CN110389848B - Partial repetition code construction method based on block construction and fault node repair method - Google Patents
Partial repetition code construction method based on block construction and fault node repair method Download PDFInfo
- Publication number
- CN110389848B CN110389848B CN201910554540.7A CN201910554540A CN110389848B CN 110389848 B CN110389848 B CN 110389848B CN 201910554540 A CN201910554540 A CN 201910554540A CN 110389848 B CN110389848 B CN 110389848B
- Authority
- CN
- China
- Prior art keywords
- block
- coding
- blocks
- row
- node
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0793—Remedial or corrective actions
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M13/00—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes
- H03M13/03—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words
- H03M13/05—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits
- H03M13/11—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits using multiple parity bits
- H03M13/1102—Codes on graphs and decoding on graphs, e.g. low-density parity check [LDPC] codes
- H03M13/1148—Structural properties of the code parity-check or generator matrix
- H03M13/118—Parity check matrix structured for simplifying encoding, e.g. by having a triangular or an approximate triangular structure
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M13/00—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes
- H03M13/03—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words
- H03M13/05—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits
- H03M13/11—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits using multiple parity bits
- H03M13/1102—Codes on graphs and decoding on graphs, e.g. low-density parity check [LDPC] codes
- H03M13/1191—Codes on graphs other than LDPC codes
- H03M13/1194—Repeat-accumulate [RA] codes
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
Abstract
The invention belongs to the field of computers, and relates to a method for constructing a partial repetition code based on a block construction. The method mainly comprises the steps of carrying out MDS coding on data blocks of an original file to generate coding blocks, constructing a lower triangular matrix, and carrying out blocking and copying processing on the coding blocks, so that the number of connected and stored movable nodes is greatly reduced in the single-node fault repairing process, and the I/O overhead of a repairing disk for repairing the fault node is reduced. In addition, the number of check blocks required by the part of repeated codes is small, the storage utilization rate of the system is high, the code construction process is simple, the popularization is easy, and the operability is strong.
Description
Technical Field
The invention belongs to the field of computers, and relates to a partial repetition code construction method and a fault node repairing method based on block construction.
Background
The scale of the distributed storage system is increased due to the massive information data, in order to ensure the availability of the data, the storage system usually adopts 'copy' to generate redundant data, a large amount of copy data needs to be stored to ensure the high reliability of the system, and the storage cost generated by a 'copy' redundant strategy is overhigh; in order to ensure the reliability of data, an "erasure code" strategy is generally adopted, and compared with a copy strategy, erasure codes can optimize the storage overhead of a distributed storage system, but the whole file must be restored in the process of repairing a single failed node, and the bandwidth overhead is too large. Aiming at the limitation of the redundancy strategy of 'copy' and 'erasure code', a regeneration code is provided, but the regeneration code has more connected nodes in the fault node repairing process, has higher disk I/O (input/output) overhead, and cannot meet the requirement of the current sea quantized storage node. And partial repeated codes fuse the copy and regeneration code technology, so that when a fault node is repaired, only a small number of data blocks are downloaded from partial survival nodes, the downloaded data blocks are transmitted to a new node, and the repair of the fault node can be completed without other operation operations, the repair complexity is low, but most of codes are constructed based on special models such as affine planes, combination designs, steiner systems, latin squares, hypergraphs and the like, and have certain complexity and limitation.
Disclosure of Invention
The invention aims to provide a part of repeated code construction method based on block construction and a fault node repairing method, which are used for solving the problems that the part of repeated code construction method in the prior art is complex, the repairing locality is large in the node repairing process and the like.
In order to realize the task, the invention adopts the following technical scheme:
the method for constructing the partial repetition code based on the block construction comprises the following steps:
step 1: dividing an original file into k original data blocks, and performing (n, k) MDS coding on the k original data blocks to obtain n coding blocks C 1 ,C 2 ,…C n And n is a positive integer;
step 2: constructing a lower triangular matrix with m rows and m columns, wherein n = m (m + 1)/2 and m is a positive integer, wherein the number of coding blocks stored in each row of the lower triangular matrix is increased by one line from top to bottom, and a coding block C is stored in the first row from top to bottom n Code block C to store the first row n Decomposes into n-1 and encodes the block C n-1 And C, storing the first two bits of the second line, and storing the first coding block C of the second line n-1 Decomposes into n-1-2 and encodes the block C n-1-2 And C 2 Storing the first two bits in the third row, and so on, and storing the first code block C in the m-1 row n-(1+2+...+m-2) Subscript n- (1 +2+ ·+ m-2) of (1) is decomposed into n- (1 +2+. ·+ m-1) and m-1 and encoding block C n-(1+2+...+m-1) And C m-1 Storing the first two digits of the mth row, then arranging the coding blocks with undecomposed subscripts in a sequence from small to large, and filling the coding blocks in sequence from top to bottom column by columnFilling the rest positions of the lower triangular matrix to complete the construction of the lower triangular matrix with m rows and m columns;
and step 3: partitioning the lower triangular matrix constructed in the step (2), wherein if m is an even number, the front m/2 line is a first partition, m/2 columns after the reciprocal in the lower triangular matrix are second partitions, and the rest coding blocks are third partitions; if m is an odd number, the front (m-1)/2 line is taken as a first block, the rear (m-1)/2 line in the lower triangular matrix is taken as a second block, and the rest coding blocks are taken as third blocks;
and 4, step 4: copying the first block and the second block and vertically overturning, enabling the overturned second block to be close to the first block of the lower triangular matrix for storage, enabling the overturned first block to be close to the second block of the lower triangular matrix for placement, copying the third block, and placing the copied third block behind the overturned second block.
The fault node repairing method comprises the following steps:
according to the block construction-based partial repetition code construction method, an original file M containing n coding blocks is stored in M nodes of a distributed storage system, each node stores M +1 coding blocks, when the number of connected surviving nodes does not exceed 2 when a single failed node is repaired, if a certain node fails, the coding blocks are collected from one to two surviving nodes, and the collected coding blocks are transmitted to a new node, so that the repairing of the failed node can be realized.
Compared with the prior art, the invention has the following technical characteristics:
1. in the node, the original data block is encoded by MDS to generate fewer check blocks, namely the storage rate of the system is higher. In addition, the repeated code constructing process of the part is simple, easy to popularize and strong in operability.
2. When a single node fails, the data reconstruction of the failed node can be quickly realized by downloading the coding blocks in the failed node from no more than two nodes, the operation of the repair process is simple, and the repair locality is small.
Drawings
Fig. 1 is a schematic diagram of a storage system having 10 coding blocks in an embodiment, where the repetition degree of the coding block is 2, and a part of the repetition code is constructed;
FIG. 2 is a schematic diagram of a storage system having 15 coding blocks in an embodiment, where the repetition degree of the coding blocks is 2, and a part of repetition codes are constructed;
FIG. 3 is a schematic diagram of a single node V1 failover comprising 4 nodes and 10 coding blocks in an embodiment;
fig. 4 is a schematic diagram of single-node V4 failover including 5 nodes and 15 coding blocks in an embodiment.
Detailed Description
The embodiment discloses a method for constructing a partial repetition code based on block construction, which comprises the following steps:
step 1: dividing an original file into k original data blocks, and performing (n, k) MDS coding on the k original data blocks to obtain n coding blocks C 1 ,C 2 ,…C n And n is a positive integer;
step 2: constructing a lower triangular matrix with m rows and m columns, wherein n = m (m + 1)/2 and m is a positive integer, wherein the number of coding blocks stored in each row of the lower triangular matrix is increased by one line from top to bottom, and a coding block C is stored in the first row from top to bottom n Code block C to store the first row n Decomposes the subscript n of (a) into n-1 and encodes the block C n-1 And C, storing the first two bits of the second line, and storing the first coding block C of the second line n-1 Decomposes into n-1-2 and encodes the block C n-1-2 And C 2 Storing the first two digits of the third row, and so on, and storing the first coding block C of the m-1 row n-(1+2+...+m-2) Subscript n- (1 +2+ ·+ m-2) of (1) is decomposed into n- (1 +2+. ·+ m-1) and m-1 and encoding block C n-(1+2+...+m-1) And C m-1 Storing the first two digits of the mth row, and ensuring that the coding blocks are not repeated in the coding block decomposition process; then, arranging the coding blocks with undecomposed subscripts in a sequence from small to large, and filling the rest positions of the lower triangular matrix row by row from top to bottom in sequence to complete the construction of the lower triangular matrix with m rows and m columns;
and step 3: partitioning the lower triangular matrix constructed in the step (2), wherein if m is an even number, the front m/2 line is a first partition, m/2 columns after the reciprocal in the lower triangular matrix are second partitions, and the rest coding blocks are third partitions; if m is an odd number, the front (m-1)/2 line is taken as a first block, the rear (m-1)/2 line in the lower triangular matrix is taken as a second block, and the rest coding blocks are taken as third blocks;
and 4, step 4: copying the first block and the second block and vertically overturning, enabling the overturned second block to be close to the first block of the lower triangular matrix for storage, enabling the overturned first block to be close to the second block of the lower triangular matrix for placement, copying the third block, placing the copied third block behind the overturned second block, and completing the construction of the FR code with the repetition degree of 2.
The invention aims to provide a part of repeated code construction method based on block construction, the part of repeated codes needs fewer check blocks, the storage utilization rate of a system is high, the repair locality is small when a single fault node is repaired, the code construction process is simple, the code is easy to popularize, and the operability is strong.
In this embodiment, a method for repairing a failed node is disclosed, including:
according to the block construction-based partial repetition code construction method implemented in embodiment 1, an original file M including n coding blocks is stored in M nodes of a distributed storage system, each node stores M +1 coding blocks, when a single failed node is repaired, the number of connected surviving nodes does not exceed 2, if a single node fails, the coding blocks are collected from one to two surviving nodes, and the collected coding blocks are transmitted to a new node, so that the repair of the failed node can be realized.
With the mass of stored data, nodes in a distributed storage system are correspondingly increased, more surviving nodes need to be connected to recover the data no matter erasure codes or regeneration codes are adopted in the process of repairing the fault nodes, and the access cost and the bandwidth cost of the nodes are increased.
Example 1
In this embodiment, a partial repetition code construction method based on a block construction is disclosed, and fig. 1 shows a storage scheme of 10 coding blocks in a distributed storage system, where the repetition degree of m =4 storage nodes is 2.
A file with the size of 7M is stored in a distributed storage system, firstly (4 x 5/2=10,7) MDS coding is carried out on an original file, and then the 10 coding blocks are represented by 1,2,3, \ 8230; 10. Coding block C 10 The index 10 of (a) is broken down into 10-1, i.e. 9 and 1, and the code block C is encoded 9 Index 9 of (a) is decomposed into 10-1-2, i.e. 7 and 2, coding block C 7 The subscript 7 of (a) is decomposed into 10-1-2-3, i.e., 4 and 3, but the block C is encoded 4 Subscript 4 of (a) cannot be further decomposed because 1,3,2 has already appeared. Then the rest coding blocks C are coded 5 ，C 6 ，C 8 In descending order, so that the first row stores one code block C 10 Subscript 10. The second row stores two code blocks C 9 And C 1 The third row stores the index of three code blocks 7,2,5 and the fourth row stores the index of 4 code blocks 4,3,6,8. The coding blocks in the first two rows are first sub-blocks of the lower triangle, the coding blocks in the last two rows are second sub-blocks of the lower triangle, and the rest coding blocks are third sub-blocks of the lower triangle. After the coding block of the second block is turned over, the coding block of the third block is sequentially placed behind the coding block of the first block, and then the coding block stored by the first node is: c 10 ，C 6 ，C 8 ，C 7 ，C 2 The second node stores the encoded blocks as follows: c 9 ，C 1 ，C 5 ，C 4 ，C 3 . Finally, the first block-dividing coding block after turning is placed behind the original second block-dividing coding block, and the coding block stored by the third node is: c 7 ，C 2 ，C 5 ，C 9 ，C 1 The fourth node stores the coding blocks as follows: c 4 ，C 3 ，C 6 ，C 8 ，C 10 。
Fig. 3 is a schematic diagram of fault repair of a single node V1 in this embodiment, and data C is respectively acquired from a node V3 and a node V4 7 ，C 2 And C and 6 ，C 8 ，C 10 and the data is transmitted to the node V1 to complete the repair of the node V1, and the number of connected nodes is 2 (the repair locality is 2) in the process.
Example 2
In the embodiment, a method for constructing a partial repetition code based on a block construction is disclosed, and fig. 2 shows a storage scheme of 15 coding blocks with a repetition degree of 2 and m =5 storage nodes in a distributed storage system.
The file with the size of 12M is stored in the distributed storage system, firstly (5 x 6/2=15, 12) MDS coding is carried out on the original file, and then the 15 coding blocks are represented by 1,2,3, \ 8230; 15. Coding block C 15 Decomposes into 15-1, i.e. 14 and 1, encodes block C 14 Is decomposed into 15-1-2, i.e. 12 and 2, encodes block C 12 The index 12 of (a) is decomposed into 15-1-2-3, i.e. 9 and 3, and the block C is coded 9 Index 9 of (a) is broken down into 15-1-2-3-4, i.e. 5 and 4, but code block C 5 Subscript 5 of (a) cannot be further decomposed because 1,4,3,2 has already appeared. Then the rest coding blocks C are processed 6 ，C 7 ，C 8 ，C 10 ，C 11 ，C 13 In order from small to large, so that the first row stores one code block C 15 Subscript 15 of ， Second row storage code block C 14， C 1 Subscript 14 and 1, third row store code block C 12 ，C 2 ，C 6 Subscript 12,2,6, fourth row store code blocks C 9 ，C 3 ，C 7 ，C 8 Subscript 9,3,7,8, fifth row store code block C 5 ，C 4 ，C 10 ，C 11 ，C 13 Subscripts 5,4, 10, 11, 13 of (a). The coding blocks in the first two rows are first blocks of the lower triangle, the coding blocks in the last two rows are second blocks of the lower triangle, and the rest coding blocks are third blocks of the lower triangle. After the coding block of the second block is turned over, and the coding block of the third block is sequentially placed behind the coding block of the first block, the coding block stored by the first node is: c 15 ，C 11 ，C 13 ，C 12 ，C 2 ，C 6。 The second node stores encoded blocks as: c 14 ，C 1 ，C 8 ，C 9 ，C 3 ，C 7 . The third node stores the coding blocks as follows: c 12 ，C 2 ，C 6 ，C 5 ，C 4 ，C 10。 Finally, the first small block coding block after turning over is placed behind the original second small block coding block, and then the coding block stored by the fourth node is: c 9 ，C 3 ，C 7 ，C 8 ，C 14 ，C 1 . The coding block stored by the fifth node is: c 5 ，C 4 ，C 10 ，C 11 ，C 13 ，C 15。
Fig. 4 is a schematic diagram of fault repair of a single node V4 in this embodiment, and data C is respectively acquired from the nodes 2 14 ，C 1 ，C 8 ，C 9 ，C 3 ，C 7 And the data is transmitted to the node V4 to complete the repair of the node V4, and the number of connected nodes is 1 (the repair locality is 1) in the process.
Claims (2)
1. The method for constructing the partial repetition code based on the block construction is characterized by comprising the following steps of:
step 1: dividing an original file into k original data blocks, and performing (n, k) MDS coding on the k original data blocks to obtain n coding blocks C 1 ,C 2 ,…C n And n is a positive integer;
and 2, step: constructing a lower triangular matrix with m rows and m columns, wherein n = m (m + 1)/2 and m is a positive integer, wherein the number of coding blocks stored in each row of the lower triangular matrix is increased by one from top to bottom row by row and one coding block C is stored in the first row from top to bottom n Code block C to store the first row n Decomposes into n-1 and encodes the block C n-1 And C, storing the first two bits of the second line, and storing the first coding block C of the second line n-1 Decomposes the subscript n-1 into n-1-2 and encodes the block C n-1-2 And C 2 Storing the first two digits of the third row, and so on, and storing the m-1 th rowOne coding block C n-(1+2+...+m-2) Subscript n- (1 +2+ ·+ m-2) of (1) is decomposed into n- (1 +2+. ·+ m-1) and m-1 and encoding block C n-(1+2+...+m-1) And C m-1 Storing the first two digits of the mth row, then arranging the coding blocks with undecomposed subscripts according to the sequence from small to large, and filling the remaining positions of the lower triangular matrix row by row from top to bottom in sequence to complete the construction of the lower triangular matrix for constructing the m rows and the m columns;
and 3, step 3: partitioning the lower triangular matrix constructed in the step (2), wherein if m is an even number, the front m/2 line is a first partition, m/2 columns after the reciprocal in the lower triangular matrix are second partitions, and the rest coding blocks are third partitions; if m is an odd number, the front (m-1)/2 line is taken as a first block, the rear (m-1)/2 line in the lower triangular matrix is taken as a second block, and the rest coding blocks are taken as third blocks;
and 4, step 4: copying the first block and the second block and vertically overturning, enabling the overturned second block to be close to the first block of the lower triangular matrix for storage, enabling the overturned first block to be close to the second block of the lower triangular matrix for placement, copying the third block, placing the copied third block behind the overturned second block, and completing the construction of the FR code with the repetition degree of 2.
2. The method for repairing the fault node is characterized by comprising the following steps:
the method for constructing partially repeated codes based on block construction as claimed in claim 1, storing an original file M containing n coding blocks into M nodes of the distributed storage system, each node storing M +1 coding blocks, when the number of connected surviving nodes does not exceed 2 when repairing a single failed node, if a single node fails, collecting the coding blocks from one to two surviving nodes only, and transmitting the collected coding blocks to a new node, thereby realizing the repair of the failed node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910554540.7A CN110389848B (en) | 2019-06-25 | 2019-06-25 | Partial repetition code construction method based on block construction and fault node repair method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910554540.7A CN110389848B (en) | 2019-06-25 | 2019-06-25 | Partial repetition code construction method based on block construction and fault node repair method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110389848A CN110389848A (en) | 2019-10-29 |
| CN110389848B true CN110389848B (en) | 2023-03-14 |
Family
ID=68285753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910554540.7A Active CN110389848B (en) | 2019-06-25 | 2019-06-25 | Partial repetition code construction method based on block construction and fault node repair method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110389848B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110990188B (en) * | 2019-11-19 | 2023-03-24 | 长安大学 | Construction method of partial repetition code based on Hadamard matrix |
| CN110990375B (en) * | 2019-11-19 | 2023-01-31 | 长安大学 | Method for constructing heterogeneous partial repeat codes based on adjusting matrix |
| CN111125014B (en) * | 2019-11-19 | 2023-02-28 | 长安大学 | Construction method of flexible partial repeat code based on U-shaped design |
| CN111030701B (en) * | 2019-11-26 | 2023-03-24 | 长安大学 | Method for constructing partial repetition code based on Harary graph |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101340193A (en) * | 2008-08-12 | 2009-01-07 | 普天信息技术研究院有限公司 | Constructing method, encoder and decoder of low density check code |
| CN102007722A (en) * | 2008-03-26 | 2011-04-06 | 马维尔国际贸易有限公司 | Block encoding with a variable rate block code |
| WO2016058289A1 (en) * | 2015-01-20 | 2016-04-21 | 北京大学深圳研究生院 | Mds erasure code capable of repairing multiple node failures |
| CN108540520A (en) * | 2018-02-06 | 2018-09-14 | 长安大学 | Locality reparation coding based on part duplication code and node failure restorative procedure |
| CN108762978A (en) * | 2018-03-29 | 2018-11-06 | 长安大学 | A kind of constructed in groups method of Part portions repetitive cycling code |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7178080B2 (en) * | 2002-08-15 | 2007-02-13 | Texas Instruments Incorporated | Hardware-efficient low density parity check code for digital communications |
| US20150095747A1 (en) * | 2013-09-30 | 2015-04-02 | Itzhak Tamo | Method for data recovery |
| US10031806B2 (en) * | 2016-11-01 | 2018-07-24 | Cisco Technology, Inc. | Efficient repair of erasure coded data based on coefficient matrix decomposition |
| CN108647108B (en) * | 2018-03-21 | 2021-04-13 | 长安大学 | Construction method of minimum bandwidth regeneration code based on cyclic VFRC |
-
2019
- 2019-06-25 CN CN201910554540.7A patent/CN110389848B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102007722A (en) * | 2008-03-26 | 2011-04-06 | 马维尔国际贸易有限公司 | Block encoding with a variable rate block code |
| CN101340193A (en) * | 2008-08-12 | 2009-01-07 | 普天信息技术研究院有限公司 | Constructing method, encoder and decoder of low density check code |
| WO2016058289A1 (en) * | 2015-01-20 | 2016-04-21 | 北京大学深圳研究生院 | Mds erasure code capable of repairing multiple node failures |
| CN108540520A (en) * | 2018-02-06 | 2018-09-14 | 长安大学 | Locality reparation coding based on part duplication code and node failure restorative procedure |
| CN108762978A (en) * | 2018-03-29 | 2018-11-06 | 长安大学 | A kind of constructed in groups method of Part portions repetitive cycling code |
Non-Patent Citations (4)
| Title |
|---|
| Regenerating Codes for Distributed Storage Networks;Nihar B. Shah 等;《 Arithmetic of Finite Fields》;20100630;全文 * |
| 分布式存储中的再生码综述;郝杰等;《重庆邮电大学学报(自然科学版)》;20130215(第01期);全文 * |
| 分布式存储系统中基于部分重复循环码的局部修复码构造;王静等;《电子测量与仪器学报》;20190415(第04期);全文 * |
| 基于简单再生码的分段编码方案;王静等;《计算机科学》;20160815(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110389848A (en) | 2019-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110389848B (en) | Partial repetition code construction method based on block construction and fault node repair method | |
| CN108540520B (en) | Partial repeated code based locality repairing coding and node fault repairing method | |
| US11531593B2 (en) | Data encoding, decoding and recovering method for a distributed storage system | |
| CN104052576B (en) | Data recovery method based on error correcting codes in cloud storage | |
| CN109643258B (en) | Multi-node repair using high-rate minimal storage erase code | |
| US8645799B2 (en) | Storage codes for data recovery | |
| CN104461781B (en) | A kind of data block method for reconstructing based on correcting and eleting codes | |
| US8775860B2 (en) | System and method for exact regeneration of a failed node in a distributed storage system | |
| US20160182088A1 (en) | Method For File Updating And Version Control For Linear Erasure Coded And Network Coded Storage | |
| CN106776112B (en) | A kind of locality reparation coding method based on Pyramid code | |
| CN106484559A (en) | A kind of building method of check matrix and the building method of horizontal array correcting and eleting codes | |
| CN111078460B (en) | Fast erasure code calculation method | |
| CN106776129B (en) | A kind of restorative procedure of the multinode data file based on minimum memory regeneration code | |
| CN107844272A (en) | A kind of cross-packet coding and decoding method for improving error correcting capability | |
| CN108762978B (en) | Grouping construction method of local part repeated cyclic code | |
| CN105356968B (en) | The method and system of network code based on cyclic permutation matrices | |
| CN112000512B (en) | Data restoration method and related device | |
| CN113901069B (en) | Data storage method and device of distributed database | |
| CN109086000B (en) | Three-fault-tolerant data layout method in RAID storage system | |
| CN103746774A (en) | Error resilient coding method for high-efficiency data reading | |
| CN102843212B (en) | Coding and decoding processing method and device | |
| CN111858169A (en) | Data recovery method, system and related components | |
| CN110781024B (en) | Matrix construction method of symmetrical partial repetition code and fault node repairing method | |
| CN110532128B (en) | Erasure code coding and data reconstruction method for reducing data updating cost | |
| CN109343998B (en) | Erasure code-based full-distribution restoration method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |