Volume performance statistical method and device, equipment and medium

Abstract

The embodiment of the invention provides a volume performance statistical method and device, equipment and a medium, and relates to the field of data statistics. The method comprises the steps that volume performance statistical data of multiple nodes in a first time period are obtained, target volume performance statistical data are obtained based on the volume performance statistical data, the target volume performance statistical data are volume performance statistical data corresponding to the first time period conforming to a preset time period, and the target volume performance statistical data are obtained based on the preset time period and node numbers of the multiple nodes. And generating a retrieval identifier of the target volume performance statistical data, and storing the target volume performance statistical data of the plurality of nodes and the retrieval identifier corresponding to the target volume performance statistical data in the database. Through the mode, the purpose of counting the volume performance of the distributed storage system is achieved, the occupied resources are less, the generated extra resource consumption is lower, and the use experience of a user is improved.

Description

Technical Field

[0001] The present application relates to the field of data statistics, and in particular to a volume performance statistics method, device, equipment and medium. Background Art

[0002] With the development of information technology, distributed storage systems have achieved efficient data management and flexible expansion by distributing and storing data on multiple independent nodes, which not only improves data reliability and availability, but also effectively reduces the risk of single point failures. At the same time, distributed storage systems can also achieve fast data transmission and efficient processing, thereby greatly improving overall performance.

[0003] Volume performance statistics for distributed storage systems are of great significance. Distributed storage stores data on multiple nodes, and in related technologies, statistics on volume performance data can usually only count the volume performance of single-path storage nodes. There is no reliable way to perform reliable and effective volume performance statistics on multi-path systems such as distributed storage systems, which is not conducive to the prevention of potential failures by distributed storage systems and is not conducive to ensuring the continuity of storage services.

[0004] Therefore, how to perform volume performance statistics on multi-path storage nodes in a distributed storage system has become an urgent problem to be solved. Summary of the invention

[0005] Based on the above technical problems, the embodiments of the present application provide a volume performance statistics method, apparatus, device and medium, aiming at how to perform volume performance statistics on multi-path storage nodes in a distributed storage system.

[0006] A first aspect of an embodiment of the present application provides a volume performance statistics method, the method comprising:

[0007] Obtaining volume performance statistics of the plurality of nodes in a first time period, the volume performance statistics at least including the number of times, the amount of tasks, and the execution duration of the plurality of tasks executed by the plurality of nodes in the first time period;

[0008] Based on the volume performance statistical data, target volume performance statistical data is obtained, where the target volume performance statistical data is the volume performance statistical data corresponding to a first time period that meets a preset time period in the volume performance statistical data;

[0009] Based on the preset time period and the node numbers of the multiple nodes, a retrieval identifier of the target volume performance statistics data is generated, the retrieval identifier is configured to be used to query the label information of the target volume performance statistics data, the retrieval identifier at least includes a timestamp and a node number, the retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different;

[0010] The target volume performance statistics data of the plurality of nodes and the retrieval identifiers corresponding to the target volume performance statistics data are stored in a database.

[0011] Optionally, volume performance statistics of multiple nodes in a first period are obtained, including:

[0012] In response to an execution command of a task assigned to a target node, a record file of the task is created, the record file at least including the task amount and the execution time, the target node being any node among the multiple nodes in the distributed storage system;

[0013] The data in the record files of all the tasks assigned to the target node in the first time period are superimposed according to the data types to obtain volume performance statistics of the target node.

[0014] Optionally, in response to an execution command of a task assigned to a target node, creating a record file of the task includes:

[0015] In response to an execution instruction of the task assigned to the target node, creating an original record file;

[0016] Recording the task amount and the first time of the task in the original record file, where the first time is used to express the time when the target node starts to execute the task;

[0017] Send the task to the node cluster and distribute it to other nodes other than the target node for backup storage;

[0018] When the target node completes the task, a second time is recorded in the original record file, where the second time is the later of the time when the target node completes the task and the time when the other nodes complete the backup storage of the task;

[0019] According to the first time and the second time, obtaining the execution time of the target node executing the task, and recording it in the original record file;

[0020] The original record file is updated based on the execution time and the task amount to obtain the record file.

[0021] Optionally, obtaining target volume performance statistics based on the volume performance statistics includes:

[0022] Obtaining the volume performance statistics of the target node in each first time period in chronological order;

[0023] If the first time period corresponding to the volume performance statistics data does not reach the preset time period, deleting the volume performance statistics data of the current time period;

[0024] When the first time period corresponding to the volume performance statistical data reaches the preset time period, the volume performance statistical data is used as the target volume performance statistical data.

[0025] Optionally, generating a retrieval identifier of the target volume performance statistics data based on the preset time period and the node numbers of the plurality of nodes includes:

[0026] Performing a modulo operation on the time of generating the retrieval identifier of the volume performance statistical data based on a second time period to obtain timestamp data, wherein the second time period represents a preset retention time of the volume performance statistical data in the database;

[0027] A timestamp of the volume performance statistics data is determined according to the timestamp data.

[0028] Optionally, after storing the volume performance statistics data of the plurality of nodes and the retrieval identifiers corresponding to the volume performance statistics data in the database, the method further includes:

[0029] In response to a user's query operation on volume performance statistics data in the database, obtaining query information, the query information at least including a start time, an end time, and an interval period;

[0030] According to the query information, a query sequence of the user is obtained, where the query sequence includes a plurality of time points to be queried;

[0031] According to the multiple time points to be queried in the query sequence, obtaining the time stamps to be queried corresponding to the multiple time points to be queried in the query sequence;

[0032] The timestamp to be queried is used as a reference, and the search identifiers of multiple volume performance statistical data in the database are matched, and the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried is used as the target query volume performance statistical data.

[0033] Optionally, the volume performance statistics data further include recording times when the multiple nodes complete volume performance statistics within the first time period, and matching retrieval identifiers of multiple volume performance statistics data in the database based on the timestamp to be queried includes:

[0034] Compare the recording time in the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried with the time point to be queried corresponding to the timestamp to be queried;

[0035] The volume performance statistical data having the same recording time as the time point to be queried is used as the target query volume performance statistical data.

[0036] A second aspect of an embodiment of the present application provides a volume performance statistics device, the device comprising:

[0037] A volume performance statistics data acquisition module is used to acquire volume performance statistics data of multiple nodes in a first time period, wherein the volume performance statistics data at least includes the number of times, the amount of tasks, and the execution time of multiple tasks executed by the multiple nodes in the first time period;

[0038] A target volume performance statistical data acquisition module is used to acquire target volume performance statistical data based on the volume performance statistical data, wherein the target volume performance statistical data is the volume performance statistical data corresponding to a first time period in the volume performance statistical data that meets a preset time period;

[0039] A retrieval identifier generating module, configured to generate a retrieval identifier of the target volume performance statistics data based on the preset time period and the node numbers of the plurality of nodes, wherein the retrieval identifier is configured to be used to query the label information of the target volume performance statistics data, and the retrieval identifier includes at least a timestamp and a node number, and the retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different;

[0040] The storage module is used to store the target volume performance statistics of the multiple nodes and the retrieval identifier corresponding to the target volume performance statistics in a database.

[0041] Optionally, the volume performance statistics data acquisition module further includes:

[0042] A record file creation submodule, for creating a record file of the task in response to an execution command of a task assigned to a target node, wherein the record file includes at least the task amount and the execution time, and the target node is any node among the multiple nodes in the distributed storage system;

[0043] The data superposition submodule is used to superimpose the data in the record files of all tasks assigned to the target node in the first time period according to the data type, so as to obtain the volume performance statistics of the target node.

[0044] Optionally, the record file creation submodule further includes:

[0045] an original record file creation unit, configured to create an original record file in response to an execution instruction of a task assigned to the target node;

[0046] A first recording unit, used to record the task amount and a first time of the task in the original recording file, where the first time is used to express the time when the target node starts to execute the task;

[0047] A task sending unit, used to send the task to the node cluster and distribute it to other nodes other than the target node for backup storage;

[0048] A second recording unit is used to record a second time in the original recording file when the target node completes the task, the second time being the later of the time when the target node completes the task and the time when the other nodes complete the backup storage of the task;

[0049] an execution duration determining unit, configured to obtain, according to the first moment and the second moment, the execution duration of the target node executing the task, and record the duration in the original record file;

[0050] The original record file updating unit is used to update the original record file based on the execution time and the task amount to obtain the record file.

[0051] Optionally, the target volume performance statistics data acquisition module further includes:

[0052] A volume performance statistics data sequential acquisition submodule, used to sequentially acquire the volume performance statistics data of the target node in each first time period in chronological order;

[0053] A volume performance statistics data deletion submodule, configured to delete the volume performance statistics data of the current period if the first period corresponding to the volume performance statistics data does not reach the preset time period;

[0054] The target volume performance statistical data determining submodule is configured to use the volume performance statistical data as the target volume performance statistical data when the first time period corresponding to the volume performance statistical data reaches the preset time period.

[0055] Optionally, the retrieval identifier generation module further includes:

[0056] A timestamp data determination submodule, configured to perform a modulo operation on a time of generating a search identifier of the volume performance statistics data based on a second time period to obtain timestamp data, wherein the second time period represents a preset retention time of the volume performance statistics data in the database;

[0057] The timestamp determination submodule is used to determine the timestamp of the volume performance statistics data according to the timestamp data.

[0058] Optionally, the volume performance statistics device further includes:

[0059] A query information acquisition module, configured to acquire query information in response to a user's query operation on volume performance statistics data in the database, wherein the query information at least includes a start time, an end time, and an interval period;

[0060] A query sequence acquisition module, used to acquire a user's query sequence according to the query information, wherein the query sequence includes a plurality of time points to be queried;

[0061] A to-be-queried timestamp acquisition module, used for acquiring, according to the multiple to-be-queried time points in the query sequence, the to-be-queried timestamps corresponding to the multiple to-be-queried time points in the query sequence;

[0062] The target query volume performance statistics data determination module is used to match the retrieval identifiers of multiple volume performance statistics data in the database based on the timestamp to be queried, and use the volume performance statistics data corresponding to the retrieval identifier matching the timestamp to be queried as the target query volume performance statistics data.

[0063] Optionally, the target query volume performance statistical data determining module further includes:

[0064] A time point comparison submodule, used for comparing the recording time in the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried with the time point to be queried corresponding to the timestamp to be queried;

[0065] The target query volume performance statistical data determination submodule is used to take the volume performance statistical data having the same recording time as the time point to be queried as the target query volume performance statistical data.

[0066] A third aspect of an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, a volume performance statistics method as in the first aspect of an embodiment of the present application is implemented.

[0067] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the volume performance statistics method of the first aspect of the embodiment of the present application is implemented.

[0068] A fifth aspect of an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the volume performance statistics method of the first aspect of an embodiment of the present application.

[0069] Through the volume performance statistics method of the embodiment of the present application, for multiple nodes in a distributed storage system, volume performance statistics of the multiple nodes in a first time period are obtained, and target volume performance statistics are selected from the obtained volume performance statistics of the multiple nodes according to a preset time period, and stored as a sampling of the volume performance statistics within the preset time period. In addition, since data at multiple time points in multiple nodes are stored, an exclusive retrieval identifier is generated according to the node number of the counted node and the preset time period, and the target volume performance statistics and the corresponding retrieval identifier are stored together in the database as a basis for subsequent viewing of the volume performance statistics history record.

[0070] In this application, based on the volume performance statistics of a single node, a method for simultaneously performing volume performance statistics on multiple storage nodes in a distributed storage system is proposed, and according to the different nodes being counted, each volume performance statistical data is bound to its corresponding storage node in the form of a retrieval identifier, thereby achieving the purpose of volume performance statistics of the distributed storage system. In addition, this application also proposes sampling and storing volume performance statistical data according to a preset time period, which solves the problem in the related art that the volume performance statistical history cannot be viewed. Viewing the volume performance statistical history can help customers fully understand the system performance trend, quickly locate and solve potential bottlenecks, optimize resource allocation, and improve overall efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0072] Figure 1 This is a flow chart of a volume performance statistics method proposed in an embodiment of the present application;

[0073] Figure 2 This is a task dispatching diagram proposed in an embodiment of the present application;

[0074] Figure 3 This is a statistical diagram of volume performance proposed in an embodiment of the present application;

[0075] Figure 4 This is a schematic diagram of a volume performance statistics data query process proposed in an embodiment of the present application;

[0076] Figure 5 It is a structural block diagram of a volume performance statistics device provided by an embodiment of the present application;

[0077] Figure 6 It is a schematic diagram of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0079] In the drawings, the size of the constituent elements, the thickness of the layer or the area may be exaggerated for the sake of clarity. Therefore, any implementation of the present disclosure is not necessarily limited to the size shown in the drawings, and the shapes and sizes of the components in the drawings do not reflect the true proportions. In addition, the drawings schematically show ideal examples, and any implementation of the present disclosure is not limited to the shapes or values ​​shown in the drawings.

[0080] There are methods for performing volume performance statistics in the related art, but they can only perform volume performance statistics on single-path storage nodes. Currently, multi-path storage technology has been widely used in distributed storage systems. Storage devices and hosts are connected through multiple physical paths to improve the reliability and performance of data access. The paths in the system are managed through multi-path software to achieve automatic switching and load balancing when paths fail, ensuring efficient transmission of data in complex network environments. For this application scenario, the related technology is not enough to achieve the purpose of completing volume performance statistics for the system. In addition, the volume performance statistics method in the related art can only view real-time volume performance statistics, while in some usage scenarios, users need to view the historical records of volume performance statistics to achieve a comprehensive insight into system performance trends, quickly locate and solve potential bottlenecks, optimize resource allocation, and improve overall efficiency. In addition, by analyzing the historical data of volume performance statistics, it can also provide a strong basis for capacity planning and future upgrades, ensuring that the distributed storage system is always in the best state.

[0081] In summary, although the volume performance statistics method of the related art can perform volume performance statistics on a single-path storage node, it cannot be applied to a distributed storage system including multiple paths.

[0082] Therefore, in order to at least partially solve one or more of the above problems and other potential problems, the embodiment of the present application proposes a volume performance statistics method, which can not only count and store the volume performance of multiple paths in a distributed storage system in real time, but also provide real-time and historical data of volume performance. Users can provide a strong basis for capacity planning and future upgrades based on the historical data of volume performance statistics, ensuring that the storage system is always kept in the best state.

[0083] Please refer to Figure 1 , Figure 1 This is a flow chart of a volume performance statistics method of the present application. Figure 1 As shown, the method may include steps S101 to S104:

[0084] Step S101: Obtain volume performance statistics of multiple nodes in a first period of time, wherein the volume performance statistics at least include the number of times, amount, and duration of execution of multiple tasks by the multiple nodes in the first period of time;

[0085] Step S102: based on the volume performance statistical data, obtaining target volume performance statistical data, the target volume performance statistical data being the volume performance statistical data corresponding to the first time period in the volume performance statistical data that meets the preset time period;

[0086] Step S103: Based on the preset time period and the node numbers of the multiple nodes, a retrieval identifier of the target volume performance statistics data is generated, the retrieval identifier is configured to be used for querying the label information of the target volume performance statistics data, the retrieval identifier includes at least a timestamp and a node number, the retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different;

[0087] Step S104: storing the target volume performance statistics data of the multiple nodes and the search identifier corresponding to the target volume performance statistics data in a database.

[0088] When performing volume performance statistics on a distributed storage system, it is necessary to consider the volume performance statistics of each node in the storage system, and it is necessary to ensure that the volume performance statistics of each node will not cause data errors or losses due to mutual overwriting during the recording and storage process. In addition, since the amount of data stored in the distributed storage system is larger, it is also necessary to avoid consuming too many resources when performing volume performance statistics. In addition, the volume performance statistics method needs to be easy to integrate into the distributed storage system for user use.

[0089] Therefore, the present application proposes a convenient and efficient volume performance statistics method, which is not only applicable to the use scenario of multi-path storage in a distributed storage system, but also provides historical storage of volume performance statistics data, so that users can query the historical records of volume performance statistics data. In the present application, after recording the volume performance statistics data of each node in a certain time period, the volume performance statistics data are sampled according to a preset sampling period. In this way, the volume performance statistics data of the node can be displayed in a more planned manner, and compared with the method of retaining all data, the space occupied in the present application is smaller, and the consumption of resources is reduced. After the sampling is completed, according to the time sampled in the preset time period and the corresponding node number, a retrieval identifier is attached to the sampled volume performance statistics data. According to the retrieval identifier, it can be determined which storage node the data is and at what time the volume performance statistics data is, and the volume performance statistics data and the retrieval identifier are stored in the database together, so that when the user needs to query the historical data of the volume performance statistics data, he can understand the previous volume performance statistics data according to the content stored in the database.

[0090] Step S101: Obtain volume performance statistics of multiple nodes in a first time period, where the volume performance statistics at least include the number of times, amount of tasks, and execution duration of multiple tasks executed by the multiple nodes in the first time period.

[0091] In an embodiment of the present application, since there are multiple storage nodes in a distributed storage system, when the client issues a task instruction, tasks will be assigned to each storage node. Therefore, it is necessary to perform volume performance statistics on each node separately. Since the node executes a single task at a fast speed, it is necessary to perform statistics on the situation where the node executes multiple tasks within a unit time to obtain volume performance statistics. In the present application, the first time period is used as the unit time for counting the volume performance of the node. Optionally, 1 second can be used as the first time period, that is, the number of tasks, task volume and execution time of the task executed by the node within 1 second are counted as the volume performance statistics of the node.

[0092] In an optional embodiment, if Figure 2 As shown, Figure 2 This is a task dispatching diagram proposed in an embodiment of the present application. The client can access nodes 1 to n in the distributed storage nodes, and the client will send tasks to each storage node.

[0093] Step S102: based on the volume performance statistical data, obtaining target volume performance statistical data, the target volume performance statistical data being volume performance statistical data corresponding to a first time period in the volume performance statistical data that meets a preset time period.

[0094] In the embodiment of the present application, since the amount of data generated by performing volume performance statistics on each node is huge, and under the condition that the volume performance statistics data are displayed in real time, it is also hoped that the volume performance statistics data can be retained as historical data, so that users can understand the historical situation of the volume performance statistics in the future, so as to optimize the distributed storage system. Therefore, it is necessary to sample the volume performance statistics data of each node counted in each first time period, and according to a preset time period, only the volume performance statistics data of the time period that just meets the preset time period is used as a sampling value, that is, the target volume performance statistics data, which is used to represent the volume performance statistics of the node in this preset time period.

[0095] Specifically, the preset time period can be set according to the user's usage requirements, and can be sampled every 15 seconds or every 30 seconds, which is not limited in this application. By setting a preset time period to sample volume performance statistics, not only can the volume performance statistics in the past time period be understood as historical data, but it also greatly reduces the amount of data that needs to be stored, reduces the space occupied by volume performance statistics, and maintains the additional resource consumption caused by this application at a low level.

[0096] Step S103: Based on the preset time period and the node numbers of multiple nodes, a retrieval identifier of the target volume performance statistics is generated, and the retrieval identifier is configured to be used to query the label information of the target volume performance statistics. The retrieval identifier includes at least a timestamp and a node number. The retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different.

[0097] In the embodiment of the present application, in order to store the target volume performance statistics obtained by sampling according to a certain preset time period as described above in the database, it is also necessary to distinguish the data of different nodes and different times, so as to avoid the situation that different volume performance statistics are overwritten when stored in the database, resulting in data loss, and it is also inconvenient to manage the data. In order to avoid this situation, the present application proposes a method of generating a retrieval identifier for the target volume performance statistics, and distinguishing each target volume performance statistics with different retrieval identifiers. Specifically, the retrieval identifier is divided into two parts. The first part is a timestamp obtained according to the preset time period, which is used to express which moment the data is the data, so as to avoid the data of the same node from being overwritten; the second part is a node number distinguished according to each node, and the node number of each node is different, which is added to the retrieval identifier as a distinction to avoid the data of different nodes at the same time from being overwritten. When searching, the two parts of the retrieval identifier are judged at the same time, so that the volume performance statistics of a node at a certain moment correspond to a unique retrieval identifier, avoiding conflicts between data.

[0098] Step S104: storing the target volume performance statistics data of the multiple nodes and the search identifier corresponding to the target volume performance statistics data in a database.

[0099] In the embodiment of the present application, after the target volume performance statistics data and the retrieval identifier corresponding to the target volume performance statistics data are determined in the above steps, the target volume performance statistics data of the multiple nodes and the retrieval identifier corresponding to the target volume performance statistics data can be stored in the database. When the historical records need to be viewed later, the historical records of the volume performance statistics data at the past moment can be obtained by searching the database according to the retrieval identifier. Optionally, the volume performance statistics data can be stored in the form of kv (key-value, key value form), with the retrieval identifier as the key and the target volume performance statistics data as the value. The key can be searched in the database to obtain the target volume performance statistics data in the value corresponding to the key.

[0100] In combination with the above embodiments, in one implementation, the present application further provides a volume performance statistics method for obtaining volume performance statistics of multiple nodes in a first time period, which specifically includes the following contents:

[0101] First, in response to an execution command of a task assigned to a target node, a record file of the task is created, the record file at least including the task amount and execution time, and the target node is any node among multiple nodes in the distributed storage system.

[0102] In an embodiment of the present application, for tasks assigned to a target node, the target node needs to create a record file for the execution of the task, which includes the task amount and execution time. The situation of the target node executing the task can be determined based on the task amount and execution time, and volume performance statistics can be performed based on this.

[0103] In an optional embodiment, after an io (Input / Output) task is assigned to a target node, an io callback class may be created to record the amount of the io task executed by the target node and the execution time of the task.

[0104] Then, the data in the record files of all the tasks assigned to the target node in the first period are superimposed according to the data types to obtain the volume performance statistics of the target node.

[0105] In the embodiment of the present application, as described above, since the execution speed of the tasks assigned to each node is relatively fast, it is necessary to count the total execution status of the tasks within a period of time. Therefore, for each task assigned to the target node in the first time period, it is necessary to accumulate the relevant data of these tasks together to obtain volume performance statistics that reflect the target node in the time period. Specifically, the data in the record files of all tasks in the target node in the first time period are superimposed, and the superposition method is based on their different data types, that is, the task amounts in each record file are superimposed together, the execution time in each file is superimposed together, and the cumulative number of tasks completed by the target node in the first time period is also counted, and finally the volume performance statistics of the target node in the first time period are obtained, which include the number of tasks, task amounts and execution time.

[0106] In an optional embodiment, a perf structure can be maintained in the memory of each node. After each io task is executed, the content in the perf structure is superimposed and updated. Specifically, the number of tasks is superimposed with perf.op++, the task amount is superimposed with perf.band+=len, and the execution time is superimposed with perf.delay+=(end-start). Finally, the superimposed results in the first time period are used as the volume performance statistics of the target node in the first time period.

[0107] In combination with the above embodiments, in one implementation, the present application further provides a volume performance statistics method, which creates a record file of the task in response to an execution command of a task assigned to a target node, specifically including the following contents:

[0108] First, in response to an execution instruction of a task assigned to the target node, an original record file is created.

[0109] In an embodiment of the present application, after the target node receives the task assigned by the client, in order to count the volume performance, it is necessary to record the execution time of the task and the workload of the task. Therefore, as described above, it is necessary to create a record file and use the newly created record file without recorded data as the original record file.

[0110] Then, the task amount and the first time of the task are recorded in the original record file, where the first time is used to express the time when the target node starts to execute the task.

[0111] In an embodiment of the present application, the target node needs to parse the task after receiving it. After creating the original record file, the task amount of the task obtained by parsing and the first moment when the target node starts to execute the task can be recorded in the record file. Optionally, the task amount can be recorded as the length len of the io task, and the first moment can be recorded as the start time.

[0112] Next, the task is sent to the node cluster and allocated to other nodes other than the target node for backup storage.

[0113] In the embodiment of the present application, since the task is executed on the target node in the distributed storage cluster, in the distributed storage cluster, while storing data on the target node, it is also necessary to create a backup of the target node storage content on other nodes other than the target node in the cluster, so as to form a redundant storage method to avoid data loss due to damage to a single node, affecting the operation of the entire distributed storage system. Therefore, while the target node is processing the task, it is also necessary to process the corresponding backup part in the same way, specifically by notifying the cluster, the cluster assigns the task to the backup storage node and also updates the backup.

[0114] Afterwards, when the target node completes the task, a second time is recorded in the original record file, where the second time is the later of the time when the target node completes the task and the time when the other nodes complete the backup storage of the task.

[0115] In an embodiment of the present application, after the target node completes the task, it is necessary to record the time when the task is completed, which corresponds to the time when the task is started as described above, and calculate the execution duration of the task. Since the processing of the task in one node also requires updating the backups in other backup nodes, the later completion time of the two is recorded as the second time, that is, the time when the target node completes the task. Optionally, the second time can be recorded as the end time.

[0116] Furthermore, according to the first moment and the second moment, the execution time of the target node executing the task is obtained and recorded in the original record file.

[0117] In the embodiment of the present application, as described above, the specific execution duration of the task on the target node can be determined based on the first moment and the second moment, that is, the execution duration is obtained by subtracting the second moment from the first moment.

[0118] Finally, the original record file is updated based on the execution time and the task amount to obtain the record file.

[0119] In an embodiment of the present application, after determining the task volume and execution time of the task, the original record file can be updated to a file that records information related to the task, namely, the record file. In this way, each task performed by the target node in the first time period is recorded, thereby obtaining volume performance statistics of the target node in the first time period.

[0120] In an optional embodiment, if Figure 3 As shown, Figure 3 This is a volume performance statistics diagram proposed in an embodiment of the present application. First, when a task starts to be executed, an original record file is created, and the first moment and the task amount of the task are recorded. Then the task is sent to the cluster and distributed to other nodes for backup. After completing the task, the completion time is recorded to determine the execution time of the task. Then, each record file in the first time period is superimposed and calculated to obtain volume performance statistics. According to the preset time period, the target volume performance statistics are determined and a retrieval identifier is added and stored in the database.

[0121] In combination with the above embodiments, in one implementation, the present application further provides a volume performance statistics method, which obtains target volume performance statistics based on the volume performance statistics data, and specifically includes the following contents:

[0122] First, the volume performance statistics of the target node in each first time period are obtained in chronological order.

[0123] In an embodiment of the present application, since the record files described above are superimposed in sequence according to the time sequence of executing the tasks, similarly, the volume performance statistics data within each time period are also obtained in sequence according to the time sequence, that is, after the end of each first time period, the volume performance statistics data of the next first time period are obtained.

[0124] Then, when the first time period corresponding to the volume performance statistics data does not reach the preset time period, the volume performance statistics data of the current time period are deleted.

[0125] In the embodiment of the present application, since the volume performance statistics can be displayed in real time, the volume performance statistics in each time period need to be counted. However, since the memory space in the node is fixed, if all the volume performance statistics are stored in the node memory, it is easy to cause excessive memory usage, affecting the normal use of the node. The target volume performance statistics that need to be saved in the database as historical data are determined according to a preset time period. In each time period, only the volume performance statistics corresponding to the first time period that meets the preset time period need to be stored in the database. Therefore, for the volume performance statistics of the corresponding first time period that does not meet the preset time period, it is necessary to delete the volume performance statistics of the current time period after the current time period ends to save more memory space.

[0126] Finally, when the first time period corresponding to the volume performance statistical data reaches the preset time period, the volume performance statistical data is used as the target volume performance statistical data.

[0127] In an embodiment of the present application, when the first time period corresponding to the volume performance statistical data does not reach the preset time period, the volume performance statistical data of the current time period is deleted, and when the first time period corresponding to the volume performance statistical data reaches the preset time period, the volume performance statistical data within the time period is determined to be the volume performance statistical data that needs to be sampled, that is, the target volume performance statistical data, and then a retrieval identifier is generated in the manner described above, and the target volume performance statistical data is stored in the database together with the corresponding retrieval identifier.

[0128] For example, when 1 second is taken as the first time period and the preset time period is 15 seconds, at the end of the 1st second and the beginning of the 2nd second, the volume performance statistics from 0 to 1 second are sent to the database as the target volume performance statistics; at the end of the 2nd second and the beginning of the 3rd second, the volume performance statistics from 1 to 2 seconds are deleted, and so on, until the end of the 16th second and the beginning of the 17th second, the volume performance statistics from 15 to 16 seconds are stored in the database as the target volume performance statistics.

[0129] In combination with the above embodiments, in one implementation, the present application further provides a volume performance statistics method, which generates a retrieval identifier of the target volume performance statistics data based on the preset time period and the node numbers of multiple nodes, and specifically includes the following contents:

[0130] First, a modulo operation is performed on the time when the retrieval mark of the volume performance statistical data is generated based on the second time period to obtain timestamp data, wherein the second time period represents the preset retention time of the volume performance statistical data in the database;

[0131] Then, according to the timestamp data, the timestamp of the volume performance statistics data is determined.

[0132] In the embodiment of the present application, the database also has a certain amount of storage space, so the volume performance statistical historical data of the entire running time of the distributed storage system cannot be stored in the database. For this reason, the present application mentioned in the previous text that only the target volume performance statistical data that meets the expected time period is stored in the database. Based on the same technical concept, the present application also proposes a second time period as the preset retention period of historical data in the database. For example, the second preset period is 30 days, and only the volume performance statistical data of the past 30 days are retained in the database.

[0133] Under such conditions, the present application proposes a specific implementation scheme for the timestamp in the retrieval identifier mentioned above, namely, by using the moment when the retrieval identifier is generated from the target volume performance statistical data as the time mark of the data, performing a modulo operation on the moment based on the second time period to obtain a remainder as the timestamp data, and determining the timestamp based on the timestamp data. In this way, the capacity of the data in the retrieval identifier is simplified. Here, taking the second preset time length of 30 days as an example, the timestamp of the target statistical data of the first time period corresponding to 0:0:01 on the first day is timestamp No. 1. After 30 days, the timestamp of the target statistical data of the first time period corresponding to 0:0:01 on the thirty-first day is still timestamp No. 1. In this way, the data format in the retrieval identifier is simplified, and resources are further saved.

[0134] In combination with the above embodiment, in an implementation manner, after the volume performance statistics data of the plurality of nodes and the retrieval identifiers corresponding to the volume performance statistics data are stored in the database, the following contents are specifically included:

[0135] First, in response to a user's query operation on volume performance statistics data in the database, query information is obtained, where the query information at least includes a start time, an end time, and an interval period.

[0136] In an embodiment of the present application, after the volume performance statistics data are stored, it also includes querying the volume performance statistics data in the database. Specifically, the user is first required to initiate a query operation for the volume performance statistics data to the database, and needs to input query information. The query information describes the volume performance statistics data of the past period that the user wishes to query. Therefore, at least the start time, end time and query period of the volume performance statistics data to be queried are required, wherein the query period is the time interval of the volume performance statistics data that the user wishes to display, which may be data at intervals of 15 seconds or data at intervals of 15 minutes.

[0137] Then, according to the query information, a query sequence of the user is obtained, where the query sequence includes a plurality of time points to be queried.

[0138] In an embodiment of the present application, based on the start time and end time in the query information, the time range of the volume performance statistical data that you want to query can be determined, and then based on the query cycle, multiple time points to be queried within this time range that are obtained at intervals of the query cycle are determined and arranged in chronological order, which is the query sequence of this query.

[0139] Next, according to the multiple time points to be queried in the query sequence, the time stamps to be queried corresponding to the multiple time points to be queried in the query sequence are obtained.

[0140] In the embodiment of the present application, since the performance statistics of each volume are stored in the database together with the corresponding retrieval identifier, when querying data for a certain period of time, it is necessary to convert the time point to be queried into a timestamp and compare it with the timestamp in each retrieval identifier. Only data with consistent timestamps are considered to be the data to be queried.

[0141] Finally, the retrieval identifiers of multiple volume performance statistical data in the database are matched based on the timestamp to be queried, and the volume performance statistical data corresponding to the retrieval identifier matching the timestamp to be queried is used as the target query volume performance statistical data.

[0142] In an embodiment of the present application, after filtering and obtaining the volume performance statistics data in the database whose timestamp is consistent with the query, the volume performance statistics data of each node at the time to be queried are obtained, and the volume performance statistics data of each node are integrated as the volume performance statistics data of the distributed storage system at that time, and displayed to the user, and then the volume performance statistics data of the next time to be queried are queried until the end time.

[0143] In combination with the above embodiments, in one implementation, the present application further provides a volume performance statistics method, wherein the volume performance statistics data also include the recording time when the multiple nodes complete the volume performance statistics within the first time period, and the retrieval identifiers of the multiple volume performance statistics data in the database are matched based on the timestamp to be queried, and specifically include the following contents:

[0144] First, the recording time in the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried is compared with the time point to be queried corresponding to the timestamp to be queried;

[0145] Then, the volume performance statistical data having the same recording time as the time point to be queried is used as the target query volume performance statistical data.

[0146] In the embodiment of the present application, there is also such a situation that the volume performance statistics data stored in the database are expected to be retained for the second period of time. However, if the volume performance statistics data continue to be stored in the database after the second period of time has passed and the original data in the database has not been cleaned up, there may be a situation where the retrieval identifiers of the two volume performance statistics data are the same. For example, when the data of the 31st day is stored in the database, if the data of the 1st day has not been cleaned up, the retrieval identifiers of the volume performance statistics data at the corresponding moments of the 31st day and the 1st day are the same. In order to continue to distinguish the volume performance statistics data in this case, the present application also records the recording time of completing the volume performance statistics within the first period of time in the volume performance statistics data, and this recording time is a specific time point.

[0147] In this way, when querying volume performance statistics in the database, after obtaining the volume performance statistics whose timestamp is consistent with the timestamp to be queried, it is also necessary to check the recorded time therein and compare it with the time point to be queried. If it is consistent, it is the volume performance statistics to be queried, and it is used as the target query volume performance statistics. If it is inconsistent, it is considered to be data from the second time period, and it will be filtered out and not displayed to the user.

[0148] In an optional embodiment, if Figure 4 As shown, Figure 4 This is a flow chart of a volume performance statistics data query proposed in an embodiment of the present application. First, query information and volume performance statistics data and retrieval identifiers stored in a database are obtained. When the current query time is less than the end time, subsequent query operations are continued to obtain the timestamp to be queried corresponding to the time point to be queried, and the data in the database are queried in sequence. When the queried data is not the last data, compare whether the timestamp of the volume performance statistics data is consistent with the timestamp to be queried, and whether the recording time of the volume performance statistics data is consistent with the time point to be queried. The consistent data are filtered out, and the inconsistent data are filtered out, that is, the volume performance statistics data of each node at the time point to be queried are obtained, integrated and displayed to the user, and the query operation for the next time point to be queried is performed.

[0149] Based on the same design concept, an embodiment of the present application provides a volume performance statistics device. Figure 5 , Figure 5 1 is a structural block diagram of a volume performance statistics device provided by an embodiment of the present application. Figure 5 As shown, the device comprises:

[0150] A volume performance statistics data acquisition module is used to acquire volume performance statistics data of multiple nodes in a first time period, wherein the volume performance statistics data at least includes the number of times, the amount of tasks, and the execution time of multiple tasks executed by the multiple nodes in the first time period;

[0151] A target volume performance statistical data acquisition module is used to acquire target volume performance statistical data based on the volume performance statistical data, wherein the target volume performance statistical data is the volume performance statistical data corresponding to a first time period in the volume performance statistical data that meets a preset time period;

[0152] A retrieval identifier generating module, configured to generate a retrieval identifier of the target volume performance statistics data based on the preset time period and the node numbers of the plurality of nodes, wherein the retrieval identifier is configured to be used to query the label information of the target volume performance statistics data, and the retrieval identifier includes at least a timestamp and a node number, and the retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different;

[0153] The storage module is used to store the target volume performance statistics of the multiple nodes and the retrieval identifier corresponding to the target volume performance statistics in a database.

[0154] Optionally, the volume performance statistics data acquisition module further includes:

[0155] A record file creation submodule, for creating a record file of the task in response to an execution command of a task assigned to a target node, wherein the record file includes at least the task amount and the execution time, and the target node is any node among the multiple nodes in the distributed storage system;

[0156] The data superposition submodule is used to superimpose the data in the record files of all tasks assigned to the target node in the first time period according to the data type, so as to obtain the volume performance statistics of the target node.

[0157] Optionally, the record file creation submodule further includes:

[0158] an original record file creation unit, configured to create an original record file in response to an execution instruction of a task assigned to the target node;

[0159] A first recording unit, used to record the task amount and a first time of the task in the original recording file, where the first time is used to express the time when the target node starts to execute the task;

[0160] A task sending unit, used to send the task to the node cluster and distribute it to other nodes other than the target node for backup storage;

[0161] A second recording unit is used to record a second time in the original recording file when the target node completes the task, the second time being the later of the time when the target node completes the task and the time when the other nodes complete the backup storage of the task;

[0162] an execution duration determining unit, configured to obtain, according to the first moment and the second moment, the execution duration of the target node executing the task, and record the duration in the original record file;

[0163] The original record file updating unit is used to update the original record file based on the execution time and the task amount to obtain the record file.

[0164] Optionally, the target volume performance statistics data acquisition module further includes:

[0165] A volume performance statistics data sequential acquisition submodule, used to sequentially acquire the volume performance statistics data of the target node in each first time period in chronological order;

[0166] A volume performance statistics data deletion submodule, configured to delete the volume performance statistics data of the current period if the first period corresponding to the volume performance statistics data does not reach the preset time period;

[0167] The target volume performance statistical data determining submodule is configured to use the volume performance statistical data as the target volume performance statistical data when the first time period corresponding to the volume performance statistical data reaches the preset time period.

[0168] Optionally, the retrieval identifier generation module further includes:

[0169] A timestamp data determination submodule, configured to perform a modulo operation on a time of generating a search identifier of the volume performance statistics data based on a second time period to obtain timestamp data, wherein the second time period represents a preset retention time of the volume performance statistics data in the database;

[0170] The timestamp determination submodule is used to determine the timestamp of the volume performance statistics data according to the timestamp data.

[0171] Optionally, the volume performance statistics device further includes:

[0172] A query information acquisition module, configured to acquire query information in response to a user's query operation on volume performance statistics data in the database, wherein the query information at least includes a start time, an end time, and an interval period;

[0173] A query sequence acquisition module, used to acquire a user's query sequence according to the query information, wherein the query sequence includes a plurality of time points to be queried;

[0174] A to-be-queried timestamp acquisition module, used for acquiring, according to the multiple to-be-queried time points in the query sequence, the to-be-queried timestamps corresponding to the multiple to-be-queried time points in the query sequence;

[0175] The target query volume performance statistics data determination module is used to match the retrieval identifiers of multiple volume performance statistics data in the database based on the timestamp to be queried, and use the volume performance statistics data corresponding to the retrieval identifier matching the timestamp to be queried as the target query volume performance statistics data.

[0176] Optionally, the target query volume performance statistical data determining module further includes:

[0177] A time point comparison submodule, used for comparing the recording time in the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried with the time point to be queried corresponding to the timestamp to be queried;

[0178] The target query volume performance statistical data determination submodule is used to take the volume performance statistical data having the same recording time as the time point to be queried as the target query volume performance statistical data.

[0179] Based on the same design concept, another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the volume performance statistics method described in any of the above embodiments of the present application are implemented.

[0180] Based on the same design concept, another embodiment of the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps in the volume performance statistics method described in any of the above embodiments of the present application.

[0181] Based on the same design concept, another embodiment of the present application provides an electronic device, such as Figure 6 shown. Figure 6 This is a schematic diagram of an electronic device shown in an embodiment of the present application. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes, the steps in the volume performance statistics method described in any of the above embodiments of the present application are implemented.

[0182] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0183] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0184] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present application may adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0185] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0186] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0187] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0188] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0189] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0190] The above is a detailed introduction to a volume performance statistics method, device, equipment and medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A volume performance statistics method, characterized in that: include: Obtaining volume performance statistics of the plurality of nodes in a first time period, the volume performance statistics at least including the number of times, the amount of tasks, and the execution duration of the plurality of tasks executed by the plurality of nodes in the first time period; Based on the volume performance statistical data, target volume performance statistical data is obtained, where the target volume performance statistical data is the volume performance statistical data corresponding to a first time period that meets a preset time period in the volume performance statistical data; Based on the preset time period and the node numbers of the multiple nodes, a retrieval identifier of the target volume performance statistics data is generated, the retrieval identifier is configured to be used to query the label information of the target volume performance statistics data, the retrieval identifier at least includes a timestamp and a node number, the retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different; The target volume performance statistics data of the plurality of nodes and the retrieval identifiers corresponding to the target volume performance statistics data are stored in a database.

2. The volume performance statistics method according to claim 1, characterized in that: Get volume performance statistics for multiple nodes in the first period, including: In response to an execution command of a task assigned to a target node, a record file of the task is created, the record file at least including the task amount and the execution time, the target node being any node among the multiple nodes in the distributed storage system; The data in the record files of all the tasks assigned to the target node in the first time period are superimposed according to the data types to obtain volume performance statistics of the target node.

3. The volume performance statistics method according to claim 2, characterized in that: In response to an execution command of a task assigned to a target node, a record file of the task is created, including: In response to an execution instruction of the task assigned to the target node, creating an original record file; Recording the task amount and the first time of the task in the original record file, where the first time is used to express the time when the target node starts to execute the task; Send the task to the node cluster and distribute it to other nodes other than the target node for backup storage; When the target node completes the task, a second time is recorded in the original record file, where the second time is the later of the time when the target node completes the task and the time when the other nodes complete the backup storage of the task; According to the first time and the second time, obtaining the execution time of the target node executing the task, and recording it in the original record file; The original record file is updated based on the execution time and the task amount to obtain the record file.

4. The volume performance statistics method according to claim 1, characterized in that: Based on the volume performance statistics, obtaining target volume performance statistics includes: Obtaining the volume performance statistics of the target node in each first time period in chronological order; If the first time period corresponding to the volume performance statistics data does not reach the preset time period, deleting the volume performance statistics data of the current time period; When the first time period corresponding to the volume performance statistical data reaches the preset time period, the volume performance statistical data is used as the target volume performance statistical data.

5. The volume performance statistics method according to claim 1, characterized in that: Generating a retrieval identifier of the target volume performance statistics data based on the preset time period and the node numbers of the plurality of nodes includes: Performing a modulo operation on the time of generating the retrieval identifier of the volume performance statistical data based on a second time period to obtain timestamp data, wherein the second time period represents a preset retention time of the volume performance statistical data in the database; A timestamp of the volume performance statistics data is determined according to the timestamp data.

6. The volume performance statistics method according to claim 1, characterized in that: After storing the volume performance statistics data of the plurality of nodes and the retrieval identifiers corresponding to the volume performance statistics data in the database, the method further includes: In response to a user's query operation on volume performance statistics data in the database, obtaining query information, the query information at least including a start time, an end time, and an interval period; According to the query information, a query sequence of the user is obtained, where the query sequence includes a plurality of time points to be queried; According to the multiple time points to be queried in the query sequence, obtaining the time stamps to be queried corresponding to the multiple time points to be queried in the query sequence; The timestamp to be queried is used as a reference, and the search identifiers of multiple volume performance statistical data in the database are matched, and the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried is used as the target query volume performance statistical data.

7. The volume performance statistics method according to claim 6, characterized in that: The volume performance statistics data also include the recording time when the multiple nodes complete the volume performance statistics within the first time period, and the retrieval identifiers of multiple volume performance statistics data in the database are matched based on the timestamp to be queried, including: Compare the recording time in the volume performance statistical data corresponding to the search identifier matching the timestamp to be queried with the time point to be queried corresponding to the timestamp to be queried; The volume performance statistical data having the same recording time as the time point to be queried is used as the target query volume performance statistical data.

8. A volume performance statistics device, characterized in that: The device comprises: A volume performance statistics data acquisition module is used to acquire volume performance statistics data of multiple nodes in a first time period, wherein the volume performance statistics data at least includes the number of times, the amount of tasks, and the execution time of multiple tasks executed by the multiple nodes in the first time period; A target volume performance statistical data acquisition module is used to acquire target volume performance statistical data based on the volume performance statistical data, wherein the target volume performance statistical data is the volume performance statistical data corresponding to a first time period in the volume performance statistical data that meets a preset time period; A retrieval identifier generating module, configured to generate a retrieval identifier of the target volume performance statistics data based on the preset time period and the node numbers of the plurality of nodes, wherein the retrieval identifier is configured to be used to query the label information of the target volume performance statistics data, and the retrieval identifier includes at least a timestamp and a node number, and the retrieval identifiers of different nodes are different, and the retrieval identifiers obtained based on different preset time period quantities under the same node are different; The storage module is used to store the target volume performance statistics of the multiple nodes and the retrieval identifier corresponding to the target volume performance statistics in a database.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by the processor, the volume performance statistics method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the volume performance statistics method according to any one of claims 1 to 7 is implemented.

Images