CN111930502A - Server management method, device, equipment and storage medium - Google Patents

Abstract

Embodiments of the present invention disclose a server management method, apparatus, device and storage medium. The method includes: acquiring the number of queued tasks and the number of idle servers in the computer cluster; judging whether the number of queued tasks is greater than a preset task number threshold, and whether the number of idle servers is less than the preset number of servers; The target available server is obtained from the list, and the target idle server is controlled to perform the boot operation; the available servers in the bootable server list are the servers that were successfully shut down in the automatic shutdown process. The embodiment of the present invention can dynamically apply for resources according to the current computing task of the computer cluster, automatically start the server, ensure the timely processing of computing tasks, maintain the power consumption of the entire cluster at a level suitable for computing tasks, and avoid resource waste.

Description

A server management method, device, device and storage medium

technical field

Embodiments of the present invention relate to the field of computer technologies, and in particular, to a server management method, apparatus, device, and storage medium.

Background technique

In a computer cluster, there are usually multiple servers that make up the computing resources. Computer clusters increase computing power by distributing computing tasks to different servers in the cluster.

In the related art, servers in a computer cluster are generally turned on and off uniformly. After all servers are turned on, they remain on. If the server obtains the assigned computing task, it executes the corresponding computing operation. If the server does not obtain a computing task, it remains on and waits for a task to be assigned.

During the actual operation of the computer cluster, the utilization rate of the computer cluster changes dynamically. There may be times when the computer cluster is underutilized, and at other times, resources are under strain due to the surge in tasks. When the utilization of computer clusters is not high, all servers in the related art are kept in an open state, which will cause a certain waste of resources.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a server management method, device, device, and storage medium, which can dynamically open an appropriate number of servers according to the actual operation of a computer cluster, so that the power consumption of the entire computer cluster can be maintained at a level suitable for computing tasks. to avoid wasting resources.

In a first aspect, an embodiment of the present invention provides a server management method, including:

Get the number of queued tasks and the number of idle servers in a computer cluster;

Determine whether the number of queued tasks is greater than a preset task number threshold, and whether the number of idle servers is less than the preset number of servers;

If the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers, obtain a target available server from the list of bootable servers of the computer cluster, and control the target idle server to perform booting operate;

The available servers in the bootable server list are servers that are successfully shut down in the automatic shutdown process.

In a second aspect, an embodiment of the present invention further provides a server management apparatus, including:

The quantity acquisition module is used to acquire the number of queued tasks and the number of idle servers in the computer cluster;

A quantity judgment module, configured to judge whether the number of queued tasks is greater than a preset task quantity threshold, and whether the number of idle servers is less than the preset number of servers;

A server power-on module, configured to obtain a target available server from the list of bootable servers of the computer cluster if the number of queued tasks is greater than the preset task number threshold and the number of idle servers is less than the preset number of servers, and control all the available servers. The target idle server performs the power-on operation;

The available servers in the bootable server list are servers that are successfully shut down in the automatic shutdown process.

In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implementing the computer program as described herein when the processor executes the computer program. The server management method described in the embodiment of the invention is provided.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the server management method according to the embodiment of the present invention is implemented .

The technical solution of the embodiment of the present invention is to obtain the number of queued tasks and the number of idle servers in the computer cluster, and then determine whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers; When the number of idle servers is greater than the preset number of tasks and the number of idle servers is less than the number of preset servers, the target available server is obtained from the list of bootable servers in the computer cluster, and the target idle server is controlled to perform the power-on operation. According to the number of queued tasks and the number of idle servers, Determine the tension of the current computing task application resources of the computer cluster. According to the number of queued tasks and the number of idle servers, it can be determined that the current computing task application resources of the computer cluster are relatively tight, and when the server needs to be automatically started, the appropriate number of servers can be dynamically started. In this way, it is possible to dynamically apply for resources according to the current computing task of the computer cluster, automatically start the server, ensure the timely processing of computing tasks, maintain the power consumption of the entire cluster at a level suitable for computing tasks, and avoid resource waste.

Description of drawings

FIG. 1 is a flowchart of a server management method according to Embodiment 1 of the present invention.

FIG. 2 is a flowchart of a server management method according to Embodiment 2 of the present invention.

FIG. 3 is a flowchart of a server management method according to Embodiment 3 of the present invention.

FIG. 4 is a flowchart of a server management method according to Embodiment 4 of the present invention.

FIG. 5 is a schematic structural diagram of a server management apparatus according to Embodiment 5 of the present invention.

FIG. 6 is a schematic structural diagram of a computer device according to Embodiment 6 of the present invention.

Detailed ways

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

In addition, it should be noted that, for the convenience of description, the drawings only show some but not all of the contents related to the present invention. Before discussing the exemplary embodiments in greater detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts various operations (or steps) as a sequential process, many of the operations may be performed in parallel, concurrently, or concurrently. Additionally, the order of operations can be rearranged. The process may be terminated when its operation is complete, but may also have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, subroutines, and the like.

Example 1

FIG. 1 is a flowchart of a server management method according to Embodiment 1 of the present invention. The embodiments of the present invention may be applicable to the situation of managing servers in a computer cluster, and the method may be executed by the server management apparatus provided by the embodiments of the present invention, which may be implemented in software and/or hardware, and generally integrated in computer equipment. For example, a management server in a computer cluster. The management server is a server for managing all the servers in the computer cluster. As shown in FIG. 1, the method of the embodiment of the present invention specifically includes:

Step 101: Obtain the number of queued tasks and the number of idle servers of the computer cluster.

In this embodiment, the number of queued tasks of the computer cluster is the number of queued tasks of all users in the computer cluster. The number of idle servers is the number of all idle servers in the computer cluster. An idle server is a server in which all computing resources within the server are in an idle state. Exemplarily, the computing resource may be a graphics processing unit (Graphics Processing Unit, GPU) card.

Optionally, the acquiring the number of queued tasks and the number of idle servers of the computer cluster may include: periodically acquiring the number of queued tasks and the number of idle servers of the computer cluster according to a preset startup time interval.

The preset power-on time interval can be set according to business requirements. Exemplarily, the preset power-on time interval may be 15 minutes. Obtain the number of queued tasks and the number of idle servers of the computer cluster every 15 minutes; determine whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers; if the number of queued tasks is greater than The preset number of tasks threshold, and the number of idle servers is less than the preset number of servers, obtain a target available server from the list of bootable servers of the computer cluster, and control the target idle server to perform a power-on operation; wherein, the bootable server The available servers in the list are the servers that were successfully shut down during the automatic shutdown process. Thus, the automatic power-on process can be executed every preset power-on time interval.

Optionally, the number of queued tasks and the number of idle servers in the computer cluster can be acquired through a preset script command for acquiring the number of queued tasks and the number of idle servers.

Step 102: Determine whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers: if yes, go to step 103; if not, go to step 104.

Optionally, the value of the preset task quantity threshold may be determined according to the frequency of tasks. Exemplarily, the value of the preset task quantity threshold is 10. In practical scenarios, users who submit computing resource requests to the server unreasonably can easily lead to task queuing. According to experience, the number of queued tasks is 10 and below can be considered normal.

Determine whether the number of queued tasks is greater than the preset task number threshold. If the number of queued tasks is greater than the preset task number threshold, it indicates that the number of queued tasks is greater than the normal value, and the current computing task application resources are relatively tight, and the server needs to be automatically started to ensure the timely processing of computing tasks. If the number of queued tasks is less than or equal to the preset number of tasks threshold, it indicates that the number of queued tasks is less than or equal to the normal value, the current computing task application resources are not very tight, and the server does not need to be automatically started temporarily to ensure the timely processing of computing tasks.

Optionally, the value of the preset number of servers may be determined according to the number of available machines. Exemplarily, the value of the preset number of servers is 2. In actual scenarios, a server is often configured with 8 GPU cards. When there is only one idle server and a user submits a computing task that requires 16 GPU cards, the task will be queued. To this end, setting the preset number of servers to 2 helps to start the servers in time to provide resource support for the computing task.

Determine whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers. If the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers, it indicates that the number of queued tasks is greater than the normal value, the number of available idle servers is less than the normal value, the current computing task application resources are relatively tight, and the server needs to be automatically started , to ensure the timely processing of computing tasks. If the number of queued tasks is less than or equal to the preset task number threshold, or the number of idle servers is greater than or equal to the preset number of servers, it indicates that the current computing task application resources are not very tight, and the server does not need to be automatically started temporarily to ensure the timely processing of computing tasks.

At the same time, according to the number of queued tasks and the number of idle servers, it is determined whether the current computing task application resources of the computer cluster are tense, and it can be more reasonably judged whether it is necessary to automatically start the server.

Optionally, it may further include: judging whether there is an available server in the bootable server list of the computer cluster.

In this embodiment, before judging whether the number of queued tasks is greater than the preset task number threshold and whether the number of idle servers is less than the preset number of servers, it can be judged whether there is an available server in the list of bootable servers of the computer cluster . Optionally, after judging whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers, it is also possible to judge whether there is an available server in the list of bootable servers of the computer cluster. .

The bootable server list of the computer cluster maintains the available servers that can be powered on in the computer cluster. An available server is a server that can be powered on. Optionally, the available servers in the bootable server list may be servers that are successfully shut down in the automatic shutdown process.

If it is determined that there is no available server in the list of bootable servers of the computer cluster, it means that even if the server needs to be automatically powered on in the subsequent process, the purpose cannot be achieved, and in this case, the process can be ended. If it is determined that there are available servers in the bootable server list of the computer cluster, it means that even if the subsequent process has the possibility of successfully booting the server, the subsequent steps can be continued.

Step 103: Acquire a target available server from a list of bootable servers of the computer cluster, and control the target idle server to perform a booting operation.

The available servers in the bootable server list are servers that are successfully shut down in the automatic shutdown process.

Optionally, the automatic shutdown process may be: acquiring the number of idle servers in the computer cluster; judging whether the computer cluster satisfies the idle server shutdown condition according to the number of idle servers; if the computer cluster satisfies the idle server shutdown condition, Then, the target idle server is acquired from the idle servers of the computer cluster, the target idle server is controlled to perform a shutdown operation, and the target idle server that has been successfully shut down is added to the bootable server list of the computer cluster.

If the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers, the target available server is obtained from the list of bootable servers in the computer cluster, and the target idle server is controlled to perform a boot operation.

Optionally, obtaining a target available server from a list of bootable servers of the computer cluster, and controlling the target idle server to perform a booting operation may include: selecting an available server from the list of bootable servers of the computer cluster as the target available server. Server; control the target idle server to perform a boot operation through an intelligent platform management interface (Intelligent Platform Management Interface, IPMI) instruction.

Optionally, after controlling the target idle server to perform a power-on operation, it may further include: after waiting for a preset power-on time period, judging whether the target available server is successfully powered on; The target available server performs an initialization operation; after waiting for a preset initialization time period, it is determined whether the target available server is successfully initialized; if the target available server is successfully initialized, the normal online information of the target available server is written into to the log file.

The preset startup time period may be determined according to the time required for the server startup operation. Exemplarily, generally, it takes 5 minutes to start the server, and the value of the preset start-up time period is 5 minutes. The preset initialization time period may be determined according to the time required for the server initialization operation. The normal online information is used to record the information that the target available server successfully completes the startup operation and initialization operation in the current automatic startup process and goes online normally.

Optionally, a network diagnostic tool (Packet Internet Groper, PING) command is used to test the target available server to determine whether the target available server is successfully powered on.

Optionally, if the target available server has not been successfully powered on, the information about the unsuccessful booting of the target available server is written into the log file, so that the operation and maintenance personnel can check the log file regularly and determine whether the target available server has failed to boot according to the failure of the target server. information, manually intervene and maintain the target available servers. The boot failure information is used to record the information that the target available server fails to boot successfully in the current automatic boot process.

Optionally, the initialization operation may include memory swap partition (SWaP) checking, resource management system SLURM configuration file synchronization, graphics card initialization, storage mounting status checking, and scheduling system services checking whether they are normal or not.

Optionally, if the target available server has not been initialized successfully, write the information about the unsuccessful initialization of the target available server into the log file, so that the operation and maintenance personnel can check the log file regularly and check if the initialization of the target available server is unsuccessful. information, manually intervene and maintain the target available servers. The initialization failure information is used to record the information that the target available server has not been successfully initialized in the current automatic startup process.

Step 104: Write the current resource situation information of the computer cluster into a log file.

In this embodiment, if the number of queued tasks is less than or equal to the preset task number threshold, or the number of idle servers is greater than or equal to the preset number of servers, the current resource situation information of the computer cluster is written into the log file, so that the operation and maintenance personnel can When checking the log file regularly, the resource situation of the computer cluster in the current automatic startup process is determined according to the current resource situation information of the computer cluster.

Optionally, the current resource situation information of the computer cluster includes the number of queued tasks and the number of idle servers of the computer cluster.

The embodiment of the present invention provides a server management method, by acquiring the number of queued tasks and the number of idle servers in a computer cluster, and then judging whether the number of queued tasks is greater than a preset task number threshold, and whether the number of idle servers is less than the preset number of servers; and When the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers, the target available server is obtained from the list of bootable servers in the computer cluster, and the target idle server is controlled to perform the power-on operation. The number of idle servers is used to determine the tense situation of the current computing task application resources of the computer cluster. According to the number of queued tasks and the number of idle servers, it can be determined that the current computing task application resources of the computer cluster are relatively tight, and the server needs to be automatically started. The number of servers, so as to dynamically apply for resources according to the current computing tasks of the computer cluster, automatically start the server, ensure the timely processing of computing tasks, maintain the power consumption of the entire cluster at a level suitable for the computing tasks, and avoid resources waste.

Embodiment 2

FIG. 2 is a flowchart of a server management method according to Embodiment 2 of the present invention. This embodiment of the present invention may be combined with each optional solution in one or more of the foregoing embodiments. In this embodiment of the present invention, the server management method may further include: judging whether an available server exists in the bootable server list of the computer cluster. And, after controlling the target idle server to perform a power-on operation, the method may further include: after waiting for a preset power-on time period, judging whether the target available server is successfully powered on; The target available server is initialized; after waiting for the preset initialization time period, it is determined whether the target available server is successfully initialized; if the target available server is successfully initialized, the normal online information of the target available server is written to the log in the file.

As shown in FIG. 2, the method of the embodiment of the present invention specifically includes:

Step 201: Obtain the number of queued tasks and the number of idle servers of the computer cluster.

For details not described in this embodiment, reference may be made to the foregoing embodiments.

Step 202, judging whether there is an available server in the bootable server list of the computer cluster: if yes, go to Step 203; if not, end the process.

In this embodiment, the bootable servers in the computer cluster are maintained in the bootable server list of the computer cluster. An available server is a server that can be powered on. Optionally, the available servers in the bootable server list may be servers that are successfully shut down in the automatic shutdown process.

If it is determined that there is no available server in the list of bootable servers of the computer cluster, it means that even if the server needs to be automatically powered on in the subsequent process, the purpose cannot be achieved, and in this case, the process can be ended. If it is determined that there are available servers in the bootable server list of the computer cluster, it means that even if the subsequent process has the possibility of successfully booting the server, the subsequent steps can be continued.

Step 203: Determine whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers: if yes, go to step 204; if not, go to step 211.

In this embodiment, it is determined whether the number of queued tasks is greater than a preset task number threshold, and whether the number of idle servers is less than the preset number of servers. If the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers, it indicates that the number of queued tasks is greater than the normal value, the number of available idle servers is less than the normal value, the current computing task application resources are relatively tight, and the server needs to be automatically started , to ensure the timely processing of computing tasks. If the number of queued tasks is less than or equal to the preset task number threshold, or the number of idle servers is greater than or equal to the preset number of servers, it indicates that the current computing task application resources are not very tight, and the server does not need to be automatically started temporarily to ensure the timely processing of computing tasks.

At the same time, according to the number of queued tasks and the number of idle servers, it is determined whether the current computing task application resources of the computer cluster are tense, and it can be more reasonably judged whether it is necessary to automatically start the server.

Step 204: Acquire a target available server from a list of bootable servers of the computer cluster, and control the target idle server to perform a booting operation.

Optionally, obtaining a target available server from a list of bootable servers of the computer cluster, and controlling the target idle server to perform a booting operation may include: selecting an available server from the list of bootable servers of the computer cluster as the target available server. Server; through the IPMI command, control the target idle server to perform the power-on operation.

Step 205 , after waiting for a preset boot time period, determine whether the target available server is successfully booted: if yes, go to step 206 ; if not, go to step 210 .

In this embodiment, the preset startup time period may be determined according to the time required for the server startup operation. Exemplarily, generally, it takes 5 minutes to start the server, and the value of the preset start-up time period is 5 minutes.

Optionally, use the PING command to test the target available server to determine whether the target available server is successfully powered on.

Step 206 , perform an initialization operation on the target available server.

Optionally, the initialization operation may include memory swap partition (SWaP) checking, resource management system SLURM configuration file synchronization, graphics card initialization, storage mounting status checking, and scheduling system services checking whether they are normal or not.

Step 207 , after waiting for a preset initialization time period, determine whether the target available server is successfully initialized: if yes, go to step 208 ; if not, go to step 209 .

In this embodiment, the preset initialization time period may be determined according to the time required for the server initialization operation.

Step 208: Write the normal online information of the target available server into a log file.

In this embodiment, the normal online information is used to record the information that the target available server successfully completes the booting operation and the initialization operation in the current automatic booting process, and goes online normally.

Step 209: Write the information about the unsuccessful initialization of the target available server into a log file.

In this embodiment, if the target available server is not successfully initialized, the information about the unsuccessful initialization of the target available server is written into the log file, so that the operation and maintenance personnel can check the log file regularly, according to the initialization failure of the target available server. Success message, manually intervene and maintain the target available server. The initialization failure information is used to record the information that the target available server has not been successfully initialized in the current automatic startup process.

Step 210: Write the information about the unsuccessful startup of the target available server into a log file.

In this embodiment, if the target available server has not been successfully powered on, the information about the unsuccessful booting of the target available server is written into the log file, so that the operation and maintenance personnel can check the log file regularly, according to the boot failure of the target available server. Success message, manually intervene and maintain the target available server. The boot failure information is used to record the information that the target available server fails to boot successfully in the current automatic boot process.

Step 211: Write the current resource situation information of the computer cluster into a log file.

In this embodiment, if the number of queued tasks is less than or equal to the preset task number threshold, or the number of idle servers is greater than or equal to the preset number of servers, the current resource situation information of the computer cluster is written into the log file, so that the operation and maintenance personnel can When checking the log file regularly, the resource situation of the computer cluster in the current automatic startup process is determined according to the current resource situation information of the computer cluster.

The embodiment of the present invention provides a server management method, by acquiring the number of queued tasks and the number of idle servers in a computer cluster, and then determining whether the number of queued tasks is greater than a preset task when it is determined that there are available servers in the list of bootable servers of the computer cluster Quantity threshold, and whether the number of idle servers is less than the preset number of servers, and when the number of queued tasks is greater than the preset number of tasks threshold, and the number of idle servers is less than the preset number of servers, the target is available from the list of bootable servers in the computer cluster. The server controls the target idle server to perform the power-on operation, and writes the corresponding information to the log file according to the start-up and initialization status of the target available server, and can determine the current computing task application resources of the computer cluster according to the number of queued tasks and the number of idle servers. In the tense situation, according to the number of queued tasks and the number of idle servers, it can be determined that the current computing task application resources of the computer cluster are relatively tight, and when the server needs to be automatically started, an appropriate number of servers can be dynamically opened, so as to dynamically In case of resource shortage for computing tasks, automatically start the server to ensure the timely processing of computing tasks, maintain the power consumption of the entire cluster at a level suitable for computing tasks, and avoid wasting resources. According to the startup status and initialization status of the server, write Enter the corresponding information into the log file, so that the operation and maintenance personnel can manually intervene and maintain the target available server according to the information in the log file when viewing the log file regularly.

Embodiment 3

FIG. 3 is a flowchart of a server management method according to Embodiment 3 of the present invention. This embodiment of the present invention may be combined with each of the optional solutions in one or more of the foregoing embodiments. In this embodiment of the present invention, the server management method may further include: acquiring the number of idle servers in the computer cluster; according to the number of idle servers , determine whether the computer cluster satisfies the idle server shutdown condition; if the computer cluster satisfies the idle server shutdown condition, obtain the target idle server from the idle servers of the computer cluster, control the target idle server to perform the shutdown operation, and The target idle server that has been successfully shut down is added to the list of bootable servers of the computer cluster.

As shown in FIG. 3 , the method of the embodiment of the present invention specifically includes:

Step 301: Obtain the number of idle servers in the computer cluster.

In this embodiment, the number of idle servers is the number of all idle servers in the computer cluster. An idle server is a server in which all computing resources within the server are in an idle state. Exemplarily, the computing resource may be a GPU card.

Optionally, the acquiring the number of idle servers in the computer cluster may include: periodically acquiring the number of idle servers in the computer cluster according to a preset shutdown time interval.

The preset shutdown time interval can be set according to business needs. Exemplarily, the preset turn-off time interval may be one day. Obtain the number of idle servers in the computer cluster every other day; according to the number of idle servers, determine whether the computer cluster satisfies the idle server shutdown condition; if the computer cluster meets the idle server shutdown condition, then select the idle server from the computer cluster The target idle server is obtained from the , the target idle server is controlled to perform a shutdown operation, and the target idle server that has been successfully shut down is added to the list of bootable servers of the computer cluster. Thus, the automatic shutdown process can be performed every preset shutdown time interval.

Optionally, because the shutdown process should not be performed frequently, the preset shutdown time interval is longer than the preset startup time interval described above.

According to experience, the computing tasks submitted by users are usually the least and the utilization rate of the computer cluster is the lowest in the time period around the middle and early morning of each day. At this time, it is often the most appropriate to trigger the automatic shutdown process. Therefore, the number of idle servers in the computer cluster can be obtained in the early morning of each day according to the preset shutdown time interval. Specifically, by judging whether the current time of the system spans days as a trigger condition for the execution of the automatic shutdown process, the automatic shutdown process can be executed once every morning in the early morning according to the preset shutdown time interval.

Optionally, the number of idle servers in the computer cluster may be acquired through a preset script command for acquiring the number of idle servers.

Step 302 , according to the number of idle servers, determine whether the computer cluster satisfies the idle server shutdown condition: if yes, go to step 303 ; if not, go to step 304 .

Optionally, judging whether the computer cluster satisfies the idle server shutdown condition according to the number of idle servers may include: judging whether the number of idle servers is greater than a preset number of idle servers threshold; if so, determining the computer cluster The cluster satisfies the idle server shutdown condition; if not, it is determined that the computer cluster does not meet the idle server shutdown condition.

The value of the preset number of idle servers threshold can be set according to business requirements. Exemplarily, the preset threshold for the number of idle servers is 5.

Determine whether the number of idle servers is greater than the preset number of idle servers threshold. If the number of idle servers is greater than the preset number of idle servers, it indicates that the number of idle servers in the computer cluster is greater than the normal value, and there are too many idle servers in the computer cluster that remain open. Then it is determined that the computer cluster satisfies the idle server shutdown condition. If the number of idle servers is less than or equal to the preset number of idle servers, it indicates that the number of idle servers in the computer cluster is less than or equal to the normal value, and there are not too many idle servers in the computer cluster to remain open, and there is no need to shut down too many idle servers temporarily. , to avoid resource waste, it is determined that the computer cluster does not meet the idle server shutdown condition.

Step 303: Acquire a target idle server from idle servers of the computer cluster, control the target idle server to perform a shutdown operation, and add the target idle server that has been successfully shut down to a list of bootable servers of the computer cluster.

Optionally, obtaining a target idle server from idle servers in the computer cluster, and controlling the target idle server to perform a shutdown operation, may include: calculating the difference between the number of idle servers and the preset threshold for the number of idle servers. obtain the idle servers with the difference in the number of idle servers from the idle servers of the computer cluster as target idle servers, and remove the target idle servers from the resource pool; perform a shutdown operation on the removed target idle servers .

A resource pool includes servers in a computer cluster that are maintained in an on state. In this embodiment, the target idle server that needs to perform the shutdown operation is removed from the resource pool in time.

Optionally, by executing a shutdown function on the eliminated target idle server, the shutdown operation of the eliminated target idle server is completed.

In a specific example, the value of the preset threshold for the number of idle servers is 5. The number of idle servers is 7. If the number of idle servers is greater than 5, it indicates that the number of idle servers in the computer cluster is greater than the normal value, and there are too many idle servers in the computer cluster to maintain the open state. It is necessary to close too many idle servers to avoid wasting resources, and then determine that the computer cluster satisfies the idle state. Server shutdown condition. The difference between the number of idle servers and the preset number of idle servers is 2. Obtain 2 idle servers from idle servers in the computer cluster as target idle servers. Remove the target idle server from the resource pool. Perform a shutdown operation on the target idle server after culling.

The bootable server list of the computer cluster maintains the available servers that can be powered on in the computer cluster. An available server is a server that can be powered on. The target idle server that is successfully shut down is an available server that can be powered on in the computer cluster. Thus, the target idle server that is successfully shut down in the automatic shutdown process is added to the list of bootable servers of the computer cluster.

Step 304: Write the current resource situation information of the computer cluster into a log file.

In this embodiment, if the computer cluster does not meet the idle server shutdown condition, the current resource situation information of the computer cluster is written into the log file, so that the operation and maintenance personnel can check the log file regularly, according to the current resources of the computer cluster. The situation information determines the resource situation of the computer cluster in the current automatic shutdown process.

Optionally, the current resource situation information of the computer cluster includes the number of idle servers in the computer cluster.

An embodiment of the present invention provides a server management method, by acquiring the number of idle servers in a computer cluster, and then judging whether the computer cluster satisfies the idle server shutdown condition according to the number of idle servers, and when the computer cluster meets the idle server shutdown condition, from the computer cluster Obtain the target idle server from the idle server, control the target idle server to perform the shutdown operation, and add the target idle server that has been successfully shut down to the list of bootable servers of the computer cluster, and can dynamically shut down too many idle servers according to the number of idle servers. , which can automatically shut down the server dynamically according to the idle condition of the server in the computer cluster, save the power consumption of the computer cluster, maintain the power consumption of the entire computer cluster at a level suitable for the computing task, and avoid the waste of resources.

Embodiment 4

FIG. 4 is a flowchart of a server management method according to Embodiment 4 of the present invention. This embodiment of the present invention may be combined with each of the optional solutions in one or more of the foregoing embodiments. In this embodiment of the present invention, determining whether the computer cluster satisfies the idle server shutdown condition according to the number of idle servers may include: : determine whether the number of idle servers is greater than the preset number of idle servers threshold; if so, determine that the computer cluster satisfies the idle server shutdown condition; if not, determine that the computer cluster does not meet the idle server shutdown condition.

And, obtaining a target idle server from idle servers in the computer cluster, and controlling the target idle server to perform a shutdown operation, may include: calculating a difference between the number of idle servers and the preset threshold for the number of idle servers; The idle servers with the difference in the number of idle servers are obtained from idle servers in the computer cluster as target idle servers, and the target idle servers are eliminated from the resource pool; a shutdown operation is performed on the eliminated target idle servers.

As shown in FIG. 4 , the method of the embodiment of the present invention specifically includes:

Step 401: Obtain the number of idle servers in the computer cluster.

For details not described in this embodiment, reference may be made to the foregoing embodiments.

Step 402 , determine whether the number of idle servers is greater than the preset number of idle servers threshold: if yes, go to step 403 ; if not, go to step 406 .

In this embodiment, the value of the preset threshold for the number of idle servers may be set according to business requirements. Exemplarily, the preset threshold for the number of idle servers is 5.

If the number of idle servers is greater than the preset number of idle servers, it indicates that the number of idle servers in the computer cluster is greater than the normal value, and there are too many idle servers in the computer cluster that remain open. Then it is determined that the computer cluster satisfies the idle server shutdown condition. If the number of idle servers is less than or equal to the preset number of idle servers, it indicates that the number of idle servers in the computer cluster is less than or equal to the normal value, and there are not too many idle servers in the computer cluster to remain open, and there is no need to shut down too many idle servers temporarily. , to avoid resource waste, it is determined that the computer cluster does not meet the idle server shutdown condition.

Step 403: Calculate the difference between the number of idle servers and the preset threshold for the number of idle servers.

Step 404: Obtain the idle servers of the difference number from idle servers of the computer cluster as target idle servers, and remove the target idle servers from the resource pool.

Step 405 : Perform a shutdown operation on the eliminated target idle server, and add the target idle server whose shutdown is successful to the list of bootable servers of the computer cluster.

Optionally, by executing a shutdown function on the eliminated target idle server, the shutdown operation of the eliminated target idle server is completed.

Step 406: Write the current resource situation information of the computer cluster into a log file.

An embodiment of the present invention provides a server management method, by judging whether the number of idle servers is greater than a preset number of idle servers threshold, to determine whether a computer cluster satisfies the idle server shutdown condition, and when the number of idle servers is greater than the preset number of idle servers Threshold, determine The computer cluster satisfies the idle server shutdown condition, and then calculates the difference between the number of idle servers and the preset number of idle servers, and obtains the idle servers with the difference from the idle servers of the computer cluster as the target idle server. Eliminate from the pool, perform the shutdown operation on the target idle server after the elimination, and dynamically shut down too many idle servers according to the number of idle servers and the preset number of idle servers. The server is automatically shut down, the power consumption of the computer cluster is saved, the power consumption of the entire computer cluster is maintained at a level suitable for the computing task, and the waste of resources is avoided.

Embodiment 5

FIG. 5 is a schematic structural diagram of a server management apparatus according to Embodiment 5 of the present invention. As shown in FIG. 5 , the apparatus includes: a quantity acquiring module 501 , a quantity judging module 502 and a server booting module 503 .

Wherein, the quantity acquisition module 501 is used to acquire the number of queued tasks and the number of idle servers in the computer cluster; the quantity judgment module 502 is used to determine whether the number of queued tasks is greater than a preset task number threshold, and whether the number of idle servers is less than The preset number of servers; the server startup module 503 is configured to obtain from the list of bootable servers of the computer cluster if the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers The target available server controls the target idle server to perform a power-on operation; wherein, the available servers in the list of bootable servers are servers that are successfully shut down in the automatic shutdown process.

An embodiment of the present invention provides a server management device, by acquiring the number of queued tasks and the number of idle servers in a computer cluster, and then determining whether the number of queued tasks is greater than a preset task number threshold, and whether the number of idle servers is less than the preset number of servers; and When the number of queued tasks is greater than the preset task number threshold, and the number of idle servers is less than the preset number of servers, the target available server is obtained from the list of bootable servers in the computer cluster, and the target idle server is controlled to perform the power-on operation. The number of idle servers is used to determine the tense situation of the current computing task application resources of the computer cluster. According to the number of queued tasks and the number of idle servers, it can be determined that the current computing task application resources of the computer cluster are relatively tight, and the server needs to be automatically started. The number of servers, so as to dynamically apply for resources according to the current computing tasks of the computer cluster, automatically start the server, ensure the timely processing of computing tasks, maintain the power consumption of the entire cluster at a level suitable for the computing tasks, and avoid resources waste.

In an optional implementation manner of the embodiment of the present invention, optionally, the server management apparatus may further include: a server judgment module, configured to judge whether there is an available server in the bootable server list of the computer cluster.

In an optional implementation of the embodiment of the present invention, optionally, the quantity acquisition module 501 may include: a quantity timing acquisition unit, configured to regularly acquire the number of queued tasks and the number of idle servers in the computer cluster according to a preset boot time interval .

In an optional implementation manner of the embodiment of the present invention, optionally, the server management apparatus may further include: a power-on judgment module, configured to judge whether the target available server is successfully powered on after waiting for a preset power-on time period; the server an initialization module, configured to perform an initialization operation on the target available server if the target available server is successfully powered on; an initialization judgment module, configured to determine whether the target available server is successfully initialized after waiting for a preset initialization time period; An information writing module, configured to write the normal online information of the target available server into a log file if the target available server is successfully initialized.

In an optional implementation manner of the embodiment of the present invention, optionally, the server management apparatus may further include: an idle quantity acquisition module, configured to acquire the idle server quantity of the computer cluster; a shutdown condition judgment module, configured to the number of idle servers, to determine whether the computer cluster satisfies the idle server shutdown condition; the server shutdown module is configured to obtain the target idle server from the idle servers of the computer cluster if the computer cluster meets the idle server shutdown condition, and control the The target idle server performs a shutdown operation, and the target idle server that is successfully shut down is added to the list of bootable servers of the computer cluster.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

The above-mentioned server management apparatus can execute the server management method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the server management method.

Embodiment 6

FIG. 6 is a schematic structural diagram of a computer device according to Embodiment 6 of the present invention. Figure 6 shows a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 6 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in FIG. 6, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors 16 , memory 28 , and bus 18 connecting various system components including memory 28 and processor 16 .

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 . Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive"). Although not shown in Figure 6, disk drives for reading and writing to removable non-volatile magnetic disks (eg "floppy disks") and removable non-volatile optical disks (eg CD-ROM, DVD-ROM) may be provided or other optical media) to read and write optical drives. In these cases, each drive may be connected to bus 18 through one or more data media interfaces. Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present invention.

A program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data , each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the described embodiments of the present invention.

Computer device 12 may also communicate with one or more external devices 14 (eg, keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with computer device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 22 . Also, the computer device 12 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through a network adapter 20 . As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18 . It should be understood that, although not shown in FIG. 6, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tapes drives and data backup storage systems.

The processor 16 executes various functional applications and data processing by running the programs stored in the memory 28, thereby realizing the server management method provided by the embodiment of the present invention: obtaining the number of queued tasks and the number of idle servers in the computer cluster; Whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers; if the number of queued tasks is greater than the preset number of tasks threshold, and the number of idle servers is less than the preset number of servers, then A target available server is obtained from the bootable server list of the computer cluster, and the target idle server is controlled to perform a booting operation; wherein, the available servers in the bootable server list are servers that are successfully shut down in the automatic shutdown process.

Embodiment 7

Embodiment 7 of the present invention provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the server management method provided by the embodiment of the present invention: obtaining the number of queued tasks of a computer cluster and The number of idle servers; determine whether the number of queued tasks is greater than the preset task number threshold, and whether the number of idle servers is less than the preset number of servers; if the number of queued tasks is greater than the preset task number threshold, and the number of idle servers If the number of servers is less than the preset number, the target available server is obtained from the list of bootable servers of the computer cluster, and the target idle server is controlled to perform the booting operation; wherein, the available servers in the bootable server list are those that were automatically shut down in the automatic shutdown process. A server that was successfully shut down.

Any combination of one or more computer-readable media may be employed. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Program code embodied on a computer readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional Procedural programming language - such as the "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or computer device. Where a remote computer is involved, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to connect).

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention. The scope is determined by the scope of the appended claims.

Claims (8)

1. A server management method, comprising:

acquiring the number of queuing tasks and the number of idle servers of a computer cluster;

judging whether the number of the queued tasks is larger than a preset task number threshold value or not and whether the number of the idle servers is smaller than the preset number of the servers or not;

if the number of the queued tasks is larger than a preset task number threshold value and the number of the idle servers is smaller than the preset server number, acquiring a target available server from a bootable server list of the computer cluster, and controlling the target idle server to execute booting operation;

the available servers in the bootable server list are servers which are successfully powered off in the automatic power-off process.

2. The method of claim 1, further comprising:

and judging whether available servers exist in the bootable server list of the computer cluster.

3. The method of claim 1, wherein obtaining the number of queued tasks and the number of free servers for the cluster of computers comprises:

and acquiring the number of queued tasks and the number of idle servers of the computer cluster at regular time according to a preset startup time interval.

4. The method of claim 1, further comprising, after controlling the target idle server to perform a boot operation:

after waiting for a preset startup time period, judging whether the target available server is successfully started;

if the target available server is successfully started, initializing the target available server;

after waiting for a preset initialization time period, judging whether the target available server is initialized successfully;

and if the initialization of the target available server is successful, writing the normal online information of the target available server into a log file.

5. The method of claim 1, further comprising:

acquiring the number of idle servers of the computer cluster;

judging whether the computer cluster meets the idle server closing condition or not according to the number of the idle servers;

and if the computer cluster meets the idle server closing condition, acquiring a target idle server from the idle servers of the computer cluster, controlling the target idle server to execute shutdown operation, and adding the target idle server which is successfully shutdown into a bootable server list of the computer cluster.

6. A server management apparatus, comprising:

the quantity acquisition module is used for acquiring the quantity of queuing tasks and the quantity of idle servers of the computer cluster;

the quantity judging module is used for judging whether the number of the queued tasks is greater than a preset task quantity threshold value or not and whether the number of the idle servers is less than the preset number of the servers or not;

a server starting module, configured to, if the number of queued tasks is greater than a preset task number threshold and the number of idle servers is less than a preset server number, obtain a target available server from a bootable server list of the computer cluster, and control the target idle server to perform a starting operation;

the available servers in the bootable server list are servers which are successfully powered off in the automatic power-off process.

7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the server management method according to any of claims 1-5 when executing the computer program.

8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the server management method according to any one of claims 1 to 5.

Images