WO2023141987A1

WO2023141987A1 - File reading method and apparatus

Info

Publication number: WO2023141987A1
Application number: PCT/CN2022/074786
Authority: WO
Inventors: 苏杰; 朱胜; 刘光辉
Original assignee: 华为技术有限公司
Priority date: 2022-01-28
Filing date: 2022-01-28
Publication date: 2023-08-03
Also published as: CN116830096A

Abstract

Provided in the present application is a file reading method, which is applied to a storage controller. The method comprises: obtaining a file reading request from a processor by means of a file reading interface, wherein the file reading request carries a logic address of a target index node, a start offset address and the length of target data, the target data is at least part of data in a target file, the target index node is an index node of the target file, the start offset address is used for indicating a start location of the target data in the target file, and the target index node is used for indicating data in the target file; reading the target data from the target file according to the logic address of the target index node, the start offset address and the length of the target data; and sending the target data to the processor. By means of the present application, the number of interactions between a processor and a storage controller is reduced, thereby improving the file reading performance.

Description

File reading method and device

technical field

The present application relates to the field of computer information technology, in particular to a file reading method and device.

Background technique

In the context of the big data era, flash memory has become the mainstream storage medium instead of disk to meet the fast storage requirements of large amounts of data.

The sequential write feature of Log Structured File Systems is very friendly to flash memory, showing good random write performance. Since the log-structured file system has a sequential writing feature, file data is frequently created, updated, and deleted, which will result in discontinuous logical addresses of multiple data blocks storing file data.

In the prior art, when reading data from a file, the processor first reads the logical address of the data block storing the data from the storage medium, and then sends the logical address of the data block storing the data to the storage medium, so that the storage medium Read data according to the logical address of the data block where the data is stored and return the read data to the processor. Based on this, when the logical addresses of multiple data blocks storing data are continuous, the processor only needs to send the logical address of the first data block and the length of the read data to the storage medium once to read the data from the storage medium. When the logical addresses of multiple data blocks storing data are discontinuous, the processor needs to send the discontinuous logical addresses of the data blocks to the storage medium multiple times to read data from the storage medium. Obviously, when the logical addresses of multiple data blocks storing data are discontinuous, the processor needs to send the discontinuous logical addresses of the data blocks to the storage medium multiple times, which increases the number of interactions between the processor and the storage medium and reduces the time required for reading files. data performance.

Contents of the invention

The present application provides a file reading method and device, which are used to solve the problem that when reading file data, the number of interactions between a processor and a storage medium increases, and the performance of reading file data decreases.

In a first aspect, the present application provides a file reading method applied to a storage controller, including: obtaining a file reading request from a processor through a file reading interface; wherein, the file reading request carries the Logical address, start offset address and the length of the target data, the target data is at least a part of data in the target file, the target index node is the index node of the target file, and the start offset address is used for Indicate the start position of the target data in the target file, and the target index node is used to indicate the data in the target file; according to the logical address of the target index node, the start offset address and the target data length of , reading the target data from the target file and sending the target data to the processor.

Since the file read request carries the logical address of the target index node, the start offset address, and the length of the target data, and the target index node is used to indicate the data in the target file, the target data is at least a part of the data in the target file, and the start The offset address is used to indicate the starting position of the target data in the target file. Therefore, after the storage controller receives the file read request, it can determine the data of the target file indicated in the target inode according to the logical address of the target inode , and read the target data from the target file according to the data of the target file, the start offset address and the length of the target data. Based on this, when the processor reads the target data from the target file, the processor only needs to send a file read request carrying the logical address of the target inode, the start offset address and the length of the target data to the storage controller, namely Allows the storage controller to return target data to the processor based on a file read request. Obviously, when reading the target data from the target file, the processor only needs to send a file read request to the storage controller. Compared with the prior art, there is no need to consider whether the logical addresses of multiple data blocks storing data are continuous, and when When the logical addresses of multiple data blocks storing data are discontinuous, there is no need for the processor to send discontinuous logical addresses of data blocks to the storage controller multiple times, which reduces the number of interactions between the processor and the storage controller and improves file reading. performance.

In a possible implementation manner, the target index node indicates an address list of the target file, where the address list of the target file includes a one-to-one correspondence between multiple offset addresses and multiple data block logical addresses ; According to the logical address of the target index node, the start offset address and the length of the target data, reading the target data from the target file includes: determining the target index node according to the logical address The target index node; according to the length of the target data and the start offset address, and in combination with the address list of the target file indicated by the target index node, determine the logical address of the data block corresponding to the target data; according to The logical address of the data block corresponding to the target data is used to read the target data.

In a possible implementation manner, the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer; the priority of the pointers is from high to The lower order is: the plurality of direct pointers, the plurality of first-level indirect pointers, the plurality of second-level indirect pointers, and the at least one third-level indirect pointer; according to the order of priority from high to low, At least one of the multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer is used to indicate the address list of the target file.

In a possible implementation manner, according to the length of the target data and the start offset address, combined with the address list of the target file indicated by the target inode, determine the address corresponding to the target data The logical address of the data block includes: according to the length of the target data and the start offset address, and based on the multiple direct pointers, the multiple primary indirect pointers, the multiple secondary indirect pointers, or the multiple an address list of the target file indicated by at least one of the at least one three-level indirect pointer, and determine the logical address of the data block corresponding to the target data.

In a possible implementation manner, the data of the target file is stored in the target index node; according to the logical address of the target index node, the starting offset address and the length of the target data, from the target file Reading the target data includes: determining the target index node according to the logical address of the target index node; according to the start offset address and the length of the target data, from the The target data is read from data in the target file.

In a possible implementation manner, the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer; the priority of the pointers is from high to The lower order is: the plurality of direct pointers, the plurality of first-level indirect pointers, the plurality of second-level indirect pointers, and the at least one third-level indirect pointer; when the size of the target file is less than or equal to In the case of the first preset value: the multiple direct pointers are used to store the data of the target file; according to the starting offset address and the length of the target data, from the target index node Reading the target data from the stored data of the target file includes: reading from the data of the target file stored in the plurality of direct pointers according to the start offset address and the length of the target data the target data.

In a second aspect, the present application provides a file reading method applied to a processor, including: sending a file reading request to the storage controller through a file reading interface; wherein, the file reading request carries a target index node The logical address, the start offset address and the length of the target data, the target data is at least a part of the data in the target file, the target index node is the index node of the target file, and the start offset address is used In order to indicate the starting position of the target data in the target file, the target index node is used to indicate the data in the target file; receiving the returned by the storage controller in response to the file read request the target data.

In a third aspect, the present application provides a file reading device, which is applied to a storage controller, including: an obtaining module, configured to obtain a file reading request from a processor through a file reading interface; wherein, the file reading request carry the logical address of the target index node, the start offset address and the length of the target data, the target data is at least a part of data in the target file, the target index node is the index node of the target file, and the start The offset address is used to indicate the starting position of the target data in the target file, and the target index node is used to indicate the data in the target file; the reading module is configured to The logical address, the start offset address and the length of the target data are used to read the target data from the target file; the sending module is used to send the target data to the processor.

In a possible implementation manner, the target index node indicates an address list of the target file, where the address list of the target file includes a one-to-one correspondence between multiple offset addresses and multiple data block logical addresses ; The reading module is specifically configured to determine the target index node according to the logical address of the target index node; according to the length of the target data and the starting offset address, combined with the target index node indication The address list of the target file, determine the logical address of the data block corresponding to the target data; read the target data according to the logical address of the data block corresponding to the target data.

In a possible implementation manner, the reading module is specifically configured to, according to the length of the target data and the start offset address, based on the multiple direct pointers, the multiple first The pointer, the address list of the target file indicated by at least one of the multiple secondary indirect pointers or the at least one tertiary indirect pointer determines the logical address of the data block corresponding to the target data.

In a possible implementation manner, the target index node stores the data of the target file; the reading module is specifically configured to determine the target index node according to the logical address of the target index node; according to the Read the target data from the data of the target file stored in the target index node according to the start offset address and the length of the target data.

In a possible implementation manner, the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer; the priority of the pointers is from high to The lower order is: the plurality of direct pointers, the plurality of first-level indirect pointers, the plurality of second-level indirect pointers, and the at least one third-level indirect pointer; when the size of the target file is less than or equal to In the case of the first preset value: the multiple direct pointers are used to store the data of the target file; the reading module is specifically configured to, according to the starting offset address and the length of the target data, The target data is read from the data of the target file stored in the plurality of direct pointers.

In a fourth aspect, the present application provides a file reading device, which is applied to a processor, including: a sending module, configured to send a file reading request to the storage controller through a file reading interface; wherein, the file reading The request carries the logical address of the target index node, the start offset address and the length of the target data, the target data is at least a part of data in the target file, the target index node is the index node of the target file, and the start The starting offset address is used to indicate the starting position of the target data in the target file, and the target index node is used to indicate the data in the target file; the receiving module is used to receive the storage controller response The target data returned by the file read request.

In a fifth aspect, the present application provides a computer-readable storage medium, including a computer program. When the computer program is executed on a storage controller or a processor, the storage controller executes any one of the above-mentioned steps in the first aspect. The method described above, or causing the processor to execute the method described in the second aspect.

In a sixth aspect, the present application provides a computer program, which is used to execute the method described in any one of the first aspect or the second aspect when the computer program is executed by a storage controller or a processor.

In a seventh aspect, the present application provides an electronic device, including: a processor and a storage controller, wherein; the storage controller is configured to execute the method described in any one of the first aspect; and the processor is configured to execute the second method described in the aspect.

Description of drawings

FIG. 1 shows a schematic diagram of writing a file A (FileA) into a storage medium in a sequential writing manner;

FIG. 2 shows a schematic diagram of updating data in File A (FileA) by sequential writing;

FIG. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present application;

FIG. 4 is a schematic flow diagram of a file reading method provided in an embodiment of the present application;

Fig. 5 is a schematic diagram of the file reading interface provided by the embodiment of the present application;

FIG. 6 is a schematic flow diagram of a storage controller reading target data provided by an embodiment of the present application;

FIG. 7 is a schematic structural diagram of a target index node provided by an embodiment of the present application;

FIG. 8 is a first schematic flow diagram of reading target data provided by the embodiment of the present application;

FIG. 9 is a second schematic flow diagram of reading target data provided by the embodiment of the present application;

FIG. 10 is the third schematic flow chart of reading target data provided by the embodiment of the present application;

FIG. 11 is the fourth schematic flow diagram of reading target data provided by the embodiment of the present application;

FIG. 12 is a first structural schematic diagram of a document reading device provided by an embodiment of the present application;

FIG. 13 is a second structural schematic diagram of the document reading device provided by the embodiment of the present application.

Detailed ways

The technical solution in this application will be described below with reference to the accompanying drawings.

In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings in this application. Obviously, the described embodiments are part of the embodiments of this application , but not all examples. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

The terms "first" and "second" in the description, embodiments, claims and drawings of the present application are only used for the purpose of distinguishing descriptions, and cannot be interpreted as indicating or implying relative importance, nor can they be interpreted as indicating or imply order. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a series of steps or elements are included. A method, system, product or device is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to the process, method, product or device. ,

It should be understood that in this application, "at least one (item)" means one or more, and "multiple" means two or more. "And/or" is used to describe the association relationship of associated objects, indicating that there can be three types of relationships, for example, "A and/or B" can mean: only A exists, only B exists, and A and B exist at the same time , where A and B can be singular or plural. The character "/" generally indicates that the contextual objects are an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one item (piece) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c ", where a, b, c can be single or multiple.

The log-structured file system is used to manage the file data stored in the storage medium. The storage medium includes, but is not limited to, a storage medium with sequential write characteristics such as a flash memory. The sequential write characteristic of the storage medium means that when performing a write operation on the storage medium, data is written in the order in which the physical addresses of the data blocks in the storage medium are from small to large.

It should be noted that the write operation includes but is not limited to writing file data into a storage medium, writing updated file data into a storage medium, and the like.

In a file management method based on a log-structured file system, file data is stored in multiple data blocks in a storage medium, and the number of multiple data blocks storing file data is determined by the size of the file data and the capacity of a single data block. A file's metadata is stored in a node. The metadata of a file includes, but is not limited to, the owner of the file, the read, write, and execute permissions of the file, and the time stamp of the file. A node storing metadata of a file is determined as an index node of the file.

The index node of the file not only stores the metadata of the file, but is also used to store the data of the file or store the address list of the file, etc. The address list of the file includes a one-to-one correspondence between multiple offset addresses and multiple data block logical addresses. The data stored in the multiple data blocks indicated by the multiple data block logical addresses is the data of the file, and the multiple offset addresses Each offset address in is used to indicate the position of the data stored in the data block indicated by the logical address of the corresponding data block in the file.

It should be noted that the index node of the file may also have at least one associated node. If the file's index node cannot completely accommodate the file's address list, the address list not accommodated in the file's index node is stored in at least one associated node of the file's index node.

The sequential writing feature of the log file structure system refers to writing data into unoccupied data blocks according to the order of physical addresses of the data blocks in the storage medium from small to large.

FIG. 1 shows a schematic diagram of writing a file A (FileA) into a storage medium in a sequential writing manner. Figure 1(a) is used to indicate the address list in the index node (inode) of file A (File A). The address list includes three offset addresses Offset1~Offset3 and three data block logical addresses LBA1~LBA3 of file A, wherein the three offset addresses Offset1~Offset3 correspond to the three data block logical addresses LBA1~LBA3 one by one, The corresponding relationship is shown in Figure 1(a). FIG. 1(b) is used to indicate the one-to-one mapping relationship between three offset addresses Offset1-Offset3 of file A and three logical addresses LBA1-LBA3 of data blocks. FIG. 1(c) is used to indicate the one-to-one mapping relationship between logical addresses LBA1-LBA5 of data blocks and physical addresses PPN1-PPN5 of data blocks.

It can be seen from Figure 1 that the data of file A is divided into three parts, and the three parts of data are stored in three data blocks in sequence according to the sequence of the positions of the three data parts in file A, and the physical data of the three data blocks The addresses (that is, the physical addresses of the data blocks) are PPN1-PPN3. From the mapping relationship indicated in Figure 1(c), it can be known that the logical addresses of the three data blocks storing the data of file A are LBA1-LBA3. According to the position of the data stored in each data block in the file A, three offset addresses Offset1-Offset3 of the file A are generated. The three offset addresses Offset1-Offset3 are in one-to-one correspondence with the three data blocks storing the data of the file A, wherein the offset addresses are used to indicate the position of the data stored in the corresponding data block in the file A. Establish a one-to-one mapping relationship between the three offset addresses Offset1～Offset3 of file A and the logical addresses LBA1～LBA3 of the three data blocks (as shown in Figure 1(b)), wherein the data block indicated by the logical address of the data block is stored in The position of the data in file A is indicated by the offset address corresponding to the logical address of the data block. According to the one-to-one mapping relationship between the three offset addresses Offset1~Offset3 of file A and the logical addresses LBA1~LBA3 of three data blocks, the address list of file A is constructed (as shown in Figure 1(a)), and the address list of file A Stored in the index node (inode) of file A.

Obviously, in FIG. 1, the logical addresses of the three data blocks storing the data of file A are continuous.

FIG. 2 shows a schematic diagram of updating data in File A (FileA) in a sequential writing manner. In Figure 2, the process of updating the data at the positions indicated by the offset addresses Offset1~Offset2 by sequential writing is as follows:

The data at the position indicated by the offset address Offset2 is updated, and the updated data is written into the data block whose physical address is PPN4. According to the mapping relationship indicated in FIG. 2( c ), it can be known that the logical address of the data block storing the updated data is LBA4. In FIG. 2( b ), the mapping relationship between the logical address LBA4 of the data block and the offset address Offset2 is established, and the established mapping relationship is updated into the address list of file A. As shown in FIG. 2(a), the logical address of the data block corresponding to the offset address Offset2 is changed from LBA2 to LBA4.

The data at the position indicated by the offset address Offset1 is updated, and the updated data is written into the data block whose physical address is PPN5. According to the mapping relationship indicated in FIG. 2( c ), it can be known that the logical address of the data block storing the updated data is LBA5. In FIG. 2( b ), the mapping relationship between the logical address of the data block LBA5 and the offset address Offset1 is established, and the established mapping relationship is updated to the address list of file A. As shown in FIG. 2(a), the logical address of the data block corresponding to the offset address Offset1 is changed from LBA1 to LBA5.

It can be seen from the above that due to the sequential writing method, when updating the data at the positions indicated by the offset addresses Offset1~Offset2, the updated data is not written into the original data block, but the updated The subsequent data are sequentially written into unoccupied data blocks.

Obviously, after updating the data at the positions indicated by the offset addresses Offset1-Offset2, the logical addresses of the data blocks corresponding to the offset addresses Offset1-Offset3 are LBA5, LBA4, and LBA3 in sequence. According to the order of offset addresses Offset1～Offset3 from small to large, the result of sorting the logical addresses of the corresponding data blocks is LBA5～LBA3. Although LBA5～LBA3 are continuous, LBA5～LBA3 are not in the order from small to large Therefore, the logical addresses LBA5-LBA3 of the data blocks corresponding to the offset addresses Offset1-Offset3 are discontinuous.

When reading the target data in the file, the offset addresses are read in ascending order. Therefore, if the logical addresses of multiple data blocks corresponding to multiple offset addresses of the file are continuous, that is, after sorting the logical addresses of the corresponding multiple data blocks according to the order of the offset addresses of the file from small to large, the sorted multiple The logical addresses of the data blocks are continuous and arranged in ascending order, so in the prior art, the process of reading the target data in the file is:

The processor sends the logical address of the inode of the file to the storage controller in the storage medium. The storage controller in the storage medium determines the physical address of the index node according to the logical address of the index node of the file, obtains the address list of the file according to the physical address of the index node, and feeds back the address list of the file to the processor. The processor determines the logical address of the data block corresponding to the starting offset address according to the address list of the file, and sends the logical address of the data block corresponding to the starting offset address and the length of the target data to the storage controller in the storage medium. The starting offset address is used to indicate the starting position of the target data in the file. The storage controller in the storage medium reads the data in the data block sequentially from the data block indicated by the data block logical address corresponding to the start offset address until the length of the read data block is equal to the length of the target data, The read data is determined as target data, and the target data is sent to the processor.

For example, on the basis of Figure 1, when reading data corresponding to offset addresses Offset1~Offset3 in file A, the processor only needs to determine the offset address Offset1 (that is, the starting offset address) corresponding to The data block logical address LBA1, and the data length corresponding to the data block logical address LBA1 and offset addresses Offset1-Offset3 are sent to the storage controller in the storage medium. The storage controller in the storage medium reads the data in the data block sequentially backward from the data block indicated by the data block logical address LBA1, that is, reads the data in the data block indicated by the data block logical address LBA1～LBA3, to Obtain the data corresponding to the offset addresses Offset1~Offset3.

If the logical addresses of multiple data blocks corresponding to the multiple offset addresses of the file are discontinuous, then in the prior art, the process of reading the target data in the file is:

The processor sends the logical address of the inode of the file to the storage controller in the storage medium. The storage controller in the storage medium determines the physical address of the index node according to the logical address of the index node of the file, obtains the address list of the file according to the physical address of the index node, and feeds back the address list of the file to the processor. According to the address list of the file and combined with the start offset address and the length of the target data, the processor determines the logical addresses of multiple discontinuous data blocks corresponding to the target data, and divides the logical addresses of multiple discontinuous data blocks corresponding to the target data into sent to the storage controller of the storage medium. The storage controller in the storage medium reads the target data according to the logical addresses of multiple discontinuous data blocks corresponding to the target data, and sends the target data to the processor, wherein the logical addresses of the multiple discontinuous data blocks corresponding to the target data Target data is stored in the indicated data block.

For example, on the basis of Figure 2, when reading the data corresponding to offset addresses Offset1~Offset3 in file A, the processor needs to determine the data block logical addresses LBA5, LBA4, and LBA3 corresponding to offset addresses Offset1~Offset3, and then, First send the logical address LBA5 of the data block to the storage controller in the storage medium, then send the logical address LBA4 of the data block to the storage controller in the storage medium, and finally send the logical address LBA3 of the data block to the storage controller in the storage medium storage controller. The storage controller in the storage medium reads the data in the data blocks indicated by the data block logical addresses LBA5 , LBA4 , and LBA3 to obtain the data corresponding to the offset addresses Offset1˜Offset3.

Obviously, in the prior art, if the logical addresses of multiple data blocks corresponding to the multiple offset addresses of the file are continuous, when reading the target data in the file, the processor only needs to send The logical address of the data block corresponding to the start offset address and the length of the target data are sufficient. However, if the logical addresses of multiple data blocks corresponding to multiple offset addresses of the file are discontinuous, when reading the target data in the file, the processor needs to send the logical addresses of multiple data blocks corresponding to the target data multiple times. To the storage controller in the storage medium, the number of interactions between the processor and the storage medium is increased, resulting in a decrease in file reading performance, and at the same time increasing the overhead of the processor.

In order to solve the above technical problems, the present application provides an electronic device, which uses a log-structured file system to manage file data. Log-structured file systems include but are not limited to F2FS, Btrfs, zoneFs, etc. Electronic devices include but are not limited to mobile phones, computers, e-readers, etc. As shown in FIG. 3 , the electronic device includes a processor 310 and a memory 320 . Wherein, the processor 310 is configured to read the target data in the target file from the memory 320 . The target data can be at least a part of the data in the target file, that is, the target data can be a part of the data in the target file, or all the data in the target file.

The processor 310 includes, but is not limited to, a central processing unit (CPU), a microcontroller (MCU), a digital signal processor (DSP), a neural processing unit (NPU), or a microprocessor.

The memory 320 may be, for example, a memory in the electronic device, or an external memory connected to the electronic device. The storage includes but is not limited to storage media with sequential write characteristics such as flash memory. The memory 320 includes a memory controller 321 .

The processor 310 is configured to send a file read request to the storage controller 321, and receive target data obtained by the storage controller 321 according to the file read request.

The storage controller 321 is configured to receive and respond to the file read request, read the target file to obtain target data, and send the target data to the processor 310 .

Obviously, when reading target data, the processor 310 only needs to send a file read request to the storage controller 321 once, which reduces the number of interactions between the storage controller 321 and the processor 310, that is, reduces the interaction between the storage controller 320 and the processing. The number of interactions between processors 310 improves file reading performance and reduces processor 310 overhead.

In the following, the file reading method provided by this application will be described in detail.

FIG. 4 is a schematic flowchart of a file reading method provided by an embodiment of the present application. As shown in Figure 4, the file reading method includes the following steps:

401. The processor 310 sends a file reading request to the storage controller 321 through the file reading interface 501.

The file read request carries the logical address of the target inode, the start offset address and the length of the target data. The target data is at least a part of data in the target file. The target index node is the index node of the target file, and the starting offset address is used to indicate the starting position of the target data in the target file. The file reading interface is shown as 501 in FIG. 5 .

The target inode is used to indicate the data in the target file. Specifically, the target index node may indicate the data in the target file by storing the data of the target file, and the target index node may also indicate the data of the target file by indicating the address list of the target file. Wherein, the address list of the target file includes a one-to-one correspondence between a plurality of offset addresses and a plurality of data block logical addresses, and the data stored in the plurality of data blocks indicated by the plurality of data block logical addresses is the data of the target file. Each of the offset addresses is used to indicate the location of the data stored in the data block indicated by the logical address of the corresponding data block in the target file.

402. The storage controller 321 receives a file reading request through the file reading interface 501.

403. The storage controller 321 reads the target data from the target file in response to the file read request. Specifically, the target data is read from the target file according to the logical address of the target index node carried in the file read request, the start offset address, and the length of the target data.

404. The storage controller 321 sends the target data to the processor 310.

405. The processor 310 receives the target data.

Since the file read request carries the logical address of the target index node, the start offset address, and the length of the target data, and the target index node is used to indicate the data in the target file, the target data is at least a part of the data in the target file, and the start The offset address is used to indicate the starting position of the target data in the target file. Therefore, after the storage controller 321 receives the file read request, it can determine the address of the target file indicated in the target index node according to the logical address of the target index node. data, and read the target data from the target file according to the data of the target file, the start offset address and the length of the target data. Based on this, when the processor 310 reads the target data from the target file, the processor 310 only needs to send the file read file carrying the logical address of the target inode, the start offset address and the length of the target data to the storage controller 321. The request means that the storage controller 321 returns the target data to the processor 310 based on the file read request. Obviously, when reading the target data from the target file, the processor 310 only needs to send a file read request to the storage controller 321. Compared with the prior art, it is not necessary to consider whether the logical addresses of multiple data blocks storing data are continuous. And when the logical addresses of a plurality of data blocks storing data are discontinuous, there is no need for the processor 310 to send the discontinuous data block logical addresses to the storage controller 321 multiple times, which reduces the number of interactions between the processor 310 and the storage controller 321 , which improves the performance of file reading.

The specific implementation steps of step 403 include but are not limited to the following two:

First, if the target index node indicates the data of the target file by indicating the address list of the target file, the implementation steps of step 403 are as shown in Figure 6:

601. The storage controller 321 determines the target index node according to the logical address of the target index node.

Specifically, the physical address of the target index node is determined according to the logical address of the target index node, and the target index node is determined according to the physical address of the target index node.

602. The storage controller 321 determines the logical address of the data block corresponding to the target data according to the length and the start offset address of the target data and in combination with the address list of the target file indicated by the target inode.

603. The storage controller 321 reads the target data according to the logical address of the data block corresponding to the target data.

Step 602 and step 603, for example, can be realized through the following steps:

First, the storage controller 321 uses the starting offset address as the offset address to be compared, matches the offset address to be compared with the offset address in the address list of the target file, and matches the offset address to be compared The logical address of the data block corresponding to the offset address is determined as the logical address of the data block corresponding to the offset address to be compared.

Then, the storage controller 321 determines the physical address of the data block corresponding to the offset address to be compared according to the logical address of the data block corresponding to the offset address to be compared, and reads the data block indicated by the physical address of the data block corresponding to the offset address to be compared. The data in the data block, the read data is sent to the processor 310 .

Finally, determine whether the length of the data sent to the processor 310 is equal to the length of the target data, if not, update the offset address to be compared, and repeat the above process according to the updated offset address to be compared until sent to The length of the data in the processor 310 is equal to the length of the target data, if so, stop reading the target file. Updating the offset address to be compared includes, but not limited to, adding one to the offset address to be compared.

It should be noted that, in the above method, the determined logical address of the data block corresponding to the offset address to be compared is the logical address of the data block corresponding to the target data, and the data sent to the processor 310 is the target data.

Next, step 602 will be described according to the structure of the log-structured file system and the target inode.

For example, a log-structured file system uses three types of nodes, index nodes, direct nodes, and indirect nodes. An index node (for example, a target index node) in a log-structured file system includes two main parts: a metadata (metadata) part and a data block addressing part. Wherein, the data block addressing part includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer. Wherein, the priority order of pointers from high to low is: multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer.

According to the order of priority from high to low, at least one of multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer is used to indicate the file (such as the target file) address list. That is, first indicate the address list of the file (such as the target file) through the pointer with the highest priority (such as multiple direct pointers), if the pointer with the highest priority cannot fully indicate the address list of the file, you can increase the priority by increasing Pointers to collectively indicate a list of addresses for object files.

Next, the meaning of the above-mentioned pointers will be described.

Direct pointer: the address array directly pointing to the data block in the index node.

First-level indirect pointer: the index node records multiple first-level indirect pointers, and multiple first-level indirect pointers indicate the addresses of multiple direct nodes, and each direct node directly points to multiple data block addresses.

Secondary indirect pointers, the index node records multiple secondary indirect pointers, multiple secondary indirect pointers indicate the addresses of multiple indirect nodes, each indirect node saves the nid (identification) of the direct node, and each direct node points to Multiple data block addresses.

The three-level indirect pointer, the index node records at least one three-level indirect pointer, each three-level indirect pointer indicates the address of an indirect node, each three-level indirect pointer records multiple two-level indirect pointers, that is, each three-level indirect pointer Multiple secondary indirect pointers are recorded in the indirect node indicated by the indirect pointer. Each secondary indirect pointer indicates the address of an indirect node, the indirect node indicated by each secondary indirect pointer stores the direct node nid, and each direct node points to multiple data block addresses.

Obviously, the direct node indicated by the first-level indirect pointer in the index node can be understood as the associated node of the target index node, and similarly, the indirect node indicated by the second-level indirect pointer and the third-level indirect pointer in the index node can also be understood as the association node of the target index node node.

Based on this, the specific implementation process of step 602 can be: according to the length of the target data and the start offset address, and based on multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, or at least one third-level indirect The address list of the target file indicated by at least one item of the pointer determines the logical address of the data block corresponding to the target data. Specifically, the implementation of step 602 will be described in detail according to the size of the target file and different locations indicated by the starting offset address. Since the first preset value to the fourth preset value will be involved in the description process, and the first preset value<the second preset value<the third preset value<the fourth preset value, therefore, first The first preset value to the fourth preset value are described.

According to the descending order of priority, at least one of multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer is used to indicate the address list of the target file. Or multiple direct pointers are used to store the data of the object file. Therefore, the first preset value to the fourth preset value can be set according to parameters such as the maximum value of data represented by the address list that can be indicated by each pointer, or the maximum value of data that can be stored by multiple direct pointers. In this way, according to the size of the target file and in combination with the indication principle of the data of the target file or the address list of the target file, it can be determined that the address list of the target file or the data of the target file are stored in those pointers. specific:

According to factors such as the maximum value of the data that can be stored by multiple direct pointers, the first preset value is determined. In this way, when the target file≤the first preset value, the data of the target file is stored in multiple direct pointers. Like this, When reading the target data in the target file, the target data is read from multiple direct pointers to improve the efficiency of data reading.

According to factors such as the maximum value of the data indicated by the largest address list that can be accommodated by multiple direct pointers, determine the second preset value. In this way, if the first preset value<the size of the target file≤the second preset value, then pass Multiple direct pointers point to a list of addresses of object files.

The third preset value is determined according to factors such as the maximum value of data indicated by the largest address list that can be indicated by the multiple direct pointers and the multiple first-level indirect pointers. In this way, if the second preset value<the size of the target file≤the third preset value, multiple direct pointers and multiple first-level indirect pointers can be used to indicate the address list of the target file.

The fourth preset value is determined according to factors such as a maximum value of data indicated by a maximum address list that can be indicated by multiple direct pointers, multiple first-level indirect pointers, and multiple second-level indirect pointers. In this way, if the third preset value<the size of the target file≤the fourth preset value, the address list of the target file is indicated by multiple direct pointers, multiple first-level indirect pointers, and multiple second-level indirect pointers. If the fourth preset value<the size of the target file, the address list of the target file is indicated by multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers and at least one third-level indirect pointer.

Based on this, the specific implementation process of step 602 can be determined according to the size of the target file and the starting offset address. The specific process is as follows:

If the first preset value<the size of the target file≤the second preset value, the implementation process of step 602 is as follows:

According to the length of the target data and the starting offset address, and based on the address list of the target file indicated by the multiple direct pointers, the logical address of the data block corresponding to the target data is determined.

In the case of the second preset value<the size of the target file≤the third preset value:

If the starting offset address≤the second preset value, the implementation process of step 602 is as follows:

According to the length of the target data and the starting offset address, and based on the address list of the target file indicated by the multiple direct pointers and the multiple first-level indirect pointers, the logical address of the data block corresponding to the target data is determined.

If the second preset value<start offset address≤the third preset value, then the implementation process of step 602 is as follows:

According to the length of the target data and the starting offset address, and based on the address list of the target file indicated by multiple first-level indirect pointers, the logical address of the data block corresponding to the target data is determined.

In the case of the second preset value<the third preset value<the size of the target file≤the fourth preset value:

According to the length and start offset address of the target data, and based on the address list of the target file indicated by multiple direct pointers, multiple first-level indirect pointers and multiple second-level indirect pointers, determine the logical address of the data block corresponding to the target data .

According to the length of the target data and the starting offset address, and based on the address list of the target file indicated by the multiple first-level indirect pointers and the multiple second-level indirect pointers, the logical address of the data block corresponding to the target data is determined.

If the third preset value<start offset address≤the fourth preset value, then the implementation process of step 602 is as follows: according to the length of the target data and the start offset address, and based on the multiple secondary indirect pointers indicated The address list of the target file determines the logical address of the data block corresponding to the target data.

In the case of the second preset value<the third preset value<the fourth preset value<the size of the target file:

Determine the target according to the length and start offset address of the target data, and based on the address list of the target file indicated by multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer The logical address of the data block corresponding to the data.

According to the length and starting offset address of the target data, and based on the address list of the target file indicated by multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer, determine the data block corresponding to the target data logical address.

If the third preset value<start offset address≤the fourth preset value, the implementation process of step 602 is as follows:

Determine the logical address of the data block corresponding to the target data according to the length of the target data and the starting offset address, and based on the address list of the target file indicated by a plurality of secondary indirect pointers and at least one third-level indirect pointer;

If the fourth preset value<start offset address, the implementation process of step 602 is as follows:

According to the length of the target data and the start offset address, and based on the address list of the target file indicated by at least one third-level indirect pointer, the logical address of the data block corresponding to the target data is determined.

It should be noted that, according to the length of the target data and the starting offset address, the principle of determining the logical address of the data block corresponding to the target data in the address list of the target file indicated by various pointers is the same as that described above. The principle of shifting the logical address of the data block corresponding to the address is similar and will not be repeated here.

Obviously, by setting the first preset value to the fourth preset value, it is possible to flexibly determine where to start matching the address list according to the size of the target file and the starting offset address, thereby improving the matching efficiency.

Second, if the target index node indicates the data of the target file by storing the data of the target file, the implementation steps of step 403 are as follows:

First, the target index node is determined according to the logical address of the target index node. The specific implementation process has been described above and will not be repeated here. Then, according to the start offset address and the length of the target data, the target data is read from the data of the target file stored in the target index node.

For example, if the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer. The priority order of pointers from high to low is: multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer. And when the size of the target file≤the first preset value, multiple direct pointers are used to store the data of the target file. Then, according to the start offset address and the length of the target data, the realization process of reading the target data from the data of the target file stored in the target index node is as follows:

According to the start offset address and the length of the target data, the target data is read from the data of the target file stored in the multiple direct pointers.

It should be noted that the structure of the target index node and the first preset value have been described above, and will not be repeated here.

In the following, taking the log-structured file system as F2FS and the target index node shown in FIG. 7 as an example, the process of the storage controller reading the target data according to the information carried in the file read request will be described.

The file read request carries the logical address of the target index node, the length of the target data, and the starting offset address.

F2FS uses three types of nodes, which are index nodes (such as target index nodes), direct nodes, and indirect nodes. As shown in FIG. 7 , an index node (such as a target index node) includes a metadata (metadata) part and a data block addressing part. Among them, the data block addressing part includes 929 direct pointers, two first-level indirect pointers, two second-level indirect pointers, and one third-level indirect pointer.

929 direct pointers store the physical addresses of 929 block data.

Two first-level indirect pointers indicate the addresses of two direct nodes, where 2*1018 blocks of data can be saved.

The two secondary indirect pointers indicate the addresses of the two indirect nodes, and the two indirect nodes store the nid of the direct node, where 2*1018*1018 blocks of data are stored.

A third-level indirect pointer indicates the address of an indirect node, the indirect node indicated by the third-level indirect pointer stores the address of the indirect node indicated by the second-level indirect pointer, and the indirect node indicated by the second-level indirect pointer stores the nid of the direct node , 1018*1018*1018 pages of data can be saved here.

On this basis, the following calculation formula can be obtained:

4KB*(923+2*1018+2*1018 x 1018+1*1018*1018*1018)＝3.93TB

From the above formula, it can be seen that a single F2FS file can save up to 3.93TB of data.

It can be seen from the above that the first default value is 3716B, the second default value is 3716KB, and the third default value is 11860KB. The fourth preset value is 8302452KB.

If the size of target file≤3716B (being first default value), then the data of target file is stored in 929 direct pointers, as shown in Figure 7, now 929 direct pointers can be called inline data.

If 3716B<the size of the target file≤3716KB, then indicate the address list of the target file through 929 direct pointers.

If 3176KB<the size of the target file≤11860KB, then indicate the address list of the target file through 929 direct pointers and two first-level indirect pointers.

If 11860KB<the size of the target file≤8302452KB, then indicate the address list of the target file through 929 direct pointers, two first-level indirect pointers and two second-level indirect pointers.

If the size of the target file is >8302452KB, the address list of the target file is indicated by 929 direct pointers, two first-level indirect pointers, two second-level indirect pointers and one third-level indirect pointer.

On this basis, the process of reading target data will be described below based on target files of different sizes and start offset addresses indicating different locations.

If the size of the target file is less than or equal to 3716B (i.e. the first preset value), the process of the storage controller reading the target data can be as follows:

First, the storage controller determines the target inode according to the logical address of the target inode. Then, the storage controller obtains the target data from the inline data in the target index node according to the start offset address and the length of the target data, and sends the target data to the processor.

If 3716B<target file size≤3716KB, as shown in Figure 8, the process of the storage controller reading target data can be as follows:

801. The storage controller determines the target index node according to the logical address of the target index node.

802. The storage controller uses the starting offset address as the offset address to be compared.

803. The storage controller matches the offset address to be compared with the offset address in the address list of the target file indicated by the 929 direct pointers in the target index node, so as to determine the data block logic corresponding to the offset address to be compared address.

804. The storage controller determines the physical address of the data block corresponding to the offset address to be compared according to the logical address of the data block corresponding to the offset address to be compared.

805. The storage controller reads data from the data block indicated by the physical address of the data block corresponding to the offset address to be compared, and sends the read data to the processor.

806. The storage controller judges whether the length of the data sent to the processor is equal to the length of the target data, if yes, execute 807, and if not, execute 808.

807. The storage controller stops reading the target data.

808. The storage controller updates the offset address to be compared, and repeats steps 803-806 based on the updated offset address to be compared.

It should be noted that the update of the offset address to be compared may be adding one to the current offset address to be compared. The data sent to the processor is object data. The determined logical address of the data block corresponding to the offset address to be compared is the logical address of the data block corresponding to the target data.

In the case of 3176KB<target file size≤11860KB:

If the starting offset address is less than or equal to 3176KB, then the process of the storage controller reading the target data is similar to the principle shown in Figure 8, that is, the starting offset address is determined as the offset address to be compared, and the 929 direct pointers indicate the Start matching in the address list of the object file. The difference is that if no offset address matching the updated offset address to be compared is found in the address list of the target files indicated by the 929 direct pointers, then the target files indicated by the two first-level indirect pointers in the address list of .

If 3176KB<start offset address≤11860KB, as shown in Figure 9, the process of the storage controller reading the target data can be as follows:

901. The storage controller determines the target index node according to the logical address of the target index node.

902. The storage controller uses the starting offset address as the offset address to be compared.

903. The storage controller determines the direct node according to the two first-level indirect pointers in the target index node.

904. The storage controller matches the offset address to be compared with the offset address in the address list of the target file stored in the direct node, so as to determine the logical address of the data block corresponding to the offset address to be compared.

905. The storage controller determines the physical address of the data block corresponding to the offset address to be compared according to the logical address of the data block corresponding to the offset address to be compared.

906. The storage controller reads data from the data block indicated by the physical address of the data block corresponding to the offset address to be compared, and sends the read data to the processor.

907. The storage controller judges whether the length of the data sent to the processor is equal to the length of the target data, if yes, go to 908, if not, go to 909.

908. The storage controller stops reading the target data.

909. The storage controller updates the offset address to be compared, and repeats steps 904-907 based on the updated offset address to be compared.

In the case of 11860KB<target file size≤8302452KB,

If the starting offset address is less than or equal to 3176KB, then the process of the storage controller reading the target data is similar to the principle shown in Figure 8, that is, the starting offset address is determined as the offset address to be compared, and the 929 direct pointers indicate the The logical address of the data block starting to match the offset address to be compared in the address list of the target file. The difference is that if no offset address matching the updated offset address to be compared is found in the address list of the target files indicated by the 929 direct pointers, then the target files indicated by the two first-level indirect pointers in the address list of . If no offset address matching the updated offset address to be compared is found in the address lists of the target files indicated by the two first-level indirect pointers, then in the address lists of the target files indicated by the two second-level indirect pointers in the search.

If 3176KB<start offset address≤11860KB, the process of the storage controller reading the target data is similar to the principle shown in Figure 9, that is, the start offset address is determined as the offset address to be compared, and the two levels The logical address of the data block starting to match the offset address to be compared in the address list of the target file indicated by the indirect pointer. The difference is that if no offset address matching the updated offset address to be compared is found in the address list of the target file indicated by the two first-level indirect pointers, then the two second-level indirect pointers indicate Lookup in the address list of the object file.

If 11860KB<start offset address≤8302452KB, as shown in Figure 10, the process of the storage controller reading the target data can be as follows:

1001. The storage controller determines the target index node according to the logical address of the target index node.

1002. The storage controller uses the starting offset address as the offset address to be compared.

1003. The storage controller determines the indirect node according to the two secondary indirect pointers in the target index node, and determines the nid of the direct node from the indirect nodes.

1004. The storage controller matches the offset address to be compared with the offset address in the address list of the target file stored in the direct node (determined according to the nid of the direct node), so as to determine the data corresponding to the offset address to be compared block logical address.

1005. The storage controller determines the physical address of the data block corresponding to the offset address to be compared according to the logical address of the data block corresponding to the offset address to be compared.

1006. The storage controller reads data from the data block indicated by the physical address of the data block corresponding to the offset address to be compared, and sends the read data to the processor.

1007. The storage controller judges whether the length of the data sent to the processor is equal to the length of the target data, if yes, execute 1008, if not, execute 1009.

1008. The storage controller stops reading the target data.

1009. The storage controller updates the offset address to be compared, and repeats steps 1004-1007 based on the updated offset address to be compared.

In the case where the size of the target file is >8302452KB:

If the starting offset address is less than or equal to 3176KB, then the process of the storage controller reading the target data is similar to the principle shown in Figure 8, that is, the starting offset address is determined as the offset address to be compared, and the 929 direct pointers indicate the The logical address of the data block starting to match the offset address to be compared in the address list of the target file. The difference is that if no offset address matching the updated offset address to be compared is found in the address list of the target files indicated by the 929 direct pointers, then the target files indicated by the two first-level indirect pointers in the address list of . If no offset address matching the updated offset address to be compared is found in the address lists of the target files indicated by the two first-level indirect pointers, then in the address lists of the target files indicated by the two second-level indirect pointers in the search. If no offset address matching the updated offset address to be compared is found in the address list of the target file indicated by the two second-level indirect pointers, then in the address list of the target file indicated by a third-level indirect pointer find.

If 3176KB<starting offset address≤11860KB, the process of the storage controller reading the target data is similar to the principle shown in Figure 9, that is, the starting offset address is determined as the offset address to be compared, and the two first-level The logical address of the data block starting to match the offset address to be compared in the address list of the target file indicated by the indirect pointer. The difference is that if no offset address matching the updated offset address to be compared is found in the address list of the target file indicated by the two first-level indirect pointers, then the two second-level indirect pointers indicate Lookup in the address list of the object file. If no offset address matching the updated offset address to be compared is found in the address list of the target file indicated by the two second-level indirect pointers, then in the address list of the target file indicated by a third-level indirect pointer find.

If 11860KB<start offset address≤8302452KB, the process of the storage controller reading the target data is similar to the principle shown in Figure 10, that is, the start offset address is determined as the offset address to be compared, and the two secondary The logical address of the data block starting to match the offset address to be compared in the address list of the target file indicated by the indirect pointer. If no offset address matching the updated offset address to be compared is found in the address list of the target file indicated by the two second-level indirect pointers, then in the address list of the target file indicated by a third-level indirect pointer find.

If 8302452KB<start offset address. Then, as shown in FIG. 11, the process of the storage controller reading the target data may be as follows:

1101. The storage controller determines the target index node according to the logical address of the target index node.

1102. The storage controller uses the starting offset address as the offset address to be compared.

1103. The storage controller determines the indirect node according to the three-level indirect pointer in the target index node, determines the address of the indirect node stored in the indirect node from the determined indirect node, and obtains the nid of the direct node according to the address of the indirect node.

1104. The storage controller matches the offset address to be compared with the offset address in the address list of the target file stored in the direct node (determined according to the direct node nid), so as to determine the data block corresponding to the offset address to be compared logical address.

1105. The storage controller determines the physical address of the data block corresponding to the offset address to be compared according to the logical address of the data block corresponding to the offset address to be compared.

1106. The storage controller reads data from the data block indicated by the physical address of the data block corresponding to the offset address to be compared, and sends the read data to the processor.

1107. The storage controller judges whether the length of the data sent to the processor is equal to the length of the target data, if yes, execute 1108, if not, execute 1109.

1108. The storage controller stops reading the target data.

1109. The storage controller updates the offset address to be compared, and repeats steps 1104-1107 based on the updated offset address to be compared.

It should be noted that the address list of the target file indicated by the indirect pointer refers to the address list of the target file stored in the direct node finally pointed by the indirect pointer. Indirect nodes include but are not limited to first-level indirect pointers, second-level indirect pointers, and third-level indirect pointers.

As can be seen from the above, in the above embodiment, according to the size of the target file and the starting position indicated by the starting offset address, the address of the target file indicated by which pointer can be flexibly determined among the direct pointer and the indirect pointer Start matching in the list, which improves the efficiency of matching.

The present application also provides a file reading device, which is applied to a storage controller. As shown in FIG. 12, the device 1200 may include: an obtaining module 1201, a reading module 1202, and a sending module 1203, wherein:

Obtaining module 1201, configured to obtain a file read request from a processor through a file read interface; wherein, the file read request carries a logical address of a target index node, a starting offset address, and a length of target data, and the The target data is at least a part of data in the target file, the target index node is the index node of the target file, and the starting offset address is used to indicate the starting position of the target data in the target file, The target index node is used to indicate the data in the target file; the reading module 1202 is used to read the data from the target file according to the logical address of the target index node, the starting offset address and the length of the target data. Read the target data; a sending module 1203, configured to send the target data to the processor.

In a possible implementation manner, the target index node indicates an address list of the target file, where the address list of the target file includes a one-to-one correspondence between multiple offset addresses and multiple data block logical addresses ; The reading module 1202 is specifically configured to determine the target index node according to the logical address of the target index node; according to the length of the target data and the start offset address, combined with the target index node The indicated address list of the target file determines the logical address of the data block corresponding to the target data; and reads the target data according to the logical address of the data block corresponding to the target data.

In a possible implementation manner, the reading module 1202 is specifically configured to, according to the length of the target data and the start offset address, and based on the multiple direct pointers, the multiple primary The indirect pointer, the address list of the target file indicated by at least one of the plurality of second-level indirect pointers or the at least one third-level indirect pointer determines the logical address of the data block corresponding to the target data.

In a possible implementation manner, the target index node stores the data of the target file; the reading module 1202 is specifically configured to determine the target index node according to the logical address of the target index node; For the start offset address and the length of the target data, the target data is read from data of the target file stored in the target index node.

In a possible implementation manner, the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer; the priority of the pointers is from high to The lower order is: the plurality of direct pointers, the plurality of first-level indirect pointers, the plurality of second-level indirect pointers, and the at least one third-level indirect pointer; when the size of the target file is less than or equal to In the case of the first preset value: the plurality of direct pointers are used to store the data of the target file; the reading module 1202 is specifically configured to use the starting offset address and the length of the target data , reading the target data from the data of the target file stored in the plurality of direct pointers.

The present application further provides a file reading device, which is applied to a processor. As shown in FIG. 13 , the device 1300 may include: a sending module 1301 and a receiving module 1302, wherein:

The sending module 1301 is configured to send a file read request to the storage controller through a file read interface; wherein, the file read request carries the logical address of the target index node, the starting offset address and the length of the target data, The target data is at least a part of data in the target file, the target index node is the index node of the target file, and the start offset address is used to indicate the start of the target data in the target file The location, the target index node is used to indicate the data in the target file; the receiving module 1302 is used to receive the target data returned by the storage controller in response to the file read request.

The implementation principles and technical effects of the document reading device of the present application have been described above, and will not be repeated here.

The present application also provides a computer-readable storage medium. A computer program is stored in the computer storage medium. When the computer program is executed on the storage controller, the storage controller executes any one of the above-mentioned storage controllers. The technical solution of the method embodiment.

The present application also provides a computer-readable storage medium, and a computer program is stored in the computer storage medium, and when the computer program is executed on a processor, the processor is made to perform any one of the method embodiments performed by the above-mentioned processor. technical solutions.

The present application also provides a computer program product, which, when the computer program is executed by the storage controller, causes the storage controller to execute the technical solution of any one of the method embodiments performed by the storage controller above.

The present application also provides a computer program product, which, when the computer program is executed by a processor, causes the processor to execute the technical solution of any one of the method embodiments executed by the processor above.

The present application also provides a chip, including a processor and a storage controller, where the processor is configured to execute the steps executed by the above-mentioned processor, and the storage controller is configured to execute the steps executed by the above-mentioned storage controller.

Further, the chip may further include a communication interface. The communication interface may be an input/output interface, a pin, or an input/output circuit.

In the implementation process, each step of the above-mentioned method embodiment can be completed by an integrated logic circuit of hardware in the network card or an instruction in the form of software. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other possible Program logic devices, discrete gate or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the methods disclosed in the embodiments of the present application may be directly implemented by a hardware coded processor, or executed by a combination of hardware and software modules in the coded processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (personal computer, server, or network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only a specific embodiment of the application, but the scope of protection of the application is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Claims

A file reading method applied to a storage controller, characterized in that it comprises:

Obtain a file read request from the processor through the file read interface;

Wherein, the file read request carries the logical address of the target index node, the start offset address and the length of the target data, the target data is at least a part of data in the target file, and the target index node is the index node, the start offset address is used to indicate the start position of the target data in the target file, and the target index node is used to indicate the data in the target file;

Reading the target data from the target file according to the logical address of the target index node, the start offset address and the length of the target data;

The target data is sent to the processor.
The method according to claim 1, wherein the target index node indicates an address list of the target file, wherein the address list of the target file includes a plurality of offset addresses and a plurality of data block logical addresses one-to-one correspondence;

According to the logical address of the target index node, the start offset address and the length of the target data, reading the target data from the target file includes:

determining the target index node according to the logical address of the target index node;

determining the logical address of the data block corresponding to the target data according to the length of the target data and the start offset address, and in combination with the address list of the target file indicated by the target inode;

The target data is read according to the logical address of the data block corresponding to the target data.
The method according to claim 2, wherein the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer;

The priority order of the pointers from high to low is: the multiple direct pointers, the multiple first-level indirect pointers, the multiple second-level indirect pointers, and the at least one third-level indirect pointer;

According to the order of priority from high to low, at least one of the multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer is used to indicate the target file address list.
The method according to claim 3, characterized in that, according to the length of the target data and the start offset address, and in combination with the address list of the target file indicated by the target index node, determine the The logical address of the data block corresponding to the target data includes:

According to the length of the target data and the start offset address, and based on the plurality of direct pointers, the plurality of first-level indirect pointers, the plurality of second-level indirect pointers, or the at least one third-level indirect The address list of the target file indicated by at least one of the pointers determines the logical address of the data block corresponding to the target data.
The method according to claim 1, wherein the data of the target file is stored in the target index node;

According to the logical address of the target index node, the start offset address and the length of the target data, reading the target data from the target file includes:

determining the target index node according to the logical address of the target index node;

Reading the target data from data of the target file stored in the target index node according to the start offset address and the length of the target data.
The method according to claim 5, wherein the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer;

The priority order of the pointers from high to low is: the multiple direct pointers, the multiple first-level indirect pointers, the multiple second-level indirect pointers, and the at least one third-level indirect pointer;

In the case where the size of the target file is less than or equal to the first preset value:

The multiple direct pointers are used to store data of the target file;

The reading the target data from the data of the target file stored in the target index node according to the start offset address and the length of the target data includes:

Reading the target data from the data of the target file stored in the plurality of direct pointers according to the start offset address and the length of the target data.
A file reading method, applied to a processor, is characterized in that, comprising:

Sending a file reading request to the storage controller through the file reading interface;

Wherein, the file read request carries the logical address of the target index node, the start offset address and the length of the target data, the target data is at least a part of data in the target file, and the target index node is the index node, the start offset address is used to indicate the start position of the target data in the target file, and the target index node is used to indicate the data in the target file;

receiving the target data returned by the storage controller in response to the file read request.
A file reading device applied to a storage controller, characterized in that it comprises:

Obtaining a module for obtaining a file reading request from a processor through a file reading interface;

Wherein, the file read request carries the logical address of the target index node, the start offset address and the length of the target data, the target data is at least a part of data in the target file, and the target index node is the index node, the start offset address is used to indicate the start position of the target data in the target file, and the target index node is used to indicate the data in the target file;

A reading module, configured to read the target data from the target file according to the logical address of the target index node, the start offset address and the length of the target data;

A sending module, configured to send the target data to the processor.
The device according to claim 8, wherein the target index node indicates an address list of the target file, wherein the address list of the target file includes a plurality of offset addresses and a plurality of data block logical addresses one-to-one correspondence;

The reading module is specifically configured to determine the target index node according to the logical address of the target index node; according to the length of the target data and the start offset address, combined with the target index node indicated The address list of the target file determines the logical address of the data block corresponding to the target data; reads the target data according to the logical address of the data block corresponding to the target data.
The device according to claim 9, wherein the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer;

The priority order of the pointers from high to low is: the multiple direct pointers, the multiple first-level indirect pointers, the multiple second-level indirect pointers, and the at least one third-level indirect pointer;

According to the order of priority from high to low, at least one of the multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer is used to indicate the target file address list.
The device according to claim 10, wherein the reading module is specifically configured to, according to the length of the target data and the start offset address, and based on the multiple direct pointers, the multiple The address list of the target file indicated by at least one of the first-level indirect pointers, the plurality of second-level indirect pointers, or the at least one third-level indirect pointer determines the logical address of the data block corresponding to the target data.
The device according to claim 8, wherein the data of the target file is stored in the target index node;

The reading module is specifically configured to determine the target index node according to the logical address of the target index node; according to the start offset address and the length of the target data, the The target data is read from data in the target file.
The device according to claim 12, wherein the target index node includes multiple direct pointers, multiple first-level indirect pointers, multiple second-level indirect pointers, and at least one third-level indirect pointer;

The priority order of the pointers from high to low is: the multiple direct pointers, the multiple first-level indirect pointers, the multiple second-level indirect pointers, and the at least one third-level indirect pointer;

In the case where the size of the target file is less than or equal to the first preset value:

The multiple direct pointers are used to store data of the target file;

The reading module is specifically configured to read the target data from the data of the target file stored in the multiple direct pointers according to the start offset address and the length of the target data.
A file reading device applied to a processor, characterized in that it comprises:

A sending module, configured to send a file reading request to the storage controller through the file reading interface;

Wherein, the file read request carries the logical address of the target index node, the start offset address and the length of the target data, the target data is at least a part of data in the target file, and the target index node is the index node, the start offset address is used to indicate the start position of the target data in the target file, and the target index node is used to indicate the data in the target file;

A receiving module, configured to receive the target data returned by the storage controller in response to the file read request.
A computer-readable storage medium comprising a computer program that, when executed on a storage controller or a processor, causes the storage controller to perform the method of any one of claims 1-6, or causing the processor to perform the method of claim 7.
A computer program, used to execute the method according to any one of claims 1-6 or 7 when said computer program is executed by a storage controller or a processor.
An electronic device comprising: a processor and a memory controller, wherein;

The storage controller is configured to execute the method according to any one of claims 1-6;

The processor is configured to perform the method of claim 7.