CN111858050A

CN111858050A - Server cluster mixed deployment method, cluster management node and related system

Info

Publication number: CN111858050A
Application number: CN202010691212.4A
Authority: CN
Inventors: 杨丽萦; 汪星辰
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2020-07-17
Filing date: 2020-07-17
Publication date: 2020-10-30
Anticipated expiration: 2040-07-17
Also published as: CN111858050B

Abstract

The embodiment of the application provides a server cluster mixed deployment method, a cluster management node and a related system, wherein the method comprises the following steps: selecting a corresponding system verification mode based on the system area version of the target node to perform system verification on the target node, and performing application software deployment processing on the target node in the server cluster; and performing application software functional verification and application software performance test on the target node, and outputting a corresponding test result to schedule the target node deployed in the server cluster based on the test result. According to the method and the system, the servers of different system area versions of the server of different system area versions can be mixed deployed and uniformly scheduled in the same server cluster, the production cost of resource allocation of the servers of different system area versions can be effectively reduced, and the allocation efficiency and the application safety of the servers of different system area versions in the same server cluster can be improved.

Description

Server cluster mixed deployment method, cluster management node and related system

Technical Field

The application relates to the technical field of data processing, in particular to a server cluster hybrid deployment method, a cluster management node and a related system.

Background

In order to effectively guarantee the autonomous controllability of information security in the financial field in the designated area, from the viewpoint of cost saving and controllability, servers of which versions belong to the designated area need to be deployed in the designated server cluster as much as possible so as to continuously promote the reliable transformation work of the server cluster deployment in the designated area. In order to transition from a server with a version belonging to a different region to a server with a version belonging to a specific region, it is necessary to enable both the server with the version belonging to the specific region and the servers with the versions belonging to other regions to operate effectively.

At present, a specific mode that a server with a version belonging to a specified region and a server with a version belonging to other regions can effectively work is to independently deploy server clusters for servers with different system region versions and respectively and independently build the servers. Different server clusters are not associated with each other and do not affect each other, and computing resources and storage resources are isolated from each other.

However, in the above manner, due to the structural composition of resource separation between clusters, the problem that the servers of different system area versions cannot be simultaneously adjusted in characteristic adaptation is caused, so that the servers of different system area versions of the servers of different system area versions cannot be uniformly scheduled, the production cost of resource allocation is increased, and the application security of the server cluster is reduced to a certain extent.

Disclosure of Invention

Aiming at the problems in the prior art, the application provides a server cluster mixed deployment method, a cluster management node and a related system, which can perform mixed deployment and unified scheduling on servers of different system area versions of servers of different system area versions in the same server cluster, can effectively reduce the production cost of resource allocation on the servers of different system area versions, and can improve the allocation efficiency and application safety of the servers of different system area versions in the same server cluster.

In order to solve the technical problem, the application provides the following technical scheme:

in a first aspect, the present application provides a server cluster hybrid deployment method, including:

acquiring system area versions of target nodes which pass node verification and complete system software deployment at present, and selecting a corresponding system verification mode to perform system verification on the target nodes based on the system area versions of the target nodes, wherein the system area versions are divided into at least two types according to the areas to which the node versions belong in advance;

if the target node passes the corresponding system verification, application software deployment processing is carried out on the target node in the server cluster;

And performing application software functional verification on the target node, if the target node passes the application software functional verification, performing application software performance test on the target node, and outputting a corresponding test result to schedule the target node deployed in the server cluster based on the test result.

Further, before the obtaining the system region version of the target node which has currently passed the node verification and completed the system software deployment, the method further includes:

automatically detecting whether a newly added node exists in a cluster network segment of the server cluster, if so, performing node check on the node by using a preset node check mode, wherein the node check mode comprises the following steps: checking the correctness of the BIOS, checking the configuration consistency, checking the completeness of an interface, checking the completeness and checking the accuracy of monitoring of various preset core hardware of the mainboard;

selecting a system software deployment strategy of the node passing the node verification based on preset deployment strategy weight and a requirement file, and deploying the system software of the node passing the node verification according to the system software deployment strategy;

and determining the nodes which have finished the system software deployment as target nodes.

Further, the system verification mode comprises a preset applicability verification mode of the software system to hardware calling;

correspondingly, the selecting a corresponding system verification mode for performing system verification on the target node based on the system area version of the target node includes:

and if the system region version of the target node is the specified region version, the applicability check of the software system to the hardware call is executed on the target node by applying the applicability check mode of the software system to the hardware call.

Further, the system verification mode comprises a preset supporting verification mode facing the software system;

and if the system region version of the target node is a non-specified region version, performing software system-oriented support verification on the target node by applying the software system-oriented support verification mode.

Further, if the target node passes the corresponding system verification, performing application software deployment processing on the target node in the server cluster, including:

If the target node passes the corresponding system check, judging whether to continue executing application software deployment aiming at the target node according to the received application software deployment designation, if so, selecting a corresponding application software deployment strategy by applying a preset software deployment strategy weight;

and carrying out application software deployment processing on the target node based on the application software deployment strategy.

Further, the outputting a corresponding test result to schedule the target node deployed in the server cluster based on the test result includes:

and sending the test result of the target node to a resource scheduling server so that the resource scheduling server stores the test result of the target node in a preset deployment strategy performance index table.

Further, the resource scheduling server is configured to perform the following:

receiving a service operation request, and acquiring the characteristic type of a scheduling task corresponding to the current service operation from the service operation request;

acquiring the estimated execution time of each node in the server cluster from the deployment strategy performance index table according to the characteristic type of the scheduling task, acquiring the queue estimated waiting time of each node or node group, and determining the estimated completion time of the scheduling task in each queue based on the corresponding queue estimated waiting time and the estimated execution time;

The deployment strategy performance index table comprises the test result and the queue estimated waiting time of each node or node group in the server cluster, and the test result comprises the corresponding relation between the characteristic type of each scheduling task and the estimated execution time of each node;

and the scheduling task is arranged into the queue with the shortest estimated completion time to execute a resource scheduling program aiming at the scheduling task, and the estimated waiting time of the queue is updated.

In a second aspect, the present application provides a server cluster hybrid deployment apparatus, including:

the system verification module is used for acquiring the system area versions of the target nodes which pass node verification and complete system software deployment at present, and selecting a corresponding system verification mode to perform system verification on the target nodes based on the system area versions of the target nodes, wherein the system area versions are divided into at least two types according to the areas to which the node versions belong in advance;

the application software deployment module is used for deploying the application software for the target node in the server cluster if the target node passes the corresponding system verification;

And the performance testing module is used for performing application software functional verification on the target node, performing application software performance testing on the target node if the target node passes the application software functional verification, and outputting a corresponding testing result to schedule the target node deployed in the server cluster based on the testing result.

Further, still include:

the node checking module is used for automatically detecting whether a newly added node exists in a cluster network segment of the server cluster, if so, a preset node checking mode is applied to carry out node checking on the node, wherein the node checking mode comprises the following steps: checking the correctness of the BIOS, checking the configuration consistency, checking the completeness of an interface, checking the completeness and checking the accuracy of monitoring of various preset core hardware of the mainboard;

the system software deployment module is used for selecting a system software deployment strategy of the node passing the node verification based on preset deployment strategy weight and a requirement file, and deploying the system software of the node passing the node verification according to the system software deployment strategy;

and the target node determining module is used for determining the nodes which are subjected to system software deployment as target nodes.

correspondingly, the system verification module comprises:

and the first system verification unit is used for executing the suitability verification of the software system on the hardware call on the target node by applying the suitability verification mode of the software system on the hardware call if the system region version of the target node is the specified region version.

correspondingly, the system verification module comprises:

and the second system verification unit is used for executing the supporting verification facing the software system on the target node by applying the supporting verification mode facing the software system if the system region version of the target node is the non-specified region version.

Further, the application deployment module comprises:

the application software deployment strategy acquisition unit is used for judging whether to continue executing application software deployment aiming at the target node according to the received application software deployment designation if the target node passes the corresponding system verification, and if so, selecting the corresponding application software deployment strategy by applying the preset software deployment strategy weight;

And the software deployment unit is used for carrying out application software deployment processing on the target node based on the application software deployment strategy.

Further, the performance testing module comprises:

and the test result sending unit is used for sending the test result of the target node to the resource scheduling server so that the resource scheduling server stores the test result of the target node into a preset deployment strategy performance index table.

Further, the resource scheduling server includes:

the request receiving module is used for receiving the service operation request and acquiring the characteristic type of the scheduling task corresponding to the current service operation from the service operation request;

the estimated completion time acquisition module is used for acquiring estimated execution time of each node in the server cluster from the deployment strategy performance index table according to the characteristic type of the scheduling task, acquiring queue estimated waiting time of each node or node group, and determining the estimated completion time of the scheduling task in each queue based on the corresponding queue estimated waiting time and the estimated execution time;

And the resource scheduling module is used for arranging the scheduling task into the queue with the shortest estimated completion time to execute a resource scheduling program aiming at the scheduling task and updating the estimated waiting time of the queue.

In a third aspect, the present application provides a cluster management node, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the server cluster hybrid deployment method when executing the program.

In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the server cluster hybrid deployment method described herein.

In a fifth aspect, the present application provides a server cluster hybrid deployment and scheduling system, including a server cluster and a resource scheduling server;

the server cluster includes: the nodes of the designated area version, the nodes of the non-designated area version and the cluster management node are respectively contained in the server cluster;

the resource scheduling server is in communication connection with the cluster management node so as to receive a test result of a target node sent by the cluster management node;

And the resource scheduling server is in communication connection with the client so as to receive the service operation request sent by the client.

According to the technical scheme, the server cluster hybrid deployment method, the cluster management node and the related system provided by the application comprise the following steps: acquiring system area versions of target nodes which pass node verification and complete system software deployment at present, and selecting a corresponding system verification mode to perform system verification on the target nodes based on the system area versions of the target nodes, wherein the system area versions are divided into at least two types according to the areas to which the node versions belong in advance; if the target node passes the corresponding system verification, application software deployment processing is carried out on the target node in the server cluster; the method comprises the steps of performing functional verification on the target node, performing application software performance test on the target node if the target node passes the functional verification on the application software, outputting a corresponding test result to schedule the target node deployed in the server cluster based on the test result, and performing system verification by selecting different system verification modes aiming at the server nodes of different system area versions, so that characteristic adaptation adjustment of the server nodes of different system area versions can be effectively realized, the server nodes of different system area versions can be effectively and reliably deployed in the same server cluster, and further the servers of different system area versions can be mixed and deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different system area versions in the same server cluster can be realized, the production cost of resource allocation of the servers of different system area versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the scheduling efficiency and application safety of the servers of different system area versions in the same server cluster can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart illustrating a server cluster hybrid deployment method in an embodiment of the present application.

Fig. 2 is a flowchart illustrating a server cluster hybrid deployment method including steps 010 to 030 in this embodiment of the application.

Fig. 3 is a first flowchart illustrating step 100 in a server cluster hybrid deployment method in this embodiment.

Fig. 4 is a second flowchart illustrating step 100 in the server cluster hybrid deployment method in the embodiment of the present application.

Fig. 5 is a schematic flowchart of step 200 in a server cluster hybrid deployment method in this embodiment.

Fig. 6 is a schematic flowchart of step 300 in the server cluster hybrid deployment method in this embodiment.

Fig. 7 is a schematic flowchart of an execution flow of the resource scheduling server in the embodiment of the present application.

Fig. 8 is a schematic structural diagram of a first hybrid deployment apparatus for a server cluster in an embodiment of the present application.

Fig. 9 is a schematic structural diagram of a second hybrid deployment apparatus for a server cluster in an embodiment of the present application.

Fig. 10 is a schematic diagram of a first structure of a system verification module 10 in a server cluster hybrid deployment apparatus in an embodiment of the present application.

Fig. 11 is a schematic diagram of a second structure of the system verification module 10 in the server cluster mixed deployment apparatus in the embodiment of the present application.

Fig. 12 is a schematic structural diagram of an application software deployment module 20 in a server cluster hybrid deployment apparatus in an embodiment of the present application.

Fig. 13 is a schematic structural diagram of a performance testing module 30 in a server cluster hybrid deployment apparatus in an embodiment of the present application.

Fig. 14 is a schematic structural diagram of a resource scheduling server in an embodiment of the present application.

Fig. 15 is a schematic structural diagram of a cluster management node in the embodiment of the present application.

Fig. 16 is a schematic structural diagram of a server cluster hybrid deployment and scheduling system in an embodiment of the present application.

Fig. 17 is a schematic diagram of a mixed deployment of full stack localization and non-localization of a cluster provided in an application example of the present application.

FIG. 18 is a flow chart of a hybrid deployment phase provided by an application example of the present application.

Fig. 19 is a resource scheduling flowchart of a hybrid usage phase provided by an application example of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In order to solve the problem that the servers with different regional versions cannot be uniformly scheduled in the application of the server cluster, the application respectively provides a server cluster mixed deployment method, a server cluster mixed deployment device, a cluster management node and a server cluster mixed deployment and scheduling system, obtains the system area version of the target node which passes the node check and completes the system software deployment at present, and selects a corresponding system verification mode to perform system verification on the target node based on the system area version of the target node, the system region versions are divided into at least two types according to the regions to which the node versions belong in advance; if the target node passes the corresponding system verification, application software deployment processing is carried out on the target node in the server cluster; the method comprises the steps of performing functional verification on the target node, performing application software performance test on the target node if the target node passes the functional verification on the application software, outputting a corresponding test result to schedule the target node deployed in the server cluster based on the test result, and performing system verification by selecting different system verification modes aiming at the server nodes of different system area versions, so that characteristic adaptation adjustment of the server nodes of different system area versions can be effectively realized, the server nodes of different system area versions can be effectively and reliably deployed in the same server cluster, and further the servers of different system area versions can be mixed and deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different system area versions in the same server cluster can be realized, the production cost of resource allocation of the servers of different system area versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the scheduling efficiency and application safety of the servers of different system area versions in the same server cluster can be improved.

Based on the above, in an example of applying the server cluster hybrid deployment method, the server cluster hybrid deployment apparatus, and the implemented cluster management node or server cluster hybrid deployment and scheduling system provided in the embodiments of the present application, if the current target region is a country, the current target region is used as a server cluster applied in the country, and in order to effectively ensure autonomous controllability of information security in the financial field of the country, from the viewpoint of cost saving and controllability, a server belonging to the country in a version is required to be deployed as much as possible in a designated server cluster, so as to continuously promote reliable transformation work of the server cluster deployment in the country. The whole stack localization refers to the localization of hardware such as CPU, memory, hard disk, operating system, software and various plug-ins. Due to the difference of the execution standard, the development degree of the software and hardware architecture and the research and development process, the related domestic products and the mainstream non-domestic products have differences in the aspects of interfaces, performance indexes, processing modes and the like. Thus, the transition in information technology from non-localization to full stack localization is necessarily progressive in order to reduce risk, maintain existing system stability and high availability. Particularly, in the transition stage of the mixed part of the full-stack localization and non-localization clusters, the hybrid management of physical facilities, the adaptation of the support capability of a system level, the compatibility adaptation and the uniform access of service software and corresponding middleware are well done, the stability maintaining system is highly available, and the perception-free effect of users is realized. In the prior art, a non-localization server cluster and a localization server cluster are usually deployed independently and are built independently. The advantage of the scheme is that the two sets of clusters are not associated and influenced, the computing resources and the storage resources are isolated from each other, the disadvantage is that the resource separation loses the characteristic adaptation adjustment caused by the framework composition, the smooth transition advantage in the process of home-made transformation is lost, the production cost of resource allocation is increased, and the logic control in the aspects of cluster safety, operation and maintenance and the like also loses value. Therefore, based on the server cluster hybrid deployment method, the server cluster hybrid deployment device, the realized cluster management node or the server cluster hybrid deployment and scheduling system provided by the application, the capacity of the new localization equipment is expanded into the original non-localization equipment cluster, the single cluster hybrid deployment localization equipment and the non-localization equipment are realized, and simultaneously, because the same cluster relates to the heterogeneous node, the load balancing and the resource scheduling both provide a hybrid deployment compiling method so as to utilize the mixed cluster to the maximum extent on the basis of the original algorithm/module.

Specifically, the following examples are given to illustrate the respective embodiments.

In order to solve the problems that the prior art cannot uniformly schedule servers of different regional versions of a server in different regional versions, so that the production cost of resource allocation is increased, and the application security of a server cluster is reduced to a certain extent, the application provides an embodiment of a server cluster mixed deployment method, which specifically includes the following contents with reference to fig. 1:

step 100: the method comprises the steps of obtaining system area versions of target nodes which pass node verification and complete system software deployment at present, and selecting a corresponding system verification mode to conduct system verification on the target nodes based on the system area versions of the target nodes, wherein the system area versions are divided into at least two types according to the areas to which the node versions belong in advance.

It can be understood that the system verification method at least comprises the following steps: in an example of step 100, because 4 mixed situations of the domestic/non-domestic hardware and the domestic/non-domestic system are involved, it is necessary to determine whether the system in the deployment policy is domestic: if the system is a domestic system, the applicability verification program called by the system to hardware is executed, and the validity of the system is mainly oriented to the instruction set. If the system is a non-domestic system, the support verification facing the system, such as the completeness of an instruction set, the completeness of a hardware interface, the completeness of a hardware module and the like, is executed.

Step 200: and if the target node passes the corresponding system verification, performing application software deployment processing on the target node in the server cluster.

It is understood that, in step 200, if the application deployment is continuously executed, the application deployment policy (including various types of domestic/non-domestic application collocations) is selected and executed according to the application deployment policy weight.

Step 300: and performing application software functional verification on the target node, if the target node passes the application software functional verification, performing application software performance test on the target node, and outputting a corresponding test result to schedule the target node deployed in the server cluster based on the test result.

It will be appreciated that in step 300, application software functionality verification is performed and it is determined whether the verification passes: if not, outputting and checking the question detail (application software deployment log file), clearing the application software in the deployment strategy, reducing the weight of the application software deployment strategy, then returning to execute the deployment strategy weight according to the application software, and selecting and executing the application software deployment strategy (comprising various domestic/non-domestic application software collocation). And if the verification is passed, executing the application software performance test.

As can be seen from the above description, according to the server cluster hybrid deployment method provided in the embodiment of the present application, different system verification methods are selected for server nodes in different regional versions to perform system verification, so that characteristic adaptation adjustment of server nodes in different regional versions can be effectively achieved, and server nodes in different regional versions can be effectively and reliably deployed in the same server cluster, and thus servers in different regional versions can be hybrid deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different regional versions of the server in the same server cluster can be realized, the production cost of resource allocation of the servers of different regional versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the allocation efficiency and application safety of the servers of different regional versions in the same server cluster can be improved.

In order to obtain a target node through automatic detection, node verification and software deployment, in an embodiment of the server cluster hybrid deployment method provided in the present application, referring to fig. 2, before step 100 of the server cluster hybrid deployment method, the following contents are further specifically included:

step 010: automatically detecting whether a newly added node exists in a cluster network segment of the server cluster, if so, performing node check on the node by using a preset node check mode, wherein the node check mode comprises the following steps: BIOS correctness checking, configuration consistency checking, interface completeness checking, mainboard monitoring completeness checking and accuracy checking on various preset core hardware.

It can be understood that the preset core hardware at least includes a CPU, a GPU, a memory, and a hard disk. The BIOS correctness check refers to a correctness suggestion for a Basic Input Output System (BIOS).

Step 020: and selecting a system software deployment strategy of the node passing the node verification based on the preset deployment strategy weight and the requirement file, and deploying the system software of the node passing the node verification according to the system software deployment strategy.

It is understood that the system software deployment policy is a mapping table stored in the cluster management node. The hardware configuration and the applicability mapping of the system software (including patches) are recorded. The deployment strategy weight is an independent non-empty field which represents the priority in the strategy, the initial values are consistent, and feedback adjustment is carried out along with the deployment experience.

Step 030: and determining the nodes which have finished the system software deployment as target nodes.

As can be seen from the above description, the server cluster hybrid deployment method provided in the embodiment of the present application can effectively improve the intelligent degree and efficiency of server node deployment, and further can effectively improve the characteristic adaptation adjustment of server nodes in different regional versions, so that server nodes in different regional versions can be effectively and reliably deployed in the same server cluster.

In order to provide a system verification mode of a specified regional version, in an embodiment of the server cluster hybrid deployment method provided by the application, the system verification mode includes a preset applicability verification mode of a software system to hardware calling; referring to fig. 3, a first implementation manner of step 100 of the server cluster hybrid deployment method specifically includes the following contents:

Step 110: and acquiring the system area versions of the target nodes which pass the node verification currently and complete the system software deployment.

Step 120: and if the system region version of the target node is the specified region version, the applicability check of the software system to the hardware call is executed on the target node by applying the applicability check mode of the software system to the hardware call.

It can be understood that the method for checking the applicability of the software system to the hardware call is mainly a method for checking the validity of the instruction set.

As can be seen from the above description, the hybrid deployment method for the server cluster provided in the embodiment of the present application can effectively implement the characteristic adaptation adjustment of the server node of the designated region version, so that the server node of the designated region version can be effectively and reliably deployed in the same server cluster, and further, the servers of different region versions can be hybrid deployed in the same server cluster.

In order to provide a system verification mode of a non-specified region version, in an embodiment of the server cluster hybrid deployment method provided by the application, the system verification mode includes a preset software system-oriented support verification mode; referring to fig. 4, a second implementation manner of step 100 of the server cluster hybrid deployment method specifically includes the following contents:

Step 130: and if the system region version of the target node is a non-specified region version, performing software system-oriented support verification on the target node by applying the software system-oriented support verification mode.

It can be understood that the supporting verification mode for the software system is mainly a supporting verification mode for the system, such as completeness of an execution instruction set, completeness of a hardware interface, and completeness of a hardware module.

As can be seen from the above description, the hybrid deployment method for the server cluster provided in the embodiment of the present application can effectively implement the characteristic adaptation adjustment of the server nodes in the non-specific region version, so that the server nodes in the non-specific region version can be effectively and reliably deployed in the same server cluster, and further, the servers in different region versions can be hybrid deployed in the same server cluster.

In order to provide a preferred manner of application software deployment, in an embodiment of the server cluster hybrid deployment method provided in the present application, referring to fig. 5, a step 200 of the server cluster hybrid deployment method specifically includes the following steps:

Step 210: and if the target node passes the corresponding system check, judging whether to continue executing application software deployment aiming at the target node according to the received application software deployment designation, and if so, selecting a corresponding application software deployment strategy by applying a preset software deployment strategy weight.

It is understood that the application software deployment policy is a mapping table stored in the cluster management node. The mapping of system software deployment policies, requirements and application software combinations is recorded. The deployment strategy weight is an independent non-empty field which represents the priority in the strategy, the initial values are consistent, and feedback adjustment is carried out along with the deployment experience.

Step 220: and carrying out application software deployment processing on the target node based on the application software deployment strategy.

As can be seen from the above description, the method for hybrid deployment of server clusters provided in the embodiments of the present application can effectively improve effectiveness and reliability of application software deployment, and further can effectively implement characteristic adaptation adjustment of server nodes of different system region versions, so that server nodes of different system region versions can be effectively and reliably deployed in the same server cluster, and further, servers of different system region versions can be hybrid deployed in the same server cluster.

In order to provide a preferred way of outputting a test result, in an embodiment of the server cluster hybrid deployment method provided in the present application, referring to fig. 6, step 300 of the server cluster hybrid deployment method specifically includes the following steps:

step 310: and performing application software functional verification on the target node.

Step 320: and if the target node passes the functional verification of the application software, performing the performance test of the application software aiming at the target node.

Step 330: and sending the test result of the target node to a resource scheduling server so that the resource scheduling server stores the test result of the target node in a preset deployment strategy performance index table.

As can be seen from the above description, the mixed deployment method for the server cluster provided in the embodiment of the present application can further implement effectiveness and reliability of unified scheduling for servers of different system area versions of the server in different system area versions in the same server cluster, and can effectively reduce the production cost of resource allocation for servers of different system area versions on the premise of ensuring high availability and no service awareness of the server cluster.

In order to provide a preferred way of invoking a cluster task, in an embodiment of the server cluster hybrid deployment method provided in the present application, referring to fig. 7, the resource scheduling server mentioned in step 330 in the server cluster hybrid deployment method is configured to execute the following:

step 400: and receiving a service operation request, and acquiring the characteristic type of a scheduling task corresponding to the current service operation from the service operation request.

Step 500: and acquiring the estimated execution time of each node in the server cluster from the deployment strategy performance index table according to the characteristic type of the scheduling task, acquiring the queue estimated waiting time of each node or node group, and determining the estimated completion time of the scheduling task in each queue based on the corresponding queue estimated waiting time and the estimated execution time.

The deployment strategy performance index table comprises the test result and the estimated waiting time of the queue of each node or node group in the server cluster, and the test result comprises the corresponding relation between the characteristic type of each scheduling task and the estimated execution time of each node.

Step 600: and the scheduling task is arranged into the queue with the shortest estimated completion time to execute a resource scheduling program aiming at the scheduling task, and the estimated waiting time of the queue is updated.

In order to improve the respective scene advantages of the domestic and domestic self-construction in the mixed cluster, the resource scheduling server stores and maintains a deployment strategy performance index table (generated by a performance test in a mixed deployment stage) and the queue estimated waiting time (represented by a vector and updated along with task scheduling processing) of each node/node group.

As can be seen from the above description, the mixed deployment method for server clusters provided in the embodiments of the present application can further implement effectiveness and reliability of unified scheduling for servers of different regional versions in the same server cluster, and can effectively reduce production cost for resource allocation for servers of different regional versions on the premise of ensuring high availability and no service awareness of the server cluster, and can improve allocation efficiency and application security of servers of different regional versions in the same server cluster.

In terms of software, in order to solve the problems that the prior art cannot uniformly schedule servers of different regional versions of a server in different regional versions, and thus the production cost of resource allocation may be increased, and the application security of a server cluster may be reduced to a certain extent, the present application provides an embodiment of a server cluster hybrid deployment apparatus for executing all or part of the contents in the server cluster hybrid deployment method, and referring to fig. 8, the server cluster hybrid deployment apparatus specifically includes the following contents:

The system verification module 10 is configured to obtain a system area version of a target node which has passed node verification and completed system software deployment at present, and select a corresponding system verification mode based on the system area version of the target node to perform system verification on the target node, where the system area version is divided into at least two types according to an area to which the node version belongs in advance;

the application software deployment module 20 is configured to perform application software deployment processing on the target node in the server cluster if the target node passes the corresponding system verification;

the performance testing module 30 is configured to perform application software functional verification on the target node, perform application software performance testing on the target node if the target node passes the application software functional verification, and output a corresponding testing result to schedule the target node deployed in the server cluster based on the testing result.

As can be seen from the above description, the server cluster hybrid deployment device provided in the embodiment of the present application selects different system verification methods for system verification with respect to server nodes in different regional versions, and can effectively implement characteristic adaptation adjustment of server nodes in different regional versions, so that server nodes in different regional versions can be effectively and reliably deployed in the same server cluster, and further, servers in different regional versions can be hybrid deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different regional versions of the server in the same server cluster can be realized, the production cost of resource allocation of the servers of different regional versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the allocation efficiency and application safety of the servers of different regional versions in the same server cluster can be improved.

In order to obtain a target node through automatic detection, node verification and software deployment, in an embodiment of the server cluster hybrid deployment device provided in the present application, referring to fig. 9, the server cluster hybrid deployment device further includes the following contents:

the node verification module 01 is configured to automatically detect whether a newly added node exists in a cluster network segment of the server cluster, and if so, apply a preset node verification method to perform node verification on the node, where the node verification method includes: BIOS correctness checking, configuration consistency checking, interface completeness checking, mainboard monitoring completeness checking and accuracy checking on various preset core hardware.

And the system software deployment module 02 is used for selecting a system software deployment strategy of the node which passes the node verification based on preset deployment strategy weights and requirement files, and deploying the system software of the node which passes the node verification according to the system software deployment strategy.

And the target node determining module 03 is configured to determine the node where the system software deployment is completed as the target node.

As can be seen from the above description, the server cluster hybrid deployment device provided in the embodiment of the present application can effectively improve the intelligent degree and efficiency of server node deployment, and further can effectively improve the characteristic adaptation adjustment of server nodes in different regional versions, so that server nodes in different regional versions can be effectively and reliably deployed in the same server cluster.

In order to provide a system verification mode of a specified regional version, in an embodiment of the server cluster hybrid deployment device provided by the application, the system verification mode includes a preset applicability verification mode of a software system to hardware calling; referring to fig. 10, the system verification module 10 in the server cluster mixed deployment apparatus specifically includes the following contents:

and the system region version acquiring unit 11 is configured to acquire a system region version of a target node which has currently passed the node verification and completed the system software deployment.

The first system verification unit 12 is configured to, if the system region version of the target node is the designated region version, apply the suitability verification mode of the software system for hardware invocation to perform suitability verification of the software system for hardware invocation on the target node.

As can be seen from the above description, the hybrid deployment apparatus for server clusters provided in the embodiments of the present application can effectively implement characteristic adaptation adjustment of server nodes of specified regional versions, so that the server nodes of the specified regional versions can be effectively and reliably deployed in the same server cluster, and further, servers of different regional versions can be hybrid deployed in the same server cluster.

In order to provide a system verification mode of a non-specified region version, in an embodiment of the server cluster hybrid deployment device provided by the application, the system verification mode includes a preset software system-oriented support verification mode; referring to fig. 11, the system verification module 10 in the server cluster mixed deployment apparatus further includes the following contents:

and the second system verification unit 13 is configured to, if the system region version of the target node is a non-specified region version, apply the software system-oriented support verification manner to perform software system-oriented support verification on the target node.

As can be seen from the above description, the hybrid deployment apparatus for server clusters provided in the embodiments of the present application can effectively implement characteristic adaptation adjustment of server nodes in non-specific region versions, so that the server nodes in non-specific region versions can be effectively and reliably deployed in the same server cluster, and further, servers in different region versions can be hybrid deployed in the same server cluster.

In order to provide a preferred mode of application software deployment, in an embodiment of the server cluster hybrid deployment apparatus provided in the present application, referring to fig. 12, an application software deployment module 20 in the server cluster hybrid deployment apparatus further includes the following contents:

An application software deployment policy obtaining unit 21, configured to, if the target node passes the corresponding system verification, determine whether to continue executing application software deployment for the target node according to the received application software deployment designation, and if so, apply a preset software deployment policy weight to select a corresponding application software deployment policy.

And the software deployment unit 22 is configured to perform application software deployment processing on the target node based on the application software deployment policy.

As can be seen from the above description, the mixed deployment device for server clusters provided in the embodiments of the present application can effectively improve effectiveness and reliability of application software deployment, and further can effectively implement characteristic adaptation adjustment of server nodes of different system area versions, so that server nodes of different system area versions can be effectively and reliably deployed in the same server cluster, and further servers of different system area versions can be mixed deployed in the same server cluster.

In order to provide a preferred way of outputting a test result, in an embodiment of the server cluster hybrid deployment apparatus provided in the present application, referring to fig. 13, a performance test module 30 in the server cluster hybrid deployment apparatus further includes the following contents:

The test result sending unit 31 is configured to send the test result of the target node to the resource scheduling server, so that the resource scheduling server stores the test result of the target node in a preset deployment policy performance index table.

As can be seen from the above description, the mixed deployment device for server clusters provided in the embodiments of the present application can further implement effectiveness and reliability of unified scheduling for servers of different system area versions in the same server cluster, and can effectively reduce production cost for resource allocation for servers of different system area versions on the premise of ensuring high availability and no service awareness of the server cluster.

In order to provide a preferred manner of invoking a cluster task, in an embodiment of the server cluster hybrid deployment apparatus provided in the present application, referring to fig. 14, in a resource scheduling server to which the test result sending unit 31 sends the test result of the target node, the resource scheduling server specifically includes the following contents:

a request receiving module 40, configured to receive a service operation request, and obtain a feature type of a scheduling task corresponding to a current service operation from the service operation request;

The estimated completion time obtaining module 50 is configured to obtain an estimated execution time of each node in the server cluster from the deployment policy performance indicator table according to the feature type of the scheduling task, obtain a queue estimated waiting time of each node or node group, and determine an estimated completion time of the scheduling task in each queue based on the corresponding queue estimated waiting time and estimated execution time.

And the resource scheduling module 60 is configured to arrange the scheduling task into the queue with the shortest estimated completion time to execute a resource scheduling program for the scheduling task, and update the estimated waiting time of the queue.

As can be seen from the above description, the mixed deployment device for server clusters provided in the embodiment of the present application can further implement effectiveness and reliability of unified scheduling for servers of different regional versions in the same server cluster, and can effectively reduce production cost for resource allocation for servers of different regional versions on the premise of ensuring high availability and no service awareness of the server cluster, and can improve allocation efficiency and application security of servers of different regional versions in the same server cluster.

In terms of hardware, in order to solve the problems that the prior art cannot uniformly schedule servers of different regional versions of a server in different regional versions, so that the production cost of resource allocation can be increased, and the application security of a server cluster can be reduced to a certain extent, the present application provides an embodiment of a cluster management node for implementing all or part of the contents in the server cluster mixed deployment method, where the cluster management node specifically includes the following contents:

fig. 15 is a schematic block diagram of a system configuration of a cluster management node 9600 according to an embodiment of the present application. As shown in fig. 15, the cluster management node 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 15 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In an embodiment, the server cluster hybrid deployment functionality may be integrated into a central processor. Wherein the central processor may be configured to control:

As can be seen from the above description, the cluster management node provided in the embodiment of the present application selects different system verification methods for system verification with respect to server nodes of different regional versions, so that characteristic adaptation adjustment of server nodes of different regional versions can be effectively achieved, and server nodes of different regional versions can be effectively and reliably deployed in the same server cluster, and further servers of different regional versions can be mixed and deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different regional versions of the server in the same server cluster can be realized, the production cost of resource allocation of the servers of different regional versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the allocation efficiency and application safety of the servers of different regional versions in the same server cluster can be improved.

In another embodiment, the cluster management node may be configured separately from the central processor 9100, for example, the cluster management node may be configured as a chip connected to the central processor 9100, and the function of mixed deployment of the server cluster is implemented by the control of the central processor.

As shown in fig. 15, the cluster management node 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that cluster management node 9600 also does not necessarily include all of the components shown in FIG. 15; further, the cluster management node 9600 may also include components not shown in fig. 15, which may be referred to in the prior art.

As shown in fig. 15, central processor 9100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of cluster management node 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to cluster management node 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the cluster management node 9600 by the central processor 9100.

The memory 9140 may also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by the cluster management node. Driver storage 9144 of memory 9140 may include various drivers for the cluster management node for communication functions and/or for performing other functions of the cluster management node (e.g., messaging applications, directory applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, in the same cluster management node, a plurality of communication modules 9110 may be provided, such as a cellular network module, a bluetooth module, and/or a wireless local area network module. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the server cluster hybrid deployment method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements all the steps of the server cluster hybrid deployment method in which an execution subject is a server or a client, for example, when the processor executes the computer program, the processor implements the following steps:

As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application selects different system verification methods for system verification with respect to server nodes in different regional versions, so that characteristic adaptation adjustment of server nodes in different regional versions can be effectively achieved, and server nodes in different regional versions can be effectively and reliably deployed in the same server cluster, and further servers in different regional versions can be mixedly deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different regional versions of the server in the same server cluster can be realized, the production cost of resource allocation of the servers of different regional versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the allocation efficiency and application safety of the servers of different regional versions in the same server cluster can be improved.

Based on the above server cluster hybrid deployment method, server cluster hybrid deployment apparatus, cluster management node, or computer readable storage medium, in order to solve the problem that the prior art cannot uniformly schedule servers of different regional versions of servers, which may increase the production cost of resource allocation, and may reduce the application security of the server cluster to a certain extent, the present application further provides an embodiment of a server cluster hybrid deployment and scheduling system including a cluster management node, referring to fig. 16, where the server cluster hybrid deployment and scheduling system specifically includes the following contents:

a server cluster and a resource scheduling server; the server cluster includes: the nodes of the designated region version, the nodes of the non-designated region version and the cluster management node are respectively contained in the server cluster; the resource scheduling server is in communication connection with the cluster management node so as to receive a test result of a target node sent by the cluster management node; and the resource scheduling server is in communication connection with the client so as to receive the service operation request sent by the client.

It is to be understood that reference to a client in one or more embodiments of the present application specifically refers to a client device.

As can be seen from the above description, the server cluster hybrid deployment and scheduling system provided in the embodiment of the present application selects different system verification methods for the server nodes in different regional versions to perform system verification, so that the characteristic adaptation adjustment of the server nodes in different regional versions can be effectively achieved, the server nodes in different regional versions can be effectively and reliably deployed in the same server cluster, and further, the servers in different regional versions can be hybrid deployed in the same server cluster; by performing software functional verification on the server nodes to test the software functions and outputting and storing the test results as scheduling basis data of the server nodes, the effectiveness and reliability of uniform scheduling of servers of different regional versions of the server in the same server cluster can be realized, the production cost of resource allocation of the servers of different regional versions can be effectively reduced on the premise of ensuring high availability and no service perception of the server cluster, and the allocation efficiency and application safety of the servers of different regional versions in the same server cluster can be improved.

In order to further explain the solution, the present application also provides a specific application example for implementing the server cluster hybrid deployment method by using a server cluster hybrid deployment and scheduling system, referring to fig. 17, a cluster of full-stack domestic and non-domestic hybrid deployment mainly includes a cluster management node, a resource scheduling server, a domestic cluster node and a non-domestic cluster node, where the cluster management node is used for conventional cluster management, and in the present application, the cluster additionally includes systematic management (registration, configuration update, status check, etc.) of the hybrid deployment node, and automatic deployment management (media management, operation start, status check, policy management, etc.) of the domestic/non-domestic system, software, middleware. The resource scheduling server is mainly used for butting a service client and pushing down the operation issued at the upstream to a localization/non-localization node, and logic disassembly, adaptive verification strategy execution and adaptive strategy adjustment are included in the process. In addition, various existing applicable architectures can be selected for the general physical architectures such as network devices, and the details are omitted in the present application.

The method for cluster full-stack localization and non-localization mixed deployment mainly comprises a mixed deployment stage (before delivery) and a mixed use stage (after delivery). After manual infrastructure preparation such as cluster node assembly, network facility deployment and the like is completed, referring to fig. 18, the flow of the hybrid deployment phase is as follows:

First, infrastructure preparation (including node assembly, network deployment, etc.) is performed.

Step 1: the cluster management node automatically detects the new node.

Step 2: and (4) judging whether a new node exists, if so, executing the step (3), and if not, ending the current process.

And step 3: and executing a node check program (including BIOS check, hardware monitoring check and the like).

And 4, step 4: judging whether the verification passes, if not, executing the step 4 (1); if yes, go to step 4 (2).

Step 4 (1): and outputting and checking the question detail, and marking the corresponding node.

Step 4 (2): and selecting and executing a system software deployment strategy (including system type, version and patch condition) according to the weight and the requirement of the system deployment strategy.

And 5: and (5) judging the system identifier, if the system identifier is domestic, executing the step 5(1), and if the system identifier is non-domestic, executing the step 5 (2).

Step 5 (1): and performing the suitability check of the domestic system on the hardware call.

Step 5 (2): and executing support verification of the hardware instruction set and other dimensions on the non-domestic system.

Step 6: and judging whether the verification passes, if not, executing the step 6(1), and if so, executing the step 7.

Step 6 (1): and outputting and checking the question details, and reducing the weight of the system deployment strategy.

And 7: and judging whether the application software deployment is executed or not, if so, executing the step 8.

And 8: and selecting and executing an application software deployment strategy (comprising various domestic/non-domestic application software collocations) according to the application software deployment strategy weight.

And step 9: application software functionality verification is performed.

Step 10: and judging whether the verification passes, if so, executing the step 11, otherwise, executing the step 10 (1).

Step 10 (1): and outputting and checking the question detail, clearing the application software and reducing the weight of the deployment strategy of the application software.

Step 11: and executing the application software performance test.

Step 12: and transmitting the test result data to a resource scheduling server as a scheduling strategy basis for storage.

Specifically, the specific process of implementing the server cluster hybrid deployment method by using the server cluster hybrid deployment and scheduling system is as follows:

s1: the cluster management node automatically detects new nodes in the network segment.

S2: and judging whether a node which newly enters the cluster network segment exists or not, and if not, ending.

S3: if the hardware is available, a node check program is executed, wherein the node check program is mainly a check program oriented to hardware availability and cluster management applicability, such as BIOS correctness and configuration consistency check, interface completeness check, and mainboard monitoring completeness and accuracy check on each core hardware (CPU/GPU/memory/hard disk). It is determined whether the verification routine of S3 passes through in full:

If not, the question details are visually output and archived on disk (hardware deployment log file), the question nodes are marked (which can be implemented in the cluster management system or simply according to the node number/IP/MAC), and the process returns to S2.

And if the system software passes the deployment strategy, selecting and executing the system software deployment strategy according to the deployment strategy weight and the requirement, wherein the system software deployment strategy comprises the system type, the version and the patch condition.

S4: because four mixed situations of domestic/non-domestic hardware and domestic/non-domestic systems are involved, it is necessary to determine whether the system in the deployment strategy is domestic:

if the system is a domestic system, the applicability verification program called by the system to hardware is executed, and the validity of the system is mainly oriented to the instruction set.

If the system is a non-domestic system, the support verification facing the system, such as the completeness of an instruction set, the completeness of a hardware interface, the completeness of a hardware module and the like, is executed.

S5: determining whether the verification program passes:

if not, the problem details are visually output and archived on disk (system deployment log file), the deployment strategy weight is reduced, and the process returns to S4.

If the result is passed, whether the application software deployment is continuously executed is determined, and if not, the step returns to the step S2.

S6: and if the application software deployment is continuously executed, selecting and executing an application software deployment strategy (comprising various domestic/non-domestic application software collocations) according to the application software deployment strategy weight.

S7: application software functionality verification is performed.

S8: determining whether the check passes:

if not, outputting and checking the question detail (application software deployment log file), clearing the application software in the deployment strategy, reducing the weight of the application software deployment strategy, and returning to S6.

And if the verification is passed, executing the application software performance test.

And transmitting the test result data to a resource scheduling server as a scheduling policy basis, storing the test result data as a deployment policy performance index table, and returning to the step S2.

It should be noted that the system software deployment policy and the application software deployment policy described in the process are two mapping tables, which are both stored in the cluster management node. The former records the applicability mapping of hardware configuration and system software (including patch), and the latter records the mapping of system software deployment strategy, requirement and application software combination. The weights of the two fields are independent non-empty fields which represent the priority in the strategy, the initial values are consistent, and feedback adjustment is carried out along with deployment experience.

After the hybrid deployment stage is completed, compared with a cluster which is not in the domestic/non-domestic hybrid deployment, the use stage has a difference, which is particularly expressed in the scheduling of heterogeneous resources, and the aim is to reduce the production cost and improve the service execution efficiency on the premise of ensuring the high availability of the cluster and no service perception. The scheduling of the domestic/non-domestic mixed use stage utilizes the conventional resource scheduling capability/program and provides a compiling type transformation method. The calculation task is issued by the client and transmitted to the resource scheduling server, referring to fig. 19, the resource scheduling process in the hybrid use phase is as follows:

After all tasks before scheduling are completed, the calculation tasks are issued by the client and transmitted to the resource scheduling server, and all tasks before scheduling are completed.

Step 41: obtaining the characteristic type of the scheduling task as the query constraint of the deployment strategy performance index table: and the resource scheduling server acquires the characteristic type of the scheduling task (depending on the modes of script rule scanning, characteristic identification and the like) according to the issued service operation, and the characteristic type is used as the query constraint of the deployment strategy performance index table.

Step 42: obtaining estimated execution time from a deployment strategy performance index table: and acquiring the estimated execution time of various deployment strategies (domestic/non-domestic) from the deployment strategy performance index table according to characteristics (such as high concurrency, large-scale writing and the like).

Step 43: calculating the estimated completion time of the current scheduling task in various deployment strategy queues according to the estimated waiting time of each node/node group task queue: and calculating the estimated completion time of the current scheduling task in various deployment strategy queues according to the estimated waiting time of each node/node group task queue.

Step 44: and (3) queuing the current scheduling task into a queue with the shortest estimated completion time, and updating the estimated waiting time of the queue: and (4) the current scheduling task is arranged in a queue with the shortest estimated completion time, and the estimated waiting time of the queue is updated.

Step 45: a conventional resource scheduler is executed.

It should be noted that, in order to improve the respective scene advantages of the domestic and domestic self-construction in the mixed cluster, the resource scheduling server stores and maintains a deployment policy performance index table (generated by a performance test in the mixed deployment phase), and the queue estimated waiting time of each node/node group (represented by a vector and updated along with the task scheduling processing).

It is particularly emphasized that the above steps are based on time as a determination basis, but the present application also supports other determination dimensions, such as non-functional requirements on stability, security, interruptibility, and the like, and requires to deploy corresponding indexes maintained in the policy performance index table for policy determination. In addition, the deployment policy performance index table also supports a feedback mechanism, and needs to obtain specific performance indexes according to the resource scheduling log of the job execution record and adjust the deployment policy performance index table according to a weighted average and other manners.

The application example realizes the mixed deployment of the full-stack localization cluster and the non-localization cluster, ensures the smooth transition of the localization transformation stage, improves the resource utilization rate compared with the scheme of the existing localization transition stage, reduces the cost, reduces the influence of the high availability aspect and the safety risk aspect of the service, and realizes the service side non-perception of the localization transformation.

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

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A server cluster hybrid deployment method is characterized by comprising the following steps:

2. The hybrid deployment method for server cluster as claimed in claim 1, further comprising, before the obtaining the system region version of the target node that has passed the node verification and completed the system software deployment, the following steps:

3. The server cluster hybrid deployment method according to claim 1, wherein the system verification manner includes a preset software system applicability verification manner for hardware invocation;

4. The server cluster hybrid deployment method according to claim 1, wherein the system verification manner comprises a preset software system-oriented support verification manner;

5. The hybrid deployment method for the server cluster according to claim 1, wherein if the target node passes the corresponding system verification, the deploying of the application software to the target node in the server cluster includes:

6. The hybrid deployment method for the server cluster according to claim 1, wherein the outputting the corresponding test result to schedule the target node deployed in the server cluster based on the test result comprises:

7. The hybrid deployment method of the server cluster according to claim 6, wherein the resource scheduling server is configured to perform the following:

8. A server cluster hybrid deployment apparatus, comprising:

9. The server cluster hybrid deployment device of claim 8, further comprising:

10. The server cluster hybrid deployment device according to claim 8, wherein the system verification means includes a preset software system applicability verification means for hardware invocation;

correspondingly, the system verification module comprises:

11. The hybrid deployment device of server cluster according to claim 8, wherein the system verification means includes a preset support verification means oriented to a software system;

correspondingly, the system verification module comprises:

12. The server cluster hybrid deployment device of claim 8, wherein the application deployment module comprises:

13. The server cluster hybrid deployment device of claim 8, wherein the performance testing module comprises:

14. The server cluster hybrid deployment device of claim 13, wherein the resource scheduling server comprises:

15. A cluster management node comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the hybrid deployment method of a server cluster according to any one of claims 1 to 7 when executing the program.

16. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the server cluster hybrid deployment method of any one of claims 1 to 7.

17. A mixed deployment and scheduling system of a server cluster is characterized by comprising the server cluster and a resource scheduling server;

the server cluster includes: a designated locale version node, a non-designated locale version node, and the cluster management node of claim 15, each contained within a cluster of servers;