CN104090934B - A kind of standards service platform Distributed Parallel Computing database and its search method - Google Patents
A kind of standards service platform Distributed Parallel Computing database and its search method Download PDFInfo
- Publication number
- CN104090934B CN104090934B CN201410291595.0A CN201410291595A CN104090934B CN 104090934 B CN104090934 B CN 104090934B CN 201410291595 A CN201410291595 A CN 201410291595A CN 104090934 B CN104090934 B CN 104090934B
- Authority
- CN
- China
- Prior art keywords
- center
- database server
- node database
- data
- node
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2453—Query optimisation
- G06F16/24532—Query optimisation of parallel queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24552—Database cache management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of standards service platform Distributed Parallel Computing database, including node database server cluster, comprising some node database servers, each node database server is responsible for the searching and managing of institute's distribution node data；Realize that the guiding of external perimysium reference data to the node database server cluster is stored in control centre, the query and search order Parallel transmutation that the center of caching is sent gives node database server, and level cache center is delivered to after node database server lookup retrieval result then is carried out into secondary operation screening；Level cache center provides the interim storage that control centre conveys query and search result, and offer is interacted with the inquiry of database front-end；Surveillance center realizes the real-time monitoring and early warning of the performance indications of node database server cluster, control centre and level cache center.The present invention is by distributed frame design and parallel computation, and standard needed for simple, fast and accurate excavation user improves retrieval precision.
Description
Technical field
The present invention relates to database technical field, more particularly to a kind of standards service platform Distributed Parallel Computing data
Storehouse.
Background technology
Parallel computation（Parallel Computing）Refer to while solving the mistake of computational problem using a variety of computing resources
Journey, is a kind of effective means for improving computer system calculating speed and disposal ability.Its basic thought is with multiple processing
Device carrys out Cooperative Solving same problem, and the problem of will being solved resolves into several parts, and each several part is by an independent place
Reason machine carrys out parallel computation.Parallel computation is a computer, equipped with multiprocessor, and contract cooperation meter is carried out between multiprocessor
Calculate, final result is by a computer disposal.Parallel computation can be divided into temporal parallel and spatially parallel.It is temporal
It is parallel just to refer to pipelining, and spatially parallel then refer to multiple processors concurrently perform calculating.
One distributed system be by one group of computer with standalone feature by network joint, it is some specific meeting
Under the management control of rule, whole system is rendered as a transparent entirety in front of the user, it is possible to achieve resource-sharing.Distribution
It is many computers networked that formula, which is calculated, there is respective main frame and processor, passes through network allocation and shares calculating task and calculating
Information.Distributed Calculation is the management in idle time ability using the CPU of the computer on internet to solve the problems, such as mass computing
A kind of computational science.
With the attention that developing rapidly for informatization, country work standard, various structural datas and non-structural
Change data to be skyrocketed through, standard number has reached that millions are other, even more high magnanimity rank.How effectively to excavate or
Related knowledge or data turn into a problem in the mass data that search criteria service platform is produced.At present, standard is improved
Service level, tries to explore the New methods in working of standard work, and standard is carried out in creative development standard informationization work
Information system management and service, are enterprises service, are customer service, are the development service of China's economic construction.
The present invention is for standard number is numerous, user is unfamiliar with to standard, and the low problem of algnment accuracy needed for inquiry is introduced
Distributed and parallel computation, proposes the distributed parallel internal memory database method for solving to retrieve Precision criterion data problem, letter
Standard needed for single, fast and accurate excavation user, effectively increases retrieval precision.
The content of the invention
In order to overcome the deficiencies in the prior art, the present invention provides a kind of standards service platform Distributed Parallel Computing
Database, by distributed frame design and parallel computation, standard needed for simple, fast and accurate excavation user is effectively improved
Retrieval precision.
To achieve the above object, the present invention is adopted the following technical scheme that：
A kind of standards service platform Distributed Parallel Computing database, including：
Node database server cluster, comprising some node database servers, each node database server is born
Blame the searching and managing of institute's distribution node data；
Control centre, for realizing that the guiding of external perimysium reference data to the node database server cluster is stored,
And the query and search order Parallel transmutation for sending level cache center is to all node database servers, then by all sections
Point data base server lookup retrieval result is delivered to level cache center after carrying out secondary operation screening；
Level cache center, the interim storage of query and search result is conveyed for providing control centre, and provide and number
Interacted according to the inquiry of storehouse front end；
Surveillance center, for realizing that the performance of node database server cluster, control centre and level cache center refers to
Target is monitored in real time, early warning.
Further, the control centre includes data guide service module, convergence service module, distributed tune
Degree center and registration center；
The distributed scheduling center is used to utilize many to the query and search order that the level cache center received is sent
The concurrent technique of main frame Multi-core is transmitted to all node database servers；
The convergence service module is used for will by the query and search that meets that all node database servers are retrieved
The retrieval result asked extracts and is pooled to convergence service module, is then ranked up according to ordering rule, and interception meets sequence
It is required that data, to query and search result carry out secondary operation screening after be delivered to caching center；
The registration center is used to safeguard node database server associated metadata, and passes through heartbeat, proactive notification, people
Work inspection mechanism realizes the monitoring management of node database server；
The data guide service module, for realizing external perimysium reference data to the node database server cluster
Storage, and joint registration center, Surveillance center realize the automatic drift and disaster tolerance function of node database server.
Further, the automatic drift function, is when the normal data capacity of node database server storage surpasses
When going out its threshold value, automatic overflow is transferred in the node database server that other are redistributed；
The disaster tolerance function, be under each node database server containing multiple leg gusset database servers therewith
It is connected, the leg gusset database server is its mapping server, internal standard data are identical, in present node number
During according to storehouse server cisco unity malfunction, leg gusset database server takes over current block completion work automatically.
Further, the metadata includes node database server ip, port numbers, included normal structure and group
Normal data amount under knitting.
Further, the level cache center includes caching center, enquiry module and caching control centre；
The caching center is used to provide the interim storage that control centre conveys query and search result；
The buffer scheduling center is used to store extracting mode to the normal data for caching central store, sequentially managed
Reason；
The enquiry module is used to provide inquiry port, and after retrieval command is received, first choice goes to caching center to carry out
Query and search, if in the presence of, directly database front-end export Query Result, otherwise, query and search order is passed through into buffer scheduling
Center is delivered to the query and search that distributed scheduling center carries out each node database server.
Further, the level cache center is deposited in operating system caching, and the operating system caching is hard
Disk controller memory chip.
The present invention also provides a kind of query and search method of standards service platform Distributed Parallel Computing database, including such as
Lower step：
Step1:Input retrieval key element, builds retrieval command；
Step2:Retrieval matching is carried out to the normal data for caching central store, if caching center, which exists, meets retrieval life
The normal data of order, then perform step 3, otherwise perform step4；
Step3:The retrieval result for meeting retrieval command is directly fed back to database front-end；
Step4:Retrieval command is transmitted to all node database servers, each node database server is responsible for
The retrieval of its normal data managed；
Step5:In each node database server, the normal data for meeting retrieval command is extracted, and according to section
Point data base server orders rule output retrieval result；
Step6:The retrieval result of all node database servers is converged, and according to convergence service module
Ordering rule is ranked up to the retrieval result after convergence again, the threshold value then set according to database front-end, intercepts threshold value model
Enclose interior qualified result；
Step7:Obtained data deposit caching center will be intercepted, be easy to next query and search；
Step8:The paging rule that the data that interception is obtained show page setting according to database front-end is shown page by page.
Further, when the Step5 interior joints database server is retrieved to the normal data of internal control,
The metadata for meeting query and search order is extracted first, and the normal data for matching retrieval command is then obtained according to metadata.Have
Beneficial effect：（1）Present invention introduces distributed and parallel computation, propose to solve the distribution for retrieving Precision criterion data problem simultaneously
Row internal memory database method, standard needed for simple, fast and accurate excavation user, effectively increases retrieval precision.（2）This hair
Bright setting caching center, the preferred retrieval buffering center in retrieval, and at the end of retrieving, inquiry data are put into caching, in case
The inquiry of next similarity condition, directly takes data cached, raising inquiry velocity.（3）Database of the present invention provided with automatic guiding and
Hand guided function, it is ensured that normal data is synchronous with normal structure mechanism.（4）Database of the present invention be additionally provided with it is automatic overflow and
Disaster tolerance function, it is ensured that database remains to normal work in abnormal cases.
Brief description of the drawings
A kind of standards service platform Distributed Parallel Computing database structure schematic diagram that Fig. 1 provides for the present invention.
The standards service platform Distributed Parallel Computing data base querying retrieval flow figure that Fig. 2 provides for the present invention.
Fig. 3 is that the query and search flow chart met when retrieval is required is not present in buffering center of the present invention.
Embodiment
The present invention is further described below in conjunction with the accompanying drawings.
As shown in figure 1, a kind of standards service platform Distributed Parallel Computing database that the present invention is provided, including one-level are slow
Center, control centre, Surveillance center and node database server cluster are deposited, level cache center includes caching center and caching
Control centre, control centre is included in data guide service module, convergence service module, distributed scheduling center and registration
The heart.
（1）Node database server cluster
Node database server cluster includes some node database servers, the standards service platform that the present invention is provided
The normal data of storage is carried out node division, section by database by normal data total amount and each node database server capacity
Count out=normal data total amount/each node database server capacity, the node data after division is used in approximate data
Suitable method is distributed to each node database server first：Node database server is initialized first, Ran Houyi
It is secondary that node data is put into first node database server that can accommodate the node data size, realize each node
Data storage is into a node database server, and each node database server is responsible for the corresponding node data of distribution
Management, node database server resides permanently operating system as service and is easy to provide inquiry service in real time.Node database is serviced
The management of corresponding node data is responsible in all node database server independent parallel operations in device cluster, independent to realize correspondence section
Loading, renewal and inquiry of point data etc..
（2）Control centre
Control centre is the control centre of integrated dispatch, including data guide service module, convergence service module, point
Cloth control centre and registration center.
Registration center is used for the metadata for safeguarding that node database server is related（IP, port numbers, the normal structure included
And the normal data amount under tissue）；And node database server is realized by mechanism such as heartbeat, proactive notification, manual inspections
Monitoring management.
Data guide service module is provided to the layout management of database magnanimity normal data, cutting loading and management by synchronization
Deng service, so as to realize automatic guiding and the hand guided of data.Database and standardized management tissue or organization data storehouse
It is connected, hand guided is generally used for the initialization of database normal data, by hand by standardized management tissue or organization data storehouse
In normal data cutting be loaded onto in database, such as from standardized management tissue database every time loading 5000 mark
Quasi- data, have been loaded until all；Automatic guiding is mainly used in database and standardized management tissue or organization data storehouse
Management by synchronization, data guide service module monitors, the real-time change for loading normal structure database standard data（Increase, delete, change）.
Also by combined registering center, Surveillance center, the automatic drift of node database server can be achieved in data guide service module
With disaster tolerance function.Automatic drift is, when the normal data capacity of node database server storage exceeds its threshold value, to overflow automatically
Go out to be transferred in other node database servers.Disaster tolerance function refers under a node database server containing multiple attached
Category node database server is attached thereto, and leg gusset database server is its mapping server, and internal standard data are complete
Exactly the same, in present node database server cisco unity malfunction, leg gusset database server is taken over currently automatically
Module completion work, so that it is guaranteed that the normal operation of database.
Distributed scheduling center is used for the parallel skill that many main frame Multi-cores are utilized to the query and search order received
Art, all node database servers are transmitted to by query and search order, and each node database server is responsible for its management
The query and search of normal data.
Convergence service module is used to the retrieval result of each node database server is evaluated and collected, right
Each node database server inquired about, and meets query and search requirement by what each node database server was retrieved
Retrieval result is drawn into convergence service module, and then the normal data of all node database servers of extraction is assembled
Get up, be ranked up according to ordering rule, interception meets the data of ordering requirements, realize and node database server lookup is examined
Hitch fruit is delivered to caching center after carrying out secondary operation screening.
（3）Level cache center
Level cache center includes caching center, enquiry module and caching control centre, and behaviour is deposited at level cache center
Make in system cache, caching is one piece of memory chip on hard disk controller, and with the access rate being exceedingly fast, it is hard drive internal
Buffer between storage and extraneous interface, caching refers to temporary file exchange area, can carry out the storage of high-speed data exchange
Device, it exchanges data with CPU prior to internal memory, therefore speed is quickly, but the data in caching are small part data in internal memory
Duplicate.
Enquiry module is responsible for the inquiry of database normal data, and enquiry module is after retrieval command is received, and first choice goes to delay
Deposit center carry out query and search, if in the presence of, directly database front-end export Query Result, otherwise, query and search order is led to
Cross caching control centre and be delivered to the query and search that distributed scheduling center carries out each node database server.
The interim storage of caching center and caching control centre's database normal data and acquisition modes and order
Deng.Cache center function relatively easy, realization is deposited temporarily to normal data, be easy to directly acquisition, data storage convergence
The inquiry data conveyed after the screening of service module secondary operation.Buffer scheduling center is used for the normal data to caching central store
Storage extracting mode, order etc. are managed, and can support the caching of session ranks, the caching of application level and based on the time
The caching of rank.Support the strategies such as first in first out, access times minimum, time of exceeding the time limit.
（4）Surveillance center
Node database server cluster, control centre, 3, level cache center constituent components to more than are supervised
Control, realizes the key performance and global control in moment monitoring data storehouse.Which record current database system carrying out and accessing,
Judge which data is hot spot data according to historical record, the internal memory of each node database server of simultaneous real-time monitoring,
The Key Performance Indicators such as CPU, disk I/O.Global early warning, local early warning can be set, so as to realize early discovery, early prevention, early pipe
Reason, the benign cycle of early optimization.
The present invention also provides a kind of standards service platform Distributed Parallel Computing database index method, in order to improve standard
Effectiveness of retrieval and precision, using Distributed Parallel Computing principle, the present invention set Surveillance center, caching center, control centre,
The components such as node database server are carried out to each function such as the retrieval of normal data, extraction, sequence, convergence, paging, display
The analyzing and processing of module and control.The collaborative work of four components more than, based on the working mode transition of passive response
Dynamic management, actively upgrading, the mode of operation of actively optimization.
（1）Data retrieval mechanism and flow
By standards service platform search criteria data, the qualified mark for wanting acquisition is retrieved according to input condition
Quasi- data.Go to cache center extraction first during retrieval every time, if any qualified, then direct feedback searching result；Conversely, then
Go in all node database servers all to go to retrieve, extract, converge, sorting, intercepting, caching, paging, display, while will knot
Fruit deposit caching center.Nominal data retrieval whole flow process is as shown in Fig. 2 comprise the following steps that：
Step1:Standards service platform is accessed, input retrieval key element builds retrieval command.
Step2:Retrieval matching is carried out to the normal data for caching central store, if caching center, which exists, meets retrieval life
The normal data of order, then perform step 3, otherwise perform step4；
Step3:Directly feedback meets the retrieval result of retrieval command；
Step4:Retrieval command is transmitted to all node database servers, each node database server is responsible for
The retrieval of its normal data managed；
Step5:In each node database server, the normal data for meeting retrieval command is extracted, and according to section
Point data base server orders rule output retrieval result；
Step6:The retrieval result of all node database servers is converged, and according to convergence service module
Ordering rule is ranked up to the retrieval result after convergence again, the threshold value then set according to database front-end, intercepts threshold value model
Enclose interior qualified result；
Step7:Obtained data deposit caching center will be intercepted, be easy to next query and search；
Step8:Shown obtained data are intercepted page by page according to paging rule is showed.
In Distributed Parallel Computing database, the metadata of node database server is safeguarded using registration center, and
The monitoring management of node database server is realized by mechanism such as heartbeat, proactive notification mechanism, manual inspections.Data guiding clothes
The guiding of pragmatic existing data, combined registering center, Surveillance center realize the automatic drift and disaster tolerance work(of node database server
Energy.Distributed parallel scheduling service, using the concurrent technique of many main frame Multi-cores, order is forwarded to the order received
Give node database server.Node database server orders rule and convergence service module ordering rule are converged by data
Poly- service module is configured, and ordering rule is set by normal data sort method.In step1-4 interior joint database servers
It is responsible for being managed the data of node, and realizes the data loading of node itself, inquiry and more New function, resides permanently as service
Operating system.In step5-8, convergence service module is evaluated to the returning result of each node database server
With collect, and dispatching algorithm is converged according to correspondence, secondary operation screening is carried out to result, and caching center is returned to.Retrieval knot
Shu Shi, inquiry data are put into caching center, in case the inquiry of next similarity condition, directly takes data cached, raising inquiry speed
Degree.
（2）Data base querying rule
During normalized service data base querying, node database server is scanned according to the search condition of input
When, data guide service module to node database server group into data-base cluster, retrieval, the loading etc. for carrying out data manage
Reason.Distributed scheduling center carries out overall control and scheduling to each functional module respectively, coordinates the parallel of each module
Perform.
Buffering center is in the absence of the retrieving met when retrieval is required as shown in figure 3, particular content is as follows：
Step1:The metadata for meeting query and search order is extracted first, is then retrieved according to metadata query matching inquiry
The normal data of order, and the data that each node database server is extracted perform internal sort；
Step2:Secondly the data after these all sequences are subjected to convergence using convergence service and are combined into one
Individual entirety, then be ranked up for this overall data；
Step3:Then intercept and wherein meet the data of demand and be put into caching center, and by according to point for showing page setting
Page rule, the information of Pagination Display user inquiry.
Coordinate each functional module by Distributed Parallel Computing database component to cooperate, realize standards service platform
Nominal data retrieval, convergence, sequence, caching etc., final display user's query criteria information.
Described above is only the preferred embodiment of the present invention, it should be pointed out that：For the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (4)
1. a kind of standards service platform Distributed Parallel Computing database, it is characterised in that including：
Node database server cluster, comprising some node database servers, each node database server is responsible for institute
The searching and managing of distribution node data；
Control centre, for realizing that the guiding of external perimysium reference data to the node database server cluster is stored, and will
The query and search order Parallel transmutation that level cache center is sent is to all node database servers, then by all nodes
Level cache center is delivered to after carrying out secondary operation screening according to storehouse server lookup retrieval result；
Level cache center, the interim storage of query and search result is conveyed for providing control centre, and provide and database
The inquiry interaction of front end；
Surveillance center, the performance indications for realizing node database server cluster, control centre and level cache center
Monitoring, early warning in real time；
The control centre is included in data guide service module, convergence service module, distributed scheduling center and registration
The heart；
The distributed scheduling center is used to utilize many main frames to the query and search order that the level cache center received is sent
The concurrent technique of Multi-core is transmitted to all node database servers；
The convergence service module is used to meet query and search requirement by what all node database servers were retrieved
Retrieval result extracts and is pooled to convergence service module, is then ranked up according to ordering rule, and interception meets ordering requirements
Data, to query and search result carry out secondary operation screening after be delivered to caching center；
The registration center is used to safeguard node database server associated metadata, and by heartbeat, proactive notification, manually patrol
Inspection mechanism realizes the monitoring management of node database server；
The data guide service module, for realizing external perimysium reference data depositing to the node database server cluster
Storage, and joint registration center, Surveillance center realize the automatic drift and disaster tolerance mechanism of node database server；
The automatic drift mechanism, is when the normal data capacity of node database server storage exceeds its threshold value, automatically
Spilling is transferred in the node database server that other are redistributed；
The disaster tolerance mechanism, is containing multiple leg gusset database servers phase therewith under each node database server
Even, the leg gusset database server is its mapping server, and internal standard data are identical, in present node data
During the server cisco unity malfunction of storehouse, leg gusset database server takes over current block completion work automatically；
The level cache center includes caching center, enquiry module and caching control centre；
The caching center is used to provide the interim storage that control centre conveys query and search result；
The buffer scheduling center is used to store extracting mode to the normal data for caching central store, is sequentially managed；
The enquiry module is used to provide inquiry port, and after retrieval command is received, first choice goes to caching center to be inquired about
Retrieval, if in the presence of, directly database front-end export Query Result, otherwise, query and search order is passed through into buffer scheduling center
It is delivered to the query and search that distributed scheduling center carries out each node database server.
2. a kind of standards service platform Distributed Parallel Computing database according to claim 1, it is characterised in that：It is described
Metadata includes the normal data amount under node database server ip, port numbers, the normal structure included and tissue.
3. a kind of standards service platform Distributed Parallel Computing database according to claim 1, it is characterised in that：It is described
Level cache center is deposited in operating system caching, and the operating system caching is hard disk controller memory chip.
4. the search method of standards service platform Distributed Parallel Computing database described in a kind of claim 1, it is characterised in that
Comprise the following steps：
Step1:Input retrieval key element, builds retrieval command；
Step2:Retrieval matching is carried out to the normal data for caching central store, if caching center, which exists, meets retrieval command
Normal data, then perform step 3, otherwise perform step4；
Step3:The retrieval result for meeting retrieval command is directly fed back to database front-end；
Step4:Retrieval command is transmitted to all node database servers, each node database server is responsible for its pipe
The retrieval of the normal data of reason；
Step5:In each node database server, the normal data for meeting retrieval command is extracted, and according to nodes
According to storehouse server orders rule output retrieval result；
Step6:The retrieval result of all node database servers is converged, and sorted according to convergence service module
Rule is ranked up to the retrieval result after convergence again, the threshold value then set according to database front-end, in interception threshold range
Qualified result；
Step7:Obtained data deposit caching center will be intercepted, be easy to next query and search；
Step8:The paging rule that the data that interception is obtained show page setting according to database front-end is shown page by page；
When the Step5 interior joints database server is retrieved to the normal data of internal control, extract to meet first and look into
The metadata of retrieval command is ask, the normal data for matching retrieval command is then obtained according to metadata.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410291595.0A CN104090934B (en) | 2014-06-26 | 2014-06-26 | A kind of standards service platform Distributed Parallel Computing database and its search method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410291595.0A CN104090934B (en) | 2014-06-26 | 2014-06-26 | A kind of standards service platform Distributed Parallel Computing database and its search method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104090934A CN104090934A (en) | 2014-10-08 |
| CN104090934B true CN104090934B (en) | 2017-09-12 |
Family
ID=51638650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410291595.0A Expired - Fee Related CN104090934B (en) | 2014-06-26 | 2014-06-26 | A kind of standards service platform Distributed Parallel Computing database and its search method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104090934B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105183394B (en) * | 2015-09-21 | 2018-09-04 | 北京奇虎科技有限公司 | A kind of data storage handling method and device |
| CN107368583A (en) * | 2017-07-21 | 2017-11-21 | 郑州云海信息技术有限公司 | A kind of method and system of more cluster information inquiries |
| CN110019255A (en) * | 2017-07-31 | 2019-07-16 | 北京嘀嘀无限科技发展有限公司 | Data query method, apparatus, server and storage medium |
| CN108170731A (en) * | 2017-12-13 | 2018-06-15 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer storage media and server |
| CN109544338A (en) * | 2018-11-15 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Assets stock trading method, equipment and computer readable storage medium |
| CN111491002B (en) * | 2019-01-29 | 2023-12-05 | 杭州海康威视系统技术有限公司 | Equipment inspection method, device, inspected equipment, inspection server and system |
| CN110598056A (en) * | 2019-08-27 | 2019-12-20 | 阿里巴巴集团控股有限公司 | Node layout determination method and device |
| CN111881181B (en) * | 2020-07-22 | 2024-03-01 | 中国工商银行股份有限公司 | Data statistics method, device and equipment based on distributed database |
| CN114706871B (en) * | 2022-04-26 | 2023-01-03 | 扬州智能科技有限公司 | Data monitoring method and system based on comprehensive monitoring management |
| CN116521969B (en) * | 2023-02-28 | 2023-12-29 | 华为云计算技术有限公司 | Data retrieval method, server, system and related equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908075A (en) * | 2010-08-17 | 2010-12-08 | 上海云数信息科技有限公司 | SQL-based parallel computing system and method |
| CN103207920A (en) * | 2013-04-28 | 2013-07-17 | 北京航空航天大学 | Parallel metadata acquisition system |
-
2014
- 2014-06-26 CN CN201410291595.0A patent/CN104090934B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908075A (en) * | 2010-08-17 | 2010-12-08 | 上海云数信息科技有限公司 | SQL-based parallel computing system and method |
| CN103207920A (en) * | 2013-04-28 | 2013-07-17 | 北京航空航天大学 | Parallel metadata acquisition system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104090934A (en) | 2014-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104090934B (en) | A kind of standards service platform Distributed Parallel Computing database and its search method | |
| CN202058147U (en) | Distribution type real-time database management system | |
| CN104903894B (en) | System and method for distributed networks database query engine | |
| CN104778188B (en) | A kind of distributed apparatus log collection method | |
| CN103678665B (en) | A kind of big data integration method of isomery based on data warehouse and system | |
| CN103345514B (en) | Streaming data processing method under big data environment | |
| US10191963B2 (en) | Prefetching analytic results across multiple levels of data | |
| CN110310051A (en) | A kind of wisdom garden management method being automatically imported and dynamically update business data | |
| CN107329982A (en) | A kind of big data parallel calculating method stored based on distributed column and system | |
| CN107679192A (en) | More cluster synergistic data processing method, system, storage medium and equipment | |
| CN104036025A (en) | Distribution-base mass log collection system | |
| CN105138679B (en) | A kind of data processing system and processing method based on distributed caching | |
| CN105117497B (en) | Ocean big data principal and subordinate directory system and method based on Spark cloud network | |
| CN105335479B (en) | A kind of text data statistics implementation method based on SQL | |
| CN107133362A (en) | Commodity Information Search method, system, computer program and electronic equipment | |
| CN103970902A (en) | Method and system for reliable and instant retrieval on situation of large quantities of data | |
| CN105808358B (en) | A kind of data dependence thread packet mapping method for many-core system | |
| Ferdman et al. | Quantifying the mismatch between emerging scale-out applications and modern processors | |
| CN109213752A (en) | A kind of data cleansing conversion method based on CIM | |
| CN102479217A (en) | Method and device for realizing computation balance in distributed data warehouse | |
| CN103257923B (en) | The application choosing method of data center's data analysis class benchmark and system | |
| CN107066546A (en) | A kind of across data center method for quickly querying and system based on MPP engines | |
| CN106570145B (en) | Distributed database result caching method based on hierarchical mapping | |
| CN108182263A (en) | A kind of date storage method of data center's total management system | |
| CN110147470A (en) | Across the computer room comparing system and method for one kind |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170912 Termination date: 20200626 |