CN107391761A - A kind of data managing method and device based on data de-duplication technology - Google Patents
A kind of data managing method and device based on data de-duplication technology Download PDFInfo
- Publication number
- CN107391761A CN107391761A CN201710750609.4A CN201710750609A CN107391761A CN 107391761 A CN107391761 A CN 107391761A CN 201710750609 A CN201710750609 A CN 201710750609A CN 107391761 A CN107391761 A CN 107391761A
- Authority
- CN
- China
- Prior art keywords
- data
- metadata information
- deposit
- fingerprint value
- length
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/174—Redundancy elimination performed by the file system
- G06F16/1748—De-duplication implemented within the file system, e.g. based on file segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0608—Saving storage space on storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/064—Management of blocks
- G06F3/0641—De-duplication techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of data managing method and device based on data de-duplication technology, methods described calculates the fingerprint value of target data by HASH algorithms；And storage location corresponding to the fingerprint value for determining target data is mapped by CRUSH；And then using target data as deposit data is treated, judgement treats whether have data in the storage location of deposit data；If having, the reference count for treating deposit data is just added one；If not having, just deposit data is treated in storage, and the reference count for treating deposit data is put into one, finally stores the first metadata information for treating deposit data.So during data storage is carried out, the multiple storage of data is avoided, improves operating efficiency；Meanwhile based on duplicate data technology, the management of data is realized, has saved cost, extends the life-span of storage system.A kind of data administrator based on data de-duplication technology provided in an embodiment of the present invention, similarly with above-mentioned technique effect.
Description
Technical field
The present invention relates to cloud computation data center technical field, and data de-duplication is based on more specifically to one kind
The data managing method and device of technology.
Background technology
With the fast development of computer technology and internet industry, data message is increasing, in order to save storage
Space, realizes resource-sharing, and distributed memory system arises at the historic moment.Distributed memory system disperses data to be stored in more independences for Taiwan
In vertical equipment, using expansible system architecture, storage load is shared using more storage servers, utilizes location server
Storage information is positioned, the reliability, availability and the efficiency of management of system can be improved, be also easy to extend.
But because numerous terminals can access storage server, wherein certainly existing a large amount of duplicate data, occupancy is deposited
Space is stored up, now the data de-duplication technology of optimized storage capacity solves this problem.Data de-duplication technology passes through
Eliminate the data repeated in storage system, the data of actual storage or the data by network transmission in reduction system, backup,
Long term archival and data disaster recovery etc. are widely used.And in field of distributed storage, deposited to reduce
Unit capacity cost is stored up, the processing of online duplicate data is extremely urgent.
Therefore, how in field of distributed storage, duplicate data technology is realized, i.e., is being distributed using duplicate data technology
In formula field of storage, the storage, reading and deletion action of data are realized, is that those skilled in the art need to solve the problems, such as.
The content of the invention
It is an object of the invention to provide a kind of data managing method and device based on data de-duplication technology, with reality
In present field of distributed storage, storage, reading and the deletion action of data are carried out based on duplicate data technology.
To achieve the above object, the embodiments of the invention provide following technical scheme：
A kind of data managing method based on data de-duplication technology, including：
S11, the fingerprint value by HASH algorithms calculating target data；
S12, pass through CRUSH mapping determinations storage location corresponding with the fingerprint value of the target data；By the target
Data are used as and treat deposit data, and perform S13；
S13, judge whether have data in storage location corresponding with treating deposit data；If so, then perform S14；If it is not, then
Perform S15；
S14, reference count corresponding with treating deposit data added one, and perform S16；
It S15, will treat that deposit data is stored to storage location corresponding with treating deposit data, and corresponding with treating deposit data will quote
Counting puts one, and performs S16；
S16, storage treat the first metadata information of deposit data, and first metadata information includes：Treat the finger of deposit data
Line value.
Wherein, before performing the S11, in addition to：
S21, judge whether the second metadata information corresponding with the target data；If so, then perform S22；If
It is no, then perform S11；
S22, obtain second metadata information；
S23, judge to whether there is fingerprint value in second metadata information；If so, then perform S24；If it is not, then perform
S11；
The length of target data described in S24, comparison and default data length；If the length of the target data is equal to institute
Default data length is stated, then performs S11；If the length of the target data is less than the default data length, perform
S25；
S25, the target data and data corresponding with second metadata information spliced, spliced
Data, and the fingerprint value of the splicing data is calculated, and perform S26；
S26, determination storage location corresponding with the fingerprint value of the splicing data is mapped by CRUSH；By the splicing
Data are used as and treat deposit data, and perform S13.
Wherein, if the length of the target data is equal to the default data length, including：
It is if the length of the target data is equal to the default data length, second metadata information is corresponding
The reference counts of data subtract one；
Whether the reference count for judging data corresponding to second metadata information is zero；
If so, then delete data corresponding to second metadata information.
Wherein, it is described to be spliced the target data and data corresponding with second metadata information, obtain
To splicing data, and the fingerprint value of the splicing data is calculated, including：
Obtain data content corresponding with second metadata information；
According to the default data length and data offset, by the target data and with the binary number
It is believed that data corresponding to breath are spliced, obtain splicing data；
Calculate the fingerprint value of the splicing data；
The reference count of data corresponding to second metadata information is subtracted one；
Whether the reference count for judging data corresponding to second metadata information is zero；
If so, then delete data corresponding to second metadata information.
Wherein, in addition to：
Receive the removal request that client is sent；
Data to be deleted are determined according to the removal request, and the trinary data information of data to be deleted described in obtaining and described
The fingerprint value of data to be deleted in trinary data information；
Storage location corresponding with the fingerprint value of the data to be deleted is determined by CRUSH mappings, and will wait to delete with described
Reference count subtracts one corresponding to data；
Judge whether reference count corresponding with the data to be deleted is zero；
If so, data to be deleted and the trinary data information described in then deleting.
A kind of data administrator based on data de-duplication technology, including：
First computing module, for calculating the fingerprint value of target data by HASH algorithms；
First determining module, for storing position by the way that CRUSH mapping determinations are corresponding with the fingerprint value of the target data
Put, using the target data as treating deposit data；
First judge module, for judging whether have data in storage location corresponding with treating deposit data；
First execution module, for when with when having data in the corresponding storage location of deposit data, will be with treating deposit data
Corresponding reference count adds one；
First memory module, for when with when not having data in the corresponding storage location of deposit data, deposit data will be treated
Store to storage location corresponding with treating deposit data, and reference count corresponding with treating deposit data is put one；
Second memory module, the first metadata information of deposit data is treated for storing, and first metadata information includes：
Treat the fingerprint value of deposit data.
Wherein, in addition to：
Second judge module, for judging whether the second metadata information corresponding with the target data；If no
In the presence of then triggering first computing module；
First acquisition module, for when the second metadata information corresponding with the target data be present, described in acquisition
Second metadata information；
3rd judge module, for judging to whether there is fingerprint value in second metadata information；If being not present, touch
Send out the first computing module described；
Comparison module, for when fingerprint value be present in second metadata information, the length of the target data
Degree and default data length；If the length of the target data is equal to the default data length, described first is triggered
Computing module；
Concatenation module, for when the length of the target data is less than the default data length, by the target
Data and data corresponding with second metadata information are spliced, and obtain splicing data, and calculate the splicing number
According to fingerprint value；
Second determining module, for being mapped by CRUSH, determination is corresponding with the fingerprint value of the splicing data to store position
Put.
Wherein, the comparison module includes：
First execution unit, described in when the length of the target data is equal to the default data length, inciting somebody to action
The reference count of data subtracts one corresponding to second metadata information；
First judging unit, for judging whether the reference count of data corresponding to second metadata information is zero；
First deletes unit, for when the reference count of data corresponding to second metadata information is zero, deleting
Data corresponding to second metadata information.
Wherein, the concatenation module includes：
Acquiring unit, for obtaining data content corresponding with second metadata information；
Concatenation unit, for according to the default data length and data offset, by the target data and
Data corresponding with second metadata information are spliced, and obtain splicing data；
Computing unit, for calculating the fingerprint value of the splicing data；
Second execution unit, for subtracting one by the reference count of data corresponding to second metadata information；
Second judging unit, for judging whether the reference count of data corresponding to second metadata information is zero；
Second deletes unit, for when the reference count of data corresponding to second metadata information is zero, deleting
Data corresponding to second metadata information.
Wherein, in addition to：
Receiving module, for receiving the removal request of client transmission；
Second acquisition module, for determining data to be deleted according to the removal request, and the of data to be deleted described in obtaining
The fingerprint value of trinary data information and the data to be deleted in the trinary data information；
3rd determining module, for storing position by the way that CRUSH mapping determinations are corresponding with the fingerprint value of the data to be deleted
Put, and reference count corresponding with the data to be deleted is subtracted one；
4th judge module, for judging whether reference count corresponding with the data to be deleted is zero；
Removing module, for when with described when it is zero to delete the corresponding reference count of data, data to be deleted described in deletion and
The trinary data information.
By above scheme, a kind of data management based on data de-duplication technology provided in an embodiment of the present invention
Method, including：
S11, the fingerprint value by HASH algorithms calculating target data；
S12, pass through CRUSH mapping determinations storage location corresponding with the fingerprint value of the target data；By the target
Data are used as and treat deposit data, and perform S13；
S13, judge whether have data in storage location corresponding with treating deposit data；If so, then perform S14；If it is not, then
Perform S15；
S14, reference count corresponding with treating deposit data added one, and perform S16；
It S15, will treat that deposit data is stored to storage location corresponding with treating deposit data, and corresponding with treating deposit data will quote
Counting puts one, and performs S16；
S16, storage treat the first metadata information of deposit data, and first metadata information includes：Treat the finger of deposit data
Line value.
It can be seen that the above method calculates the fingerprint value of target data by HASH algorithms；And determination and institute are mapped by CRUSH
State storage location corresponding to the fingerprint value of target data；Wherein, fingerprint value determines the uniqueness of target data, and then determines
The uniqueness of destination data storage location；And then using the target data as deposit data is treated, judge with treating that deposit data is corresponding
Whether there are data in storage location；Due to treating that deposit data has unique storage location, if so having been deposited in storage location
There are data, then show to treat that deposit data is stored, just no longer deposit data is treated in storage, but corresponding with treating deposit data will quote meter
Number plus one；If there not being data in storage location, show to treat that deposit data does not store, just will treat deposit data store to number to be deposited
One is put according to corresponding storage location, and by reference count corresponding with treating deposit data, will finally treat the first metadata of deposit data
Information stores, and first metadata information includes：Treat the fingerprint value of deposit data.Thus by the above method, data are being carried out
During storage, the multiple storage of data was both avoided, has improved operating efficiency again, has saved the memory space of system；Together
When, based on duplicate data technology, the management of data is realized in field of distributed storage, has saved cost, extend storage
System lifetim.
Correspondingly, a kind of data administrator based on data de-duplication technology provided in an embodiment of the present invention, also together
Sample has above-mentioned technique effect.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of data managing method flow chart based on data de-duplication technology disclosed in the embodiment of the present invention；
Fig. 2 is data managing method flow of the another kind disclosed in the embodiment of the present invention based on data de-duplication technology
Figure；
Fig. 3 is the data deletion side in a kind of data managing method based on data de-duplication technology of the embodiment of the present invention
Method flow chart；
Fig. 4 is a kind of data administrator schematic diagram based on data de-duplication technology disclosed in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
The embodiment of the invention discloses a kind of data managing method and device based on data de-duplication technology, to realize
In field of distributed storage, storage, reading and the deletion action of data are carried out based on duplicate data technology.
Referring to Fig. 1, a kind of data managing method based on data de-duplication technology provided in an embodiment of the present invention, bag
Include：
S11, the fingerprint value by HASH algorithms calculating target data；
Specifically, in the present embodiment, the target data is the current operation data to be stored, target data is being calculated
Fingerprint value before, it is necessary first to target data is subjected to piecemeal.
At present, in field of distributed storage, in order that the data normalization of bottom storage, typically will storing
Data are divided according to the size of bottom storage object.Such as：If bottom storage object is divided according to 4M size,
And the size of target data is 10M, then by target data using 4M be according to cutting as these three blocks of 4M, 4M and 2M.I.e. will
The data of storage are cut to the block less than or equal to 4M.
Specifically, when calculating the fingerprint value of target data, HASH algorithm meters are passed through according to the data content of above-mentioned piecemeal
Calculate the fingerprint value of target data, the data content of the fingerprint value and piecemeal corresponds, i.e., with a pair of the data 1 to be stored
Should, i.e., data content matches in pairs with fingerprint value, and forms key-value pair match information.If target data is divided into multiple piecemeals,
Then each piecemeal has a fingerprint value, for each fingerprint value for data carry out subsequent operation；If target data is divided
For a piecemeal, then target data has a fingerprint value, and subsequent operation is carried out for this fingerprint value.In the present embodiment, mesh
Mark data are divided into a piecemeal, have unique fingerprint value.
S12, pass through CRUSH mapping determinations storage location corresponding with the fingerprint value of the target data；By the target
Data are used as and treat deposit data, and perform S13；
Specifically, according to by the above-mentioned calculated fingerprint value of HASH algorithms, mapped in Rados layers by CRUSH
Journey replaces with target data the fingerprint value of target data, and is transferred to object storage device, and then is existed by object storage device
Storage location corresponding with target data is found in itself storage system, and then determines storage location.
S13, judge whether have data in storage location corresponding with treating deposit data；If so, then perform S14；If it is not, then
Perform S15；
Specifically, using target data as deposit data is treated, object storage device is determined after the storage location of deposit data, first
First judge whether have data in this storage location, if there being data, show to treat deposit data stored mistake；If do not deposit
There are data, then show to treat that deposit data not yet stores.
S14, reference count corresponding with treating deposit data added one, and perform S16；
Specifically, determining to treat deposit data stored mistake by step S13, then no longer deposit data is treated in storage, but will be with
Treat that reference count adds one corresponding to deposit data.
It S15, will treat that deposit data is stored to storage location corresponding with treating deposit data, and corresponding with treating deposit data will quote
Counting puts one, and performs S16；
Specifically, determining to treat that deposit data not yet stores by step S13, then it will treat that deposit data is stored to treating deposit data pair
The storage location answered, and reference count corresponding with treating deposit data is put one.
S16, storage treat the first metadata information of deposit data, and first metadata information includes：Treat the finger of deposit data
Line value.
Specifically, completing after the storage of deposit data, treat that reference count corresponding to deposit data can be also stored to object and deposit
Store up the private storage locations that equipment prepares；Meanwhile treat that the metadata information of deposit data will also be stored, wrapped in metadata information
Include each attribute such as the fingerprint value for treating deposit data.
Specifically, when metadata is stored in storage fingerprint value, 8K metadata can be stored first, then will be in member
Fingerprint value corresponding to this document is stored behind data.Metadata storage metadata information be in units of file, using 8K as
One object is stored in cluster environment, and for 4MB deblocking, the space for having 4088KB now is stored into fingerprint number
According to, as fingerprint HASH algorithms, a fingerprint size it is 20byte using SHA-1, will now stores 209305 fingerprint values,
817GB data are corresponded to.
It can be seen that a kind of data managing method based on data de-duplication technology that the present embodiment provides, methods described are led to
Cross the fingerprint value that HASH algorithms calculate target data；And determined by CRUSH mappings corresponding with the fingerprint value of the target data
Storage location；Wherein, fingerprint value determines the uniqueness of target data, and then the unique of destination data storage location is determined
Property；And then using the target data as deposit data is treated, judge whether have data in storage location corresponding with treating deposit data；
Due to treating that deposit data has unique storage location, if so there have been data in storage location, show to treat deposit data
Stored, just no longer deposit data is treated in storage, but reference count corresponding with treating deposit data is added into one；If do not deposited in storage location
There are data, then show to treat that deposit data does not store, just will treat that deposit data is stored to storage location corresponding with treating deposit data, and will be with
Treat that reference count corresponding to deposit data puts one, finally store the first metadata information for treating deposit data, first metadata
Information includes：Treat the fingerprint value of deposit data.Thus by the above method, during data storage is carried out, number is both avoided
According to multiple storage, improve operating efficiency again, saved the memory space of system；Meanwhile based on duplicate data technology, dividing
The management of data is realized in cloth field of storage, has saved cost, extends the life-span of storage system.
Referring to Fig. 2, data managing method of the another kind based on data de-duplication technology provided in an embodiment of the present invention, bag
Include：
S21, judge whether the second metadata information corresponding with the target data；If so, then perform S22；If
It is no, then perform S11；
Specifically, in the present embodiment, before being stored to target data, the second of target data can be first determined whether
Metadata information whether there is, that is, it is to store or store again first to judge target data, so that it is determined that current operation is wound
Build to write or change and write.If the second metadata information of target data is present, it is not to store first to show target data, then really
Determine current operation to write for modification, continue executing with step S22；If the second metadata information of target data is not present, show mesh
It is to store first to mark data, then performs step S11.
S22, obtain second metadata information；
Specifically, the detailed process for obtaining second metadata information is as follows：File system client obtains number of targets
Index information, and to metadata store the metadata information of acquisition request second；Metadata stores the index according to target data
The metadata information of acquisition of information second, including the fingerprint value of target data, the fingerprint value is stored in the form of key-value pair.
It should be noted that the second metadata information is only got herein, to obtain corresponding to certain metadata in data
Hold, that is, read the data, then need client to obtain the index information that read data, and request metadata letter is stored to metadata
Breath；Metadata storage obtains metadata information according to index information, including each object of composing document, with key-value pair
The fingerprint value of form storage；Rados according to data offset, data length and fingerprint value, to object storage device in directly
Read data.So just complete the reading process of data.
S23, judge to whether there is fingerprint value in second metadata information；If so, then perform S24；If it is not, then perform
S11；
Specifically, got by step S22 after the second metadata information of target data, it is necessary to judge the second metadata
Whether information is complete, that is, judges to whether there is fingerprint value in the second metadata information, if fingerprint value be present, continue executing with step
S24；If fingerprint value is not present, step S11 is performed.
The length of target data described in S24, comparison and default data length；If the length of the target data is equal to institute
Default data length is stated, then performs S11；If the length of the target data is less than the default data length, perform
S25；
Specifically, determined to exist in the second metadata information after fingerprint value, it is necessary to comparison object number by above-mentioned steps S23
According to length and default data length size.Before the size of relatively data length, target data can typically be carried out
Size divides, and it is similar to the above embodiments to divide the detailed process of size, therefore does not repeat herein.
Specifically, after target data is carried out into piecemeal processing, compare the length of piecemeal and the size of default data length,
In this example, it is assumed that target data is divided into a data block, then the length of this data block is equal to target data
Length, then the length of comparison object data and default data length.Default data length is to be write from memory in system herein
The length recognized, General System default-length are 4M.If the length of the target data is equal to the default data length, hold
Row S11；If the length of the target data is less than the default data length, S25 is continued executing with；
S25, the target data and data corresponding with second metadata information spliced, spliced
Data, and the fingerprint value of the splicing data is calculated, and perform S26；
Specifically, if the length of target data is less than default data length, need according to data offset, data length
Degree is spliced target data data corresponding with second metadata information.In the present embodiment, by default data
Length is set to 4M.Such as：The length of data corresponding to second metadata information is 0~4M data object, and number of targets
According to length be 1M, now need this position of 2~3M in 0~4M of modification；First number corresponding to the second metadata information
All read according to 0~4M, and target data 1M is spliced, i.e., is 0~2M by 0~4M points, 2~3M, tri- sections of 3~4M, and will
The common 1M contents of 2~3M originally replace with the 1M contents of target data, then 0~2M, this three sections new of 2~3M, 3~4M are spliced
To together, a new 4M data are formed, that is, have obtained splicing data.
S26, determination storage location corresponding with the fingerprint value of the splicing data is mapped by CRUSH；By the splicing
Data are used as and treat deposit data, and perform S13.
Specifically, in the present embodiment, it is determined that the detailed process of storage location corresponding to the fingerprint value of splicing data with it is upper
It is similar to state embodiment, therefore will not be repeated here.And it is determined that, it is necessary to will spell after storage location corresponding to the fingerprint value of splicing data
Data are connect as deposit data is treated, continue executing with step S13.
It can be seen that a kind of data managing method based on data de-duplication technology that the present embodiment provides, methods described is first
First judge whether the second metadata information corresponding with the target data；When target data has the second metadata information
When, then obtain second metadata information；When the second metadata information is not present in target data, then S11 is performed；Obtaining
To after the second metadata information, judge to whether there is fingerprint value in second metadata information；If in the presence of the mesh
Mark the length of data and default data length；If being not present, S11 is performed；Comparison object data length with it is default
After data length, if the length of the target data is equal to the default data length, S11 is performed；If the number of targets
According to length be less than the default data length, then by the target data and corresponding with second metadata information
Data are spliced, and obtain splicing data, and calculate the fingerprint value of the splicing data, and map determination and institute by CRUSH
State storage location corresponding to the fingerprint value of splicing data；Using the splicing data as treating deposit data, and then execution S13.Pass through
The above method, during data storage is carried out, the multiple storage of data was both avoided, has improved operating efficiency again, saved
The memory space of system；Meanwhile based on duplicate data technology, the management of data is realized in field of distributed storage, is saved
About cost, extend life-span of storage system.
Based on above-mentioned any embodiment, it is necessary to illustrate, if the length of the target data is equal to described preset
Data length, including：
It is if the length of the target data is equal to the default data length, second metadata information is corresponding
The reference counts of data subtract one；
Whether the reference count for judging data corresponding to second metadata information is zero；
If so, then delete data corresponding to second metadata information.
Specifically, during the modification of data is write, when the length of the target data is equal to the default data length
When spending, the reference count of data corresponding to second metadata information is subtracted one, if data corresponding to the second metadata information
There is no other references, then the reference count after subtracting one is zero, is now just deleted data corresponding to the second metadata information
Remove.
Based on above-mentioned any embodiment, it is necessary to explanation, it is described by the target data and with the binary number
It is believed that data corresponding to breath are spliced, obtain splicing data, and calculate the fingerprint value of the splicing data, including：
Obtain data content corresponding with second metadata information；
According to the default data length and data offset, by the target data and with the binary number
It is believed that data corresponding to breath are spliced, obtain splicing data；
Calculate the fingerprint value of the splicing data；
The reference count of data corresponding to second metadata information is subtracted one；
Whether the reference count for judging data corresponding to second metadata information is zero；
If so, then delete data corresponding to second metadata information.
Specifically, during the modification of data is write, the length of the target data is less than the default data length,
And according to the default data length and data offset, by the target data and with second metadata information
Corresponding data are spliced, and obtain splicing data, after the fingerprint value for calculating the splicing data；And then judge the second metadata
Whether data corresponding to information also have other references, and detailed process is as follows：By data corresponding to second metadata information
Reference count subtract one, if the reference count subtract one after be zero, show that data corresponding to the second metadata information are not present
Other are quoted, and just delete data corresponding to the second metadata information；If the reference count is not zero after subtracting one, show
Data corresponding to binary data information are quoted in the presence of other, then retain data corresponding to the second metadata information.
Based on above-mentioned any embodiment, it is necessary to which explanation, one kind provided in an embodiment of the present invention are deleted based on duplicate data
The data managing method removed, include the delet method of data, it is as follows referring to Fig. 3, detailed process：
S31, receive the removal request that client is sent；
S32, determine data to be deleted according to the removal request, and the trinary data information of data to be deleted described in obtaining and
The fingerprint value of data to be deleted in the trinary data information；
S33, determine corresponding with the fingerprint value of the data to be deleted storage location by CRUSH mappings, and will with it is described
Reference count corresponding to data to be deleted subtracts one；
S34, judge whether reference count corresponding with the data to be deleted is zero；
S35, if so, then delete described in data to be deleted and the trinary data information；
S36, if it is not, deletion action wouldn't be performed.
Specifically, when performing the delet method of data, wherein containing the reading process of data, i.e., according to the deletion
Request determines data to be deleted, and is treated in the trinary data information and the trinary data information of data to be deleted described in acquisition
The fingerprint value of data is deleted, only have read the trinary data information of data to be deleted and fingerprint value therein herein, for number to be deleted
According to content do not read.And then storage location corresponding with the fingerprint value of the data to be deleted is determined by CRUSH mappings, and
Reference count corresponding with the data to be deleted is subtracted and deletes its metadata information in the lump, informs client data success to be deleted
Delete；If the reference count is zero after subtracting one, show that data corresponding to the second metadata information are quoted in the absence of other, just
Data to be deleted are deleted.
A kind of data administrator based on data de-duplication technology provided in an embodiment of the present invention is situated between below
Continue, a kind of data administrator based on data de-duplication technology described below is based on repeat number with above-described one kind
Can be with cross-referenced according to the data managing method of deleting technique.
Referring to Fig. 4, a kind of data administrator based on data de-duplication technology provided in an embodiment of the present invention, bag
Include：
First computing module 401, for calculating the fingerprint value of target data by HASH algorithms；
First determining module 402, for determining storage corresponding with the fingerprint value of the target data by CRUSH mappings
Position, using the target data as treating deposit data；
First judge module 403, for judging whether have data in storage location corresponding with treating deposit data；
First execution module 404, for when with when having data in the corresponding storage location of deposit data, will be with number to be deposited
Add one according to corresponding reference count；
First memory module 405, for when with when not having data in the corresponding storage location of deposit data, by number to be deposited
According to storing to storage location corresponding with treating deposit data, and reference count corresponding with treating deposit data is put one；
Second memory module 406, the first metadata information of deposit data, the first metadata information bag are treated for storing
Include：Treat the fingerprint value of deposit data.
Wherein, in addition to：
Second judge module, for judging whether the second metadata information corresponding with the target data；If no
In the presence of then triggering first computing module；
Specifically, when the second judge module judges the second metadata information corresponding with the target data is not present,
First computing module is triggered, calculates the fingerprint value of target data by HASH algorithms by the first computing module；And by first
Determining module determines storage location corresponding with the fingerprint value of the target data by CRUSH mappings, by the target data
As treating deposit data；And then first judge module judge whether have data in corresponding with treating deposit data storage location；When with
When having data in storage location corresponding to deposit data, the first execution module adds reference count corresponding with treating deposit data
One；When with when not having data in the corresponding storage location of deposit data, the first memory module will treat that deposit data is stored to treating
Storage location corresponding to deposit data, and reference count corresponding with treating deposit data is put one；The second last memory module storage is treated
First metadata information of deposit data, first metadata information include：Treat the fingerprint value of deposit data.
First acquisition module, for when the second metadata information corresponding with the target data be present, described in acquisition
Second metadata information；
3rd judge module, for judging to whether there is fingerprint value in second metadata information；If being not present, touch
Send out the first computing module described；
Specifically, when the 3rd reading module judges fingerprint value is not present in the second metadata information, triggering described first
Computing module；The fingerprint value of target data is calculated by HASH algorithms by the first computing module；And passed through by the first determining module
CRUSH mappings determine corresponding with the fingerprint value of target data storage location, using the target data as treating deposit data；
And then first judge module judge whether have data in corresponding with treating deposit data storage location；When with treating that deposit data is corresponding
When having data in storage location, reference count corresponding with treating deposit data is added one by the first execution module；When with treating deposit data
When not having data in corresponding storage location, the first memory module will treat that deposit data is stored to storage corresponding with treating deposit data
Position, and reference count corresponding with treating deposit data is put one；First yuan of number of deposit data is treated in the second last memory module storage
It is believed that breath, first metadata information include：The fingerprint value for treating deposit data.
Comparison module, for when fingerprint value be present in second metadata information, the length of the target data
Degree and default data length；If the length of the target data is equal to the default data length, described first is triggered
Computing module；
Specifically, when fingerprint value be present in the second metadata information, the length of the target data with it is default
Data length；If the length of the target data is equal to the default data length, first computing module is triggered；By
First computing module calculates the fingerprint value of target data by HASH algorithms；And mapped really by CRUSH by the first determining module
Fixed storage location corresponding with the fingerprint value of the target data, using the target data as treating deposit data；And then first sentences
Disconnected module judges whether have data in storage location corresponding with treating deposit data；When in storage location corresponding with treating deposit data
When having data, reference count corresponding with treating deposit data is added one by the first execution module；When storage corresponding with treating deposit data
When not having data in position, the first memory module will treat that deposit data is stored to storage location corresponding with treating deposit data, and will
Reference count corresponding with treating deposit data puts one；The first metadata information of deposit data, institute are treated in the second last memory module storage
Stating the first metadata information includes：Treat the fingerprint value of deposit data.
Concatenation module, for when the length of the target data is less than the default data length, by the target
Data and data corresponding with second metadata information are spliced, and obtain splicing data, and calculate the splicing number
According to fingerprint value；
Second determining module, for being mapped by CRUSH, determination is corresponding with the fingerprint value of the splicing data to store position
Put.
Wherein, the comparison module includes：
First execution unit, described in when the length of the target data is equal to the default data length, inciting somebody to action
The reference count of data subtracts one corresponding to second metadata information；
First judging unit, for judging whether the reference count of data corresponding to second metadata information is zero；
First deletes unit, for when the reference count of data corresponding to second metadata information is zero, deleting
Data corresponding to second metadata information.
Wherein, the concatenation module includes：
Acquiring unit, for obtaining data content corresponding with second metadata information；
Concatenation unit, for according to the default data length and data offset, by the target data and
Data corresponding with second metadata information are spliced, and obtain splicing data；
Computing unit, for calculating the fingerprint value of the splicing data；
Second execution unit, for subtracting one by the reference count of data corresponding to second metadata information；
Second judging unit, for judging whether the reference count of data corresponding to second metadata information is zero；
Second deletes unit, for when the reference count of data corresponding to second metadata information is zero, deleting
Data corresponding to second metadata information.
Wherein, in addition to：
Receiving module, for receiving the removal request of client transmission；
Second acquisition module, for determining data to be deleted according to the removal request, and the of data to be deleted described in obtaining
The fingerprint value of trinary data information and the data to be deleted in the trinary data information；
3rd determining module, for storing position by the way that CRUSH mapping determinations are corresponding with the fingerprint value of the data to be deleted
Put, and reference count corresponding with the data to be deleted is subtracted one；
4th judge module, for judging whether reference count corresponding with the data to be deleted is zero；
Removing module, for when with described when it is zero to delete the corresponding reference count of data, data to be deleted described in deletion and
The trinary data information.
It can be seen that a kind of data administrator based on data de-duplication technology that the present embodiment provides, the first first meter
Calculate the fingerprint value that module calculates target data by HASH algorithms；First determining module is determined and the mesh by CRUSH mappings
Storage location corresponding to the fingerprint value of data is marked, using the target data as treating deposit data；By the first judge module judge with
Treat whether have data in storage location corresponding to deposit data；When with when having data in the corresponding storage location of deposit data,
Reference count corresponding with treating deposit data is added one by the first execution module；Do not have when in storage location corresponding with treating deposit data
During data, the first memory module will treat that deposit data is stored to storage location corresponding with treating deposit data, and will be with treating deposit data pair
The reference count answered puts one；The first metadata information of deposit data, first metadata are treated in the second last memory module storage
Information includes：Treat the fingerprint value of deposit data.So as to complete the storage of the storage of data and its metadata information.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be and other
The difference of embodiment, between each embodiment identical similar portion mutually referring to.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
- A kind of 1. data managing method based on data de-duplication technology, it is characterised in that including：S11, the fingerprint value by HASH algorithms calculating target data；S12, pass through CRUSH mapping determinations storage location corresponding with the fingerprint value of the target data；By the target data As treating deposit data, and perform S13；S13, judge whether have data in storage location corresponding with treating deposit data；If so, then perform S14；If it is not, then perform S15；S14, reference count corresponding with treating deposit data added one, and perform S16；S15, it will treat that deposit data is stored to storage location corresponding with treating deposit data, and will reference count corresponding with treating deposit data One is put, and performs S16；S16, storage treat the first metadata information of deposit data, and first metadata information includes：Treat the fingerprint value of deposit data.
- 2. the data managing method according to claim 1 based on data de-duplication technology, it is characterised in that perform institute Before stating S11, in addition to：S21, judge whether the second metadata information corresponding with the target data；If so, then perform S22；If it is not, then Perform S11；S22, obtain second metadata information；S23, judge to whether there is fingerprint value in second metadata information；If so, then perform S24；If it is not, then perform S11；The length of target data described in S24, comparison and default data length；If the length of the target data is equal to described pre- If data length, then perform S11；If the length of the target data is less than the default data length, S25 is performed；S25, the target data and data corresponding with second metadata information spliced, obtain splicing number According to, and the fingerprint value of the splicing data is calculated, and perform S26；S26, determination storage location corresponding with the fingerprint value of the splicing data is mapped by CRUSH；By the splicing data As treating deposit data, and perform S13.
- 3. the data managing method according to claim 2 based on data de-duplication technology, it is characterised in that if described The length of the target data is equal to the default data length, including：If the length of the target data is equal to the default data length, by number corresponding to second metadata information According to reference count subtract one；Whether the reference count for judging data corresponding to second metadata information is zero；If so, then delete data corresponding to second metadata information.
- 4. the data managing method according to claim 2 based on data de-duplication technology, it is characterised in that described to incite somebody to action The target data and data corresponding with second metadata information are spliced, and obtain splicing data, and calculate institute The fingerprint value of splicing data is stated, including：Obtain data content corresponding with second metadata information；According to the default data length and data offset, believe by the target data and with second metadata Data are spliced corresponding to breath, obtain splicing data；Calculate the fingerprint value of the splicing data；The reference count of data corresponding to second metadata information is subtracted one；Whether the reference count for judging data corresponding to second metadata information is zero；If so, then delete data corresponding to second metadata information.
- 5. according to the data managing method based on data de-duplication technology described in claim 1-4 any one, its feature It is, in addition to：Receive the removal request that client is sent；Data to be deleted, and the trinary data information and the described 3rd of data to be deleted described in acquisition are determined according to the removal request The fingerprint value of data to be deleted in metadata information；Storage location corresponding with the fingerprint value of the data to be deleted is determined by CRUSH mappings, and will be with the data to be deleted Corresponding reference count subtracts one；Judge whether reference count corresponding with the data to be deleted is zero；If so, data to be deleted and the trinary data information described in then deleting.
- A kind of 6. data administrator based on data de-duplication technology, it is characterised in that including：First computing module, for calculating the fingerprint value of target data by HASH algorithms；First determining module, will for determining storage location corresponding with the fingerprint value of the target data by CRUSH mappings The target data is used as and treats deposit data；First judge module, for judging whether have data in storage location corresponding with treating deposit data；First execution module, for when with when having data in the corresponding storage location of deposit data, will be with treating that deposit data is corresponding Reference count add one；First memory module, for when with when not having data in the corresponding storage location of deposit data, will treat that deposit data stores To storage location corresponding with treating deposit data, and reference count corresponding with treating deposit data is put one；Second memory module, the first metadata information of deposit data is treated for storing, and first metadata information includes：Wait to deposit The fingerprint value of data.
- 7. the data administrator according to claim 6 based on data de-duplication technology, it is characterised in that also wrap Include：Second judge module, for judging whether the second metadata information corresponding with the target data；If being not present, Then trigger first computing module；First acquisition module, for when the second metadata information corresponding with the target data be present, obtaining described second Metadata information；3rd judge module, for judging to whether there is fingerprint value in second metadata information；If being not present, institute is triggered State the first computing module；Comparison module, for when fingerprint value be present in second metadata information, the length of the target data with Default data length；If the length of the target data is equal to the default data length, triggers described first and calculate Module；Concatenation module, for when the length of the target data is less than the default data length, by the target data And data corresponding with second metadata information are spliced, obtain splicing data, and calculate the splicing data Fingerprint value；Second determining module, storage location corresponding with the fingerprint value of the splicing data is determined for being mapped by CRUSH.
- 8. the data administrator according to claim 7 based on data de-duplication technology, it is characterised in that the ratio Include compared with module：First execution unit, for when the length of the target data is equal to the default data length, by described second The reference count of data corresponding to metadata information subtracts one；First judging unit, for judging whether the reference count of data corresponding to second metadata information is zero；First deletes unit, for when the reference count of data corresponding to second metadata information is zero, described in deletion Data corresponding to second metadata information.
- 9. the data administrator according to claim 7 based on data de-duplication technology, it is characterised in that the spelling Connection module includes：Acquiring unit, for obtaining data content corresponding with second metadata information；Concatenation unit, for according to the default data length and data offset, by the target data and with institute Data corresponding to stating the second metadata information are spliced, and obtain splicing data；Computing unit, for calculating the fingerprint value of the splicing data；Second execution unit, for subtracting one by the reference count of data corresponding to second metadata information；Second judging unit, for judging whether the reference count of data corresponding to second metadata information is zero；Second deletes unit, for when the reference count of data corresponding to second metadata information is zero, described in deletion Data corresponding to second metadata information.
- 10. according to the data administrator based on data de-duplication technology described in claim 6-9 any one, its feature It is, in addition to：Receiving module, for receiving the removal request of client transmission；Second acquisition module, for determining data to be deleted, and the ternary of data to be deleted described in acquisition according to the removal request The fingerprint value of data message and the data to be deleted in the trinary data information；3rd determining module, for determining storage location corresponding with the fingerprint value of the data to be deleted by CRUSH mappings, and Reference count corresponding with the data to be deleted is subtracted one；4th judge module, for judging whether reference count corresponding with the data to be deleted is zero；Removing module, for when with described when it is zero to delete the corresponding reference count of data, data to be deleted described in deletion and described Trinary data information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710750609.4A CN107391761B (en) | 2017-08-28 | 2017-08-28 | Data management method and device based on repeated data deletion technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710750609.4A CN107391761B (en) | 2017-08-28 | 2017-08-28 | Data management method and device based on repeated data deletion technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107391761A true CN107391761A (en) | 2017-11-24 |
| CN107391761B CN107391761B (en) | 2020-03-06 |
Family
ID=60346237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710750609.4A Active CN107391761B (en) | 2017-08-28 | 2017-08-28 | Data management method and device based on repeated data deletion technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107391761B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800218A (en) * | 2019-01-04 | 2019-05-24 | 平安科技（深圳）有限公司 | Distributed memory system, memory node equipment and data duplicate removal method |
| CN110399348A (en) * | 2019-07-19 | 2019-11-01 | 苏州浪潮智能科技有限公司 | File deletes method, apparatus, system and computer readable storage medium again |
| CN111711674A (en) * | 2020-06-05 | 2020-09-25 | 华南师范大学 | Cloud computing method based on Internet of things |
| WO2021016728A1 (en) * | 2019-07-26 | 2021-02-04 | 华为技术有限公司 | Data processing method and device in storage system, and computer readable storage medium |
| CN112889021A (en) * | 2019-07-23 | 2021-06-01 | 华为技术有限公司 | Apparatus, system, and method for deduplication |
| US12019890B2 (en) | 2022-01-25 | 2024-06-25 | Huawei Technologies Co., Ltd. | Adjustable deduplication method, apparatus, and computer program product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101276366A (en) * | 2007-03-27 | 2008-10-01 | 株式会社日立制作所 | Computer system preventing storage of duplicate files |
| US20110184910A1 (en) * | 2009-07-31 | 2011-07-28 | Joel Michael Love | Chain-of-Custody for Archived Data |
| CN102495894A (en) * | 2011-12-12 | 2012-06-13 | 成都市华为赛门铁克科技有限公司 | Method, device and system for searching repeated data |
| CN103248711A (en) * | 2013-05-23 | 2013-08-14 | 华为技术有限公司 | File uploading method and server |
| CN105049213A (en) * | 2015-07-27 | 2015-11-11 | 小米科技有限责任公司 | File signature method and device |
| CN106649702A (en) * | 2016-12-20 | 2017-05-10 | 上海斐讯数据通信技术有限公司 | File storage method and apparatus of cloud storage system, and cloud storage system |
-
2017
- 2017-08-28 CN CN201710750609.4A patent/CN107391761B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101276366A (en) * | 2007-03-27 | 2008-10-01 | 株式会社日立制作所 | Computer system preventing storage of duplicate files |
| US20110184910A1 (en) * | 2009-07-31 | 2011-07-28 | Joel Michael Love | Chain-of-Custody for Archived Data |
| CN102495894A (en) * | 2011-12-12 | 2012-06-13 | 成都市华为赛门铁克科技有限公司 | Method, device and system for searching repeated data |
| CN103248711A (en) * | 2013-05-23 | 2013-08-14 | 华为技术有限公司 | File uploading method and server |
| CN105049213A (en) * | 2015-07-27 | 2015-11-11 | 小米科技有限责任公司 | File signature method and device |
| CN106649702A (en) * | 2016-12-20 | 2017-05-10 | 上海斐讯数据通信技术有限公司 | File storage method and apparatus of cloud storage system, and cloud storage system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800218A (en) * | 2019-01-04 | 2019-05-24 | 平安科技（深圳）有限公司 | Distributed memory system, memory node equipment and data duplicate removal method |
| WO2020140622A1 (en) * | 2019-01-04 | 2020-07-09 | 平安科技（深圳）有限公司 | Distributed storage system, storage node device and data duplicate deletion method |
| CN109800218B (en) * | 2019-01-04 | 2024-04-09 | 平安科技（深圳）有限公司 | Distributed storage system, storage node device and data deduplication method |
| CN110399348A (en) * | 2019-07-19 | 2019-11-01 | 苏州浪潮智能科技有限公司 | File deletes method, apparatus, system and computer readable storage medium again |
| CN112889021A (en) * | 2019-07-23 | 2021-06-01 | 华为技术有限公司 | Apparatus, system, and method for deduplication |
| CN112889021B (en) * | 2019-07-23 | 2023-11-28 | 华为技术有限公司 | Apparatus, system and method for deduplication |
| WO2021016728A1 (en) * | 2019-07-26 | 2021-02-04 | 华为技术有限公司 | Data processing method and device in storage system, and computer readable storage medium |
| CN111711674A (en) * | 2020-06-05 | 2020-09-25 | 华南师范大学 | Cloud computing method based on Internet of things |
| CN111711674B (en) * | 2020-06-05 | 2023-03-14 | 华南师范大学 | Cloud computing method based on Internet of things |
| US12019890B2 (en) | 2022-01-25 | 2024-06-25 | Huawei Technologies Co., Ltd. | Adjustable deduplication method, apparatus, and computer program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107391761B (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107391761A (en) | A kind of data managing method and device based on data de-duplication technology | |
| US10776396B2 (en) | Computer implemented method for dynamic sharding | |
| US10380073B2 (en) | Use of solid state storage devices and the like in data deduplication | |
| US9305005B2 (en) | Merging entries in a deduplication index | |
| CN109543455B (en) | Data archiving method and device for block chain | |
| CN102629247B (en) | Method, device and system for data processing | |
| CN107045422B (en) | Distributed storage method and device | |
| US10949405B2 (en) | Data deduplication device, data deduplication method, and data deduplication program | |
| CN106201771B (en) | Data-storage system and data read-write method | |
| CN112380149B (en) | Data processing method, device, equipment and medium based on node memory | |
| CN109889505A (en) | The data property held verification method and terminal device | |
| CN103959256A (en) | Fingerprint-based data deduplication | |
| CN107622079A (en) | Data storage, querying method and device | |
| CN109522283A (en) | A kind of data de-duplication method and system | |
| CN107085613B (en) | Method and device for filtering files to be put in storage | |
| CN114490060A (en) | Memory allocation method and device, computer equipment and computer readable storage medium | |
| CN107506150A (en) | Distributed storage devices, delete, write again, deleting, read method and system | |
| CN111522502A (en) | Data deduplication method and device, electronic equipment and computer-readable storage medium | |
| US11372570B1 (en) | Storage device, computer system, and data transfer program for deduplication | |
| CN102799659A (en) | Overall repeating data deleting system and method based on non-centre distribution system | |
| JP6059558B2 (en) | Load balancing judgment system | |
| CN110633261A (en) | Picture storage method, picture query method and device | |
| CN106528703A (en) | Deduplication mode switching method and apparatus | |
| CN109388335A (en) | A kind of date storage method and system | |
| Li et al. | NFT content data placement strategy in P2P storage network for permissioned blockchain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200110 Address after: 215100 No. 1 Guanpu Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Applicant after: Suzhou Wave Intelligent Technology Co., Ltd. Address before: 450018 Henan province Zheng Dong New District of Zhengzhou City Xinyi Road No. 278 16 floor room 1601 Applicant before: Zhengzhou Yunhai Information Technology Co. Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |