CN113297000B - A kind of RAID encoding circuit and encoding method - Google Patents

Abstract

The application discloses RAID encoding circuit and encoding method, the circuit includes: the first parameter module is used for acquiring a first check parameter corresponding to a current target data strip of data to be coded in the current RAID mode, and determining data after first parameter operation by using the first check parameter and the current target data strip; the first verification parameter in the RAID6 mode is a coding parameter corresponding to a first verification code determined based on the Van der Mongolian RS coding relation, and the first verification parameter in the RAID5 mode is 1; and the first coding module is used for carrying out coding operation on the current first check code read from the first check code storage position and the data after the current first parameter operation to obtain a new first check code, and storing the new first check code to the first check code storage position until the final first check code corresponding to the data to be coded is determined based on the last target data stripe of the data to be coded. RAID6 can be realized quickly and in a lower area on the premise of realizing RAID 5.

Description

A kind of RAID encoding circuit and encoding method

technical field

The present application relates to the field of storage technology, in particular to a RAID encoding circuit and encoding method.

Background technique

With the rapid development of communication technology and network technology, digital information is growing exponentially, and data storage technology is therefore facing huge challenges. The reliability of data in the storage system and the energy consumption of the storage system are more and more concerned by people. Nowadays, in the face of such a huge data scale, the reliability of the data in the storage system is inversely proportional to the number of components contained in the storage system, that is, the more components in the storage system, the lower the reliability of the data in the storage system. In large-scale storage systems, data reliability degradation caused by disk failure is a very serious problem, and people have launched research on related fault-tolerant technologies. RAID (Redundant Arrays of Independent Disks, that is, independent redundant disk array) technology came into being, using RAID storage technology can greatly increase storage capacity, improve system input and output request processing capabilities and through data distributed storage technology, parallel access Means and information redundancy technology improve data reliability. At present, RAID can be divided into different levels: RAID 0, 1, 5, 6, and 10. In actual circuits, RAID 6 generally needs to be implemented on the premise of implementing RAID 5. Therefore, how to implement RAID 5 on the premise of Therefore, it is a problem to be solved to realize RAID6 quickly and with a lower area.

Contents of the invention

In view of this, the purpose of this application is to provide a RAID encoding circuit and encoding method, which can implement RAID 6 quickly and with a relatively small area on the premise of implementing RAID 5. The specific plan is as follows:

In a first aspect, the application discloses a RAID encoding circuit, comprising:

The first parameter module is configured to obtain the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and use the first verification parameter and the current target data stripe to determine the first parameter after operation Data; wherein, the first check parameter in the RAID 6 mode is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS coding relationship, and the first check parameter in the RAID 5 mode is 1;

The first encoding module is used to encode the current first check code read from the storage location of the first check code and the data after the current first parameter operation to obtain a new first check code, and convert the new first check code The first check code is stored in the first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded.

Optionally, also include:

A data strip division module, configured to divide the data to be encoded into a preset number of data strips;

A Galois field conversion module, configured to convert each data strip into Galois field data, and obtain the target data strip corresponding to each data strip;

Correspondingly, the first encoding module is configured to perform an XOR operation on the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code code, and store a new first check code in the storage location of the first check code.

Optionally, also include:

The second parameter module is configured to obtain the second verification parameter corresponding to the current target data stripe of the data to be encoded in RAID 6 mode, and use the second verification parameter and the current target data stripe to determine the second parameter after operation Data; wherein, the second check parameter corresponding to RAID 6 is the encoding parameter corresponding to the second check code determined based on the Vandermonde RS encoding relationship;

The second encoding module is used to encode the current second check code read from the second check code storage location and the current second parameter operation data to obtain a new second check code, and convert the new The second check code is stored in the second check code storage location.

Optionally, the first parameter module is further configured to obtain a second verification parameter corresponding to the current target data stripe of the data to be encoded under RAID 6, and use the second verification parameter and the current target data stripe Determine the data after the operation of the second parameter; wherein, the second verification parameter corresponding to RAID 6 is a coding parameter corresponding to the second verification code determined based on the Vandermonde RS coding relationship;

Correspondingly, the first encoding module is further configured to perform an encoding operation on the current second check code read from the second check code storage location and the current second parameter operation data to obtain a new second check code code, and store a new second check code in the second check code storage location.

Optionally, also include:

A data caching module, configured to store the target data strips of the data to be encoded in the cache;

The data reading module is configured to read the target data strip from the cache, and simultaneously transmit it to the data storage location corresponding to the target data strip and the first parameter module.

Optionally, the first parameter module is specifically used for:

确定RAID 6模式下待编码数据的当前目标数据条带对应的第一校验参数；formula based

Determine the first check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode;

表示异或运算。Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation.

Optionally, the second parameter module is specifically used for:

确定RAID 6模式下待编码数据的当前目标数据条带对应的第二校验参数；formula based

Determine the second check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode;

表示异或运算。Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation.

In a second aspect, the application discloses a RAID encoding method, comprising:

Obtain the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and use the first verification parameter and the current target data stripe to determine the data after the first parameter operation; wherein, the RAID 6 mode The first check parameter below is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS encoding relationship, and the first check parameter in the RAID 5 mode is 1;

Perform encoding operation on the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code, and store the new first check code in The first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded.

Optionally, also include:

dividing the data to be encoded into a preset number of data strips;

Convert each data stripe to Galois field data to obtain the target data stripe corresponding to each data stripe.

Optionally, the encoding operation of the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code includes:

An XOR operation is performed on the current first check code read from the storage location of the first check code and the current first parameter operation data to obtain a new first check code.

It can be seen that a RAID encoding circuit disclosed in the present application includes: a first parameter module, configured to obtain a first check parameter corresponding to a current target data stripe of data to be encoded in the current RAID mode, and use the first check parameter to The verification parameters and the current target data strip determine the data after the operation of the first parameter; wherein, the first verification parameter in RAID 6 mode is the encoding parameter corresponding to the first verification code determined based on the Vandermonde RS coding relationship, and the RAID 5 mode The first check parameter below is 1; the first encoding module is used to encode the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new The first check code, and store the new first check code in the first check code storage location, until the last target data strip of the data to be encoded is determined based on the data to be encoded The final first checksum. In this way, only the first parameter module is needed to realize the code conversion from RAID 5 to RAID 6, and RAID 6 can be realized quickly and with a relatively small area under the premise of realizing RAID 5.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present application, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

Fig. 1 is a schematic structural diagram of a RAID encoding circuit disclosed in the present application;

Fig. 2 is a kind of specific RAID encoding circuit encoding schematic diagram disclosed in the present application;

Fig. 3 is a schematic diagram of encoding of a RAID 5 encoding circuit disclosed by the present application;

Fig. 4 is a schematic diagram of encoding of a RAID 6 encoding circuit disclosed in the present application;

FIG. 5 is a flowchart of a RAID encoding method disclosed in the present application.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

Referring to Fig. 1, the embodiment of the present application discloses a RAID encoding circuit, including:

The first parameter module 11 is configured to obtain the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and determine the first parameter operation by using the first verification parameter and the current target data stripe The latter data; wherein, the first check parameter in the RAID 6 mode is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS encoding relationship, and the first check parameter in the RAID 5 mode is 1.

In a specific implementation manner, the multiplication operation is performed by using the first verification parameter and the current target data strip to obtain the data after the operation of the first parameter.

The first encoding module 12 is used to encode the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code, and convert the new The first check code is stored in the first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded.

In a specific implementation manner, the circuit also includes:

A data strip division module, configured to divide the data to be encoded into a preset number of data strips.

Wherein, the preset number is the number of data stripes of the RAID.

The Galois field conversion module is configured to convert each data strip into Galois field data, and obtain the target data strip corresponding to each data strip.

Correspondingly, the first encoding module is configured to perform an XOR operation on the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code code, and store a new first check code in the storage location of the first check code.

That is, in the embodiment of the present application, encoding operations can be performed based on data strips in the Galois field, which can improve encoding efficiency.

It should be pointed out that RAID 5 has only one parity stripe (parity stripe), that is, the first parity code. The relationship between code verification is expressed as:

表示异或运算。Among them, d ₀ , d ₁ ... d _n represent data strips, p represents the first check code,

Indicates an XOR operation.

When implementing RAID 6, it is necessary to support two parity stripes at the same time, that is, the first parity code and the second parity code. This application uses RS (that is, Reed-Solomon Code, Reed-Solomon Code) code to carry out the encoding of the first check code and the second check code. RS codes have various implementation methods such as Vandermonde and Cauchy. The characteristics of the characteristics and the simple requirements of the operation, the embodiment of the present application uses the implementation method of Vandermonde, assuming that the data to be encoded is divided into n data strips, then according to the above formula, the data strips, the first check code and the second The relationship of the check code is expressed as:

表示异或运算，α表示范德蒙参数。Among them, d ₀ , d ₁ ... d _n represent data strips, p represents the first check code, q represents the second check code,

Represents an XOR operation, and α represents a Vandermonde parameter.

In order to facilitate calculation and storage, in this embodiment, the Galois field is processed into a finite field and then coded and stored. In addition, since the transmission of data in the circuit is generally based on byte, the Galois field used in the embodiment of this application is an 8-bit finite field 0X11D, that is:

P(X)＝ ^x8 + ^x4 + ^x3 + ^x2 +1;

Under the Galois field of the finite field 0X11D, the definition of data can be expressed as shown in Table 1:

Table I

generate elements polynomial representation binary representation numerical representation The derivation process 0 0 0000 0000 0 x^0 x^0 0000 0001 1 x^1 x^1 0000 0010 2 x^2 x^2 0000 0100 4 x^3 x^3 0000 1000 8 x^4 x^4 0001 0000 16 x^5 x^5 0010 0000 32 x^6 x^6 0100 0000 64 x^7 x^7 1000 0000 128 x^8 x^4+x^3+x^2+1 0001 1101 29 x^7*x＝x^8mod P(x) x^9 x^5+x^4+x^3+x 0011 1010 58 x^8*x＝x^5+x^4+x^3+x x^10 x^6+x^5+x^4+x^2 0111 0100 116 x^9*x＝x^6+x^5+x^4+x^2 … … … … … x^255 1 0000 0001 1

For example, when the index of the generating element is 10, it is expressed as binary 01110100 through the above-mentioned Galois field original polynomial P(X) conversion. Through such conversion, all data will be converted into 8-bit binary numbers, and four arithmetic operations based on 8-bit binary numbers will be performed. Based on the situation of the Galois field, it can be seen that both traditional RAID 5 and 6 can realize common data arithmetic operations through the Galois field, but the coding of RAID 6 based on the Vandermonde RS code proposed in the application needs to consider the corresponding exponential relationship. When it comes to four arithmetic operations, especially multiplication, it is necessary to consider whether the data overflow still conforms to the Vandermonde relationship. In order to verify its applicability, the following calculation derivation is done:

Assuming that there are two data strips d ₀ and d ₁ that need to be multiplied, they are expanded according to the 8-bit Galois field and converted using the Vandermonde-based RS code as follows:

Since multiplication is the most prone to overflow problems, the multiplication of d ₀ and d ₁ can be obtained:

d ₀ *d ₁ = A ₇ B ₇ α ¹⁴

+(A ₇ B ₆ +A ₆ B ₇ )α ¹³

+...+

+A ₀ B ₀ α ⁰

Express A ₇ B ₇ , (A ₇ B ₆ +A ₆ B ₇ ) to A ₀ B ₀ in the above formula with parameters P ₁₄ , P ₁₃ ,...,P ₀ , then the above formula can be expressed as:

d ₀ *d ₁ ＝P ₁₄ α ¹⁴ +P ₁₃ α ¹³ +...+P ₂ α ² +P ₁ α ¹ +P ₀ α ⁰

Query the 8-bit binary representation of overflow items α ¹⁴ , α ¹³ , ..., α ⁸ based on Table 1. For example, α ⁸ =29 is expressed as α ⁸ =α ⁴ +α ³ +α ² +α ⁰ and then re-enclosed Into the above formula, you can get:

d ₀ *d ₁ =C ₇ α ⁷ +C ₆ α ⁶ +...+C ₂ α ² +C ₁ α ¹ +C ₀ α ⁰ ;

Among them, C ₀ , C ₁ ... C ₆ , C ₇ are the data for α ⁷ represented by P(X)=x ⁸ +x ⁴ +x ³ +x ² +1 after the split operation is performed through the lookup table 1. , α ⁶ ,..., the new parameters of α ⁰ . It can be seen that the perfect adaptation to the requirements of the RS code based on Vandermonde can complete the four arithmetic operations of RAID 6, that is to say, the RS code based on Vandermonde proposed in this application can be used for the encoding and decoding of RAID 6 to realize the operation of RAID 6.

In a specific implementation manner, the RAID encoding circuit also includes:

The second parameter module is configured to obtain the second verification parameter corresponding to the current target data stripe of the data to be encoded in RAID 6 mode, and use the second verification parameter and the current target data stripe to determine the second parameter after operation Data; wherein, the second check parameter corresponding to RAID 6 is the encoding parameter corresponding to the second check code determined based on the Vandermonde RS encoding relationship;

The second encoding module is used to encode the current second check code read from the second check code storage location and the current second parameter operation data to obtain a new second check code, and convert the new The second check code is stored in the second check code storage location.

In another specific implementation manner, the first parameter module is further configured to obtain the second verification parameter corresponding to the current target data stripe of the data to be encoded under RAID 6, and use the second verification parameter Determine the data after the second parameter operation with the current target data strip; wherein, the second verification parameter corresponding to RAID 6 is the encoding parameter corresponding to the second verification code determined based on the Vandermonde RS encoding relationship;

Correspondingly, the first encoding module is further configured to perform an encoding operation on the current second check code read from the second check code storage location and the current second parameter operation data to obtain a new second check code code, and store a new second check code in the second check code storage location.

That is, in a specific implementation manner, the first check code and the second check code can be serially determined by using the same parameter module and encoding module, so as to reduce the circuit area. In order to increase the encoding speed, different parameter modules and encoding modules can be used in parallel to determine the first check code and the second check code respectively.

And, in a specific embodiment, the RAID coding circuit also includes:

The data caching module is configured to store the target data strips of the data to be encoded into the cache.

In a specific implementation manner, the buffer mode may be buffer (buffer) or FIFO (namely First Input First Output, first in first out).

The data reading module is configured to read the target data strip from the cache, and simultaneously transmit it to the data storage location corresponding to the target data strip and the first parameter module.

For example, refer to FIG. 2 , which is a schematic diagram of encoding of a specific RAID encoding circuit disclosed in the present application.

1. The data to be encoded enters the RAID encoding circuit. The RAID encoding circuit first divides the data to be encoded into a preset number of data strips, and then converts each data strip into Galois field data to obtain the data corresponding to each data strip. The target data strips are temporarily stored in buffer or FIFO, and when the data reading module is idle, the data reading module sends the target data strips to the data storage location corresponding to the current data strip and the first parameter module, the second parameter module, and the first parameter module obtains the first verification parameter corresponding to the current target data stripe of the data to be encoded under the current RAID mode, and uses the first verification parameter and the current target data stripe to perform multiplication, Obtain the calculated data of the first parameter, transmit the calculated data of the first parameter to the first encoding module, and obtain the second verification parameter corresponding to the current target data strip of the data to be encoded in the current RAID mode by the second parameter module, and use The second verification parameter is multiplied by the current target data strip to obtain the data after the operation of the second parameter, and the data after the operation of the second parameter is transmitted to the second encoding module. For example, the current target data strip is d ₀ , and the data is transmitted to the storage location corresponding to d ₀ and the first parameter module and the second parameter module. At the same time, read the stored data from the storage locations of the first check code p and the second check code q, that is, the current first check code and the current second check code are transmitted to the first encoding module, the second encoding module.

2. The data after the operation of the first parameter and the data after the operation of the second parameter are respectively compared with the current first check code read from the storage location of the first check code and the current second check code read from the storage location of the second check code. After the data stored in the check code is XORed in the first encoding module and the second encoding module, a new first check code and a new second check code are generated, and then the storage location of the first check code is updated and the data in the second check code storage location.

Wherein, the initial values of the first check code storage location and the second check code storage location are both 0, so that the check code determined by using the last target data strip of the data to be encoded is the corresponding value of the data to be encoded. The final check code completes the encoding of the data to be encoded.

It should be pointed out that the first check parameter in the RAID 5 mode is 1, and the encoding can be completed through the first parameter module and the first encoding module to obtain the corresponding first check code.

In a specific implementation manner, the first parameter module is specifically used for:

确定RAID 6模式下待编码数据的当前目标数据条带对应的第一校验参数；formula based

Determine the first check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode;

表示异或运算。Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation.

The second parameter module is specifically used for:

确定RAID 6模式下待编码数据的当前目标数据条带对应的第二校验参数；formula based

Determine the second check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode;

表示异或运算。Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation.

Introduce the realization process of the RAID coding circuit that this application provides below:

当需要实现RAID5的编码时，操作方式如图3所示，图3为本申请实施例公开的一种RAID 5编码电路编码示意图。1、待编码数据进入RAID5编码电路，RAID编码电路先将待编码数据分割为预设数量个数据条带，通过buffer或FIFO等方式暂存等待等待数据读取模块空闲时，数据读取模块将数据条带分别同时送往当前数据条带对应的数据存储位置以及编码模块。同一时间，从存储校验码p的位置读取现在所存的数据进入编码模块。2、数据条带与从存储校验码p的位置读取到的当前校验码进行在编码模块进行异或运算后，产生的新的校验码写入存储校验码p的位置，更新该位置的数据。It should be pointed out that the implementation of RAID 5 is:

When the encoding of RAID5 needs to be implemented, the operation mode is shown in FIG. 3 . FIG. 3 is a schematic diagram of encoding of a RAID 5 encoding circuit disclosed in the embodiment of the present application. 1. The data to be encoded enters the RAID5 encoding circuit. The RAID encoding circuit first divides the data to be encoded into a preset number of data strips, and temporarily stores them through buffer or FIFO. When the data reading module is idle, the data reading module will The data stripes are respectively sent to the data storage location corresponding to the current data stripe and the encoding module at the same time. At the same time, read the currently stored data from the location where the check code p is stored and enter the encoding module. 2. The data strip and the current check code read from the location where the check code p is stored are performed after the encoding module performs an XOR operation, and the new check code generated is written into the location where the check code p is stored, and updated data for this location.

Realize the multiplexing of hardware circuits, achieve the minimum area, and maximize multiplexing optimization. Therefore, for RAID6, it is necessary to set the same method for encoding.

The relationship of RAID 6 can be expressed as:

Wherein, the formula (1) can simply expand the expression of RAID 5 to obtain the second parity strip q. Therefore, when implementing the coding of formula (1) of RAID 6, the module of RAID 5 can be applied. You can use two encoding modules to operate in parallel, or you can use only one encoding module like RAID 5, and calculate the values of p and q in two steps and then update them separately. Because the formula (1) of RS RAID 6 encoding is very similar to RAID 5, q can be considered to be updated in the same way as p, so the calculation and update of p and q can be realized in parallel or in series by applying the same circuit. For example, referring to FIG. 4 , FIG. 4 is a schematic diagram of encoding of a RAID 6 encoding circuit disclosed in an embodiment of the present application, and is used to implement encoding of Formula (1) for implementing RAID 6. 1. The data to be encoded enters the RAID6 encoding circuit. The RAID6 encoding circuit first divides the data to be encoded into a preset number of data strips, and temporarily stores them in buffer or FIFO. When the data reading module is idle, the data reading module will The data stripes are sent to the data storage location corresponding to the current data stripe and to two different encoding modules at the same time. At the same time, the currently stored data is read from the location where the check codes p and q are stored and sent to the two encoding modules respectively. 2. After the data strip and the current check code p read from the location where the check code p is stored are XORed in the corresponding encoding module, the new check code generated is written into the location where the check code p is stored , to update the data for that location. After the data strip and the current check code q read from the location where the check code q is stored are XORed in the corresponding encoding module, the new check code generated is written into the location where the check code q is stored, and updated data for this location.

The formula (2) of RS RAID 6 is quite different from that of RAID 5, because compared with the XOR operation of RAID 5, different parameters and corresponding multiplications are added. In order to set the encoding in the same way and realize circuit multiplexing, a parameter module is added in this embodiment, and the data strip is multiplied by the parameter before performing the XOR operation through the parameter module, and the parameter can satisfy the formula of RAID 6 at the same time ( 1) and (2). The calculation and updating of p and q can be completed by formula (2) based on the updated data strips through additional multiplication operations and XOR operations.

Let any stored data be d _x , and its corresponding check codes be p and q. The updated stored data is d _x ', and its corresponding check codes are p' and q'. x is the serial number corresponding to the data stripe.

According to the coding relationship of formula (1) of RAID 6, it can be seen that the following relationship is satisfied:

Let d _x -d _x '=Δ, then the above formula can be updated as:

Assuming that the parameters of RS RAID 6 corresponding to p and q are α ^p , α ^q respectively, then multiply the above formula by α ^p , α ^q to obtain the relationship:

And, based on the RS RAID 6 encoding relationship corresponding to α ^p , α ^q can be obtained:

α ^x in formula (5) refers to the encoding coefficient corresponding to the stored data Δ.

Take the calculation of q' as an example, add the formulas (3) and (5), the addition here refers to the addition in the Galois field, and perform XOR operation in time, we can get:

Similarly, the relational formula of p' can be obtained by adding (3) and (4).

In the above formula, as defined above, p and q are the original stored check codes, and Δ is the increment of the corresponding data to be stored, which can represent data changes or new data. α ^p , α ^q and α ^x represent the corresponding coding coefficients as mentioned above. In the formula (2) of RAID 6, α ^p , α ^q are α ⁿ⁺¹ and α ⁿ⁺² respectively, and α ^x is the corresponding The coefficient value with data, such as α ⁰ , is a definite parameter that has nothing to do with the specific value of the data, and can be directly calculated.

In a specific implementation manner, the data strip of the data to be encoded can be regarded as Δ, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship.

和

为确定参数，则通过以上运算转换，可知RS RAID 6的p和q的数据更新可以通过添加可参数计算然后利用图4中的电路实现。添加参数模块即可得到如图2的电路。because

and

In order to determine the parameters, through the above calculation conversion, it can be seen that the data update of p and q of RS RAID 6 can be realized by adding parameter calculations and then using the circuit in Figure 4. The circuit shown in Figure 2 can be obtained by adding the parameter module.

It can be seen that the RAID encoding circuit disclosed in the embodiment of the present application includes: a first parameter module, configured to obtain the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and use the first verification parameter The verification parameters and the current target data strip determine the data after the operation of the first parameter; wherein, the first verification parameter in RAID 6 mode is the encoding parameter corresponding to the first verification code determined based on the Vandermonde RS coding relationship, and the RAID 5 mode The first check parameter below is 1; the first encoding module is used to encode the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new The first check code, and store the new first check code in the first check code storage location, until the last target data strip of the data to be encoded is determined based on the data to be encoded The final first checksum. In this way, only the first parameter module is needed to realize the code conversion from RAID 5 to RAID 6, and RAID 6 can be realized quickly and with a relatively small area under the premise of realizing RAID 5.

Referring to Fig. 5, the embodiment of the present application discloses a RAID encoding method, including:

Step S11: Obtain the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and use the first verification parameter and the current target data stripe to determine the data after the first parameter operation; wherein, The first check parameter under the RAID6 mode is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS encoding relationship, and the first check parameter under the RAID 5 mode is 1;

Step S12: Perform encoding operation on the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code, and convert the new first check code The code is stored in the first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded.

In a specific implementation, the data to be encoded can be divided into a preset number of data strips; each data strip is converted into Galois field data, and the target data strip corresponding to each data strip is obtained .

Correspondingly, the encoding operation of the current first check code read from the first check code storage location and the current first parameter operation data to obtain a new first check code includes:

An XOR operation is performed on the current first check code read from the storage location of the first check code and the current first parameter operation data to obtain a new first check code.

In a specific implementation mode, it is possible to:

Obtaining the first verification parameter corresponding to the current target data strip of the data to be encoded in the current RAID mode through the first parameter module, and using the first verification parameter and the current target data strip to determine the data after the first parameter operation; Wherein, the first check parameter in the RAID 6 mode is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS encoding relationship, and the first check parameter in the RAID 5 mode is 1;

Through the first encoding module, the current first check code read from the first check code storage location and the current first parameter operation data are encoded to obtain a new first check code, and the new first check code The check code is stored in the first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded.

Obtaining the second verification parameter corresponding to the current target data strip of the data to be encoded in RAID 6 mode through the second parameter module, and using the second verification parameter and the current target data strip to determine the second parameter operation data; Wherein, the second check parameter corresponding to RAID 6 is the encoding parameter corresponding to the second check code determined based on the Vandermonde RS encoding relationship;

Through the second encoding module, the current second check code read from the second check code storage location and the current second parameter operation data are encoded to obtain a new second check code, and the new second check code The check code is stored in the second check code storage location.

In another specific embodiment, it can be

Obtaining the first verification parameter corresponding to the current target data strip of the data to be encoded in the current RAID mode through the first parameter module, and using the first verification parameter and the current target data strip to determine the data after the first parameter operation; Wherein, the first check parameter in the RAID 6 mode is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS encoding relationship, and the first check parameter in the RAID 5 mode is 1;

Through the first encoding module, the current first check code read from the first check code storage location and the current first parameter operation data are encoded to obtain a new first check code, and the new first check code The check code is stored in the first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded.

Obtain the second verification parameter corresponding to the current target data stripe of the data to be encoded under RAID 6 through the first parameter module, and use the second verification parameter and the current target data stripe to determine the second parameter operation data; wherein , the second check parameter corresponding to RAID 6 is the encoding parameter corresponding to the second check code determined based on the Vandermonde RS encoding relationship;

Correspondingly, the current second check code read from the second check code storage location and the current second parameter operation data are encoded and operated by the first encoding module to obtain a new second check code, and the new The second check code is stored in the second check code storage location.

Moreover, in a specific implementation manner, the target data strips of the data to be encoded may be stored in a cache; the target data strips are read from the cache, and simultaneously transmitted to the corresponding The data storage location and the first parameter module.

确定RAID 6模式下待编码数据的当前目标数据条带对应的第一校验参数；And, in a specific embodiment, it can be based on the formula

Determine the first check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode;

表示异或运算。Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation.

确定RAID 6模式下待编码数据的当前目标数据条带对应的第二校验参数；formula based

Determine the second check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode;

表示异或运算。Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation.

It can be seen that the present application obtains the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and uses the first verification parameter and the current target data stripe to determine the data after the first parameter operation; wherein , the first check parameter in RAID 6 mode is the encoding parameter corresponding to the first check code determined based on the Vandermonde RS coding relationship, and the first check parameter in RAID 5 mode is 1; The current first check code read from the storage location and the data after the current first parameter operation are encoded and operated to obtain a new first check code, and the new first check code is stored in the first check code The location is stored until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded. In this way, the code conversion from RAID 5 to RAID 6 can be realized only by changing the first check code parameter, and RAID 6 can be realized quickly and with a relatively small area under the premise of realizing RAID 5.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other. As for the method disclosed in the embodiment, since it corresponds to the circuit disclosed in the embodiment, the description is relatively simple, and for related parts, please refer to the description of the circuit part.

The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be directly implemented by hardware, software modules executed by a processor, or a combination of both. Software modules can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other Any other known storage medium.

A kind of RAID encoding circuit and encoding method provided by the application has been introduced in detail above, and specific examples have been used in this paper to illustrate the principle and implementation of the application. The description of the above embodiments is only used to help understand the application. method and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation and application scope. Application Restrictions.

Claims (8)

1. A RAID coding circuit, characterized in that, comprising: The first parameter module is used to obtain the first verification parameter corresponding to the current target data stripe of the data to be encoded in the current RAID mode, and use the first verification parameter and the current target data stripe to perform a multiplication operation to determine the first verification parameter Data after a parameter operation; wherein, the first verification parameter in RAID 6 mode is based on the formula

Determined, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is The coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates XOR operation, the first check parameter in RAID 5 mode is 1; The first encoding module is used to perform an XOR operation on the current first check code read from the first check code storage location and the data after the current first parameter operation to obtain a new first check code, and convert the new The first check code is stored in the first check code storage location until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded. 2. RAID coding circuit according to claim 1, is characterized in that, also comprises: A data strip division module, configured to divide the data to be encoded into a preset number of data strips; The Galois field conversion module is configured to convert each data strip into Galois field data, and obtain the target data strip corresponding to each data strip. 3. RAID encoding circuit according to claim 1, is characterized in that, also comprises: The second parameter module is configured to obtain the second verification parameter corresponding to the current target data stripe of the data to be encoded in RAID 6 mode, and use the second verification parameter and the current target data stripe to determine the second parameter after operation Data; wherein, the second check parameter corresponding to RAID 6 is the encoding parameter corresponding to the second check code determined based on the Vandermonde RS encoding relationship; The second encoding module is used to encode the current second check code read from the second check code storage location and the current second parameter operation data to obtain a new second check code, and convert the new The second check code is stored in the second check code storage location. 4. RAID coding circuit according to claim 1, is characterized in that, The first parameter module is further configured to obtain a second verification parameter corresponding to the current target data stripe of the data to be encoded under RAID 6, and determine the second parameter by using the second verification parameter and the current target data stripe Data after operation; wherein, the second verification parameter corresponding to RAID 6 is the corresponding encoding parameter of the second verification code determined based on the Vandermonde RS coding relationship; Correspondingly, the first encoding module is further configured to perform an encoding operation on the current second check code read from the second check code storage location and the current second parameter operation data to obtain a new second check code code, and store a new second check code in the second check code storage location. 5. RAID encoding circuit according to claim 1, is characterized in that, also comprises: A data caching module, configured to store the target data strips of the data to be encoded in the cache; The data reading module is configured to read the target data strip from the cache, and simultaneously transmit it to the data storage location corresponding to the target data strip and the first parameter module. 6. RAID coding circuit according to claim 3, is characterized in that, described second parameter module is specifically used for: formula based

Determine the second check parameter corresponding to the current target data stripe of the data to be encoded in the RAID 6 mode; Wherein, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is the coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates an XOR operation. 7. A RAID encoding method, characterized in that, comprising: Obtain the first verification parameter corresponding to the current target data strip of the data to be encoded in the current RAID mode, and use the first verification parameter and the current target data strip to perform a multiplication operation to determine the data after the first parameter operation; wherein , the first parity parameter in RAID6 mode is based on the formula

Determined, α ^p is the coding coefficient value corresponding to the first check code determined based on the Vandermonde RS coding relationship, α ^q is the coding coefficient value corresponding to the second check code determined based on the Vandermonde RS coding relationship, and α ^x is The coding coefficient value corresponding to the current target data strip determined based on the Vandermonde RS coding relationship,

Indicates XOR operation, the first check parameter in RAID 5 mode is 1; Perform an XOR operation on the current first check code read from the first check code storage location and the data after the current first parameter operation to obtain a new first check code, and store the new first check code to the storage location of the first check code until the final first check code corresponding to the data to be encoded is determined based on the last target data strip of the data to be encoded. 8. RAID encoding method according to claim 7, is characterized in that, also comprises: dividing the data to be encoded into a preset number of data strips; Convert each data stripe to Galois field data to obtain the target data stripe corresponding to each data stripe.

Images