Server partitioning method, server and storage medium

Abstract

The invention discloses a server partitioning method, a server and a storage medium, and relates to the technical field of servers, and the method comprises the steps: generating a plurality of corresponding partitioning strategies according to at least one piece of feature information of each business scene and a corresponding hardware parameter, and optimizing the partitioning strategies based on at least one target optimization parameter, according to the server partition method and device, the corresponding target partition strategy is determined from the multiple partition strategies, the server is divided according to the target partition strategy, at least two target partitions are obtained, the technical problem that a server partition method cannot be suitable for various service environments is solved, the flexibility and hardware compatibility of the server partition method are improved, and the server partition method and device are suitable for being applied to various service environments. And the method is suitable for various business scenes.

Description

Technical Field

[0001] This application relates to the technical field of servers, and particularly to a server partitioning method, a server, and a storage medium. Background Art

[0002] With the vigorous development of technology, servers, as data centers, are gradually developing towards hardware heterogeneity and diverse business scenarios. In order to enable servers to meet the business requirements of different business scenarios, servers can be partitioned.

[0003] The existing server partitioning methods mainly include the partitioning method using a templated configuration tool, the partitioning method using a basic performance analysis tool, the partitioning method based on a rule engine, the partitioning method based on machine learning, and the partitioning method based on business awareness, etc. The above methods have poor flexibility and poor hardware compatibility, and are not applicable to diverse business environments. Summary of the Invention

[0004] This application provides a server partitioning method, a server, and a storage medium to at least solve the problem that the server partitioning method in the related art cannot be applied to multiple business environments.

[0005] This application provides a server partitioning method, including:

[0006] Obtaining the hardware parameters of each hard disk and at least one feature information of at least one business scenario;

[0007] Generating multiple partitioning policies based on each hardware parameter and each feature information;

[0008] Determining a target partitioning policy based on each partitioning policy and at least one target optimization parameter;

[0009] Determining at least two target partitions and the regional parameters of each target partition based on the target partitioning policy; wherein, the regional parameters include target hardware parameters and / or target feature information;

[0010] Partitioning the server based on the regional parameters of each target partition to obtain at least two target partitions.

[0011] This application also provides a server partitioning device, including:

[0012] A first obtaining module, configured to obtain the hardware parameters of each hard disk and at least one feature information of at least one business scenario;

[0013] A first generating module, configured to generate multiple partitioning policies based on each hardware parameter and each feature information;

[0014] A first determining module, configured to determine a target partitioning policy based on each partitioning policy and at least one target optimization parameter;

[0015] A second determination module, configured to determine at least two target partitions and regional parameters of each target partition based on a target partitioning policy; wherein, the regional parameters include target hardware parameters and / or target feature information;

[0016] A partitioning module, configured to partition a server based on the regional parameters of each target partition to obtain at least two target partitions.

[0017] This application also provides a server, including: a memory, configured to store a computer program; a processor, configured to implement the steps of any of the above server partitioning methods when executing the computer program.

[0018] This application also provides a computer-readable storage medium, in which a computer program is stored, and wherein the computer program implements the steps of any of the above server partitioning methods when executed by a processor.

[0019] This application also provides a computer program product, including a computer program, and the computer program implements the steps of any of the above server partitioning methods when executed by a processor.

[0020] Through this application, multiple corresponding partitioning policies can be generated according to at least one feature information and corresponding hardware parameters of each service scenario, and a corresponding target partitioning policy can be determined from multiple partitioning policies based on at least one target optimization parameter, and a server can be partitioned according to the target partitioning policy to obtain at least two target partitions. Therefore, the technical problem that the server partitioning method in the related art cannot be applied to multiple service environments can be solved, the flexibility and hardware compatibility of the server partitioning method are improved, and it can be applied to multiple service scenarios. Description of the Drawings

[0021] To more clearly illustrate the embodiments of this application, the following will briefly introduce the drawings required for the embodiments. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a schematic diagram of the architecture of a server provided by an embodiment of this application;

[0023] Figure 2 It is one of the flow diagrams of the server partitioning method provided by an embodiment of this application;

[0024] Figure 3 It is the second flow diagram of the server partitioning method provided by an embodiment of this application;

[0025] Figure 4Schematic diagram of the server partitioning system provided by the embodiment of the present application;

[0026] Figure 5 Schematic diagram of the server partitioning device provided by the embodiment of the present application;

[0027] Figure 6 Schematic diagram of the server provided by the embodiment of the present application. Detailed implementation manners

[0028] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0029] It should be noted that in the description of the present application, the terms "include", "comprise" or any other variant thereof are intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. The terms "first", "second", etc. in the present application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0030] Server partitioning refers to the process of dividing a physical server into multiple independent virtual server spaces.

[0031] With the vigorous development of technology, as the data center, the server is gradually developing towards hardware heterogeneity and business scenario diversification. In order to enable the server to meet the business requirements of different business scenarios, the server can be partitioned.

[0032] The related server partitioning methods mainly include the partitioning method of the templated configuration tool, the partitioning method of the basic performance analysis tool, the partitioning method based on the rule engine, the partitioning method based on machine learning, and the partitioning method based on business awareness, etc. The above methods all have the characteristics of poor flexibility and poor hardware compatibility and cannot be applied to diverse business environments.

[0033] For example, an automated server configuration method includes hardware scanning, generating a device tree, rule engine matching, and outputting a partitioning scheme. This method can collect information such as disk capacity and model through the Smart Platform Management Interface (SMART / IPMI) interface, define a partitioning template using an XML rule file, and select the disk with the largest available space based on an algorithm (such as the greedy algorithm) to generate a partitioning scheme. The partitioning rule template of this automated server configuration method is relatively single and cannot be applied to different business scenarios. Moreover, the optimization objective is single. For example, the optimization objective includes maximizing the space utilization rate and cannot achieve other optimization objectives, resulting in an increased risk of resource fragmentation and lower flexibility and efficiency of the server partitioning method.

[0034] To solve the above problems, the present application provides a server partitioning method, a server, and a storage medium. It can generate corresponding multiple partitioning policies according to at least one characteristic information of each business scenario and the corresponding hardware parameters, determine the corresponding target partitioning policy from the multiple partitioning policies based on at least one target optimization parameter, and partition the server according to the target partitioning policy to obtain at least two target partitions, improving the flexibility and hardware compatibility of the server partitioning method and being applicable to multiple business scenarios.

[0035] To enable those skilled in the art of this technology to better understand the solution of the present application, the following further details the present application in conjunction with the accompanying drawings and specific embodiments.

[0036] Combined with the specific application environment architecture or specific hardware architecture on which the execution of the server partitioning method depends, the specific application environment architecture or specific hardware architecture is described herein. Refer to Figure 1 , Figure 1 which is a schematic diagram of the server architecture.

[0037] As Figure 1 shown, the server includes at least one central processing unit ( Figure 1 only two are shown in Figure 1 ), at least one hard disk (

[0038] only two are shown in

[0039] ), and the hard disk refers to the device in the server for storing data. Figure 1 To enable the server to meet the business requirements of different business scenarios, the server can be partitioned, that is, the server is divided into one or more regions, and at least one central processing unit, hard disk, and network resources, etc. are allocated to each region, so that each region of the server can form an independent virtual environment.

[0040] Figure 2 Schematic diagram of the server partitioning method provided by the embodiment of this application Figure 1 As Figure 2 shown, the embodiment of this application provides a server partitioning method, and the method is described in detail as follows:

[0041] S201: Obtain the hardware parameters of each hard disk and at least one feature information of at least one service scenario.

[0042] Optionally, the server includes at least one central processing unit and at least one hard disk, and the server can receive services under one or more service scenarios. By parsing the hardware structure of the server and obtaining the hardware topology information of the server, the hardware parameters of each hard disk in the server are obtained. Among them, the above hardware parameters include but are not limited to at least one of the disk controller type, the number of disks, the disk type, the disk location, the connection relationship between disks, the I / O path of the disk, the domain to which the disk belongs, and the performance index of the disk, etc. The disk type is such as Non-Volatile Memory Express (NVMe), SAS HDD, etc., and the performance index is such as Input / Output Operations Per Second (IOPS), etc. Parse each service scenario, and convert the service requirements of each service scenario into specific storage feature requirements to obtain at least one feature information of each service scenario.

[0043] Optionally, the service scenario includes but is not limited to at least one of Online Transaction Processing (OLTP) and Online Analytical Processing (OLAP). The feature information includes but is not limited to at least one of the Redundant Array of Independent Disks (RAID) level, IOPS, and file system type.

[0044] Optionally, by parsing the RAID card and NVMe mapping table, obtain the hardware parameters of each hard disk, and organize the hardware parameters into structured data to facilitate the determination of the partitioning strategy.

[0045] S202: Generate multiple partitioning strategies based on each hardware parameter and each feature information.

[0046] Optionally, based on the feature information of each service scenario, determine the target hardware parameters matching each service scenario from the hardware parameters of each hard disk, and generate multiple partitioning strategies based on the feature information and target hardware parameters of each service scenario.

[0047] Among them, the partitioning strategy includes, but is not limited to, the number of server partitions and the partitioning parameters of each target partition. The partitioning parameters include, but are not limited to, at least one of the characteristic information of the business scenarios that the target partition can handle and the configured hardware parameters.

[0048] S203: Determine the target partitioning strategy based on each partitioning strategy and at least one target optimization parameter.

[0049] Optionally, screen each partitioning strategy based on at least one target optimization parameter to determine the target partitioning strategy.

[0050] Optionally, determine the scores of each partitioning strategy based on at least one target optimization parameter, and determine the partitioning strategy with the highest score as the target partitioning strategy.

[0051] S204: Based on the target partitioning strategy, determine at least two target partitions and the regional parameters of each target partition; among them, the regional parameters include target hardware parameters and / or target characteristic information.

[0052] Optionally, parse the target partitioning strategy to determine at least two target partitions in the target partitioning strategy and the regional parameters of each target partition. The regional parameters include target hardware parameters and / or target characteristic information.

[0053] S205: Divide the server based on the regional parameters of each target partition to obtain at least two target partitions.

[0054] Optionally, divide each hardware resource (such as a central processing unit, hard disk, etc.) and / or network resource in the server based on the regional parameters of each target partition in the target partitioning strategy to obtain at least two target partitions.

[0055] Exemplarily, the target partitioning strategy includes 2 target partitions. Among them, the regional parameter 1 of target partition 1 includes: RAID6, file system type: File Allocation Table (FAT), high IOPS, and the business scenario is the OLTP scenario. The regional parameter 2 of target partition 2 includes: RAID10, file system type: New Technology File System (NTFS), high IOPS, and the business scenario is the OLAP scenario. The server is divided into two target partitions based on the above regional parameter 1 and regional parameter 2.

[0056] Optionally, generate specific partitioning configuration commands based on the regional parameters of each target partition, such as at least one of a RAID configuration command, a partition creation command, and a file system formatting command, and perform the partitioning operation of the server based on the partitioning configuration command to obtain at least two target partitions.

[0057] Exemplarily, the partition configuration command includes partitioning the hard disk sda into areas ranging from 1MB to 100GB, configuring the file system type as: journaling file system, and setting the mount options to disable the recording of access times for journaling files.

[0058] Optionally, based on each hardware parameter and each feature information, multiple partitioning policies are generated, including:

[0059] Based on the feature information of each business scenario, at least one target hardware parameter that matches the feature information is determined from each hardware parameter;

[0060] Based on the feature information of each business scenario and at least one target hardware parameter, multiple partitioning policies for each business scenario are generated.

[0061] Optionally, based on the feature information of each business scenario, at least one target hardware parameter that matches the feature information of each business scenario is determined from each hardware parameter. For each feature information in each business scenario, the corresponding target hardware parameters are traversed and combined for configuration to obtain multiple partitioning policies for each business scenario.

[0062] Exemplarily, the feature information of business scenario A includes a1, a2, and a3. Among them, the target hardware parameters that match a1 include b1 and b3, the target hardware parameters that match a2 include b2 and b3, and the target hardware parameters that match a3 include b1 and b4. Then the partitioning policy for business scenario A includes , , , , and .

[0063] Exemplarily, based on the topology structure of the server and each business scenario, multiple partitioning policies for each business scenario are generated by traversing the Raid levels satisfied in this business scenario, the file systems that meet the requirements of the business scenario, the hard disk capacity allocation, the business scenario optimization rules, etc.

[0064] By determining the performance, capacity, etc. characteristics of each hard disk through hardware parameters, combined with the feature information of the business scenario, different partitioning policies are configured and generated, so as to reasonably allocate hardware resources, while taking into account the specific requirements of the business scenario for performance, capacity, etc., and the above multiple partitioning policies can be used as input data for subsequent optimization decisions to improve the accuracy of the target partitioning policy.

[0065] Optionally, after obtaining the hardware parameters of each hard disk and at least one feature information of at least one business scenario, it includes:

[0066] Obtain at least one target optimization parameter;

[0067] Calculate the weights of the respective target optimization parameters based on the hardware parameters of each hard disk and at least one piece of characteristic information.

[0068] Optionally, obtain at least one target optimization parameter, where the target optimization parameter is used to indicate the capabilities of each area in the server to process services. Calculate the weights of the respective optimization parameters based on the hardware parameters of each hard disk and at least one piece of characteristic information.

[0069] Exemplarily, when the hardware parameters of each hard disk in the server indicate a high number of input / output operations per second (IOPS) and the service requirements of the service scenario indicate a high IOPS requirement, it is determined that the proportion of the target optimization parameter (such as the performance value) is high.

[0070] Optionally, when there are multiple target optimization parameters, the sum of the weights of the respective target optimization parameters is 1.

[0071] Dynamically adjust the weights of the respective target optimization parameters based on the hardware parameters of each hard disk and at least one piece of characteristic information, so as to dynamically allocate weights based on the priorities of the service scenarios, achieve flexible adjustment of the partitioning strategy under different service scenarios, enable the partitioning strategy to accurately match the service load requirements, and improve the overall performance and resource utilization rate of the partitioning strategy.

[0072] Optionally, the target optimization parameter includes at least one of a performance value, a fragmentation rate, and a redundancy level; correspondingly, the weight of the target optimization parameter includes at least one of a first weight corresponding to the performance value, a second weight corresponding to the fragmentation rate, and a third weight corresponding to the redundancy level.

[0073] Optionally, the target optimization parameter includes at least one of a performance value, a fragmentation rate, and a redundancy level, where the performance value (PerfScore) is used to indicate the degree of satisfaction of the partitioning strategy with the service performance requirements, and comprehensively evaluate the achievement rate of the storage performance metrics (such as IOPS, throughput, latency, etc.) in the partitioning measurement. The fragmentation rate (FragRate) is used to indicate the effective utilization rate of the storage resources. The redundancy level (RedundancyLevel) is used to indicate the data protection ability of the partitioning strategy. Correspondingly, the weight of the target optimization parameter includes at least one of a first weight corresponding to the performance value, a second weight corresponding to the fragmentation rate, and a third weight corresponding to the redundancy level.

[0074] Optionally, the redundancy level can be determined based on redundancy configuration parameters such as the RAID level and the replica strategy.

[0075] Optionally, when the target optimization parameter includes a performance value, a fragmentation rate, and a redundancy level, the sum of the first weight, the second weight, and the third weight is 1.

[0076] Table 1 shows a redundancy evaluation table.

[0077]

[0078] Table 1 Redundancy Evaluation Table

[0079] As can be seen from Table 1, the redundancies corresponding to different Raid levels are different, and the data risk levels they represent are also different.

[0080] It can be understood that when different Raid levels are mixed and configured in the partitioning strategy, the redundancy of the partitioning strategy can be comprehensively calculated by combining the redundancies of the above Raid levels.

[0081] Exemplarily, if the partitioning strategy adopts a mixed configuration, the comprehensive redundancy of the corresponding partitioning strategy is: .

[0082] Figure 3 The flowchart of the server partitioning method provided by the embodiment of the present application Figure 2 , as Figure 3 shown, step S203 of the server partitioning method includes:

[0083] S2031. Based on the characteristic information of each partitioning strategy and the target hardware parameters, determine at least one of the first parameter value of the performance value, the second parameter value of the fragmentation rate, and the third parameter value of the redundancy in each partitioning strategy;

[0084] S2032. Based on the first parameter value of the performance value, the second parameter value of the fragmentation rate, the third parameter value of the redundancy in each partitioning strategy, and the first weight corresponding to the first parameter value, the second weight corresponding to the second parameter value, and the third weight corresponding to the third parameter value, calculate the scores of each partitioning strategy;

[0085] S2033. Based on the scores of each partitioning strategy, determine the target partitioning strategy among multiple partitioning strategies.

[0086] Optionally, based on the characteristic information included in each partitioning strategy and the target hardware parameters, calculate at least one of the first parameter value of the performance value, the second parameter value of the fragmentation rate, and the third parameter value of the redundancy in each partitioning strategy. Based on the first parameter value of the performance value, the first weight corresponding to the first parameter value, the second parameter value of the fragmentation rate, the second weight corresponding to the second parameter value, the third parameter value of the redundancy, and the third weight corresponding to the third parameter value in each partitioning strategy, calculate the branches of each partitioning strategy. Based on the scores of each partitioning strategy, among multiple partitioning strategies, determine the partitioning strategy with the largest score as the target partitioning strategy.

[0087] Optionally, calculate at least one of the data of each partitioning strategy, the feature information included in each partitioning strategy, the target hardware parameters, the first weight corresponding to the performance value, the second weight corresponding to the fragmentation rate, and the third weight corresponding to the redundancy. Through non-dominated sorting and elitist retention strategies, with the disk channel and controller load as constraints, determine the scores of each partitioning strategy, and solve for the global optimal partitioning layout to determine the target partitioning strategy among multiple partitioning strategies.

[0088] Exemplarily, based on the feature information included in each partitioning strategy and the target hardware parameters, calculate at least one of the first parameter value of the performance value, the second parameter value of the fragmentation rate, and the third parameter value of the redundancy in the partitioning strategy, and determine the scores of each partitioning strategy based on the first weight, the second weight, and the third weight. Sort each partitioning strategy based on the scores (including ascending or descending order), and select the partitioning strategy with the largest score value in the sequence as the target partitioning strategy.

[0089] Optionally, based on the first parameter value of the performance value, the second parameter value of the fragmentation rate, the third parameter value of the redundancy in each partitioning strategy, as well as the first weight corresponding to the first parameter value, the second weight corresponding to the second parameter value, and the third weight corresponding to the third parameter value, calculate the scores of each partitioning strategy, including:

[0090] Multiply the first parameter value of the performance value in each partitioning strategy by the first weight to determine the performance evaluation value of each partitioning strategy;

[0091] Multiply the second parameter value of the fragmentation rate in each partitioning strategy by the second weight to determine the fragmentation rate evaluation value of each partitioning strategy;

[0092] Multiply the third parameter value of the redundancy in each partitioning strategy by the third weight to determine the redundancy evaluation value of each partitioning strategy;

[0093] Sum the performance evaluation value, the fragmentation rate evaluation value, and the redundancy evaluation value of each partitioning strategy to determine the score of each partitioning strategy.

[0094] Optionally, calculate the product of the first parameter value of the performance value in each partitioning strategy and the first weight, and determine it as the performance evaluation value of each partitioning strategy. Calculate the product of the second parameter value of the fragmentation rate in each partitioning strategy and the second weight, and determine it as the fragmentation rate evaluation value of each partitioning strategy. Calculate the product of the third parameter value of the redundancy in each partitioning strategy and the third weight, and determine it as the redundancy evaluation value of each partitioning strategy. Calculate the sum of the performance evaluation value, the fragmentation rate evaluation value, and the redundancy evaluation value of each partitioning strategy, and determine it as the score of each partitioning strategy.

[0095] Optionally, the fitness function of the branch that determines the partitioning strategy can be expressed by the following formula:

[0096] ;

[0097] where represents the first weight of the performance value, represents the second weight of the fragmentation rate, represents the third weight of the redundancy level, PerfScpre represents the performance value, FragRate represents the fragmentation rate, and RedundancyLevel represents the redundancy level.

[0098] Exemplarily, when the business requirement of the business scenario is high performance, the weights in terms of IOPS and latency performance (such as the performance value) can be increased, while the reasonable utilization of disk space (such as the fragmentation rate) and the proportion of data redundancy are evenly distributed. Resource and performance waste are reduced.

[0099] By finding the Pareto optimal solution among performance, capacity, and redundancy, the risk of resource fragmentation is reduced, the overall performance and resource utilization rate of the partitioning strategy are improved, and the performance, capacity, and redundancy balance ability of server partitioning are significantly improved.

[0100] Optionally, based on the scores of each partitioning strategy, determining the target partitioning strategy among multiple partitioning strategies includes:

[0101] Sorting each partitioning strategy based on the scores of each partitioning strategy and the preset sorting method to obtain a partitioning strategy sequence; where the preset sorting method includes ascending sorting or descending sorting;

[0102] In the partitioning strategy sequence, determining the partitioning strategy that meets the first condition as the target partitioning strategy;

[0103] where the first condition includes at least one of the following:

[0104] Being at the first place in the partitioning strategy sequence;

[0105] Being at the last place in the partitioning strategy sequence;

[0106] The score is greater than or equal to the first threshold.

[0107] Optionally, sort each partitioning strategy based on the branches of each partitioning strategy and the preset sorting method. The preset sorting method includes ascending sorting by score or descending sorting by score to obtain the corresponding partitioning strategy sequence, and in the partitioning strategy sequence, determine the partitioning strategy that meets the first condition as the target partitioning strategy. Among them, the first condition can be specifically set according to the actual situation.

[0108] Exemplarily, the first condition includes at least one of the following: being at the head of the partition policy sequence, being at the end of the partition policy sequence, and having a score greater than or equal to the first threshold.

[0109] Optionally, when obtaining the partition policy sequence in ascending order of scores, the partition policy at the end of the partition policy sequence is determined as the target partition policy.

[0110] Optionally, when obtaining the partition policy sorting in descending order of branches, the partition policy at the head of the partition policy sequence is determined as the target partition policy.

[0111] Optionally, obtain the first threshold, and determine the partition policies in the partition policy sequence whose scores are greater than or equal to the first threshold as the target partition policies.

[0112] Optionally, the first threshold can be specifically set according to the actual situation. For example, when the first threshold is 0.8, the partition policies in the partition policy sequence with scores greater than or equal to 0.8 can be determined as the target partition policies. Or, when the first threshold is 0.9, correspondingly, the partition policies in the partition policy sequence with scores greater than or equal to 0.9 can be determined as the target partition policies.

[0113] Exemplarily, the first threshold can be determined based on the scores of the partition policies in the partition policy sequence.

[0114] For example, when obtaining the partition policy sequence in ascending order of scores, the first threshold is the score at the 10% position in the partition policy sequence. Correspondingly, the partition policies in the partition policy sequence with scores in the top 10% can be determined as the target partition policies. Another example is that the first threshold is the score at the 15% position in the partition policy sequence. Correspondingly, the partition policies in the partition policy sequence with scores in the top 15% can be determined as the target partition policies.

[0115] Optionally, when the number of target partition policies is greater than one, after determining the target partition policies based on each partition policy and at least one target optimization parameter, it includes:

[0116] In response to receiving a partition instruction, parse the partition instruction to obtain the first target partition policy carried by the partition instruction; the target partition policy includes the first target partition policy;

[0117] Among the target partition policies, update the target partition policies that do not match the first target partition policy to the first alternative partition policies;

[0118] Or,

[0119] Select a second target partition policy among the target partition policies;

[0120] In each target partitioning policy, update each target partitioning policy that does not match the second target partitioning policy to the second alternative partitioning policy.

[0121] Optionally, when the number of target partitioning policies is greater than one, in response to receiving a partitioning instruction, parse the partitioning instruction to obtain the first target partitioning policy carried by the partitioning instruction, so as to perform a server partitioning operation according to the first target partitioning policy, and update each target partitioning policy that does not match the first target partitioning policy (which can also be referred to as a non-first target partitioning policy) in each target partition to the first alternative partitioning policy.

[0122] Among them, the partitioning instruction can be an instruction that instructs the user to specify the first target partitioning policy as the target partitioning policy for performing the server partitioning operation among the target partitioning policies.

[0123] Optionally, the partitioning instruction can be an instruction sent by the user through a user terminal, or an instruction generated by the user performing operations such as clicking or dragging on the current terminal.

[0124] Optionally, when performing a server partitioning operation based on the first target partitioning policy and determining a partitioning verification failure notification, select a third target partitioning policy from the first alternative partitioning policies, so as to perform a server partitioning operation according to the third target partitioning policy, thereby improving the flexibility and hardware compatibility of the server partitioning method.

[0125] Optionally, when the number of target partitioning policies is greater than one, randomly select a second target partitioning policy among the target partitioning policies, so as to perform a server partitioning operation according to the second target partitioning policy, and update each target partitioning policy that does not match the second target partitioning policy (which can also be referred to as a non-second target partitioning policy) in each target partitioning policy to the second alternative partitioning policy.

[0126] Optionally, the target partitioning policy includes a first target partitioning policy and a second target partitioning policy.

[0127] Optionally, when performing a server partitioning operation based on the second target partitioning policy and determining a partitioning verification failure notification, select a fourth target partitioning policy from the second alternative partitioning policies, so as to perform a server partitioning operation according to the fourth target partitioning policy, thereby improving the flexibility and hardware compatibility of the server partitioning method.

[0128] In some embodiments, partitioning at least two target partitions based on a target partitioning policy includes:

[0129] Determine the boundaries of each target partition based on the hardware parameters of the target partition.

[0130] Optionally, the physical boundaries of each hard disk can be determined based on the hardware parameters of each hard disk. Through the hardware parameters in the target partition, the boundaries of the target partition can be determined, thereby avoiding cross-controller partitioning or allocating partitions on high-latency paths, and making the target partition conform to the actual layout rules of the physical hardware.

[0131] Optionally, obtain the hardware parameters of each hard disk and at least one characteristic information of at least one service scenario, including:

[0132] Call the first interface to extract the hardware parameters of each hard disk;

[0133] Obtain at least one service scenario and determine the characteristic information mapped to each service scenario.

[0134] Optionally, call the first interface to extract the hardware parameters of each hard disk, where the first interface can be the Redfish Scalable Platforms Management API (RedFish API). Obtain at least one service scenario that the server can handle and determine the characteristic information mapped to each service scenario, so as to determine the configurable hardware parameters of each service scenario based on the above characteristic information.

[0135] Exemplarily, the hardware parameters obtained by calling the Redfish Scalable Platforms Management API include: controller: A-xxx, bay: 0-1, type: NVMe, iops: 550000, and bay: 2-3, type: SAS hard disk (SAS_HDD), iops: 180.

[0136] Optionally, the hardware parameters also include the path of the hard disk.

[0137] Exemplarily, by inputting the service scenario name: OLTP, and the requirements of the service scenario (REQUIRES): PartitionPolicy, the raid level, the minimum number of input / output operations per second (iops), and the recommended file system type (recommended_fs), etc. can be obtained.

[0138] Optionally, after dividing at least two target partitions based on the target partition policy, it includes:

[0139] Collect the check values of each target partition;

[0140] When the verification values of the target partitions match the corresponding area parameters, a partition verification success notification is generated and displayed.

[0141] Optionally, collect the verification values of each target partition. When the verification values of the target partitions match the area parameters corresponding to the target partitions, generate a partition verification success notification and display it.

[0142] Optionally, the verification values include hardware parameters and / or feature information.

[0143] It can be understood that when the verification values of one or more target partitions do not match the area parameters corresponding to the target partitions, a partition verification failure notification is generated and displayed.

[0144] By obtaining the verification values of the target partitions, it is possible to check whether the partition layout conforms to hardware topology constraints and whether it meets parameters such as the performance requirements of the business scenario, so that the partition policy can operate stably in actual deployment, improving the stability and efficiency of the partition policy.

[0145] Figure 4 A structural schematic diagram of a server partitioning system is provided.

[0146] See Figure 4, the server partitioning system includes a hardware topology acquisition module, a business scenario feature extraction module, a case splitting strategy generation module, a target strategy optimization module, and a partitioning and verification module. Among them, the hardware topology acquisition module includes an interface call unit, a structure parsing unit, a hardware parameter acquisition unit, and a structuring unit. The interface call unit is used to call an interface to obtain the hardware topology structure. The structure parsing unit is used to parse the hardware topology structure. The hardware parameter acquisition unit is used to acquire hardware parameters. The structuring unit is used to organize the hardware parameters into structured parameters. The business scenario feature extraction module includes a feature information extraction unit, a mapping unit, and a weight adjustment unit. Among them, the feature information extraction unit is used to determine the feature information of each business scenario. The mapping unit is used to establish a mapping relationship between each business scenario and the feature information of each business scenario. The weight adjustment unit is used to dynamically adjust the weights of each target optimization parameter based on the feature information. The case splitting strategy generation module includes a matching unit, a strategy generation unit, and a target optimization unit. Among them, the matching unit is used to determine the hardware parameters that match the feature information of each business scenario. The strategy generation unit is used to generate the partitioning strategies of each business scenario. The target optimization unit is used to determine the optimization rules of each business scenario in combination with each target optimization parameter. The target strategy optimization module includes a calculation unit, a sorting unit, and a screening unit. Among them, the calculation unit is used to obtain each partitioning strategy, each target optimization parameter, and the weights, and calculate the scores of each partitioning strategy. The sorting unit is used to sort each partitioning strategy according to the non-dominated sorting and elitist retention strategies. The screening unit is used to determine the target partitioning strategy among each partitioning strategy. The partitioning and verification module includes a command generation unit, a verification unit, and an output unit. Among them, the command generation unit is used to generate the configuration commands of each target partition. The verification unit is used to obtain the verification values of each target partition and perform verification. The output unit is used to output the verification result (including verification success or verification failure).

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0148] Figure 5 It is a schematic structural diagram of the server partitioning device provided by the embodiment of the present application. As Figure 5 shown, the embodiment of the present application also provides a server partitioning device, including:

[0149] A first acquisition module 501, configured to acquire the hardware parameters of each hard disk and at least one feature information of at least one business scenario;

[0150] A first generation module 502, configured to generate a plurality of partitioning strategies based on each hardware parameter and each feature information;

[0151] The first determination module 503 is configured to determine a target partitioning policy based on each partitioning policy and at least one target optimization parameter;

[0152] The second determination module 504 is configured to determine at least two target partitions and the regional parameters of each target partition based on the target partitioning policy; wherein, the regional parameters include target hardware parameters and / or target feature information;

[0153] The partitioning module 505 is configured to partition the server based on the regional parameters of each target partition to obtain at least two target partitions.

[0154] Optionally, the generation module 502 includes:

[0155] The first determination unit is configured to determine at least one target hardware parameter that matches each feature information among each hardware parameter based on the feature information of each service scenario;

[0156] The generation unit is configured to generate multiple partitioning policies for each service scenario based on the feature information of each service scenario and at least one target hardware parameter.

[0157] Optionally, the server partitioning device includes:

[0158] The second acquisition module is configured to acquire at least one target optimization parameter;

[0159] The calculation module is configured to calculate the weight of each target optimization parameter based on the hardware parameters of each hard disk and at least one feature information.

[0160] Optionally, the target optimization parameter includes at least one of a performance value, a fragmentation rate, and a redundancy; correspondingly, the weight of the target optimization parameter includes at least one of a first weight corresponding to the performance value, a second weight corresponding to the fragmentation rate, and a third weight corresponding to the redundancy;

[0161] Optionally, the first determination module 503 includes:

[0162] The second determination unit is configured to determine at least one of a first parameter value of the performance value, a second parameter value of the fragmentation rate, and a third parameter value of the redundancy in each partitioning policy based on the feature information of each partitioning policy and the target hardware parameter;

[0163] The calculation unit is configured to calculate the score of each partitioning policy based on the first parameter value of the performance value, the second parameter value of the fragmentation rate, the third parameter value of the redundancy in each partitioning policy, and the first weight corresponding to the first parameter value, the second weight corresponding to the second parameter value, and the third weight corresponding to the third parameter value;

[0164] The third determination unit is configured to determine the target partitioning policy among multiple partitioning policies based on the scores of each partitioning policy.

[0165] Optionally, the calculation unit is specifically configured to:

[0166] Determine the product of the first parameter value of the performance value in each partitioning policy and the first weight as the performance evaluation value of each partitioning policy;

[0167] Determine the product of the second parameter value of the fragmentation rate in each partitioning policy and the second weight as the fragmentation rate evaluation value of each partitioning policy;

[0168] Determine the product of the third parameter value of the redundancy in each partitioning policy and the third weight as the redundancy evaluation value of each partitioning policy;

[0169] Determine the sum of the performance evaluation value, the fragmentation rate evaluation value, and the redundancy evaluation value of each partitioning policy as the score of each partitioning policy.

[0170] Optionally, the third determination unit is specifically configured to:

[0171] Sort each partitioning policy based on the scores of each partitioning policy and a preset sorting method to obtain a partitioning policy sequence; wherein, the preset sorting method includes an ascending sorting method or a descending sorting method;

[0172] In the partitioning policy sequence, determine the partitioning policy that meets the first condition as the target partitioning policy;

[0173] Wherein, the first condition includes at least one of the following:

[0174] Located at the first position in the partitioning policy sequence;

[0175] Located at the last position in the partitioning policy sequence;

[0176] The score is greater than or equal to the first threshold;

[0177] Optionally, the server partitioning device includes:

[0178] A parsing module, configured to parse the partitioning instruction in response to receiving the partitioning instruction to obtain the first target partitioning policy carried by the partitioning instruction; the target partitioning policy includes the first target partitioning policy;

[0179] A first update module, configured to update each target partitioning policy that does not match the first target partitioning policy to a first alternative partitioning policy among each target partitioning policy;

[0180] Or,

[0181] A screening module, configured to select a second target partitioning policy among each target partitioning policy;

[0182] A second update module, configured to update, in each target partitioning policy, each target partitioning policy that does not match the second target partitioning policy to a second alternative partitioning policy.

[0183] Optionally, the first acquisition module 501 includes:

[0184] An extraction unit, configured to call a first interface to extract hardware parameters of each hard disk;

[0185] An acquisition unit, configured to acquire at least one service scenario and determine characteristic information mapped to each service scenario.

[0186] Optionally, the server partitioning device includes:

[0187] An acquisition module, configured to acquire check values of each target partition;

[0188] A second generation module, configured to generate and display a partition check success notification when the check value of each target partition matches the corresponding area parameter.

[0189] For the description of the features in the embodiments corresponding to the server partitioning device, reference may be made to the relevant descriptions of the embodiments corresponding to the server partitioning method, which will not be elaborated here one by one.

[0190] Figure 6 This is a schematic structural diagram of the server provided by this application. As Figure 6 shown, the server 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the server 60 further includes a communication component 603. Among them, the processor 601, the memory 602, and the communication component 603 are connected through a bus.

[0191] In a specific implementation process, at least one processor 601 executes computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above-mentioned server partitioning method embodiment.

[0192] For the specific implementation process of the processor 601, reference may be made to the above-mentioned method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0193] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the application can be directly implemented by the execution of the hardware processor, or can be implemented by the combination of the hardware and software modules in the processor.

[0194] The memory may include a random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0195] The bus may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0196] The embodiments of the present application further provide a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above embodiments of the server partitioning method when running.

[0197] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs, and other media that can store computer programs.

[0198] The embodiments of the present application further provide a computer program product, the above computer program product includes a computer program, and when the computer program is executed by a processor, the steps in any one of the above embodiments of the server partitioning method are implemented.

[0199] An embodiment of the present application also provides another computer program product, including a non-volatile computer-readable storage medium storing a computer program, and the computer program, when executed by a processor, implements the steps in any of the above server partitioning method embodiments.

[0200] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0201] The above has introduced in detail a server partitioning method, a server, and a storage medium provided by this application. Specific examples are used herein to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A server partitioning method, characterized in that: include: Obtaining hardware parameters of each hard disk and at least one feature information of at least one business scenario; Based on the hardware parameters and the feature information, generate multiple partition strategies; Determining a target partitioning strategy based on each of the partitioning strategies and at least one target optimization parameter; Based on the target partition strategy, determining at least two target partitions and regional parameters of each of the target partitions; wherein the regional parameters include target hardware parameters and / or target feature information; The server is divided based on the area parameters of each of the target partitions to obtain the at least two target partitions.

2. The server partitioning method according to claim 1, characterized in that: The generating of multiple partition strategies based on the hardware parameters and the feature information includes: Based on the characteristic information of each of the business scenarios, determining at least one target hardware parameter matching each of the characteristic information from among the hardware parameters; Based on the characteristic information of each business scenario and the at least one target hardware parameter, multiple partition strategies for each business scenario are generated.

3. The server partitioning method according to claim 1, characterized in that: After obtaining the hardware parameters of each hard disk and at least one feature information of at least one business scenario, the method includes: obtaining at least one target optimization parameter; Based on the hardware parameters of each hard disk and the at least one feature information, a weight of each target optimization parameter is calculated.

4. The server partitioning method according to claim 3, characterized in that: The target optimization parameter includes at least one of a performance value, a fragmentation rate, and a redundancy; correspondingly, the weight of the target optimization parameter includes at least one of a first weight corresponding to the performance value, a second weight corresponding to the fragmentation rate, and a third weight corresponding to the redundancy; The determining of a target partitioning strategy based on each of the partitioning strategies and at least one target optimization parameter comprises: Based on the characteristic information of each of the partition strategies and the target hardware parameters, determining at least one of a first parameter value of a performance value, a second parameter value of a fragmentation rate, and a third parameter value of redundancy in each of the partition strategies; Based on the first parameter value of the performance value in each partition strategy, the second parameter value of the fragmentation rate, the third parameter value of the redundancy, and the first weight corresponding to the first parameter value, the second weight corresponding to the second parameter value, and the third weight corresponding to the third parameter value, the score of each partition strategy is calculated; The target partition strategy is determined from among the multiple partition strategies based on the scores of the partition strategies.

5. The server partitioning method according to claim 4, characterized in that: The score of each partition strategy is calculated based on the first parameter value of the performance value in each partition strategy, the second parameter value of the fragmentation rate, the third parameter value of the redundancy, and the first weight corresponding to the first parameter value, the second weight corresponding to the second parameter value, and the third weight corresponding to the third parameter value, including: Determine the product of the first parameter value of the performance value in each of the partition strategies and the first weight as the performance evaluation value of each of the partition strategies; Determine the product of the second parameter value of the fragmentation rate in each of the partition strategies and the second weight as the fragmentation rate evaluation value of each of the partition strategies; Determine the product of the third parameter value of the redundancy in each of the partition strategies and the third weight as the redundancy evaluation value of each of the partition strategies; The sum of the performance evaluation value, the fragmentation rate evaluation value and the redundancy evaluation value of each partition strategy is determined as the score of each partition strategy.

6. The server partitioning method according to claim 4, characterized in that: The step of determining the target partition strategy from the plurality of partition strategies based on the scores of the partition strategies comprises: Based on the scores of the partition strategies and the preset sorting method, the partition strategies are sorted to obtain a partition strategy sequence; wherein the preset sorting method includes an ascending sorting method or a descending sorting method; In the partition strategy sequence, determining a partition strategy that meets a first condition as a target partition strategy; The first condition includes at least one of the following: Located first in the partition strategy sequence; Located at the end of the partition strategy sequence; The score is greater than or equal to a first threshold; Correspondingly, when the number of the target partition strategies is greater than one, after determining the target partition strategy based on each of the partition strategies and at least one target optimization parameter, the method includes: In response to receiving a partition instruction, parsing the partition instruction to obtain a first target partition strategy carried by the partition instruction; the target partition strategy includes the first target partition strategy; In each of the target partition strategies, each target partition strategy that does not match the first target partition strategy is updated to a first candidate partition strategy; or, Among the target partition strategies, selecting a second target partition strategy; Among the target partitioning strategies, each target partitioning strategy that does not match the second target partitioning strategy is updated to a second candidate partitioning strategy.

7. The server partitioning method according to any one of claims 1 to 6, characterized in that: After dividing at least two target partitions based on the target partition strategy, the method includes: Collecting the checksum value of each target partition; When the verification value of each target partition matches the corresponding regional parameter, a partition verification success notification is generated and displayed.

8. A server partitioning device, characterized in that: include: A first acquisition module, used to acquire hardware parameters of each hard disk and at least one feature information of at least one business scenario; A first generating module, used for generating a plurality of partitioning strategies based on the hardware parameters and the characteristic information; A first determination module, configured to determine a target partitioning strategy based on each of the partitioning strategies and at least one target optimization parameter; A second determination module is used to determine at least two target partitions and regional parameters of each of the target partitions based on the target partition strategy; wherein the regional parameters include target hardware parameters and / or target feature information; A partitioning module is used to divide the server based on the area parameters of each target partition to obtain the at least two target partitions.

9. A server, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the server partitioning method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the server partitioning method according to any one of claims 1 to 7.

Images