WO2020006715A1

WO2020006715A1 - Data storage method and apparatus, and related device

Info

Publication number: WO2020006715A1
Application number: PCT/CN2018/094545
Authority: WO
Inventors: 龚伟; 王华强; 李吉坤
Original assignee: 华为技术有限公司
Priority date: 2018-07-04
Filing date: 2018-07-04
Publication date: 2020-01-09
Also published as: CN110881277A

Abstract

Provided are a data storage method and apparatus, and a related device. The method comprises: a data storage device acquiring first instruction information from a first storage area, wherein the first instruction information is generated after the data storage device stores first sub-data, the first instruction information contains an identification of target data and position information of second sub-data in the target data, and the second sub-data is the next piece of sub-data, which is adjacent to the first sub-data in the target data; according to the first instruction information, obtaining a target write command from at least one write command received at present and at least one write command stored in a second storage area, wherein position information carried in the target write command is matched with the position information in the first instruction information; and storing a write command, which is to be processed, in the second storage area, storing third sub-data carried in the target write command in a storage area corresponding to the identification of the target data, and updating and saving the position information in the first instruction information.

Description

Data storage method, device and related equipment

Technical field

The present application relates to the field of computer technology, and in particular, to a data storage method, device, and related equipment.

Background technique

With the continuous increase of data scale, storage devices need to have exabyte (EB) -level seamless capacity expansion, tens of millions of concurrent access capabilities, and reliability guarantees on top of this. Due to the limitations of the storage device's head capacity and cabinet space, traditional network storage architectures (such as storage area network (SAN) architecture or network attached storage (NAS) architecture) have weak expansion capabilities and prices It is expensive, and disaster tolerance cannot be guaranteed, which cannot meet the storage requirements of massive data. An object-based storage device (OSD) architecture based on object storage technology came into being. The OSD architecture uses identification (ID) to refer to objects, making the storage device expandable to meet the growing data storage requirements. .

In the process of data storage, the data sending device usually sends the entire target data to be stored to the data storage device, so that it takes a long time for the target data to be transmitted to the data storage device through the network, especially when the network status is poor. , Resulting in lower data storage efficiency. Therefore, how to improve the efficiency of data storage is an urgent problem.

Summary of the invention

The present application provides a data storage method, device, and related equipment to improve data storage efficiency.

In a first aspect, the present application provides a data storage method. The method includes: a data storage device obtaining first indication information from a first storage area, wherein the first indication information is Generated after a piece of sub data, the first indication information includes an identifier of the target data and position information of the second sub data in the target data, and the first sub data and the second sub data for the target data include Two of the plurality of sub-data, and the second sub-data is a next sub-data adjacent to the first sub-data; and the data storage device obtains the first instruction information from the current A target write command is obtained from the received at least one write command and the at least one write command stored in the second storage area, wherein the target write command carries an identifier of the target data, a third sub-data, and the first Location information of three sub-data in the target data, and the location information carried in the target write command matches the location information in the first instruction information The data storage device stores a write command to be processed in the second storage area, where the write command to be processed is at least one write command currently received except for the target write command, and carries the target write command. The write command of the identifier of the target data; the data storage device stores the third sub data carried in the obtained target write command into a storage area corresponding to the identifier of the target data, and updates the first instruction information The position information in the first storage area, and the updated first indication information is stored in the first storage area; the position information in the updated first indication information is the position of the fourth sub-data in the target data Information, among the plurality of sub data included in the target data, the fourth sub data is a next sub data adjacent to the third sub data.

With the above method, the data storage device can receive one or more write commands sent by the data sending device each time, and determine the write command in the write command according to the position information of the sub data carried in the received write command in the target data. A position of the carried subdata in the target data, so that the write command sent by the data storage device in the data sending device does not follow the subdata carried in the write command sent by the data sending device in the target data In the case where the order of the data arrives at the data storage device, it can also determine that the sub-data carried in the write command sent by the data sending device is in the target according to the location information carried in the write command sent by the data sending device. Positioning the data correctly and completely storing the target data can reduce the time for the target data as a whole to be transmitted on the network, and improve the storage efficiency and accuracy of the target data. In addition, because the data storage device processes write commands at a rate much faster than the speed at which the write commands are transmitted over the network, the data storage device carries the pending write command, that is, at least one write command currently received, with the The write command that identifies the target data and carries positional information of the sub-data in the target data that does not match the positional information in the first indication information is stored in the second storage area, so that the write command The data storage device processes the write command in time when the location information contained in the first instruction information matches the location information carried in the write command stored in the second storage area, and does not require the data sending device to resend The write command can further improve the storage efficiency of the target data.

In a possible implementation manner, the data storage device may receive the at least one write command through a host connected to the data storage device, where the write command is sent to the host by a data sending device to store data, or the data storage device The device directly receives the at least one write command sent by the data sending device.

In a possible implementation manner, the data storage device may be a solid-state storage hard disk SSD.

In a possible implementation manner, the write command received by the data storage device and the position information of the sub-data carried in the write command stored in the second storage area in the target data may be through, but not limited to, the following two Any one of these ways:

1. When the size of each sub data in the target number is the same, the position information of the sub data carried in the write command in the target data may be relative to the target using the first byte of the sub data. The offset of the first byte of data is represented, or it is expressed by the offset of the last byte of the sub-data relative to the first byte of the target data.

2. When the size of each sub data in the target number is different, the position information of the sub data carried in the write command in the target data may be relative to the target by using the first byte of the sub data. The offset of the first byte of data and the number of bytes occupied by the subdata (that is, the length of the subdata), or the last word of the subdata relative to the first word of the target data The offset of the section and the number of bytes occupied by the subdata.

3. When the size of each sub-data in the target number is the same, the position information of the sub-data carried in the write command in the target data may be represented by the sort identifier of the sub-data in the target data , Wherein the sort identifier of the sub-data in the target data may be represented by numbers or characters.

4. When the size of each sub-data in the target number is different, the position information of the sub-data carried in the write command in the target data may be identified by the sorting of the sub-data in the target data and The number of bytes occupied by the sub-data (that is, the length of the sub-data) indicates that the sort identifier of the sub-data in the target data may be represented by numbers or characters.

In a possible implementation manner, for any one write command stored in the second storage area, a storage order of the write command in the second storage area is determined according to position information carried in the write command. The position information carried in the write command is used to identify the position of the sub-data carried in the write command in the target data, so that the data storage device is in at least one write command stored from the second storage area, When obtaining the target write command, it is only necessary to determine the position information carried in the first unexecuted write command stored in the second storage area or the last unexecuted write command stored in the second storage area. Whether the location information matches the location information contained in the first indication information, and it is not necessary to traverse all write commands stored in the second storage area, thereby reducing the data storage device's need to obtain the target write command Time to improve the efficiency of the data storage device storing the target data.

In a possible implementation manner, after the data storage device stores the third sub data carried in the target write command into a storage area corresponding to an identifier of the target data, the data storage device may also send the data to the host through a host connected to the target data. The data sending device of the write command sends the second instruction information, or the second instruction information is directly sent to the data sending device of the write command, and the second instruction information is used to indicate that the target write command carries the The child data has been stored.

According to the above method, after receiving the second instruction information, the data sending device may determine, according to the second instruction information, the sub data corresponding to the second instruction information and the target data in the sub data. All previous sub-data are stored, and a subsequent write command is sent to the data storage device, or a subsequent write command is sent to the data storage device through the host, and a part or all of the remaining sub-data of the target data is sent. Sending to the data storage device can reduce the time required for the target data to be transmitted to the data storage device through the network, thereby improving the storage efficiency of the target data without being affected by the second instruction information reaching the The impact of the sequence of data transmission equipment.

In a possible implementation manner, the data storage device stores the pending write command in the currently received at least one write command into the second storage area, which may specifically include the following steps: the data storage device will obtain The identifier of the target data and the position information of the sub-data in the target data carried in the received pending write command are correspondingly stored in the second storage area.

Because the data storage device stores the identifier of the target data carried in the obtained write command to be processed and the position information of the target data's sub-data in the target data, it is correspondingly stored in the second storage area. , The sub-data of the target data carried in the obtained write command to be stored is not stored, and the command and data can be separated, reducing the storage space required to store the write command to be processed, and preventing the data from being stored The device cannot process the received write command because it has no free resources.

In a second aspect, the present application provides another data storage method, which includes: the data sending device determines the number of write commands N that can be sent in parallel according to the current network state, and generates the N write commands, where N It is a positive integer, and each write command carries an identifier of the target data to be stored, subdata, and position information of the subdata in the target data, and the subdata is a plurality of subdata obtained by dividing the target data. And the sub data carried in each write command are different; the data sending device sends the generated N write commands in parallel to a host connected to the data storage device or directly to the data storage device.

According to the above method, the data sending device can send multiple write commands in parallel to the host or data storage device connected to the data storage device according to the current network status, where each write command carries an identifier of the target data to be stored, The sub data and the position information of the sub data in the target data, where the sub data is one of a plurality of sub data obtained by dividing the target data, so that the data storage device can carry the received data according to the received write command The position information of the subdata in the target data to determine the position of the subdata carried in the write command in the target data, even if the network status is poor, the writes sent by the data sending device are received out of order In the case of a command, the target data can also be stored correctly and completely, which can reduce the transmission time of the target data in the network, and improve the storage efficiency and storage accuracy of the target data.

In a possible implementation manner, the data sending device receives instruction information sent by the data storage device, where the instruction information is used to indicate that the sub data carried in the write command sent by the data sending device has been stored; The data sending device sends a subsequent write command to the data storage device according to the instruction information, or sends a subsequent write command to the data storage device through the host.

According to the above method, after receiving the instruction information sent by the data storage device, the data sending device may determine, according to the instruction information, subdata corresponding to the instruction information and the target data before the subdata. All the sub-data are stored, send a subsequent write command to the data storage device, or send a subsequent write command to the data storage device through the host, and send some or all of the remaining sub-data of the target data To the data storage device, the time required for the target data to be transmitted to the data storage device through the network can be reduced, thereby further improving the storage efficiency of the target data without being affected by the second instruction information reaching the data. The effect of the order of sending devices.

In a third aspect, the present application provides a data storage device, which has a function of realizing the behavior of the data storage device in the method example of the first aspect. The functions may be implemented by hardware, and may also be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

In a possible implementation manner, the structure of the data storage device includes a communication unit, a processing unit, a data storage unit, and a command storage unit, and these units can execute the corresponding functions in the method example of the first aspect above. For details, refer to the method. The detailed description in the example is not repeated here.

In a possible implementation manner, a structure of the data storage device includes a communication interface, a controller, and a memory, and the controller is configured to support the data storage device to perform a corresponding function in the method provided by the first aspect. . The memory is coupled to the controller and stores program instructions and data necessary for the data storage device.

In a fourth aspect, the present application provides a data sending device, and the data sending device has a function of implementing the behavior of the data sending device in the method example of the second aspect. The functions may be implemented by hardware, and may also be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

In a possible implementation manner, the structure of the data sending device includes a processing unit and a communication unit, and these units can perform corresponding functions in the method example of the second aspect described above. For details, refer to the detailed description in the method example. Do not go into details.

In a possible implementation manner, a structure of the data sending device includes a transceiver, a processor, and a memory, and the processor is configured to support the data storage device to perform a corresponding function in the method provided in the second aspect above. . The memory is coupled to the controller and stores program instructions and data necessary for the data transmitting device.

In a fifth aspect, the present application provides a communication system including the data storage device described in the third aspect and the data transmission device described in the fourth aspect.

According to a sixth aspect, the present application further provides a chip, where the chip is connected to a memory or the chip includes the memory, and is used to read and execute a software program stored in the memory to implement any of the foregoing aspects. The method provided by any one of the embodiments.

In a seventh aspect, the present application further provides a computer-readable storage medium, where the computer storage medium stores computer-executable instructions, and when the instructions are run on a computer, the computer is caused to execute any of the foregoing aspects. A method provided by an embodiment.

In an eighth aspect, the present application also provides a computer program product containing instructions that, when the instructions are run on a computer, cause the computer to perform any of the methods in any of the above aspects.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of a communication system architecture according to an embodiment of the present application; FIG.

2 is a schematic flowchart of a data storage method according to an embodiment of the present application;

3 is a schematic flowchart of a write command processing method according to an embodiment of the present application;

4 is a schematic flowchart of a data storage method according to a specific embodiment of the present application;

5 is a schematic structural diagram of a data storage device according to an embodiment of the present application;

6 is a schematic structural diagram of a data sending apparatus according to an embodiment of the present application;

7 is a schematic structural diagram of a data storage device according to an embodiment of the present application;

8 is a schematic structural diagram of a data storage device according to a specific embodiment of the present application;

FIG. 9 is a schematic structural diagram of a data sending device according to an embodiment of the present application.

detailed description

The present application provides a data storage method, device, and related equipment to improve data storage efficiency. Among them, the method and the device are based on the same inventive concept. Since the principle of the method and the device for solving the problem is similar, the implementation of the device and the method can be referred to each other, and duplicated details will not be repeated.

It should be noted that in the description of this application, "multiple" means two or more; words such as "first" and "second" are used only for the purpose of distinguishing descriptions, and cannot be understood as instructions. Or imply relative importance, nor can it be understood as indicating or implying order.

In order to make the purpose, technical solution, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings.

The data storage method provided in the embodiment of the present application is applied to a scenario in which a data storage device receives and stores target data to be stored sent by a data sending device through a network. FIG. 1 shows a possible communication system architecture to which the data storage method provided by the embodiment of the present application is applicable. The communication system includes: at least one of the data storage device 101 and at least one of the data sending device 102. The data storage device 101 may be connected to the host 103.

The data storage device 101 is configured to receive a write command sent by the data sending device through a network, and store subdata in the target data to be stored carried in the write command to the data storage device 101 Medium; the data storage device 101 can simultaneously receive write commands sent by different data sending devices 102, and when the data storage device 101 can be connected to a host 103, the data storage device 101 receives the data through the host The write command sent by the data transmitting device 102 through the network. The data sending device 102 may divide the target data to be stored into multiple sub-data, carry the divided sub-data in a corresponding write command, and send the write command to the data storage device through a network. 101.

When the network environment is complicated, the communication system further includes at least one data forwarding device 104, where the data forwarding device 104 is configured to forward a write command sent by the data sending device 102 to the corresponding data storage device 101 or Corresponds to the host 103 connected to the data storage device 101. Specifically, the data forwarding device 104 may be a router or a switch. The data storage device 101 may be inserted into a corresponding card slot in the host 103 to achieve connection with the host 103. The data storage device 101 may be a solid-state storage hard disk SSD.

As shown in FIG. 2, an embodiment of the present application provides a data storage method, which is applied to a scenario in which target data to be stored is divided into multiple sub-data, and the obtained multiple sub-data are transmitted through a network and stored to a corresponding storage device, respectively. , Suitable for communication systems as shown in Figure 1. The method includes:

S201: The data sending device determines the number of write commands N that can be sent in parallel according to the current network state, and generates the N write commands.

Wherein, N is a positive integer, and each write command carries an identifier of the target data to be stored, sub data, and position information of the sub data in the target data. The sub data is obtained by dividing the target data. One of the sub data, and the sub data carried in each write command is different; the data sending device sends the generated N write commands in parallel to a host or data storage device connected to the data storage device.

It should be noted that the embodiment of the present application does not limit the specific name of the write command sent by the data sending device. For example, the above write command may be an append command.

S202: The data sending device sends the generated N write commands in parallel to a host or a data storage device connected to the data storage device.

Correspondingly, the data storage device may receive at least one write command through a host connected to the data storage device, or directly receive at least one write command. The at least one write command currently received by the data storage device is one or more of the N write commands sent by the data sending device.

S203: The data storage device obtains first instruction information from a first storage area.

The first instruction information is generated after the data storage device stores the first sub data, and the first instruction information includes an identifier of the target data and position information of the second sub data in the target data, The first sub data and the second sub data are two sub data of a plurality of sub data included in the target data, and the second sub data is a next sub data adjacent to the first sub data.

S204: The data storage device obtains the target write command from at least one write command currently received and at least one write command stored in the second storage area according to the obtained first instruction information.

The target write command carries an identifier of the target data, a third subdata, and position information of the third subdata in the target data, and the position information carried in the target write command is related to all The position information in the first indication information matches, and the third sub-data is one of a plurality of sub-data included in the target data.

The first storage area and the second storage area may be a storage space in the data storage device, or may be a storage space in another device with a storage function connected to the data storage device.

S205: The data storage device stores the third sub data carried in the target write command into a storage area corresponding to an identifier of the target data, and updates the position information in the first instruction information, and updates the position information. The subsequent first instruction information is stored in the first storage area.

Wherein, the updated position information in the first instruction information is position information of a fourth sub-data in the target data, and among the plurality of sub-data included in the target data, the fourth sub-data is all The next sub-data adjacent to the third sub-data is described.

S206: The data storage device stores a pending write command in at least one currently received write command into the second storage area.

The write command to be processed is a write command in addition to the target write command among the currently received at least one write command and carrying the identifier of the target data, that is, the at least one write command currently received is carried in A write command in which the identifier of the target data and the position information of the sub-data of the target data in the target data and the position information in the first indication information do not match.

The data sending device and the data storage device may execute the above steps S201-S206 through cycles to store all the sub-data of the target data in the data storage device. It should be noted that the data storage device may simultaneously store the sub-data of the data to be stored sent by different data sending devices. For a write command sent by any data sending device that carries the sub-data of the data to be stored, the data The storage devices can all adopt the above steps S201-S206 for processing.

1. When the size of each sub data of the target number is the same, the position information of the sub data carried in the write command in the target data may be relative to the target data by using the first byte of the sub data. The offset of the first byte of, or the offset of the last byte of the sub-data relative to the first byte of the target data. For example, the size of the target data is 100 megabytes, and each sub-data size of the target data is 10 MB. The first sub-data of the target data carried in the write command is in the The position information in the target data may be represented by an offset of 10MB of the last byte of the first sub-data relative to the first byte of the target data. The position information of the second sub-data in the target data may be represented by an offset 20MB of the last byte of the second sub-data relative to the first byte of the target data ..., in the write command The position information of the tenth sub-data of the target data carried in the target data may be represented by an offset of 100 MB of the last byte of the tenth sub-data relative to the first byte of the target data .

2. When the size of each sub data of the target number is different, the position information of the sub data carried in the write command in the target data may be relative to the target data by using the first byte of the sub data. The offset of the first byte of the and the number of bytes occupied by the subdata (that is, the length of the subdata), or the last byte of the subdata relative to the first byte of the target data The offset and the number of bytes occupied by the subdata. For example, the size of the target data is 100 megabytes, the first sub-data size of the target data is 10 MB, and the first sub-data of the target data carried in the write command is For the position information in the target data, an offset 0 of the first byte of the first sub-data relative to the first byte of the target data and the bytes occupied by the first sub-data can be used. The number 10MB indicates that the size of the second subdata of the target data is 30MB, and the position information of the second subdata of the target data carried in the write command in the target data can use the second subdata The offset of the first byte from the first byte of the target data by 10MB and the number of bytes occupied by the second sub-data is 30MB, and so on.

3. When the size of each sub-data of the target number is the same, the position information of the sub-data carried in the write command in the target data may be represented by the sort identifier of the sub-data in the target data, The sorting identifier of the sub-data in the target data may be represented by numbers or characters. For example, the size of the target data is 100MB, and the size of each sub-data of the target data is 10MB. The ordering identifier of each sub-data of the target data in the target data is represented by numbers 1-10, that is, all The position information of the first sub-data of the target data carried in the write command in the target data may be represented by 1, and the second sub-data of the target data carried in the write command is at the target. The position information in the data may be represented by 2 ..., and the position information of the tenth sub-data of the target data carried in the write command in the target data may be represented by 10.

4. When the size of each sub-data of the target number is different, the position information of the sub-data carried in the write command in the target data may be identified by the sorting of the sub-data in the target data and the The sub-data indicates the number of bytes occupied (that is, the length of the sub-data), and the sort identifier of the sub-data in the target data may be represented by numbers or characters. For example, the size of the target data is 100 megabytes, the first sub-data size of the target data is 10 MB, and the first sub-data of the target data carried in the write command is The position information in the target data may be represented by the sort identifier 1 of the first sub data in the target data and the number of bytes occupied by the first sub data is 10 MB. The size of each sub-data is 30MB, and the position information of the second sub-data of the target data carried in the write command in the target data can be identified by the ordering of the second sub-data in the target data 2 and The number of bytes occupied by the second sub-data is 30MB, and so on.

In a possible implementation manner, position information of the second sub-data included in the first indication information in the target data, that is, the next sub-data to be stored by the data storage device is in the target data. The position information in the target data may be the same as that of the currently received at least one write command and at least one write command stored in the second storage area in the target data. different. When the location information in the first instruction information is different from the representation method of the location information carried in the write command, the data storage device and the data sending device agree on the location information in the first instruction information and The correspondence between the position information in the write command enables the data storage device to receive at least one write command currently received or at least one write command stored in the second storage area according to the first instruction information. The target write command is obtained, and the sub-data of the target data carried in the obtained target write command is stored.

In a possible implementation manner, when the data storage device obtains, from the host, the first carrying the target data identifier, a subdata of the target data, and location information of the subdata in the target data. When the command is written, the data storage device generates the first instruction information, and the position information of the next sub-data of the target data to be stored included in the first instruction information may be set in the target data. Fixed initial value.

In a possible implementation manner, for any one write command stored in the second storage area, a storage order of the write command in the second storage area is determined according to position information carried in the write command. The position information carried in the write command is used to identify the position of the sub-data carried in the write command in the target data, so that the data storage device is in at least one write command stored from the second storage area, When obtaining the target write command, it is only necessary to determine the position information carried in the first unexecuted write command stored in the second storage area or the last unexecuted write command stored in the second storage area. Whether the location information matches the location information contained in the first indication information, and it is not necessary to traverse all write commands stored in the second storage area, thereby reducing the data storage device's need to obtain the target write command Time, further improving the efficiency of the data storage device storing the target data.

In a possible implementation manner, after the data storage device stores the sub data carried in the target write command into a storage area corresponding to an identifier of the target data, step 207 may be further performed: a host connected through itself Send the second instruction information to the data sending device that sends the target write command, or send the second instruction information directly to the data sending device that sends the target write command, where the second instruction information is used to indicate the The sub-data of the target data carried in the target write command is successfully stored.

Accordingly, after receiving the second instruction information, the data sending device may send a subsequent write command to the data storage device according to the second instruction information, or send the subsequent write command to the data storage device through the host. Subsequent write commands.

Since the data sending device can determine that the sub data corresponding to the second instruction information and the sub data before the sub data in the target data are stored according to the second instruction information, the data The sending device can continue to send multiple write commands to the data storage device in parallel within the range allowed by the network bandwidth, and send some or all of the remaining sub-data of the target data to the data storage device, which can reduce The time required for the target data to be transmitted to the data storage device over the network can further improve the storage efficiency of the target data, and is not affected by the order in which the second instruction information reaches the data sending device.

Although affected by the network status, the second indication information sent after the data storage device stores the subdata carried in the target write command each time may not be able to send the second indication according to the data storage device The order of the information reaches the data sending device, but the data storage device stores only when the position information in the first instruction information matches the position information of the sub-data carried in the write command in the target data. The sub data carried in the write command, so when the data transmitting device receives the second indication information that a certain sub data of the target data is successfully stored, the data transmitting device can determine that the position in the target data is in a certain position. All the sub-data before each sub-data are stored, and continue to send at least one of the write commands to the data storage device. For example, when the data sending device receives the second instruction information indicating that the third sub-data storage of the target data is completed, and the data sending device does not receive the first one indicating the target data When the sub data or the second indication data of the target data is stored, the data sending device may send the three write commands to the data storage device in parallel, or may send the write command to the data storage device in parallel. Two of the write commands are sent in parallel, or one of the write commands may be sent to the data storage device.

Generally, the data storage device reserves a larger second storage area to store command information and data information that cannot be processed currently, but the data sending device may send the data storage device to the data storage device at the same time. Issue a large number of write commands, and the data storage device may receive multiple write commands corresponding to different target data issued by the data sending device at the same time, and these write commands are transmitted through the network to the data storage device in the order It is unpredictable that the data storage device may need a large number of write commands stored in the second storage area, which causes the second area to be completely occupied, thereby making the data storage device unable to process newly received data. The write command cannot release the resources of the second storage area, causing resource deadlock. In order to solve the foregoing problem, the data storage device includes a pending write command in at least one currently received write command (the pending write command carries an identifier of the target data, and the target data carried in the target data includes (The position information of the sub data in the target data does not match the position information in the first indication information), and when stored in the second storage area, the sub data carried in the write command to be stored is not stored Only the identifier of the target data and the position information of the sub-data in the target data are stored to reduce the resources occupied by storing write commands that cannot be processed immediately among the currently received at least one write command. To this end, in step S206, when the data storage device stores the pending write command in the second storage area, the identifier of the target data carried in the obtained pending write command may be specifically determined. And the position information of the sub-data in the target data is correspondingly stored in the second storage area.

Because the data storage device stores the identifier of the target data carried in the obtained write command to be processed and the position information of the target data's sub-data in the target data, it is correspondingly stored in the second storage area. , The sub-data of the target data carried in the obtained write command to be processed is not stored, and the command and data can be separated, reducing the storage of the write command to be processed, and the storage resources of the data storage device (for example, The double-rate synchronous dynamic random access memory (DDR, dynamic random access, memory, DDR, SDRAM (or DDR)) resources of the data storage device are occupied, so that the data storage device can maintain good performance and process the received data. The write command prevents the data storage device from being unable to process the received write command due to lack of idle resources.

In a possible implementation manner, when a host connected to the data storage device receives at least one write command sent by the data sending device, it may include the at least one write command sent by the data sending device. The sub data of the target data is cached in the memory of the host, and the data storage device is notified of the storage location information of the sub data of the target data carried in at least one write command sent by the data sending device; Alternatively, after the host buffers the sub-data of the target data carried in the at least one write command sent by the data sending device to the memory of the host, the host carries at least one write command sent by the data sending device. Replace the sub data in the target data with the storage location information of the sub data of the target data, and send the replaced write command to the data storage device.

Therefore, when the data storage device determines that the currently received at least one write command contains an identifier carrying the target data, and the position information of the sub-data of the target data carried in the target data and the first When there is a pending write command whose location information in the indication information does not match, that is, the data storage device determines that at least one write command currently received by the host has the target data that the data storage device cannot process immediately. When the corresponding write command is issued, the data storage device may further store the storage location information of the sub-data carried in the pending write command into the second storage area, so that subsequent storage in the second storage area is performed. When the location information carried in the write command matches the location information contained in the first instruction information, the data storage device obtains the corresponding sub data for storage according to the storage location information of the sub data carried in the write command. .

Taking the data storage device as an SSD, the first indication information stored in the SSD includes the identification ID0 of the target data and the position of the sub-data of the next target data to be stored in the target data. Information, the position information contained in the first indication information is represented by an offset of the first byte of the next sub target data to be stored by the data storage device relative to the first byte of the target data And the position information contained in the first indication information is an offset curofffset0, and the position information carried in a write command corresponding to the target data received by the SSD uses the target data carried in the write command The offset of the first byte of the sub-data relative to the first byte of the target data indicates that the storage medium in the SSD is DDR, and the host connected to the SSD will The sub-data carried in the write command is cached in its own memory. As shown in FIG. 3, the process of the SSD processing the received write command is as follows:

(1) The SSD first obtains a write command 1 from a host connected to the SSD, wherein the write command 1 carries an identification ID0 of the target data, a subdata buff1 of the target data, and the subdata. The offset of the first byte of buff1 from the first byte of the target data is offset1. Because the offset curofffset0 in the first instruction information does not match the offset offset1 in the write command 1, that is, the write command 1 is the pending write command, and the SSD is the write command 1 Allocate a storage space for storing command information in the DDR, and store the storage location information of the target data identifier ID0, the offset offset1, and the sub-data buff1 carried in the write command 1 to the allocation. (2) Next, the SSD receives a write command 2, wherein the write command 2 carries the identification ID0 of the target data, the subdata buff2 of the target data, and the subdata buff2. The offset of the first byte of the relative to the first byte of the target data is offset2. Because the offset curofffset0 in the first instruction information does not match the offset offset2 in the write command 2, that is, the write command 2 is the pending write command, and the SSD is the command 2 Allocate a storage space for storing command information in the DDR, and store the storage location information of the offset ID2, the offset 2 and the subdata buff2 of the target data in the write command 2 into the allocated storage space. , Forming a queue PendList0 with the identifier ID0 of the target data and the offset offset1 carried in the write command 1; (3) the SSD receives the write command 0, wherein the write command 0 carries all The identifier ID0 of the target data, the subdata buff0 of the target data, and the offset 0 of the first byte of the subdata buff0 relative to the first byte of the target data are offset0. Because the offset curofffset0 in the first instruction information matches the offset offset0 in the write command 0, that is, the write command 0 is the target write command, and the SSD is allocated in the DDR for storage. Data storage space, and stores the sub-data buff0 carried in the write command 0 to the allocated storage space, and updates the offset in the first instruction information to curofffset1, where the curofffset1 identifies the target number of The position information of the second sub-data buff1 in the target data, and according to the updated offset in the first instruction information, is matched with the write command in the queue PendList0, and the write command is a successful match Allocate storage space for storing data, complete data storage, and so on, and finally update the offset in the first instruction information to curofffset3, where curofffset3 identifies the fourth sub-data buff3 of the target number in all locations The position information in the target data is described.

In a possible implementation manner, the data storage device is a solid state storage (SSD), and the SSD has the advantages of fast data storage speed, low latency, and strong stability. The SSD is usually connected to the host, and obtains the write command sent by the data sending device through the host connected to the SSD, and the second instruction information to the data sending device.

In the embodiment of the present application, the data sending device can send multiple write commands in parallel to the host or data storage device connected to the data storage device according to the current network status, so that the data storage device can receive the data sent by the data sending device each time. Multiple write commands, and determining the position of the sub data carried in the write command in the target data according to the position information of the sub data carried in the received write command in the target data, so that the data is stored In a case where the write command sent by the data sending device does not reach the data storage device in the order of the sub data carried in the write command sent by the data sending device in the target data, the device can also The location information carried in the write command sent by the data sending device, determining the position of the sub data carried in the write command sent by the data sending device in the target data, and storing the target data correctly and completely can reduce the The time that the target data is transmitted on the network as a whole, and the storage efficiency of the target data is improved. Storage and accuracy.

In addition, because the data storage device processes write commands at a rate much faster than the speed at which the write commands are transmitted over the network, the data storage device carries the pending write command, that is, at least one write command currently received, with the The write command that identifies the target data and carries positional information of the sub-data in the target data that does not match the positional information in the first indication information is stored in the second storage area, so that the write command The data storage device can process the write command in time when the location information contained in the first instruction information matches the location information carried in the write command stored in the second storage area, without the data sending device needing to resend The write command can further improve the storage efficiency of the target data.

The following describes the data storage method provided in this application in detail through a specific embodiment. The data storage device takes an SSD as an example, the data sending device takes a server as an example, and the write command sent by the data sending device takes an additional write command as an example. The target data to be stored sent by the server includes 7 sub-nodes. The data is sequentially buff0, buff1, buff2, ..., buff6. The position information of the subdata of the next target data to be stored included in the first instruction information stored in the data storage device is used in the target data. The offset of the first byte of the sub-data of the next target data to be stored relative to the first byte of the target data indicates that the target data carried in the additional write command sent by the server Position information of a sub data in the target data is represented by an offset of a first byte of the sub data with respect to a first byte of the target data.

As shown in FIG. 4, the process in which the server stores target data to be stored in the SSD mainly includes the following steps:

S401: The server sends an additional write command 0, an additional write command 1, an additional write command 2 and an additional write command 3 to the host connected to the SSD in parallel according to the current network status.

Wherein, the additional write command 0 carries the identification ID0 of the target data, the first sub-data buff0 of the target data, and the first byte of the first sub-data relative to the first of the target data Byte offset offset0; the additional write command 1 carries the identification ID0 of the target data, the second sub-data buff1 of the target data, and the first byte of the second sub-data relative to the Offset1 of the first byte of the target data; the additional write command 2 carries the identification ID0 of the target data, the third sub-data buff2 of the target data, and the first word of the third sub-data The offset offset2 of the section from the first byte of the target data; the additional write command 3 carries the identification ID0 of the target data, the fourth sub-data buff3 of the target data, and the fourth sub-data The offset of the first byte of data from the first byte of the target data is offset3.

Correspondingly, the SSD obtains the additional write command 0, the additional write command 1, the additional write command 2 and the additional write command 3 sent by the server through the host.

Specifically, before sending the four additional write commands to the SSD-connected host, the server divides the target data into multiple sub-data and sorts the multiple sub-data in the target data, Assign an offset to each subdata.

S402: The SSD first receives the additional write command 2 and the additional write command 3, generates first instruction information, and stores the first instruction information in a first storage area. The first indication information includes an identifier ID0 of the target data and an offset of a first byte of a first sub-data buff0 of the target data from the first byte of the target data to be stored.量 curoffset0.

S403: The SSD determines that neither curoffset0 included in the first instruction information does not match offset2 carried in the additional write command 2 and offset3 carried in the additional write command 3, that is, the additional write command 2 and The additional write command 3 is the pending write command, and the additional write command 2 and the additional write command 3 are stored in a write command buffer queue pendlist0 corresponding to the target data in the second storage area.

The write commands in the write command buffer queue pendlist0 are arranged in ascending order from the offset carried in the write command, that is, the additional write command 2 is arranged before the additional write command 3.

S404: The SSD receives the additional write command 0, and determines that curoffset0 included in the first instruction information matches the offset0 carried in the additional write command 0, that is, the additional write command 0 is the target write. A command to store the first sub data buff0 of the target data carried in the append write command 0 to a storage area corresponding to the target data.

S405: The SSD sends to the server second instruction information indicating that the first sub-data buff0 of the target data has been stored.

S406: The SSD updates the offset included in the first instruction information to curoffset1, stores the updated first instruction information to the first storage area, and determines the write command cache queue pendlist0. The offset offset2 carried in the first write command (that is, the additional write command 2) does not match the offset curoffset1 included in the updated first instruction information, and is waiting to receive the next sent from the server. An append write command.

Wherein, the offset curoffset1 included in the updated first indication information indicates position information of the second subdata buff1 of the target subdata in the target subdata.

S407: The SSD receives the additional write command 1, and determines that curoffset1 included in the first instruction information matches the offset1 carried in the additional write command 1, that is, the additional write command 1 is the target write. A command to store the second sub-data buff1 of the target data carried in the additional write command 1 to a storage area corresponding to the target data.

S408: The SSD sends second indication information indicating that the second sub-data buff1 of the target data is stored to the server.

S409: The SSD updates the offset included in the first instruction information to curoffset2, stores the updated first instruction information in the first storage area, and determines the write command cache queue pendlist0. The offset offset2 carried in the first write command (that is, the additional write command 2) in the first write command matches the offset curoffset2 included in the updated first instruction information, that is, the additional write command 2 is The target write command stores the third sub-data buff2 of the target data carried in the additional write command 2 to a storage area corresponding to the target data.

Wherein, the offset curoffset2 included in the updated first indication information indicates position information of the third sub-data buff2 of the target sub-data in the target sub-data.

Optionally, after the SSD stores the third sub-data buff2 of the target data carried in the additional write command 2 to a storage area corresponding to the target data, the additional write command 2 is removed from the target data. The write command is deleted from the cache queue pendlist0.

S410: The SSD sends second indication information indicating that the third sub-data buff2 of the target data is stored to the server.

S411: The SSD updates the offset included in the first instruction information to curoffset3, stores the updated first instruction information in the first storage area, and determines the write command cache queue pendlist0. The offset offset3 carried in the first write command (that is, the additional write command 3) matches the offset curoffset3 included in the updated first instruction information, and the additional write command 3 is carried The fourth sub-data buff3 of the target data is stored in a storage area corresponding to the target data, and the offset included in the first instruction information is updated to curoffset4.

Wherein, the offset curoffset3 included in the updated first indication information represents position information of the fourth subdata buff3 of the target subdata in the target subdata.

S412: The SSD sends to the server second instruction information indicating that the fourth sub-data buff3 of the target data has been stored.

S413: The server first receives the second instruction information indicating that the third sub-data buff2 of the target data is stored, and determines that when the first sub-data buff0-the third sub-data buff2 of the target data are all stored, , Continuously adding a write command 4, a write command 5 and a write command 6 to the SSD.

Wherein, the additional write command 4 carries the identification ID0 of the target data, the fifth sub-data buff4 of the target data, and the first byte of the fifth sub-data relative to the first word of the target data Offset 4 of the section; the additional write command 5 carries the identification ID0 of the target data, the sixth sub-data buff5 of the target data, and the first byte of the sixth sub-data relative to the target Offset 5 of the first byte of data; the additional write command 6 carries the identification ID0 of the target data, the seventh sub-data buff6 of the target data, and the first byte of the seventh sub-data An offset of offset6 from the first byte of the target data.

After the SSD receives the additional write command 4, the additional write command 5 and the additional write command 6, the SSD processes the additional write command 4, any one of the additional write command 5 and the additional write command 6. The method of one command is the same as the method of processing the additional write command 0-the additional write command 3, which will not be repeated here. For details about the steps S402-S411 described above.

Based on the above embodiments, an embodiment of the present application further provides a data storage device, where the data storage device is configured to implement the data storage method shown in FIG. 2 to FIG. 4. Referring to FIG. 5, the data storage device 500 includes: a communication unit 501, a processing unit 502, a command storage unit 503, and a data storage unit 504. among them,.

The communication unit 501 is configured to receive at least one write command;

The processing unit 502 is configured to obtain first instruction information from a first storage area, where the first instruction information is generated after the data storage device stores the first sub-data, and the first instruction information includes The identification of the target data and the position information of the second sub-data in the target data, the first sub-data and the second sub-data are two sub-data among a plurality of sub-data included in the target data, and the first The two sub-data are the next sub-data adjacent to the first sub-data; and according to the obtained first instruction information, at least one write command currently received from the communication unit 501 and stored in the second storage area In at least one write command, a target write command is obtained; wherein the target write command carries an identifier of the target data, a third sub-data, and position information of the third sub-data in the target data, and all The location information carried in the target write command matches the location information in the first indication information; and at least one write command currently received from the communication unit 501 Obtaining a write command to be processed, wherein the write command to be processed is a write command other than the target write command and carrying an identifier of the target data among at least one write command currently received;

The command storage unit 503 is configured to store a write command to be processed obtained by the processing unit 502 in the second storage area;

The data storage unit 504 is configured to store the third sub-data carried in the target write command into a storage area corresponding to the identifier of the target data, and update the position information in the first instruction information, Storing the updated first instruction information in the first storage area; the updated position information in the first instruction information is position information of fourth subdata in the target data, and Among the plurality of sub data included in the target data, the fourth sub data is a next sub data adjacent to the third sub data;

In a possible implementation manner, for any one write command stored in the second storage area, a storage order of the write command in the second storage area is determined according to position information carried in the write command. The position information carried in the write command is used to identify the position of the sub-data carried in the write command in the target data.

In a possible implementation manner, the communication unit 501 is further configured to: store, in the data storage unit 504, the third sub-data carried in the target write command obtained by the processing unit 502 to a corresponding one of the identifiers of the target data. After being stored in the storage area, the host sending the second instruction information is sent to the data sending device through the host connected to the storage area, or the second instruction information is directly sent to the data sending device, and the second instruction information is used to indicate that the target write command carries the The sub data has been stored, and the data sending device is a device that sends the write command.

In a possible implementation manner, the command storage unit 503 is specifically configured to: identify the target data identifier and the sub-data of the target data carried in the to-be-processed write command obtained by the processing unit 502 The position information in the target data is correspondingly stored in the second storage area.

In a possible implementation manner, the data storage device is a solid-state storage hard disk SSD.

An embodiment of the present application provides a data storage device. The data storage device can receive multiple write commands sent by a data sending device each time, and according to the sub-data carried in the received write command in the target data. Location information to determine the position of the sub-data carried in the write command in the target data, so that the data storage device carries a write command sent by the data sending device that does not follow the write command sent by the data sending device In the case where the sub data of the target data arrives in the data storage device in the order, it can also be determined in the write command sent by the data sending device according to the location information carried in the write command sent by the data sending device. The position of the carried sub-data in the target data to correctly and completely store the target data can reduce the time for transmitting the target data as a whole in the network, and improve the storage efficiency and storage accuracy of the target data.

In addition, since the speed of processing the write command by the data storage device is much faster than the speed at which the write command is transmitted in the network, the data storage device carries the write command to be processed, that is, at least one write command currently received, with the The write command that identifies the target data and carries positional information of the sub-data in the target data that does not match the positional information in the first indication information is stored in the second storage area, so that the write command When the location information contained in the first instruction information matches the location information carried in a write command stored in the second storage area, the data storage device can process the write command in time, and does not require the data sending device to resend The write command can further improve the storage efficiency of the target data.

Based on the above embodiments, an embodiment of the present application further provides a data sending device, where the data sending device is configured to implement the data storage method shown in FIG. 2 to FIG. 4. As shown in FIG. 6, the data sending device 600 includes a processing unit 601 and a communication unit 602. among them,

The processing unit 601 is configured to determine the number of write commands N that can be sent in parallel according to the current network status, where N is a positive integer; and generate the N write commands; wherein each write command carries a target to be stored A data identifier, sub-data, and position information of the sub-data in the target data, the sub-data is one of a plurality of sub-data obtained by dividing the target data by the data sending device, and each of the writes The subdata carried in the command are different.

The communication unit 602 is configured to send the N write commands generated by the processing unit 601 to a host or a data storage device connected to the data storage device in parallel.

In a possible implementation manner, the communication unit 602 is further configured to: receive instruction information sent by the data storage device, where the instruction information is used to indicate that the sub data carried in the write command sent by the data sending device is stored Complete; and, send a subsequent write command to the data storage device according to the instruction information, or send a subsequent write command to the data storage device through the host.

An embodiment of the present application provides a data sending device capable of sending multiple write commands to a host or data storage device connected to a data storage device in parallel according to a current network status, where each write command carries The identifier of the target data to be stored, the sub data, and the position information of the sub data in the target data, where the sub data is one of a plurality of sub data obtained by dividing the target data, so that the data storage device can The position information of the sub-data carried in the received write command in the target data is used to determine the position of the sub-data carried in the write command in the target data. Even if the network status is poor, all the In the case of the write command sent by the data sending device, the target data can also be stored correctly and completely, which can reduce the transmission time of the target data in the network, and improve the storage efficiency and storage accuracy of the target data. .

It should be noted that the division of the units in the embodiments of the present application is schematic, and is only a logical function division. In actual implementation, there may be another division manner. The functional units in the embodiments of the present application may be integrated into one processing unit, or each of the units may exist separately physically, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially a part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium , Including a number of instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The foregoing storage media include: various types of media that can store program code, such as a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc.

Based on the above embodiments, an embodiment of the present application further provides a data storage device. The data storage device is configured to implement the data storage method shown in FIG. 2, and has the functions of the data storage device 500 shown in FIG. 5. As shown in FIG. 7, the data storage device includes: a communication interface 701, a controller 702, and a memory 703. The communication interface 701, the controller 702, and the memory 703 are connected to each other. among them,

The communication interface 701 is configured to receive at least one write command.

The controller 702 is configured to obtain first instruction information from a first storage area, where the first instruction information is generated after the data storage device stores first sub-data, and the first instruction information includes The identification of the target data and the position information of the second sub-data in the target data, the first sub-data and the second sub-data are two sub-data among a plurality of sub-data included in the target data, and the first The two sub data are the next sub data adjacent to the first sub data;

Obtaining the target write command from at least one write command currently received and at least one write command stored in the second storage area according to the first instruction information obtained by the acquiring unit; wherein the target write command carries the The target data identifier, the third sub data, and the position information of the third sub data in the target data, and the position information carried in the target write command matches the position information in the first instruction information ;

And, the third sub-data carried in the target write command is stored in a storage area corresponding to the identifier of the target data in the memory 703, and the position information in the first instruction information is updated, and The updated first indication information is stored in the first storage area; the position information in the updated first indication information is position information of fourth subdata in the target data, and Among the plurality of sub-data included in the data, the fourth sub-data is a next sub-data adjacent to the third sub-data; and, a write command to be processed is stored in the second storage area, wherein the The pending write command is a write command other than the target write command and carrying an identifier of the target data among at least one write command currently received.

The memory 703 is used for the third sub-data carried in the target write command.

The memory 703 may include non-volatile memory (non-volatile memory), such as flash memory (also called flash memory), and hard disk (hard disk drive). The memory 703 may further include the foregoing. A combination of kinds of memories. The memory 703 may be a memory or a memory array composed of multiple memories. As shown in FIG. 8, the memory in the memory array is a flash memory as an example.

The controller 702 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. The controller 702 may further include a hardware chip. The above hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

In a possible implementation manner, after the controller 702 stores the third sub data carried in the target write command to a storage area corresponding to the identifier of the target data in the memory 703, the communication interface 701 Also used for:

Sending the second instruction information to the data sending device through the host connected to itself, or directly sending the second instruction information to the data sending device, where the second instruction information is used to indicate that the sub-data carried in the target write command has been stored, The data sending device is a device that sends the target write command.

In a possible implementation manner, the controller 702 is specifically configured to: obtain the pending write command from at least one currently received write command; and acquire the target data carried in the obtained pending write command. The identifier and the position information of the sub-data in the target data are correspondingly stored in the second storage area.

An embodiment of the present application provides a data storage device. The data storage device can receive multiple write commands sent by a data sending device each time, and according to the sub-data carried in the received write command in the target data. Location information to determine the position of the sub-data carried in the write command in the target data, so that the data storage device does not carry the write command sent by the data sending device in accordance with the write command sent by the data sending device In the case where the sub data of the target data arrives in the data storage device in the order, it can also be determined in the write command sent by the data sending device according to the location information carried in the write command sent by the data sending device. The position of the carried sub-data in the target data to correctly and completely store the target data can reduce the time for transmitting the target data as a whole in the network, and improve the storage efficiency and storage accuracy of the target data.

Based on the above embodiments, an embodiment of the present application further provides a data sending device, which is used to implement the data storage method shown in FIG. 2 and has the functions of the data sending device 600 shown in FIG. 6. Referring to FIG. 9, the data storage device 900 includes: a memory 901, a processor 902, and a transceiver 903. The memory 901, the processor 902, and the transceiver 903 are connected to each other. among them,

The memory 901 is configured to store a program instruction.

The processor 902 is configured to call a program instruction stored in the memory 901 and execute: determine the number of write commands N that can be sent in parallel according to the current network status, where N is a positive integer;

The data sending device generates the N write commands; wherein each write command carries an identifier of the target data to be stored, sub data, and position information of the sub data in the target data, and the sub data is The data sending device divides the target data into one of a plurality of sub-data, and the sub-data carried in each write command is different.

The transceiver 903 is configured to send the N write commands generated by the processor 902 to the host or the data storage device connected to the data storage device in parallel.

Wherein, the memory 901 may include volatile memory, such as RAM; the memory 901 may also include non-volatile memory, such as flash memory, HDD or SSD; the memory 901 may further include the above-mentioned types of Memory combination.

The processor 902 may be a CPU, an NP, or a combination of a CPU and an NP. The processor 902 may further include a hardware chip. The aforementioned hardware chip may be an ASIC, a PLD, or a combination thereof. The PLD may be a CPLD, an FPGA, a GAL, or any combination thereof.

In a possible implementation manner, the transceiver 903 is further configured to: receive instruction information sent by the data storage device, where the instruction information is used to indicate that the sub data carried in the write command sent by the data sending device has been Storage completed

The processor 902 is further configured to control the transceiver 903 to send a subsequent write command to the data storage device or send a subsequent write command to the data storage device through the host according to the instruction information.

An embodiment of the present application provides a data sending device. The data sending device can send multiple write commands to a host or data storage device connected to the data storage device in parallel according to the current network status, where each write command carries The identifier of the target data to be stored, sub-data, and position information of the sub-data in the target data, the sub-data is one of a plurality of sub-data obtained by dividing the target data, so that the data storage device can The position of the sub-data carried in the write command in the target data is determined according to the position information of the sub-data carried in the received write command in the target data. Even if the network status is poor, the data is received out of order. In the case of the write command sent by the data sending device, the target data can also be stored correctly and completely, which can reduce the transmission time of the target data in the network, and improve the storage efficiency and storage accuracy of the target data. .

Because the data storage device and the data sending device are used to implement the data storage method shown in FIG. 2 to FIG. 4, and the related technical features involved in the data storage device and the data sending device have been attached in combination with the foregoing. The figure is described in detail, so it will not be repeated here, please refer to the relevant description in the above method embodiment.

Those skilled in the art should understand that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, this application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

This application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and combinations of processes and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, so that the instructions generated by the processor of the computer or other programmable data processing device are used to generate instructions Means for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a specific manner such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, the instructions The device implements the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of steps can be performed on the computer or other programmable device to produce a computer-implemented process, which can be executed on the computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.

Obviously, those skilled in the art can make various modifications and variations to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. In this way, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and variations.

Claims

A data storage method, comprising:

The data storage device obtains first instruction information from a first storage area, where the first instruction information is generated after the data storage device stores the first sub-data, and the first instruction information includes an identifier of the target data and Position information of a second sub-data in the target data, the first sub-data and the second sub-data are two sub-data among a plurality of sub-data included in the target data, and the second sub-data is all The next sub-data adjacent to the first sub-data;

The data storage device obtains a target write command from at least one write command currently received and at least one write command stored in a second storage area according to the obtained first instruction information; wherein, in the target write command, Carry the identifier of the target data, the third sub-data, and position information of the third sub-data in the target data, and the position information carried in the target write command and the position in the first instruction information Information matching, the third sub-data is one of a plurality of sub-data included in the target data;

The data storage device stores a write command to be processed in the second storage area, where the write command to be processed is at least one write command currently received except for the target write command, and carries the target write command. The write command of the identification of the target data;

The data storage device stores the third sub-data carried in the target write command into a storage area corresponding to an identifier of the target data, and updates the position information in the first instruction information, and updates the updated information. The first indication information is stored in the first storage area; the updated position information in the first indication information is position information of the fourth subdata in the target data, and the information included in the target data Among the plurality of sub-data, the fourth sub-data is a next sub-data adjacent to the third sub-data.
The method according to claim 1, wherein, for any one write command stored in the second storage area, a storage order of the write command in the second storage area is according to the carry command carried in the write command. The location information is determined, and the location information carried in the write command is used to identify the position of the sub-data carried in the write command in the target data.
The method according to claim 1 or 2, wherein after the data storage device stores the third sub-data in a storage area corresponding to an identifier of the target data, the method further comprises:

The data storage device sends the second instruction information to the data sending device through the host connected to the data storage device, or the data storage device directly sends the second instruction information to the data sending device;

The second instruction information is used to indicate that the sub data carried in the target write command has been stored, and the data sending device is a device that sends the target write command.
The method according to any one of claims 1-3, wherein the storing, by the data storage device, a write command to be processed into the second storage area comprises:

Obtaining, by the data storage device, the pending write command from at least one write command currently received;

The data storage device stores the identifier of the target data and the position information of the sub data in the target data carried in the write command to be processed into the second storage area correspondingly.
The method according to any one of claims 1-4, wherein the data storage device is a solid-state storage hard disk SSD.
A data storage method, comprising:

The data sending device determines the number of write commands N that can be sent in parallel according to the current network status, where N is a positive integer;

The data sending device generates the N write commands; wherein each write command carries an identifier of the target data to be stored, sub data, and position information of the sub data in the target data, and the sub data is One of a plurality of sub-data obtained by dividing the target data, and the sub-data carried in each write command is different;

The data sending device sends the generated N write commands to the host or data storage device connected to the data storage device in parallel.
The method according to claim 6, further comprising:

Receiving, by the data sending device, instruction information sent by the data storage device, where the instruction information is used to indicate that the sub data carried in the write command sent by the data sending device has been stored;

The data sending device sends a subsequent write command to the data storage device according to the instruction information, or sends a subsequent write command to the data storage device through the host.
A data storage device, comprising:

A communication unit, configured to receive at least one write command;

A processing unit, configured to obtain first instruction information from a first storage area, where the first instruction information is generated after the data storage device stores the first sub-data, and the first instruction information includes the target data; An identifier and position information of a second sub-data in the target data, the first sub-data and the second sub-data are two sub-data among a plurality of sub-data included in the target data, and the second sub-data Is the next sub-data adjacent to the first sub-data; and according to the obtained first instruction information, at least one write command currently received from the communication unit and at least one write command stored in the second storage area To obtain a target write command; wherein the target write command carries an identifier of the target data, a third sub data, and position information of the third sub data in the target data, and the target write command The location information carried in the first location information matches the location information in the first indication information; and obtaining, from the at least one write command currently received by the communication unit, Processing the write command, wherein the write command to be processed for the current received at least one write command in write command other than the target, and the write command carrying the target identification data;

A command storage unit, configured to store a write command to be processed obtained by the processing unit in the second storage area;

A data storage unit, configured to store the third sub-data carried in the target write command obtained by the processing unit into a storage area corresponding to an identifier of the target data, and update the position information in the first instruction information Storing the updated first instruction information in the first storage area; the updated position information in the first instruction information is position information of fourth subdata in the target data, and Among the plurality of sub data included in the target data, the fourth sub data is a next sub data adjacent to the third sub data.
The data storage device according to claim 8, wherein, for any one write command stored in the second storage area, a storage order of the write command in the second storage area is based on the write command. The location information carried is determined, and the location information carried in the write command is used to identify the position of the sub-data carried in the write command in the target data.
The data storage device according to claim 8 or 9, wherein the communication unit is further configured to:

After the data storage unit stores the third sub-data carried in the target write command obtained by the processing unit into a storage area corresponding to the identifier of the target data, the data storage unit sends the first sub-data to the data sending device through the host connected to itself. Two instructions, or directly send the second instructions to the data sending device;

The second instruction information is used to indicate that the third sub-data carried in the target write command has been stored, and the data sending device is a device that sends the target write command.
The data storage device according to any one of claims 8 to 10, wherein the command storage unit is specifically configured to:

The identifier of the target data carried in the to-be-processed write command obtained by the processing unit and the position information of the sub-data in the target data are correspondingly stored in the second storage area.
The data storage device according to any one of claims 8-11, wherein the data storage device is a solid-state storage hard disk SSD.
A data sending device, comprising:

A processing unit, configured to determine the number of write commands N that can be sent in parallel according to the current network status, where N is a positive integer; and generate the N write commands; wherein each write command carries an identifier of target data to be stored , Sub data, and position information of the sub data in the target data, the sub data is one of a plurality of sub data obtained by dividing the target data, and the sub data carried in each write command are different;

The communication unit is configured to send the N write commands generated by the processing unit in parallel to a host or a data storage device connected to the data storage device.
The data transmitting device according to claim 13, wherein the communication unit is further configured to receive instruction information sent by the data storage device, and the instruction information is used to indicate a write command sent by the data sending device. The sub-data carried in it has been stored; and according to the instruction information, a subsequent write command is sent to the data storage device, or a subsequent write command is sent to the data storage device through the host.
A chip, characterized in that the chip is connected to a memory or the chip includes the memory, and is used to read and execute a software program stored in the memory, so as to implement the device according to any one of claims 1-7. The method described.
A computer storage medium, characterized in that computer executable instructions are stored on the computer storage medium, and the computer executable instructions, when called by the computer, cause the computer to execute any one of claims 1-7 The method described.
A computer program product containing instructions, wherein when the computer program product is run on a computer, the computer is caused to execute the method according to any one of claims 1-7.