CN102467572A - Data block query method supporting repeated data deletion procedure - Google Patents

Data block query method supporting repeated data deletion procedure Download PDF

Info

Publication number
CN102467572A
CN102467572A CN2010105761462A CN201010576146A CN102467572A CN 102467572 A CN102467572 A CN 102467572A CN 2010105761462 A CN2010105761462 A CN 2010105761462A CN 201010576146 A CN201010576146 A CN 201010576146A CN 102467572 A CN102467572 A CN 102467572A
Authority
CN
China
Prior art keywords
hash
hash value
index list
client
server
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2010105761462A
Other languages
Chinese (zh)
Other versions
CN102467572B (en
Inventor
刘威
王云松
陈志丰
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.)
Shenzhen Excellent Clothing Co Ltd
Original Assignee
Inventec Corp
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 Inventec Corp filed Critical Inventec Corp
Priority to CN 201010576146 priority Critical patent/CN102467572B/en
Publication of CN102467572A publication Critical patent/CN102467572A/en
Application granted granted Critical
Publication of CN102467572B publication Critical patent/CN102467572B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

A data block query method supporting a repeating data deleting procedure improves the speed of the repeating data deleting procedure for querying data blocks. The query method comprises the following steps: storing a hash index list in a server; generating a data block and a hash value according to an input file in a client; the client sends a query request to the server, and the hash value of the corresponding data block is recorded in the query request; when the hash value is not stored in the server, the server sends a storage requirement to the client, and adds the received hash value into a hash index list; establishing a corresponding associated data index list for the hash index list, and recording information of data blocks related to the hash values in the associated data index list; and when the hash value is stored in the server, returning the hash value in the corresponding associated data index list to the client according to the hash value.

Description

Support the block querying method of data de-duplication program
Technical field
The present invention relates to a kind of querying method of block, particularly a kind of block querying method of supporting the data de-duplication program.
Background technology
Data de-duplication is a kind of data reduction technology, is generally used for the standby system based on disk, and fundamental purpose is to reduce the memory capacity of using in the storage system.Its working method is in certain time cycle, to search the repeating data piece of the variable-size of diverse location in the different files.The data block that repeats replaces with designator.Owing to always be flooded with a large amount of redundant datas in the storage system.In order to address this problem, space more than the saving, " repeating deletion " technology has become focus of people's concerns just naturally.Adopting " repeating deletion " technology can be original 1/20 with the data reduction of storage; Thereby the backup space more than abdicating; Not only can make the Backup Data on the storage system preserve the also long time, but also required a large amount of bandwidth can practice thrift offline storage the time.
For reaching the purpose that data integrity is preserved, so in the process of carrying out data de-duplication, can carry out the processing of cutting to input file.Input file can produce a plurality of block after handling through cutting.For effective management data block, so in the process of carrying out cutting, can utilize index file to write down each item canned data of all block.
Client produces the corresponding cryptographic hash of block after whole input file has been carried out cutting processing (fixed length or elongated) immediately.Client is sent query requests to service end subsequently, uses cryptographic hash whether to have identical cryptographic hash to the service end query.Service end can be searched in the hash index table each query requests, returns Query Result through network then.Please refer to shown in Figure 1ly, it is the synoptic diagram of the data query block of prior art.
When the data volume of client 110 inquiry is very big; The hash index table also can increase severely thereupon; Service end 120 low memories might appear to deposit the hash index table; Like this hash index table will relate to from the slow memory device of file access and inquire about, and will drag the travelling speed of slow total system greatly.
Summary of the invention
In view of above problem; Technical matters to be solved by this invention is to provide a kind of block querying method of supporting the data de-duplication program; Be applied in many data blocks that produced through the data de-duplication program; And the processing that the data block is inquired about, and then improve the inquiry velocity of block.
For achieving the above object, the block querying method of the support data de-duplication program that the present invention disclosed may further comprise the steps: in service end, store the hash index tabulation, the many groups of record cryptographic hash in the hash index tabulation; Load input file in the client, and produce the block of corresponding input file and the cryptographic hash of corresponding each block; Client is sent query requests to service end, and whether the cryptographic hash of record corresponding data block in query requests is in order to have identical cryptographic hash to the service end inquiry; In the hash index tabulation of service end, do not store cryptographic hash; Then service end is sent storage request to client; Store in the service end in order to the corresponding block of cryptographic hash institute is sent to, and service end adds received cryptographic hash in the hash index tabulation in regular turn; Cryptographic hash in the hash index tabulation is set up corresponding associated data index, and other cryptographic hash that the record cryptographic hash is correlated with in the associated data index; In service end, store cryptographic hash, then service end returns to client according to cryptographic hash with the cryptographic hash in the corresponding associated data index in the lump; During the cryptographic hash of data query block, whether client has existed cryptographic hash from the associated data index inquiry that is received to client next time; In the associated data index that client received, there has been cryptographic hash; Then by the descriptor that obtains cryptographic hash information or cryptographic hash relevant data block in the associated data index; For example this data block number of times that has been cited can increase according to quoting needs; In the associated data index that client received, do not have cryptographic hash, then client is carried out the inquiry of cryptographic hash to service end.
Because the associated data index can show the relevance (forward-backward correlation) of block, and in use service end can constantly adjustment should the tabulation of couplet data directory according to statistical information.So can guarantee the hit rate that client is inquired about to a certain extent in local internal memory.Service end can use the cost of once visiting memory device at a slow speed to obtain a large amount of relative recordings, has significantly reduced client like this and has carried out query requests repeatedly and cause that service end constantly reads the problem of inquiry at memory device at a slow speed.Simultaneously the single pass network sends the data directory collection and has also reduced in the network request/affirmation back and forth and carried out the consuming time of network access.
Describe the present invention below in conjunction with accompanying drawing and specific embodiment, but not as to qualification of the present invention.
Description of drawings
Fig. 1 is the synoptic diagram of the data query block of prior art;
Fig. 2 is a configuration diagram of the present invention;
Fig. 3 is an operation workflow synoptic diagram of the present invention;
Fig. 4 is the synoptic diagram of record related data indexed set of the present invention.
Wherein, Reference numeral
110 clients
120 service ends
210 service ends
The tabulation of 211 hash indexs
212 associated data index
220 clients
Embodiment
Below in conjunction with accompanying drawing structural principle of the present invention and principle of work are done concrete description:
Please refer to shown in Figure 2ly, it is a configuration diagram of the present invention.The present invention includes service end 210 and client 220.Client 220 can be connected in service end 210 through the mode of the Internet (Internet) or corporate intranet (intranet); Can client 220 and service end 210 be run on simultaneously also that service end 210 also comprises hash index tabulation 211 on same the calculator device, the many groups of hash index tabulation 211 records cryptographic hash.During the search request of client 220 a certain block cryptographic hash in service end 210 is sent an input file, content that service end 210 is put down in writing according to hash index tabulation 211 and the action of inquiring about through following manner.Please refer to shown in Figure 3ly, it is an operation workflow synoptic diagram of the present invention.
Step S310: in service end, store the hash index tabulation, the many groups of record cryptographic hash in the hash index tabulation;
Step S320: client loads input file, and produces the block of corresponding input file and the cryptographic hash of corresponding each block;
Step S330: client is sent query requests to service end, and whether the cryptographic hash of record corresponding data block in query requests is in order to have identical cryptographic hash to the service end inquiry;
Step S340: in the hash index tabulation of service end, do not store cryptographic hash; Then service end is sent storage request to client; Store in the service end in order to the corresponding block of cryptographic hash institute is sent to, and service end adds received cryptographic hash in the hash index tabulation in regular turn;
Step S350: the cryptographic hash in the hash index tabulation is set up corresponding associated data index, and other cryptographic hash that the record cryptographic hash is correlated with in the associated data index; And
Step S360: in service end, store cryptographic hash, then service end returns to client according to cryptographic hash with the cryptographic hash in the corresponding associated data index in the lump.
By loading input file in the client 220,220 pairs of input files of client carry out cutting to be handled, and produces the block of corresponding input file and the cryptographic hash of corresponding each block.The algorithm that cryptographic hash is calculated can be but be not limited to SHA-1 or MD5.And block be according to regular length mode (fixed-size partition) or content-based elongated degree partitioning scheme (content-defined chunking, CDC).The block size that fixed length cutting algorithm use defines is in advance carried out cutting to input file.The advantage of fixed length block algorithm be simple, performance is high.Content-defined cutting algorithm is a kind of elongated block algorithm, the partition strategy that its employing fingerprint data (like the Rabin fingerprint) become length to differ in size file division.Different with fixed length cutting algorithm, content-defined cutting algorithm is based on file content and carries out the block cutting, so the block size is transformable.
Then, client 220 is sent query requests to service end 210, and whether the cryptographic hash of record corresponding data block in query requests is in order to have identical cryptographic hash to service end 210 inquiries.In the hash index tabulation 211 of service end 210, do not store cryptographic hash; Then service end 210 is sent storage request to client 220; Store in order to the corresponding block of cryptographic hash institute is sent in the service end 210, and service end 210 adds received cryptographic hash in the hash index tabulation 211 in regular turn.And the cryptographic hash in the hash index tabulation 211 set up corresponding associated data index 212, and the information of the block that the record cryptographic hash is relevant in associated data index 212.For instance, the cryptographic hash that can the storage data block in associated data index 212 or the number value of block, also or the index information of block memory location.
Suppose the processing spec inquired about from first block of input file, and service end 210 was not noted down arbitrary block of input file.Client 220 at first converts first block of input file into the first cryptographic hash hash1 (corresponding to the first cryptographic hash hash1), and the first cryptographic hash hash1 is proposed query requests to service end 210.Owing to do not store the cryptographic hash of any block of input file in the service end 210, so service end 210 is written to service end 210 with the received first cryptographic hash hash1 (first block).In like manner, second block (corresponding to the second cryptographic hash hash2) is when still being written to service end 210 according to top process.Service end 210 judges that according to the context of two data blocks the first cryptographic hash hash1 and the second cryptographic hash hash2 have relevance.Service end 210 is put into the second cryptographic hash hash2 associated data index 212 of the first cryptographic hash hash1.Please refer to shown in Figure 4ly, it is the synoptic diagram of record related data indexed set of the present invention.
Cryptographic hash for other block also is written to the associated data index 212 of the first cryptographic hash hash1 according to it in proper order.The amount of capacity of associated data index 212 has certain limitation in the present invention.When the quantity of the cryptographic hash in the associated data index 212 meets threshold value; Service end 210 is proceeded to deposit the processing of cryptographic hash except meeting in next associated data index 212; Also can this cryptographic hash of up-to-date inquiry be recorded in this associated data index 212 deleting from associated data index 212 through cryptographic hash at most after the inquiry.
For instance; If the max cap. of associated data index 212 is 10 groups of cryptographic hash of record, then the relative index of first cryptographic hash hash1 record is the second cryptographic hash hash2～the 11 cryptographic hash hash11 (in other words being exactly continuous ten data blocks after first block).
After the 12 cryptographic hash hash12 produced, service end 210 can leave the 12 cryptographic hash hash12 in the associated data index 212 of the 11 cryptographic hash hash11 in.In addition, if a certain group of cryptographic hash all exists when related with other cryptographic hash simultaneously, can adopt according to correlation properties and leave in the associated data index 212 of which cryptographic hash.Or take place all to preserve in the relevant associated data index 212 all a.
The above situation is not store the cryptographic hash that can be queried in the service end 210.In service end 210, store cryptographic hash, then service end 210 returns to client 220 according to cryptographic hash with the cryptographic hash in the corresponding associated data index 212 in the lump.Accept example.When client 220 desires are inquired about the 5th block (meaning is promptly inquired about the 5th cryptographic hash hash5), because the 5th cryptographic hash hash5 is sorted in the corresponding associated data index 212 of first cryptographic hash hash1 institute in the service end 210.So service end 210 is except returning to the 5th cryptographic hash hash5 that is inquired the client 220, service end 210 also can send the associated data index 212 of the first cryptographic hash hash1 to client 220 simultaneously in the lump.
Client 220 is after receiving the associated data concordance list, and client 220 is stored in the associated data concordance list in the internal memory.Make client 220 when the cryptographic hash of data query block next time, client 220 can begin to inquire about earlier the cryptographic hash that has had the desire inquiry whether from the associated data index 212 that is received.In the associated data index 212 that client 220 is received, there has been cryptographic hash, then by obtaining cryptographic hash in the associated data index 212.By the block of being inquired about possibly is continuously, therefore can reduce the access time of client 220 and 210 of service ends effectively through associated data index 212, and then the efficient of raising access.Otherwise, in the associated data index 212 that client 220 is received, there is not cryptographic hash, then client 220 is carried out the cryptographic hash query processing of step S330～step S360 again to service end 210.
Because associated data index 212 can show the relevance (meaning i.e. the association of front and back order) of block, and in use service end 210 can constantly be adjusted associated data index 212 according to statistical information.So can guarantee the hit rate that client 220 is inquired about to a certain extent in local internal memory.Service end 210 can use the cost of once visiting memory device at a slow speed to obtain a large amount of relative recordings, has significantly reduced client 220 like this and has carried out query requests repeatedly and cause that service end 210 constantly reads the problem of inquiry at memory device at a slow speed.Simultaneously the single pass network sends the data directory collection and has also reduced in the network request/affirmation back and forth and carried out the consuming time of network access.
Certainly; The present invention also can have other various embodiments; Under the situation that does not deviate from spirit of the present invention and essence thereof; Those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the present invention.

Claims (4)

1.一种支持重复数据删除程序的数据区块查询方法，应用在经过一重复数据删除程序所产生的多笔数据区块，并对该数据区块进行查询的处理，其特征在于，该支持重复数据删除程序的数据区块查询方法包括以下步骤：1. A data block query method that supports a deduplication program is applied to a plurality of data blocks generated by a deduplication program, and the processing of querying the data blocks is characterized in that the support The data block query method of the deduplication program includes the following steps: 在一服务端中储存一哈希索引列表，在该哈希索引列表中记录多组哈希值；storing a hash index list in a server, and recording multiple sets of hash values in the hash index list; 一客户端加载一输入文件，并产生相应该输入文件的该些数据区块与相应每一该数据区块的该哈希值；A client loads an input file, and generates the data blocks corresponding to the input file and the hash value corresponding to each of the data blocks; 该客户端向该服务端发送一查询请求，在该查询请求中记录相应该些数据区块的该哈希值，用以向该服务端查询是否存在有相同的该哈希值；The client sends a query request to the server, records the hash values of the corresponding data blocks in the query request, and inquires from the server whether there is the same hash value; 当该服务端的该哈希索引列表中未储存该哈希值，则该服务端向该客户端发送一储存要求，用以将该哈希值所相应的该数据区块传送至该服务端中储存，并且该服务端将所接收到的该哈希值依序加入该哈希索引列表中；When the hash value is not stored in the hash index list of the server, the server sends a storage request to the client to transmit the data block corresponding to the hash value to the server storage, and the server sequentially adds the received hash value to the hash index list; 对该哈希索引列表中的该哈希值建立相应的一关联数据索引列表，并在该关联数据索引列表中记录该哈希值相关的其它该些哈希值；Establishing a corresponding associated data index list for the hash value in the hash index list, and recording other hash values related to the hash value in the associated data index list; 当该服务端中储存该哈希值，则该服务端根据该哈希值将相应的该关联数据索引列表中的该些哈希值一并返回给该客户端；When the hash value is stored in the server, the server returns the hash values corresponding to the associated data index list to the client according to the hash value; 该客户端下一次查询该数据区块的该哈希值时，该客户端从所接收的该关联数据索引列表查询是否已存在该哈希值；When the client queries the hash value of the data block next time, the client queries whether the hash value already exists from the received associated data index list; 当该客户端所接收的该关联数据索引列表中已存在该哈希值，则由该关联数据索引列表中取得该哈希值；以及When the hash value already exists in the associated data index list received by the client, the hash value is obtained from the associated data index list; and 当该客户端所接收的该关联数据索引列表中不存在该哈希值，则该客户端向该服务端进行该哈希值的查询。When the hash value does not exist in the associated data index list received by the client, the client queries the server for the hash value. 2.根据权利要求1所述的支持重复数据删除程序的数据区块查询方法，其特征在于，产生的该些数据区块根据一固定长度方式或一基于内容变长度分割方式。2 . The data block query method supporting deduplication program according to claim 1 , wherein the data blocks are generated according to a fixed-length method or a content-based variable-length segmentation method. 3 . 3.根据权利要求1所述的支持重复数据删除程序的数据区块查询方法，其特征在于，该关联数据索引列表中的该些哈希值的数量符合一门坎值时，则将查询后经过最久的该哈希值从该关联数据索引列表中删除，将最新查询的该哈希值记录在该关联数据索引列表中。3. The data block query method supporting de-duplication program according to claim 1, characterized in that, when the number of the hash values in the associated data index list meets a threshold value, the query process The oldest hash value is deleted from the associated data index list, and the latest queried hash value is recorded in the associated data index list. 4.根据权利要求1所述的支持重复数据删除程序的数据区块查询方法，其特征在于，该关联数据索引列表中的该些哈希值的数量符合一门坎值时，则该服务端会向下一该关联数据索引列表中继续进行存放该哈希值的处理。4. The data block query method supporting de-duplication program according to claim 1, characterized in that, when the number of the hash values in the associated data index list meets a threshold value, the server will Continue to store the hash value in the next associated data index list.
CN 201010576146 2010-11-17 2010-11-17 Data block query methods that support deduplicators Expired - Fee Related CN102467572B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201010576146 CN102467572B (en) 2010-11-17 2010-11-17 Data block query methods that support deduplicators

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201010576146 CN102467572B (en) 2010-11-17 2010-11-17 Data block query methods that support deduplicators

Publications (2)

Publication Number Publication Date
CN102467572A true CN102467572A (en) 2012-05-23
CN102467572B CN102467572B (en) 2013-10-02

Family

ID=46071215

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201010576146 Expired - Fee Related CN102467572B (en) 2010-11-17 2010-11-17 Data block query methods that support deduplicators

Country Status (1)

Country Link
CN (1) CN102467572B (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915278A (en) * 2012-09-19 2013-02-06 浪潮(北京)电子信息产业有限公司 Data deduplication method
CN102930004A (en) * 2012-10-29 2013-02-13 华为技术有限公司 Hash value storage method, device and chip
CN102968507A (en) * 2012-12-14 2013-03-13 中国银行股份有限公司 Cache table based data query method
CN103473298A (en) * 2013-09-04 2013-12-25 华为技术有限公司 Data archiving method and device and storage system
WO2014067063A1 (en) * 2012-10-30 2014-05-08 华为技术有限公司 Duplicate data retrieval method and device
CN105706041A (en) * 2013-10-16 2016-06-22 网络装置公司 Technique for global deduplication across datacenters with minimal coordination
CN105917304A (en) * 2014-12-09 2016-08-31 华为技术有限公司 Apparatus and method for de-duplication of data
CN106815260A (en) * 2015-12-01 2017-06-09 阿里巴巴集团控股有限公司 A kind of index establishing method and equipment
WO2018165963A1 (en) * 2017-03-17 2018-09-20 深圳市秀趣品牌文化传播有限公司 E-commerce data redundancy processing system and method
CN109902086A (en) * 2019-01-31 2019-06-18 阿里巴巴集团控股有限公司 A kind of index creation method, device and equipment
CN110008249A (en) * 2019-01-31 2019-07-12 阿里巴巴集团控股有限公司 A kind of time-based data query method, device and equipment
CN112817920A (en) * 2021-03-03 2021-05-18 深圳市知小兵科技有限公司 Distributed big data cleaning method
CN114647658A (en) * 2022-03-30 2022-06-21 新华三信息技术有限公司 Data retrieval method, device, equipment and machine-readable storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006215735A (en) * 2005-02-02 2006-08-17 Mitsubishi Electric Corp Duplicate website detection device
CN101706825A (en) * 2009-12-10 2010-05-12 华中科技大学 Replicated data deleting method based on file content types

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006215735A (en) * 2005-02-02 2006-08-17 Mitsubishi Electric Corp Duplicate website detection device
CN101706825A (en) * 2009-12-10 2010-05-12 华中科技大学 Replicated data deleting method based on file content types

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915278A (en) * 2012-09-19 2013-02-06 浪潮(北京)电子信息产业有限公司 Data deduplication method
CN102930004A (en) * 2012-10-29 2013-02-13 华为技术有限公司 Hash value storage method, device and chip
CN102930004B (en) * 2012-10-29 2015-07-08 华为技术有限公司 Hash value storage method, device and chip
WO2014067063A1 (en) * 2012-10-30 2014-05-08 华为技术有限公司 Duplicate data retrieval method and device
CN102968507A (en) * 2012-12-14 2013-03-13 中国银行股份有限公司 Cache table based data query method
CN103473298B (en) * 2013-09-04 2017-01-11 华为技术有限公司 Data archiving method and device and storage system
CN103473298A (en) * 2013-09-04 2013-12-25 华为技术有限公司 Data archiving method and device and storage system
CN105706041A (en) * 2013-10-16 2016-06-22 网络装置公司 Technique for global deduplication across datacenters with minimal coordination
US11775503B2 (en) 2013-10-16 2023-10-03 Netapp, Inc. Technique for global deduplication across datacenters with minimal coordination
US11301455B2 (en) 2013-10-16 2022-04-12 Netapp, Inc. Technique for global deduplication across datacenters with minimal coordination
CN105706041B (en) * 2013-10-16 2019-07-19 Netapp股份有限公司 Techniques for global deduplication between data centers with minimal collaboration
US10685013B2 (en) 2013-10-16 2020-06-16 Netapp Inc. Technique for global deduplication across datacenters with minimal coordination
CN105917304A (en) * 2014-12-09 2016-08-31 华为技术有限公司 Apparatus and method for de-duplication of data
CN106815260B (en) * 2015-12-01 2021-05-04 阿里巴巴集团控股有限公司 Index establishing method and equipment
CN106815260A (en) * 2015-12-01 2017-06-09 阿里巴巴集团控股有限公司 A kind of index establishing method and equipment
WO2018165963A1 (en) * 2017-03-17 2018-09-20 深圳市秀趣品牌文化传播有限公司 E-commerce data redundancy processing system and method
CN110008249A (en) * 2019-01-31 2019-07-12 阿里巴巴集团控股有限公司 A kind of time-based data query method, device and equipment
CN109902086A (en) * 2019-01-31 2019-06-18 阿里巴巴集团控股有限公司 A kind of index creation method, device and equipment
CN109902086B (en) * 2019-01-31 2022-12-20 创新先进技术有限公司 Index creation method, device and equipment
CN110008249B (en) * 2019-01-31 2023-08-08 创新先进技术有限公司 Time-based data query method, device and equipment
CN112817920A (en) * 2021-03-03 2021-05-18 深圳市知小兵科技有限公司 Distributed big data cleaning method
CN114647658A (en) * 2022-03-30 2022-06-21 新华三信息技术有限公司 Data retrieval method, device, equipment and machine-readable storage medium

Also Published As

Publication number Publication date
CN102467572B (en) 2013-10-02

Similar Documents

Publication Publication Date Title
CN102467572A (en) Data block query method supporting repeated data deletion procedure
CN101963982B (en) Method for managing metadata of redundancy deletion and storage system based on location sensitive Hash
US8271462B2 (en) Method for creating a index of the data blocks
CN102364474B (en) Metadata storage system for cluster file system and metadata management method
KR102564170B1 (en) Method and device for storing data object, and computer readable storage medium having a computer program using the same
CN101504670A (en) Data operation method, system, client terminal and data server
JP6050503B2 (en) Mail indexing and retrieval using a hierarchical cache
CN102456059A (en) Data de-duplication processing system
WO2013152678A1 (en) Method and device for metadata query
CN113626431A (en) LSM tree-based key value separation storage method and system for delaying garbage recovery
CN105094695B (en) A kind of storage method and system
CN102662992A (en) Method and device for storing and accessing massive small files
CN104881481A (en) Method and device for accessing mass time sequence data
CN104092670A (en) Method for utilizing network cache server to process files and device for processing cache files
CN102999605A (en) Method and device for optimizing data placement to reduce data fragments
CN110888837A (en) Object storage small file merging method and device
CN103744913A (en) Database retrieval method based on search engine technology
CN110532201A (en) A kind of metadata processing method and device
CN103605778A (en) Method, device and system for locating video file
CN104462388B (en) A kind of redundant data method for cleaning based on tandem type storage medium
CN102467458B (en) Create an index method for data blocks
CN107066503A (en) The method and device of magnanimity metadata burst distribution
CN114356878A (en) Distributed storage method and device for unstructured data
CN106066818A (en) A kind of data layout's method improving data de-duplication standby system restorability
CN102467523A (en) Method for establishing index file and method for querying data block by using index file

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20160919

Address after: 518000, JINGWAH Road, road, Futian District, Guangdong, Shenzhen Province, room 605

Patentee after: Shenzhen excellent Clothing Co., Ltd.

Address before: Taipei City, Taiwan, China

Patentee before: Inventec Corporation

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: 20131002

Termination date: 20201117