operating condition of operation in real time.
Step 6）It obtains operation and exports destination file, journal file and error message.
2. the multinuclear job scheduling method according to claim 1 based on pre-allocation of resources and public guiding agency, special
Sign is, the step 1）In normalized operation include following three parts：
A. essential information
The essential attribute of operation described, including job number, homework type, owning user, operation group, job priority and associated
Fileinfo；
B. demand information
The information of storage, memory and cpu resource needed for describing job scheduling and executing, including performing environment, specified sites, institute
Need cpu resource, memory space, memory requirements and CPU run times；
C. status information
The information of state and resource actual use of the description user job in life cycle, including the basic status of operation,
Creation time, Starting Executing Time, deadline, residing nodal information, memory actual consumption, CPU actual run times.
3. the multinuclear job scheduling method according to claim 1 based on pre-allocation of resources and public guiding agency, special
Sign is, the step 3）It is middle to use pre-allocation of resources strategy, guiding proxy job is sent to point as resource reservation container
The specified sites of cloth computing platform, guiding, which acts on behalf of size and is designated as the scheduling queue, can support maximum operation check figure and current
The minimum value of both maximum operation demand check figures, guiding the quantity of proxy job is total to by resource status and job queue information
With what is determined, calculation formula is：
PilotsToSubmit=max (0, min (totalSlots, totalTQJobs-totalWaitingPilots)),
Wherein, pilotsToSubmit is that website acts on behalf of the quantity that guiding proxy job is submitted under one cycle, totalSlots
For the site resource quantity, totalTQJobs is the operation waiting number of current queue, and totalWaitingPilots is current
The guiding for occupying resource is waited for act on behalf of quantity.
4. the multinuclear job scheduling method according to claim 1 based on pre-allocation of resources and public guiding agency, special
Sign is, the step 4）To step 5）It is to complete the scheduling and execution of multinuclear operation under public guiding scheduling agent pattern,
The scheduling of operation is moved to guiding agency inside from website is calculated, it is assumed that and existing M mixture operation waits for scheduling,
It is the check figure of i-th of operation, i ∈ [1, M] are acted on behalf of if website is guided there are N cores, when+...+≤N
When, wherein 1≤k≤m≤M, then operation...It can be guided to act on behalf of while dispatch execution, if+...+=N, then it represents that guiding proxy resources are on the contrary then will produce resource fragmentation without the free time；
Under the scheduling and executive condition of multi-user's different type operation, using the performance of operation and resource utilization as system
The evaluation index for performance of uniting, the calculation formula of operation resource utilization are represented by：
,
Wherein, website available resources number is N, and it is n that number is completed in operation,For the check figure of i-th of operation,For the operation
Run time.
5. the multinuclear job scheduling method according to claim 2 based on pre-allocation of resources and public guiding agency, special
Sign is that the basic status of the operation includes waiting, matching, operation, end and failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810182628.6A CN108446174B (en) | 2018-03-06 | 2018-03-06 | Multi-core job scheduling method based on resource pre-allocation and public boot agent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810182628.6A CN108446174B (en) | 2018-03-06 | 2018-03-06 | Multi-core job scheduling method based on resource pre-allocation and public boot agent |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108446174A true CN108446174A (en) | 2018-08-24 |
| CN108446174B CN108446174B (en) | 2022-03-11 |
Family
ID=63193712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810182628.6A Active CN108446174B (en) | 2018-03-06 | 2018-03-06 | Multi-core job scheduling method based on resource pre-allocation and public boot agent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108446174B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767199A (en) * | 2020-06-24 | 2020-10-13 | 中国工商银行股份有限公司 | Resource management method, device, equipment and system based on batch processing operation |
| CN112905562A (en) * | 2021-02-04 | 2021-06-04 | 中国工商银行股份有限公司 | Host job submitting method and device |
| CN114168314A (en) * | 2021-10-27 | 2022-03-11 | 厦门国际银行股份有限公司 | Multithreading concurrent data index batch processing method and device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8073908B2 (en) * | 2003-12-10 | 2011-12-06 | Zerotouchdigital, Inc. | Method and apparatus for utility computing in ad-hoc and configured peer-to-peer networks |
| CN102549984A (en) * | 2009-05-05 | 2012-07-04 | 思杰系统有限公司 | Systems and methods for packet steering in a multi-core architecture |
| CN103995735A (en) * | 2013-02-14 | 2014-08-20 | 韩国电子通信研究院 | Device and method for scheduling working flow |
| CN104102548A (en) * | 2014-08-04 | 2014-10-15 | 北京京东尚科信息技术有限公司 | Task resource scheduling processing method and task resource scheduling processing system |
| CN104156505A (en) * | 2014-07-22 | 2014-11-19 | 中国科学院信息工程研究所 | Hadoop cluster job scheduling method and device on basis of user behavior analysis |
| CN105739949A (en) * | 2014-12-26 | 2016-07-06 | 英特尔公司 | Techniques for cooperative execution between asymmetric processor cores |
| CN105786612A (en) * | 2014-12-23 | 2016-07-20 | 杭州华为数字技术有限公司 | Resource management method and apparatus |
| US20170139744A1 (en) * | 2015-11-18 | 2017-05-18 | Freescale Semiconductor, Inc. | Systems and methods for frame presentation and modification in a networking environment |
| CN106797382A (en) * | 2014-08-01 | 2017-05-31 | 格林伊登美国控股有限责任公司 | For the system and method for the route based on event of call center |
| CN106874084A (en) * | 2017-01-04 | 2017-06-20 | 北京百度网讯科技有限公司 | A kind of method and apparatus of distributed work flow scheduling |
| CN107450983A (en) * | 2017-07-14 | 2017-12-08 | 中国石油大学(华东) | It is a kind of based on the hierarchical network resource regulating method virtually clustered and system |
-
2018
- 2018-03-06 CN CN201810182628.6A patent/CN108446174B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8073908B2 (en) * | 2003-12-10 | 2011-12-06 | Zerotouchdigital, Inc. | Method and apparatus for utility computing in ad-hoc and configured peer-to-peer networks |
| CN102549984A (en) * | 2009-05-05 | 2012-07-04 | 思杰系统有限公司 | Systems and methods for packet steering in a multi-core architecture |
| CN103995735A (en) * | 2013-02-14 | 2014-08-20 | 韩国电子通信研究院 | Device and method for scheduling working flow |
| CN104156505A (en) * | 2014-07-22 | 2014-11-19 | 中国科学院信息工程研究所 | Hadoop cluster job scheduling method and device on basis of user behavior analysis |
| CN106797382A (en) * | 2014-08-01 | 2017-05-31 | 格林伊登美国控股有限责任公司 | For the system and method for the route based on event of call center |
| CN104102548A (en) * | 2014-08-04 | 2014-10-15 | 北京京东尚科信息技术有限公司 | Task resource scheduling processing method and task resource scheduling processing system |
| CN105786612A (en) * | 2014-12-23 | 2016-07-20 | 杭州华为数字技术有限公司 | Resource management method and apparatus |
| CN105739949A (en) * | 2014-12-26 | 2016-07-06 | 英特尔公司 | Techniques for cooperative execution between asymmetric processor cores |
| US20170139744A1 (en) * | 2015-11-18 | 2017-05-18 | Freescale Semiconductor, Inc. | Systems and methods for frame presentation and modification in a networking environment |
| CN106874084A (en) * | 2017-01-04 | 2017-06-20 | 北京百度网讯科技有限公司 | A kind of method and apparatus of distributed work flow scheduling |
| CN107450983A (en) * | 2017-07-14 | 2017-12-08 | 中国石油大学(华东) | It is a kind of based on the hierarchical network resource regulating method virtually clustered and system |
Non-Patent Citations (3)
| Title |
|---|
| FARMWANG: ""Linux内核进程调度schedule深入理解"", 《HTTPS://BLOG.CSDN.NET/FARMWANG/ARTICLE/DETAILS/70160131》 * |
| PISUT PONGCHAIRERKS: ""A self-tuning PSO for job-shop scheduling problems"", 《INTERNATIONAL JOURNAL OF OPERATIONAL RESEARCH》 * |
| 许璐璐: ""支持对称多核处理器的嵌入式实时操作系统研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767199A (en) * | 2020-06-24 | 2020-10-13 | 中国工商银行股份有限公司 | Resource management method, device, equipment and system based on batch processing operation |
| CN111767199B (en) * | 2020-06-24 | 2023-09-19 | 中国工商银行股份有限公司 | Resource management method, device, equipment and system based on batch job |
| CN112905562A (en) * | 2021-02-04 | 2021-06-04 | 中国工商银行股份有限公司 | Host job submitting method and device |
| CN114168314A (en) * | 2021-10-27 | 2022-03-11 | 厦门国际银行股份有限公司 | Multithreading concurrent data index batch processing method and device and storage medium |
| CN114168314B (en) * | 2021-10-27 | 2022-09-20 | 厦门国际银行股份有限公司 | Multithreading concurrent data index batch processing method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108446174B (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104243617B (en) | Towards the method for scheduling task and system of mixed load in a kind of isomeric group | |
| US9239734B2 (en) | Scheduling method and system, computing grid, and corresponding computer-program product | |
| Liu et al. | Resource preprocessing and optimal task scheduling in cloud computing environments | |
| CN104050042B (en) | The resource allocation methods and device of ETL operations | |
| CN104123182B (en) | Based on the MapReduce task of client/server across data center scheduling system and method | |
| CN106557369A (en) | A kind of management method and system of multithreading | |
| CN106844198A (en) | Distributed dispatching automation test platform and method | |
| DE112020007085T5 (en) | METHOD AND APPARATUS FOR WORKLOAD FEEDBACK MECHANISM ENABLING CLOSED LOOP ARCHITECTURE | |
| CN105373432B (en) | A kind of cloud computing resource scheduling method based on virtual resource status predication | |
| CN103425536B (en) | A kind of test resource management method of Based on Distributed system performance testing | |
| CN103491024B (en) | Job scheduling method and device for streaming data | |
| CN108446174A (en) | Multinuclear job scheduling method based on pre-allocation of resources and public guiding agency | |
| CN107450983A (en) | It is a kind of based on the hierarchical network resource regulating method virtually clustered and system | |
| US20130198758A1 (en) | Task distribution method and apparatus for multi-core system | |
| CN109240814A (en) | A kind of deep learning intelligent dispatching method and system based on TensorFlow | |
| CN107370796A (en) | A kind of intelligent learning system based on Hyper TF | |
| CN109614227A (en) | Task resource concocting method, device, electronic equipment and computer-readable medium | |
| CN104615945A (en) | Code cracking method and system based on multiple GPU cracking devices | |
| CN104112049A (en) | P2P (peer-to-peer) architecture based cross-data-center MapReduce task scheduling system and P2P architecture based cross-data-center MapReduce task scheduling method | |
| CN107807854A (en) | The method and rendering task processing method of a kind of Automatic dispatching Node station | |
| CN110347489A (en) | A kind of method for stream processing that the multicenter data collaborative based on Spark calculates | |
| CN108132840A (en) | Resource regulating method and device in a kind of distributed system | |
| Barone et al. | An approach to forecast queue time in adaptive scheduling: how to mediate system efficiency and users satisfaction | |
| CN105426247A (en) | HLA federate planning and scheduling method | |
| Ivanov et al. | Improving efficiency of analysis jobs in CMS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |