CN106293537A - A kind of autonomous block management method of the data-intensive file system of lightweight - Google Patents
A kind of autonomous block management method of the data-intensive file system of lightweight Download PDFInfo
- Publication number
- CN106293537A CN106293537A CN201610665489.3A CN201610665489A CN106293537A CN 106293537 A CN106293537 A CN 106293537A CN 201610665489 A CN201610665489 A CN 201610665489A CN 106293537 A CN106293537 A CN 106293537A
- Authority
- CN
- China
- Prior art keywords
- data
- memory node
- block
- data memory
- data block
- 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
- 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
- G06F3/0604—Improving or facilitating administration, e.g. storage management
-
- 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
-
- 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
- G06F3/0643—Management of files
Abstract
The invention discloses the autonomous block management method of the data-intensive file system of a kind of lightweight, (ISD is divided by cross transfer, Intersected Shifted Declustering) realize the data block mapping to data memory node, the quick lookup of data block in data memory node, the quick redistribution etc. of data block when the fast quick-recovery of data block and newly added data memory node when data memory node lost efficacy, host node is made only to be responsible for the storage and maintenance of file name space in data-intensive file system, and data block is to the mapping relation information storage and maintenance of data memory node, and data memory node time the replacement of data block and new data memory node add when losing efficacy the redistribution etc. of data block all completed by data memory node autonomy.This invention saves the memory headroom of host node in data-intensive file system, improves the disposal ability of host node, can increase substantially the block management data efficiency of data-intensive file system under big data environment.
Description
Technical field
The present invention relates to computer security technique, particularly relate to the autonomy of the data-intensive file system of a kind of lightweight
Block management method.
Background technology
Data-intensive file system DiFS, such as Google's file system GFS, Hadoop distributed file system HDFS
Deng, have become as the main file system of big data storage management.Current data-intensive file system DiFS uses principal and subordinate
Formula framework, host node (meta data server) manages all of metadata, deposits from node (data memory node) the most responsible data
Storage.In order to maintain high availability, data file is generally divided into the block of fixed size by these storage systems, and each data block is usual
There are 3 copies, and they are all assigned in the data memory node of different clusters.Host node must record hundreds and thousands of
The address of data memory node, and record the data block map information to these memory nodes of all data files.Further,
Host node must check the change of the address mapping information of all data blocks termly.Along with the continuous increase of data volume, these
Metadata information does not occupy the memory headroom of host node, affects the disposal ability of host node, and seriously limits master
The extensibility of node.
In order to solve the problem that data-intensive file system exists, by the distribution of data file physical block with safeguard from unit
Separating in data management, the maintaining method by each data memory node execution data block to memory node map information should
Transport and give birth to.Adopting said method, host node need not preserve substantial amounts of data block metadata information again and data block is deposited to data
Storage node map information, but need with one group of data block to data memory node, data memory node to data block it
Between invertible mapping function complete.
The data of data-intensive file system management magnanimity, these data have the following characteristics that 1) data volume is big, data
Total amount increases fast;2) data storage performance demand is high;3) high reliability and high restorability are required: when data occur to lose or number
When losing efficacy according to memory node, on the premise of not affecting normal work, it is possible to quick extensive restored data;4) requirement can be quick
The storage position of lookup data block;5) require as far as possible the fewest memory headroom taking host node and the fewest affect host node
Disposal ability;
As seen from the above analysis, the management method of traditional file systems is not suitable with the pipe of data-intensive file system
Reason, main cause: 1) along with the continuous increase of data volume, the storage of file data blocks address table will take substantial amounts of storage sky
Between;2) host node is responsible for the maintenance of file data blocks address table, along with being continuously increased of file data blocks address table, is substantially reduced
The disposal ability of host node;3) being continuously increased of data volume not only occupies the substantial amounts of memory space of host node, increases ground
The metadata maintenance costs such as location, also reduce the extensibility of host node simultaneously;4) each data memory node is storing
Will first seek advice from host node during with inquiry, so increase the time of addressing.
Summary of the invention
Data block for data-intensive file system stores and searching and managing demand, the invention provides a kind of light weight
The autonomous block management method of the data-intensive file system of level, by by the distribution of physical data block, unit's number of inquiring about and be correlated with
Separate from traditional metadata management according to safeguarding, each data memory node complete, reduce host node memory space
Expense and burden.The present invention can promote the extensibility of the data-intensive file system under big data environment, reduce data
Block addressing the time, and can first mate's degree improve whole system performance.
The know-why of the present invention is, the present invention is by cross transfer division methods (ISD, Intersected
Shifted Declustering) realize the autonomous management of data block, i.e. by realizing data block with one group of reversible mathematical function
To data memory node, and data memory node is to the mapping of data block, completes the distributed storage of data block and fast quick checking
Ask.
The present invention specifically comprises following several operation:
Operation 1, data block storage operation;
Operation 2, data block search operation;
Operation 3, fail data memory node crash handling operation;
Operation 4, interpolation new data memory node operation.
(1) data block storage operation comprises the following steps:
Step 1.1, host node select data block place logical groups (LG) by reversible linear hash function;
Step 1.2, host node select data memory node storage data in logical groups by reversible displacement segmentation function
Blocks of data;
Step 1.3, data memory node storage data block data and data block address map information.
(2) data block search operation comprises the following steps:
Step 2.1, data block b place data memory node calculate data block b according to its call number with reverse invertible function
The new ID of place logical groups;
Step 2.2, data block b place data memory node, according to data block b place logical groups ID, use reverse invertible function
Calculating the physics ID of data block b, the data file complete for file system recovery provides condition;
Step 2.3, data memory node, according to the physics ID of data block, obtain data block and believe in the mapping of memory node
Breath;
Step 2.4, data memory node send file system according to the fetch data data of block b of the map information of data block b.
(3) fail data memory node crash handling operation comprises the following steps:
Step 3.1, determine fail data memory node place logic groups;
The data memory node loading minimum in logic groups beyond step 3.2, selection data storage failure node is made
For backup node;
Step 3.3, multiple post data memory node use intelligence restructuring mapping method to replicate parallel in each logical groups
The data comprised in this corresponding fail data memory node.
(4) add the operation of new data memory node to comprise the following steps:
The average load COV of data memory node in all logical groups in step 4.1, calculating whole systemave;
Step 4.2, one logical groups of selection, calculate load C OV maximum in all data memory nodes in this groupmax;
Step 4.3, compare COVmaxAnd COVaveSize, if COVmax≥COVave, with being newly added data memory node
Replace this data memory node of logical groups.Otherwise, choose next logical groups, repeat step 4.1, step 4.2 and step 4.3,
Until the load of the data memory node being newly added reaches or close to the average load of data memory node in system.
The advantage of this data-intensive file system autonomy block management method is:
(1) host node memory space expense is greatly reduced.By data block to data memory node map information from tradition
Metadata in separate, stored by the carrying out that each data memory node is autonomous and managed, host node need not preserve and
Safeguarding substantial amounts of data block address information, the metadata information making host node preserve reduces more than 90% than traditional file systems.
(2) disposal ability of host node it is greatly improved.Map information between data block and data memory node is by often
The storage and maintenance that individual data memory node is autonomous, eliminates the burden of host node.This kind of method and distributed file system
HDFS compares, and the process performance of host node can be made to improve more than 30%.
(3) improve restorability and the extensibility of system.When data memory node fault by using intelligence weight
Group mapping method, when adding new data memory node by using decoupling address mapping method, so only migrates minority data
Block just can complete recovering and the duplication of newly added back end data of fail data node data, and substantially increase system can
Restorative and extensibility.
Accompanying drawing explanation
Fig. 1 is the flow chart of concrete operations of the present invention;
Fig. 2 is the schematic diagram that in the present invention, host node and data memory node management function divide;
Fig. 3 is continuous blocks to the mapping of back end and back end to the example of the lookup of block;
Fig. 4 is the example of back end failure recovery process;
Fig. 5 is the example of new data node adding procedure.
Detailed description of the invention
For the technological means making the present invention realize, creation characteristic, reach purpose and be easy to understand with effect, below knot
Close diagram and specific embodiment, the autonomy of the data-intensive file system of a kind of lightweight that the present invention propose is expanded on further
Block management method.
A kind of autonomous block management method of the data-intensive file system of lightweight, real by one group of reversible mathematical function
Existing data block is to back end and back end to the mapping of data block.As in figure 2 it is shown, each node concrete function in the present invention
Divide: host node is only responsible for system name space maintenance, the distribution of data block to data memory node, each data memory node
Management;Each data memory node is responsible for the consistency check of data block, data block is recovered and the mapping of data memory node
Information storage and maintenance.
As it is shown in figure 1, autonomous block management method of the present invention, specifically include following several operation:
Operation 1, data block storage operation;
Operation 2, data block search operation;
Operation 3, fail data memory node crash handling operation;
Operation 4, interpolation new data memory node operation.
(1) data block storage operation, comprises the following steps:
Step 1.1, host node select block place logical groups (LG) by reversible linear hash function;
Step 1.2, host node select data memory node storage data in logical groups by reversible displacement segmentation function
Blocks of data;
Step 1.3, data memory node storage data block data and data block address map information.
In the step 1.1 of data block storage operation, selected the logic at data block place by reversible linear hash function
Group (LG) formula:
Wherein, g is intended to logical groups ID mapped, and x is group number current in system, the logical groups in system when X is to start
Number, it is newly-increased logical groups number that b is intended to store data block block ID, s in its file,
In the step 1.2 of data block storage operation, data in logical groups are selected to store by reversible displacement segmentation function
The process of node includes:
A) the new block identification after data block b is mapped to logical groups g is calculated, its formula:
Wherein, a is data block new logo in logical groups g, and x is current logic group number, and X is initial logical groups number, b
Data-oriented block ID, s are newly-increased logical groups numbers,
B) the index ID of the data memory node that data block b is mapped in logical groups g is calculated, its formula:
D=node (a, i)=(a+i) %4 (3)
Wherein, a is data block b new data block mark in logical groups g, i be data block b copy number (value 0,1,
2), d is the index (value 0,1,2,3) of the data memory node that data block b selects in logical groups.
Described copy number, refers to that intensive file system provides three copies for each data block, fully ensures that it can
By property, they are numbered 0,1,2 years old;The index of described data memory node, refers to all data memory nodes in a logical groups
Numbering, in the present invention, each logical groups includes 4 data memory nodes, and its call number is respectively 0,1,2,3.
(2) data block search operation comprises the following steps:
Step 2.1, data block b place data memory node calculate data block b according to its call number with reverse invertible function
The new ID of place logical groups;
Step 2.2, data block b place data memory node, according to data block b place logical groups ID, use reverse invertible function
Calculating the physics ID of data block b, the data file complete for file system recovery provides condition;
Step 2.3, data memory node, according to the physics ID of data block, obtain data block and believe in the mapping of memory node
Breath;
The data that step 2.4, data memory node obtain data block b according to the map information of data block b deliver to file system
System.
Step 2.1 in data block search operation calculates number according to data memory node call number d with reverse invertible function
According to the new ID of block b place logical groups, its formula:
D=(a+i) %4 → can inverse operation → a=4 j+ (d-i) %4 (4)
Wherein i represents the copy number of data block, can take 0,1,2 with iteration, j is desirable 0,1,2 ..., n etc.;
Step 2.2 in data block search operation reversely invertible function calculates the physics ID of data block b, its formula:
Wherein, g is the index comprising data-oriented memory node logical groups,
Fig. 3 (a) be continuous print data block by linear Hash mapping to each logical groups, and by migrate division realize number
According to block distributed storage of each data memory node in logical groups;Fig. 3 (b) is as a example by back end 2, demonstrates by can
Inverse function realizes the reverse process searching data block.
(3) fail data memory node crash handling operation comprises the following steps:
Step 3.1, determine fail data memory node place logic groups;
The data memory node loading minimum in logic groups beyond step 3.2, selection data storage failure node is made
For backup node;
Step 3.3, multiple post data memory node use intelligence restructuring mapping method to replicate parallel in each logical groups
The data comprised in this corresponding fail data memory node.
Described intelligence restructuring mapping method, is to choose post data memory node number and comprise fail data memory node
Logical groups number equal, a fail data memory node is likely to be contained in multiple logical groups, and each post data is deposited
Storage node is only responsible for replicating the part data in this fail data memory node in a corresponding logical groups.
Fig. 4, as a example by back end 2 lost efficacy, demonstrates each logical groups and back end 2 is replaced recovery process.
(4) adding the operation of new data memory node, main employing decouples address mapping method, comprises the following steps:
The average load COV of data memory node in all logical groups in step 4.1, calculating whole systemave;
Step 4.2, one logical groups of selection, calculate load C OV maximum in all data memory nodes in this groupmax;
Step 4.3, compare COVmaxAnd COVaveSize, if COVmax≥COVave, with being newly added data memory node
Replace the data memory node loading maximum in logical groups.Otherwise, choose next logical groups, repeat step 4.1, step 4.2
With step 4.3, the load until the data memory node being newly added reaches or bears close to the average of data memory node in system
Till load.
Fig. 5 demonstrates system and adds new data node node128Constitute new new logic group LG1000Time, the number of whole system
According to block transition process.
By Fig. 4 and Fig. 5 it can be seen that system by invertible function and uses intelligence restructuring mapping method and uses decoupling
Address mapping method, when making back end lose efficacy with the interpolation of new data node, the most little data block migration, fully ensure that
The stability of system and the availability to user.
This method is illustrated below with an example.
Selection HDFS is as data-intensive file system, by 10000 back end of emulation, 1000000 data
Under the big data environment of block, using the autonomous block management method of data-intensive file system of lightweight and do not using the party
During method, host node EMS memory occupation situation is as shown in table 1, and it is as shown in table 2 that host node CUP takies situation.Wherein 1000000 data block
Being generally evenly distributed in 10000 back end, each data block size is 64MB.
Table 1 host node management data block EMS memory occupation situation
Data section is counted | 1000 | 2000 | 5000 | 7000 | 9000 | 10000 |
Committed memory (MB) after optimization | 15 | 20 | 27 | 36 | 42 | 50 |
It is not optimised committed memory (MB) | 180 | 186 | 189 | 192 | 194 | 196 |
Table 2 host node management data block CPU takies situation
Data section is counted | 500 | 2000 | 3000 | 4000 | 5000 |
CPU usage (%) after optimization | 1.4 | 2.3 | 2.5 | 3.1 | 4.2 |
It is not optimised rear CPU usage (%) | 6.3 | 12.1 | 16.6 | 19.8 | 23.2 |
Knowable to Tables 1 and 2, after using the autonomous block management method of data-intensive file system of lightweight, main joint
The EMS memory occupation situation of point and the situation that takies of CPU are substantially better than the autonomy of the data-intensive file system being provided without lightweight
The situation of block management method.
Although present disclosure has been made to be discussed in detail by above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read foregoing, for the present invention's
Multiple amendment and replacement all will be apparent from.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (7)
1. the autonomous block management method of the data-intensive file system of a lightweight, it is characterised in that data-intensive literary composition
Part system passes through cross transfer division methods, it is achieved the autonomous management of data block, i.e. by using one group of reversible mathematical function, real
Existing data block is to data memory node, and data memory node is to the mapping of data block, complete the distributed storage of data block with
Search;
Realize data block storage operation by described autonomous block management method, comprise the following steps:
Step 1.1, host node, by reversible linear hash function, select data block place logical groups;
Step 1.2, host node, by reversible displacement segmentation function, select data memory node in described logical groups;
Step 1.3, at the data memory node chosen, the data of storage data block and data block address map information.
2. the autonomous block management method of the data-intensive file system of lightweight as claimed in claim 1, it is characterised in that
Realize data block search operation by described autonomous block management method, comprise the following steps:
Step 2.1, data block place data memory node, according to its call number, calculate data block place with reverse invertible function and patrol
Collect the new ID of group;
Step 2.2, data block place data memory node are according to the new ID of data block place logical groups, with reverse invertible function meter
Calculate the physics ID of data block;
Step 2.3, data memory node, according to the physics ID of data block, obtain the data block map information at memory node;
Step 2.4, data memory node deliver to data-intensive literary composition according to the map information of data block, the data obtaining data block
Part system.
3. the autonomous block management method of the data-intensive file system of lightweight as claimed in claim 2, it is characterised in that
The crash handling realizing fail data memory node by described autonomous block management method operates, and comprises the following steps:
Step 3.1, determine fail data memory node place logic groups;
Logic groups beyond step 3.2, selection data storage failure node loads the data memory node of minimum as rear
Slave node;
Step 3.3, multiple post data memory node use intelligence restructuring mapping method, corresponding in parallel each logical groups of duplication
This fail data memory node in the data that comprise;
Described intelligence restructuring mapping method, is to make the post data memory node number chosen and comprise fail data memory node
Logical groups number is equal, and a fail data memory node is comprised in multiple logical groups, and the storage of each post data
Node only replicates the part data of this fail data memory node in a corresponding logical groups.
4. the autonomous block management method of the data-intensive file system of lightweight as described in Claims 2 or 3, its feature exists
In,
Realize adding new data memory node by described autonomous block management method to operate, wherein use decoupling address mapping side
Method, comprises the following steps:
The average load COV of data memory node in all logical groups in step 4.1, calculating whole systemave;
Step 4.2, select any one logical groups, calculate load maximum in all data memory nodes in this logical groups
COVmax;
Step 4.3, compare COVmaxAnd COVaveSize, if COVmax≥COVave, replace with the data memory node being newly added
Change the data memory node loading maximum in logical groups;Otherwise, next logical groups, repeated execution of steps 4.1, step are chosen
4.2 and step 4.3, until the load of the data memory node being newly added reaches or close to data memory node average in system
Till load.
5. the autonomous block management method of the data-intensive file system of lightweight as claimed in claim 1, it is characterised in that
In step 1.1, by the formula of reversible linear hash function selection data block place logical groups:
Wherein, g is logical groups ID, and x is current logic group number in system, and the logical groups number in system when X is initial, b is intended to deposit
The data block of storage data block ID in its file, s is newly-increased logical groups number,
In step 1.2, the process of data memory node in logical groups is selected to include by reversible displacement segmentation function:
A) the new block identification after data block b is mapped to logical groups g is calculated, its formula:
Wherein, a is data block b new logo in logical groups g;
B) the index ID of the data memory node that data block b is mapped in logical groups g is calculated, its formula:
D=node (a, i)=(a+i) %4 (3)
Wherein, i is the copy number of data block b, and d is the call number of the data memory node that data block b selects in logical groups.
6. the autonomous block management method of the data-intensive file system of lightweight as claimed in claim 5, it is characterised in that
In step 2.1, calculate the new ID of data block b place logical groups with reverse invertible function;
A=4 j+ (d-i) %4 (4)
This formula is by carrying out inverse operation obtaining to d=(a+i) %4;
Wherein, the copy i iteration of data block takes 0,1,2, and j takes zero or positive integer;
In step 2.2, with reverse invertible function calculate data block b physics ID:
7. the autonomous block management method of the data-intensive file system of lightweight as claimed in claim 1, it is characterised in that
In described data-intensive file system, carry out system name space maintenance by host node, data block to data stores
The distribution of node, the management of each data memory node;
And, it is responsible for the consistency check of data block, data block recovery and data memory node by each data memory node
Map information storage and maintenance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610665489.3A CN106293537B (en) | 2016-08-12 | 2016-08-12 | A kind of autonomous block management method of the data-intensive file system of lightweight |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610665489.3A CN106293537B (en) | 2016-08-12 | 2016-08-12 | A kind of autonomous block management method of the data-intensive file system of lightweight |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106293537A true CN106293537A (en) | 2017-01-04 |
CN106293537B CN106293537B (en) | 2019-11-12 |
Family
ID=57670722
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610665489.3A Active CN106293537B (en) | 2016-08-12 | 2016-08-12 | A kind of autonomous block management method of the data-intensive file system of lightweight |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106293537B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783398A (en) * | 2019-01-18 | 2019-05-21 | 上海海事大学 | One kind is based on related perception page-level FTL solid state hard disk performance optimization method |
CN114844911A (en) * | 2022-04-20 | 2022-08-02 | 网易(杭州)网络有限公司 | Data storage method and device, electronic equipment and computer readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101488104A (en) * | 2009-02-26 | 2009-07-22 | 北京世纪互联宽带数据中心有限公司 | System and method for implementing high-efficiency security memory |
US20140052706A1 (en) * | 2011-04-29 | 2014-02-20 | Prateep Misra | Archival storage and retrieval system |
CN104052576A (en) * | 2014-06-07 | 2014-09-17 | 华中科技大学 | Data recovery method based on error correcting codes in cloud storage |
CN104077423A (en) * | 2014-07-23 | 2014-10-01 | 山东大学(威海) | Consistent hash based structural data storage, inquiry and migration method |
-
2016
- 2016-08-12 CN CN201610665489.3A patent/CN106293537B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101488104A (en) * | 2009-02-26 | 2009-07-22 | 北京世纪互联宽带数据中心有限公司 | System and method for implementing high-efficiency security memory |
US20140052706A1 (en) * | 2011-04-29 | 2014-02-20 | Prateep Misra | Archival storage and retrieval system |
CN104052576A (en) * | 2014-06-07 | 2014-09-17 | 华中科技大学 | Data recovery method based on error correcting codes in cloud storage |
CN104077423A (en) * | 2014-07-23 | 2014-10-01 | 山东大学(威海) | Consistent hash based structural data storage, inquiry and migration method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783398A (en) * | 2019-01-18 | 2019-05-21 | 上海海事大学 | One kind is based on related perception page-level FTL solid state hard disk performance optimization method |
CN114844911A (en) * | 2022-04-20 | 2022-08-02 | 网易(杭州)网络有限公司 | Data storage method and device, electronic equipment and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106293537B (en) | 2019-11-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100565512C (en) | Eliminate the system and method for redundant file in the document storage system | |
US10761758B2 (en) | Data aware deduplication object storage (DADOS) | |
US10620862B2 (en) | Efficient recovery of deduplication data for high capacity systems | |
CN103136114B (en) | Storage means and memory storage | |
CN103152395B (en) | A kind of storage means of distributed file system and device | |
US10031675B1 (en) | Method and system for tiering data | |
CN103874980B (en) | Mapping in a storage system | |
US20230013281A1 (en) | Storage space optimization in a system with varying data redundancy schemes | |
US10176113B2 (en) | Scalable indexing | |
CN107798130B (en) | Method for storing snapshot in distributed mode | |
CN104395904B (en) | Efficient data object storage and retrieval | |
CN102222085B (en) | Data de-duplication method based on combination of similarity and locality | |
US10810161B1 (en) | System and method for determining physical storage space of a deduplicated storage system | |
CN101963982B (en) | Method for managing metadata of redundancy deletion and storage system based on location sensitive Hash | |
CN101777017B (en) | Rapid recovery method of continuous data protection system | |
US20120030477A1 (en) | Scalable segment-based data de-duplication system and method for incremental backups | |
CN104077423A (en) | Consistent hash based structural data storage, inquiry and migration method | |
CN103080910A (en) | Storage system | |
CN107391391A (en) | The method, system and solid state hard disc of data copy are realized in the FTL of solid state hard disc | |
CN104317669A (en) | Cloud heterogeneous storage system and data copy management method thereof | |
CN104462389A (en) | Method for implementing distributed file systems on basis of hierarchical storage | |
CN104951464B (en) | Date storage method and system | |
CN108073472B (en) | Memory erasure code distribution method based on heat perception | |
CN107944041A (en) | A kind of storage organization optimization method of HDFS | |
CN108141229A (en) | Damage the efficient detection of data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |