CN105930345A - Hierarchical indexing method based on distributed real-time database system (DRTDBS) - Google Patents
Hierarchical indexing method based on distributed real-time database system (DRTDBS) Download PDFInfo
- Publication number
- CN105930345A CN105930345A CN201610208956.XA CN201610208956A CN105930345A CN 105930345 A CN105930345 A CN 105930345A CN 201610208956 A CN201610208956 A CN 201610208956A CN 105930345 A CN105930345 A CN 105930345A
- Authority
- CN
- China
- Prior art keywords
- label point
- data
- storage server
- hash
- data storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2246—Trees, e.g. B+trees
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention provides a hierarchical indexing method based on a distributed real-time database system (DRTDBS), and belongs to the field of a database. The hierarchical indexing method includes the steps of acquiring a data operation request from a client; extracting tag points in the operation request; determining a target data storage server in a hash index annular list; further enabling the target data storage server to perform hierarchical indexing in a B+ tree; and after determining an operation position, performing data operation. The invention can ensure high efficiency in real-time database data storage and retrieval by using the hash index annular list, and can also allows the tag point indexing to be more independent thanks to the establishment of a separate B+ tree data index for each tag point, so that a high fault tolerance is attained among data storage servers in the distributed real-time database.
Description
Technical field
The invention belongs to database field, index particularly to a kind of level based on distributing real-time data bank
Method.
Background technology
Along with the development of computer technology, occur in that more and more application relying on data high-speed access.Due to
This type of application is mainly used in the information gathering of real-time monitoring equipment, and the information owing to collecting has the highest
Frequency acquisition and extremely strong ageing, it is therefore desirable to use real-time data base that the information collected is stored
And management.
Existing real-time data base mainly uses centralized management, although can provide the preferable efficiency of management,
But in the access speed and data fault-tolerant of data, or there is more significantly defect.
Summary of the invention
In order to solve problem of the prior art, the invention provides level rope based on distributing real-time data bank
Draw method, described level indexing means, including:
The central control server being arranged in described distributing real-time data bank receives the data that client sends
Operation operation requests, extracts the label point specified in described data manipulation operation requests, from the Kazakhstan built in advance
Uncommon index annular list is chosen the relevant unit letter of the target data storage server corresponding to described label point
Breath, sends described relevant meta information to described client；
Described client receives described relevant meta information, extracts described target data from described relevant meta information
The IP address of storage server and COM1, will comprise the data to be operated of described label point by described logical
Letter port sends the described target data storage server pointed to described IP address；
Described target data storage server extracts described label point, determines institute according to the title of described label point
State the Hash key assignments of label point, determine that described label point structural information builds in advance according to described Hash key assignments
Label point Hash table in target location, according to described target location build in advance label point structure letter
Breath table obtains the position of B+ root vertex belonging to described label point；
According to the position of described index tree root node, in conjunction with the historical time of the data manipulation prestored, really
Surely the pointer of next layer index node structure is traveled through, according to the joint traveling through described B+ tree of described pointer level
Point, determines inode structures corresponding with described data to be operated in described B+ tree, by described to be operated
Data are mounted at described inode structures, revise described pointer and grasp to described client feedback data
Make successful message；
Wherein, the structure flow process of described hash index annular list is:
Step one, central control server obtains the check value of label point title, according to default hash algorithm
Get the Hash key assignments corresponding with described check value；
Step 2, described central control server gets the Hash key assignments of whole label point, by described label
The relevant meta information of data storage server and the Hash key assignments of described label point of some ownership are stored in list
In；
Step 3, is connected the headers and footers of described list, obtains hash index circular chart.
Optionally, if first number that described data manipulation operation requests is described distributing real-time data bank
During according to operation operation, described distributing real-time data bank is carried out initialization process.
Optionally, described relevant meta information includes IP address and the communication ends of described target data storage server
Mouthful.
Optionally, in described hash index annular list, according to choosing and described label point clockwise
The relevant meta information of corresponding target data storage server.
Optionally, in described target data storage server, storage has and comprises pointer, the going through of data manipulation
The history time is in interior B+ tree inode structures.
The technical scheme that the present invention provides has the benefit that
By using hash index annular list to can ensure that real-time data base data storage and search greater efficiency
While, due also to each label point to be set up single B+ tree data directory so that label point index has
Higher independence, so that have higher between each data storage server of distributing real-time data bank
Fault-tolerant ability.
Accompanying drawing explanation
In order to be illustrated more clearly that technical scheme, required use in embodiment being described below
Accompanying drawing be briefly described, it should be apparent that, the accompanying drawing in describing below is only that some of the present invention are real
Execute example, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the level indexing means based on distributing real-time data bank that the present invention provides；
Fig. 2 is the structural representation of the distributing real-time data bank that the present invention provides；
Fig. 3 is the structural representation of the hash index annular list that the present invention provides.
Detailed description of the invention
Structure and advantage for making the present invention are clearer, below in conjunction with accompanying drawing the structure of the present invention made into
One step ground describes.
Embodiment one
The invention provides level indexing means based on distributing real-time data bank, as it is shown in figure 1, described
Level indexing means, including:
Step one, the central control server being arranged in distributing real-time data bank receives what client sent
Data manipulation operation requests, extracts the label point specified in data manipulation operation requests, from the Kazakhstan built in advance
Uncommon index annular list is chosen the relevant meta information of the target data storage server corresponding with label point, will
Relevant meta information sends to client.
Step 2, client receives relevant meta information, extracts target data storage service from relevant meta information
The data to be operated comprising label point are sent to IP ground by the IP address of device and COM1 by COM1
The target data storage server that location is pointed to.
Step 3, target data storage server extracts label point, determines label point according to the title of label point
Hash key assignments, determine that label point structural information is in the label point Hash table built in advance according to Hash key assignments
Target location, obtain belonging to label point in the label point structural information table built in advance according to target location
The position of B+ root vertex.
Step 4, according to the position of index tree root node, in conjunction with the historical time of the data manipulation prestored,
Determine the pointer traveling through next layer index node structure, travel through described B+ tree according to described pointer level
Node, determines inode structures corresponding with data to be operated in B+ tree, data to be operated is mounted to
At inode structures, revise pointer and operate successful message to client feedback data.
In force, owing to the operation of data base to be divided a lot of type, insert behaviour with data in the present embodiment
Illustrate as example.
Level indexing means in the present embodiment based on distributing real-time data bank mainly comprise two category nodes,
First central control server NameServer, (in accompanying drawing 1, center controls clothes to whole system only one of which
Business device NameServer employs the mode of two-node cluster hot backup, and therefore the central control server in Fig. 1 comprises
Master server NameServer Active and standby name server NameServer Standby), mainly store system
System associated metadata, such as each data storage server nodal information, data fragmentation information, accesses and controls letter
Breath etc.；It two is data storage server DataServer, and whole system can have multiple, can substep not
Same computer, it is mainly used in the storage of distributing real-time data bank data.Client Client is to data
Storage and retrieval first to central control server NameServer send request, inquire about real data place
Data storage server, the most again with concrete data storage server DataServer communication, it is achieved number
According to real storage and retrieval.Thus the transmission of real data database data is at client and data storage server
Between carry out.
For ease of understanding the structure of distributed data base, build distributing real-time data bank as shown in Figure 2.
Assume the frame construction drawing such as accompanying drawing 1 of whole distributed real-time database system, including 7 DataServer
With two NameServer, two NameServer use the mode of two-node cluster hot backup to dispose, when system is run,
Only NameServer Active externally provide service；In addition, it is assumed that take the annular space of 32, namely
The numerical space of 0～2^32-1 power.Simultaneously, it is assumed that current system exists 17 TAG points, each TAG
Point deposit position is as shown in Figure 1；TAG point is Hash according to PointName and maps, DataServer
IP according to place machine and externally provide the port numbers of service to be Hash to map, after mapping they
Deployment scenario above Hash ring is as shown in Figure 2.Describe the storage number of the present invention below in conjunction with the accompanying drawings in detail
According to the embodiment with retrieval data.
Step 1, when Client need to certain label TAG point such as P11 insertion data time, Client is first
Sending a request to NameServer, inquiry label point title PointName is the TAG point place of P11
DataServer, NameServer calculate the MD5 of this label point title according to request TAG point title P11
Value, is mapped to annular Hash space by identical hash algorithm by this MD5 value, and by the most square
To (Hash key value augment direction) find DataServer node, find P11 point on DataServer6,
Then NameServer is by DataServer6 relevant meta information (IP address and the port numbers such as DataServer6
Deng) be sent to request Client.
After step 2, Client receive the reply of NameServer, resolve packet, take out P11 point place
The IP address of data storage server DataServer6 and port, then will really need the data inserted to send
To DataServer6.
After step 3, DataServer6 receive the request that Client inserts data, resolve packet, take out TAG
Point PointName is P11, determines that P11 structural information exists by calculating the Hash key assignments Hash value of P11
Position in label point Hash table PointHashTable is j, and counter structure information is label point structural information
PointConfigItem [j] is as shown in Figure 3.
After step 4, DataServer6 determine P11 structural information position in PointHashTable, from
PointConfigItem [j] takes out the root node position RawHist of P11 index B+ tree.
Step 5, DataServer6 are from the beginning of P11 node index B+ root vertex Root, and correction data is grasped
Initial time StartTime and end time EndTime in the historical time made determine next layer of traversal
The pointer Pointer of IndexNode, travels through B+ tree inode structures IndexNode, finally determines request
Back end structure DataNode being actually inserted into or depositing of storage data, by data after overcompression, hangs
It is downloaded to corresponding IndexNode, and revises corresponding pointer.Meanwhile, DataServer6 send back complex information to
Client, returns and inserts data success.So far, whole data insertion process terminates.
When the data operation request according to client distributing real-time data bank is deleted, the operation such as amendment
Time, concrete executive mode is identical with above-mentioned steps, is only in operational order content and to determine pointer
Inode structures concrete operations slightly difference when carrying out carry, the present embodiment no longer to other operate into
Row repeats.
It should be noted that in above-mentioned steps, imply the three layer index sides to distributing real-time data bank
Method, in order to make it easy to understand, be described in detail herein:
Ground floor: determine the data storage server that label point is deposited.During system adds label point,
Client sends to add some points and asks to central control server, and central control server is according to request label point feature
Identification code (as called the roll, put ID) calculates the MD5 value of this label point title, should by identical hash algorithm
MD5 value is mapped to annular hash space, and (Hash key assignments augment direction) finds data in the direction of the clock
Storage server node, first successful node is this label point deposit position；System is inserted data or looks into
When asking data, first send request to central control server, search respective labels point in which data stores
Server.
The second layer: determine that label point data B+ tree indexes deposit position.Inside each data storage server,
Maintain a label point Hash table storing each label point structural information, record notebook data storage service
The dot structure information of all label point that device is safeguarded, label point structural information includes a title, label point ID,
Label point B+ root vertex position etc..After client determines request label point place data storage server,
It transmit a request to the data storage server at label point place, if increasing label point, by label point
Signature identification code (as called the roll, some ID etc.) does Hash will need the label point added to be mapped to label point Hash table
In relevant position；If storage or retrieval data, data storage server is breathed out by calling the roll label
Uncommon, obtain label point information, thus obtain B+ tree index root node position.
Third layer: determine the actual deposit position of the label point data of storage or retrieval.Label point B+ to be determined
Tree index position after, if request be storage or retrieval data, system from the beginning of B+ root vertex,
Contrast the time range of each index node index, determine the pointer traveling through next layer index node, such layer
The search B+ tree index node of secondary property, finally determines being actually inserted into or depositing of request storage or retrieval data
Back end position.
It addition, propose the concept of hash index annular list in step one, also referred to as annular Hash is empty
Between, it is to realize the efficient storage of distributing real-time data bank data and retrieve the concept constructed, passing through
Entity to be mapped is mapped out by certain hash algorithm the Hash key assignments of N position, composition 0～2^N-1 time
The numerical space of side, is connected first for this numerical space (0) tail (2^N-1), constitutes the hash space of annular.
In order to make it easy to understand, the structure flow process of hash index annular list as shown in Figure 3 is:
Step one, central control server obtains the check value of label point title, according to default hash algorithm
Get the Hash key assignments corresponding with check value.
Step 2, central control server gets the Hash key assignments of whole label point, label point is belonged to
The relevant meta information of data storage server and the Hash key assignments of label point are stored in list.
Step 3, is connected the headers and footers of list, obtains hash index circular chart.
Based on the hash index circular chart built, rotate according to default direction and may determine that the index of target closes
System, i.e. in the present embodiment, label roll-call claims the corresponding relation of the data storage server with label point ownership.?
Being limited due to length in the present embodiment, only list the example of seven data storage servers, it is actual
During use, the thousands of even hundreds of thousands of TAG point of storage, DataServer on each DataServer
Quantity also can embody the biggest quantity according to the concrete storage demand difference of user.
Optionally, if the first time data manipulation that data manipulation operation requests is distributing real-time data bank is grasped
When making, distributing real-time data bank is carried out initialization process.
During inserting in data or delete, B+ tree, it is possible that the division of node or merging, also has
Error handling mechanism in storage or retrieving, therefore when inserting data for the first time, needs to initialize B+
Tree index.
Optionally, in hash index annular list, according to choosing the mesh corresponding with label point clockwise
The relevant meta information of mark data storage server.
In force, in order to improve index efficiency, according to the most i.e. in hash index annular list
The relevant meta information of the target data storage server corresponding with label point is chosen in the direction that Hash key assignments increases.
The invention provides level indexing means based on distributing real-time data bank, including obtaining client
Data operation request, extracts the label point in operation requests, determines number of targets in hash index annular list
According to storage server, and then make target data storage server carry out level index in B+ tree, determining
After operating position, carry out data manipulation.By using hash index annular list to can ensure that real-time data base
While data storage and search greater efficiency, due also to each label point to be set up single B+ tree data rope
Draw so that label point index has higher independence, so that each data of distributing real-time data bank are deposited
Between storage server, there is higher fault-tolerant ability.
It should be understood that the level indexing means based on distributing real-time data bank that above-described embodiment provides
Carry out the embodiment of database manipulation, be only used as this level indexing means explanation in actual applications, also may be used
To use in other application scenarios according to actual needs and by above-mentioned level indexing means, it implemented
Journey is similar to above-described embodiment, repeats no more here.
The foregoing is only embodiments of the invention, not in order to limit the present invention, all spirit in the present invention
Within principle, any modification, equivalent substitution and improvement etc. made, should be included in the protection of the present invention
Within the scope of.
Claims (5)
1. level indexing means based on distributing real-time data bank, it is characterised in that described level index side
Method, including:
The central control server being arranged in described distributing real-time data bank receives the data that client sends
Operation operation requests, extracts the label point specified in described data manipulation operation requests, from the Kazakhstan built in advance
Uncommon index annular list is chosen the relevant unit letter of the target data storage server corresponding to described label point
Breath, sends described relevant meta information to described client；
Described client receives described relevant meta information, extracts described target data from described relevant meta information
The IP address of storage server and COM1, will comprise the data to be operated of described label point by described logical
Letter port sends the described target data storage server pointed to described IP address；
Described target data storage server extracts described label point, determines institute according to the title of described label point
State the Hash key assignments of label point, determine that described label point structural information builds in advance according to described Hash key assignments
Label point Hash table in target location, according to described target location build in advance label point structure letter
Breath table obtains the position of B+ root vertex belonging to described label point；
According to the position of described index tree root node, in conjunction with the historical time of the data manipulation prestored, really
Surely the pointer of next layer index node structure is traveled through, according to the joint traveling through described B+ tree of described pointer level
Point, determines inode structures corresponding with described data to be operated in described B+ tree, by described to be operated
Data are mounted at described inode structures, revise described pointer and grasp to described client feedback data
Make successful message；
Wherein, the structure flow process of described hash index annular list is:
Step one, central control server obtains the check value of label point title, according to default hash algorithm
Get the Hash key assignments corresponding with described check value；
Step 2, described central control server gets the Hash key assignments of whole label point, by described label
The relevant meta information of data storage server and the Hash key assignments of described label point of some ownership are stored in list
In；
Step 3, is connected the headers and footers of described list, obtains hash index circular chart.
Level indexing means based on distributing real-time data bank the most according to claim 1, its feature
It is:
If the first time data manipulation behaviour that described data manipulation operation requests is described distributing real-time data bank
When making, described distributing real-time data bank is carried out initialization process.
Level indexing means based on distributing real-time data bank the most according to claim 1, its feature
Being, described relevant meta information includes IP address and the COM1 of described target data storage server.
Level indexing means based on distributing real-time data bank the most according to claim 1, its feature
It is, in described hash index annular list, corresponding with described label point according to choosing clockwise
The relevant meta information of target data storage server.
Level indexing means based on distributing real-time data bank the most according to claim 1, its feature
Being, in described target data storage server, storage has the historical time comprising pointer, data manipulation
In interior B+ tree inode structures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610208956.XA CN105930345A (en) | 2016-04-05 | 2016-04-05 | Hierarchical indexing method based on distributed real-time database system (DRTDBS) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610208956.XA CN105930345A (en) | 2016-04-05 | 2016-04-05 | Hierarchical indexing method based on distributed real-time database system (DRTDBS) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105930345A true CN105930345A (en) | 2016-09-07 |
Family
ID=56840557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610208956.XA Pending CN105930345A (en) | 2016-04-05 | 2016-04-05 | Hierarchical indexing method based on distributed real-time database system (DRTDBS) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105930345A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169055A (en) * | 2017-04-27 | 2017-09-15 | 北京众享比特科技有限公司 | The operating method and operating system of a kind of database table |
| CN108920542A (en) * | 2018-06-13 | 2018-11-30 | 苏州涅瓦信息科技有限公司 | A kind of distributed memory big data processing system and its data processing method |
| CN109767247A (en) * | 2019-01-15 | 2019-05-17 | 武汉费米坊科技有限公司 | A kind of distribution commodity traceability system and source tracing method |
| CN110275838A (en) * | 2018-03-16 | 2019-09-24 | 北京忆芯科技有限公司 | The address conversion and its accelerator of KV storage equipment |
| CN111400266A (en) * | 2019-01-02 | 2020-07-10 | 阿里巴巴集团控股有限公司 | Data processing method and system, and diagnosis processing method and device of operation event |
| CN111581206A (en) * | 2019-03-15 | 2020-08-25 | 北京忆芯科技有限公司 | B + tree operation device and method |
| CN111984691A (en) * | 2020-09-11 | 2020-11-24 | 苏州浪潮智能科技有限公司 | Object metadata retrieval and enumeration method and device in distributed storage system |
| CN117539962A (en) * | 2024-01-09 | 2024-02-09 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
| US12013861B2 (en) | 2020-09-11 | 2024-06-18 | Inspur Suzhou Intelligent Technology Co., Ltd. | Method and apparatus for retrieving and enumerating object metadata in distributed storage system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101997884A (en) * | 2009-08-18 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Distributed storage system and method |
| CN103020078A (en) * | 2011-09-24 | 2013-04-03 | 国家电网公司 | Distributed real-time database data hierarchical indexing method |
-
2016
- 2016-04-05 CN CN201610208956.XA patent/CN105930345A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101997884A (en) * | 2009-08-18 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Distributed storage system and method |
| CN103020078A (en) * | 2011-09-24 | 2013-04-03 | 国家电网公司 | Distributed real-time database data hierarchical indexing method |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169055B (en) * | 2017-04-27 | 2019-10-18 | 北京众享比特科技有限公司 | A kind of operating method and operating system of database table |
| CN107169055A (en) * | 2017-04-27 | 2017-09-15 | 北京众享比特科技有限公司 | The operating method and operating system of a kind of database table |
| CN110275838A (en) * | 2018-03-16 | 2019-09-24 | 北京忆芯科技有限公司 | The address conversion and its accelerator of KV storage equipment |
| CN108920542B (en) * | 2018-06-13 | 2021-07-20 | 苏州涅瓦信息科技有限公司 | Distributed memory big data processing system and data processing method thereof |
| CN108920542A (en) * | 2018-06-13 | 2018-11-30 | 苏州涅瓦信息科技有限公司 | A kind of distributed memory big data processing system and its data processing method |
| CN111400266A (en) * | 2019-01-02 | 2020-07-10 | 阿里巴巴集团控股有限公司 | Data processing method and system, and diagnosis processing method and device of operation event |
| CN111400266B (en) * | 2019-01-02 | 2023-05-02 | 阿里巴巴集团控股有限公司 | Data processing method and system, and diagnosis processing method and device for operation event |
| CN109767247A (en) * | 2019-01-15 | 2019-05-17 | 武汉费米坊科技有限公司 | A kind of distribution commodity traceability system and source tracing method |
| CN111581206A (en) * | 2019-03-15 | 2020-08-25 | 北京忆芯科技有限公司 | B + tree operation device and method |
| CN111984691B (en) * | 2020-09-11 | 2023-01-06 | 苏州浪潮智能科技有限公司 | Object metadata retrieval and enumeration method and device in distributed storage system |
| CN111984691A (en) * | 2020-09-11 | 2020-11-24 | 苏州浪潮智能科技有限公司 | Object metadata retrieval and enumeration method and device in distributed storage system |
| US12013861B2 (en) | 2020-09-11 | 2024-06-18 | Inspur Suzhou Intelligent Technology Co., Ltd. | Method and apparatus for retrieving and enumerating object metadata in distributed storage system |
| CN117539962A (en) * | 2024-01-09 | 2024-02-09 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
| CN117539962B (en) * | 2024-01-09 | 2024-05-14 | 腾讯科技（深圳）有限公司 | Data processing method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930345A (en) | Hierarchical indexing method based on distributed real-time database system (DRTDBS) | |
| CN103020078B (en) | Distributing real-time data bank data hierarchy indexing means | |
| CN103473334B (en) | Data storage method, inquiry method and system | |
| CN104731516B (en) | A kind of method, apparatus and distributed memory system of accessing file | |
| CN103890738B (en) | The system and method for the weight that disappears in storage object after retaining clone and separate operation | |
| CN102779185B (en) | High-availability distribution type full-text index method | |
| CN103150394B (en) | Distributed file system metadata management method facing to high-performance calculation | |
| US7899850B2 (en) | Relational objects for the optimized management of fixed-content storage systems | |
| CN103067461B (en) | A kind of metadata management system of file and metadata management method | |
| CN102708165B (en) | Document handling method in distributed file system and device | |
| CN104539681B (en) | The processing method of distributed GIS acceleration systems and GIS service | |
| CN103067521B (en) | Node in a kind of distributed reptile cluster and system | |
| CN113986873B (en) | Method for processing, storing and sharing data modeling of mass Internet of things | |
| WO2007149701A2 (en) | A method and system for federated resource discovery service in distributed systems | |
| WO2008014062A2 (en) | System and apparatus for optimally trading off the replication overhead and consistency level in distributed applications | |
| CN101673289B (en) | Method and device for constructing distributed file storage framework | |
| CN107800808A (en) | A kind of data-storage system based on Hadoop framework | |
| CN106326239A (en) | Distributed file system and file meta-information management method thereof | |
| CN109542861A (en) | File management method, device and system | |
| CN102378407B (en) | Object name resolution system and method in internet of things | |
| CN104205730B (en) | Network element data access method, Virtual NE, network management server and NMS | |
| WO2020215580A1 (en) | Distributed global data deduplication method and device | |
| CN110502472A (en) | A kind of the cloud storage optimization method and its system of large amount of small documents | |
| CN107704475A (en) | Multilayer distributed unstructured data storage method, querying method and device | |
| CN101719155B (en) | Method of multidimensional attribute range inquiry for supporting distributed multi-cluster computing environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160907 |
|
| RJ01 | Rejection of invention patent application after publication |