CN110781024B - Matrix construction method of symmetrical partial repetition code and fault node repairing method - Google Patents
Matrix construction method of symmetrical partial repetition code and fault node repairing method Download PDFInfo
- Publication number
- CN110781024B CN110781024B CN201910930824.1A CN201910930824A CN110781024B CN 110781024 B CN110781024 B CN 110781024B CN 201910930824 A CN201910930824 A CN 201910930824A CN 110781024 B CN110781024 B CN 110781024B
- Authority
- CN
- China
- Prior art keywords
- matrix
- node
- nodes
- repair
- blocks
- 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
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1076—Parity data used in redundant arrays of independent storages, e.g. in RAID systems
Abstract
The invention belongs to the field of computers, and discloses a matrix construction method of a symmetrical part repetition code and a fault node repairing method. The matrix construction method of the symmetrical part repetition code is mainly based on the claw-shaped matrix s 1 Constructing an adjustment matrix s 2 Then the claw matrix s 1 And an adjustment matrix s 2 And adding the elements at the corresponding positions to obtain an incidence matrix s of the symmetrical part repetition code, thereby completing the matrix construction of the symmetrical part repetition code. The system storage rate of the constructed symmetrical part repetition code is high, and a plurality of repair schemes with the repair degree of 2 are provided for repairing a single-fault node. When any two nodes fail, a repair scheme with the node repair degree of 2 also exists. Compared with the traditional partial repeated code, the disk I/O overhead is relatively small when the node is repaired, two-node faults can be solved, 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 particularly relates to a matrix construction method of a symmetrical part repetition code and a fault node repairing method.
Background
The scale of the distributed storage system is increased due to the massive information data, in order to ensure the availability and reliability of the data, the storage system usually adopts 'copy' and 'erasure code' strategies to generate redundant data, and the storage cost generated by the 'copy' redundant strategy is too high; although erasure codes can optimize the storage overhead of the distributed storage system, the entire 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 redundancy strategies of 'copy' and 'erasure code', dimakis et al propose regeneration codes, but the regeneration codes have more connected nodes in the fault node repair process and higher disk I/O (input/output) overhead. And the partial repeated codes integrate the copying and regeneration code technology, so that when the failed 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, the repair of the failed node can be completed without other operation, and the repair complexity is low.
The FR codes constructed by pairwise balanced design or the FR codes constructed by incomplete balanced block design need to meet the complex parameter requirements, the construction process of the FR codes constructed by hypergraph dyeing and the FR codes constructed by projection geometry is complicated, and certain parameter limitation exists according to the geometry of the graph. Because the amount of data stored in the storage system is large, the number of storage nodes is increased, if a traditional partial repetition code construction method is adopted, when a single node fails, the repair scheme of the failed node is single, the disk I/O (input/output) cost in the repair process is high, meanwhile, the fault-tolerant capability of the system is low, and the requirement of the current time on the storage nodes is not met. For example, a traditional partial repetition code constructed based on a regular graph and a traditional partial repetition code constructed based on a hypergraph can only repair single-node faults, and the node repair degree is the node storage capacity.
Disclosure of Invention
The invention aims to provide a matrix construction method of a symmetrical partial repetition code and a fault node repairing method, which are used for solving the problems of complex construction method of the partial repetition code, large repairing locality in the node repairing process, small fault tolerance, small node repairing selectivity and the like in the prior art.
In order to realize the task, the invention adopts the following technical scheme:
a matrix construction method of a symmetrical partial repetition code 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 Wherein n is more than or equal to 4, and n and k are positive integers;
step 2: constructing an n-order claw matrix s 1 According to s 1 Constructing an n-order adjustment matrix s 2 ；
And 3, step 3: will n-order matrix s 1 And n-order adjustment matrix s 2 The elements at the corresponding positions are logically added to obtain an n-order incidence matrix s of the repeated codes of the symmetrical parts, the rows of the incidence matrix s represent nodes, the columns of the incidence matrix s represent coding blocks, s ij Denotes an element in s, if s ij If not than 1, the coding block C is stored in the ith node j If s is ij =0 th node does not store coding block C j And acquiring the coding block stored in each node to complete the construction of the symmetrical part repeated code.
Further, according to s 1 Constructing an adjustment matrix s to order n 2 The method comprises the following substeps:
step a: according to a matrixs 1 Removing s 1 The last column and the last row of the first-order matrix result in a matrix s of order n-1 3 ；
Step b: obtaining a matrix s 3 Adding 0 element at the end of the last line to obtain a line vector m;
step c: constructing an n-order adjustment matrix s 2 Let m be s 2 Then cyclically shifting m to the right so that m is shifted by one bit to the right to obtain a row vector as s 2 So that m is shifted to the right by two bits to obtain a row vector as s 2 And so on, so that m is shifted to the right by n-1 bits to obtain a row vector as s 2 N th row of (c), completes s 2 The structure of (1).
According to the matrix construction method of the symmetrical part repetition code, an original file M containing n coding blocks is stored in n nodes of a distributed storage system, and each node stores 3 coding blocks;
if the single node fails, collecting coding blocks from any two surviving nodes from all surviving nodes, and then transmitting the collected coding blocks to a new node to complete the repair of the single node failure;
if the double nodes have faults, any two surviving nodes are selected from all surviving nodes to collect the coding blocks, and then the collected coding blocks are respectively transmitted to two new nodes to finish the repair of the double node faults.
Compared with the prior art, the invention has the following technical characteristics:
(1) In the node, the number of redundant blocks generated by the original data block through MDS coding is less, and 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 from the two nodes, the repair scheme has more selectivity, the repair process is simple to operate, and the repair locality is small.
(3) The constructed symmetrical part repetition code can tolerate the failure of two nodes, and when the two continuous or discontinuous nodes fail, the failed node can be repaired by adopting the repair scheme of the failed node with the repair degree of 2, and the disk I/O overhead is relatively small.
Drawings
FIG. 1 is a schematic diagram of a storage system having 5 encoding blocks in an embodiment, wherein the repetition degree of the encoding blocks is 3, and a part of repetition codes are constructed;
FIG. 2 is a single node v containing 5 nodes and 5 coding blocks in an embodiment 1 A schematic of fault repair;
FIG. 3 is a schematic diagram of a storage system having 6 coding blocks in an embodiment, where the repetition degree of the coding block is 3 and a part of the repetition codes are constructed;
FIG. 4 is a diagram of two consecutive nodes v in an embodiment comprising 6 nodes and 6 coding blocks 1 And v 2 Schematic illustration of failover.
FIG. 5 shows two discontinuous nodes v in 6 coding blocks including 6 nodes in the embodiment 3 And node v 6 Schematic diagram of fault repair.
Detailed Description
Example 1
In this embodiment, a method for constructing a matrix of a symmetric partial repetition code is disclosed, and the method is applicable to a construction scheme with a coding block repetition degree of 3, and includes the following steps:
step 1: dividing an original file into k original data blocks, and performing (n, k) MDS encoding on the k original data blocks to obtain n encoding blocks C 1 ,C 2 ,…，C n Wherein n is more than or equal to 4, and n and k are positive integers;
step 2: constructing a n-order claw matrix s 1 According to s 1 Constructing an n-order adjustment matrix s 2 ；
And 3, step 3: will n-order matrix s 1 And an n-order adjustment matrix s 2 The elements at the corresponding positions are logically added to obtain an n-order incidence matrix s of the repeated codes of the symmetrical parts, the rows of the incidence matrix s represent nodes, the columns of the incidence matrix s represent coding blocks, and s ij Denotes an element in s, if s ij If not than 1, the coding block C is stored in the ith node j If s is ij If =0, no coding exists in the ith nodeCode block C j And acquiring the coding block stored in each node to complete the construction of the symmetrical part repeated code.
The invention aims to provide a matrix construction method of a symmetrical part repetition code, which has high system storage rate and can tolerate the failure of two nodes. There are a number of repair scenarios with a locality of repair of 2 when repairing a single failed node. When two continuous or discontinuous nodes have faults, the two nodes can be repaired only by connecting two survival nodes, and no calculation operation is needed in the repairing process. In addition, the code construction process is simple, easy to popularize and high in operability.
In particular, according to s 1 Constructing an adjustment matrix s to order n 2 The method comprises the following substeps:
step a: according to s 1 Removing s 1 The last column and the last row of (A) obtain a matrix s of order n-1 3 ；
Step b: obtaining a matrix s 3 Adding 0 at the end of the last line to obtain a line vector m;
step c: constructing an n-order adjustment matrix s 2 Let m be s 2 Then cyclically shifting m to the right so that m is shifted by one bit to the right to obtain a row vector as s 2 So that m is shifted to the right by two bits to obtain a row vector as s 2 And so on, so that m is shifted to the right by n-1 bits to obtain a row vector as s 2 N th row of (c), completes s 2 The structure of (3).
In the embodiment, a method for repairing a fault node is also disclosed, wherein an original file M containing n coding blocks is stored in n nodes of a distributed storage system according to the above method for constructing the matrix of the symmetric part repetition code, and each node stores 3 coding blocks;
if the single node fails, randomly selecting two surviving nodes from all surviving nodes to collect coding blocks, and then transmitting the collected coding blocks to a new node to finish the repair of the single node failure;
if the double nodes have faults, any two surviving nodes are selected from all surviving nodes to collect the coding blocks, and then the collected coding blocks are respectively transmitted to two new nodes to finish the repair of the double node faults.
Because there are more combinations of two surviving nodes containing failed node storage coded blocks, there are multiple repair schemes for node repair. In addition, for a dual-node failure, when two continuous or discontinuous nodes fail, a repair scheme that the repair degree of the failed node is still 2 still exists, and the disk I/O overhead is relatively small.
With the mass of stored data, nodes in the distributed storage system are correspondingly increased, and no matter erasure codes or regeneration codes are adopted, more surviving nodes need to be connected to recover the data in the process of repairing the failed nodes, so that the access overhead and bandwidth overhead of the nodes are increased. When a single node fails, if a traditional partial repetition code construction method is adopted, the failed node repair scheme is single, and the disk I/O overhead in the repair process is large. Meanwhile, the traditional partial repetition codes (the FR codes constructed based on the regular graph and the partial repetition codes constructed based on the hypergraph) can only accommodate single-node faults, have low fault tolerance and do not meet the requirements of mass data storage on nodes. Therefore, the matrix construction method of the symmetrical partial repeat codes has multiple repair schemes that only two surviving nodes need to be connected in the process of repairing single-node faults and any two node faults, reduces the pressure of the system to a certain extent, and improves the reliability of the system. Compared with the traditional partial repetition code, the number of the connected live nodes is greatly reduced, so that the number of the connected live nodes in the whole system in the process of repairing the fault node is correspondingly reduced, and the I/O of a disk is correspondingly reduced.
Example 2
The embodiment discloses a matrix construction method of a symmetrical partial repetition code, and provides a storage scheme of 5 coding blocks with 3 repetition degrees in a distributed storage system comprising 5 storage nodes on the basis of embodiment 1.
As shown in fig. 1, a file with a size of 4M is stored in a distributed storage system, and an original file is first (5, 4) encoded with MDS, and then the 5 encoded blocks are denoted by 1,2, 3. Removing 5 th order claw matrixs 1 To the last row and the last column of the matrix to obtain a 4-row and 4-column matrix s 3 In a matrix s 3 Adds a zero element at the end of the last row of elements, i.e. row vector m = (1 1 1 0), and takes the row vector m as the adjustment matrix s 2 The first row of elements. Then, the elements of the row vector m are sequentially shifted to the right by one bit, i.e., {0,1, 0} is placed in the adjustment matrix s 2 The second row of (2). Will matrix s 2 Is shifted to the right by two bits in turn, i.e. {0, 1} is placed in the adjustment matrix s 2 The third row of (2). Will matrix s 2 Is sequentially shifted to the right by three bits, i.e. {1,0, 1} is placed in the adjustment matrix s 2 The fourth row of (c). Will matrix s 2 Is sequentially shifted to the right by four bits, i.e., {1,0, 1} is placed in the adjustment matrix s 2 To obtain the adjustment matrix s 2 . Will claw matrix s 1 And an adjustment matrix s 2 And adding the elements at the corresponding positions of each row to obtain the incidence matrix s of the symmetrical partial repetition code.
The node v can be obtained according to the incidence matrix s 1 The stored code blocks are: c 1 、C 4 、C 5 (ii) a Node v 2 The stored code blocks are: c 1 、C 2 、C 5 (ii) a Node v 3 The stored code blocks are: c 1 、C 2 、C 3 (ii) a Node v 4 The stored code blocks are: c 2 、C 3 、C 4 (ii) a Node v 5 The stored code blocks are: c 3 、C 4 、C 5 。
The embodiment also discloses a plurality of repair schemes of the single failure node, as shown in figure 2, such as a single failure node v 1 There are four repair schemes. Specifically, repair protocol 1: slave node v 2 Upper collected data C 1 And C 5 At node v 4 Upper collected data C 4 And transmitted to node v 1 Completion node v 1 The number of connected nodes in the process is 2 (the repair locality is 2). Repair protocol 2: slave node v 2 Upper collected data C 1 Node v 5 Upper collected data C 4 And C 5 And transmitted to node v 1 Completion node v 1 In the process, the number of connected nodes is 2 (the repair locality is 2). Repair protocol 3: slave node v 2 Upper collected data C 1 、C 5 Node v 5 Upper collected data C 4 And transmitted to node v 1 Completion node v 1 The number of connected nodes in the process is 2 (the repair locality is 2). Repair protocol 4: slave node v 3 Upper collected data C 1 At node v 5 Upper collected data C 4 And C 5 And transmitted to node v 1 Completion of node v 1 The number of connected nodes in the process is 2 (the repair locality is 2).
Example 3
The embodiment discloses a matrix construction method of a symmetrical partial repetition code, and provides a storage scheme of 6 coding blocks with 3 repetition degrees in a distributed storage system comprising 6 storage nodes on the basis of embodiment 1.
As shown in fig. 3, a file of size 5M is stored in the distributed storage system, and the file is (6, 5) MDS encoded, with the 5 encoded blocks denoted by 1,2, 3. Removing the 6 th order claw matrix s 1 To the last row and the last column of the matrix to obtain a 5-row 5-column matrix s 3 In the matrix s 3 Adding a zero element at the end of the last row of elements to be recorded as a row vector m = (1 1 1 0), and taking the row vector m as an adjusting matrix s 2 The first row of elements of (a). Then, the elements of m are sequentially shifted to the right by one bit, i.e., {0,1, 0} is placed in the adjustment matrix s 2 The second row of (2). Matrix s 2 Is shifted to the right by two bits in turn, i.e. by placing {0, 1} in the adjustment matrix s 2 The third row of (2). Will matrix s 2 Is shifted to the right by three bits, i.e., {1,0, 1} is placed in the adjustment matrix s 2 The fourth row of (2). Will matrix s 2 Is sequentially shifted to the right by four bits, i.e. by placing {1,0, 1} in the adjustment matrix s 2 The fifth row of (1). Will matrix s 2 Is sequentially shifted to the right by five bits, i.e. the first row element of{1,0, 1} in the adjustment matrix s 2 To obtain the adjustment matrix s 2 . Will claw matrix s 1 And an adjustment matrix s 2 And adding the elements at the corresponding positions to obtain the incidence matrix s of the symmetrical part repetition code.
The node v can be obtained according to the incidence matrix s 1 The stored code blocks are: c 1 、C 5 、C 6 (ii) a Node v 2 The stored code blocks are: c 1 、C 2 、C 6 (ii) a Node v 3 The stored code blocks are: c 1 、C 2 、C 3 ；v 4 The stored code blocks are: c 2 、C 3 、C 4 ；v 5 The stored code blocks are: c 3 、C 4 、C 5 ；v 6 The stored code blocks are: c 4 、C 5 、C 6 。
The embodiment also discloses a method for repairing two failed nodes, and fig. 4 shows that two nodes v are continuous in the embodiment 1 And v 2 Repair schematic for fault repair. Slave node v 3 And node v 6 Respectively collecting data C 1 、C 2 And C 5 、C 6 And C is 1 、C 5 、C 6 To node v 1 Completion node v 1 Repair of (C) 1 、C 2 、C 6 To node v 2 Completion node v 2 In the process, the number of connected nodes is 2 (the repair locality is 2). FIG. 5 shows two discontinuous nodes v in the present embodiment 3 And v 6 Repair schematic for failover. Scheme 1: slave node v 2 And node v 5 Respectively collecting data C 1 、C 2 、C 6 And C 3 、C 4 、C 5 And C is 1 、C 2 、C 3 To node v 3 Completion node v 3 Repair of (C) 4 、C 5 、C 6 To node v 6 Completion of node v 6 In the process, the number of connected nodes is 2 (the repair locality is 2).Scheme II: slave node v 1 And node v 4 Respectively collecting data C 1 、C 5 、C 6 And C 2 、C 3 、C 4 And C is 1 、C 2 、C 3 To node v 3 Completion of node v 3 Repair of (C) 4 、C 5 、C 6 To node v 6 Completion node v 6 The number of connected surviving nodes in this process is still 2 (the repair locality is 2).
Claims (3)
1. A method for constructing a matrix of a symmetric partial repetition code, comprising the steps of:
step 1: dividing an original file into k original data blocks, and performing (n, k) MDS encoding on the k original data blocks to obtain n encoding blocks C 1 ,C 2 ,…，C n Wherein n is more than or equal to 4, and n and k are positive integers;
step 2: constructing a n-order claw matrix s 1 According to s 1 Constructing an n-order adjustment matrix s 2 ；
And step 3: will n-order matrix s 1 And n-order adjustment matrix s 2 The elements at the corresponding positions are logically added to obtain an n-order incidence matrix s of the repeated codes of the symmetrical parts, the rows of the incidence matrix s represent nodes, the columns of the incidence matrix s represent coding blocks, s ij Represents an element in s if ij =1 then the ith node has a coding block C j If s is ij =0 th node does not store coding block C j And acquiring the coding block stored in each node to complete the construction of the symmetrical part repeated code.
2. The method of matrix construction of symmetric partial repetition codes according to claim 1, characterized in that it is based on s 1 Constructing an n-order adjustment matrix s 2 The method comprises the following substeps:
a, step a: according to s 1 Removing s 1 The last column and the last row of (A) obtain a matrix s of order n-1 3 ；
Step b: obtaining a matrix s 3 And in the last row ofAdding 0 element at the end of the next line to obtain a line vector m;
step c: constructing an n-order adjustment matrix s 2 Let m be s 2 Then cyclically shifting m to the right such that m is shifted by one bit to the right to obtain a row vector s 2 So that m is shifted to the right by two bits to obtain a row vector as s 2 And so on, so that m is moved to the right by n-1 bits to obtain a row vector as s 2 N th row of (c), completes s 2 The structure of (3).
3. A method for repairing a failed node, comprising the steps of storing an original file containing n coding blocks into n nodes of a distributed storage system according to any one of the matrix construction methods of the symmetrical partial repeat codes of claim 1 or 2, and enabling each node to store 3 coding blocks;
if the single node fails, collecting coding blocks from any two surviving nodes from all surviving nodes, and then transmitting the collected coding blocks to a new node to complete the repair of the single node failure;
if the double nodes have faults, any two surviving nodes are selected from all surviving nodes to collect the coding blocks, and then the collected coding blocks are respectively transmitted to two new nodes to finish the repair of the double node faults.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910930824.1A CN110781024B (en) | 2019-09-29 | 2019-09-29 | Matrix construction method of symmetrical partial repetition code and fault node repairing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910930824.1A CN110781024B (en) | 2019-09-29 | 2019-09-29 | Matrix construction method of symmetrical partial repetition code and fault node repairing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110781024A CN110781024A (en) | 2020-02-11 |
| CN110781024B true CN110781024B (en) | 2023-02-28 |
Family
ID=69384644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910930824.1A Active CN110781024B (en) | 2019-09-29 | 2019-09-29 | Matrix construction method of symmetrical partial repetition code and fault node repairing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110781024B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157485B (en) * | 2021-05-06 | 2022-07-15 | 中南大学 | Expansion construction method of partial repetition code |
| CN116192192B (en) * | 2023-04-25 | 2023-07-25 | 西安电子科技大学 | Coding hierarchical repair method for redundancy-free TSV of three-dimensional integrated circuit |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9722637B2 (en) * | 2013-03-26 | 2017-08-01 | Peking University Shenzhen Graduate School | Construction of MBR (minimum bandwidth regenerating) codes and a method to repair the storage nodes |
| CN108540520B (en) * | 2018-02-06 | 2020-09-11 | 长安大学 | Partial repeated code based locality repairing coding and node fault repairing method |
| CN109521955B (en) * | 2018-10-15 | 2022-03-15 | 长安大学 | Heterogeneous part repeated code construction and conversion method based on hierarchical cross design |
-
2019
- 2019-09-29 CN CN201910930824.1A patent/CN110781024B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110781024A (en) | 2020-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108540520B (en) | Partial repeated code based locality repairing coding and node fault repairing method | |
| CN104052576B (en) | Data recovery method based on error correcting codes in cloud storage | |
| US11531593B2 (en) | Data encoding, decoding and recovering method for a distributed storage system | |
| US8219887B2 (en) | Parallel Reed-Solomon RAID (RS-RAID) architecture, device, and method | |
| CN109643258B (en) | Multi-node repair using high-rate minimal storage erase code | |
| US8775860B2 (en) | System and method for exact regeneration of a failed node in a distributed storage system | |
| CN110178122B (en) | Data synchronous repair method of distributed storage system and storage medium | |
| CN110168505B (en) | Data repair method of distributed storage system and storage medium | |
| CN106776129B (en) | A kind of restorative procedure of the multinode data file based on minimum memory regeneration code | |
| CN105956128B (en) | A kind of adaptive coding storage fault-tolerance approach based on simple regeneration code | |
| CN112000512B (en) | Data restoration method and related device | |
| CN105260259A (en) | System minimum storage regeneration code based local repair encoding method | |
| CN112799875B (en) | Method, system, device and medium for verification recovery based on Gaussian elimination | |
| CN108762978B (en) | Grouping construction method of local part repeated cyclic code | |
| WO2018072294A1 (en) | Method for constructing check matrix and method for constructing horizontal array erasure code | |
| CN107844272A (en) | A kind of cross-packet coding and decoding method for improving error correcting capability | |
| CN110389848B (en) | Partial repetition code construction method based on block construction and fault node repair method | |
| CN109086000B (en) | Three-fault-tolerant data layout method in RAID storage system | |
| CN110781024B (en) | Matrix construction method of symmetrical partial repetition code and fault node repairing method | |
| CN105808170B (en) | A kind of RAID6 coding methods that can repair single disk error | |
| CN113190377A (en) | Reliable redundancy method and equipment based on distributed storage system | |
| CN112799605A (en) | Square part repeated code construction method, node repair method and capacity calculation method | |
| CN109358980A (en) | A kind of pair of data update and single disk error repairs friendly RAID6 coding method | |
| CN106788455B (en) | A kind of building method of the optimal partial repairable system code based on packet | |
| CN110990375B (en) | Method for constructing heterogeneous partial repeat codes based on adjusting matrix |
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 |