WO2020233001A1

WO2020233001A1 - Distributed storage system comprising dual-control architecture, data reading method and device, and storage medium

Info

Publication number: WO2020233001A1
Application number: PCT/CN2019/117349
Authority: WO
Inventors: 王新; 王欣
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-05-20
Filing date: 2019-11-12
Publication date: 2020-11-26
Also published as: CN110286852A

Abstract

The present invention relates to distributed storage techniques. Disclosed are a distributed storage system comprising a dual-control architecture, a data reading method and device, and a storage medium. In the present invention, each distributed storage node has a dual-control architecture, that is, each node is provided with two servers, being respectively a master server and a backup server. The two servers are configured to be in an active/passive (A/P) mode. When the master server is in an operating state, the backup server is in a standby state. A cluster resource manager is used to dynamically configure a same virtual IP address, that is, the two servers are presented as a same virtual node for a ceph system. Compared with the prior art, the dual control design of a storage node can avoid the copying of a large amount of data merely due to a server fault, and reduces the probability of a ceph system performing node data recovery.

Description

Double-control architecture distributed storage system, data reading method, device and storage medium

This application requires the priority of a Chinese patent application filed with the Chinese Patent Office on May 20, 2019, the application number is 201910418969.3, and the invention title is "Dual-control architecture distributed storage system, data reading method, device and storage medium". The entire content is incorporated into the application by reference.

Technical field

This application relates to the field of distributed storage technology, and in particular to a dual-control architecture distributed storage system, electronic device, data reading method, device, and computer-readable storage medium.

Background technique

CEPH distributed file system is a distributed storage system with large capacity, high performance and strong reliability. In the existing CEPH distributed system, multiple storage nodes are provided and multiple copies of data can be stored. In a system with this distributed structure, when a server (host) in a storage node fails, the data stored in the server is also inaccessible at the same time. At this time, the ceph system needs to restore the relevant data on this server before it can be accessed. It takes a long time to restore data on a server, which will affect the performance of the cluster. Especially with the current increase in the capacity of hard disks, a single disk can usually have a storage capacity of 6T or 8T, so the data stored on a server may be dozens of terabytes. The huge amount of data makes the above impact on the system more obvious.

When a server fails, many times the storage (disk) on the server is not actually damaged, and the data on the disk is still valid. Therefore, simply copying data is actually a relatively ineffective work. How to avoid copying large amounts of data It also becomes an urgent problem to make the system work normally.

Summary of the invention

The main purpose of this application is to provide a dual-control architecture distributed storage system, electronic device, data reading method, device, and computer-readable storage medium, aiming to adopt the dual-control design of storage nodes, in the case of only server failure Avoid copying large amounts of data and reduce the probability of node data recovery by the ceph system.

In order to achieve the above objective, this application proposes an electronic device which is respectively connected to the active server and the standby server of multiple distributed nodes in a distributed system, and the active server and the standby server in the same distributed node The servers are connected through a network. The main server in each distributed node is in working state, the standby server in each distributed node is in standby state, and each distributed node corresponds to a shared disk. The main server and the backup server are respectively connected to the same shared disk corresponding to the distributed node where they are located. The electronic device includes a memory and a processor. The memory stores a data reading program, and the data reading program is The processor implements the following steps when executing:

Initial access steps: real-time, or, timing, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently working in the distributed node to read the corresponding Data on the shared disk;

State conversion step: if the active server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state;

Data reading step: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.

In addition, in order to achieve the above-mentioned purpose, this application also proposes a data reading method. The electronic device is respectively communicatively connected with the active server and the standby server of multiple distributed nodes in the distributed system, and the main server in the same distributed node The server and the backup server are connected through a network. The main server in each distributed node is in working state, the backup server in each distributed node is in standby state, and each distributed node corresponds to a shared disk. The main server and the backup server in the distributed node are respectively connected to the same shared disk corresponding to the distributed node in communication, and the method includes the steps:

In addition, in order to achieve the above purpose, the present application also provides a distributed storage system, including electronic devices, multiple active servers of multiple distributed nodes, and multiple backup servers in communication connection, and the active server in the same distributed node It is connected to the standby server through a network, the active server in each distributed node is in working state, the standby server in each distributed node is in standby state, each distributed node corresponds to a shared disk, and the same distributed node The main server and the backup server are respectively in communication connection with the same shared disk corresponding to the distributed node where they are located. The electronic device includes a memory and a processor, and a data reading program is stored on the memory, and the data reading program When executed by the processor, the following steps are implemented:

In addition, in order to achieve the above-mentioned object, this application also provides a computer-readable storage medium that stores a data reading program, and the data reading program can be executed by at least one processor to enable all The at least one processor executes the steps of the data reading program method described in any one of the above.

Compared with the prior art, the dual-control architecture distributed storage system, electronic device, and computer-readable storage medium proposed in this application are designed with dual-control architecture at each distributed storage node, that is, equipped with two Two servers, respectively the active server and standby server. The two servers adopt A/P (Active/Passive) mode, the active server of the distributed node is in working state, and the standby server of the distributed node is in standby state. The same virtual IP address is dynamically configured through the cluster resource manager, that is, the two servers appear as the same virtual node to the entire ceph system. Two actual physical hosts (servers) can access the same shared storage hard disk in the same way in working mode. Under normal circumstances, the storage disk under the distributed node is taken over by the active server in a working state. The distributed system accesses the storage disk through the virtual IP address on the active server. When the active server in the working state of the server fails, the cluster resource manager switches the virtual IP address on the current active server to the standby server, and the standby server of the distributed node is switched to working state and can access the storage disk data. Since most of the data information on the current shared storage disk is still valid, for the ceph system, the above-mentioned access mode is equivalent to the short-term disconnection of the distributed storage node and then reconnection. Through the above-mentioned dual-control architecture design, the probability that the previous ceph system must recover large-scale data when the storage node fails can be greatly reduced. The system is also designed with a monitoring module that can monitor whether data is being written when the working status of the two servers is switched. If data is written during the period, it will detect the data version number and synchronize this part of the data information to the current Server in working state. At the same time, by manually shutting down a physical host, it is also possible to upgrade the storage node configuration (such as adding memory sticks) when the ceph system is online.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, without creative work, other drawings can be obtained based on the structure shown in these drawings.

Figure 1 is a schematic diagram of the system architecture of the first embodiment of the distributed storage system of this application;

Figure 2 is a schematic diagram of the storage distribution relationship of the distributed storage system of this application;

3 is a schematic diagram of the operating environment of the first embodiment of the data reading program of this application;

4 is a program module diagram of the first embodiment of the data reading program of this application;

FIG. 5 is a schematic flowchart of the first embodiment of the data reading program of this application.

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

The principles and features of the application are described below in conjunction with the accompanying drawings. The examples cited are only used to explain the application, and are not used to limit the scope of the application.

Refer to FIG. 1, which is a schematic diagram of the system architecture of the first embodiment of the distributed storage system of the present application.

In this embodiment, the distributed storage system includes multiple distributed storage nodes. Each distributed storage node has two physical hosts. In this application, the two physical hosts are a primary server and a backup server. The active server and the standby server in the distributed nodes are connected through a network, the active server in each distributed node is in working state, the standby server in each distributed node is in standby state, and each distributed node corresponds to For a shared disk, the active server and backup server in the same distributed node are respectively connected to the same shared disk corresponding to the distributed node, and the shared disk can be accessed in the same way.

In some application scenarios, an electronic device 1 is also provided in the distributed storage system, and the electronic device is in communication connection with the main server and the backup server in each distributed node (for example, communication connection via the network 2).

In some application scenarios, the above-mentioned electronic device 1 is set independently of the distributed storage system, and is in communication connection with the distributed storage system (for example, communication connection via the network 2).

Below, various embodiments of the present application will be proposed based on the above-mentioned distributed system and related equipment.

This application proposes a data reading program.

Please refer to FIG. 1, which is a schematic diagram of the system architecture of the first embodiment of the distributed storage system of this application.

In this embodiment, the data reading program 10 is installed and run in the electronic device 1. The electronic device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a server. The electronic device 1 may include, but is not limited to, a memory 11 and a processor 12 that communicate with each other through a program bus. FIG. 3 only shows the electronic device 1 with the components 11 and 12, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.

The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk or a memory of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, for example, a plug-in hard disk equipped on the electronic device 1, a smart media card (SMC), and a secure digital (SD) Card, Flash Card, etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 is used to store application software and various data installed in the electronic device 1, for example, the program code of the data writing program 10. The memory 11 can also be used to temporarily store data that has been output or will be output.

In some embodiments, the processor 12 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run program codes or process data stored in the memory 11, for example to perform data writing Procedure 10 etc.

Please refer to FIG. 4, which is a program module diagram of the first embodiment of the data reading program 10. In this embodiment, the data reading program 10 can be divided into one or more modules, one or more modules are stored in the memory 11, and are run by one or more processors (in this embodiment, the processor 12) Executed to complete this application. For example, in FIG. 4, the data reading program 10 can be divided into an initial access module 101, a state transition module 102, and a data reading module 103. The module referred to in this application refers to a series of computer program instruction segments that can complete specific functions, and is more suitable than a program to describe the execution process of the data reading program 10 in the electronic device 1, where:

Initial access module: real-time, or, timing, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently in working state in the distributed node to read the corresponding Data on the shared disk.

In a common distributed system, when a host (ie, a server) on a node fails, most of the time the storage disk communicating with the server is not actually damaged, and the data on the storage disk is still valid. If you can immediately start another server and take over the data at this time, and replace the broken faulty server, then for the entire distributed system, the node is still running normally, so there is no need for a large amount of data at this time Recovery, the entire system will naturally be restored to normal operation soon.

Refer to Figure 2, which is a schematic diagram of the storage distribution relationship of a distributed storage system.

As shown in Figure 2, in the CEPH dual-control architecture distributed system of this embodiment, each distributed node in the system is configured with two servers, and the two servers are in working and standby states respectively, according to the initial state The difference is that the two servers in node A serve as the active server (A1) and the standby server (A2) respectively in the working state, that is, A1 is in the working state at this time, and A2 is ready in the standby state. The primary server A1 and the backup server A2 are respectively connected to the same shared disk and can access the shared disk in the same way. Similarly, node B configures server B1 and server B2, and communicates with the shared disk. Among them, B1 is in working state and B2 is in standby state. Node C configures server C1 and server C2, and communicates with the shared disk. Among them, C1 is in working state and C2 is in standby state. When the distributed system in this embodiment accesses the distributed node A, the system will first access the active server A1 in the node A that is currently working.

State conversion module: if the main server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state.

Please refer to FIG. 3, which is a schematic diagram of the operating environment of the first embodiment of the data reading program.

As shown in FIG. 3, in this embodiment, although the main server A1 and the backup server A2 are in the working state and the standby state, respectively, they appear as node A for the entire system. When the system accesses the storage disk in the current node through the active server A1, when the active server is working normally and there is no failure, the active server A1 will directly access the storage disk connected to the communication, if the server A1 in the working state fails Can't access normally, originally in the standby state A2 will start the application process to start, and enter the working state from the standby state. Since the active server A1 and the standby server A2 appear to the system as the same node A, the switching of the working status between the active server A1 and the standby server A2 is equivalent to the node A being disconnected and connected again for a short time. , And at this time, the standby server A2 replaces the active server A1 and plays the role of node A in the system cluster.

Data reading module: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.

In this embodiment, in node A, due to a failure of the active server A1, the standby server A2 that has transitioned from the standby state to the working state reads the data on the shared disk of the communication connection. As mentioned above, the primary server A1 and the backup server A2 are respectively connected to the same shared disk in communication, and the two servers can access the shared disk in exactly the same way. When the main server A1 fails, the system accesses the shared disk through the standby server A2 that is converted to working state.

Preferably, in this embodiment, the program further includes a monitoring module (not shown in the figure), which is used to implement the following steps when performing the state transition step:

Writing detection step: if the main server in the distributed node fails and cannot be accessed, the monitoring module detects whether data is being written to the corresponding share through the main server in the distributed node Disk.

In this embodiment, the monitoring module in the Ceph distributed system can detect whether data is being written. When no data is being written, the distributed system can automatically end the subsequent steps after the write detection step.

Step of synchronizing data: if data is being written to the corresponding shared disk through the active server in the distributed node, after the standby server in the distributed node is successfully switched to the working state, the standby server The written data is written to the corresponding shared disk through the standby server in the distributed node.

In this embodiment, the distributed system can recover the data changes that may be written in the system during the state transition between the primary server A1 and the backup server A2. Therefore, the system is still in a normal operating state instead of the previous one. The deployment architecture takes a long time to recover a large amount of data, which affects the overall performance of the system. When the monitoring module detects that data is being written to the active server A1 when the active server A1 and the backup server A2 in the distributed node are in transition, the distributed system will resynchronize the written data To the standby server A2 in the distributed node that has been converted to a working state.

Preferably, in this embodiment, the same virtual address is configured on the active server and the standby server in the distributed node.

In this embodiment, by configuring the same virtual IP address for two servers in the same node, the active server A1 and the backup server A2 in the distributed node can behave as the same node A to the distributed system as a whole. The virtual IP address is dynamically configured on the active server A1 or the standby server A2 that is in the working state. For example, the virtual addresses of the two servers are both set to 160.1.0.0. When the two servers switch their working states, the overall performance of the distributed system is that the node is always working online, and no state transition or address transition occurs.

Preferably, through the configuration of the virtual address, the following steps are further implemented when the data reading program is executed by the processor:

Virtual access step: access the main server in the distributed node through the virtual address.

In this embodiment, the system accesses the current node A through the virtual address 160.1.0.0 configured by the primary server A1.

Address conversion step: when the active server in the distributed node fails, configure the virtual address configured on the active server in the distributed node to the standby server in the distributed node .

In this embodiment, when the active server A2 fails, the virtual address 160.1.0.0 originally configured on the active server A1 will be dynamically configured on the standby server A2, and the standby server A2 originally in the standby state will be converted to Working status.

Address access step: access the standby server in the distributed node through the virtual address.

In this embodiment, the system accesses the current node A through the virtual address 160.1.0.0 configured on the standby server A2 at this time.

In the above-mentioned access process, through the dynamic configuration of the same virtual address on the primary server and the backup server, when the primary server A1 fails, it does not affect the normal operation of the system, and the system is accessed through the server A2 at this time The current distributed node.

Preferably, the electronic device further has a cluster resource manager for configuring the virtual address.

In this embodiment, the configuration of the virtual IP address can be implemented by using pacemaker resource agent. For example, run the script Ocf::heartbeat::IPaddr2 in the current system. When the server A2 takes over from the server A1 and the working status is switched, implement a simple script Ocf::heartbeat::ceph to start the ceph related process, such as mon or osd can be used to dynamically configure the same virtual address on two servers.

In addition, in order to achieve the above object, this application also proposes a data reading method.

As shown in FIG. 5, FIG. 5 is a schematic flowchart of the first embodiment of the data reading method of this application.

The data reading method of this embodiment is applicable to electronic devices, which are respectively connected to the active server and the standby server of multiple distributed nodes in a distributed system, and the active server and the standby server in the same distributed node The main server in each distributed node is in working state, the standby server in each distributed node is in standby state, each distributed node corresponds to a shared disk, and the main server in the same distributed node is The server and the standby server are respectively connected to the same shared disk corresponding to the distributed node where they are located, and the method includes the steps:

Initial access step S10: real-time, or, at regular intervals, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently working in the distributed node to read The data on the corresponding shared disk.

As shown in Figure 3, in the CEPH dual-control architecture distributed system of this embodiment, each distributed node in the system is configured with two servers, and the two servers are in working state and standby state, according to the difference of initial state , The two servers in node A respectively serve as the active server (A1) and the standby server (A2) in the working state, that is, at this time, A1 is in the working state, and A2 is ready in the standby state. The primary server A1 and the backup server A2 are respectively connected to the same shared disk and can access the shared disk in the same way. Similarly, node B configures server B1 and server B2, and communicates with the shared disk. Among them, B1 is in working state and B2 is in standby state. Node C configures server C1 and server C2, and communicates with the shared disk. Among them, C1 is in working state and C2 is in standby state. When the distributed system in this embodiment accesses the distributed node A, the system will first access the active server A1 in the node A that is currently working.

State conversion step S20: If the main server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state.

In this embodiment, although the primary server A1 and the backup server A2 are in the working state and the standby state, respectively, they appear as node A for the entire system. When the system accesses the storage disks in the current node through the active server A1, when the active server is working normally and there is no failure, the active server A1 will directly access the storage disk connected to the communication, if the server A1 in the working state fails Can't access normally, originally in the standby state A2 will start the application process to start, and enter the working state from the standby state. Since the active server A1 and the standby server A2 appear to the system as the same node A, the switching of the working status between the active server A1 and the standby server A2 is equivalent to the node A being disconnected and connected again for a short time. , And at this time, the standby server A2 replaces the active server A1 and plays the role of node A in the system cluster.

Data reading step S30: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.

Preferably, in the data reading method, in the state transition step, the method further includes:

Writing detection step: if the main server in the distributed node fails and cannot be accessed, the monitoring unit detects whether data is being written to the corresponding share through the main server in the distributed node Disk.

In this embodiment, the distributed system can recover the data changes that may be written in the system during the state transition between the primary server A1 and the backup server A2. Therefore, the system is still in a normal operating state instead of the previous one. The deployment architecture takes a long time to recover a large amount of data, which affects the overall performance of the system. When the monitoring module detects that data is written to the active server A1 when the active server A1 and the standby server A2 are in the transition state, the distributed system will resynchronize the written data to the standby server that is converted to the operating state. Server A2.

Preferably, in the data reading method, the method further includes: configuring the same virtual address on the active server and the standby server in the distributed node.

Preferably, in the data reading method, the method further includes the following steps:

Access the main server in the distributed node through the virtual address.

When the main server in the distributed node fails, the virtual address configured on the main server in the distributed node is configured to the standby server in the distributed node.

Access the standby server in the distributed node through the virtual address.

Preferably, the distributed storage system further has a cluster resource manager for configuring the virtual address.

In this embodiment, the configuration of the virtual IP address can be implemented by using pacemaker resource agent.

In addition, in order to achieve the above purpose, this application also provides a distributed storage system,

The distributed storage system includes electronic devices, multiple primary servers and multiple backup servers of multiple distributed nodes in communication connection. The primary servers and backup servers in the same distributed node are connected through a network. The active server in the node is in working state, the standby server in each distributed node is in standby state, each distributed node corresponds to a shared disk, and the active server and standby server in the same distributed node are respectively distributed The same shared disk communication connection corresponding to the mode node, the electronic device includes a memory and a processor, the memory stores a data reading program, and the data reading program is executed by the processor to implement the following steps:

In addition, an embodiment of the present application also proposes a computer-readable storage medium that stores a data reading program, and the data reading program can be executed by at least one processor, so that the at least one The processor executes the data reading method in any of the foregoing embodiments.

Compared with the prior art, the dual-control architecture distributed storage system, electronic device, and computer-readable storage medium proposed in this embodiment are designed with dual-control architecture at each distributed storage node, that is, equipped with two Servers are the active server and standby server respectively. The two servers adopt the A/P (Active/Passive) mode, the active server of the distributed node is in a working state, and the standby server of the distributed node is in a standby state. The same virtual IP address is dynamically configured through the cluster resource manager, that is, the two servers appear as the same virtual node to the entire ceph system. Two actual physical hosts (servers) can access the same shared storage hard disk in the same way in working mode. Under normal circumstances, the storage disk under the distributed node is taken over by the active server in a working state. The distributed system accesses the storage disk through the virtual IP address on the active server. When the active server in the working state of the server fails, the cluster resource manager switches the virtual IP address on the current active server to the standby server, and the standby server of the distributed node is switched to working state and can access the storage disk data. Since most of the data information on the current shared storage disk is still valid, for the ceph system, the above-mentioned access mode is equivalent to the short-term disconnection of the distributed storage node and then reconnection. Through the above-mentioned dual-control architecture design, the probability that the previous ceph system must recover large-scale data when the storage node fails can be greatly reduced. This embodiment is also designed with a monitoring module that can monitor whether data is being written when the working status of the two servers is switched. If data is written during the period, the data version number will be detected and this part of the data information will be synchronized to The server that is currently working. At the same time, by manually shutting down a physical host, it is also possible to upgrade the storage node configuration (such as adding memory modules) when the ceph system is online.

It should be noted that in this article, the terms "including", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, It also includes other elements that are not explicitly listed, or elements inherent to the process, device, article, or method. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, device, article or method that includes the element.

The serial numbers of the foregoing embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. Through the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only preferred embodiments of this application, and do not limit the scope of this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of this application, or directly or indirectly used in other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims

An electronic device, characterized in that the electronic device is respectively connected to the main server and the backup server of a plurality of distributed nodes in a distributed system, and the main server and the backup server in the same distributed node are connected through a network Connection, the active server in each distributed node is in working state, the standby server in each distributed node is in standby state, each distributed node corresponds to a shared disk, the active server and standby in the same distributed node The servers are respectively in communication connection with the same shared disk corresponding to the distributed node where they are located, the electronic device includes a memory and a processor, the memory stores a data reading program, and the data reading program is implemented when the processor is executed The following steps:

Initial access steps: real-time, or, timing, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently working in the distributed node to read the corresponding Data on the shared disk;

State conversion step: if the active server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state;

Data reading step: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.
5. The electronic device according to claim 1, wherein the electronic device is also in communication connection with a monitoring unit in the distributed system, and the data reading program further implements the following steps when being executed by the processor:

Writing detection step: if the main server in the distributed node fails and cannot be accessed, the monitoring unit detects whether data is being written to the corresponding share through the main server in the distributed node Disk

Step of synchronizing data: If data is being written to the corresponding shared disk through the active server in the distributed node, after the backup server in the distributed node is successfully switched to the working state, the data to be written The data of is written into the corresponding shared disk through the standby server in the distributed node.
3. The electronic device according to claim 2, wherein the active server and the standby server in the distributed node dynamically configure the same virtual address, and the data reading program further implements the following steps when being executed by the processor:

Access the primary server in the distributed node through the virtual address;

When the active server in the distributed node fails, configure the virtual address configured on the active server in the distributed node to the standby server in the distributed node;

Access the standby server in the distributed node through the virtual address.
The electronic device according to claim 3, wherein the electronic device is also in communication connection with a cluster resource manager in the distributed system for the active server and the backup in the distributed node The same virtual address is configured on the server.
5. The electronic device of claim 1, wherein after the backup server in the distributed node is successfully switched to a working state, the backup server in the distributed node is accessed to read the corresponding The data on the shared disk includes:

The active server and the standby server are respectively connected to the same shared disk in communication, and the two servers respectively access the shared disk in the same manner. When the active server fails, the standby server is converted to a working state to access the shared disk. Share the disk to read the data.
A data reading method suitable for electronic devices, characterized in that the electronic devices are respectively connected to the main server and the backup server of multiple distributed nodes in a distributed system, and the main server in the same distributed node It is connected to the standby server through a network, the active server in each distributed node is in working state, the standby server in each distributed node is in standby state, each distributed node corresponds to a shared disk, and the same distributed node The main server and the standby server in the, are respectively connected to the same shared disk corresponding to the distributed node where they are located, and the method includes the steps:

Initial access steps: real-time, or, timing, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently working in the distributed node to read the corresponding Data on the shared disk;

State conversion step: if the active server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state;

Data reading step: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.
8. The data reading method according to claim 6, wherein in the state transition step, the method further comprises:

Writing detection step: if the main server in the distributed node fails and cannot be accessed, the monitoring unit detects whether data is being written to the corresponding shared disk through the main server in the distributed node;

Step of synchronizing data: If data is being written to the corresponding shared disk through the active server in the distributed node, after the backup server in the distributed node is successfully switched to the working state, the data to be written The data of is written into the corresponding shared disk through the standby server in the distributed node.
The data reading method according to claim 6 or 7, wherein the method further comprises: configuring the same virtual address on the active server and the standby server in the distributed node.
9. The data reading method according to claim 8, wherein the method further comprises the following steps:

Access the primary server in the distributed node through the virtual address;

When the active server in the distributed node fails, configure the virtual address configured on the active server in the distributed node to the standby server in the distributed node;

Access the standby server in the distributed node through the virtual address.
The data reading method according to claim 6, wherein after the backup server in the distributed node is successfully switched to the working state, the backup server in the distributed node is accessed to read The data on the corresponding shared disk includes:

The active server and the standby server are respectively connected to the same shared disk in communication, and the two servers respectively access the shared disk in the same manner. When the active server fails, the standby server is converted to a working state to access the shared disk. Share the disk to read the data.
A distributed storage system, characterized in that the distributed storage system includes electronic devices, multiple primary servers of multiple distributed nodes and multiple backup servers in communication connection, and the primary server in the same distributed node and The backup servers are connected through a network, the active server in each distributed node is in working state, the backup server in each distributed node is in standby state, each distributed node corresponds to a shared disk, and the same distributed node The main server and the backup server are respectively in communication connection with the same shared disk corresponding to the distributed node where they are located, the electronic device includes a memory and a processor, and a data reading program is stored on the memory, and the data reading program is The processor implements the following steps when executing:

Initial access steps: real-time, or, timing, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently working in the distributed node to read the corresponding Data on the shared disk;

State conversion step: if the active server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state;

Data reading step: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.
11. The distributed storage system of claim 11, wherein in the state transition step, the distributed storage system further comprises:

Writing detection step: if the main server in the distributed node fails and cannot be accessed, the monitoring unit detects whether data is being written to the corresponding shared disk through the main server in the distributed node;

Step of synchronizing data: If data is being written to the corresponding shared disk through the active server in the distributed node, after the backup server in the distributed node is successfully switched to the working state, the data to be written The data of is written into the corresponding shared disk through the standby server in the distributed node.
The distributed storage system according to claim 11 or 12, wherein the distributed storage system further comprises:

The same virtual address is configured on the active server and the standby server in the distributed node.
13. The distributed storage system of claim 13, wherein the distributed storage system further comprises the following steps:

Access the primary server in the distributed node through the virtual address;

When the active server in the distributed node fails, configure the virtual address configured on the active server in the distributed node to the standby server in the distributed node;

Access the standby server in the distributed node through the virtual address.
The distributed storage system of claim 11, wherein after the backup server in the distributed node is successfully switched to the working state, the backup server in the distributed node is accessed to read The data on the corresponding shared disk includes:

The active server and the standby server are respectively connected to the same shared disk in communication, and the two servers respectively access the shared disk in the same manner. When the active server fails, the standby server is converted to a working state to access the shared disk. Share the disk to read the data.
A computer-readable storage medium, wherein the computer-readable storage medium stores a data reading program, and the data reading program can be executed by at least one processor, so that the at least one processor executes the following The steps of the data reading program method:

Initial access steps: real-time, or, timing, or, after receiving an instruction to read data from the main server of a distributed node, access the main server currently working in the distributed node to read the corresponding Data on the shared disk;

State conversion step: if the active server in the distributed node fails and cannot be accessed, the standby server in the distributed node currently in the standby state is switched to the working state;

Data reading step: After the backup server in the distributed node is successfully switched to the working state, access the backup server in the distributed node to read the data on the corresponding shared disk.
16. The computer-readable storage medium of claim 16, wherein in the state transition step, the computer-readable storage medium further comprises:

Writing detection step: if the main server in the distributed node fails and cannot be accessed, the monitoring unit detects whether data is being written to the corresponding shared disk through the main server in the distributed node;

Step of synchronizing data: If data is being written to the corresponding shared disk through the active server in the distributed node, after the backup server in the distributed node is successfully switched to the working state, the data to be written The data of is written into the corresponding shared disk through the standby server in the distributed node.
18. The computer-readable storage medium of claim 16 or 17, wherein the computer-readable storage medium further comprises:

The same virtual address is configured on the active server and the standby server in the distributed node.
18. The computer-readable storage medium of claim 18, wherein the computer-readable storage medium further comprises the following steps:

Access the primary server in the distributed node through the virtual address;

When the active server in the distributed node fails, configure the virtual address configured on the active server in the distributed node to the standby server in the distributed node;

Access the standby server in the distributed node through the virtual address.
The computer-readable storage medium according to claim 16, wherein after the backup server in the distributed node is successfully switched to the working state, the backup server in the distributed node is accessed to Reading the data on the corresponding shared disk includes:

The active server and the standby server are respectively connected to the same shared disk in communication, and the two servers respectively access the shared disk in the same manner. When the active server fails, the standby server is converted to a working state to access the shared disk. Share the disk to read the data.