Storage system management method and device, electronic equipment, medium and product

Abstract

The application discloses a management method and device of a storage system, electronic equipment, medium and product, relates to the technical field of system management, and determines a target global specification parameter according to a real-time node running state and current configuration information of the storage system to perform specification management. Compared with static management in the related art, the real-time state of the storage system can be effectively adapted, and therefore, the accuracy of specification management is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of system management, and particularly relates to a management method and device of a storage system, an electronic device, a medium and a product. BACKGROUND

[0002] In an application scenario of an enterprise-level storage system, such as a cloud computing platform, a data center, or a big data analysis platform, the reliability of the storage system has a high requirement.

[0003] In the related art, a static management manner such as manual configuration or a preset configuration file is used to manage the specifications of the storage system. However, this method cannot accurately adapt to the state of the storage system, resulting in low management accuracy. SUMMARY

[0004] The present application provides a management method and device of a storage system, an electronic device, a medium and a product to at least solve the problem of low management accuracy in the related art.

[0005] The present application provides a management method of a storage system, comprising: obtaining node running states corresponding to each storage node of a clustered storage system through an event listening mechanism; in response to a change in any one node running state, obtaining current device configuration information corresponding to each storage node; respectively assigning corresponding weights to each storage node according to the node running states and the current device configuration information; obtaining target global specification parameters of the storage system through a preset calculation rule calculation according to the weights, the node running states, and the current device configuration information; and performing specification management on the storage system according to the target global specification parameters.

[0006] The present application also provides a management device of a storage system, comprising: a listening module configured to obtain node running states corresponding to each storage node of a clustered storage system through an event listening mechanism; an obtaining module configured to, in response to a change in any one node running state, obtain current device configuration information corresponding to each storage node; an assigning module configured to respectively assign corresponding weights to each storage node according to the node running states and the current device configuration information; a calculation module configured to obtain target global specification parameters of the storage system through a preset calculation rule calculation according to the weights, the node running states, and the current device configuration information; and a management module configured to perform specification management on the storage system according to the target global specification parameters.

[0007] The present application also provides an electronic device, comprising: a memory configured to store a computer program; and a processor configured to execute the computer program to implement the steps of any one of the above-mentioned management methods of a storage system.

[0008] The application further provides a nonvolatile computer readable storage medium, and the nonvolatile computer readable storage medium stores a computer program.

[0009] The application further provides a computer program product, which comprises a computer program.

[0010] According to the application, the target global specification parameter is determined according to the real-time node running state and the current configuration information of the storage system, and compared with the static management in the related art, the real-time state of the storage system can be effectively adapted, and thus the accuracy of the specification management is improved. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the application, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0012] Figure 1 An application scenario diagram of a storage system management method provided by the embodiments of the application is shown.

[0013] Figure 2 A flowchart of a storage system management method provided by the embodiments of the application is shown.

[0014] Figure 3 A flowchart of another storage system management method provided by the embodiments of the application is shown.

[0015] Figure 4 A schematic diagram of a listening processing provided by the embodiments of the application is shown.

[0016] Figure 5 A schematic diagram of weight calculation provided by the embodiments of the application is shown.

[0017] Figure 6 A schematic diagram of specification management provided by the embodiments of the application is shown.

[0018] Figure 7 A structural schematic diagram of a storage system management device provided by the embodiments of the application is shown.

[0019] Figure 8 A structural schematic diagram of another storage system management device provided by the embodiments of the application is shown.

[0020] Figure 9A structural schematic diagram of an electronic device is provided in the embodiments of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be clearly and completely described in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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 a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0022] It should be noted that, in the description of the present application, the terms “comprise”, “contain” or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. The terms “first”, “second” and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0023] In modern storage systems, a storage system is usually composed of multiple storage nodes to form a clustered architecture, supporting high availability, load balancing, and data redundancy, and other advanced functions. The storage system needs to adapt to complex hardware configuration changes (such as node online / offline, hardware expansion / downgrade, etc.) and dynamic business requirements (such as storage volume quantity, host connection quantity, etc. specification adjustment) in real time.

[0024] In combination with a scenario example, in a data center storage cluster, a multi-node storage system needs to dynamically adjust the maximum storage volume quantity and / or host connection quantity and other specifications according to the online storage node quantity and hardware configuration, to avoid resource over-provisioning or waste. In a cloud storage platform, the storage system needs to automatically adapt the performance specifications (such as the number of data read / write times per second IOPS, throughput, etc.) according to the user-subscribed hardware configuration (such as all-flash or hybrid storage). In edge computing and distributed storage, in a dynamic environment where storage nodes are frequently online / offline, the storage system needs to real-time perceive the hardware state and adjust the specifications to ensure service continuity. In summary, the specification management of the storage system directly affects the resource utilization, service stability and operation and maintenance efficiency, and therefore an intelligent and automated specification dynamic updating mechanism is urgently needed.

[0025] In order for those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments.

[0026] In combination with the specific application environment architecture on which the execution of the management method of the storage system depends, the specific application environment architecture is described herein. Refer to Figure 1 , Figure 1As shown in a scene diagram of an application scenario of the management method of the storage system, a specification parameter is used to perform specification management on an original storage system, so as to optimize the specification of the original storage system and obtain an optimized storage system.

[0027] In the related art, a specification parameter is determined by a static mode such as manual configuration or a preset configuration file, so as to perform specification management on a storage system.

[0028] However, the state of the storage system changes in real time, and the specification management by the static mode cannot adapt to the real-time state of the storage system, and thus a problem of low management accuracy occurs. For example, a large number of storage nodes of the storage system are offline at the current time, and the static mode cannot perceive this state change. If the specification management is performed according to the configuration of the static mode, the actual specification that can be provided by the storage system at the current time is much smaller than the configured specification. This deviation can cause a series of serious problems: on the one hand, the storage system can cause service overload, performance drop, or even system crash due to resource allocation exceeding the actual processing capacity; on the other hand, an upstream user or a scheduler can issue a task based on incorrect specification information, which can cause service quality accidents such as business timeout and data write failure. Therefore, how to accurately perform specification management is a key to ensure normal operation of the storage system.

[0029] Figure 2 As shown in a flowchart of the management method of the storage system provided by the embodiments of the present application, Figure 2 as shown in the flowchart, the embodiments of the present application provide a management method of a storage system, and the method is described in detail as follows.

[0030] S201, a node running state corresponding to each storage node of a clustered storage system is acquired by using an event listening mechanism.

[0031] For example, the event listening mechanism is an active and notification-based monitoring mode. The event listening mechanism is different from a passive periodic polling mode, and can continuously pay attention to the node running state of each storage node.

[0032] For example, the node running state includes at least one of the following: an offline state, an online state, or a service mode state, but is not limited to the above.

[0033] In combination with a scene example, each storage node is listened to in real time, so as to acquire the real-time node running state of the storage node, and thus dynamic management is accurately performed.

[0034] S202, in response to a change in any one node running state, current device configuration information corresponding to each storage node is acquired.

[0035] Exemplarily, the storage system includes a plurality of storage nodes, the specification of the storage system as a whole is determined by the sum of the specifications of the plurality of storage nodes, when the running state of any one node changes, the specification of the storage system as a whole changes, at this time, the specification management is used to adapt to the real-time state of the storage system.

[0036] Exemplarily, the current device configuration information is the current device attribute and capability parameter of the storage node, the device attribute and capability parameter affects the current available specification of the storage node, and further affects the specification of the storage system. By real-time acquisition of the current device information, the current specification of the storage system can be accurately managed.

[0037] S203, according to the node running state and the current device configuration information, a corresponding weight is respectively allocated to each storage node.

[0038] Exemplarily, the weight is used to quantify the contribution degree of each storage node to the specification of the clustered storage system at the current time.

[0039] Exemplarily, the weight is a value determined flexibly according to the node running state and the device configuration information, so as to accurately adapt to the current state of the storage system.

[0040] Combined with a scene example, for example, a storage node entering the service mode due to planned maintenance, if the hardware of the storage node itself has a high availability architecture such as dual controller and redundant power supply, the corresponding weight can be corrected upwards (such as from 0.5 to 0.7), because the reliability of service recovery is higher and the risk is lower. For example, a single-point architecture storage node entering the service mode due to failure, the weight can be adjusted downward. Compared with simple judgment, this dynamic weight allocation realizes accurate and gradient evaluation of the current residual service capability of each storage node.

[0041] S204, according to the weight, the node running state, and the current device configuration information, the target global specification parameter of the storage system is obtained through preset calculation rules.

[0042] Optionally, a reference value is determined in combination with the node running state and the current device configuration information, the product of the reference value and the weight is calculated to obtain an effective contribution value, the effective contribution values of the storage nodes are summed to obtain the target global specification parameter of the storage system as a whole.

[0043] Optionally, a hardware nominal high performance value is determined as a reference value for the online state node, and a conservative safety value is determined as a reference value for the offline state node and the service mode state node.

[0044] For example, the specification parameter is a quantitative index for measuring the service capability of the storage system, such as total IOPS (read-write times per second, representing random processing capability), total throughput (MB / s, representing sequential transmission capability), or total available capacity (TB), and the like.

[0045] S205, performing specification management on the storage system according to the target global specification parameter.

[0046] Optionally, the specification management provides a specification for reconfiguring the storage system, such as a performance specification, a capacity specification, a connection specification, or a computing specification, and the like.

[0047] In terms of performance, according to the new total IOPS and throughput specification, the I / O requests from different users or services are traffic shaped and priority scheduled to ensure that the total load does not exceed the current actual processing capability of the storage system, thereby avoiding overload and performance collapse. In terms of capacity, the storage space allocation of the storage system can be managed according to the new total available capacity, and when the used space approaches the new specification, an alarm can be triggered or a read-only mode can be entered to prevent data loss.

[0048] The management method of the storage system provided by the embodiments of the present application acquires the node running states of the storage nodes of the clustered storage system through an event listening mechanism; in response to any change in the node running state, the current device configuration information of the storage nodes is acquired; the corresponding weight is allocated to each storage node according to the node running state and the current device configuration information; the target global specification parameter of the storage system is obtained through a preset calculation rule according to the weight, the node running state, and the current device configuration information; and the specification management is performed on the storage system according to the target global specification parameter. The above scheme determines the target global specification parameter for specification management according to the real-time node running state and the current configuration information of the storage system, which can effectively adapt to the real-time state of the storage system, thereby improving the accuracy of the specification management.

[0049] On the basis of any one of the above embodiments, the following will be described in combination with Figure 3 The detailed process of the management of the storage system is described.

[0050] Figure 3 Another flowchart of the management method of the storage system provided by the embodiments of the present application is shown in FIG. 3. As shown in the figure, the method comprises the following steps. Figure 3

[0051] S301, acquiring the node running states of the storage nodes of the clustered storage system through an event listening mechanism.

[0052] ​One feasible implementation method is to obtain the node running status through the following steps: periodic heartbeat communication between the cluster management service and the agent program deployed on each storage node to monitor the node running status of each storage node; if no heartbeat information is received from a storage node within a preset time period, the node running status is determined to be offline; if heartbeat information is received from a preset number of storage nodes within a preset time period, the node running status is determined to be online; if heartbeat information is received from a preset number of storage nodes within a preset time period, the node running status is determined to be in service mode.

[0053] For example, a periodic heartbeat communication channel (e.g., sending a heartbeat packet every 3 seconds) is established between the cluster management service (e.g., a central control node) of the storage system and the agents deployed on each storage node. This design forms a distributed monitoring network, enabling the cluster management service to continuously monitor the operating status of the storage nodes.

[0054] Below, in conjunction with Figure 4 The process of listening in is explained.

[0055] Figure 4 This is a schematic diagram illustrating the monitoring process provided in an embodiment of this application. Figure 4 As shown, continuous heartbeat monitoring is performed based on preset duration and preset quantity. If no heartbeat is received within the preset duration, the system is determined to be offline. If the number of heartbeats received within the preset duration is greater than or equal to the preset quantity (i.e., a large number of heartbeats are received), the system is determined to be online. Conversely, if heartbeats are received but the number is small, less than the preset quantity, the system is determined to be in service mode.

[0056] In this feasible implementation, the heartbeat information of storage nodes is accurately quantified by preset duration and preset quantity to accurately determine the node operation status of storage nodes, thereby improving the accuracy of specification management.

[0057] S302. In response to a change in the operating status of any node, obtain the current device configuration information corresponding to each storage node.

[0058] One feasible implementation method is to obtain the current device configuration information by: sending a read request to the controller of each storage node through the management interface of each storage node to obtain the current device configuration information of each storage node; or, obtaining the current device configuration information of each storage node by parsing the virtual file of the storage node or the system device tree, wherein the system device tree is a data structure maintained by the storage system for storing hardware information.

[0059] Exemplarily, in one path of obtaining device configuration information, out-of-band communication is performed through a management interface of the storage node. The management interface is a separate management channel provided at the hardware level, such as an Intelligent Platform Management Interface (IPMI) or a Baseboard Management Controller (BMC) interface. Through the management interface, the cluster management service can directly send a standardized read request to the hardware controller of the storage node, so as to obtain Vital Product Data (VPD) information stored in the firmware of the controller, such as device model, serial number, firmware version, CPU, memory configuration, number of hard disks, or capacity. This path is independent of the main operating system running on the storage node, and even if the operating system of the storage node has crashed or is unresponsive, as long as the power supply of the management controller of the storage node is connected, the underlying hardware information can be obtained through the network.

[0060] Exemplarily, in another path of obtaining device configuration information, information is obtained by parsing a virtual file or a system device tree provided by the operating system of the storage node. In the operating system, the hardware configuration information of the system is exposed in the form of a virtual file under a specified directory, or the relationship between hardware components is described through a device tree structure. By reading and parsing these files, the hardware configuration recognized by the operating system can be obtained. This method usually has small overhead and fast response, but depends on the stable operation of the operating system.

[0061] In this feasible implementation manner, by setting multiple paths, the path for obtaining the current device configuration information can be determined according to different application scenarios, thereby improving the scenario coverage of storage system management.

[0062] S303, determining historical device configuration information from the database.

[0063] Exemplarily, after obtaining the device configuration information each time, the device configuration information is stored in the database for backtracking and reference.

[0064] Exemplarily, the historical device configuration information is historical obtained device configuration information, and the historical device configuration information is device configuration information that has been used for specification management.

[0065] S304, performing consistency verification processing by comparing the current device configuration information and the historical device configuration information to obtain a verification result, the verification result including verification pass or verification fail.

[0066] Exemplarily, the consistency verification is used to verify whether the device configuration information is changed unexpectedly, which may indicate that there is a problem, so as to find the abnormality in the current device configuration information in time and avoid the technical problem of low management accuracy caused by directly using the abnormal current configuration information for specification management.

[0067] In combination with a scene example, for example, the number of hard disks of a storage node suddenly changes from 24 in the historical record to 0 at present, which is obviously an abnormal situation.

[0068] In S305, if the verification result is passed, corresponding weights are respectively assigned to the storage nodes according to the node running state and the current device configuration information.

[0069] Exemplarily, the passed verification indicates that the current configuration information has a certain credibility, and the specification management using the current configuration information can improve the reliability of the specification management.

[0070] Based on the above embodiments, by the consistency verification processing, the specification management can be performed using the reliable current configuration information, and the current configuration information with low reliability is avoided to interfere with the specification management, so as to improve the accuracy of the specification management.

[0071] A feasible implementation manner can assign the weights by the following method, including: determining the basic weights of the storage nodes according to the node running state, wherein the first basic weight is assigned to the storage node in the offline state, the second basic weight is assigned to the storage node in the service mode state, and the third basic weight is assigned to the storage node in the online state, the third basic weight is greater than the second basic weight, and the second basic weight is greater than the first basic weight; determining the proportion of the online state from the node running state; determining a weight correction value according to the proportion of the online state and the current device configuration information; correcting the basic weight according to the weight correction value to obtain a plurality of corrected weights; performing normalization processing on the plurality of corrected weights to obtain a plurality of normalized weights; and assigning the plurality of normalized weights to the storage nodes.

[0072] Exemplarily, the initial basic weights are first given to the storage nodes according to the running states of the storage nodes themselves.

[0073] In combination with a scene example, for the storage node in the online state, the storage node is completely healthy and should fully contribute its ability. For the storage node in the service mode state, the storage node is partially limited in function, and the contribution degree should be correspondingly reduced. For the storage node in the offline state, the storage node is basically unavailable, and the contribution degree is reduced to the minimum.

[0074] Exemplarily, the proportion of the online state is used to evaluate the health degree of the whole cluster, and the proportion of the online state reflects the stability of the storage system and the size of the available resource pool.

[0075] For example, the proportion of online state and the current device configuration information are used to correct the weight.

[0076] For example, the proportion of online state can reflect the synergy effect between storage nodes. For example, when the proportion is high, the overall health of the cluster is high, and the tolerance to an offline state node can be higher. The offline state node can be given a certain weight to retain its potential capacity and avoid excessive contraction of the resource pool.

[0077] For example, the current device configuration information can reflect the differentiated treatment of storage node capacity. For example, a storage node with high hardware configuration (such as all-flash and high redundancy) enters service mode due to planned maintenance, and its correction value can be higher than that of a storage node with low configuration entering service mode due to failure.

[0078] For example, the base weight and the weight correction value are combined to obtain the correction weight of each storage node. This makes the weight value no longer a few fixed levels, but a continuous value that can reflect complex actual situations.

[0079] For example, the correction weight of each storage node is normalized to ensure that the sum is 1. This step ensures that the overall resource budget of the entire cluster is 100%, and no matter how the storage nodes change, there will be no overallocation or insufficient allocation of resources, mathematically ensuring the stability of the storage system. The normalized weight calculated is allocated to each storage node as the basis for subsequent calculation of the contribution of the storage node to the global specification.

[0080] For example, in the related art, the weight of the offline state storage node is set to 0, causing the running business to be interrupted due to a sudden decrease in resources. The related art does not distinguish between service mode storage nodes and directly considers service mode storage nodes as offline, which cannot fully utilize the performance of the storage nodes.

[0081] Next, the weight calculation is described. Figure 5 The weight calculation provided by the embodiments of the present application is described.

[0082] Figure 5 The weight calculation provided by the embodiments of the present application is described. Figure 5 As shown in FIG. 1, the base weight and the proportion of online state are determined according to the node running state. The weight correction value is determined according to the proportion of online state and the current configuration information. The base weight is corrected according to the weight correction value to obtain the correction weight. The correction weight is normalized to obtain the normalized weight. The normalized weight is used as the final weight.

[0083] In the feasible implementation, the cluster global health degree is introduced into the weight calculation by determining the proportion of the online state, and the weight of the storage node is flexibly allocated to adapt to the current scene, instead of a fixed weight, so as to effectively adapt to the real-time state of the storage system, thereby improving the accuracy of the specification management.

[0084] In a feasible implementation, if the verification result is a verification failure, alarm information is generated according to the current device configuration information and the historical device configuration information, and alarm processing is performed according to the alarm information.

[0085] For example, when the consistency verification fails, the specification management is stopped, and an alarm is given through the alarm information. The next scheme is determined according to the alarm processing result.

[0086] In the feasible implementation, the alarm processing avoids the interference of the abnormal current device configuration information on the specification management, thereby improving the reliability of the specification management.

[0087] S306, according to the node running state and the current device configuration information, determining the reference specification parameter corresponding to each storage node.

[0088] For example, the reference specification parameter is adapted to the specification parameter of the node running state and the current device configuration information. The reference specification parameter is the maximum service capability that the storage node can theoretically provide.

[0089] Optionally, the reference specification parameter realizes the preliminary screening of safety priority: the healthy storage node releases all potential, and the abnormal storage node enables the degraded capability.

[0090] S307, according to the weight, performing weighted summation on the reference specification parameter to obtain a target global specification parameter.

[0091] Optionally, the target global specification parameter is determined by the following formula:

[0092]

[0093] wherein, the target global specification parameter, n represents the number of storage nodes, the specification upper limit value of the i th storage node under the high-performance configuration (preconfigured), the specification lower limit value of the i th storage node under the degraded configuration or the restricted state, the weight of the i th storage node.

[0094] Optionally, appropriate upper and lower limit values ​​for specifications can be pre-assigned to storage nodes. These upper and lower limit values ​​define the range of baseline specification parameters, preventing the accuracy of specification management from being too low due to excessively large or small baseline specification parameters.

[0095] Optionally, when the storage system is first started or reinitialized, the baseline specification parameters of each storage node are initialized to the default values ​​of the lowest specification. The default values ​​of the lowest specification are the parameters of the lowest specification among the storage nodes, ensuring that the storage system can operate normally under any hardware configuration.

[0096] S308. Perform specification management on the storage system based on the target global specification parameters.

[0097] Below, in conjunction with Figure 6 Explanation of specification management.

[0098] Figure 6 This is a schematic diagram illustrating specification management as provided in an embodiment of this application. Figure 6 As shown, during the initialization of the storage system nodes, default specification values ​​are set. Based on the node's operating status and device configuration information, the default specification values ​​are adjusted using calculation rules to obtain global specification parameters for running the storage system. During the operation of the storage system, an event listening mechanism continuously monitors the system. When the node's operating status changes, it triggers an adjustment to the storage system's specifications, re-determining the global specification parameters.

[0099] One feasible implementation method for specification management includes: determining multiple sub-specification parameters in the target global specification parameters, wherein the multiple sub-specification parameters include at least one of the following: bandwidth quota, storage capacity threshold, or computing resource threshold; performing policy parsing on the multiple sub-specification parameters respectively through a policy parsing engine to obtain resource control instructions corresponding to each sub-specification parameter; and executing the resource control instructions through a resource scheduler to perform specification management on the storage system.

[0100] For example, the overall target, the calculated global specification parameter, can be broken down into multiple specific sub-specification parameters, each representing a different type of key resource.

[0101] With scenario examples, bandwidth quotas control the read and write throughput of the storage system, storage capacity thresholds control the total available logical capacity of the storage system, and computing resource thresholds control the computing resources occupied by the storage system.

[0102] For example, the policy parsing engine acts as the decision center, parsing sub-specification parameters into resource control instructions that the resource scheduler can execute, based on predefined business policies.

[0103] Exemplarily, the resource scheduler, as an execution structure, executes the resource control instruction to set the specification of the storage system to conform to the current state of the storage system.

[0104] In this feasible implementation, by decomposing into sub-specification parameters, independent and accurate control can be implemented for each resource type, thereby improving the accuracy of management.

[0105] In a feasible implementation, after the specification management, the method can further include: monitoring a current performance value of the storage system; determining a historical global specification parameter and a historical performance value of the storage system; and if the current performance value is less than the historical performance value, and a difference between the current performance value and the historical performance value is greater than or equal to a difference threshold value, rolling back the storage system to a specification corresponding to the historical global specification parameter.

[0106] Exemplarily, the historical global specification parameter and the historical performance value of the storage system are recorded for comparison and rollback.

[0107] Exemplarily, the current performance value reflects whether the storage system is abnormal after running according to the new specification after the specification management.

[0108] Exemplarily, if the current performance value is much less than the historical performance value, it indicates that the storage system is abnormal, and the storage system can be determined to be able to run normally by rolling back to the historical global specification parameter of the stable storage system.

[0109] In this feasible implementation, through the rollback mechanism, the abnormality of the storage system can be effectively responded and processed, thereby improving the reliability of the storage system.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better implementation.

[0111] Figure 7 The structural schematic diagram of the management device of the storage system provided by the embodiments of the present application is shown in FIG. 1. Figure 7 As shown in FIG. 1, the embodiments of the present application further provide a management device of a storage system, which can include a listening module 71, an acquisition module 72, an allocation module 73, a calculation module 74, and a management module 75.

[0112] The listening module 71 is configured to acquire node running states of each storage node of the clustered storage system through an event listening mechanism.

[0113] The acquisition module 72 is configured to acquire current device configuration information of each storage node in response to a change in any one node running state.

[0114] the distribution module 73 is configured to distribute a corresponding weight to each storage node according to the node running state and the current device configuration information.

[0115] the calculation module 74 is configured to calculate a target global specification parameter of the storage system according to the weight, the node running state, and the current device configuration information through a preset calculation rule.

[0116] the management module 75 is configured to perform specification management on the storage system according to the target global specification parameter.

[0117] Optionally, the listening module 71 can perform S201 in the embodiment. Figure 2

[0118] Optionally, the obtaining module 72 can perform S202 in the embodiment. Figure 2

[0119] Optionally, the distribution module 73 can perform S203 in the embodiment. Figure 2

[0120] Optionally, the calculation module 74 can perform S204 in the embodiment. Figure 2

[0121] Optionally, the management module 75 can perform S205 in the embodiment. Figure 2

[0122] It should be noted that the management apparatus of the storage system shown in the embodiment of the present application can perform the technical solutions shown in the above method embodiments, and the implementation principles and beneficial effects are similar, which will not be described here in detail.

[0123] In a possible implementation, the listening module 71 is specifically configured to:

[0124] perform event listening on the node running state of each storage node through periodic heartbeat communication between the cluster management service and the agent program deployed on each storage node;

[0125] if no heartbeat information of the storage node is received within a preset time length, it is determined that the node running state is an offline state;

[0126] if heartbeat information of more than or equal to a preset number of storage nodes is received within a preset time length, it is determined that the node running state is an online state;

[0127] if heartbeat information of less than a preset number of storage nodes is received within a preset time length, it is determined that the node running state is a service mode state.

[0128] In a possible implementation, the obtaining module 72 is specifically configured to:​​​​​

[0129] sending, through a management interface of each storage node, a read request to a controller of each storage node to obtain current device configuration information of each storage node; or

[0130] obtaining the current device configuration information of each storage node by parsing a virtual file of the storage node or a system device tree, the system device tree being a data structure maintained by the storage system and used for storing hardware information.

[0131] In a possible implementation, the computing module 74 is specifically configured to:

[0132] determining the reference specification parameter corresponding to each storage node according to the node running state and the current device configuration information;

[0133] performing weighted summation on the reference specification parameter according to the weight to obtain the target global specification parameter.

[0134] Figure 8 Another structural schematic diagram of a management apparatus of a storage system is provided in the embodiments of the present application. Figure 7 On the basis of the embodiment shown in Figure 8 The management apparatus 70 of the storage system further includes an executing module 76, an alarming module 77, a processing module 78, and a monitoring module 79.

[0135] The executing module 76 is configured to:

[0136] determining the historical device configuration information from the database;

[0137] performing consistency verification processing by comparing the current device configuration information and the historical device configuration information to obtain a verification result, the verification result including verification pass or verification fail;

[0138] If the verification result is verification pass, the corresponding weight is respectively assigned to each storage node according to the node running state and the current device configuration information.

[0139] In a possible implementation, the executing module 76 is specifically configured to:

[0140] determining the basic weight of each storage node according to the node running state, wherein the first basic weight is assigned to the storage node in the offline state, the second basic weight is assigned to the storage node in the service mode state, and the third basic weight is assigned to the storage node in the online state, the third basic weight being greater than the second basic weight, and the second basic weight being greater than the first basic weight;

[0141] determining the proportion of the online state from the node running state;

[0142] According to the proportion of the online state and the current device configuration information, a weight correction value is determined;

[0143] According to the weight correction value, the base weight is corrected to obtain a plurality of correction weights;

[0144] The plurality of correction weights are normalized to obtain a plurality of normalized weights;

[0145] The plurality of normalized weights are assigned to each storage node.

[0146] The alarm module 77 is configured to:

[0147] If the verification result is a verification failure, alarm information is generated according to the current device configuration information and the historical device configuration information, and alarm processing is performed according to the alarm information.

[0148] The processing module 78 is configured to:

[0149] A plurality of sub-specification parameters in the target global specification parameter are determined, and the plurality of sub-specification parameters include at least one of a bandwidth quota, a storage capacity threshold, or a computing resource threshold;

[0150] The plurality of sub-specification parameters are respectively analyzed by a policy analysis engine to obtain resource control instructions corresponding to each sub-specification parameter;

[0151] The resource control instructions are executed by a resource scheduler to perform specification management on the storage system.

[0152] The monitoring module 79 is configured to:

[0153] The current performance value of the storage system is monitored;

[0154] The historical global specification parameter and the historical performance value of the storage system are determined;

[0155] If the current performance value is less than the historical performance value, and the difference between the current performance value and the historical performance value is greater than or equal to a difference threshold, the storage system is rolled back to the specification corresponding to the historical global specification parameter.

[0156] The features of the embodiments corresponding to the management device of the storage system can be referred to the related descriptions of the embodiments corresponding to the management method of the storage system, which will not be repeated here.

[0157] Figure 9 The structural schematic diagram of the electronic device provided in the present application is shown in FIG. 1. As shown in FIG. 1, the electronic device 90 provided in the present embodiment includes at least one processor 901 and a memory 902. Optionally, the electronic device 90 further includes a communication component 903. The processor 901, the memory 902 and the communication component 903 are connected through a bus. Figure 9 The structural schematic diagram of the electronic device provided in the present application is shown in FIG. 1. As shown in FIG. 1, the electronic device 90 provided in the present embodiment includes at least one processor 901 and a memory 902. Optionally, the electronic device 90 further includes a communication component 903. The processor 901, the memory 902 and the communication component 903 are connected through a bus.

[0158] In a process of implementation, the at least one processor 901 executes the computer-executed instructions stored in the memory 902, so that the at least one processor 901 executes the above-mentioned method embodiments of the management method of the storage system.

[0159] The implementation process of the processor 901 can refer to the above-mentioned method embodiments, which have similar implementation principles and technical effects, and details are not described here.

[0160] In the above-mentioned embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as execution completed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0161] The memory can contain a random access memory (RAM), and can also include a non-volatile memory (NVM), for example, at least one disk memory.

[0162] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can 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 does not limit to only one bus or one type of bus.

[0163] The embodiments of the present application also provide a non-volatile computer readable storage medium, which stores a computer program, wherein the computer program is configured to execute the steps in any of the above-mentioned method embodiments of the management method of the storage system when running.

[0164] In one exemplary embodiment, the aforementioned non-volatile computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0165] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above-described storage system management method embodiments.

[0166] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above-described storage system management method embodiments.

[0167] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0168] The foregoing has provided a detailed description of a storage system management method, apparatus, electronic device, medium, and product provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only intended to aid in understanding the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for managing a storage system, characterized in that, include: The event listening mechanism is used to obtain the node running status of each storage node in the clustered storage system; In response to a change in the operating status of any node, obtain the current device configuration information corresponding to each storage node; Based on the node's operating status and the current device configuration information, each storage node is assigned a corresponding weight. Based on the weights, the node running status, and the current device configuration information, the target global specification parameters of the storage system are calculated using preset calculation rules. The storage system is managed according to the target global specification parameters; The step of assigning corresponding weights to each storage node based on the node's operating status and the current device configuration information includes: Based on the node's operating status, the basic weight of each storage node is determined. Specifically, a first basic weight is assigned to storage nodes in offline state, a second basic weight is assigned to storage nodes in service mode state, and a third basic weight is assigned to storage nodes in online state. The third basic weight is greater than the second basic weight, and the second basic weight is greater than the first basic weight. Determine the percentage of nodes that are online from their operating status; The weight adjustment value is determined based on the proportion of online status and the current device configuration information; Based on the weight correction value, the basic weights are corrected to obtain multiple corrected weights; The multiple modified weights are normalized to obtain multiple normalized weights; The multiple normalized weights are assigned to each of the storage nodes.

2. The storage system management method according to claim 1, characterized in that, The event listening mechanism is used to obtain the node running status of each storage node in the clustered storage system, including: The system monitors the running status of each storage node through periodic heartbeat communication between the cluster management service and the agent program deployed on each storage node. If no heartbeat information is received from the storage node within the preset time period, the node is determined to be in an offline state. If a preset number of heartbeat messages are received from storage nodes within a preset time period, the node is determined to be in an online state. If less than the preset number of storage nodes' heartbeat information is received within a preset time period, the node's operating state is determined to be in service mode.

3. The storage system management method according to claim 1, characterized in that, Obtain the current device configuration information corresponding to each storage node, including: Through the management interface of each storage node, a read request is sent to the controller of each storage node to obtain the current device configuration information of each storage node; or, The current device configuration information of each storage node is obtained by parsing the virtual file of the storage node or the system device tree. The system device number is a data structure maintained by the storage system for storing hardware information.

4. The storage system management method according to claim 3, characterized in that, Based on the node's operating status and the current device configuration information, each storage node is assigned a corresponding weight, including: Determine historical device configuration information from the database; By comparing the current device configuration information and the historical device configuration information to perform consistency verification, a verification result is obtained, which includes verification passed or verification failed. If the verification result is successful, then each storage node is assigned a corresponding weight based on the node's operating status and the current device configuration information.

5. The storage system management method according to claim 4, characterized in that, The method further includes: If the verification result is that the verification fails, an alarm message is generated based on the current device configuration information and the historical device configuration information, and alarm processing is performed based on the alarm message.

6. The storage system management method according to claim 1, characterized in that, Based on the weights, the node operating status, and the current device configuration information, the target global specification parameters of the storage system are calculated using preset calculation rules, including: Based on the node's operating status and the current device configuration information, determine the baseline specification parameters corresponding to each storage node; The target global specification parameters are obtained by weighted summation of the baseline specification parameters based on the weights.

7. The management method for a storage system according to any one of claims 1-6, characterized in that, The storage system is managed according to the target global specification parameters, including: Determine multiple sub-specification parameters in the target global specification parameters, wherein the multiple sub-specification parameters include at least one of the following: bandwidth quota, storage capacity threshold, or computing resource threshold; The strategy parsing engine is used to parse the multiple sub-specification parameters to obtain the resource control instructions corresponding to each sub-specification parameter. The resource scheduler executes the resource control instructions to manage the specifications of the storage system.

8. The storage system management method according to claim 1, characterized in that, After managing the storage system's specifications based on the target global specification parameters, the process also includes: Monitor the current performance values ​​of the storage system; Determine the historical global specification parameters and historical performance values ​​of the storage system; If the current performance value is less than the historical performance value, and the difference between the current performance value and the historical performance value is greater than or equal to the difference threshold, then the storage system will be rolled back to the specification corresponding to the historical global specification parameter.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for implementing the steps of the storage system management method as claimed in any one of claims 1 to 8 when executing the computer program.

Images