Data replication method and device based on solid state disk and computer equipment

Abstract

The invention relates to the technical field of data processing, and provides a data replication method and device based on a solid state disk and computer equipment, the method is applied to a target controller of a target solid state disk, the target controller comprises a data receiving path, a data sending path and a replication accelerator, and the method comprises the steps that a replication command of host equipment is received, analyzing the copy command; reading original data from a first position of the target storage device according to an analysis result of the copy command; processing the original data by using the data receiving path to generate first data; circulating the first data to the transmission data transmission path by using the replication accelerator; processing the first data by using the data sending path to generate second data; and writing the second data into a second position of the target storage device. According to the technical scheme provided by one or more embodiments, the data replication efficiency of the solid state disk can be optimized, and the performance of the solid state disk can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, in particular to a data replication method and device based on a solid state disk and a computer device. BACKGROUND

[0002] NVMe (Non-Volatile Memory Express) is an interface protocol for high-performance storage devices. In a traditional NVMe data replication operation, source data needs to be read from a storage device to the memory of a host device, and then written back to the target location of the storage device. This method has high data latency and additional host resource overhead, and is easily limited by the bandwidth of the host system bus.

[0003] In addition, a solid state disk (SSD) based on NVMe can receive a replication command from a host device, read source data from one or more storage areas of the solid state disk, and then write the data to other storage areas of the solid state disk. At this time, the old data in the original storage area may no longer be needed and can be erased, thereby releasing the storage space of the solid state disk.

[0004] Therefore, in the use of a solid state disk, data replication operation is a common and important operation. Optimizing the data replication efficiency of a solid state disk has engineering value and economic value. SUMMARY

[0005] Therefore, in the use of a solid state disk, data replication operation is a common and important operation. Optimizing the data replication efficiency of a solid state disk has engineering value and economic value.

[0006] In one aspect, the present disclosure provides a data replication method based on a solid state disk. The target solid state disk includes a target controller and a target storage device. The method is applied to the target controller, and the target controller includes a data receiving path, a data sending path, and a replication accelerator. The method includes receiving a replication command of a host device and parsing the replication command, reading original data from a first location of the target storage device according to the parsing result of the replication command, processing the original data using the data receiving path to generate first data, circulating the first data to the data sending path using the replication accelerator, processing the first data using the data sending path to generate second data, and writing the second data to a second location of the target storage device.

[0007] Another aspect of the present disclosure also provides a data replication device based on a solid state disk, a target solid state disk comprising a target controller and a target storage device, the device being applied to the target controller, the target controller comprising a data receiving path, a data sending path and a replication accelerator, the device comprising: a command receiving unit configured to receive a replication command of a host device and analyze the replication command; a data reading unit configured to read original data from a first location of the target storage device according to an analysis result of the replication command; a data receiving unit configured to process the original data by using the data receiving path to generate first data; a data replication unit configured to circulate the first data to the data sending path by using the replication accelerator; a data sending unit configured to process the first data by using the data sending path to generate second data; and a data writing unit configured to write the second data to a second location of the target storage device.

[0008] Another aspect of the present disclosure also provides a computer device comprising a memory and a processor, the memory being configured to store a computer program, the computer program being configured to implement the data replication method based on a solid state disk when executed by the processor.

[0009] Another aspect of the present disclosure also provides a computer readable storage medium configured to store a computer program, the computer program being configured to implement the data replication method based on a solid state disk when executed by a processor.

[0010] The technical solution provided by one or more embodiments of the present disclosure can bypass the intervention of a host device when executing a replication command, can directly read data from a source address of a target storage device and write the data to a target address of the target storage device, and is suitable for large-scale data migration scenarios. Inside a controller of a solid state disk, the data receiving path, the data sending path and the replication accelerator are used in cooperation to efficiently complete data replication work, which not only greatly reduces the data transmission delay of the solid state disk, but also saves host resource overhead. BRIEF DESCRIPTION OF DRAWINGS

[0011] The features and advantages of the embodiments of the present disclosure will be more clearly understood through reference to the following drawings, which are schematic and should not be construed as any limitation to the present disclosure, in which:

[0012] Figure 1 a step schematic diagram of a data replication method based on a solid state disk in an embodiment of the present disclosure is shown;

[0013] Figure 2 a system structure schematic diagram of a data replication system based on a solid state disk in an embodiment of the present disclosure is shown;

[0014] Figure 3 An operation schematic diagram of a data storage device executing a copy command in an embodiment of the present disclosure is shown;

[0015] Figure 4 An internal structure and data processing path schematic diagram of a data storage device in an embodiment of the present disclosure is shown;

[0016] Figure 5 A flow schematic diagram of a solid state disk based data copy method in an embodiment of the present disclosure is shown;

[0017] Figure 6 A functional module schematic diagram of a solid state disk based data copy device in an embodiment of the present disclosure is shown;

[0018] Figure 7 A structure schematic diagram of a computer device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0020] The solid state disk based data copy method provided by an embodiment of the present disclosure can be applied to a target controller of a target solid state disk. The target solid state disk can include the target controller and a target storage device. The target controller can include a data receiving path, a data sending path and a copy accelerator.

[0021] Referring to Figure 1 The solid state disk based data copy method provided by an embodiment of the present disclosure can include the following steps.

[0022] S1: receiving a copy command of a host device and parsing the copy command.

[0023] In the embodiment, when the target controller receives the copy command of the host device, the command is parsed to determine the data to be copied and the storage address after the data is copied. The copy command can include address information of the data to be copied and storage address information of the data after the copy. The target controller can check the correctness and integrity of the copy command. Only when the copy command passes the check, the target controller starts to read the original data from one or more initial positions in the target storage device and performs subsequent copy operations.

[0024] S2: read the original data from the first location of the target storage device according to the analysis result of the copy command.

[0025] In this embodiment, the target storage device of the target solid state drive is a NAND (Nand-flash) flash memory, which is a type of non-volatile memory. The target storage device can be divided into multiple dies, each of which can contain multiple physical blocks. These physical blocks can be further divided into multiple pages, each of which can contain multiple storage units. Multiple storage units can be electrically connected through a word line, thereby defining a page in multiple pages. The target storage device can write and read data at the page level and can erase data at the block level.

[0026] In this embodiment, the first location can be one or more source logical block (LBA) addresses of the NAND flash memory, which can be non-contiguous.

[0027] S3: process the original data using the data receiving path to generate first data.

[0028] In this embodiment, the original data can be subjected to some data processing work through the data receiving path, including but not limited to decoding, decryption, and verification of protection information.

[0029] In some embodiments, the original data can be decoded using a decoding module of the data receiving path to generate first decoded data.

[0030] In some embodiments, the original data can be decrypted using a decryption module of the data receiving path to generate first decrypted data.

[0031] In some embodiments, the original protection information of the original data can be verified using a direct memory access and data protection module of the data receiving path; if the original protection information passes the verification, the first data is generated.

[0032] S4: use the copy accelerator to loop the first data to the data sending path.

[0033] In this embodiment, the original data or the first data will not be returned to the host device for use, but the copy accelerator will loop the data from the data receiving path to the data sending path. By using the copy accelerator, the delay of executing the copy command operation and other data management operations can be reduced.

[0034] In one practical application example, the target controller can read the original data indicated by the copy command from the target storage device. The target controller can perform a plurality of operations on the data receiving path on the original data, including verifying the data protection information read from one or more first locations of the target storage device. Then, the copy accelerator part of the target controller transmits the processed first data from the data receiving path to the data sending path in a loopback mode. In the loopback mode, the data is not provided to the host device. In the data sending path, the first data can be processed again, including generating new protection information. Then, the target controller can process the second data and write it to the target location of the target storage device, which is indicated by the initial copy command.

[0035] S5: processing the first data using the data sending path to generate second data.

[0036] In the present embodiment, the first data can be subjected to some data processing work through the data sending path, including but not limited to encoding, encryption and adding protection information.

[0037] In some embodiments, the first data can be subjected to encoding processing using the encoding module of the data sending path to generate second encoded data.

[0038] In some embodiments, the first data can be subjected to encryption processing using the encryption module of the data sending path to generate second encrypted data.

[0039] In some embodiments, the first data can be subjected to adding target protection information using the direct memory access and data protection module of the data sending path to generate the second data.

[0040] In some embodiments, the target solid state disk further comprises a volatile memory. Before processing the original data using the data receiving path, the original data can be cached to the receiving buffer area of the volatile memory. Before processing the first data using the data sending path, the first data can be cached to the sending buffer area of the volatile memory.

[0041] Specifically, the NAND flash is a non-volatile memory, which can receive data and instruction messages from the target controller. When the host issues a hard disk operation command such as reading, writing, copying, etc. to the target controller, the target controller can temporarily store the data related to the hard disk operation command in the buffer area based on the non-volatile memory until the buffer data is completely written or read out from the NAND flash. The volatile memory can include but is not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), etc.

[0042] S6: Write the second data to the second location of the target storage device.

[0043] In this embodiment, the second location can be a contiguous address range. Thus, when the host device sends a copy command to the target solid-state drive, the target controller can copy the original data from one or more source logical block (LBA) address ranges of the NAND flash memory to a contiguous target address range. This improves the parallel processing capability for multi-source, non-contiguous data, fully utilizes the parallel characteristics of NAND flash memory, and enhances the performance of the target solid-state drive.

[0044] In this embodiment, after the raw data read from the NAND flash memory has completed data processing such as decoding, decryption, and verification on the data receiving path, it can be directly looped back to the data sending path through the copy accelerator without returning the raw data to the host or occupying an additional buffer. By bypassing host interaction and reducing intermediate data transmission steps, the completion time of the copy command is significantly shortened.

[0045] In some embodiments, the target solid-state drive further includes a target dynamic random access memory (DRAM), which contains a logical-to-physical table for managing address information of the target storage device.

[0046] Please see Figure 2 In a practical application example, after the host device sends a copy command to the target solid-state drive, the target controller can copy the raw data from one or more source logical block (LBA) address ranges of the NAND flash to a contiguous target address range. Figure 2 The copy command in the command consists of two source address logical block ranges, srcA and srcB, and a destination logical address, DstC. The logical addresses of srcA and srcB can be non-contiguous. When the target controller executes the copy command, it reads the data from the corresponding positions in srcA and srcB through the logical-to-physical table, and writes it starting from the beginning of DstC. srcA can be written to the DstA range of DstC, and srcB can be written to the DstB range of DstC, with the writing order consistent with the order of the source address logical blocks in the copy command.

[0047] Please see Figure 3One embodiment of the disclosure provides a data replication system based on a solid state drive. The system includes a data storage device, such as a SSD. A host communicates with the data storage device through an interface and can store and read data. The host device includes a host dynamic random access memory (DRAM). The data storage device includes components such as a SSD interface unit, a controller, a NAND flash memory, a volatile memory, an optional DRAM, etc. The host DRAM can optionally include a host memory buffer (HMB) allocated to the data storage device for use by the controller. If the data storage device does not include a DRAM, the controller can use the HMB as a DRAM for the data storage device and store mapping data, logical-to-physical tables, metadata, etc. in the HMB.

[0048] The NAND flash memory is a non-volatile memory that receives data and instruction messages from the controller. When the host issues a write command, the controller initiates a data storage command and temporarily stores data associated with the write command in a write buffer before sending the data to the NAND flash memory. The volatile memory can be used by the controller as a cache to store information until the information is written to the NAND flash memory. The volatile memory includes, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), etc. The controller can also include an optional second volatile memory, such as an SRAM. The controller can allocate a portion of the optional second volatile memory to the host device as a control memory buffer (CMB) that is directly accessible by the host. Thus, the host can store generated commands in the CMB and the controller directly accesses the CMB to obtain the commands or associated data stored therein.

[0049] Referring to Figure 4 , an internal structure and data processing path of a data storage device (SSD) are shown. The data storage device includes a controller and a NAND flash memory. The controller includes a PCIe bus, a control path coupled to the PCIe bus, a data transmit path Ts, a data receive path Rc, a flash controller (FIC), and a replication accelerator. The replication accelerator is responsible for transferring data between the Rc and Ts paths. The Ts path and the Rc path work together and are collectively referred to as a data path and are responsible for write and read processing of data, respectively. For example, when the controller receives a write command at the PCIe bus, the control path parses the write command and generates any one or more write commands necessary to write all of the data to the NAND flash memory while performing address translation corresponding to the write command.

[0050] On the Ts path, a memory access module (DMA) and a data protection module can generate and add protection information to the received data. An encryption module generates encryption and decryption keys for the data and encrypts the data. The encrypted data is provided to a disk array (RAID) to generate parity information, and then the data is encoded by an encoder. Finally, the data is transmitted to a flash controller (FIC), which can access a NAND flash memory to write the data to a relevant location in the NAND flash memory. Similarly, on the Rc path, the data read from the NAND flash memory is decoded and decrypted by a decoder and a decryption module, respectively, and an Rc DMA and a data protection module verify the read data.

[0051] A copy accelerator is coupled to the receive path and the transmit path to loop data from the Rc path to the Ts path without additional buffering. This is a closed loop path, i.e., the looped data is not visible to the host device. A multi-channel DMA engine is integrated in the copy accelerator to support simultaneous reading of data from multiple non-contiguous LBA ranges and merging of the data into a target area.

[0052] Referring to Figure 5 One embodiment of the present disclosure provides a data copying method based on a solid state disk, and the operation flow of executing a copy command is as follows:

[0053] A controller receives a copy command issued by a host, parses the command and checks the correctness of the command, returns a failure if data to be read by the command is not written or the command is illegal, and otherwise performs the next step.

[0054] The controller obtains source data from one or more initial locations in a NAND flash memory.

[0055] A decoder decodes the source data.

[0056] A decryption module decrypts the decoded data using a decryption key associated with the data.

[0057] A receive-side direct memory access (Rc DMA) and a data protection module verify protection information associated with the data.

[0058] A copy accelerator module transmits the data from the receive path to the transmit path.

[0059] A transmit-side direct memory access (Ts DMA) and a data protection module generate and add new protection information based on a destination address of the data in the NAND flash memory.

[0060] An encryption module encrypts the data using a new encryption key.

[0061] An encoder encodes the encrypted data.

[0062] The controller writes the encoded data to the NAND flash memory.

[0063] The controller sends a completion message to the host, indicating that the copy command operation is completed.

[0064] In the embodiment, by using the copy accelerator to loopback the data generated by the copy command, the host buffer is not involved in the whole process, and the performance of the data storage device in executing the copy command operation is improved.

[0065] The technical solution provided by one or more embodiments of the present disclosure bypasses the intervention of the host device when executing the copy command, can directly read data from the source address of the target storage device and write it to the target address of the target storage device, and is suitable for large-scale data migration scenarios. Inside the controller of the solid state disk, the data copy work is efficiently completed through the cooperation of the data receiving path, the data sending path and the copy accelerator, which not only greatly reduces the data transmission delay of the solid state disk, but also saves the host resource overhead.

[0066] Referring to Figure 6 The present disclosure also provides a data copy device based on a solid state disk, which can be applied to a target controller of a target solid state disk. The target solid state disk can include a target controller and a target storage device. The target controller can include a data receiving path, a data sending path and a copy accelerator. The data copy device specifically includes:

[0067] A command receiving unit 100 is configured to receive a copy command of a host device and analyze the copy command;

[0068] A data reading unit 200 is configured to read original data from a first position of the target storage device according to the analysis result of the copy command;

[0069] A data receiving unit 300 is configured to process the original data by using the data receiving path to generate first data;

[0070] A data copy unit 400 is configured to loop the first data to the data sending path by using the copy accelerator;

[0071] A data sending unit 500 is configured to process the first data by using the data sending path to generate second data;

[0072] A data writing unit 600 is configured to write the second data to a second position of the target storage device.

[0073] In an embodiment, the data receiving unit 300 is specifically configured to decode the original data by using a decoding module of the data receiving path to generate first decoded data.

[0074] In an embodiment, the data sending unit 500 is specifically configured to encode the first data by using an encoding module of the data sending path to generate second encoded data.

[0075] In an embodiment, the data receiving unit 300 is specifically configured to decrypt the original data by using a decryption module of the data receiving path to generate first decrypted data.

[0076] In an embodiment, the data sending unit 500 is specifically configured to encrypt the first data by using an encryption module of the data sending path to generate second encrypted data.

[0077] In an embodiment, the data receiving unit 300 is specifically configured to verify original protection information of the original data by using a direct memory access and data protection module of the data receiving path.

[0078] If the original protection information passes the verification, the first data is generated.

[0079] In an embodiment, the data sending unit 500 is specifically configured to add target protection information to the first data by using a direct memory access and data protection module of the data sending path to generate the second data.

[0080] In an embodiment, the target solid state disk further includes a volatile memory; the data receiving unit 300 is further configured to cache the original data to a receiving cache area of the volatile memory; and the data sending unit 500 is further configured to cache the first data to a sending cache area of the volatile memory.

[0081] In an embodiment, the target solid state disk further includes a target dynamic random access memory, the target dynamic random access memory containing a logical-to-physical table, the logical-to-physical table being used to manage address information of the target storage device.

[0082] Each unit illustrated in the above embodiments can be specifically implemented by a computer chip, or by a product with certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an electronic mail device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0083] For the convenience of description, the above apparatus is described in various units by function respectively. Of course, the functions of the units can be implemented in one or more software and / or hardware in the implementation of the present application.

[0084] Referring to Figure 7 The present disclosure also provides a computer device, comprising a memory and a processor, wherein the memory is configured to store a computer program, and the computer program, when executed by the processor, implements the above-mentioned data replication method based on a solid state disk.

[0085] The present disclosure also provides a computer-readable storage medium configured to store a computer program, and the computer program, when executed by a processor, implements the above-mentioned data replication method based on a solid state disk.

[0086] The processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination thereof.

[0087] The memory is a non-transitory computer-readable storage medium, which can be configured to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions / modules corresponding to the method in the embodiments of the present disclosure. The processor executes various functions and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, i.e. implements the method in the above-mentioned method embodiments.

[0088] The memory can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required by a function. The data storage area can store data created by the processor and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory disposed remotely with respect to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0089] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc. The storage medium can also include a combination of the above-mentioned types of memories.

[0090] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, the embodiments of the device, the equipment and the storage medium are basically similar to the method embodiments, and thus the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0091] The above only describes the embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various modifications and changes to the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

[0092] Although the embodiments of the present disclosure are described in conjunction with the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present disclosure, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A data copying method based on a solid-state drive, characterized in that, The target solid-state drive includes a target controller and a target storage device. The method is applied to the target controller, which includes a data receiving path, a data sending path, and a replication accelerator. The method includes: Receive the copy command from the host device and parse the copy command; Based on the parsing result of the copy command, read the original data from the first location of the target storage device; Using the data receiving path, the raw data is processed to generate the first data; Using the replication accelerator, the first data is looped through to the data transmission path; Using the data transmission path, process the first data to generate the second data; The second data is written to the second location of the target storage device.

2. The method according to claim 1, characterized in that, The process of using the data receiving path to process the raw data and generate the first data includes: The original data is decoded using the decoding module of the data receiving path to generate the first decoded data.

3. The method according to claim 2, characterized in that, The step of processing the first data and generating the second data using the data transmission path includes: The first data is encoded using the encoding module of the data transmission path to generate the second encoded data.

4. The method according to claim 1, characterized in that, The process of using the data receiving path to process the raw data and generate the first data includes: The original data is decrypted using the decryption module of the data receiving path to generate the first decrypted data.

5. The method according to claim 4, characterized in that, The step of processing the first data and generating the second data using the data transmission path includes: The first data is encrypted using the encryption module of the data transmission path to generate the second encrypted data.

6. The method according to claim 1, characterized in that, The process of using the data receiving path to process the raw data and generate the first data includes: The original protection information of the original data is verified using the direct memory access and data protection module of the data receiving path. If the original protection information passes verification, the first data is generated.

7. The method according to claim 6, characterized in that, The step of processing the first data and generating the second data using the data transmission path includes: Using the direct memory access and data protection module of the data transmission path, target protection information is added to the first data to generate the second data.

8. A data copying device based on a solid-state drive, characterized in that, The target solid-state drive includes a target controller and a target storage device. The apparatus is applied to the target controller, which includes a data receiving path, a data sending path, and a replication accelerator. The apparatus includes: A command receiving unit is used to receive copy commands from the host device and parse the copy commands; A data reading unit is used to read raw data from a first location of the target storage device based on the parsing result of the copy command; A data receiving unit is used to process the raw data using the data receiving path to generate first data; A data replication unit is used to use the replication accelerator to cycle through the first data to the data transmission path. The data sending unit is used to process the first data and generate the second data using the data sending path; A data writing unit is used to write the second data to a second location of the target storage device.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory being used to store a computer program that, when executed by the processor, implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images