Server data storage method and device

Abstract

The present application provides a method and device for storing server data, wherein a storage controller is used to establish a connection between a business server and multiple storage media, wherein the multiple storage media have different read and write speeds. The method comprises: receiving a target data write request initiated by a target business server connected to the storage controller; generating a target data feature of the target data based on a detected target data parameter of the target data, wherein the target data parameter is used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target read and write speed expected for writing the target data; selecting a target storage medium whose read and write speed matches the target data feature from multiple reference storage media based on the target data feature; and writing the target data to the target storage medium. Through the present application, the problem of low data storage efficiency of the server is solved, thereby achieving the effect of improving the data storage efficiency of the server.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, to a method and apparatus for storing server data. Background Art

[0002] Business server data is typically stored on storage media that is not connected to the business server. When a business server needs to store data, it generates an IO request to write the data to the storage media. In modern data storage systems, data storage strategies have become an important means of improving storage performance. Multiple storage media are deployed within the data storage system to meet data storage needs. However, the storage solution employed in related technologies for storing data in storage systems is to directly store all data on storage media with faster read speeds. This results in excessive usage of high-speed storage media, making server operation susceptible to storage space limitations on the high-speed storage media, and resulting in inefficient server data storage. Summary of the Invention

[0003] The embodiments of the present application provide a method and device for storing server data, so as to at least solve the problem of low data storage efficiency of the server in the related art.

[0004] According to one embodiment of the present application, a method for storing server data is provided, which is applied to a storage controller, wherein the storage controller is used to establish a connection between a service server and multiple storage media, wherein the multiple storage media have different read and write speeds. The method includes:

[0005] receiving a target data write request initiated by a target service server connected to the storage controller, wherein the target data write request is used to request writing target data into a plurality of reference storage media connected to the storage controller;

[0006] generating a target data feature of the target data according to the detected target data parameters of the target data, wherein the target data parameters are used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target read / write speed expected for writing the target data;

[0007] Filtering, from the plurality of reference storage media according to the target data feature, a target storage medium whose reading and writing speeds do not match the target data feature;

[0008] The target data is written into the target storage medium.

[0009] In an exemplary embodiment, generating the target data feature of the target data according to the detected target data parameter of the target data includes:

[0010] Extracting a data volume parameter, a duration parameter, and a call parameter of the target data, wherein the target data parameters include the data volume parameter and the duration parameter, the data volume parameter is used to indicate the data volume of the target data, the duration parameter is used to indicate the time consumed for writing the target data, and the call parameter is used to indicate how frequently the target data is called;

[0011] A weighted sum operation is performed on the data volume parameter, the duration parameter, and the call parameter to obtain the target data feature.

[0012] In an exemplary embodiment, generating the target data feature of the target data according to the detected target data parameter of the target data includes:

[0013] detecting compression ratio information and a target data access mode of the target data, wherein the compression ratio information is used to indicate a data compression ratio of the target data, and the target data access mode is used to indicate a data access mode supported by the target data;

[0014] The target data characteristics are generated based on the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode, wherein the target data parameters include the complexity parameter and the access parameter, the complexity parameter is used to indicate the complexity of the data content of the target data, and the target access parameter is used to indicate the degree of influence of the target data access mode on the difficulty of data storage.

[0015] In an exemplary embodiment, generating the target data feature according to the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode includes:

[0016] Calculating the complexity parameter using the compression ratio information, and extracting the access parameter corresponding to the target data access mode from the data access modes and access parameters having a corresponding relationship as the target access parameter;

[0017] A weighted sum operation is performed on the complexity parameter and the target access parameter to obtain the target data feature.

[0018] In an exemplary embodiment, selecting a target storage medium having a read / write speed that does not match the target data characteristic from the plurality of reference storage media according to the target data characteristic includes:

[0019] Searching for a target data feature interval in which the target data feature falls from a plurality of data feature intervals;

[0020] Extracting a target reading and writing speed interval corresponding to the target data feature interval from data feature intervals and reading and writing speed intervals having a corresponding relationship;

[0021] Storage media having a read / write speed falling within the target read / write speed range are screened out from the multiple reference storage media to obtain the target storage medium.

[0022] In an exemplary embodiment, the step of selecting a storage medium having a read / write speed falling within the target read / write speed range from the plurality of reference storage media to obtain the target storage medium includes:

[0023] Traversing the read and write speed of each reference storage medium among the plurality of reference storage media;

[0024] Compare the current read / write speed traversed with the target read / write speed range;

[0025] If the current read / write speed falls within the target read / write speed range, adding the current storage medium corresponding to the current read / write speed to the storage medium set until the read / write speeds of all reference storage media in the multiple reference storage media are traversed to obtain a target storage medium set;

[0026] In a case where there is one reference storage medium in the target storage medium set, determining the one reference storage medium as the target storage medium;

[0027] In a case where there are at least two reference storage media in the target storage medium set, the target storage medium is selected from the at least two reference storage media.

[0028] In an exemplary embodiment, the storage controller includes: a storage control component and a storage receiving component, wherein the storage control component is deployed on the service server, the storage receiving component is deployed on the storage device where the multiple storage media are located, and the storage control component is not connected to the storage receiving component;

[0029] The receiving a target data write request initiated by a target service server connected to the storage controller includes: extracting, by the storage control component, the target data write request generated by the target service server and to be sent to the storage device;

[0030] Generating the target data feature of the target data according to the detected target data parameter of the target data includes: detecting the target data parameter by the storage control component; generating the target data feature according to the target data parameter by the storage control component; adding the target data feature to the target data write request by the storage control component to obtain a feature data write request; and sending the feature data write request to the storage receiving component by the storage control component;

[0031] The method of screening out a target storage medium whose reading and writing speed does not match the target data feature from the multiple reference storage media according to the target data feature comprises: receiving, by the storage receiving component, a reference data write request sent by the storage control component; detecting whether the reference data write request carries the target data feature; if it is detected that the reference data write request carries the target data feature, screening out the target storage medium from the multiple reference storage media according to the target data feature by the storage receiving component; if it is detected that the reference data write request does not carry the target data feature, detecting, by the storage receiving component, a candidate data feature of the target data; screening out, by the storage receiving component, a storage medium whose reading and writing speed does not match the candidate data feature from the multiple reference storage media as the target storage medium according to the candidate data feature;

[0032] The writing the target data into the target storage medium includes: writing the target data into the target storage medium through the storage receiving component.

[0033] According to another embodiment of the present application, a server data storage device is provided, which is applied to a storage controller, wherein the storage controller is used to establish a connection between a service server and multiple storage media, wherein the multiple storage media have different read and write speeds. The device includes:

[0034] a receiving module, configured to receive a target data write request initiated by a target service server connected to the storage controller, wherein the target data write request is used to request writing target data into a plurality of reference storage media connected to the storage controller;

[0035] a generating module, configured to generate a target data feature of the target data according to the detected target data parameters of the target data, wherein the target data parameters are used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target reading and writing speed expected for writing the target data;

[0036] A screening module, configured to screen out a target storage medium having a reading and writing speed that does not match the target data characteristics from the plurality of reference storage media according to the target data characteristics;

[0037] A writing module is used to write the target data into the target storage medium.

[0038] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0039] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0040] Through the present application, since the storage controller is used to establish a connection between a business server and multiple storage media with different read and write speeds, by receiving a target data write request initiated by a target business server connected to the storage controller for requesting to write target data into multiple storage media connected to the storage controller, a target data feature of the target data for characterizing the target read and write speed expected for writing the target data is generated based on a target data parameter for indicating the complexity of writing the target data detected, and a target storage medium with a read and write speed that does not match the target data feature is screened out from multiple reference storage media based on the target data feature, and the target data is written into the target storage medium, that is, by connecting to the business server And a storage controller for multiple storage media with different read and write speeds, so that the storage controller generates a target data feature that represents the expected read and write speed of the target data to be written according to the target data parameter that represents the complexity of the data, and then screens the target storage media whose read and write speeds do not match the target data feature according to the target data feature and writes the target data into the target storage media, so that when there is target data to be written in the storage medium, the screened target storage media is more matched with the expected read and write speed of the target data, avoiding excessive occupation of high-speed storage media and improving the storage efficiency of server data. Therefore, the problem of low data storage efficiency of the server can be solved, and the effect of improving the data storage efficiency of the server is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a hardware structure block diagram of a server device for a server data storage method according to an embodiment of the present application;

[0042] Figure 2 is a flowchart of a method for storing server data according to an embodiment of the present application;

[0043] Figure 3 is a topological diagram of a method for improving system availability based on a management module according to an embodiment of the present application;

[0044] Figure 4 This is a topological diagram of a method for storing server data according to an embodiment of the present application;

[0045] Figure 5 It is a structural block diagram of a storage device for server data according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0047] It should be noted that the terms "first", "second", etc. in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0048] The method embodiments provided in the embodiments of the present application can be executed in a server device or a similar computing device. Taking running on a server device as an example, Figure 1 This is a hardware structure diagram of a server device for a method of storing server data according to an embodiment of the present application. Figure 1 As shown, the server device may include one or more ( Figure 1 The server device includes a processor 102 (only one of which is shown) (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. The server device may also include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above server device. Figure 1 More or fewer components than shown, or with different Figure 1 Different configurations shown.

[0049] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the server data storage method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory set relative to the processor 102 process, and these process memories may be connected to the server device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0050] Transmission device 106 is used to receive or transmit data via a network. A specific example of such a network may include a wireless network provided by a communication provider of a server device. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0051] In this embodiment, a method for storing server data is provided, which is applied to a storage controller. The storage controller is used to establish a connection between a service server and multiple storage media, wherein the multiple storage media have different read and write speeds. Figure 2 is a flow chart of a method for storing server data according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0052] Step S202: receiving a target data write request initiated by a target service server connected to the storage controller, wherein the target data write request is used to request writing target data into a plurality of reference storage media connected to the storage controller;

[0053] Step S204, generating a target data feature of the target data according to the detected target data parameters of the target data, wherein the target data parameters are used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target read / write speed expected for writing the target data;

[0054] Step S206, selecting a target storage medium whose read / write speed does not match the target data feature from the plurality of reference storage media according to the target data feature;

[0055] Step S208: writing the target data into the target storage medium.

[0056] Through the above steps, since the storage controller is used to establish a connection between the business server and multiple storage media with different read and write speeds, by receiving a target data write request initiated by the target business server connected to the storage controller for requesting to write the target data into the multiple storage media connected to the storage controller, a target data feature of the target data for characterizing the target read and write speed expected for writing the target data is generated according to the target data parameter for indicating the complexity of writing the target data detected, and a target storage medium with a read and write speed that does not match the target data feature is screened out from multiple reference storage media according to the target data feature, and the target data is written into the target storage medium, that is, through the storage controller for connecting to the business server. The invention relates to a storage controller for a device and multiple storage media with different read and write speeds, so that the storage controller generates a target data feature that represents the expected read and write speed of the target data to be written according to the target data parameter that represents the complexity of the data, and then screens the target storage media whose read and write speeds do not match the target data feature according to the target data feature and writes the target data into the target storage media, so that when there is target data to be written into the storage medium, the screened target storage media is more matched with the expected read and write speed of the target data, avoiding excessive occupation of high-speed storage media and improving the storage efficiency of server data. Therefore, the problem of low data storage efficiency of the server can be solved, and the effect of improving the data storage efficiency of the server is achieved.

[0057] Optionally, in an embodiment of the present application, the storage medium includes but is not limited to a hard disk drive (HDD), a magnetic tape (Disk), a solid state drive (SSD), a single level cell (SLC), a multi-level cell (MLC), a triple level cell (TLC), a quad-level cell (QLC), etc., and multiple storage media have different read and write speeds. Multiple storage media are connected to a business server through a storage controller and are used to store business data of the business server.

[0058] Optionally, in the embodiment provided in step S202, receiving a target data write request initiated on the target business server connected to the storage controller includes but is not limited to the storage controller connecting to the business server and multiple storage media, the business server generating a target data write request, sending the target business server to the storage controller, and the storage controller receiving the target data write request initiated on the target business server connected to the storage controller, or, the first functional part of the storage controller is deployed on the business server, and after the target data write request is generated on the business server, the first functional part detects the target data write request and receives the target data write request initiated on the target business server connected to the storage controller, wherein the first functional part is used to generate the target data characteristics based on the historical data processing information recorded in the business server and the information carried by the target data write request.

[0059] Optionally, in an embodiment of the present application, the target data write request includes but is not limited to a write request for completely new data, or a rewrite request for data already stored in the multiple storage media, and this solution does not make specific limitations on this.

[0060] Optionally, in the embodiment provided in step S204, the target data parameters of the target data include, but are not limited to, a data compression ratio parameter, a data access mode parameter, a data size parameter, and a data write duration parameter. Optionally, the target data parameters of the target data include, but are not limited to, data carried in the target data write request itself, or attribute parameters of the target data obtained by analyzing the processing of historical data.

[0061] Optionally, in an embodiment of the present application, the target data characteristics include but are not limited to being used to characterize the hotness or coldness of the data. In order to more reasonably allocate the storage resources of the storage medium, hot data is stored in high-speed storage media as much as possible, and cold data can be stored in low-speed storage media, that is, different hotness or coldness corresponds to different expected storage medium read and write speeds.

[0062] Optionally, in an embodiment of the present application, generating the target data characteristics of the target data based on the detected target data parameters of the target data includes but is not limited to detecting the target server system usage mode selected by the business server, wherein the server system usage mode includes a normal mode and a high availability mode; determining the target data parameters required for calculating the target data characteristics as target characteristic data parameters based on the target server system usage mode, and determining the target weight values ​​of the target characteristic data parameters based on the target server system usage mode, wherein the target data parameters required for not calculating the target data characteristics in the target server system usage mode and the corresponding weight values ​​of the target data parameters have a corresponding relationship; and obtaining the target data characteristics by weighted calculation based on the target characteristic data parameters and the target weight values.

[0063] Optionally, in the embodiment provided in step S206, including but not limited to recording the correspondence between the data feature interval and the read and write speed interval of the storage medium in the storage controller, the corresponding data feature interval can be found according to the target data feature, and then the corresponding read and write speed interval can be obtained, and then the target storage medium whose read and write speed matches the target data feature can be further screened out based on the read and write speeds of multiple storage media connected to the storage controller.

[0064] Optionally, in an embodiment of the present application, target storage media whose read and write speeds do not match the target data characteristics are screened out from the multiple reference storage media according to the target data characteristics, including but not limited to detecting the target server system usage mode selected by the business server, wherein the server system usage mode includes normal mode and high availability mode; determining a target correspondence between a data feature interval and a read and write speed interval of a storage medium according to the target server system usage mode, wherein the normal mode corresponds to a first correspondence and the high availability mode corresponds to a second correspondence; obtaining the read and write speeds of multiple storage media; searching for a target data feature interval into which the target data feature falls from multiple data feature intervals; searching for a target read and write speed interval corresponding to the target data feature interval according to the target correspondence; and determining a reference storage medium whose read and write speed falls within the target read and write speed interval among the multiple storage media as the target storage medium.

[0065] Optionally, in the embodiment provided in step S208, writing the target data into the target storage medium includes but is not limited to detecting the storage space margin of the target storage medium; if the space margin meets the writing requirement of the target data, writing the target data into the target storage medium; if the space margin does not meet the writing requirement of the target data, excluding the target storage medium from the range of multiple reference storage media, and re-screening an updated storage medium whose reading and writing speed does not match the target data characteristics from the updated multiple reference storage media according to the target data characteristics, and writing the target data into the updated storage medium.

[0066] Optionally, in an embodiment of the present application, the storage controller includes but is not limited to receiving a data read request initiated on a target business server connected to the storage controller, wherein the data read request is used to request access to reference data stored in the multiple reference storage media; according to the data read request, a temporary storage medium storing the reference data is found from the multiple reference storage media connected to the storage controller; a reference data feature of the reference data is generated according to the detected reference data parameters of the reference data, wherein the reference data parameters are used to indicate the complexity of writing the reference data, and the reference data feature is used to characterize the target read and write speed expected for writing the reference data; according to the reference data feature, a target storage medium whose read and write speed does not match the reference data feature is screened out from the multiple reference storage media; it is determined whether the target storage medium is the temporary storage medium; and if the target storage medium is not the temporary storage medium, the reference data is migrated from the temporary storage medium to the target storage medium.

[0067] As an optional embodiment, generating the target data feature of the target data according to the detected target data parameter of the target data includes:

[0068] Extracting a data volume parameter, a duration parameter, and a call parameter of the target data, wherein the target data parameters include the data volume parameter and the duration parameter, the data volume parameter is used to indicate the data volume of the target data, the duration parameter is used to indicate the time consumed for writing the target data, and the call parameter is used to indicate how frequently the target data is called;

[0069] A weighted sum operation is performed on the data volume parameter, the duration parameter, and the call parameter to obtain the target data feature.

[0070] Optionally, in the embodiment of the present application, the target data features include but are not limited to those that can be calculated by the following formula: C i =α·T a+β·F r +γ·S d , where C i represents the target data feature value of the i-th request, T a Indicates the access time of the data (timestamp difference), F r Indicates the access frequency of data, S d represents the size of the data, α, β, and γ are weight coefficients, which are adjusted by the storage controller according to the specific application scenario, or can be adjusted by manually inputting determined weight coefficients into the storage controller.

[0071] Through the above steps, multiple influencing factors are comprehensively considered to obtain the target data characteristic value that characterizes the expected target read and write speed, thereby improving the accuracy of the expected read and write speed of the target data. Obtaining a more accurate expected read and write speed can enable the target data to be stored in a more suitable storage medium, thereby improving the storage efficiency of the server data.

[0072] As an optional embodiment, generating the target data feature of the target data according to the detected target data parameter of the target data includes:

[0073] detecting compression ratio information and a target data access mode of the target data, wherein the compression ratio information is used to indicate a data compression ratio of the target data, and the target data access mode is used to indicate a data access mode supported by the target data;

[0074] The target data characteristics are generated based on the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode, wherein the target data parameters include the complexity parameter and the access parameter, the complexity parameter is used to indicate the complexity of the data content of the target data, and the target access parameter is used to indicate the degree of influence of the target data access mode on the difficulty of data storage.

[0075] Optionally, in the embodiment of the present application, the target data features include but are not limited to those that can be calculated by the following formula: C i =δ·D c +ε·A p , where C i represents the target data characteristic value of the i-th request; D c Indicates the complexity of the data content (e.g., measured by data compression ratio), A p represents the data access mode (such as random access or sequential access), δ and ε are weight coefficients, which are adjusted by the storage controller according to the specific application scenario, or can be adjusted by manually inputting the determined weight coefficients into the storage controller.

[0076] As an optional embodiment, generating the target data feature according to the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode includes:

[0077] Calculating the complexity parameter using the compression ratio information, and extracting the access parameter corresponding to the target data access mode from the data access modes and access parameters having a corresponding relationship as the target access parameter;

[0078] A weighted sum operation is performed on the complexity parameter and the target access parameter to obtain the target data feature.

[0079] Optionally, in an embodiment of the present application, the data access mode includes but is not limited to a random access mode and a sequential access mode, the random access mode corresponds to an access parameter B1, and the sequential access mode corresponds to an access parameter B2, where B1 is greater than B2.

[0080] Through the above steps, starting from the complexity parameters of the target data and the target data access mode, it is possible to achieve that even if the plug-in on the business server cannot calculate the target data features based on the powerful data analysis capabilities of the business server, the storage area can still calculate the candidate data features of the target data, ensuring that the data can be stored in a suitable storage medium, thereby improving the storage efficiency of the server data.

[0081] As an optional embodiment, selecting a target storage medium having a read / write speed that does not match the target data characteristic from the plurality of reference storage media according to the target data characteristic includes:

[0082] Searching for a target data feature interval in which the target data feature falls from a plurality of data feature intervals;

[0083] Extracting a target reading and writing speed interval corresponding to the target data feature interval from data feature intervals and reading and writing speed intervals having a corresponding relationship;

[0084] Storage media having a read / write speed falling within the target read / write speed range are screened out from the multiple reference storage media to obtain the target storage medium.

[0085] Optionally, in the embodiment of the present application, including but not limited to setting when C i When it is greater than M, the target data is allocated to high-speed media such as SSD (Further, SLC / MLC / TLC / QLC are further differentiated within the high-speed media, and each has a separate subdivision characteristic value corresponding to it). iIf the threshold is not greater than M, the target data is directly allocated to low-speed media such as HDDs or tape libraries. M represents the target data characteristic threshold, determined through experiments and historical data analysis, and embedded in the storage controller. The M value differs between normal mode and high-availability mode, with the latter generally being lower.

[0086] Through the above steps, the target data characteristics are matched with the target data characteristic interval, and then the target read and write speed interval is further matched. Then, the target storage medium is screened based on the target read and write speed interval. This more clearly and specifically realizes the acquisition of the target storage medium that is suitable for the target data characteristics, thereby improving the efficiency of obtaining the target storage medium.

[0087] As an optional embodiment, selecting a storage medium whose read / write speed falls within the target read / write speed range from the plurality of reference storage media to obtain the target storage medium includes:

[0088] Traversing the read and write speed of each reference storage medium among the plurality of reference storage media;

[0089] Compare the current read / write speed traversed with the target read / write speed range;

[0090] If the current read / write speed falls within the target read / write speed range, adding the current storage medium corresponding to the current read / write speed to the storage medium set until the read / write speeds of all reference storage media in the multiple reference storage media are traversed to obtain a target storage medium set;

[0091] In a case where there is one reference storage medium in the target storage medium set, determining the one reference storage medium as the target storage medium;

[0092] In a case where there are at least two reference storage media in the target storage medium set, the target storage medium is selected from the at least two reference storage media.

[0093] Optionally, in an embodiment of the present application, after obtaining the target storage medium set, the method further includes: when there is no reference storage medium in the target storage medium set, determining the reference storage medium with the highest read / write speed among the multiple reference storage media as the target storage medium, and sending hierarchical storage exception information to the business server, wherein the hierarchical storage exception information is used to indicate that the target data is stored in a storage medium with an unexpected read / write speed, and the business server is used to issue an alarm message in response to the received hierarchical storage exception information; when there are at least two reference storage media in the target storage medium set, the reference storage medium with the highest read / write speed among the multiple reference storage media is determined as the target storage medium, and sending hierarchical storage exception information to the business server, wherein the hierarchical storage exception information is used to indicate that the target data is stored in a storage medium with an unexpected read / write speed, and the business server is used to issue an alarm message in response to the received hierarchical storage exception information; The target storage medium is selected from the at least two reference storage media, including: querying the storage space margin of the reference storage media in the target storage media set, selecting the reference storage media whose storage space margin meets the target data read and write requirements from the target storage media set, and obtaining a candidate storage medium set; when there is one reference storage medium in the candidate storage media set, determining the one reference storage medium as the target storage medium; when there are at least two reference storage media in the candidate storage media set, selecting the reference storage medium with the fastest read and write speed from the at least two reference storage media as the target storage medium. Through the above steps, the target storage medium selection process is refined, and a reasonable method for determining the target storage medium is provided when there is no storage medium that meets the expected read and write speed and when there are multiple storage media that meet the expected read and write speed, so that a suitable target storage medium can be determined in any case, thereby improving the storage efficiency of the server data.

[0094] As an optional implementation method, the present application also provides a method for improving system availability based on a management module to solve the problem that a data storage method with a certain delay and the inability to respond immediately to the hot and cold changes of data affects the overall performance of the storage system. At the same time, it solves the problem that there is no independent module to uniformly manage this real-time data tiering strategy, and under the pressure of a complex business model with a high load, it is easy for the cluster to be unable to respond to the front-end business in time due to the background tiering tasks, thereby affecting the availability of the entire system. Based on the above problems, the method provided in the present application uses the management module to allocate data directly to the appropriate storage medium according to the hot and cold characteristic values ​​of the data (i.e., the target data characteristics) as soon as the data enters the storage system, thereby achieving more efficient data management and resource optimization. In particular, the differentiated management strategy processing for normal mode and high availability mode avoids extreme scenarios such as abnormal situations such as the inability of the cluster to respond to the front-end business in time due to background data tiering tasks under the pressure of a complex business model with a high load, thereby improving the availability of the entire system. Specifically, Figure 3FIG. 1 is a topological diagram of a method for improving system availability based on a management module according to an embodiment of the present application. Figure 3 As shown, the method provided by this application involves the cooperation of the following modules: the management module is located on the board, and mainly uses programmable logic devices such as ARM. The management module (part of the storage controller) can dynamically manage the business module (i.e., business server), storage system receiving module (part of the storage controller), data allocation module (part of the storage controller) and metadata management module (part of the storage controller) in normal mode and high availability mode respectively. Specifically, the business module is generally the user's business server, etc., more specifically, the server-side plug-in, etc., to implement the characteristic value identification of each IO request (i.e., target data write request) and attach the characteristic value to the IO request. The storage system receiving module receives the IO request and parses the characteristic value, and at the same time performs data analysis on the IO request without the characteristic value identification to generate the characteristic value. The data allocation module directly allocates the data to the corresponding storage medium based on the characteristic value. The metadata management module maintains the metadata information of the data, including the hot and cold characteristic values ​​of the data, storage location, etc. Parameter module: The parameter module can be used to exchange information with the external HSR management module, preset parameters and enable related functions.

[0095] Optionally, the technical implementation of the method provided by this application includes the following aspects: 1. Characteristic value identification: In the server-side plug-in, a characteristic value identification is added to each IO request to indicate the hotness or coldness of the data. The characteristic value can be calculated by the following formula: C i =α·T a +β·F r +γ·S d , where C i represents the hot and cold characteristic value of the i-th IO request; T a Indicates the access time of the data (timestamp difference); F r Indicates the access frequency of data; S d Indicates the size of the data; α, β, and γ are weight coefficients, which are adjusted by the management module according to the specific application scenario, or can be adjusted through the parameter module. 2. Data analysis without identification: If the IO request does not have a characteristic value identification, the storage system calculates the characteristic value using the following formula when receiving data: C i =δ·D c +ε·A p , where C i represents the hot and cold characteristic value of the i-th IO request; D c Indicates the complexity of the data content (e.g., measured by data compression ratio); A pIndicates the data access mode (such as random access or sequential access); δ and ε are weight coefficients, which are adjusted by the management module according to the specific application scenario, or can be adjusted through the parameter module. 3. Direct data allocation: Based on the calculated eigenvalues, the data is directly allocated to the appropriate storage medium. The specific allocation strategy is as follows: When C i When it is greater than M, the IO is allocated to high-speed media such as SSD (Further SLC / MLC / TLC / QLC are further differentiated within the high-speed media, each with a separate subdivision characteristic value). i When it is not greater than M, IO is directly allocated to low-speed media such as HDD or tape library. M is the threshold of hot and cold data, which is determined through experiments and historical data analysis and is embedded in the management module. The M value in normal mode and high availability mode is different. Generally speaking, the M value in high availability is lower. In addition, in high availability mode, the management module will allow certain background data tiering tasks (generally when the business pressure is small) based on the pressure of the front-end business, while background data tiering tasks are not allowed in normal mode. In summary, the management module directly allocates data to appropriate storage media based on the hot and cold characteristic values ​​of the data as soon as the data enters the storage system, thereby achieving more efficient data management and resource optimization. In particular, the differentiated management strategy processing for normal mode and high availability mode avoids extreme scenarios such as abnormal situations such as the inability of the cluster to respond to the front-end business in a timely manner due to background data tiering tasks under the pressure of a high-load complex business model, thereby improving the availability of the entire system.

[0096] Optionally, in embodiments of the present application, including but not limited to, continuously monitoring data access patterns during storage system operation, if changes in the hot and cold characteristics (i.e., data characteristics) of the data are detected, the data storage location can be dynamically adjusted. For example, data with a significant increase in access frequency over a period of time can be migrated from the HDD to the SSD to improve access performance.

[0097] From the above content, it can be seen that the centralized storage tiering strategy based on real-time IO characteristic values ​​proposed in this application has significant advantages in the following aspects: 1. Real-time: This application implements real-time tiered storage of data by directly allocating the data to the appropriate storage medium according to the hot and cold characteristic values ​​of the data as soon as the data enters the storage system, thereby avoiding the delay problem of data tiered storage. 2. Efficiency: This application analyzes and identifies the data when the IO request arrives, and directly determines the storage location of the data by the characteristic value, eliminating the steps of regular data classification and migration, and significantly improving the overall efficiency of the storage system. 3. Simplified management: This application simplifies the management and control mechanism of data tiered storage through real-time analysis and characteristic value identification, reducing the complexity and maintenance cost of the system.

[0098] As an optional embodiment, the storage controller includes: a storage control component and a storage receiving component, the storage control component is deployed on the service server, the storage receiving component is deployed on the storage device where the multiple storage media are located, and the storage control component is not connected to the storage receiving component;

[0099] The receiving a target data write request initiated by a target service server connected to the storage controller includes: extracting, by the storage control component, the target data write request generated by the target service server and to be sent to the storage device;

[0100] Generating the target data feature of the target data according to the detected target data parameter of the target data includes: detecting the target data parameter by the storage control component; generating the target data feature according to the target data parameter by the storage control component; adding the target data feature to the target data write request by the storage control component to obtain a feature data write request; and sending the feature data write request to the storage receiving component by the storage control component;

[0101] The method of screening out a target storage medium whose reading and writing speed does not match the target data feature from the multiple reference storage media according to the target data feature comprises: receiving, by the storage receiving component, a reference data write request sent by the storage control component; detecting whether the reference data write request carries the target data feature; if it is detected that the reference data write request carries the target data feature, screening out the target storage medium from the multiple reference storage media according to the target data feature by the storage receiving component; if it is detected that the reference data write request does not carry the target data feature, detecting, by the storage receiving component, a candidate data feature of the target data; screening out, by the storage receiving component, a storage medium whose reading and writing speed does not match the candidate data feature from the multiple reference storage media as the target storage medium according to the candidate data feature;

[0102] The writing the target data into the target storage medium includes: writing the target data into the target storage medium through the storage receiving component.

[0103] Optionally, in the embodiment of the present application, Figure 4 FIG. 1 is a topological diagram of a method for storing server data according to an embodiment of the present application. Figure 4As shown, on the business server side, each IO request (i.e., data write request) is identified by a characteristic value through the storage control component. The storage control component calculates the characteristic value and attaches it to the IO request by monitoring the access frequency and size of the data. After receiving the IO request, the storage device directly stores the data in a suitable storage medium based on the characteristic value. By installing the storage control component in the server operating system, the component can monitor IO requests in real time. The storage control component is configured to capture and analyze the access time, frequency, and data size of each IO request. The storage control component runs in the background and captures IO requests in real time. The characteristic value is calculated and attached to the metadata of each IO request. The IO request with the characteristic value attached is transmitted to the storage device via the network. The storage receiving component in the storage device allocates the data to the suitable storage medium based on the characteristic value. For IO requests without characteristic value identification, the storage receiving component in the storage device generates a characteristic value by analyzing the data content and access mode corresponding to the request when receiving the request. The storage location of the data is then determined based on the characteristic value.

[0104] Through the above steps, when a data request is generated and when the data request enters the storage device, the data characteristics can be analyzed according to the data situation, so as to match the storage medium of the data, so that the data entering the storage device can be stored in the appropriate storage medium as quickly as possible, thereby improving the storage efficiency of the server data.

[0105] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of inferior software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0106] This embodiment also provides a server data storage device, which is applied to a storage controller. The storage controller is used to establish a connection between a service server and multiple storage media, wherein the multiple storage media have different read and write speeds. The device is used to implement the above-mentioned embodiments and preferred implementation methods, and the details that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0107] Figure 5 is a structural block diagram of a storage device for server data according to an embodiment of the present application, such as Figure 5 As shown, the device includes:

[0108] a receiving module, configured to receive a target data write request initiated by a target service server connected to the storage controller, wherein the target data write request is used to request writing target data into a plurality of reference storage media connected to the storage controller;

[0109] a generating module, configured to generate a target data feature of the target data according to the detected target data parameters of the target data, wherein the target data parameters are used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target reading and writing speed expected for writing the target data;

[0110] A screening module, configured to screen out a target storage medium having a reading and writing speed that does not match the target data characteristics from the plurality of reference storage media according to the target data characteristics;

[0111] A writing module is used to write the target data into the target storage medium.

[0112] Through the above steps, since the storage controller is used to establish a connection between the business server and multiple storage media with different read and write speeds, by receiving a target data write request initiated by the target business server connected to the storage controller for requesting to write the target data into the multiple storage media connected to the storage controller, a target data feature of the target data for characterizing the target read and write speed expected for writing the target data is generated according to the target data parameter for indicating the complexity of writing the target data detected, and a target storage medium with a read and write speed that does not match the target data feature is screened out from multiple reference storage media according to the target data feature, and the target data is written into the target storage medium, that is, through the storage controller for connecting to the business server. The invention relates to a storage controller for a device and multiple storage media with different read and write speeds, so that the storage controller generates a target data feature that represents the expected read and write speed of the target data to be written according to the target data parameter that represents the complexity of the data, and then screens the target storage media whose read and write speeds do not match the target data feature according to the target data feature and writes the target data into the target storage media, so that when there is target data to be written into the storage medium, the screened target storage media is more matched with the expected read and write speed of the target data, avoiding excessive occupation of high-speed storage media and improving the storage efficiency of server data. Therefore, the problem of low data storage efficiency of the server can be solved, and the effect of improving the data storage efficiency of the server is achieved.

[0113] As an optional embodiment, the generating module includes:

[0114] a first extraction unit, configured to extract a data volume parameter, a duration parameter, and a call parameter of the target data, wherein the target data parameters include the data volume parameter and the duration parameter, the data volume parameter is used to indicate the data volume of the target data, the duration parameter is used to indicate the duration consumed for writing the target data, and the call parameter is used to indicate how frequently the target data is called;

[0115] A weighting unit is used to perform a weighted sum operation on the data volume parameter, the duration parameter and the call parameter to obtain the target data feature.

[0116] As an optional embodiment, the generating module includes:

[0117] a first detection unit, configured to detect compression ratio information and a target data access mode of the target data, wherein the compression ratio information is used to indicate a data compression ratio of the target data, and the target data access mode is used to indicate a data access mode supported by the target data;

[0118] A first generating unit is used to generate the target data characteristics based on the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode, wherein the target data parameters include the complexity parameter and the access parameter, the complexity parameter is used to indicate the complexity of the data content of the target data, and the target access parameter is used to indicate the degree of influence of the target data access mode on the difficulty of data storage.

[0119] As an optional embodiment, the first generating unit is further configured to:

[0120] Calculating the complexity parameter using the compression ratio information, and extracting the access parameter corresponding to the target data access mode from the data access modes and access parameters having a corresponding relationship as the target access parameter;

[0121] A weighted sum operation is performed on the complexity parameter and the target access parameter to obtain the target data feature.

[0122] As an optional embodiment, the screening module includes:

[0123] a searching unit, configured to search, from a plurality of data feature intervals, a target data feature interval into which the target data feature falls;

[0124] A second extraction unit is configured to extract a target reading and writing speed interval corresponding to the target data feature interval from data feature intervals and reading and writing speed intervals having a corresponding relationship;

[0125] The first screening unit is configured to screen out storage media having a read / write speed falling within the target read / write speed range from the plurality of reference storage media to obtain the target storage medium.

[0126] As an optional embodiment, the first screening unit is further configured to:

[0127] Traversing the read and write speed of each reference storage medium among the plurality of reference storage media;

[0128] Compare the current read / write speed traversed with the target read / write speed range;

[0129] If the current read / write speed falls within the target read / write speed range, adding the current storage medium corresponding to the current read / write speed to the storage medium set until the read / write speeds of all reference storage media in the multiple reference storage media are traversed to obtain a target storage medium set;

[0130] In a case where there is one reference storage medium in the target storage medium set, determining the one reference storage medium as the target storage medium;

[0131] In a case where there are at least two reference storage media in the target storage medium set, the target storage medium is selected from the at least two reference storage media.

[0132] As an optional embodiment, the storage controller includes: a storage control component and a storage receiving component, the storage control component is deployed on the service server, the storage receiving component is deployed on the storage device where the multiple storage media are located, and the storage control component is not connected to the storage receiving component;

[0133] The receiving module includes: a third extracting unit, configured to extract, through the storage control component, the target data write request generated by the target service server and to be sent to the storage device;

[0134] The generating module includes: a second detecting unit for detecting the target data parameter through the storage control component; a second generating unit for generating the target data characteristic according to the target data parameter through the storage control component; an adding unit for adding the target data characteristic to the target data write request through the storage control component to obtain a characteristic data write request; and a sending unit for sending the characteristic data write request to the storage receiving component through the storage control component.

[0135] The screening module includes: a receiving unit for receiving, through the storage receiving component, a reference data write request sent by the storage control component; a third detecting unit for detecting whether the reference data write request carries the target data feature; a second screening unit for, if it is detected that the reference data write request carries the target data feature, screening the target storage medium from the multiple reference storage media according to the target data feature through the storage receiving component; a fourth detecting unit for, if it is detected that the reference data write request does not carry the target data feature, detecting candidate data features of the target data through the storage receiving component; a third screening unit for, if it is detected that the reference data write request does not carry the target data feature, screening the storage medium from the multiple reference storage media according to the candidate data feature, as the target storage medium;

[0136] The writing module includes: a writing unit, configured to write the target data into the target storage medium through the storage receiving component.

[0137] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0138] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above method embodiments when run.

[0139] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0140] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0141] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0142] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0143] An embodiment of the present application further provides another computer program product, comprising a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0144] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any of the above method embodiments.

[0145] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0146] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0147] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Persons skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for storing server data, characterized in that: Applied to a storage controller, the storage controller is used to establish a connection between a service server and multiple storage media, wherein the multiple storage media have different read and write speeds, the method comprising: receiving a target data write request initiated by a target service server connected to the storage controller, wherein the target data write request is used to request writing target data into a plurality of reference storage media connected to the storage controller; generating a target data feature of the target data according to the detected target data parameters of the target data, wherein the target data parameters are used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target read / write speed expected for writing the target data; Filtering, from the plurality of reference storage media according to the target data characteristics, a target storage medium whose read / write speed matches the target data characteristics; The target data is written into the target storage medium.

2. The method according to claim 1, characterized in that Generating the target data features of the target data according to the detected target data parameters of the target data includes: Extracting a data volume parameter, a duration parameter, and a call parameter of the target data, wherein the target data parameters include the data volume parameter and the duration parameter, the data volume parameter is used to indicate the data volume of the target data, the duration parameter is used to indicate the time consumed for writing the target data, and the call parameter is used to indicate how frequently the target data is called; A weighted sum operation is performed on the data volume parameter, the duration parameter, and the call parameter to obtain the target data feature.

3. The method according to claim 1, characterized in that Generating the target data features of the target data according to the detected target data parameters of the target data includes: detecting compression ratio information and a target data access mode of the target data, wherein the compression ratio information is used to indicate a data compression ratio of the target data, and the target data access mode is used to indicate a data access mode supported by the target data; The target data characteristics are generated based on the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode, wherein the target data parameters include the complexity parameter and the access parameter, the complexity parameter is used to indicate the complexity of the data content of the target data, and the target access parameter is used to indicate the degree of influence of the target data access mode on the difficulty of data storage.

4. The method according to claim 3, characterized in that Generating the target data feature according to the complexity parameter corresponding to the compression ratio information and the target access parameter corresponding to the target data access mode includes: Calculating the complexity parameter using the compression ratio information, and extracting the access parameter corresponding to the target data access mode from the data access modes and access parameters having a corresponding relationship as the target access parameter; A weighted sum operation is performed on the complexity parameter and the target access parameter to obtain the target data feature.

5. The method according to claim 1, characterized in that The step of selecting a target storage medium having a read / write speed matching the target data characteristic from the plurality of reference storage media according to the target data characteristic includes: Searching for a target data feature interval in which the target data feature falls from a plurality of data feature intervals; Extracting a target reading and writing speed interval corresponding to the target data feature interval from data feature intervals and reading and writing speed intervals having a corresponding relationship; Storage media having a read / write speed falling within the target read / write speed range are screened out from the multiple reference storage media to obtain the target storage medium.

6. The method according to claim 5, characterized in that The step of selecting a storage medium having a read / write speed falling within the target read / write speed range from the plurality of reference storage media to obtain the target storage medium includes: Traversing the read and write speed of each reference storage medium among the plurality of reference storage media; Compare the current read / write speed traversed with the target read / write speed range; If the current read / write speed falls within the target read / write speed range, adding the current storage medium corresponding to the current read / write speed to the storage medium set until the read / write speeds of all reference storage media in the multiple reference storage media are traversed to obtain a target storage medium set; In a case where there is one reference storage medium in the target storage medium set, determining the one reference storage medium as the target storage medium; In a case where there are at least two reference storage media in the target storage medium set, the target storage medium is selected from the at least two reference storage media.

7. The method according to claim 1, characterized in that The storage controller includes: a storage control component and a storage receiving component, the storage control component is deployed on the service server, the storage receiving component is deployed on the storage device where the multiple storage media are located, and the storage control component is connected to the storage receiving component; The receiving a target data write request initiated by a target service server connected to the storage controller includes: extracting, by the storage control component, the target data write request generated by the target service server and to be sent to the storage device; Generating the target data feature of the target data according to the detected target data parameter of the target data includes: detecting the target data parameter by the storage control component; generating the target data feature according to the target data parameter by the storage control component; adding the target data feature to the target data write request by the storage control component to obtain a feature data write request; and sending the feature data write request to the storage receiving component by the storage control component; The selecting, from the plurality of reference storage media according to the target data feature, a target storage medium having a read / write speed that matches the target data feature, comprises: receiving, by the storage receiving component, a reference data write request sent by the storage control component; detecting whether the reference data write request carries the target data feature; if it is detected that the reference data write request carries the target data feature, selecting, by the storage receiving component, the target storage medium from the plurality of reference storage media according to the target data feature; if it is detected that the reference data write request does not carry the target data feature, detecting, by the storage receiving component, a candidate data feature of the target data; selecting, by the storage receiving component, a storage medium having a read / write speed that matches the candidate data feature as the target storage medium, from the plurality of reference storage media according to the candidate data feature; The writing the target data into the target storage medium includes: writing the target data into the target storage medium through the storage receiving component.

8. A storage device for server data, characterized in that: Applied to a storage controller, the storage controller is used to establish a connection between a service server and multiple storage media, wherein the multiple storage media have different read and write speeds, the device comprising: a receiving module, configured to receive a target data write request initiated by a target service server connected to the storage controller, wherein the target data write request is used to request writing target data into a plurality of reference storage media connected to the storage controller; a generating module, configured to generate a target data feature of the target data according to the detected target data parameters of the target data, wherein the target data parameters are used to indicate the complexity of writing the target data, and the target data feature is used to characterize the target reading and writing speed expected for writing the target data; a screening module, configured to screen, from the plurality of reference storage media, a target storage medium having a read / write speed matching the target data characteristic according to the target data characteristic; A writing module is used to write the target data into the target storage medium.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images