CN107357921A - A kind of small documents storage localization method and system - Google Patents
A kind of small documents storage localization method and system Download PDFInfo
- Publication number
- CN107357921A CN107357921A CN201710600589.2A CN201710600589A CN107357921A CN 107357921 A CN107357921 A CN 107357921A CN 201710600589 A CN201710600589 A CN 201710600589A CN 107357921 A CN107357921 A CN 107357921A
- Authority
- CN
- China
- Prior art keywords
- small documents
- storage
- file
- big file
- numbering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/13—File access structures, e.g. distributed indices
- G06F16/137—Hash-based
-
- 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
- G06F16/11—File system administration, e.g. details of archiving or snapshots
- G06F16/113—Details of archiving
Abstract
The invention discloses a kind of small documents storage localization method and system, the numbering that the present invention correspondingly stores big file by positioning small documents to the title Hash calculation of small documents, then the disk of big all copies of file is stored where the method positioning small documents of uniformity Hash by storing the numbering of big file, determine offset of the small documents in big file is stored so that it is determined that the storage location of small documents finally by the index file on disk, center metadata service node is eliminated in small documents storage system, the positioning to the more copies of small documents is realized under decentralization framework, solve the problems, such as Single Point of Faliure and scalability, remove extra position enquiring request simultaneously.
Description
Technical field
The present invention relates to technical field of data storage, and localization method and system are stored more particularly to a kind of small documents.
Background technology
The high speed development of internet generates the files such as the picture of magnanimity, document, be size the characteristics of these files compared with
Small (typically in below 100KB), enormous amount (hundreds of millions of), traditional POSIX interface document systems have been difficult to meet need
Ask, here it is the mass small documents problem that industry is famous.
For mass small documents problem, common practice is to merge storage at present, i.e., stores small documents traditional to one
POSIX files, because small documents are stored on disk in a manner of merging storage, a small documents are positioned, except physics is big
Outside file path, also to include small documents the offset in big file, therefore Hash merely common using tradition
Method will be unable to navigate to the physical storage locations of small documents.In addition, in order to ensure the availability of system and fault-tolerance, this
A little small documents are generally preserved in a manner of more copies again, and localization method is required to position the position of multiple copies simultaneously.
And on stored copies orientation problem, common practice is that the path of big file is managed using central server at present,
By offset coding of the small documents in big file hereof, the rope that client preserved or be stored in big file is then given
In quotation part.The defects of this method is to need a center metadata service to provide positioning service, thus brings 2 problems:
Client, which is often once read and write, at least to be carried out interacting for 2 times with server end, is big document alignment for the first time, for the second time
It is actual reading and writing data;Cluster is likely to occur Single Point of Faliure, and scalability is poor.The reason for causing this problem be
Merge in storage, the physical storage locations of small documents can not be predicted, and then small documents can not be mapped with traditional hash method
Physical storage locations.
The content of the invention
It is an object of the invention to propose a kind of small documents storage localization method and system, to solve in the prior art small
Center metadata server is needed to provide positioning service in document storage system, and in order to ensure the availability of system and fault-tolerant
Property, it is necessary to small documents are preserved in a manner of more copies, causing client often to carry out this read-write will be with server end at least
2 interactions are carried out, is big document alignment for the first time, is only actual reading and writing data for the second time;And cluster is likely to occur single-point event
Barrier, and the problem of scalability is poor.
To reach above-mentioned purpose, the invention provides following technical scheme:
A kind of small documents store localization method, including:
Obtain the filename of small documents;
Show that the small documents correspond to the big file of storage by Hash calculation according to the filename of the small documents
Numbering;
Storage location according to where the numbering of the big file of storage determines the small documents.
Wherein, show that the small documents are deposited described in corresponding by Hash calculation in the filename according to the small documents
Before the numbering for storing up big file, in addition to:
It is described according to corresponding to the filename of the small documents is mapped to by rule set in advance to store big file.
Wherein, the storage described according to corresponding to the filename of the small documents is mapped to by rule set in advance is greatly
File, it is specially:
Numbering in big file where the filename of the small documents is shown into the small documents by Hash calculation;
Numbering in big file where the small documents is drawn into the big file institute of storage by uniformity Hash calculation
In storage disk.
Wherein, the filename of the small documents is mapped to by corresponding storage location according to rule set in advance described
Before, in addition to:
Quantity, number of copies and the numbering of the big file of storage are preset, while is determined needed for the big file of storage
The storage disk wanted.
Wherein, the big file of storage that merges is equipped with corresponding index file, and is recorded in the index file described small
File is in the offset merged in storing big file.
A kind of small documents store alignment system, including:
Acquiring unit, for obtaining the filename of small documents;
Computing unit, drawn for the filename according to the small documents by Hash calculation described in the small documents correspondence
Store the numbering of big file;
Determining unit, for the storage location where determining the small documents according to the numbering of the big file of storage.
Wherein, small documents storage alignment system also includes:
Map unit, for depositing described in corresponding to the filename of the small documents is mapped to according to rule set in advance
Store up big file.
Wherein, the computing unit includes:
First Hash subelement, for the filename of the small documents to be shown into the small documents place by Hash calculation
Numbering in big file;
Second Hash subelement, for the numbering in big file where the small documents to be obtained by uniformity Hash calculation
Storage disk where going out the big file of storage.
Wherein, small documents storage alignment system also includes:
Default unit, for presetting quantity, number of copies and the numbering of the big file of storage, while deposited described in determination
Store up the storage disk required for big file.
Wherein, the big file of storage that merges is equipped with corresponding index file, and is recorded in the index file all small
The original position of file and the small documents are in the offset merged in storing big file.
Understood via above-mentioned technical scheme, compared with prior art, the invention discloses a kind of storage of small documents to position
Method and system, this method include:Preset quantity, number of copies and the numbering for merging and storing big file;Obtain small documents
Filename;Show that small documents correspondingly store the numbering of big file by Hash calculation according to the filename of small documents;According to storage
The numbering of big file determines the disk where big file by the method for uniformity Hash;Determined according to the index file on disk
Offset of the small documents in big file.By being positioned to the filename Hash calculation of small documents, small documents are corresponding to be stored the present invention
The numbering of big file, then position the big text of small documents place storage with the method for uniformity Hash by storing the numbering of big file
The disk of all copies of part, finally by the index file on disk determine offset of the small documents in big file is stored so as to
Determine the storage location of small documents.The present invention eliminates center metadata service node in small documents storage system, in going
The positioning to the more copies of small documents is realized under heart framework, solves the problems, such as Single Point of Faliure and scalability, while remove volume
Outer position enquiring request.
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
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 stores localization method schematic flow sheet for a kind of small documents provided in an embodiment of the present invention;
Fig. 2 is a kind of small documents storage positioning schematic diagram provided in an embodiment of the present invention;
The idiographic flow schematic diagram of step S102 in Fig. 3 Fig. 1 provided in an embodiment of the present invention;
Fig. 4 is uniformity Hash principle schematic provided in an embodiment of the present invention;
Fig. 5 is uniformity Hash principle schematic of the big file provided in an embodiment of the present invention to storage disk;
Fig. 6 stores positioning system structure schematic diagram for a kind of small documents provided in an embodiment of the present invention;
Fig. 7 is the concrete structure schematic diagram of the default unit 602 in Fig. 6 provided in an 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.
Accompanying drawing 1 is referred to, Fig. 1 stores localization method schematic flow sheet for a kind of small documents provided in an embodiment of the present invention.
As shown in figure 1, the invention discloses a kind of small documents to store localization method, specifically, this method comprises the following steps:
S101, the filename for obtaining small documents.
S102, according to the filename of small documents show that small documents correspondingly store the numbering of big file by Hash calculation.
S103, the storage location according to where the numbering for storing big file determines small documents.
The storage demand for being mainly used for solving mass small documents stored in the present embodiment, common small documents have figure
Piece, text etc., specifically, the storage available for picture and some UGC small videos, subtitle files etc..It is mentioned in the present embodiment
The single file of small documents more than one, it can be multiple small documents, herein without the restriction to quantity.
Specifically, show that small documents correspondingly store the numbering of big file by Hash calculation in the filename according to small documents
Before, in addition to:Big file is stored according to corresponding to the filename of small documents is mapped to by rule set in advance.
Specifically, stored corresponding to according to rule set in advance, the filename of small documents is being mapped to big file it
Before, in addition to:
Quantity, number of copies and the numbering of the big file of the storage are preset, while required for determining to store big file
Storage disk.
Big file is stored as shown in Fig. 2 having preset 9 and having merged, and number consecutively is 0,1 ..., 9, according to small documents
Filename calculate an integer value, as the key assignments K of small documents, then in the default position being stored in small documents in big file
Integer value corresponding to lookup is put, big file is stored and is equipped with corresponding index file, and all small documents are recorded in index file
Offset in big file is stored of original position and small documents.Small documents are searched in big file from storing, and from storage
Big file, which is equipped with corresponding index file, searches the offset of the original position and small documents of small documents wherein to determine
The storage location of small documents.
Present embodiment discloses a kind of small documents to store localization method, and this method includes:Obtain the title of small documents;According to
The title of small documents draws an integer value by Hash calculation, and integer value is the numbering that small documents correspondingly store big file;Root
The storage location where small documents is determined according to the numbering for storing big file.
Specifically, referring to accompanying drawing 3, the idiographic flow that Fig. 3 is the step S102 in Fig. 1 provided in an embodiment of the present invention shows
It is intended to.As shown in figure 3, S102, showing that small documents are corresponding by Hash calculation according to the filenames of small documents and merging the big text of storage
The numbering of part, specially following steps:
S301, the filename of small documents is passed through into Hash calculation small documents where numbering in big file.
, it is necessary to plan the quantity for storing big file in advance in the present embodiment, compiled successively to each big file since 0
Number, 0,1,2 ..., n-1, and the storage disk of numbering distribution corresponding to each big file is set, a numbering can set storage
In at least one storage disk, you can to realize that more copies of small documents store.Such as the big file of numbering 0 is stored in machine
On A first piece of disk, the big file of numbering 1 is stored on machine B the 3rd piece of disk etc., or numbering 0 and numbering 1
Big file can be stored on machine A first piece of disk and machine B the 3rd piece of disk simultaneously, so to determine a small text
During the deposit position of part, as long as the numbering of big file where determining small documents.
S302, deposited where the numbering in big file where small documents is shown into the big file of storage by uniformity Hash calculation
Store up disk.
Integer in one 1 to n-1 is calculated according to the filename of each small documents, corresponding integer is hashing onto in advance
In the numbering of the big file of storage of setting.
Then, as shown in figure 4, can be by key k values key assignments to default storage disk, then the volume that big file will be stored
Number it is mapped to by uniformity hash mode at least one default storage disk, more copies storages is realized, such as institute in Fig. 5
Show, an integer 3 calculated according to the file of a small documents, by numbering 3 can be mapped to by uniformity hash algorithm C,
D, stored on E disks.
Wherein, uniformity hash algorithm is the algorithm commonly used in distributed system.A such as distributed storage system
System, will store data on specific node, if using common hash methods, map the data into specific node
On, such as key%N, key is the key value of data, and N is machine nodes, if a machine adds or exits this cluster, then
All data mappings are all invalid, if persistent storage will then do Data Migration, if distributed caching, then other
Caching just fails.Uniformity Hash can solve this problem well.
Wherein, store big file and be equipped with corresponding index file, and the start bit of all small documents is recorded in index file
Put and offset of the small documents in big file is stored.
So far, we can located big file where small documents on the premise of independent of Centroid directory service
Numbering, offset of the path and small documents of big file in big file where then further positioning small documents, so as to
Correct read-write small documents.
The invention discloses a kind of small documents to store localization method, and this method includes:Preset the number for storing big file
Amount, number of copies and numbering;Obtain the filename of small documents;Small documents institute is drawn by Hash calculation according to the filename of small documents
Storing the numbering of big file;Depositing according to where the numbering of the big file of storage determines big file by the method for uniformity Hash
Store up disk;Offset of the small documents in big file is determined according to the index file in storage disk.The present invention is by small text
The filename Hash calculation positioning small documents of part correspondingly store the numbering of big file, then by storing the numbering of big file with one
The disk of big all copies of file is stored where the method positioning small documents of cause property Hash, finally by the index file on disk
Offset of the small documents in big file is stored is determined so that it is determined that the storage location of small documents, in small documents storage system
Except center metadata service node, the positioning to the more copies of small documents is realized under decentralization framework, solves single-point event
The problem of barrier and scalability, while remove extra position enquiring request.
On the basis of method disclosed above, the invention also discloses a kind of system.
Accompanying drawing 6 is referred to, Fig. 6 stores positioning system structure schematic diagram for a kind of small documents provided in an embodiment of the present invention.
As shown in fig. 6, the invention discloses a kind of small documents to store alignment system, the system specifically includes following structure:
Acquiring unit 601, for obtaining the filename of small documents;Computing unit 602, for the filename according to small documents
Show that the small documents correspondingly store the numbering of big file by Hash calculation;Determining unit 603, for according to the big file of storage
Numbering determine small documents where storage location.
Specifically, small documents storage alignment system also includes:Map unit, for will be small according to rule set in advance
The filename of file stores big file corresponding to being mapped to.
Specifically, small documents storage alignment system also includes:Default unit 600, for presetting the big file of storage
Quantity, number of copies and numbering, while determine to store the storage disk required for big file.
Wherein, accompanying drawing 7 is referred to, Fig. 7 is the concrete structure of the computing unit 602 in Fig. 6 provided in an embodiment of the present invention
Schematic diagram.As shown in fig. 7, the computing unit 602 includes:
First Hash subelement 701, for big text where the filename of small documents is shown into small documents by Hash calculation
Numbering in part;
Second Hash subelement 702, for the numbering in big file where small documents to be obtained by uniformity Hash calculation
Storage disk where going out to store big file.
Wherein, the big file of storage is equipped with corresponding index file, and all small documents are recorded in the index file
The offset of original position and the small documents in the big file of storage.
Present embodiment discloses a kind of small documents of decentralization to merge storage alignment system, and the present embodiment passes through to small text
The title Hash calculation positioning small documents of part correspondingly store the numbering of big file, and then the numbering positioning by storing big file is small
The offset of the path and small documents of big file in big file is stored is stored where file, but is needed according to set in advance
The title of small documents is mapped to corresponding storage location by rule, and the present embodiment eliminates center element in small documents storage system
Data serving node, positioning to the more copies of small documents is realized under decentralization framework, solve Single Point of Faliure and expansible
Property the problem of, while remove extra position enquiring request.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference with other embodiment, between each embodiment identical similar part mutually referring to.
It should also be noted that, herein, such as first and second or the like relational terms are used merely to one
Entity or operation make a distinction with another entity or operation, and not necessarily require or imply between these entities or operation
Any this actual relation or order be present.Moreover, term " comprising ", "comprising" or its any other variant are intended to contain
Lid nonexcludability includes, so that article or equipment including a series of elements not only include those key elements, but also
Including the other element being not expressly set out, or also include for this article or the intrinsic key element of equipment.Do not having
In the case of more limitations, the key element that is limited by sentence "including a ...", it is not excluded that including the article of above-mentioned key element
Or other identical element in equipment also be present.
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)
1. a kind of small documents store localization method, it is characterised in that including:
Obtain the filename of small documents;
Show that the small documents correspondingly store the numbering of big file by Hash calculation according to the filename of the small documents;
Storage location according to where the numbering of the big file of storage determines the small documents.
2. small documents according to claim 1 store localization method, it is characterised in that described according to the small documents
Before filename draws the numbering that the small documents correspondingly store big file by Hash calculation, in addition to:
It is described according to corresponding to the filename of the small documents is mapped to by rule set in advance to store big file.
3. small documents according to claim 2 store localization method, it is characterised in that described according to rule set in advance
The filename of the small documents is mapped to the corresponding big file of storage, is specially:
Numbering in big file where the filename of the small documents is shown into the small documents by Hash calculation;
Deposited where the numbering in big file where the small documents is shown into the big file of storage by uniformity Hash calculation
Store up disk.
4. small documents according to claim 2 store localization method, it is characterised in that described according to rule set in advance
Before the filename of the small documents then is mapped into corresponding storage location, in addition to:
Quantity, number of copies and the numbering of the big file of the storage are preset, while required for determining the big file of storage
Storage disk.
5. small documents according to claim 1 store localization method, it is characterised in that the big file of storage that merges is equipped with
Corresponding index file, and the small documents are recorded in the index file in the offset merged in storing big file.
6. a kind of small documents store alignment system, it is characterised in that including:
Acquiring unit, for obtaining the filename of small documents;
Computing unit, the big text of the corresponding storage of the small documents is drawn by Hash calculation for the filename according to the small documents
The numbering of part;
Determining unit, for the storage location where determining the small documents according to the numbering of the big file of storage.
7. small documents according to claim 6 store alignment system, it is characterised in that also include:
Map unit, for the storage corresponding to the filename of the small documents is mapped to according to rule set in advance greatly
File.
8. small documents according to claim 7 store alignment system, it is characterised in that the computing unit includes:
First Hash subelement, for big text where the filename of the small documents is shown into the small documents by Hash calculation
Numbering in part;
Second Hash subelement, for the numbering in big file where the small documents to be shown into institute by uniformity Hash calculation
Storage disk where stating the big file of storage.
9. small documents according to claim 7 store alignment system, it is characterised in that also include:
Default unit, for presetting quantity, number of copies and the numbering of the big file of storage, while determine that the storage is big
Storage disk required for file.
10. small documents according to claim 6 store alignment system, it is characterised in that the big file of storage that merges is matched somebody with somebody
Standby corresponding index file, and recorded in the index file all small documents original position and the small documents described
Merge the offset stored in big file.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710600589.2A CN107357921A (en) | 2017-07-21 | 2017-07-21 | A kind of small documents storage localization method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710600589.2A CN107357921A (en) | 2017-07-21 | 2017-07-21 | A kind of small documents storage localization method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107357921A true CN107357921A (en) | 2017-11-17 |
Family
ID=60285795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710600589.2A Pending CN107357921A (en) | 2017-07-21 | 2017-07-21 | A kind of small documents storage localization method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107357921A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109885535A (en) * | 2019-01-04 | 2019-06-14 | 平安科技(深圳)有限公司 | A kind of method and relevant apparatus of file storage |
CN110502711A (en) * | 2019-07-17 | 2019-11-26 | 汉海信息技术(上海)有限公司 | Page display method, device, electronic equipment and readable storage medium storing program for executing |
CN111400251A (en) * | 2020-03-17 | 2020-07-10 | 深圳市卡牛科技有限公司 | File access method, device, server and storage medium based on gateway |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996217A (en) * | 2009-08-24 | 2011-03-30 | 华为技术有限公司 | Method for storing data and memory device thereof |
CN103501319A (en) * | 2013-09-18 | 2014-01-08 | 北京航空航天大学 | Low-delay distributed storage system for small files |
CN103514210A (en) * | 2012-06-28 | 2014-01-15 | 华为技术有限公司 | Method and device for processing small files |
CN103561057A (en) * | 2013-10-15 | 2014-02-05 | 深圳清华大学研究院 | Data storage method based on distributed hash table and erasure codes |
CN103593436A (en) * | 2013-11-12 | 2014-02-19 | 华为技术有限公司 | File merging method and device |
CN105069048A (en) * | 2015-07-23 | 2015-11-18 | 东方网力科技股份有限公司 | Small file storage method, query method and device |
CN105956183A (en) * | 2016-05-30 | 2016-09-21 | 广东电网有限责任公司电力调度控制中心 | Method and system for multi-stage optimization storage of a lot of small files in distributed database |
-
2017
- 2017-07-21 CN CN201710600589.2A patent/CN107357921A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996217A (en) * | 2009-08-24 | 2011-03-30 | 华为技术有限公司 | Method for storing data and memory device thereof |
CN103514210A (en) * | 2012-06-28 | 2014-01-15 | 华为技术有限公司 | Method and device for processing small files |
CN103501319A (en) * | 2013-09-18 | 2014-01-08 | 北京航空航天大学 | Low-delay distributed storage system for small files |
CN103561057A (en) * | 2013-10-15 | 2014-02-05 | 深圳清华大学研究院 | Data storage method based on distributed hash table and erasure codes |
CN103593436A (en) * | 2013-11-12 | 2014-02-19 | 华为技术有限公司 | File merging method and device |
CN105069048A (en) * | 2015-07-23 | 2015-11-18 | 东方网力科技股份有限公司 | Small file storage method, query method and device |
CN105956183A (en) * | 2016-05-30 | 2016-09-21 | 广东电网有限责任公司电力调度控制中心 | Method and system for multi-stage optimization storage of a lot of small files in distributed database |
Non-Patent Citations (2)
Title |
---|
IT_ARCH_NOTES: "海量小文件存储与Ceph实践", 《HTTPS://WWW.CNBLOGS.COM/WUHUIYUAN/4651698.HTML》 * |
小树桩的朋友: "分布式存储系统横向对比", 《HTTPS://WWW.CNBLOGS.COM/TAOXINRUI/P/6431510.HTML》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109885535A (en) * | 2019-01-04 | 2019-06-14 | 平安科技(深圳)有限公司 | A kind of method and relevant apparatus of file storage |
CN110502711A (en) * | 2019-07-17 | 2019-11-26 | 汉海信息技术(上海)有限公司 | Page display method, device, electronic equipment and readable storage medium storing program for executing |
CN110502711B (en) * | 2019-07-17 | 2022-08-26 | 汉海信息技术(上海)有限公司 | Page display method and device, electronic equipment and readable storage medium |
CN111400251A (en) * | 2020-03-17 | 2020-07-10 | 深圳市卡牛科技有限公司 | File access method, device, server and storage medium based on gateway |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104408091B (en) | The date storage method and system of distributed file system | |
US9558194B1 (en) | Scalable object store | |
US9710535B2 (en) | Object storage system with local transaction logs, a distributed namespace, and optimized support for user directories | |
US7992037B2 (en) | Scalable secondary storage systems and methods | |
US9043540B2 (en) | Systems and methods for tracking block ownership | |
CN103229173B (en) | Metadata management method and system | |
US9628438B2 (en) | Consistent ring namespaces facilitating data storage and organization in network infrastructures | |
US8996490B1 (en) | Managing logical views of directories | |
US7797283B2 (en) | Systems and methods for maintaining distributed data | |
JP5856680B2 (en) | Method of single instance using file clone and file storage device using the same | |
CN102819599B (en) | The method building hierarchical directory in uncommon data distributed basis is breathed out in consistence | |
CN106201771B (en) | Data-storage system and data read-write method | |
US10691553B2 (en) | Persistent memory based distributed-journal file system | |
US20130226888A1 (en) | Systems and methods for caching data files | |
US20120054253A1 (en) | Method and System for Forming a Virtual File System at a Computing Device | |
CN103890738A (en) | System and method for retaining deduplication in a storage object after a clone split operation | |
Frey et al. | Probabilistic deduplication for cluster-based storage systems | |
CN111045857B (en) | Method for data backup and recovery, electronic device and computer readable storage medium | |
US9383936B1 (en) | Percent quotas for deduplication storage appliance | |
US11120046B2 (en) | Data replication in a distributed storage system | |
CN109522283A (en) | A kind of data de-duplication method and system | |
CN107357921A (en) | A kind of small documents storage localization method and system | |
US10558373B1 (en) | Scalable index store | |
CN107357920A (en) | The more copy data synchronous method and system of a kind of increment type | |
JP5556025B2 (en) | Storage system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171117 |
|
RJ01 | Rejection of invention patent application after publication |