CN115145782A - A server switching method, MooseFS system and storage medium - Google Patents

Abstract

The embodiment of the present application discloses a server switching method, a MooseFS system and a storage medium. The MooseFS system includes: a main server, a backup server, and a cluster monitoring module, and the server switching method includes: when the backup server monitors that the main server is running abnormally, sending a message to the cluster The monitoring module sends a query request; wherein, the query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein, the first service information represents the actual running state of the main server; the cluster monitoring module Send a query response to the backup server; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. The server switching method proposed in the present application can prevent the active and standby nodes in the MooseFS system from competing for resources, and realize the high availability of the MooseFS system.

Description

A server switching method, MooseFS system and storage medium

technical field

The invention relates to the technical field of distributed storage, in particular to a server switching method, a MooseFS system and a storage medium.

Background technique

Distributed storage refers to a storage cluster formed by connecting multiple single machines, which can combine the storage and read-write capabilities of all machines. The MooseFS system is a distributed file system. By storing files in the cluster, it solves the problem of limited storage capacity of a single machine, and at the same time solves the limitation of the throughput of a single machine itself through network media, and the multi-copy mechanism ensures data security. , and the system is easy to expand.

Dynamic replacement of IP (Ucarp) is a Linux implementation of the Common Access Redundancy Protocol (CARP). Ucarp allows the main server and other servers to share a virtual Internet Protocol (Internet Protocol, IP) address, and when the main server In the event of a failure, other servers will automatically take over from the primary server to provide services to the cluster.

However, in practical applications, there is usually a misjudgment that the main server is faulty. At this time, the main server is still running normally and provides services to the cluster, but Ucarp decides that other servers should replace the main server to provide services to the cluster, so that other servers can provide services to the cluster. Competing with the main server for resources, which causes the state of the MooseFS system to be chaotic and data corruption.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a server switching method, a MooseFS system and a storage medium, which can avoid the problems that the active and standby nodes in the MooseFS system compete for resources, causing the state of the MooseFS system to be chaotic and data corrupt, thereby effectively realizing the high availability of the MooseFS system. .

The technical solutions of the embodiments of the present application are implemented as follows:

In a first aspect, an embodiment of the present application provides a server switching method, and the method is applied to a MooseFS system, wherein the MooseFS system includes: a main server, a backup server, and a cluster monitoring module, and the method includes:

When the backup server monitors that the primary server is running abnormally, it sends a query request to the cluster monitoring module; wherein, the query request carries the identification information of the primary server;

The cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein, the first service information represents the actual running state of the main server;

The cluster monitoring module sends a query response to the backup server; wherein, the query response carries the first service information;

The primary server and the backup server determine whether to perform server switching according to the first service information.

In a second aspect, an embodiment of the present application provides a MooseFS system, wherein the MooseFS system includes: a main server, a backup server, and a cluster monitoring module, wherein:

The main server is used to manage the MooseFS system and perform data transmission with the data node;

the backup server, configured to monitor the running state of the primary server and save the metadata in the primary server;

The cluster monitoring module is used for monitoring the actual running status of the main server and the data node.

In a third aspect, an embodiment of the present application provides a MooseFS system, where the MooseFS system includes: a primary server, a backup server, and a cluster monitoring module, the MooseFS system further includes a processor, a processor that stores executable instructions of the processor The memory, when the instructions are executed by the processor, implements the server switching method as described above.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a program is stored and applied in a MooseFS system, where the MooseFS system includes: a main server, a backup server, and a cluster monitoring module, characterized in that: When the program is executed by the processor, the server switching method as described above is implemented.

The embodiment of the present application provides a server switching method, a MooseFS system and a storage medium. The MooseFS system includes a main server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is abnormally running, it sends a query request to the cluster monitoring module; The query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server ; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. That is to say, in the embodiment of the present application, when the backup server in the MooseFS system determines that the current state of the main server is abnormal, it does not directly perform the server switching process, but first obtains the first server corresponding to the main server through the cluster monitoring module. The first service information determines the actual running state of the main server, and then determines whether to perform server switching processing. It can be seen that if there is an abnormal situation such as a communication interruption between the active and standby nodes during the process of the master node's normal management of the entire MooseFS system, the MooseFS system can monitor the active and standby nodes through the cluster monitoring module to prevent the standby nodes from The state of the master node is misjudged and competes for resources and services, thereby avoiding state confusion and data corruption in the MooseFS system, ensuring the high availability of the MooseFS system.

Description of drawings

1 is a schematic diagram of the composition structure of the MooseFS system proposed by the embodiment of the present application;

FIG. 2 is a schematic diagram 1 of the implementation flow of the server switching method proposed by the embodiment of the present application

FIG. 3 is a second implementation flowchart of the server switching method proposed by the embodiment of the present application;

FIG. 4 is a schematic diagram 2 of the composition structure of the MooseFS system proposed by the embodiment of the present application;

FIG. 5 is a schematic diagram 3 of the implementation flow of the server switching method proposed by the embodiment of the present application;

FIG. 6 is a fourth schematic diagram of the implementation flow of the server switching method proposed by the embodiment of the present application;

FIG. 7 is a schematic diagram three of the composition structure of the MooseFS system proposed in the embodiment of the present application;

FIG. 8 is a schematic diagram five of the implementation flow of the server switching method proposed by the embodiment of the present application;

FIG. 9 is a sixth schematic flowchart of the implementation of the server switching method proposed by the embodiment of the present application;

FIG. 10 is a schematic diagram 7 of the implementation flow of the server switching method proposed by the embodiment of the present application;

FIG. 11 is a schematic diagram eight of the implementation flow of the server switching method proposed by the embodiment of the application;

FIG. 12 is a fourth schematic diagram of the composition and structure of the MooseFS system proposed by the embodiment of the application;

13 is a schematic diagram five of the composition and structure of the MooseFS system proposed by the embodiment of the application;

FIG. 14 is a sixth schematic diagram of the composition and structure of the MooseFS system proposed by the embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to explain the related application, but not to limit the application. In addition, it should be noted that, for the convenience of description, only the parts related to the relevant application are shown in the drawings.

At present, with the development of Internet technology and the gradual deepening of various information systems, new data sources continue to emerge, the amount of business data is gradually increasing, and the demand for unstructured file storage has increased significantly. However, traditional centralized storage usually adopts high-end storage such as Storage Area Network (SAN) and Network Attached Storage (NAS) to cope with the explosive growth of data, because the space and capacity of such storage cannot be arbitrarily Expansion and upgrading of equipment require high monetary cost, and there are disadvantages such as low storage efficiency, insufficient horizontal expansion function, poor load balancing ability, and low concurrent access performance. The introduction of distributed storage can well solve the problems of traditional SAN, NAS and other storage. the problem.

The MooseFS system is a distributed file system that allocates and stores files through the client that comes with the MooseFS system, instead of the traditional way of directly storing local disks. However, the overall failure rate of the MooseFS system is relatively high, and there may be a split-brain problem caused by abnormal conditions such as the communication between the main and standby nodes, which will cause the state of the MooseFS system to be chaotic and data corruption. In order to ensure that the MooseFS system faces the above exceptions It is a technical problem that needs to be solved urgently in order to continuously provide services to users and improve the overall high availability of the MooseFS system without loss of important data.

In order to solve the problems existing in the existing MooseFS system, the embodiments of the present application provide a server switching method, a MooseFS system and a storage medium, and make script adjustments based on the MooseFS 3.0 mechanism. Specifically, the MooseFS system includes a primary server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is running abnormally, it sends a query request to the cluster monitoring module; wherein, the query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; The service information represents the actual running state of the primary server; the cluster monitoring module sends a query response to the backup server; the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. This prevents the standby node from misjudging the status of the master node in the case of abnormal network communication, and the competition for resources and services will cause a split-brain problem, thereby preventing the state of the MooseFS system from being chaotic and data corrupted. High availability of MooseFS system.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

Example 1

An embodiment of the present application provides a server switching method. The server switching method is applied to the MooseFS system. FIG. 1 is a schematic diagram 1 of the composition and structure of the MooseFS system. As shown in FIG. 1 , the MooseFS system 10 may include a main server 11 and a backup server. 12 and the cluster monitoring module 13.

In the embodiment of the present application, the main server 11 is responsible for maintaining the namespace of the entire MooseFS system 10 and exposing it to users for data transmission with multiple data nodes, and managing the entire MooseFS system 10 .

The backup server 12 is connected to the primary server 11, and can perform a master-standby switchover when the primary server fails, taking over the work of the primary server 11, and the backup server 12 can synchronize the metadata of the primary server 11 in real time, using Rsync and Sersync architecture, synchronization Changed files or directories not only have a high transmission rate, but also achieve real-time synchronization and backup of metadata.

The cluster monitoring module 13 is used to monitor the main server 11 and the backup server 12. Through real-time monitoring of the main server and the backup server, it can prevent some abnormal situations, such as the situation of communication failure, the backup server will make a misjudgment of the status of the main server , mistakenly believe that the main server is faulty at this time, and the competition for resources and services causes a split-brain problem, thereby achieving the effect of preventing the state of the MooseFS system 10 from being chaotic and data corrupted.

An embodiment of the present application provides a server switching method, and FIG. 2 is a schematic diagram 1 of the implementation flow of the server switching method proposed by the embodiment of the present application. As shown in FIG. 2 , in the embodiment of the present application, the server switching method may include the following step:

Step 101: When the backup server monitors that the primary server is abnormally running, it sends a query request to the cluster monitoring module, wherein the query request carries the identification information of the primary server.

In the embodiment of the present application, the backup server in the MooseFS system can first monitor the main server in real time based on the heartbeat monitoring mechanism. When the backup server determines that the current state of the main server is abnormal based on the heartbeat monitoring mechanism, the backup server will report to the cluster monitoring module. To request to query the current state of the master server, that is, to send a query request to the cluster monitoring module, wherein the query request carries the identification information of the master server.

It should be noted that, in the embodiment of the present application, the backup server regularly sends heartbeat packets to the main server based on the heartbeat monitoring mechanism, and receives feedback information. If the sent heartbeat packets do not receive feedback information within the preset time, it is determined that The current status of the master server is abnormal. Further, a query request is sent to the cluster monitoring module, wherein the query request carries the identification information of the main server.

In this embodiment of the present application, the query request may be used to obtain the service status of the primary server. Specifically, when the backup server does not receive the feedback information within the preset time and judges that the current state of the primary server is abnormal, the backup server requests the cluster monitoring module to send the monitored first service information of the primary server, and then the backup server can send the first service information of the primary server monitored by the backup server. The received first service information specifies the service status of the primary server.

In the embodiment of the present application, the identification information can be used to represent the identity information of the main server, and further, the cluster monitoring module can determine the corresponding main server according to the identification information sent by the backup server in the service information of all nodes acquired and stored by the cluster monitoring module. the first service information. The setting method of the identification information is not specifically limited in this application.

It should be noted that since the monitoring of the master server by the backup server based on the heartbeat monitoring mechanism may cause misjudgment due to the interruption of communication between the master and the backup server, when the backup server determines that the master server may be faulty at this time, it needs to report to the cluster monitoring module. Send a query request to clarify the real status of the primary server at this time, instead of performing the primary-standby switchover directly based on fault judgment.

Step 102: The cluster monitoring module determines the first service information corresponding to the master server according to the identification information; wherein the first service information represents the actual running state of the master server.

In the embodiment of the present application, when the backup server determines that the current state of the main server is abnormal based on the heartbeat monitoring mechanism, the backup server sends a query request to the cluster monitoring module, and the cluster monitoring module in the MooseFS system receives the After the query request carrying the identification information, the first service information of the main server may be further determined according to the identification information.

In the embodiment of the present application, the first service information of the main server may be the first service information obtained by monitoring the main server by the cluster monitoring module, and is the first service information generated according to all services running on the main server, which represents In addition to the current status information obtained by the backup server monitoring the primary server, another kind of service status information obtained by monitoring the primary server by the cluster monitoring module located at the upper layer of the backup server is the first service information. The first service information is used for Indicates the actual operational status of the master server.

Exemplarily, in the embodiment of the present application, when the cluster monitoring module determines the first service information corresponding to the main server according to the identification information, the cluster monitoring module can always monitor the service status of the main server, and at the same time store the information according to the identification information. For the first service information, when the cluster monitoring module receives the query request sent by the backup server, it can locate the corresponding first service information pre-stored in the cluster monitoring module according to the identification information carried in the query request; The first state information of the primary server at this time may be directly queried according to the identification information without storing the first service information in advance.

Exemplarily, in the embodiment of the present application, when the cluster monitoring module determines the first service information corresponding to the main server according to the identification information, the cluster monitoring module may monitor the main server to obtain the first service information, and then according to the first service information information to determine the service status of the main server, especially when the backup server makes a fault judgment on the current service status of the main server, it is necessary to make a more objective judgment and comparison of the service status of the main server according to the first service information sent by the cluster monitoring module. Sure.

Step 103: The cluster monitoring module sends a query response to the backup server, where the query response carries the first service information.

In the embodiment of the present application, after determining the first service information corresponding to the primary server according to the identification information, the cluster monitoring module responds to the query request sent by the backup server, and sends a query response carrying the first service information to the backup server, so that the backup server can Acquire the first service information of the master server monitored by the cluster monitoring module.

Step 104: The primary server and the backup server determine whether to perform server switching according to the first service information.

In the embodiment of the present application, after the cluster monitoring module sends a query response to the backup server, the primary server and the backup server determine whether to perform server switching according to the first service information.

In the embodiment of the present application, server switching refers to switching between the backup server and the primary server, and using the backup server to take over the work of the primary server, thereby providing services for the system.

It should be noted that, since the first service information represents the actual operating state of the primary server, the primary server and the backup server can determine whether the server needs to perform server switching based on the first service information. Then, server switching is performed, and the backup server takes over the work of the main server. If it is determined according to the first service information that server switching is not necessary, server switching is not performed.

FIG. 3 is a second implementation flowchart of the server switching method proposed by the embodiment of the present application. As shown in FIG. 3 , in the embodiment of the present application, the primary server and the backup server determine whether to perform server switching according to the first service information, that is, Step 104 may include the following steps:

Step 104a: If the first service information received by the backup server is normal, the primary server and the backup server do not perform server switching processing.

In the embodiment of the present application, the primary server and the backup server determine whether to perform server switching according to the first service information. If the backup server determines that the first service information of the primary server is normal at this time, the primary server and the backup server do not execute the server switch. Switch processing.

In the embodiment of the present application, if the first service information obtained by the backup server is normal, it means that the backup server may have misjudged the current service status of the primary server, that is, the primary server is not faulty. The communication between the backup servers is blocked, and the backup server does not receive the information returned by the primary server, which causes the backup server to mistakenly think that the status of the primary server is abnormal. Therefore, according to the obtained first service information, the backup server can determine that the primary server is in a normal operating state, so that the primary server and the backup server do not perform server switching processing, which avoids system confusion due to a split-brain problem caused by communication failure. The problem of data loss ensures the high availability of the MooseFS system.

In the embodiment of the present application, when the primary server is temporarily unresponsive due to an excessively high load, that is, when the primary service is suspended, it will also cause the backup server to judge that the primary server is down, resulting in a misjudgment, which may cause brain damage. cracking problem. The specific fault information is not limited in this application.

Step 104b: If the first service information received by the backup server is abnormal, the primary server and the backup server perform server switching processing.

In this embodiment of the present application, the cluster monitoring module sends a query response to the backup server, wherein the query response carries the first service information. If the query response received by the backup server shows that the first service information is abnormal, it indicates that the primary server is currently If the status is indeed abnormal, the primary server and the backup server perform server switching processing, and the backup server takes over the work of the primary server, thereby reducing the fault processing time of the MooseFS system and ensuring the high availability of the MooseFS system.

The embodiment of the present application provides a server switching method, a MooseFS system and a storage medium. The MooseFS system includes a main server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is abnormally running, it sends a query request to the cluster monitoring module; The query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server ; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. That is to say, in the embodiment of the present application, when the backup server in the MooseFS system determines that the current state of the main server is abnormal, it does not directly perform the server switching process, but first obtains the first server corresponding to the main server through the cluster monitoring module. The first service information determines the actual running state of the main server, and then determines whether to perform server switching processing. It can be seen that if there is an abnormal situation such as a communication interruption between the active and standby nodes during the process of the master node's normal management of the entire MooseFS system, the MooseFS system can monitor the active and standby nodes through the cluster monitoring module to prevent the standby nodes from The state of the master node is misjudged and competes for resources and services, thereby avoiding state confusion and data corruption in the MooseFS system, ensuring the high availability of the MooseFS system.

Embodiment 2

Based on the above-mentioned first embodiment, in yet another embodiment of the present application, FIG. 4 is a second schematic diagram of the composition and structure of the MooseFS system. As shown in FIG. 4 , the cluster monitoring module 13 in the MooseFS system 10 may include a service monitoring sub-module 131, Threshold monitoring sub-module 132 , information storage sub-module 133 , and global monitoring sub-module 134 .

FIG. 5 is a schematic diagram 3 of the implementation flow of the server switching method proposed by the embodiment of the present application. As shown in FIG. 5 , the method for the cluster monitoring module to determine the first service information corresponding to the main server according to the identification information includes the following steps:

Step 102a, the service monitoring sub-module monitors the service status of the main server based on the heartbeat monitoring mechanism, and obtains at least one service information corresponding to at least one service; wherein, one service corresponds to one service information.

It should be noted that, in the embodiment of this application, at least one service of the main server may include at least one of multiple services, such as the storage heartbeat information service, the MooseFS system operation log storage service, and the MooseFS system data node service. Specific restrictions.

Step 102b: If at least one service information is normal, determine that the first service information is normal.

Step 102c: If any one of the at least one service information is abnormal, determine that the first service information is abnormal.

Exemplarily, in this application, if the service monitoring sub-module monitors the storage heartbeat information service of the main server, the MooseFS system operation log storage service, and the MooseFS system data node service are all normal, it is considered that the first server of the main server at this time. Service information is normal.

Further, in the embodiment of the present application, the information storage sub-module in the cluster monitoring module may receive the heartbeat monitoring file corresponding to the main server sent by the service monitoring submodule, and store the heartbeat monitoring file.

It should be noted that, in the embodiment of the present application, the information storage sub-module stores heartbeat monitoring files, ie service heartbeat related information, in a pre-established shared directory, and the information storage sub-module serves the service monitoring sub-module.

FIG. 6 is a fourth schematic flowchart of the implementation process of the server switching method proposed by the embodiment of the application. As shown in FIG. 6 , the method for the cluster monitoring module to determine the first service information corresponding to the main server according to the identification information further includes the following steps:

Step 102d, the cluster monitoring module acquires the heartbeat monitoring file corresponding to the main server stored in the information storage sub-module.

In the embodiment of the present application, the information storage sub-module receives the heartbeat monitoring file corresponding to the main server sent by the service monitoring submodule, and stores the heartbeat monitoring file. When the cluster monitoring module needs to obtain the heartbeat monitoring file, it can obtain the heartbeat monitoring file from the information storage submodule.

Step 102e: The cluster monitoring module performs verification processing according to the heartbeat maintenance file and the heartbeat monitoring file to obtain a verification result.

In the embodiment of the present application, after the cluster monitoring module obtains the heartbeat monitoring file, it can perform verification processing according to the heartbeat maintenance file and the heartbeat monitoring file, and obtain the verification result.

It should be noted that, in the embodiment of the present application, the heartbeat maintenance file is the heartbeat information of the primary server obtained by the backup server based on the heartbeat monitoring mechanism.

It should be noted that, in the embodiment of the present application, the heartbeat monitoring file is the heartbeat monitoring information corresponding to the main server obtained by the service monitoring sub-module in the cluster monitoring module.

Step 102f: If the verification result is that the verification is successful, it is determined that the first service information corresponding to the primary server is normal.

Step 102g, if the verification result is that the verification fails, determine that the first service information corresponding to the primary server is abnormal.

In the embodiment of the present application, the cluster monitoring module performs verification processing according to the heartbeat maintenance file and the heartbeat monitoring file, and if the verification result is that the verification is successful, it is determined that the first service information of the main server is normal; if the verification result is If the verification fails, it is determined that the first service information corresponding to the primary server is abnormal.

In the embodiment of the present application, the verification is successful means that after comparing or verifying the heartbeat maintenance file and the heartbeat monitoring file, it is found that the heartbeat monitoring file shows that the first service information of the main server is normal, and it can be determined that the heartbeat maintenance file has The abnormal status of the main server displayed may cause misjudgment. The main server should be in normal service status at this time, and the result is that the verification is successful; the verification failure refers to the comparison or verification of the heartbeat maintenance file and the heartbeat monitoring file. If it is found that the heartbeat monitoring file shows that the first service information of the main server is abnormal, it can be determined that the main server is indeed abnormal at this time, that is, the result is that the verification fails.

The embodiment of the present application provides a server switching method, a MooseFS system and a storage medium. The MooseFS system includes a main server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is abnormally running, it sends a query request to the cluster monitoring module; The query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server ; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. That is to say, in the embodiment of the present application, when the backup server in the MooseFS system determines that the current state of the main server is abnormal, it does not directly perform the server switching process, but first obtains the first server corresponding to the main server through the cluster monitoring module. The first service information determines the actual running state of the main server, and then determines whether to perform server switching processing. It can be seen that if there is an abnormal situation such as a communication interruption between the active and standby nodes during the process of the master node's normal management of the entire MooseFS system, the MooseFS system can monitor the active and standby nodes through the cluster monitoring module to prevent the standby nodes from The state of the master node is misjudged and competes for resources and services, thereby avoiding state confusion and data corruption in the MooseFS system, ensuring the high availability of the MooseFS system.

Embodiment 3

Based on the first and second embodiments above, in another embodiment of the present application, FIG. 7 is a third schematic diagram of the composition and structure of the MooseFS system method proposed in the embodiment of the present application. As shown in FIG. 7 , the MooseFS system 10 further includes a data node 14 .

It should be noted that, in the embodiment of the present application, the MooseFS system may further include a plurality of data nodes 14 for providing a storage service of real file data.

FIG. 8 is a schematic diagram 5 of the implementation flow of the server switching method proposed by the embodiment of the present application. As shown in FIG. 8 , in the embodiment of the present application, the server switching method may include the following steps:

Step 201: The service monitoring sub-module monitors the data nodes based on the heartbeat monitoring mechanism, and obtains second service information corresponding to the data nodes.

In the embodiment of this application, the MooseFS system further includes multiple data nodes, and the service monitoring sub-module also monitors multiple data nodes in the system at the same time, and obtains the second service information of the multiple data nodes, the second service information Represents the service status of a data node.

It should be noted that, in the embodiment of the present application, the data node can use the dual network card binding technology, which can not only improve the network transmission speed, but also ensure that when one of the network cards fails, normal and efficient work can still be achieved. Exemplarily, when one network card of a certain data node fails, the other one immediately takes over the entire load, so that the service is not interrupted, and waits for the maintenance personnel to perform subsequent maintenance, thereby ensuring the normal use of the entire system.

Step 202: If the second service information is suspended, execute the service pulling process, and re-monitor the data node to obtain the updated second service information.

Step 203: If the second service information is suspended after the update, perform alarm processing.

In the embodiment of the present application, the service monitoring sub-module monitors the data nodes based on the heartbeat monitoring mechanism, and after obtaining the second service information corresponding to the data nodes, if the second service status is found to be suspended, the second service is started. ; If the status of the second service is that it cannot be started again, an alarm will be processed.

In the embodiment of the present application, if the second service information is suspended, the service pulling process is performed, and the data node is re-monitored to obtain the updated second service information; if the updated second service information is suspended, then Perform alarm processing.

Further, in the embodiment of the present application, the information storage sub-module in the cluster monitoring module may receive the second service information corresponding to the data node sent by the service monitoring sub-module, and store the second service information.

In the embodiment of the present application, after the service monitoring sub-module monitors the data nodes based on the heartbeat monitoring mechanism, and obtains and processes the second service information corresponding to the data nodes, the information storage sub-module is further configured to monitor the second service information of the data nodes. Service information is stored.

The embodiment of the present application provides a server switching method, a MooseFS system and a storage medium. The MooseFS system includes a main server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is abnormally running, it sends a query request to the cluster monitoring module; The query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server ; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. That is to say, in the embodiment of the present application, when the backup server in the MooseFS system determines that the current state of the main server is abnormal, it does not directly perform the server switching process, but first obtains the first server corresponding to the main server through the cluster monitoring module. The first service information determines the actual running state of the main server, and then determines whether to perform server switching processing. It can be seen that if there is an abnormal situation such as a communication interruption between the active and standby nodes during the process of the master node's normal management of the entire MooseFS system, the MooseFS system can monitor the active and standby nodes through the cluster monitoring module to prevent the standby nodes from The state of the master node is misjudged and competes for resources and services, thereby avoiding state confusion and data corruption in the MooseFS system, ensuring the high availability of the MooseFS system.

Embodiment 4

Based on the above-mentioned first to third embodiments, in another embodiment of the present application, FIG. 9 is a sixth schematic flowchart of the implementation of the server switching method proposed by the embodiment of the present application. As shown in FIG. 9 , in the embodiment of the present application, the server The switching method may further include the following steps:

Step 301: The threshold monitoring sub-module acquires the first state parameter corresponding to the primary server.

In the embodiment of the present application, the threshold monitoring sub-module may acquire the first state parameter corresponding to the main server.

It should be noted that, in the embodiment of the present application, the first state parameter is the running state parameter of the main server, which may include the central processing unit (Central Processing Unit, CPU) usage rate, memory usage rate, input/output ratio corresponding to the main server There are various parameters that characterize the running state, such as an output (Input/Output, I/O) access rate and a disk storage rate, which are not specifically limited in this application.

Step 302: If the first state parameter is greater than the first preset state threshold, perform alarm processing; wherein the first state parameter is used to monitor the running state of the main server.

In the embodiment of the present application, after acquiring the first state parameter corresponding to the main server, the threshold monitoring sub-module can compare the first state parameter with the first preset state threshold, so that further processing can be performed according to the comparison result.

Specifically, in this application, after obtaining the first state parameter corresponding to the main server, the threshold monitoring sub-module compares the first state parameter with the first preset threshold, if the first state parameter is greater than the first preset state threshold , then alarm processing is performed; wherein, the first state parameter is used to monitor the running state of the main server.

In the embodiment of the present application, the first preset threshold is a value preset according to the operating parameter of the main server, and is used to monitor the operating state of the main server. When the first state parameter is greater than the first preset state threshold , it indicates that the running status of the main server may be overloaded at this time, alarm and notify the cluster administrator to carry out timely maintenance, so as to avoid the failure of the main server, which will cause the chaos of the MooseFS system and the loss of data, which has reached MooseFS. The effect of high system availability.

FIG. 10 is a seventh schematic flowchart of the implementation of the server switching method proposed by the embodiment of the present application. As shown in FIG. 10 , in the embodiment of the present application, the server switching method may further include the following steps:

Step 303: The threshold monitoring sub-module acquires the second state parameter corresponding to the data node.

In the embodiment of the present application, the second state parameter is the operating state parameter of each data node, which may include various representations of the operating state, such as the CPU usage rate, memory usage rate, I/O access rate, and disk storage rate corresponding to the data node. parameters, which are not specifically limited in this application.

Step 304: If the second state parameter is greater than the second preset state threshold, perform alarm processing; wherein the second state parameter is used to monitor the running state of the data node.

In the embodiment of the present application, after the threshold monitoring sub-module acquires the second state parameter corresponding to the data node, if the second state parameter is greater than the second preset state threshold, an alarm processing is performed; wherein the second state parameter is used for Monitor the running status of data nodes.

In the embodiment of the present application, the second preset state threshold is a value preset according to the operation parameter of the data node, and is used to monitor the operation state of the data node. When the second state parameter is greater than the second preset state threshold When the data node is overloaded, it indicates that the running state of the data node may be overloaded, and an alarm is issued to notify the cluster administrator to perform timely maintenance, so as to avoid the failure of the data node and increase the load of the remaining data nodes, which may cause the data nodes to fail. downtime, thus achieving high availability of data nodes.

It should be noted that the first state parameter and the second state parameter are the operating state parameters of the main server and the data node respectively, and represent the operating states of the main server and the data node respectively; the first preset state threshold and the second preset state threshold The values are preset values for the running states of the main server and the data nodes, respectively, and are used for early warning of the running states of the main server and the data nodes.

FIG. 11 is a schematic diagram 8 of the implementation flow of the server switching method proposed by the embodiment of the present application. As shown in FIG. 11 , in the embodiment of the present application, the server switching method may further include the following steps:

Step 305: The global monitoring submodule monitors the service monitoring submodule, the threshold monitoring submodule, and the information storage submodule, and obtains the first service process corresponding to the service monitoring submodule, the second service process corresponding to the threshold monitoring submodule, and the information storage. The third service process corresponding to the submodule.

In the embodiment of the present application, the global monitoring sub-module is a sub-module in the cluster monitoring module, and is used to provide services to the remaining three sub-modules in the cluster monitoring module: the service monitoring sub-module, the threshold monitoring sub-module and the information storage sub-module Monitoring on the process to ensure that the service process of the service monitoring sub-module, the threshold monitoring sub-module and the information storage sub-module can maintain a normal state and achieve high availability of the cluster monitoring module.

Step 306: If any one of the first service process, the second service process, and the third service process is abnormal, perform alarm processing to ensure high availability of the cluster monitoring module.

In the embodiment of the present application, the global monitoring sub-module monitors the service monitoring sub-module, the threshold monitoring sub-module and the information storage sub-module, and obtains the first service process corresponding to the service monitoring sub-module and the first service process corresponding to the threshold monitoring sub-module. After the second service process and the third service process corresponding to the information storage sub-module, if any one of the first service process, the second service process and the third service process is abnormal, an alarm process is performed.

In the embodiment of the present application, the first service process, the second service process, and the third service process are monitored by the global monitoring module. When the process is abnormal, an alarm is issued for the abnormal situation, and the cluster management personnel are notified to perform maintenance. , to ensure the high availability of the cluster monitoring module.

FIG. 12 is a fourth schematic diagram of the composition and structure of the MooseFS system proposed by the embodiment of the present application. As shown in FIG. 12 , in the embodiment of the present application, the MooseFS system may include a main server, a backup server, a data node, a switch, a cluster monitoring module and client application.

In the embodiment of the present application, the active and standby high-availability modules are composed of the main server and the backup server, and the high-availability function between the main and backup servers is mainly realized by Ucarp and virtual IP technology, and the virtual IP technology provides between applications and data nodes. A floating access point, which does not affect the connection and interaction between applications and data nodes when switching between active and standby.

In the embodiment of the present application, the backup server can synchronize the metadata of the main server in real time, using the Rsync and Sersync architecture, Sersync records a certain file or a certain directory name that has any changes in the monitored directory, and Rsync is responsible for real-time transmission of files, In this way, under the combination of Rsync and Sersync architecture, the changed files or directories can be synchronized, not only the transmission rate is high, but also the purpose of real-time synchronization and backup of metadata can be achieved, which can effectively prevent the failure of the metadata synchronization mechanism of the primary and backup servers. The backup server has an issue with metadata loss.

In the embodiment of the present application, the switch is used to connect to the server, and assist the server to complete the work of data receiving and forwarding. The switch in this application uses dual network cards, so that the failure of any switch will not affect the normal use of the system and improve the availability of the switch.

In the embodiment of the present application, the data node uses the dual network card binding technology, which can not only improve the network transmission speed, but also ensure that when one of the network cards fails, normal and efficient work can still be achieved. Exemplarily, when one network card of a certain data node fails, the other one immediately takes over the entire load, so that the service is not interrupted, and waits for the maintenance personnel to perform subsequent maintenance, thereby ensuring the normal use of the entire system.

In the embodiment of the present application, the cluster monitoring module includes a service monitoring sub-module, a threshold monitoring sub-module, an information storage sub-module, and a global monitoring sub-module. The cluster monitoring module is used to monitor the main server, backup server and data nodes to achieve the overall high availability of the MooseFS system.

The embodiment of the present application provides a server switching method, a MooseFS system and a storage medium. The MooseFS system includes a main server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is abnormally running, it sends a query request to the cluster monitoring module; The query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server ; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. That is to say, in the embodiment of the present application, when the backup server in the MooseFS system determines that the current state of the main server is abnormal, it does not directly perform the server switching process, but first obtains the first server corresponding to the main server through the cluster monitoring module. The first service information determines the actual running state of the main server, and then determines whether to perform server switching processing. It can be seen that if there is an abnormal situation such as a communication interruption between the active and standby nodes during the process of the master node's normal management of the entire MooseFS system, the MooseFS system can monitor the active and standby nodes through the cluster monitoring module to prevent the standby nodes from The state of the master node is misjudged and competes for resources and services, thereby avoiding state confusion and data corruption in the MooseFS system, ensuring the high availability of the MooseFS system.

Embodiment 5

Based on the server switching methods provided in the foregoing embodiments 1 to 4, as shown in the aforementioned FIG. 1 , an embodiment of the present application provides a MooseFS system 10, including: a primary server 11, a backup server 12, and a cluster monitoring module 13, wherein:

The main server is used to manage the MooseFS system and perform data transmission with the data node;

the backup server, configured to monitor the running state of the primary server and save the metadata in the primary server;

The cluster monitoring module is used for monitoring the actual running status of the main server and the data node.

FIG. 13 is a fifth structural diagram of the MooseFS system proposed by the embodiment of the present application. As shown in FIG. 13 , the MooseFS system 10 proposed by the embodiment of the present application includes a sending unit 15 , a determining unit 16 and an executing unit 17 .

The sending unit 15 is configured to send a query request to the cluster monitoring module when the backup server monitors that the primary server runs abnormally; wherein the query request carries the identification information of the primary server.

The determining unit 16 is used for the cluster monitoring module to determine the first service information corresponding to the main server according to the identification information; wherein, the first service information represents the actual running state of the main server.

Further, the sending unit 15 is further configured for the cluster monitoring module to send a query response to the backup server, wherein the query response carries the first service information.

The determining unit 16 is further configured for the primary server and the backup server to determine whether to perform server switching according to the first service information.

The execution unit 17 is configured to, if the first service information is normal, the primary server and the backup server do not perform server switching processing.

Further, the executing unit 17 is further configured to execute server switching processing on the primary server and the backup server if the first service information is abnormal.

In the embodiments of the present application, further, as shown in FIG. 13 , the MooseFS system proposed in the embodiments of the present application may further include: an acquisition unit 18 .

The obtaining unit 18 is used for the node service monitoring sub-module to monitor the service state of the main server based on the heartbeat monitoring mechanism, and obtain at least one service state corresponding to at least one service.

Further, in the embodiment of the present application, the determining unit 16 is specifically configured to determine that the current service state is normal if at least one service state is normal; if any one of the at least one service state is abnormal, then Determines that the current service status is abnormal.

In the embodiment of the present application, further, as shown in FIG. 13 , the MooseFS system proposed in the embodiment of the present application may further include: an alarm unit 19 .

The alarm unit 19 is configured to perform alarm processing if the first state parameter is greater than the first preset state threshold; wherein the first state parameter is used to monitor the motion state of the main server.

Further, in the embodiment of the present application, the obtaining unit 18 is further configured to obtain the first state parameter corresponding to the main server by the threshold monitoring sub-module.

In the embodiments of the present application, further, as shown in FIG. 13 , the MooseFS system proposed in the embodiments of the present application may further include: a receiving unit 110 and a storage unit 111 .

The receiving unit 110 is used for the information storage sub-module to receive the first service information corresponding to the main server sent by the service monitoring sub-module.

The storage unit 111 is configured to store the first service information.

Further, in the embodiment of the present application, the obtaining unit 18 is also used for the cluster monitoring module to obtain the first service information of the main server stored by the information storage sub-module; the cluster monitoring module performs calibration according to the heartbeat maintenance file and the first service information. The verification process is performed to obtain the verification result.

Further, in the embodiment of the present application, the determining unit 16 is further configured to determine that the current service status of the main server is normal if the verification result is that the verification is successful; and determine that the main server is the main server if the verification result is that the verification fails. The corresponding first service information is abnormal.

In the embodiments of the present application, further, as shown in FIG. 13 , the MooseFS system proposed in the embodiments of the present application may further include: a monitoring unit 112 .

The monitoring unit 112 is used for the global monitoring sub-module to monitor the service monitoring sub-module, the threshold monitoring sub-module and the information storage sub-module, and obtain the first service process corresponding to the service monitoring sub-module and the second service process corresponding to the threshold monitoring sub-module , and the third service process corresponding to the information storage submodule.

Further, in the embodiment of the present application, the alarm unit 19 is further configured to perform alarm processing if any one of the first service process, the second service process and the third service process is abnormal.

Further, in the embodiment of the present application, the obtaining unit 18 is further configured for the service monitoring sub-module to monitor the data node based on the heartbeat monitoring mechanism, and obtain the second service information corresponding to the data node.

Further, in the embodiment of the present application, the execution unit 17 is further configured to start the second service if the second service status is suspended; and perform alarm processing if the second service status cannot be restarted.

Further, in the embodiment of the present application, the obtaining unit 18 is further configured to obtain the second state parameter of the data node by the threshold monitoring sub-module.

Further, in the embodiment of the present application, the execution unit 17 is further configured to perform alarm processing if the second state parameter is greater than the second preset state threshold.

Further, in the embodiment of the present application, the receiving unit 110 is further configured for the information storage sub-module to receive the second service information corresponding to the data node sent by the service monitoring sub-module.

Further, in the embodiment of the present application, the storage unit 111 is further configured to store the second service information.

FIG. 14 is a schematic diagram 6 of the composition and structure of the MooseFS system proposed by the embodiment of the present application. As shown in FIG. 14 , the MooseFS system proposed by the present application further includes a processor 113 , a memory 114 storing executable instructions of the processor 113 , and a communication interface 115 , and a bus 116 for connecting the processor 113 , the memory 114 and the communication interface 115 .

In the embodiments of the present application, the processor 113 may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), or a digital signal processing device (DSPD). At least one of a programmable logic device (ProgRAMmable Logic Device, PLD), a field programmable gate array (Field ProgRAMmable GateArray, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, and a microprocessor A sort of. It can be understood that, for different devices, the electronic device used to implement the above processor function may also be other, which is not specifically limited in the embodiment of the present application. It can also include a memory 114, which can be connected to the processor 113, wherein the memory 114 is used to store executable program codes, which include computer operation instructions. The memory 114 may include high-speed RAM memory, and may also include non-volatile memory. Volatile memory, for example, at least two disk drives.

In the embodiment of the present application, the bus 116 is used to connect the communication interface 115 , the processor 113 and the memory 114 and the mutual communication among these devices.

In the embodiment of the present application, the memory 114 is used to store instructions and data.

Further, in the embodiment of the present application, the above-mentioned processor 113 is configured to send a query request to the cluster monitoring module when the backup server monitors that the main server is running abnormally; wherein, the query request carries the identification information of the main server; the cluster monitoring The module determines the first service information corresponding to the main server according to the identification information; wherein, the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server; wherein, the query response carries the first service information; the main server and the backup server determines whether to perform server switching according to the first service information.

In practical applications, the above-mentioned memory 114 may be a volatile memory (volatile memory), such as a random-access memory (Random-Access Memory, RAM); or a non-volatile memory (non-volatile memory), such as a read-only memory ( Read-Only Memory, ROM), flash memory (flash memory), hard disk (Hard Disk Drive, HDD) or solid-state drive (Solid-State Drive, SSD); or a combination of the above types of memory, and provide the processor 111 with instructions and data.

In addition, each functional module in this embodiment may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of software function modules.

If the integrated unit is implemented in the form of software function modules and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment is essentially or correct. Part of the contribution made by the prior art or all or part of the technical solution can be embodied in the form of a software product, the computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal A computer, a server, or a network device, etc.) or a processor (processor) executes all or part of the steps of the method in this embodiment. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (Read Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes.

The embodiment of the present application provides a server switching method, a MooseFS system and a storage medium. The MooseFS system includes a main server, a backup server, and a cluster monitoring module. When the backup server monitors that the main server is abnormally running, it sends a query request to the cluster monitoring module; The query request carries the identification information of the main server; the cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein the first service information represents the actual running state of the main server; the cluster monitoring module sends a query response to the backup server ; wherein, the query response carries the first service information; the primary server and the backup server determine whether to perform server switching according to the first service information. That is to say, in the embodiment of the present application, when the backup server in the MooseFS system determines that the current state of the main server is abnormal, it does not directly perform the server switching process, but first obtains the first server corresponding to the main server through the cluster monitoring module. The first service information determines the actual running state of the main server, and then determines whether to perform server switching processing. It can be seen that if there is an abnormal situation such as a communication interruption between the active and standby nodes during the process of the master node's normal management of the entire MooseFS system, the MooseFS system can monitor the active and standby nodes through the cluster monitoring module to prevent the standby nodes from The state of the master node is misjudged and competes for resources and services, thereby avoiding state confusion and data corruption in the MooseFS system, ensuring the high availability of the MooseFS system.

The embodiments of the present application provide a first computer-readable storage medium, on which a program is stored, and when the program is executed by the first processor, the methods according to Embodiments 1 to 4 are implemented.

Specifically, a program instruction corresponding to a server switching method in this embodiment may be stored on a storage medium such as an optical disc, a hard disk, a U disk, etc. When the program instruction corresponding to a server switching method in the storage medium is When the electronic device reads or is executed, it includes the following steps:

When the backup server monitors that the primary server is running abnormally, it sends a query request to the cluster monitoring module; wherein, the query request carries the identification information of the primary server;

The cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein, the first service information represents the actual running state of the main server;

The cluster monitoring module sends a query response to the backup server; wherein, the query response carries the first service information;

The primary server and the backup server determine whether to perform server switching according to the first service information.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, optical storage, and the like.

The present application is described with reference to schematic flowcharts and/or block diagrams of implementations of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It will be understood that each process and/or block in the schematic flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the schematic flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a process or processes and/or a block or blocks in the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions An apparatus implements the functions specified in a flow or flows of the implementation flow diagram and/or a block or blocks of the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the implementing flow diagram and/or the block or blocks of the block diagram.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the protection scope of the present application.

Claims (11)

1. a server switching method, it is characterized in that, described server switching method is applied to distributed file system MooseFS system, described MooseFS system comprises: main server, backup server and cluster monitoring module, described method comprises: When the backup server monitors that the primary server is running abnormally, it sends a query request to the cluster monitoring module; wherein, the query request carries the identification information of the primary server; The cluster monitoring module determines the first service information corresponding to the main server according to the identification information; wherein, the first service information represents the actual running state of the main server; The cluster monitoring module sends a query response to the backup server; wherein, the query response carries the first service information; The primary server and the backup server determine whether to perform server switching according to the first service information. 2. The method according to claim 1, wherein the primary server and the backup server determine whether to perform server switching according to the first service information, comprising: If the first service information received by the backup server is normal, the primary server and the backup server do not perform server switching processing; If the first service information received by the backup server is abnormal, the primary server and the backup server perform server switching processing. 3 . The method according to claim 1 , wherein the cluster monitoring module comprises: a service monitoring sub-module, and the cluster monitoring module determines the first service information corresponding to the main server according to the identification information, comprising: 3 . : The service monitoring submodule performs service status monitoring on the main server based on the heartbeat monitoring mechanism, and obtains at least one service information corresponding to at least one service; wherein, one service corresponds to one service information; If the at least one service information is normal, determining that the first service information is normal; If any one of the at least one service information is abnormal, it is determined that the first service information is abnormal. 4. The method according to claim 3, wherein the cluster monitoring module further comprises: a threshold monitoring sub-module, and the method further comprises: The threshold monitoring sub-module acquires the first state parameter corresponding to the main server; If the first state parameter is greater than the first preset state threshold, alarm processing is performed; wherein, the first state parameter is used to monitor the running state of the main server. 5. The method according to claim 4, wherein the cluster monitoring module further comprises: an information storage sub-module, and the method further comprises: The information storage submodule receives the heartbeat monitoring file corresponding to the main server sent by the service monitoring submodule, and stores the heartbeat monitoring file. 6. The method according to claim 5, wherein the query request also carries a heartbeat maintenance file of the main server, and the cluster monitoring module determines the first service corresponding to the main server according to the identification information information, including: The cluster monitoring module obtains the heartbeat monitoring file corresponding to the main server stored by the information storage sub-module; The cluster monitoring module performs verification processing according to the heartbeat maintenance file and the heartbeat monitoring file to obtain a verification result; If the verification result is that the verification is successful, it is determined that the first service information corresponding to the primary server is normal; If the verification result is a verification failure, it is determined that the first service information corresponding to the primary server is abnormal. 7. The method according to claim 6, wherein the cluster monitoring module further comprises: a global monitoring sub-module, and the method further comprises: The global monitoring sub-module monitors the service monitoring sub-module, the threshold monitoring sub-module and the information storage sub-module, and obtains the first service process and the threshold monitoring sub-module corresponding to the service monitoring sub-module a corresponding second service process and a third service process corresponding to the information storage submodule; If any one of the first service process, the second service process, and the third service process is abnormal, alarm processing is performed to ensure high availability of the cluster monitoring module. 8. The method according to claim 3, wherein the MooseFS system further comprises: a data node, and the method further comprises: The service monitoring sub-module monitors the data node based on a heartbeat monitoring mechanism, and obtains second service information corresponding to the data node; If the second service information is suspended, execute the service pulling process, and re-monitor the data node to obtain the updated second service information; If the updated second service information is discontinued, an alarm process is performed. 9. A MooseFS system, characterized in that the MooseFS system comprises: a main server, a backup server and a cluster monitoring module, wherein, The main server is used to manage the MooseFS system and perform data transmission with the data nodes; the backup server, configured to monitor the running state of the primary server and save the metadata in the primary server; The cluster monitoring module is used for monitoring the actual running status of the main server and the data node. 10. A MooseFS system, characterized in that the MooseFS system comprises: a main server, a backup server and a cluster monitoring module, the MooseFS system further comprises a processor, a memory storing executable instructions of the processor, and when all When the instructions are executed by the processor, the method according to any one of claims 1-8 is implemented. 11. A computer-readable storage medium on which a program is stored, applied in the MooseFS system, the MooseFS system comprising: a main server, a backup server and a cluster monitoring module, it is characterized in that, when the program is executed by the processor , implementing the method according to any one of claims 1-8.

Images