CN101694712B - The bill generation system of cluster job scheduling and method - Google Patents

The bill generation system of cluster job scheduling and method Download PDF

Info

Publication number
CN101694712B
CN101694712B CN200910091836.6A CN200910091836A CN101694712B CN 101694712 B CN101694712 B CN 101694712B CN 200910091836 A CN200910091836 A CN 200910091836A CN 101694712 B CN101694712 B CN 101694712B
Authority
CN
China
Prior art keywords
data
supvr
module
request
operating index
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.)
Active
Application number
CN200910091836.6A
Other languages
Chinese (zh)
Other versions
CN101694712A (en
Inventor
聂华
邵宗有
历军
郭庆
鲁四美
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dawning Information Industry Beijing Co Ltd
Dawning Information Industry Co Ltd
Original Assignee
Dawning Information Industry Beijing Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dawning Information Industry Beijing Co Ltd filed Critical Dawning Information Industry Beijing Co Ltd
Priority to CN200910091836.6A priority Critical patent/CN101694712B/en
Publication of CN101694712A publication Critical patent/CN101694712A/en
Application granted granted Critical
Publication of CN101694712B publication Critical patent/CN101694712B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Debugging And Monitoring (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention provides a kind of bill generation system and method for cluster job scheduling, wherein, the method comprises the following steps: job scheduling monitoring module monitors the operating index data of each operation and record, record object properties information corresponding to operation simultaneously, then the information of record is sent to data processing module.Data processing module receives the information from job scheduling monitoring module, is stored to database after processing to the operating index data of each operation.Interactive module receiving management person ask and send it to accounting engine.Accounting engine receiving management person asks, and reads the data meeting request, and generates bill according to request to after Data Analysis Services, then bill is fed back to interactive module and present to supvr according to supvr's request from database.The present invention is supplied to supvr with reasonable manner, for charge provides more reliable believable foundation by analyzing job run achievement data, adding up, after the process such as normalization.

Description

The bill generation system of cluster job scheduling and method
Technical field
The present invention relates to computer technology high-performance field, particularly a kind of bill generation system and method.
Background technology
In High-Performance Computing Cluster job scheduling system, job scheduling system can according to the job request of user, automatic Distribution Calculation node is for operation, and the supvr of cluster needs to grasp the situation that user job uses machine resources accurately, and collects cost of use to user accordingly.In the use procedure of cluster, can produce a large amount of data relevant to cluster job scheduling, supvr needs to carry out statistical study to these data, draws the data result for book keeping operation charge.
Existing bill generation system is only simply added achievement data, resource comparison cannot be used to provide reliable Data support for user.Further, existing bill generation system only only has data, and does not provide data display mode intuitively.In addition, supvr can only pass through browser browsing data, and can not download.Therefore, a kind of system and method is needed to solve the problem.
Summary of the invention
For the one or more problems existed in correlation technique, the object of the present invention is to provide a kind of bill generation system and method for cluster job scheduling, with in solving the problem one of at least.
For achieving the above object, one aspect of the present invention provides a kind of bill generation system of cluster job scheduling, comprises job scheduling monitoring module, data processing module, database, interactive module and accounting engine.Wherein, job scheduling monitoring module is for monitoring the operating index data of each operation, and record the operating index data of each operation and object properties information corresponding to operation, and the operating index data of each operation and object properties information corresponding to operation are sent to data processing module.Data processing module, for receiving from the operating index data of each operation of job scheduling monitoring module and object properties information corresponding to operation, processes the operating index data of each operation, and the data after process is stored to database.Database is for storing the data of data processing module.Interactive module is used for receiving management person request and supvr's request is sent to accounting engine, and receives the bill that returns of accounting engine and present to supvr.Accounting engine is asked for the supvr received from interactive module, and from database, read according to supvr's request the data meeting supvr's request, and generate bill according to supvr's request to after the Data Analysis Services meeting supvr's request, and bill is fed back to interactive module.
Preferably, job scheduling monitoring module comprises monitoring module, logging modle and sending module.Wherein, monitoring module is for monitoring the operating index data of each operation.Logging modle is for object properties information corresponding to the operating index data and operation that record each operation.Sending module is used for the operating index data of each operation and object properties information corresponding to operation to be sent to data processing module.
Preferably, data processing module comprises data reception module and processing module.Wherein, data reception module is for receiving from the operating index data of each operation of job scheduling monitoring module and object properties information corresponding to operation.Processing module is used for processing in units of operation the operating index data of each operation, and the operating index data of each operation are classified by the object properties that operation is corresponding, and process in units of object properties, and the data after process are stored to database.
Preferably, interactive module comprises and represents interface and request processing module.Wherein, represent that interface is used for receiving management person request, and the bill returned by accounting engine presents to supvr.Request processing module is used for supvr's request to be sent to accounting engine.
Preferably, accounting engine comprises receiver module, data read module, bill generation module and result feedback module.Wherein, receiver module is asked for the supvr received from interactive module.Data read module is used for from database, reading according to supvr's request the data meeting supvr's request.Bill generation module be used for according to supvr request to meet supvr request Data Analysis Services after generate bill.The bill that result feedback module is used for bill generation module generates feeds back to interactive module.
Preferably, the form of bill comprise following one of at least: PDF, XLS and HTML.Object properties information corresponding to operation comprise following one of at least: the affiliated cluster of submission user corresponding to described operation, described operation.
The present invention also proposes a kind of bill generation method of cluster job scheduling on the other hand, comprise the following steps: job scheduling monitoring module monitors the operating index data of each operation, and record the operating index data of each operation and object properties information corresponding to operation, then the operating index data of each operation and object properties information corresponding to operation are sent to data processing module.Data processing module receives from the operating index data of each operation of job scheduling monitoring module and object properties information corresponding to operation, processes, and the data after process are stored to database to the operating index data of each operation.Supvr's request is also sent to accounting engine by interactive module receiving management person request.The supvr that accounting engine receives from interactive module asks, and from database, read according to supvr's request the normalization data meeting supvr's request, then generate bill according to supvr's request to after the Data Analysis Services meeting supvr's request, and bill is fed back to interactive module present to supvr.
Preferably, the operating index data of each operation are processed, comprising: the operating index data of each operation are processed in units of operation; And the operating index data of each operation are classified by the object properties that operation is corresponding, and process in units of object properties.
By the present invention's at least one technical scheme above-mentioned, after being processed by analyze job run achievement data, add up and normalization etc., be supplied to supvr with reasonable manner, for charge provides more reliable believable foundation.
The aspect that the present invention adds and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the structural drawing of the bill generation system according to cluster job scheduling of the present invention; And
Fig. 2 is the process flow diagram of the bill generation method according to cluster job scheduling of the present invention.
Embodiment
Consider the one or more problems existed in correlation technique, the invention provides a kind of bill generation system and method for cluster job scheduling.Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings.Should be understood that below by the embodiment be described with reference to the drawings be exemplary, only for explaining the present invention, and can not limitation of the present invention be interpreted as.
Fig. 1 is the structural drawing of the bill generation system according to cluster job scheduling of the present invention.As shown in Figure 1, this system comprises job scheduling monitoring module 100, data processing module 200, database 300, interactive module 400 and accounting engine 500.Wherein, job scheduling monitoring module 100 is for monitoring the operating index data of each operation, and record the operating index data of each operation and object properties information corresponding to operation, and the operating index data of each operation and object properties information corresponding to operation are sent to data processing module 200.Data processing module 200 is for receiving from the operating index data of each operation of job scheduling monitoring module 100 and object properties information corresponding to operation, the operating index data of each operation are processed, and the data after process are stored to database 300.Database 300 is for storing the data of data processing module 200.Interactive module 400 is for receiving management person request and supvr's request is sent to accounting engine 500, and receives the bill that returns of accounting engine 500 and present to supvr.Accounting engine 500 is asked for the supvr received from interactive module 400, and from database 300, read according to supvr's request the data meeting supvr's request, and generate bill according to supvr's request to after the Data Analysis Services meeting supvr's request, and bill is fed back to interactive module 400.
Job scheduling monitoring module 100 comprises monitoring module 110, logging modle 120 and sending module 130.Wherein, monitoring module 110 is for monitoring the operating index data of each operation.Logging modle 120 is for object properties information corresponding to the operating index data and operation that record each operation.Sending module 130 is for being sent to data processing module 200 by the operating index data of each operation and object properties information corresponding to operation.Wherein, the operating index data of operation comprise internal memory use amount, CPU holding time etc.Object properties information corresponding to operation comprises the information such as submission user, described cluster corresponding to operation.
Data processing module 200 comprises data reception module 210 and processing module 220.Wherein, data reception module 210 is for receiving from the operating index data of each operation of job scheduling monitoring module 100 and object properties information corresponding to operation.Processing module 220 is for processing in units of operation the operating index data of each operation, and the operating index data of each operation are classified by the object properties that operation is corresponding, and process in units of object properties, and the data after process are stored to database 300.Wherein, process comprises analysis, normalizing, statistics etc.
Interactive module 400 comprises and represents interface 410 and request processing module 420.Wherein, represent that interface 410 is for receiving management person request, and the bill that accounting engine 500 returns is presented to supvr.Request processing module 420 is for being sent to accounting engine 500 by supvr's request.
Accounting engine 500 comprises receiver module 510, data read module 520, bill generation module 530 and result feedback module 540.Wherein, receiver module 510 is asked for the supvr received from interactive module 400.Data read module 520 for reading according to supvr's request the data meeting supvr's request from database 300.Bill generation module 530 for according to supvr request, to meet supvr request Data Analysis Services after generate bill.Result feedback module 540 feeds back to interactive module 400 for the bill generated by bill generation module.Wherein, the form of bill comprises PDF, XLS and HTML etc.
The bill generation method according to cluster job scheduling of the present invention is described in detail below in conjunction with accompanying drawing 2.As shown in Figure 2, the method comprises the following steps:
Step S210, job scheduling monitoring module 100 monitors the operating index data of each operation, and record the operating index data of each operation and object properties information corresponding to operation, then the operating index data of each operation and object properties information corresponding to operation are sent to data processing module 200.
The operating index data of each operation comprise internal memory use amount, CPU holding time etc.Object properties information corresponding to operation comprises the information such as submission user, affiliated cluster corresponding to operation.Record in units of operation, has accomplished the data statistics of smaller particle size, can provide reliable Data support for follow-up data statistic analysis.Have recorded the object properties information that operation is corresponding simultaneously, the Data support of multi-angle can be provided for follow-up book keeping operation, the computational resource that the All Jobs submitted to as added up certain user takies.
Step S220, data processing module 200 receives from the operating index data of each operation of job scheduling monitoring module 100 and object properties information corresponding to operation, processes, and data are stored to database 300 to the operating index data of each operation.
Because the data volume of record in job scheduling monitoring module 100 can be comparatively large, be the performance and the efficiency that improve book keeping operation function, data processing module 200 every day can automatically to the same day job run data be weighted statistics.For improving the availability of data, carry out unit normalization to data, the internal memory taken as operation is all converted into MB *hour unit, by normalization, well makes data have comparability and with reference to property, and then provides true and reliable believable data for book keeping operation charge.Additionally provide by user, add up by the data weighting of the different levels such as cluster, the use resource in units of user accounts for the ratio data of whole resource, for charging provides the foundation of more perspective.
Step S230, supvr's request is also sent to accounting engine 500 by interactive module 400 receiving management person request.
Supvr can select relevant condition of keeping accounts, as select time scope, cluster wide etc.
Step S240, the supvr that accounting engine 500 receives from interactive module 400 asks, and from database 300, read according to supvr's request the data meeting supvr's request, then generate bill according to supvr's request to after the Data Analysis Services meeting supvr's request, and bill is fed back to interactive module 400 and present to supvr.
Can charge according to concrete operating index data genaration bill, if CPU use amount is by every core × hour charge 1 yuan, also resource can be used to account for the percentage cost fee of whole resource by user, because supvr can calculate operation cost according to the electricity charge, depreciation of machinery etc. sometimes, and shares the expenses equally accordingly.Therefore, bill generation method of the present invention is that supvr charges and provides the Data support of multi-angle.
Meanwhile, can be drawn with curve map the resource data counted in units of user and be represented, make between different user, to use the contrast of resource situation more directly perceived, very clear.
Supvr directly can browse bill, also book keeping operation content can be derived with document form with forms such as PDF, XLS, thus facilitates user to the secondary treating of data, and as write monthly magazine, superior reports machine resources service condition etc.
Should be understood that above-described embodiment is only schematic embodiment, do not limit the present invention and only can be realized by above-described embodiment.Those of ordinary skill in the art can also propose other amendments or change according to such scheme, and these amendments or change all should be included in of the present invention comprising within scope.
Supvr is supplied to reasonable manner, for charge provides more reliable believable foundation after being processed by analyze job run achievement data, add up and normalization etc.
Although illustrate and describe embodiments of the invention, for the ordinary skill in the art, be appreciated that and can carry out multiple change, amendment, replacement and modification to these embodiments without departing from the principles and spirit of the present invention, scope of the present invention is by claims and equivalency thereof.

Claims (12)

1. a bill generation system for cluster job scheduling, is characterized in that, described system comprises,
Job scheduling monitoring module, for monitoring the operating index data of each operation, and record the operating index data of described each operation and object properties information corresponding to described operation, and the operating index data of described each operation and object properties information corresponding to described operation are sent to data processing module, wherein, described operating index data are the computational resource that each operation takies;
Described data processing module, for receiving from the operating index data of each operation of described job scheduling monitoring module and object properties information corresponding to described operation, the operating index data of described each operation are processed, and the data after process are stored to database;
Described database, for storing the data of described data processing module;
Interactive module, is sent to accounting engine for receiving management person request by described supvr request, and receives bill that described accounting engine returns and present to supvr; And
Described accounting engine, ask for the supvr received from described interactive module, and from described database, read according to described supvr's request the data meeting described supvr request, and generate bill according to described supvr's request to after the Data Analysis Services of the described supvr's of meeting request, and described bill is fed back to described interactive module.
2. system according to claim 1, is characterized in that, described job scheduling monitoring module comprises,
Monitoring module, for monitoring the operating index data of each operation;
Logging modle, the object properties information that operating index data and described operation for recording described each operation are corresponding; And
Sending module, for being sent to described data processing module by the operating index data of described each operation and object properties information corresponding to described operation.
3. system according to claim 1, is characterized in that, described data processing module comprises,
Data reception module, for receiving from the operating index data of each operation of described job scheduling monitoring module and object properties information corresponding to described operation; And
Processing module, for processing in units of operation the operating index data of described each operation, and the operating index data of described each operation are classified by the object properties that described operation is corresponding, and process in units of object properties, and the data after process are stored to described database.
4. system according to claim 1, is characterized in that, described interactive module comprises,
Represent interface, for receiving management person request, and the bill that described bill generation module returns is presented to supvr; And
Request processing module, for being sent to described accounting engine by described supvr's request.
5. system according to claim 1, is characterized in that, described accounting engine comprises:
Receiver module, asks for the supvr received from described interactive module;
Data read module, for reading according to described supvr's request the data meeting described supvr request from described database;
Bill generation module, for asking according to described supvr, generates bill to after the Data Analysis Services of the described supvr's of meeting request; And
Result feedback module, feeds back to described interactive module for the described bill generated by described bill generation module.
6. the system according to claim 1 or 3, is characterized in that, the described process to data comprise following one of at least: to analyze, normalizing and statistics.
7. system according to claim 1 or 5, is characterized in that, the form of described bill comprise following one of at least: PDF, XLS and HTML.
8. the bill generation method of a cluster job scheduling, is characterized in that, said method comprising the steps of:
Job scheduling monitoring module monitors the operating index data of each operation, and record the operating index data of described each operation and object properties information corresponding to described operation, then the operating index data of described each operation and object properties information corresponding to described operation are sent to data processing module, wherein, described operating index data are the computational resource that each operation takies;
Described data processing module receives from the operating index data of each operation of described job scheduling monitoring module and object properties information corresponding to described operation, the operating index data of described each operation are processed, and the data after process are stored to database;
Described supvr's request is also sent to accounting engine by interactive module receiving management person request; And
The supvr that described accounting engine receives from described interactive module asks, and from described database, read according to described supvr's request the data meeting described supvr request, then generate bill according to described supvr request to after the Data Analysis Services of the described supvr's of meeting request, and described bill is fed back to described interactive module present to supvr.
9. method according to claim 8, is characterized in that, object properties information corresponding to described operation comprise following one of at least: the affiliated cluster of submission user corresponding to described operation, described operation.
10. method according to claim 8, is characterized in that, the described operating index data to described each operation process, and comprise,
The operating index data of described each operation are processed in units of operation; And
The operating index data of described each operation are classified by the object properties that described operation is corresponding, and processes in units of object properties.
11. methods according to claim 8, is characterized in that, the described process to data comprise following one of at least: to analyze, normalizing and statistics.
12. methods according to claim 8, is characterized in that, the form of described bill comprise following one of at least: PDF, XLS and HTML.
CN200910091836.6A 2009-08-28 2009-08-28 The bill generation system of cluster job scheduling and method Active CN101694712B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN200910091836.6A CN101694712B (en) 2009-08-28 2009-08-28 The bill generation system of cluster job scheduling and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN200910091836.6A CN101694712B (en) 2009-08-28 2009-08-28 The bill generation system of cluster job scheduling and method

Publications (2)

Publication Number Publication Date
CN101694712A CN101694712A (en) 2010-04-14
CN101694712B true CN101694712B (en) 2016-04-06

Family

ID=42093681

Family Applications (1)

Application Number Title Priority Date Filing Date
CN200910091836.6A Active CN101694712B (en) 2009-08-28 2009-08-28 The bill generation system of cluster job scheduling and method

Country Status (1)

Country Link
CN (1) CN101694712B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180158035A1 (en) * 2016-12-06 2018-06-07 Sap Se Independent processing streams for event data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2648712Y (en) * 2003-10-10 2004-10-13 尹政弘 Network bar paying and monitoring system
CN101159927A (en) * 2007-11-08 2008-04-09 中兴通讯股份有限公司 Fee counting method in cluster communication
CN101309208A (en) * 2008-06-21 2008-11-19 华中科技大学 Job scheduling system suitable for grid environment and based on reliable expense

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2648712Y (en) * 2003-10-10 2004-10-13 尹政弘 Network bar paying and monitoring system
CN101159927A (en) * 2007-11-08 2008-04-09 中兴通讯股份有限公司 Fee counting method in cluster communication
CN101309208A (en) * 2008-06-21 2008-11-19 华中科技大学 Job scheduling system suitable for grid environment and based on reliable expense

Also Published As

Publication number Publication date
CN101694712A (en) 2010-04-14

Similar Documents

Publication Publication Date Title
US10154153B2 (en) Application resource usage information
CN102880676A (en) Statistical method for user behavior data and user behavior data statistical system
US20120232934A1 (en) Automated insurance policy form generation and completion
CN103873528A (en) Method and equipment for distributing system resources for user
CN111314869B (en) Flow quota distribution method and device, electronic equipment and storage medium
CN102736971A (en) Information processing apparatus and method, electronic device and control method thereof, and log collection system
CN107729137A (en) Server, the method and storage medium of the decryption of block chain sign test
CN110147470B (en) Cross-machine-room data comparison system and method
CA2733857A1 (en) Automated insurance policy form generation and completion
CN107291539A (en) Cluster program scheduler method based on resource significance level
CN110175152A (en) A kind of log inquiring method, transfer server cluster and log query system
CN113872813A (en) Full life cycle management method and system for carrier communication equipment
CN111652485A (en) New energy data acquisition and analysis system based on big data platform
CN113722276A (en) Log data processing method, system, storage medium and electronic equipment
CN112297934A (en) Charging station processing method and device, storage medium and processor
CN107451301B (en) Processing method, device, equipment and storage medium for real-time delivery bill mail
CN101694712B (en) The bill generation system of cluster job scheduling and method
CN110084476A (en) Case method of adjustment, device, computer equipment and storage medium
CN109542848A (en) A kind of vehicle-mounted media file fast scanning method and system
CN111314234B (en) Flow distribution method and device, storage medium and electronic equipment
TWI706366B (en) Electric vehicle charging station power management method
CN115630127A (en) Vehicle machine data analysis method and device, storage medium and vehicle
CN101431742B (en) Communication service access method and system
CN114090686A (en) Account-out acceleration method and device
CN101355772B (en) Method, apparatus and system for discriminating service

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C53 Correction of patent of invention or patent application
CB02 Change of applicant information

Address after: 100193 Beijing, Haidian District, northeast Wang West Road, building 8, No. 36

Applicant after: Dawning Information Industry (Beijing) Co.,Ltd.

Address before: 100084 No. 6 South Road, Zhongguancun Academy of Sciences, Beijing, Haidian District

Applicant before: Dawning Information Industry (Beijing) Co.,Ltd.

C14 Grant of patent or utility model
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20220725

Address after: 100089 building 36, courtyard 8, Dongbeiwang West Road, Haidian District, Beijing

Patentee after: Dawning Information Industry (Beijing) Co.,Ltd.

Patentee after: DAWNING INFORMATION INDUSTRY Co.,Ltd.

Address before: 100193 No. 36 Building, No. 8 Hospital, Wangxi Road, Haidian District, Beijing

Patentee before: Dawning Information Industry (Beijing) Co.,Ltd.