CN115543216A - Disk array distribution architecture, block calculation method, system, device and medium - Google Patents

Abstract

The present application relates to a disk array distribution architecture, block computing method, system, device and medium, wherein the disk array is RAID10, and RAID10 includes a plurality of stripes, and each stripe includes at least one pair of partitions. When each stripe in RAID10 When the partition size of each disk is set to the first preset size, each stripe includes two pairs of partitions; when the partition size of each disk in RAID10 is set to the second preset size, each stripe includes one Pair of blocks; wherein, each pair of blocks is a mirror image of each other, effectively reducing the memory requirements of the stripe information. In addition, the block calculation method of the disk array distribution architecture is adopted, which eliminates the judgment of the two block sizes in the prior art , directly substituting the block size and other information into the block calculation method can obtain the target block code and target block internal offset of the target block, which reduces the complexity of the calculation method and improves the block calculation efficiency.

Description

Disk array distribution architecture, block computing method, system, device and medium

technical field

The present application relates to the field of storage technology, in particular to a disk array distribution architecture, a block computing method, system, equipment and media.

Background technique

RAID (Redundant Arrays of Independent Disks, disk array) technology is widely used in the storage field, and RAID technology means a set of redundant arrays composed of independent disks. RAID10 is a type of RAID technology. The main technical features of RAID10 are: the construction of disks that are mirror images of each other, and the content of stored data is consistent. When any one of the mirrored disks fails, the data will not be lost, thus ensuring the security of the stored information.

The RAID10 technology includes stripes, and the stripes include blocks, and the block sizes are 256KB (512sector) and 128KB (256sector). When the segment size of a stripe is 256KB (512sector), a stripe consists of 2 segments; due to the fixed capacity of the disk, if the segment size of a stripe is The number of belts will be doubled. Since each stripe requires a certain amount of memory to store the corresponding stripe information, memory requirements become a major issue for doubled stripes.

Contents of the invention

Based on this, the present application provides a disk array distribution architecture, a block computing method, system, device, and medium, so as to reduce memory requirements for stripe information.

In one aspect, a disk array distribution architecture is provided, the disk array is RAID10, the RAID10 includes multiple stripes, each of the stripes includes at least one pair of partitions, when the partitions of each disk in the RAID10 When the block size is set to the first preset size, each of the stripes includes two pairs of blocks; when the block size of each disk in the RAID10 is set to the second preset size, each of the stripes A pair of blocks is included; wherein each pair of blocks is a mirror image of each other.

In one embodiment, when the first preset size is 128KB, the block size of each disk in the RAID10 is set to 128KB, and each stripe includes two pairs of blocks.

In one embodiment, when the first preset size is 256KB, the block size of each disk in the RAID10 is set to 256KB, and each stripe includes a pair of blocks.

On the other hand, a block computing method is provided, and the block computing method includes:

Carry out stripe division to described RAID10 and perform block division under described stripe, and number the divided stripe and division;

Receiving a data transfer instruction, and determining a target stripe, a target stripe number of the target stripe, and an offset within the target stripe according to the data transfer instruction;

Calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

Calculate the target block number of the target block in the target strip according to the number of blocks in the above row of the row where the target strip is located in the RAID10;

calculating a target intra-slice offset of the target block according to a target intra-strip offset of the target slice;

Wherein, the number of blocks is the number of blocks with different block numbers.

In one of the embodiments, the RAID10 is divided into stripes and divided into blocks under the stripes, and the divided stripes and blocks are numbered, including:

Divide the stripes according to the requirements, and determine the block size and its block logarithm;

Carry out block division according to the block size and block logarithm thereof;

Number the divided stripes and blocks.

In one of the embodiments, after obtaining the target block number and the target block internal offset of the target block, it further includes:

A destination address is determined according to the target block number of the target block and the offset within the target block, and data is read or written into the destination address.

In one of the embodiments, the calculation of the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe includes:

Determine the number of disk pairs that are mirror images of each other in the RAID10, and the number of different partitions in each row of the RAID10 with a partition number;

According to the number of disk pairs that are mirror images of each other in the RAID10 and the number of blocks with different block numbers in each row of the RAID10, the above row of the row where the target stripe in the RAID10 is located is calculated by the block number calculation formula number of blocks.

In one of the embodiments, the formula for calculating the number of blocks is:

Stripfirst=(Stretch/Mirrors)*Rowstripcount;

Wherein, Stripfirst is the number of blocks in the above row of the row where the target stripe is located in the RAID10; Stretch is the target stripe number of the target stripe; Mirrors is the number of disk pairs that are mirror images of each other in the RAID10 ; Rowstripcount is the number of blocks with different block numbers in each row of the RAID10.

In one of the embodiments, the calculation of the target block number in the target stripe according to the number of blocks in the row above the row where the target stripe is located in the RAID10 includes:

Calculate the block number of the first block of the disk where the target stripe is located according to the number of blocks in the row above the row where the target stripe is located in the RAID10;

Calculate the incremental number of the specific block where the target block falls on the disk according to the target stripe number of the target stripe and the offset within the target stripe;

According to the block number of the first block of the disk where the target stripe is located and the incremental number of the specific block where the target block falls on the disk, calculate the number of blocks in the target stripe through the block number calculation formula The target chunk number of the target chunk.

In one of the embodiments, the block number calculation formula is:

Stripnum=Stripfirst+Stretch%Mirrors+Mirrors*(Stretchoffset>>Stripsizeshift);

Wherein, Stripnum is the target block number of the target block in the target strip; Stripfirst+Stretch%Mirrors is the number of the first block in the disk where the target strip is located; Stretchoffset is the target strip The offset within the target strip; Stripsizeshift is the calculation index; the Stretchoffset>>Stripsizeshift operation is Stretchoffset/2^(Stripsizeshift).

In one of the embodiments, the calculation method for calculating the index is:

Stripsizeshift=log2(2*Stripsize);

Among them, Stripsize is the block size, and the unit is KB.

In one of the embodiments, the calculating the target intra-block offset of the target block in the target slice according to the target intra-strip offset of the target slice includes:

calculating a block calculation mask according to the block size;

Calculate the target intra-slice offset of the target block by using a block offset calculation formula according to the target intra-slice offset of the target slice and the block calculation mask.

In one of the embodiments, the calculation formula of the block calculation mask is:

Stripsizemask=2*Stripsize-1;

Wherein, Stripsizemask is the block calculation mask.

In one of the embodiments, the formula for calculating the offset within the target block is:

Stripoffset=Stretchoffset&Stripsizemask;

Wherein, Stripoffset is the offset within the target block.

In another aspect, a block computing system is provided, and the block computing system includes:

A stripe partitioning module, configured to divide the RAID10 into stripes and divide the stripes into blocks, and number the divided stripes and partitions;

A target stripe determining module, configured to receive a data transmission instruction, and determine a target stripe, a target stripe number and an intra-strip offset of the target stripe according to the data transmission instruction;

A block number calculation module, configured to calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

A block number calculation module, configured to calculate the target block number of the target block in the target stripe according to the number of blocks in the above row of the row where the target stripe is located in the RAID10;

The block offset calculation module is configured to calculate the target intra-slice offset of the target block according to the target intra-strip offset of the target slice.

In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the following steps when executing the computer program:

Carry out stripe division to described RAID10 and perform block division under described stripe, and number the divided stripe and division;

Receiving a data transfer instruction, and determining a target stripe, a target stripe number of the target stripe, and an offset within the target stripe according to the data transfer instruction;

Calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

Calculate the target block number of the target block in the target strip according to the number of blocks in the above row of the row where the target strip is located in the RAID10;

calculating the target intra-slice offset of the target block according to the target intra-slice offset of the target slice.

In yet another aspect, a computer-readable storage medium is provided, the computer-readable storage medium stores a program, and when the program is executed by a processor, the processor is made to perform the following steps:

Carry out stripe division to described RAID10 and perform block division under described stripe, and number the divided stripe and division;

Receiving a data transfer instruction, and determining a target stripe, a target stripe number of the target stripe, and an offset within the target stripe according to the data transfer instruction;

Calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

Calculate the target block number of the target block in the target strip according to the number of blocks in the above row of the row where the target strip is located in the RAID10;

calculating the target intra-slice offset of the target block according to the target intra-slice offset of the target slice.

The above-mentioned technical scheme of the present application has the following advantages compared with the prior art:

The above-mentioned disk array distribution architecture, block calculation method, system, device and medium, the disk array is RAID10, RAID10 includes a plurality of stripes, each stripe includes at least one pair of partitions, when the partition of each disk in RAID10 When the block size is set to the first preset size, each stripe includes two pairs of blocks; when the block size of each disk in RAID10 is set to the second preset size, each stripe includes a pair of blocks, Whether the block size is the first preset size of 128KB (256sector) or the second preset size of 256KB (512sector), when the hard disk capacity is fixed, the number of stripes of the two sizes is the same, and the required memory is the same. By increasing the number of stripes, there is no need to increase the memory to store additional stripe information, which effectively reduces the demand for memory; in addition, the block calculation method using the RAID10 distribution architecture eliminates the need for two types of data in the prior art. To judge the block size, directly substitute the block size and other information into the block calculation method to obtain the target block code and target block offset, which reduces the complexity of the calculation method and improves the block size. Computational efficiency.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

Fig. 1 is the first architecture diagram of the disk array distribution architecture provided by the embodiment of the present application;

FIG. 2 is a second architecture diagram of the disk array distribution architecture provided by the embodiment of the present application;

Fig. 3 is a flow chart of the first method of the block calculation method provided by the embodiment of the present application;

Fig. 4 is a second method flow chart of the block calculation method provided by the embodiment of the present application;

Fig. 5 is a system structure diagram of the block computing system provided by the embodiment of the present application;

FIG. 6 is a device structural diagram of a computer device provided by an embodiment of the present application.

detailed description

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

Embodiment one:

Referring to FIG. 1 and FIG. 2 , FIG. 1 is a first architecture diagram of a disk array distribution architecture provided by an embodiment of the present application; FIG. 2 is a second architecture diagram of a disk array distribution architecture provided by an embodiment of this application.

The disk array is RAID10, and the partition architecture (spatial distribution architecture) of the RAID10 includes multiple stripes, and each stripe includes at least one pair of partitions. When the partition size of each disk in the RAID10 is When set to the first preset size, each of the stripes includes two pairs of blocks; when the block size of each disk in the RAID10 is set to the second preset size, each of the stripes includes a pairs of blocks; wherein each pair of blocks is a mirror image of each other.

Specifically, in the prior art, each stripe includes a pair of partitions, and the size of each partition includes two specifications: 128KB and 256KB. In a disk, if the block size is changed from 256KB to 128KB, since the capacity of each disk is fixed, the number of stripes needs to be increased, and memory is required to save stripe information, and additional stripes need to increase memory to Storing stripe information increases memory requirements. Therefore, the present invention proposes a RAID10 distribution architecture. As shown in FIG. 1 and FIG. 2 , the RAID10 distribution architecture includes multiple stripes, and each stripe includes at least one pair of partitions. The RAID10 distribution architecture in the present invention is no longer limited to only one pair of partitions, but increases the number of partitions. When the block size of each disk in RAID10 is set to the first preset size, each stripe includes two pairs of blocks; when the block size of each disk in RAID10 is set to the second preset size, each A stripe includes a pair of partitions; no matter whether the partition size is the first preset size or the second preset size, the number of stripes is controlled to be the same, and there is no need to increase the number of stripes, and there is no need to increase the memory to store additional The strip information effectively reduces the memory requirement. Wherein, whether it is the block of the first preset size or the second preset size, each pair of blocks is a mirror image of each other, that is, the data stored in each pair of blocks is the same, achieving data redundancy and improving the security of stored information sex.

In one embodiment, when the first preset size is 128KB, the block size of each disk in the RAID10 is set to 128KB, and each stripe includes two pairs of blocks.

Specifically, there are two block sizes, one is 256KB (512sector), and the other is 128KB (256sector). Therefore, there are two preset sizes of the partitions, the first preset size is 256KB (512sector), and the second preset size is 128KB (256sector). When the first preset size is 128KB, the partition size of each disk in RAID10 is set to 128KB (256sector), and each stripe includes two pairs of partitions, as shown in Figure 1, including 9 stripes, each A stripe includes two pairs of partitions.

In one embodiment, when the second preset size is 256KB, the block size of each disk in the RAID10 is set to 256KB, and each stripe includes a pair of blocks.

Specifically, when the second preset size is 256KB, the partition size of each disk in RAID10 is set to 256KB (512sector), and each stripe includes a pair of partitions, as shown in Figure 2, including 9 stripes , each stripe consists of a pair of partitions.

It can be seen that whether the block size is the first preset size of 128KB (256sector) or the second preset size of 256KB (512sector), when the hard disk capacity is fixed, the number of stripes of the two sizes is the same, and the required The memory is the same, there is no need to increase the number of stripes, and there is no need to increase memory to store additional stripe information, effectively reducing the demand for memory.

Embodiment two:

Referring to FIG. 3 , FIG. 3 is a flow chart of the first method of the block calculation method provided by the embodiment of the present application.

The method includes the following steps:

S101. Divide the RAID10 into stripes and divide the stripes into blocks, and number the divided stripes and blocks;

Specifically, preparations need to be made before data transmission, that is, RAID10 is divided into stripes and partitions under the stripes, and the divided stripes and partitions are numbered, so that the subsequent The target stripe number and the target intra-strip offset of the target block are calculated to obtain the target block number and the target intra-block offset.

S102. Receive a data transmission instruction, and determine a target stripe, a target stripe number of the target stripe, and an offset within the target stripe according to the data transmission instruction;

Specifically, after receiving the data transfer instruction, the target stripe, the target stripe number and the target stripe internal offset can be determined according to the data transfer instruction, so that according to the target stripe number and the target stripe The in-band offset is calculated to obtain the target block number and the target block internal offset, obtain the specific address, and transmit the data to the corresponding address.

S103. Calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

Specifically, in order to store data in the disk, it is necessary to calculate the storage address of the disk, that is, calculate the block number and the offset within the block according to the stripe number and the offset within the stripe. In the present invention, a stripe that needs to store data is called a target stripe, and a block that needs to store data is called a target block. Therefore, the block calculation method of the present invention calculates the target block number and the target block offset of the target block according to the target slice number and the target slice offset. First, calculate the number of blocks in the row above the row where the target stripe is located in RAID10 based on the target stripe number of the target stripe, as shown in Figure 1. For example, if the target stripe number is Stretch4, then the number of blocks in the row where the target stripe is located The number of chunks in the above row is the number of chunks 6 in the first row. Wherein, the number of blocks is the number of blocks with different block numbers, so the number of blocks in the first row is 6.

S104. Calculate the target block number of the target block in the target stripe according to the number of blocks in the row above the row where the target stripe is located in the RAID10;

Specifically, after calculating the number of partitions in the row above the row where the target stripe is located in RAID10 according to the target stripe number of the target stripe, the number of partitions in the row above the row where the target stripe is located in RAID10 can be calculated by Get the target block number of the target block in the target stripe.

S105. Calculate the target intra-slice offset of the target block according to the target intra-strip offset of the target slice;

Specifically, after the target block number of the target block in the target stripe is obtained by calculation, the target block offset of the target block can be obtained through calculation according to the target stripe offset of the target slice, and the target block The specific address in the disk can be obtained by adding the number and the offset in the target block, and then the data can be written into the address in the disk. A block calculation method using the RAID10 distribution architecture is given, which removes the judgment of the two block sizes in the prior art, and directly substitutes the block size and other information into the block calculation method to obtain the target score of the target block. The block encoding and the offset within the target block reduce the complexity of the calculation method and improve the block calculation efficiency.

Wherein, the number of blocks is the number of blocks with different block numbers.

In one of the implementation manners, the RAID10 is divided into stripes and divided into blocks under the stripes, and the divided stripes and blocks are numbered, including:

Divide the stripes according to the requirements, and determine the block size and its block logarithm;

Specifically, divide the stripes according to the actual needs, determine how many stripes need to be divided; then determine the block size according to the actual needs, that is, the block size is 128KB or 256KB, and determine the logarithm of the blocks.

Carry out block division according to the block size and block logarithm thereof;

Specifically, after the block size and the logarithm of the blocks are determined, the blocks can be divided according to the block size and the logarithm of the blocks.

Number the divided stripes and blocks.

Specifically, after the stripes and blocks are divided, all the stripes and blocks are numbered, so that the number of the target block can be obtained through subsequent calculations based on the target stripe number and the offset within the target stripe. The target block number and the offset within the target block.

In one of the implementation manners, after obtaining the target block number and the target block internal offset of the target block, it further includes:

A destination address is determined according to the target block number of the target block and the offset within the target block, and data is read or written into the destination address.

Specifically, after calculating the target block number and the target block offset according to the target stripe number and the target stripe offset, according to the target block number and the target The offset within the block determines the destination address, and the data is read or written to the destination address to complete the data transmission operation.

In one of the implementation manners, the calculation of the number of partitions in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe includes:

Determine the number of disk pairs that are mirror images of each other in the RAID10, and the number of different partitions in each row of the RAID10 with a partition number;

Specifically, in order to obtain the target block number through calculation, the target block number must be obtained through corresponding calculation according to the target stripe number of the target stripe. First of all, according to RAID10, it is necessary to determine the number of disk pairs that are mirrored to each other in the disk array, and the number of blocks with different block numbers in each row in the RAID10 disk array, so that through the number of disk pairs that are mirrored and each row The number of partitions with different block numbers is used to determine the number of partitions in the row above the row of the target stripe.

According to the number of disk pairs that are mirror images of each other in the RAID10 and the number of blocks with different block numbers in each row of the RAID10, the above row of the row where the target stripe in the RAID10 is located is calculated by the block number calculation formula number of blocks.

Specifically, after obtaining the number of disk pairs that are mirrored to each other and the number of blocks with different block numbers in each row, you can use related calculation formulas to pass the number of disk pairs that are mirrored to each other and the block numbers in each row. Calculate the number of blocks in the row above the row where the target stripe is located in RAID10, so as to calculate the first disk number of the target stripe based on the number of blocks in the row above the row where the target stripe is located in RAID10 The block number of the block.

In one of the implementation manners, the formula for calculating the number of blocks is:

Stripfirst = (Stretch/Mirrors)*RowStripCount;

Wherein, Stripfirst is the number of blocks in the above row of the row where the target stripe is located in the RAID10; Stretch is the target stripe number of the target stripe; Mirrors is the number of disk pairs that are mirror images of each other in the RAID10 ; Rowstripcount is the number of blocks with different block numbers in each row of the RAID10.

Specifically, according to the number of disk pairs that are mirror images of each other in RAID10 and the number of blocks with different block numbers in each row of RAID10, the number of blocks in the above row of the row where the target stripe is located in RAID10 is calculated through the block number calculation formula, The formula for calculating the number of blocks is Stripfirst=(Stretch/Mirrors)*Rowstripcount. As shown in Figure 1, the block size is 128KB, and Mirrors is the number of disk pairs that are mirrored to each other in RAID10 (the number of disks divided by 2). The distribution architecture shown in Figure 1 includes 6 disks, and Disk 0 and Disk 1 are mutually mirrored. Mirroring, disk 2 and disk 3 are mirror images of each other, and disk 4 and disk 5 are mirror images of each other, that is, three pairs of disks (dividing the number of disks by 6 by 2 equals 3). Assuming Stretch4 is given, then Stripfirst=(Stretch/Mirrors)*Rowstripcount=(4/3)*6=6, where the operation symbol "/" is the quotient, and the number of blocks is the number of blocks with different block numbers , the number of blocks in the row above the row where the target strip is located is 6, that is, Strip0, Strip1, Strip2, Strip3, Strip4, and Strip5.

In one of the implementation manners, the calculation of the target block number in the target stripe according to the number of blocks in the row above where the target stripe is located in the RAID10 includes:

Calculate the block number of the first block of the disk where the target stripe is located according to the number of blocks in the row above the row where the target stripe is located in the RAID10;

Specifically, after obtaining the number of blocks in the row above the row where the target stripe is located in RAID10, the target stripe can be obtained by calculating according to the corresponding calculation formula according to the number of blocks in the row above the row where the target stripe is located in RAID10. The block number of the first block of the disk where the tape is located, so as to calculate the target block number of the target block in the target stripe through the block number.

Calculate the incremental number of the specific block where the target block falls on the disk according to the target stripe number of the target stripe and the offset within the target stripe;

Specifically, after obtaining the block number of the first block of the disk where the target stripe is located, the target score can be calculated according to the target stripe number and the offset within the target stripe through the corresponding calculation formula. The incremental number of the specific block where the block falls on the disk, so as to calculate the target block number of the target block in the target stripe through the block number and the incremental number of the first block.

According to the block number of the first block of the disk where the target stripe is located and the incremental number of the specific block where the target block falls on the disk, calculate the number of blocks in the target stripe through the block number calculation formula The target chunk number of the target chunk.

Specifically, after obtaining the block number of the first block of the disk where the target stripe is located and the incremental number of the specific block in the disk where the target block is located, the number of the first block of the disk where the target stripe is located is Substituting the block number and the incremental number of the specific block where the target block falls on the disk into the corresponding calculation formula can obtain the target block number of the target block in the target stripe.

In one of the implementation manners, the formula for calculating the block number is:

Stripnum=Stripfirst+Stretch%Mirrors+Mirrors*(Stretchoffset>>Stripsizeshift);

Wherein, Stripnum is the target block number of the target block in the target strip; Stripfirst+Stretch%Mirrors is the number of the first block in the disk where the target strip is located; Stretchoffset is the target strip The offset within the target strip; Stripsizeshift is the calculation index; the Stretchoffset>>Stripsizeshift operation is Stretchoffset/2^(Stripsizeshift).

Specifically, in order to obtain the target block number of the target block, it is first necessary to calculate the block number of the first block of the disk where the target stripe is located based on the number of blocks in the row above the line where the target stripe is located in RAID10 , and then calculate the incremental number of the specific block where the target block falls on the disk according to the target stripe number of the target stripe and the offset within the target stripe, and then according to the block of the first block of the disk where the target stripe is located The number and the incremental number of the specific block where the target block falls on the disk is used to calculate the target block number of the target block in the target stripe through the block number calculation formula. The calculation formula for the partition number is: Stripnum=Stripfirst+Stretch%Mirrors+Mirrors*(Stretchoffset>>Stripsizeshift); where, the number of partitions in the row above the row where the target stripe is located in RAID10 is used to calculate the number of disks where the target stripe is located. The calculation method of the block number of the first block is Stripfirst+Stretch%Mirrors; for example, given Stretch4, as shown in Figure 2, when the block size is 256KB, Stripfirst+Stretch%Mirrors = (4/3)* 3+(4%3)=4, corresponding to the block number 4 (Strip4) in Figure 2; when the block size is 128KB, Stripfirst+Stretch%Mirrors = (4/3)*6+(4%3)= 7, corresponding to the block number 7 (Strip4) in Figure 1, where the operation symbol "%" is the remainder. According to the target stripe number of the target stripe and the offset within the target stripe, calculate the incremental number of the target block falling on the disk. The calculation method is Stretchoffset >>Stripsizeshift, and the specific operation is Stretchoffset/2^(Stripsizeshift) ;For example, the target strip number of a given target strip is Stretch4, and the target strip's internal offset is Stretchoffset=258sector, as shown in Figure 1, the block size is 128KB=256sector=2^8=2^Stripsizeshift , then Stretchoffset>>Stripsizeshift=Stretchoffset/2^(Stripsizeshift)=258/256=1, which means it falls on the second block of the two blocks (the calculation result of falling on the first block is 0, and it falls on The second chunk evaluates to 1). As shown in Figure 2, the block size is 256KB=512sector=2^9=2^Stripsizeshift, then Stretchoffset>>Stripsizeshift=Stretchoffset/2^(Stripsizeshift)=256/512=0, in this architecture, one disk is in one row There is only one block in , therefore, the Stretchoffset/512 value is always 0, which means it falls on the first one. Then, according to the block number of the first block of the disk where the target stripe is located and the incremental number of the specific block where the target block falls on the disk, calculate the target of the target block in the target stripe through the block number calculation formula The calculation method of the block number is Stripnum=Stripfirst+Stretch%Mirrors+Mirrors*(Stretchoffset>>Stripsizeshift); as shown in Figure 1, assuming that the target strip number of a given target strip is Stretch4, the target strip number of the target strip The inner offset is Stretchoffset=258sector, then Stripfirst+Stretch%Mirrors+Mirrors*(Stretchoffset>>Stripsizeshift)=(4/3)*6+(4%3)+3*(258/2^8)=10, It corresponds to Strip10 in Figure 1.

In one of the implementations, the calculation method for calculating the index is:

Stripsizeshift=log2(2*Stripsize);

Among them, Stripsize is the block size, and the unit is KB.

Specifically, according to the target strip number of the target strip and the offset within the target strip, the calculation method for calculating the incremental number of the specific block where the target block falls in the disk is Stretchoffset/2^(Stripsizeshift), wherein, Stripsizeshift The calculation method is Stripsizeshift=log2(2*Stripsize); Stripsize is the block size, the unit is KB, 2*Stripsize means the unit is converted to sector, that is, the block size=128KB, and the converted sector unit is 256sector.

In one of the implementation manners, the calculating the target intra-block offset of the target block in the target slice according to the target intra-strip offset of the target slice includes:

calculating a block calculation mask according to the block size;

Specifically, after calculating the number of target blocks in the target stripe according to the number of blocks in the row above the row where the target stripe is located in RAID10, it is necessary to further calculate the number of blocks in the target stripe based on the offset within the target stripe. The target intra-block offset of the target block first needs to be calculated according to the block size to obtain the block calculation mask, so that the target strip intra-strip offset and block calculation mask can be calculated through the block offset The formula calculates the offset within the target block for the target block.

Calculate the target intra-slice offset of the target block by using a block offset calculation formula according to the target intra-slice offset of the target slice and the block calculation mask.

Specifically, after the block calculation mask is calculated according to the block size, the target block internal offset of the target block is calculated according to the target slice offset and the block calculation mask through the block offset calculation formula. Offset, through the above calculation, the target block number of the target block and the offset within the target block are obtained, so that the specific address in the disk is located, and the data can be written to the address.

In one of the implementation manners, the calculation formula of the block calculation mask is:

Stripsizemask=2*Stripsize-1;

Wherein, Stripsizemask is the block calculation mask.

Specifically, the formula for calculating the block calculation mask calculated according to the block size is Stripsizemask=2*Stripsize-1, where Stripsizemask is the block calculation mask, and Stripsize is the block size, and the unit is KB. For example, when the block size is 128KB, the block calculation mask is 2*128-1=255; when the block size is 256KB, the block calculation mask is 2*256-1=511.

In one of the implementation manners, the formula for calculating the offset within the target block is:

Stripoffset=Stretchoffset &Stripsizemask;

Wherein, Stripoffset is the offset within the target block.

Specifically, after the block calculation mask is calculated according to the block size, the target block internal offset of the target block is calculated according to the target slice offset and the block calculation mask through the block offset calculation formula. Offset, the block offset calculation formula is: Stripoffset=Stretchoffset &Stripsizemask; as shown in Figure 2, when the block size is 256KB, the converted sector unit is 512sector, Stripsizemask=512-1=2^9-1=511 (Binary 11111111), at this time Stripsizeshift is 9, when the target strip offset within the target strip is Stretchoffset=510sector (binary 111111110), Stripoffset=Stretchoffset & Stripsizemask=111111110&11111111=111111110 (decimal 510), so it can be obtained The target intra-block offset of the target block is 510sector.

Embodiment three:

Referring to FIG. 4 , FIG. 4 is a flowchart of a second method of the method provided by the embodiment of the present application. Wherein, in the method shown in FIG. 4 , for the same or similar content as in the method shown in FIG. 3 , reference may be made to the description in the method shown in FIG. 3 , and details are not repeated here.

S201, perform stripe division according to requirements, and determine the block size and the logarithm of the block;

Carry out stripe division according to actual needs, determine how many stripes need to be divided; then determine the block size according to actual needs, that is, the block size is 128KB or 256KB, and determine the logarithm of the blocks.

S202. Perform block division according to the block size and logarithm thereof;

After the block size and block logarithm are determined, the blocks can be divided according to the block size and block logarithm.

S203. Number the divided stripes and blocks.

After the stripes and blocks are divided, number all the stripes and blocks, so that the target block of the target block can be obtained by calculation according to the target stripe number and the offset within the target stripe Number and offset within the target block.

S204. Receive a data transmission instruction, and determine a target stripe, a target stripe number and an offset within the target stripe according to the data transmission instruction;

After receiving the data transmission instruction, the target stripe, the target stripe number and the target stripe internal offset can be determined according to the data transmission instruction, so that the target stripe number and the target stripe internal offset of the target stripe can be The shift obtains the target block number and the offset within the target block by calculating the target block, obtains the specific address, and transmits the data to the corresponding address.

S205. Determine the number of disk pairs that are mirror images of each other in the RAID10, and the number of blocks with different block numbers in each row of the RAID10;

In order to obtain the target block number through calculation, the target block number must be obtained through corresponding calculation according to the target stripe number of the target stripe. First of all, according to RAID10, it is necessary to determine the number of disk pairs that are mirrored to each other in the disk array, and the number of blocks with different block numbers in each row in the RAID10 disk array, so that through the number of disk pairs that are mirrored and each row The number of partitions with different block numbers is used to determine the number of partitions in the row above the row of the target stripe.

S206, according to the number of disk pairs that are mirror images of each other in the RAID10 and the number of blocks with different block numbers in each row of the RAID10, calculate the above number of the row where the target stripe in the RAID10 is located by using the block number calculation formula the number of chunks in the row;

After obtaining the number of disk pairs that are mirrored to each other and the number of blocks with different block numbers in each row, you can use related calculation formulas to pass the number of disk pairs that are mirrored to each other and the number of blocks with different block numbers in each row Calculate the number of partitions in the row above the row where the target stripe is located in RAID10, so as to calculate the first partition of the disk where the target stripe is located based on the number of partitions in the row above the row where the target stripe is located in RAID10 block number.

S207. Calculate the block number of the first block of the disk where the target stripe is located according to the number of blocks in the row above the row where the target stripe is located in the RAID10;

After obtaining the number of blocks in the row above the row where the target stripe is located in RAID10, the disk where the target stripe is located can be obtained by calculating according to the corresponding calculation formula based on the number of blocks in the row above the row where the target stripe is located in RAID10 The block number of the first block of , so as to calculate the target block number of the target block in the target stripe through the block number.

S208. Calculate, according to the target stripe number of the target stripe and the offset within the target stripe, the incremental number of the specific block where the target block falls on the disk;

After obtaining the block number of the first block of the disk where the target stripe is located, according to the target stripe number and the offset within the target stripe, the corresponding calculation formula can be used to calculate the location of the target Incremental numbers of specific blocks in the disk, so as to calculate the target block number of the target block in the target stripe through the block number of the first block and the incremental number.

S209, calculate the target stripe according to the block number of the first block of the disk where the target stripe is located and the increment number of the specific block where the target block falls on the disk, using a block number calculation formula The target block number of the target block in ;

After obtaining the block number of the first block of the disk where the target stripe is located and the incremental number of the specific block where the target block falls on the disk, set the block number of the first block of the disk where the target stripe is located The target block number of the target block in the target stripe can be obtained by substituting the incremental number of the specific block on the disk with the target block into the corresponding calculation formula.

S210. Calculate and obtain a block calculation mask according to the block size;

After calculating the number of target blocks in the target stripe according to the number of blocks in the row above the row where the target stripe is located in RAID10, it is necessary to further calculate the target block in the target stripe according to the offset within the target stripe The target intra-block offset of , firstly, calculate the block calculation mask according to the block size, so that the target strip intra-strip offset and block calculation mask can be calculated by the block offset calculation formula The offset within the target chunk for the target chunk.

S211. Calculate the target intra-slice offset of the target block by using a block offset calculation formula according to the target intra-slice offset of the target slice and the block calculation mask;

After calculating the block calculation mask according to the block size, calculate the target block offset of the target block through the block offset calculation formula according to the target stripe intra-strip offset and block calculation mask, Through the above calculation, the target block number and the target block internal offset of the target block are obtained, so that the specific address in the disk is located, and the data can be written into the address.

S212. Determine a destination address according to the target block number of the target block and the offset within the target block, and read or write data to the destination address.

After calculating the target block number and the target block offset according to the target stripe number and target stripe offset of the target stripe, according to the target block number and target block The offset determines the destination address, and the data is read or written to the destination address to complete the data transfer operation.

It should be understood that although the steps in the flow charts of FIGS. 3 to 4 are displayed sequentially according to the arrows, these steps are not necessarily executed in sequence according to the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in FIGS. 3 to 4 may include a plurality of sub-steps or stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. These sub-steps or The execution order of the stages is not necessarily performed sequentially, but may be executed alternately or alternately with at least a part of other steps or substeps of other steps or stages.

Embodiment four:

Referring to FIG. 5 , FIG. 5 is a system structure diagram of a block computing system provided by an embodiment of the present application.

The block computing system of this embodiment includes:

A stripe partitioning module, configured to divide the RAID10 into stripes and divide the stripes into blocks, and number the divided stripes and partitions;

Before data transmission, it is necessary to make preparations, that is, divide the RAID10 into stripes and partitions under the stripes through the stripe and block division module, and number the divided stripes and blocks for subsequent The target segment number and the target internal offset of the target block are obtained through calculation according to the target stripe number and the target intra-strip offset.

A target stripe determining module, configured to receive a data transmission instruction, and determine a target stripe, a target stripe number and an intra-strip offset of the target stripe according to the data transmission instruction;

After receiving the data transmission instruction, according to the data transmission instruction, the target stripe, the target stripe number and the target stripe internal offset can be determined through the target stripe determination module, so that the target stripe number and the target stripe number of the target stripe and the offset in the target stripe are calculated to obtain the target block number and the offset in the target block, obtain a specific address, and transmit the data to the corresponding address.

A block number calculation module, configured to calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

To store data in the disk, it is necessary to calculate the storage address of the disk, that is, calculate the block number and the offset within the block according to the stripe number and the offset within the stripe. In the present invention, a stripe that needs to store data is called a target stripe, and a block that needs to store data is called a target block. Therefore, the block calculation method of the present invention calculates the target block number and the target block offset of the target block according to the target slice number and the target slice offset. First, calculate the number of blocks in the row above the row where the target stripe is located in RAID10 according to the target stripe number of the target stripe through the block number calculation module.

A block number calculation module, configured to calculate the target block number of the target block in the target stripe according to the number of blocks in the above row of the row where the target stripe is located in the RAID10;

After calculating the number of blocks in the row above the row where the target stripe is located in RAID10 according to the target stripe number of the target stripe, use the block number calculation module to calculate the number of blocks in the row above the row where the target stripe is located in RAID10 The target block number of the target block in the target stripe can be obtained through calculation.

The block offset calculation module is configured to calculate the target intra-slice offset of the target block according to the target intra-strip offset of the target slice.

After the target block number of the target block in the target stripe is obtained by calculation, the target block offset of the target block can be obtained through calculation according to the target stripe offset of the target stripe through the block offset calculation module , the target block number plus the offset within the target block can get the specific address in the disk, and then the data can be written into the address in the disk.

In one of the implementation manners, the block calculation system also includes:

The first block calculation module is used to calculate the block number of the first block of the disk where the target stripe is located according to the number of blocks in the row above the row where the target stripe is located in the RAID10;

After obtaining the number of blocks in the row above the line where the target stripe is located in RAID10, the first block calculation module is used to calculate the number of blocks in the row above the line where the target stripe is located in RAID10 through the corresponding calculation formula. The block number of the first block of the disk where the target stripe is located can be obtained, so as to calculate the target block number of the target block in the target stripe through the block number.

An incremental number calculation module, configured to calculate the incremental number of the target block falling on the disk according to the target stripe number and the target stripe internal offset;

After obtaining the block number of the first block of the disk where the target stripe is located, the incremental number calculation module can calculate it according to the target stripe number of the target stripe and the offset within the target stripe through the corresponding calculation formula Output the incremental number of the specific block where the target block falls on the disk, so as to calculate the target block number of the target block in the target stripe through the block number and the incremental number of the first block.

A block mask calculation module, configured to calculate a block calculation mask according to the block size.

After calculating the number of target blocks in the target stripe according to the number of blocks in the row above the row where the target stripe is located in RAID10, it is necessary to further calculate the target block in the target stripe according to the offset within the target stripe The offset within the target block of the target slice, firstly, the block calculation mask is calculated by the block mask calculation module according to the block size, so that the target slice offset and the block calculation mask can be passed through the block The block offset calculation formula calculates the target intra-block offset of the target block.

For specific limitations on the block computing system, refer to the above-mentioned limitations on the method, and details will not be repeated here. Each module in the above block computing system can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

Embodiment five:

This embodiment provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the steps of the block calculation method when executing the computer program.

The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 6 . The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the block computing method can be realized. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touch pad provided on the casing of the computer device , and can also be an external keyboard, touchpad, or mouse.

Those skilled in the art should understand that the structure shown in Figure 6 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this application is applied. The specific computer Devices may include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one of the embodiments, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the following steps are implemented:

Carry out stripe division to described RAID10 and perform block division under described stripe, and number the divided stripe and division;

Receiving a data transfer instruction, and determining a target stripe, a target stripe number of the target stripe, and an offset within the target stripe according to the data transfer instruction;

Calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

Calculate the target block number of the target block in the target strip according to the number of blocks in the above row of the row where the target strip is located in the RAID10;

calculating the target intra-slice offset of the target block according to the target intra-slice offset of the target slice.

Embodiment six:

This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

Carry out stripe division to described RAID10 and perform block division under described stripe, and number the divided stripe and division;

Receiving a data transfer instruction, and determining a target stripe, a target stripe number of the target stripe, and an offset within the target stripe according to the data transfer instruction;

Calculate the number of blocks in the above row of the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

Calculate the target block number of the target block in the target strip according to the number of blocks in the above row of the row where the target strip is located in the RAID10;

calculating the target intra-slice offset of the target block according to the target intra-slice offset of the target slice.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only represent several implementation modes of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as limiting the scope of the patent for the invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of protection of the patent application should be based on the appended claims.

Claims (17)

1. A disk array distribution architecture, wherein the disk array is a RAID10, the RAID10 includes a plurality of stripes, each stripe includes at least one pair of split blocks, and when a split block size of each disk in the RAID10 is set to a first preset size, each stripe includes two pairs of split blocks; when the block size of each disk in the RAID10 is set to be a second preset size, each stripe comprises a pair of blocks; wherein each pair of the blocks are mirror images of each other.

2. The disk array distribution architecture as claimed in claim 1, wherein when the first predetermined size is 128KB, the block size of each disk in the RAID10 is set to 128KB, and each of the stripes comprises two pairs of blocks.

3. The disk array distribution architecture as claimed in claim 1, wherein when the first predetermined size is 256KB, the block size of each disk in the RAID10 is set to 256KB, and each of the stripes comprises a pair of blocks.

4. A block calculation method using the disk array distribution architecture according to any one of claims 1 to 3, the block calculation method comprising:

performing stripe division on the RAID10, performing block division under the stripes, and numbering the divided stripes and blocks;

receiving a data transmission instruction, and determining a target band, a target band number of the target band and an offset in the target band according to the data transmission instruction;

calculating the number of blocks in the rows above the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

calculating the target block number of the target block in the target stripe according to the block number in the upstream row of the target stripe in the RAID 10;

calculating a target intra-block offset of the target block according to the target intra-band offset of the target band;

and the number of the blocks is the number of the blocks with different block numbers.

5. The partition calculation method of claim 4, wherein striping the RAID10 and partitioning the partitions under the stripes, and numbering the partitioned stripes and partitions comprises:

dividing strips according to requirements, and determining the size and the logarithm of the blocks;

partitioning according to the size and the number of the partitioning pairs of the partitions;

and numbering the divided strips and blocks.

6. The block calculation method according to claim 4, wherein after obtaining the target block number and the target intra-block offset of the target block, the method further comprises:

and determining a destination address according to the target block number of the target block and the offset in the target block, and reading or writing data into the destination address.

7. The block calculation method according to claim 4, wherein the calculating the number of blocks in the rows above the row of the target stripe in the RAID10 according to the target stripe number of the target stripe comprises:

determining the disk pairs which are mirror images of each other in the RAID10 and the number of blocks with different block numbers in each row of the RAID 10;

and calculating the number of blocks in the rows above the row of the target strip in the RAID10 according to the disk pair number which is a mirror image in the RAID10 and the number of blocks with different block numbers in each row of the RAID10 by using a block number calculation formula.

8. The block calculation method according to claim 7, wherein the block number calculation formula is:

Stripfirst=（Stretch/Mirrors)*Rowstripcount；

wherein, stripfirst is the number of blocks in the row above the row where the target stripe is located in the RAID 10; stretch is the target stripe number of the target stripe; mirrors are the number of pairs of disks which are mirror images in the RAID 10; rowstripcount is the number of blocks with different block numbers in each row of the RAID 10.

9. The partition calculation method according to claim 7, wherein the calculating a target partition number in the target stripe according to the number of partitions in the row above the row where the target stripe is located in the RAID10 comprises:

calculating the block number of the first block of the disk where the target strip is located according to the block number in the upstream of the row where the target strip is located in the RAID 10;

calculating the increment number of the specific block of the target block in the disk according to the target strip number of the target strip and the offset in the target strip;

and calculating the target block number of the target block in the target strip through a block number calculation formula according to the block number of the first block of the disk where the target strip is located and the increment number of the specific block of the target block in the disk.

10. The block calculation method according to claim 9, wherein the block number calculation formula is:

Stripnum=Stripfirst+Stretch%Mirrors+Mirrors*（Stretchoffset>>Stripsizeshift）；

wherein Stripnum is a target block number of a target block in the target stripe; the Stripfirst + Stretch% Mirrors is the number of the first block in the disk where the target stripe is located; stretchoffset is a target intra-band offset of the target band; strisizeshift is a calculation index; stretchoffset > > Stripsezeshift operation is Stretchoffset/2^ (Stripsezeshift).

11. The block calculation method according to claim 10, wherein the calculation method of the calculation index is:

Stripsizeshift=log ₂ (2*Stripsize)；

wherein, the Stripsize is the size of the block and the unit is KB.

12. The partition calculation method of claim 9, wherein the calculating a target intra-partition offset for a target partition in the target stripe from a target intra-stripe offset for the target stripe comprises:

calculating according to the size of the blocks to obtain a block calculation mask;

and calculating the target intra-block offset of the target block through a block offset calculation formula according to the target intra-strip offset of the target strip and the block calculation mask.

13. The block calculation method according to claim 12, wherein the calculation formula of the block calculation mask is:

Stripsizemask=2*Stripsize-1；

wherein the stripzemask computes a mask for the partitions.

14. The block computation method of claim 13, wherein the target intra-block offset computation formula is:

Stripoffset=Stretchoffset&Stripsizemask；

wherein the Stripoffset is the target intra-block offset.

15. A tile computing system, comprising:

the system comprises a stripe partitioning module, a data partitioning module and a data partitioning module, wherein the stripe partitioning module is used for performing stripe partitioning on RAID10, performing partitioning under the stripe, and numbering the partitioned stripes and the partitioned blocks;

the target strip determining module is used for receiving a data transmission instruction and determining a target strip, a target strip number of the target strip and an offset in the target strip according to the data transmission instruction;

the block number calculation module is used for calculating the block number in the rows above the row where the target stripe is located in the RAID10 according to the target stripe number of the target stripe;

a block number calculation module, configured to calculate a target block number of a target block in the target stripe according to the number of blocks in an uplink above a row where the target stripe is located in the RAID 10;

and the block offset calculation module is used for calculating the target block offset of the target block according to the target intra-stripe offset of the target stripe.

16. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any one of claims 4 to 14 are implemented when the computer program is executed by the processor.

17. A computer-readable storage medium, characterized in that: the computer-readable storage medium stores a program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 4 to 14.

Images