WO2019223445A1

WO2019223445A1 - Hard disk read-write control method and apparatus, electronic device and storage medium

Info

Publication number: WO2019223445A1
Application number: PCT/CN2019/082262
Authority: WO
Inventors: 张宏海; 余高峰; 吴海波; 严杰
Original assignee: 杭州海康威视数字技术股份有限公司
Priority date: 2018-05-22
Filing date: 2019-04-11
Publication date: 2019-11-28
Also published as: CN110515535B; CN110515535A

Abstract

Disclosed are a hard disk read-write control method and apparatus, an electronic device and a storage medium. The method comprises: if the operating state of a computing node regarding a target hard disk is a disallowed state, acquiring a token depth of the target hard disk (S103); determining a magnitude relationship between the token depth of the target hard disk and a depth threshold value (S104); and if the token depth of the target hard disk is less than the depth threshold value, changing the operating state of the computing node regarding the target hard disk to an allowed state, and increasing the token depth of the target hard disk according to a pre-set depth increase rule (S105). According to the hard disk read-write control method, whether a computing node is still allowed to access a target hard disk is determined according to a token depth of the target hard disk, and when the token depth of the target hard disk is less than a depth threshold value, the computing node is allowed to carry out corresponding read-write operations on the target hard disk, so that a plurality of computing nodes can simultaneously access one hard disk, and the working efficiency of the computing nodes can be improved, thereby improving the overall running efficiency of a network.

Description

Hard disk read-write control method, device, electronic equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on May 22, 2018, with application number 201810496764.2 and entitled "Hard Disk Read / Write Control Method, Device, Electronic Equipment, and Storage Medium", the entire contents of which are hereby incorporated by reference. Incorporated in this application.

Technical field

The present application relates to the technical field of data reading and writing, and in particular, to a hard disk reading and writing control method, device, electronic device, and storage medium.

Background technique

SAN (Storage Area Network) is a storage network that integrates storage devices, connected devices, and interfaces, and assumes data storage tasks. Data transmission is completed in a SAN via SCSI (Small Computer System Interface). SAS (Serial Attached SCSI, Serial Attached SCSI) is a new generation of SCSI technology. It adopts serial technology to achieve higher transmission speed, and shortens the connection line to improve internal space.

In a related SAN network, each hard disk allows only one I / O (Input / Output) operation of a computing node at the same time. However, with the rise of SAS technology, the number of computing nodes in a SAN network has increased significantly. The hard disk allows only one computing node's IO operations at the same time, causing a large number of computing nodes to queue up, which seriously affects the computing node's working efficiency and the overall network operation efficiency is low.

Summary of the Invention

The present application provides a hard disk read-write control method, device, electronic device, and storage medium, so as to achieve low overall operating efficiency. The specific technical solutions are as follows:

In a first aspect, an embodiment of the present application provides a hard disk read-write control method. The method includes:

Determine the target hard disk where the data to be operated is located;

Determine an operation state of a computing node requesting operation of the data to be operated with respect to the target hard disk;

Obtaining the token depth of the target hard disk if the operation status of the target hard disk for the target hard disk is a non-permitted state, wherein the token depth of the target hard disk is used to represent an occupied read in the target hard disk; Write resources

Determining a magnitude relationship between a token depth of the target hard disk and a depth threshold;

If the token depth of the target hard disk is less than the depth threshold, change the operation state of the computing node for the target hard disk to an allowed state, and increase the token depth of the target hard disk according to a preset depth increase rule. .

Optionally, after the judging the operating status of the computing node requesting the data to be operated on the target hard disk, the method further includes:

If the operation state of the computing node with respect to the target hard disk is an allowed state, reading and writing operations to be performed on the target hard disk by the computing node are completed.

Optionally, the hard disk read-write control method in the embodiment of the present application further includes:

When the computing node satisfies a preset token release rule, the operation state of the computing node for the target hard disk is changed to a non-permitted state, and the preset depth reduction rule is used to reduce the token depth of the target hard disk. .

Optionally, in the hard disk read-write control method in the embodiment of the present application, the steps of determining whether the computing node satisfies a preset token release rule are as follows:

Determining that the computing node satisfies a preset after the computing node completes a read-write operation on the target hard disk, or when the time when the operating state of the computing node for the target hard disk is in an allowed state reaches a preset time threshold Token release rules.

Optionally, after determining the magnitude relationship between the token depth and the depth threshold of the target hard disk, the method further includes:

If the token depth of the target hard disk is not less than the depth threshold, the computing node is prohibited from performing read and write operations on the target hard disk.

Optionally, before the judging the relationship between the token depth of the target hard disk and the depth threshold, the method further includes:

Determining that the read and write resources of the target hard disk occupied by the computing node when performing read and write operations on the data to be operated are used as read and write resources to be used;

The read and write resources to be used are removed from the total read and write resources of the target hard disk to obtain the depth threshold.

In a second aspect, an embodiment of the present application provides a hard disk read-write control device, where the device includes:

A hard disk determining module for determining a target hard disk where the data to be operated is located;

A state determination module, configured to determine an operation state of a computing node requesting operation of the data to be operated on the target hard disk;

A depth acquisition module, configured to obtain a token depth of the target hard disk if the operation status of the computing node for the target hard disk is not allowed, wherein the token depth of the target hard disk is used to characterize the target; Read and write resources occupied on the hard disk;

A threshold determination module, configured to determine a magnitude relationship between a token depth of the target hard disk and a depth threshold;

A state calibration module, configured to change the operation state of the computing node for the target hard disk to an allowed state if the token depth of the target hard disk is less than the depth threshold, and add the preset depth increase rule to increase the The token depth of the target hard disk.

Optionally, the hard disk read-write control device in the embodiment of the present application further includes:

An operation permission module is configured to complete the reading and writing of data to be operated on the target hard disk by the computing node if the operation status of the computing node for the target hard disk is allowed.

A deep release module is configured to change an operation state of the computing node for the target hard disk to a non-permitted state when the computing node meets a preset token release rule, and reduce the rule according to a preset depth reduction rule to reduce the The token depth of the target hard disk.

Optionally, the deep release module is specifically configured to:

After the computing node completes the read and write operations on the target hard disk, or when the time when the operation status of the computing node for the target hard disk is allowed to reach a preset time threshold, the computing node is The operating state of the target hard disk is changed to a non-permitted state, and the token depth of the target hard disk is reduced according to a preset depth reduction rule.

An operation prohibition module is configured to prohibit the computing node from performing read and write operations on the target hard disk if the token depth of the target hard disk is not less than the depth threshold.

A resource determining module, configured to determine the read and write resources of the target hard disk occupied by the computing node when performing read and write operations on the data to be operated, as the read and write resources to be used;

A threshold determination module is configured to remove the read-write resources to be used from the total read-write resources of the target hard disk to obtain the depth threshold.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory;

The memory is used to store a computer program;

The processor is configured to implement the hard disk read-write control method according to any one of the first aspects when executing a program stored in the memory.

According to a fourth aspect, an embodiment of the present application provides a storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the hard disk read or write according to any one of the first aspects is implemented. Control Method.

The hard disk read-write control method, device, electronic device and storage medium provided in the embodiments of the present application determine the target hard disk where the data to be operated is located; determine the operation status of the computing node requesting the operation of the data to be operated against the target hard disk; The operating status of the hard disk is non-permitted, and the token depth of the target hard disk is obtained. The token depth of the target hard disk is used to represent the read and write resources occupied by the target hard disk. The token depth and the depth threshold of the target hard disk are determined. Relationship; if the token depth of the target hard disk is less than the depth threshold, the operation state of the computing node for the target hard disk is changed to an allowed state, and the token depth of the target hard disk is increased according to a preset depth increase rule. According to the token depth of the target hard disk, determine whether the target hard disk can still allow access to the computing node. When the token depth of the target hard disk is less than the depth threshold, allow the computing node to perform corresponding read and write operations on the target hard disk, which can implement multiple computing nodes. Accessing a hard disk at the same time can improve the working efficiency of the computing node, thereby improving the overall operating efficiency of the network. Of course, the implementation of any product or method of this application does not necessarily need to achieve all the above advantages at the same time.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application and the technical solutions of the prior art, the following briefly introduces the embodiments and the drawings needed in the prior art. Obviously, the drawings in the following description are only the present invention. Some embodiments of the application, for those of ordinary skill in the art, can obtain other drawings according to these drawings without paying creative labor.

1 is a schematic flowchart of a hard disk read-write control method according to an embodiment of the present application;

2a is a schematic diagram of a data storage system according to an embodiment of the present application;

2b is another schematic diagram of a data storage system according to an embodiment of the present application;

FIG. 3 is another schematic flowchart of a hard disk read-write control method according to an embodiment of the present application; FIG.

4 is a schematic diagram of a hard disk read-write control device according to an embodiment of the present application;

FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution, and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and examples. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

In related SAN networks, in order to ensure the bandwidth of hard disks, each hard disk allows only one computing node's IO operations at the same time, and other computing nodes that need to read and write the hard disk need to wait in line. However, with the development of SAS and other technologies, the bandwidth of hard disks has increased greatly. At the same time, the number of computing nodes in the SAN network has also increased significantly. A hard disk allows only one compute node to perform IO operations at the same time, which reduces the utilization efficiency of hard disks and seriously affects SAN The overall speed of the network.

In view of this, an embodiment of the present application provides a hard disk read-write control method. Referring to FIG. 1, the method includes:

S101. Determine a target hard disk where the data to be operated is located.

The hard disk read-write control method in the embodiment of the present application can be implemented by a control system, and the control system is any system capable of realizing the hard disk read-write control method in the embodiment of the present application. E.g:

The control system may be a kind of equipment, including: a processor, a memory, a communication interface, and a bus; the processor, the memory, and the communication interface are connected through a bus and complete communication with each other; the memory stores executable program code; and the processor reads the memory by The executable program code stored in the program is used to run a program corresponding to the executable program code, and is used to execute the hard disk read-write control method in the embodiment of the present application.

The control system may also be an application program for executing the hard disk read-write control method in the embodiment of the present application at runtime.

The control system may also be a storage medium for storing executable code, and the executable code is used to execute the hard disk read-write control method in the embodiment of the present application.

The control system may determine the target hard disk where the data to be operated is located according to the acquired data request instruction, wherein the data request instruction includes an identifier of the data to be operated. Optionally, the data request instruction may further include an identification of a computing node requesting operation of the data to be operated.

S102. Determine an operation state of the computing node requesting to operate the data to be operated on the target hard disk.

The control system determines the operating state of the computing node with respect to the target hard disk, and the operating state of the computing node with respect to the target hard disk is an allowed state or an unallowed state. For example, the control system establishes an operation status table of the hard disk and the computing node, and for each hard disk in the operating status table, records each computing node whose operating status is allowed for the hard disk; or for each computing node in the operating status table To record which hard disks' operation status is allowed for this compute node. Optionally, the control system is a computing node, and the operation state table of the control system includes an identification of each hard disk targeted by the computing node for an operating state that is allowed.

The control system can also determine whether the computing node is in the allowed operating state of the target hard disk by judging whether the computing node holds the token of the target hard disk. If the computing node holds the token of the target hard disk, determine the operating status of the computing node for the target hard disk. It is an allowed state; if the computing node does not hold the token of the target hard disk, it is determined that the operating state of the computing node for the target hard disk is a non-permitted state.

S103: If the computing node's operation status for the target hard disk is not allowed, obtain the token depth of the target hard disk, where the token depth of the target hard disk is used to represent the read and write resources occupied by the target hard disk.

The token depth of the target hard disk may also be stored in the local storage of the control system, for example, the control system obtains the token depth of the target hard disk in the local storage. The token depth of the target hard disk can also be saved on the storage management node of the target hard disk. For example, the control system can obtain the token depth of the target hard disk through the storage management node of the target hard disk. Specifically, the control system sends an access request to the storage management node of the target hard disk, and the storage management node of the target hard disk returns to the target after receiving the access request. The token depth of the hard disk. The token depth is used to characterize the read and write resources occupied in the hard disk. For example, the token depth of the target hard disk can be the bandwidth occupied by the target hard disk, or the token depth of the target hard disk can also be the number of computing nodes that are performing read and write operations on the target hard disk.

S104. Determine the magnitude relationship between the token depth of the target hard disk and the depth threshold.

When the token depth of the target hard disk is the number of computing nodes that are performing read and write operations on the target hard disk, the depth threshold can be set in advance. The depth threshold must be set to ensure that at least two computing nodes can simultaneously access a hard disk. For example, the depth threshold can be set to 2, 3, 4, or 5 and so on.

The depth threshold can also be calculated based on resources such as the bandwidth of the target hard disk. Optionally, before judging the magnitude relationship between the token depth and the depth threshold of the target hard disk, the hard disk read-write control method in the embodiment of the present application further includes:

Step 1: Determine the read and write resources of the target hard disk occupied by the computing node when performing read and write operations on the to-be-operated data, as the read and write resources to be used.

The control system determines that when the computing node performs read and write operations of the data to be operated on the target hard disk, it needs to use the read and write resources of the target hard disk, that is, the read and write resources to be used.

Step 2: Remove the to-be-used read and write resources from the total read and write resources of the target hard disk to obtain the depth threshold.

The control system removes the read-write resources to be used based on the total read-write resources of the target hard disk, and uses the remaining resources as the depth threshold. For example, if the total bandwidth of the target hard disk is 100MB (MByte / Megabyte) / second, and the hard disk bandwidth required by the compute node to perform the read and write operations of the data request instruction is 20MB / second, then the depth threshold is 100-20 = 80MB / second .

In the implementation of this application, the depth threshold is determined according to the data to be operated, and the read and write resources of the hard disk can be fully utilized.

S105: If the token depth of the target hard disk is smaller than the depth threshold, change the operation state of the computing node for the target hard disk to an allowed state, and increase the token depth of the target hard disk according to a preset depth increase rule.

When the token depth of the target hard disk is less than the depth threshold, the operation status of the computing node for the target hard disk is changed from a non-permitted state to an allowed state, for example, the computing node holds the target hard disk token; at the same time, a rule is added according to a preset depth To increase the token depth of the target hard disk. The computing node whose operation status is allowed for the target hard disk can perform read and write operations on the target hard disk.

The preset depth increase rule may be: In a computing node whose operation status for the target hard disk is in a non-permitted state, each computing node changes the operation status of the target hard disk for the target hard disk to the allowed status, and the current token depth of the target hard disk The token depth occupied by the compute node is increased on the basis of. For example, when the token depth of the target hard disk is the number of compute nodes that are performing read and write operations on the target hard disk, it can be set as follows: for each compute node whose operation status for the target hard disk is not allowed, each When the node changes the permitted state of the operation status of the target hard disk, the node adds 1 to the current token depth of the target hard disk. For example, when the token depth is the bandwidth occupied by the target hard disk, it can be set: in a computing node whose operating status for the target hard disk is not allowed, each computing node changes the permitted status for the operating status of the target hard disk. In addition, the bandwidth occupied by the computing node is increased based on the current token depth of the target hard disk.

In the embodiment of the present application, it is determined whether the target hard disk can still allow access to the computing node according to the token depth of the target hard disk. When the token depth of the target hard disk is less than the depth threshold, the computing node is allowed to perform corresponding read and write operations on the target hard disk. It can realize that multiple computing nodes access one hard disk at the same time, which can improve the working efficiency of the computing nodes, thereby improving the overall operating efficiency of the network.

Optionally, after the judging the operation status of the computing node that requested the operation of the data to be operated on the target hard disk, the method further includes:

If the operation state of the computing node with respect to the target hard disk is an allowable state, the read and write operations of the data to be operated on the target hard disk are completed by the computing node.

If the operation status of the computing node for the target hard disk is allowed, for example, the computing node holds the token of the target hard disk, the computing node is allowed to perform read and write operations on the target hard disk.

In the embodiment of the present application, when the computing node is in the allowed operating state of the target hard disk, the computing node performs read and write operations on the target hard disk according to the data request instruction, so that multiple computing nodes can simultaneously access one hard disk, which can improve the computing node's performance. Work efficiency, thereby improving the overall operating efficiency of the network.

In order to reduce the unnecessary use of hard disks by computing nodes, the token depth of hard disks needs to be reduced. Optionally, the hard disk read-write control method in the embodiment of the present application further includes:

When the computing node satisfies a preset token release rule, the operating state of the computing node for the target hard disk is changed to a non-permitted state, and the token depth of the target hard disk is reduced according to a preset depth reduction rule.

The preset token release rules can be set according to actual needs. Optionally, the steps to determine whether the computing nodes meet the preset token release rules are as follows:

After the computing node completes the read and write operations on the target hard disk, or when the time when the computing node's operating state for the target hard disk is allowed to reach a preset time threshold, it is determined that the computing node satisfies a preset token release rule.

The preset time threshold can be set according to the actual situation, for example, it is set to 1 second, 5 seconds, or 10 seconds. When the computing node satisfies a preset token release rule, the operating state of the computing node for the target hard disk is changed to a non-permitted state, and the token depth of the target hard disk occupied by the computing node is released.

The preset depth reduction rule is a rule that arbitrarily reduces the token depth of the target hard disk. It can be set as follows: In a computing node whose operation status is allowed for the target hard disk, each computing node's operation status for the target hard disk is changed to In the non-permitted state, the token depth released by the compute node is subtracted from the current token depth of the target hard disk. For example, when the token depth of the target hard disk is the number of compute nodes that are performing read and write operations on the target hard disk, it can be set that: each of the compute nodes is When the operating status of the target hard disk is changed to a non-permitted state, it is reduced by 1 based on the current token depth of the target hard disk. For example, when the token depth is the bandwidth occupied by the target hard disk, you can set: In a computing node whose operating status for the target hard disk is allowed, each computing node's operating status for the target hard disk is changed to a non-allowed status. , Subtract the bandwidth occupied by the compute node from the current token depth of the target hard disk.

When the token depth of the target hard disk is stored in the local storage of the control system, the control system can directly modify the token depth of the target hard disk in the local storage, thereby reducing the token depth of the target hard disk. When the token depth of the target hard disk is stored on the storage management node of the target hard disk, the control system sends a token depth reduction instruction of the target hard disk to the storage management node of the target hard disk, so that the storage management node of the target hard disk follows the token depth. Reduce instructions to reduce the token depth of the target hard disk.

In the embodiment of the present application, when the computing node satisfies a preset token release rule, the operation state of the computing node for the target hard disk is changed to a non-permitted state, and the preset depth reduction rule is used to reduce the token depth of the target hard disk. The release of the hard disk token is guaranteed, thereby ensuring that new computing nodes have the opportunity to read and write to the target hard disk.

Optionally, after determining the magnitude relationship between the token depth of the target hard disk and the depth threshold, the method further includes:

In the embodiment of the present application, when the token depth of the target hard disk is not less than the depth threshold, the read / write operation of the target hard disk by the computing node is prohibited, thereby ensuring the bandwidth of the computing node which is performing read / write operations on the target hard disk.

The hard disk read-write control method in the embodiment of the present application can be implemented by a data storage system. Referring to FIG. 2a, the data storage system is a cluster distributed storage system, each computing resource of the computing nodes is distributed, and the data storage resources of the storage nodes are hard disks. It is also distributed. Through a single or multiple SAS switch network routes, each computing node can see each other, and each computing node can see each hard disk.

Compute nodes include: software-business application layer, software-IO flow management layer, software-SAS-HBA driver layer, hardware motherboard, and SAS-HBA card.

Software-business application layer: used to implement various computer application software, initiate data storage read and write requests, and initiate or respond to data communication requests.

Software-IO flow management layer: It is used to aggregate or split data from the software-business application layer, and send it to the software-SAS-HBA (Host Bus Adapter) driver layer after grouping, and the software- The data packet returned by the SAS-HBA driver is passed back to the software-business application layer.

Software-SAS-HBA driver layer: used as the initiator to send IO streams to the hard disk, or send the IO streams to the computing node of the destination; when acting as the destination, respond to the IO stream request sent by the computing node of the initiator, via The software-IO flow management layer of this computing node is passed to the software-business application layer of this computing node.

Hardware motherboard and SAS-HBA card: Specific hardware resources used to carry computing nodes, including hardware motherboard, processor, and SAS-HBA card.

SAS switch: It is a hardware device responsible for SASIO routing. Its software program records the SAS address routing table of all SAS devices in the data storage system of the embodiment of this application, which can implement SASIO switching.

SAS expander: It is a hardware device of a storage node and can be connected to multiple hard disks. The software program of the SAS expander records the SAS address routing table of all SAS devices in the data storage system in the embodiment of this application, and can control SASIO exchange.

The data storage system in the embodiment of the present application can not only realize data transmission between a computing node and a hard disk, but also data transmission between computing nodes, thereby realizing cluster communication. Distributed management is adopted for computing nodes. When some computing nodes are lost due to crashes and other reasons, other computing nodes do not need to switch data storage. They only need to take over the hard disk data storage resources managed by the lost nodes on average and use it to trigger the average. The amount of information that is taken over is small. Distributed management of hard disks. When the hard disk's resources are lost due to power failure and other reasons, in the case of redundancy, for example, computing nodes based on RAID (Redundant Arrays of Independent Disks) data redundancy backup Principle, reconstruct lost hard disk data to other hard disks, and enhance disaster recovery capabilities.

The above data storage system may also be shown in FIG. 2b. A plurality of computing nodes form a ring network. Adjacent computing nodes in the ring network communicate through a SAS switching unit, and the SAS switching unit of the computing node is connected to a SAS expander. Each computing node can see each other, and each computing node can see each hard disk.

Compute nodes include software-business application layer, software-IO flow management layer, software-SAS-HBA driver layer, hardware motherboard and SAS-HBA card, SAS switching unit; storage nodes include SAS expanders and hard disks.

Software-IO flow management layer: It is used to aggregate or split data from the software-business application layer, send it to the software-SAS-HBA driver layer after grouping, and send the data packets returned by the software-SAS-HBA driver. Back to the software-business application layer.

SAS switching unit: is a module responsible for SASIO routing. Its software program records the SAS address routing table of all SAS devices in the data storage system in the embodiment of this application, which can implement SASIO switching.

Based on the above data storage system, referring to FIG. 3, a hard disk read-write control method according to an embodiment of the present application includes:

S301. Obtain a data request instruction periodically.

For each compute node, the software-SAS-HBA driver layer of the compute node periodically queries the HBA queue. For example, the software-SAS-HBA driver layer polls the HBA queue every 10 milliseconds, and obtains from the HBA queue to be sent to Data request instruction for the target hard disk.

S302: Determine whether the computing node holds the token of the target hard disk. If the token of the target hard disk is held, execute S306; if the token of the target hard disk is not held, execute S303.

The software-SAS-HBA driver layer determines whether the compute node holds the token of the target hard disk.

S303. Send a token application request to the SAS switch where the target hard disk is located, so that the SAS expander where the target hard disk is located returns the current token depth of the target hard disk.

The software-SAS-HBA driver layer sends a token application request to the SAS expander where the target hard disk is located through a SAS-HBA card and a SAS switch. After receiving the token application request, the SAS expander returns the current token depth of the target hard disk to the computing node that sent the token application request.

S304. Determine the size of the current token depth and depth threshold of the target hard disk. If the current token depth of the target hard disk is less than the depth threshold, perform S305; otherwise, return to S301 to continue execution.

After the software-SAS-HBA driver layer of the compute node obtains the current token depth of the target hard disk, compare the current token depth of the target hard disk with the depth threshold. The depth threshold must be set to ensure that it can meet at least two calculations. Nodes access a hard disk at the same time. If the current token depth of the target hard disk is greater than or equal to the depth threshold, the data request instruction is not executed to read or write the target hard disk, and S301 is executed, that is, the data request instruction is reacquired in the next cycle.

S305. The token acquisition of the target hard disk is successful, and a token acquisition success instruction is returned to the SAS expander where the target hard disk is located, so that the SAS expander increases the token depth of the target hard disk according to the token acquisition success instruction.

When the current token depth of the target hard disk is less than the depth threshold, it is determined that the compute node successfully obtained the token of the target hard disk. The software-SAS-HBA driver layer sends the SAS expander where the target hard disk is located through the SAS-HBA card and SAS switch. The token acquisition success instruction, wherein the token acquisition success instruction signifies that the token acquisition of the target hard disk is successful. After receiving the token acquisition success instruction, the SAS expander increases the token depth of the target hard disk according to a preset depth increase rule, for example, increases the token depth of the target hard disk by one.

S306: Send a read / write instruction to the target hard disk to perform a read / write operation.

Software-SAS-HBA driver layer, through the SAS-HBA card and SAS switch, etc., sends read and write instructions to the target hard disk for read and write operations to complete the read and write operations on the target hard disk. The read and write instructions can be The data request instruction may be an instruction different from the data request instruction.

S307: Determine whether the computing node satisfies a preset token release rule, and if the preset token release rule is satisfied, execute S308.

It is determined whether the computing node satisfies a preset token release rule. If the preset token release rule is satisfied, S308 is performed, and if the preset token release rule is not satisfied, the process returns to S301. The preset token release rule can be set according to actual needs, for example, when the computing node completes reading and writing to the target hard disk, or when the computing node holds the token of the target hard disk for a preset time threshold, It is determined that the computing node satisfies a preset token release rule.

S308: Release the token of the target hard disk, and send a token release instruction to the SAS expander where the target hard disk is located, so that the SAS expander where the target hard disk is located can reduce the token depth of the target hard disk according to the token release instruction.

When the computing node meets the preset token release rules, the token of the target hard disk is released, so that the computing node no longer holds the token of the target hard disk. The software-SAS-HBA driver layer sends a token release instruction to the SAS expander where the target hard disk is located through a SAS-HBA card, a SAS switch, etc., where the token release instruction represents a token for releasing the target hard disk. After receiving the token release instruction, the SAS expander reduces the token depth of the target hard disk according to a preset depth reduction rule, for example, reduces the token depth of the target hard disk by one.

In the embodiment of the present application, by allocating a hard disk token to a computing node, multiple computing nodes can access a hard disk at the same time, which can improve the working efficiency of the computing node, thereby improving the overall operating efficiency of the network.

An embodiment of the present application further provides a hard disk read-write control device. Referring to FIG. 4, the device includes:

A hard disk determining module 401, configured to determine a target hard disk where the data to be operated is located;

A state determination module 402, configured to determine an operation state of the computing node requesting the operation of the data to be operated on the target hard disk;

The depth obtaining module 403 is configured to obtain the token depth of the target hard disk if the operation status of the computing node for the target hard disk is not allowed, wherein the token depth of the target hard disk is used to characterize that the target hard disk is occupied. Read and write resources;

A threshold determination module 404, configured to determine the magnitude relationship between the token depth of the target hard disk and the depth threshold;

The state calibration module 405 is configured to change the operation state of the computing node for the target hard disk to an allowed state if the token depth of the target hard disk is less than the depth threshold, and add a command for the target hard disk according to a preset depth increase rule. Card depth.

The operation permitting module is configured to complete the read / write operation of the data to be operated on the target hard disk by the computing node if the operation status of the computing node with respect to the target hard disk is allowed.

The deep release module is used to change the operation status of the computing node for the target hard disk to a non-permitted state when the computing node meets the preset token release rule, and reduce the order of the target hard disk according to the preset depth reduction rule. Card depth.

Optionally, in the hard disk read-write control device in the embodiment of the present application, the above-mentioned depth release module is specifically configured to:

After the computing node completes the read and write operations on the target hard disk, or when the time when the operation status of the computing node for the target hard disk is allowed to reach a preset time threshold, the operation status of the computing node for the target hard disk is changed The state is not allowed, and the depth of the token of the target hard disk is reduced according to the preset depth reduction rule.

A resource determining module, configured to determine the read and write resources of the target hard disk occupied by the computing node when the read and write operations are performed on the data to be operated, as the read and write resources to be used;

The threshold determination module is configured to remove the read-write resources to be used from the total read-write resources of the target hard disk to obtain the depth threshold.

An embodiment of the present application further provides an electronic device. Referring to FIG. 5, the electronic device includes a processor 501 and a memory 502.

The memory 502 is configured to store a computer program;

The processor 501 is configured to execute the following steps when executing a program stored in the memory 502:

Determine the target hard disk where the data to be operated is located;

Determine the operation status of the computing node requesting the operation of the data to be operated on the target hard disk;

Obtaining the token depth of the target hard disk if the operation status of the target hard disk for the target hard disk is not allowed, wherein the token depth of the target hard disk is used to represent the read and write resources occupied by the target hard disk;

Judging the relationship between the token depth of the target hard disk and the depth threshold;

If the token depth of the target hard disk is smaller than the depth threshold, the operation state of the computing node for the target hard disk is changed to an allowed state, and the token depth of the target hard disk is increased according to a preset depth increase rule.

Optionally, the electronic device in the embodiment of the present application further includes a communication interface and a communication bus, where the processor 501, the communication interface, and the memory 502 complete communication with each other through the communication bus.

Optionally, when the processor 501 is configured to execute a program stored in the memory 502, it can also implement any of the hard disk read-write control methods described above.

The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, the figure only uses a thick line, but it does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the aforementioned electronic device and other devices.

The memory may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the foregoing processor.

The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc .; it may also be a digital signal processor (Digital Signal Processing, DSP), special integration Circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

An embodiment of the present application further provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the following steps are implemented:

Determine the target hard disk where the data to be operated is located;

Optionally, when the computer program stored in the computer-readable storage medium is executed by a processor, any of the hard disk read-write control methods described above can also be implemented.

It should be noted that in this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations There is any such actual relationship or order among them. Moreover, the terms "including", "comprising", or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements but also those that are not explicitly listed Or other elements inherent to such a process, method, article, or device. Without more restrictions, the elements defined by the sentence "including a ..." do not exclude the existence of other identical elements in the process, method, article, or equipment that includes the elements.

Each embodiment in this specification is described in a related manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, refer to the description of the method embodiment.

The above are only preferred embodiments of this application, and are not intended to limit this application. Any modification, equivalent replacement, or improvement made within the spirit and principle of this application shall be included in this application Within the scope of protection.

Claims

A hard disk read-write control method, characterized in that the method includes:

Determine the target hard disk where the data to be operated is located;

Determine an operation state of a computing node requesting operation of the data to be operated with respect to the target hard disk;

Obtaining the token depth of the target hard disk if the operation status of the target hard disk for the target hard disk is a non-permitted state, wherein the token depth of the target hard disk is used to represent an occupied read in the target hard disk; Write resources

Determining a magnitude relationship between a token depth of the target hard disk and a depth threshold;

If the token depth of the target hard disk is less than the depth threshold, change the operation state of the computing node for the target hard disk to an allowed state, and increase the token depth of the target hard disk according to a preset depth increase rule. .
The method according to claim 1, wherein after the judging an operation state of the computing node that requested to operate the data to be operated on the target hard disk, the method further comprises:

If the operation state of the computing node with respect to the target hard disk is an allowed state, reading and writing operations to be performed on the target hard disk by the computing node are completed.
The method according to claim 1 or 2, further comprising:

When the computing node satisfies a preset token release rule, the operation state of the computing node for the target hard disk is changed to a non-permitted state, and the preset depth reduction rule is used to reduce the token depth of the target hard disk. .
The method according to claim 3, wherein the step of determining whether the computing node satisfies a preset token release rule is as follows:

Determining that the computing node satisfies a preset after the computing node completes a read-write operation on the target hard disk, or when the time when the operating state of the computing node for the target hard disk is in an allowed state reaches a preset time threshold Token release rules.
The method according to claim 1, wherein after determining a magnitude relationship between a token depth and a depth threshold of the target hard disk, the method further comprises:

If the token depth of the target hard disk is not less than the depth threshold, the computing node is prohibited from performing read and write operations on the target hard disk.
The method according to claim 1, wherein before the determining a magnitude relationship between a token depth and a depth threshold of the target hard disk, the method further comprises:

Determining that the read and write resources of the target hard disk occupied by the computing node when performing read and write operations on the data to be operated are used as read and write resources to be used;

The read and write resources to be used are removed from the total read and write resources of the target hard disk to obtain the depth threshold.
A hard disk read-write control device is characterized in that the device includes:

A hard disk determining module for determining a target hard disk where the data to be operated is located;

A state determination module, configured to determine an operation state of a computing node requesting operation of the data to be operated on the target hard disk;

A depth acquisition module, configured to obtain a token depth of the target hard disk if the operation status of the computing node for the target hard disk is not allowed, wherein the token depth of the target hard disk is used to characterize the target; Read and write resources occupied on the hard disk;

A threshold determination module, configured to determine a magnitude relationship between a token depth of the target hard disk and a depth threshold;

A state calibration module, configured to change the operation state of the computing node for the target hard disk to an allowed state if the token depth of the target hard disk is less than the depth threshold, and add the preset depth increase rule to increase the The token depth of the target hard disk.
The apparatus according to claim 7, further comprising:

An operation permission module is configured to complete the reading and writing of data to be operated on the target hard disk by the computing node if the operation status of the computing node for the target hard disk is allowed.
The device according to claim 7 or 8, wherein the device further comprises:

A deep release module is configured to change an operation state of the computing node for the target hard disk to a non-permitted state when the computing node meets a preset token release rule, and reduce the rule according to a preset depth reduction rule to reduce the The token depth of the target hard disk.
The device according to claim 9, wherein the depth release module is specifically configured to:

After the computing node completes the read and write operations on the target hard disk, or when the time when the operation status of the computing node for the target hard disk is allowed to reach a preset time threshold, the computing node is The operating state of the target hard disk is changed to a non-permitted state, and the token depth of the target hard disk is reduced according to a preset depth reduction rule.
The apparatus according to claim 7, further comprising:

An operation prohibition module is configured to prohibit the computing node from performing read and write operations on the target hard disk if the token depth of the target hard disk is not less than the depth threshold.
The apparatus according to claim 7, further comprising:

A resource determining module, configured to determine the read and write resources of the target hard disk occupied by the computing node when performing read and write operations on the data to be operated, as the read and write resources to be used;

A threshold determination module is configured to remove the read-write resources to be used from the total read-write resources of the target hard disk to obtain the depth threshold.
An electronic device, comprising a processor and a memory;

The memory is used to store a computer program;

The processor is configured to implement the method steps according to any one of claims 1-6 when executing a program stored in the memory.
A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method steps according to any one of claims 1-6 are implemented.