A data storage method, system, device and medium

Abstract

This invention relates to the field of storage technology and discloses a data storage method, system, device, and medium. The method includes: determining whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request; in response to the network path being in a fault state, acquiring target data based on the read / write request; encapsulating the target data and caching the encapsulated target data to an external preset storage device; monitoring whether the corresponding network path has recovered to a healthy state; and in response to the network path recovering to a healthy state, storing the memory data corresponding to the read / write request to the target storage device based on the preset storage device. This invention avoids the problem of external storage being unable to write data normally when a SAN network or SAN storage device fails, enhancing the data reliability and integrity of the SAN storage device in fault scenarios.

Description

Technical Field

[0001] This invention relates to the field of storage technology, and in particular to a data storage method, system, device and medium. Background Technology

[0002] In large data centers, to meet the high storage capacity demands of businesses, servers typically use SAN (Storage Area Network) connections to external storage as a solution. At the operating system level, due to performance considerations, when data changes, the system generally does not immediately write the data directly to disk. Instead, it modifies the data in memory first and only writes it to disk after certain conditions are met. However, if the SAN network or SAN storage device fails, the system cannot synchronize the data updates in memory to disk, leading to the loss of a small amount of data. Currently, to compensate for this data loss, rollback or data repair is usually performed using application layer, database transaction logs, or file system logs. However, even with these methods, some data loss cannot be completely avoided.

[0003] Therefore, there is still room for improvement in the existing technology. Summary of the Invention

[0004] In view of this, the present invention proposes a data storage method, system, device and medium to avoid the problem that external storage cannot be written normally when the SAN network or SAN storage device fails, thereby enhancing the data reliability and integrity of SAN storage devices in failure scenarios.

[0005] To achieve the above objectives, one aspect of the present invention provides a data storage method, specifically including the following steps:

[0006] Based on the response message corresponding to the read / write request, determine whether the network path corresponding to the read / write request is in a fault state;

[0007] In response to a fault in the corresponding network path, the target data is obtained based on the read / write request;

[0008] The target data is encapsulated, and the encapsulated target data is cached to an external preset storage device;

[0009] Monitor whether the corresponding network path has returned to a healthy state;

[0010] In response to the network path recovering to a healthy state, the memory data corresponding to the read / write request is stored in the target storage device based on the preset storage device.

[0011] In some embodiments, the step of encapsulating the target data and caching the encapsulated target data to an external preset storage device includes:

[0012] The target data is encapsulated into a structured data packet;

[0013] According to the preset configuration information, the packaged target data is cached to an external preset storage device;

[0014] The target data includes metadata and memory data. The preset configuration information includes IP address, timeout period, backup storage device IP address and available space alarm threshold. The preset storage device includes one of NFS file system and iSCSI storage system.

[0015] In some implementations, the step of determining whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request includes:

[0016] The system monitors the read and write requests sent to the target storage device in real time and determines whether the received response message is a success response message returned by the target storage device.

[0017] In response to the received response message being a success response message returned by the target storage device, the network path corresponding to the read / write request is determined to be in a healthy state;

[0018] If the received response message is not a success response message returned by the target storage device, the network path corresponding to the read / write request is determined to be in a fault state.

[0019] In some embodiments, the step of storing the memory data corresponding to the read / write request to the target storage device based on the preset storage device includes:

[0020] Based on the metadata, the memory data is loaded from the preset storage device to restore the read / write request;

[0021] The recovered read / write requests are rescheduled and sent to the network path;

[0022] The memory data corresponding to the read / write request is stored in the target storage device via the network path.

[0023] In some implementations, the step of obtaining the target data based on the read / write request includes:

[0024] Obtain the metadata and stored data corresponding to the read / write request, and use the metadata and stored data together as the target data.

[0025] In some implementations, the step of monitoring whether the corresponding network path has recovered to a healthy state includes:

[0026] Test commands are sent to the corresponding network path at intervals, and the corresponding network path is monitored to see if it receives a success response message from the target storage device.

[0027] Upon receiving a success response message from the target storage device, it is confirmed that the network path has returned to a healthy state.

[0028] In some embodiments, the data storage method further includes:

[0029] In response to the read / write request, the memory data corresponding to the read / write data is stored in the target storage device, and the target data cached in the preset storage device is deleted.

[0030] Another aspect of this invention provides a data storage system, comprising:

[0031] The fault monitoring unit is configured to determine whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request.

[0032] A data acquisition unit is configured to acquire target data based on the read / write request in response to a fault in the corresponding network path.

[0033] A data encapsulation unit is configured to encapsulate the target data and cache the encapsulated target data to an external preset storage device.

[0034] A health monitoring unit is configured to monitor whether the corresponding network path has recovered to a healthy state.

[0035] The data recovery unit is configured to restore the health status of the corresponding network path and, based on the preset storage device, store the memory data corresponding to the read / write request to the target storage device.

[0036] In another aspect of the present invention, a computer device is provided, comprising: at least one processor; and a memory storing a computer program executable on the processor, the computer program performing the steps of the method described above when executed by the processor.

[0037] In another aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method steps.

[0038] The present invention has at least the following beneficial technical effects: The data storage method of the present invention adopts a real-time monitoring mechanism for read and write requests, and quickly detects SAN network anomalies by responding to messages. For read and write requests on faulty network paths, the target data corresponding to them is temporarily stored in a preset storage device to provide additional data security protection and avoid data loss. When the faulty network path recovers, the temporarily stored target data is restored as a read and write request and rescheduled to the network path to correctly write the memory data in the read and write request to the target storage device, avoiding data errors or missing data caused by the fault, and enhancing the data reliability and integrity in SAN storage device failure scenarios. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0040] Figure 1 A block diagram illustrating an embodiment of the data storage method provided by the present invention;

[0041] Figure 2 A schematic diagram of an embodiment of the data storage method execution flow provided by the present invention.

[0042] Figure 3 A schematic diagram of an embodiment of the data storage system provided by the present invention;

[0043] Figure 4 A schematic diagram of the structure of an embodiment of the computer device provided by the present invention;

[0044] Figure 5 This is a schematic diagram of an embodiment of the computer-readable storage medium provided by the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to specific examples and the accompanying drawings.

[0046] It should be noted that all uses of "first" and "second" in the embodiments of the present invention are for the purpose of distinguishing two entities or parameters with the same name but different names. It is clear that "first" and "second" are only for the convenience of expression and should not be construed as limiting the embodiments of the present invention. Subsequent embodiments will not explain this in detail.

[0047] In critical production environments, to ensure I / O (Input / Output) performance and system reliability, each server (or operating system) is typically configured with multiple HBA (Host Bus Adapter) cards. These HBA cards connect to the target storage device via different SAN storage network switches. Therefore, each storage disk identified by the operating system usually has multiple independent physical paths (PATHs) for I / O interaction with the external storage device. Traditional MPIO (Multi-Path I / O) software, including built-in integrated solutions or third-party storage multi-path software, distributes disk I / O requests to different PATHs based on specific algorithms to ensure that requests successfully reach the target storage device and return a completion message. However, when external storage or the SAN network fails and cannot recover on its own, I / O requests may return errors or fail, impacting business continuity.

[0048] Based on the above objectives, a first aspect of the present invention provides a data storage method. For example... Figure 1 As shown, the data storage method includes the following steps:

[0049] Step S100: Based on the response message corresponding to the read / write request, determine whether the network path corresponding to the read / write request is in a fault state;

[0050] Step S200: In response to the corresponding network path being in a fault state, obtain the target data based on the read / write request;

[0051] Step S300: Encapsulate the target data and cache the encapsulated target data to an external preset storage device;

[0052] Step S400: Monitor whether the corresponding network path has returned to a healthy state;

[0053] In step S500, in response to the corresponding network path recovering to a healthy state, the memory data corresponding to the read / write request is stored in the target storage device based on the preset storage device.

[0054] In some implementations, read / write requests are I / O requests used to write memory data to the target storage device. MPIO multipathing software schedules these I / O requests to the corresponding PATH (i.e., network path) according to a specific algorithm, ensuring the memory data reaches the target storage device. Preset storage devices include iSCSI (Internet Small Computer System Interface, a storage protocol based on IP networks) devices or NFS (Network File System) network file systems. The target storage device is any external storage connected to the SAN network.

[0055] In some implementations, to address the above-mentioned problems, an I / O scheduling module is provided. The data storage method of the present invention is applied to this I / O scheduling module as a kernel extension program of the operating system, and is automatically loaded when the host system starts up. Figure 2 As shown, this IO scheduling module can be considered a functional enhancement to existing MPIO multipath software, aiming to provide higher fault tolerance and data protection mechanisms to ensure that IO requests can be properly handled and recovered in the event of SAN storage device or SAN network failure. The IO scheduling module includes a preset storage device, an IP network write module, a SAN data recovery module, and a SAN storage fault detection module. The IP network write module saves unsaved memory data and target storage device information to the preset storage device when the SAN network fails. The SAN data recovery module reads the unsaved memory data from the preset storage device and writes it to the target storage device when the SAN network recovers. The SAN storage fault detection module is used to detect SAN network failures in real time, activates the IP network write module to back up memory data when the SAN network fails, and calls the SAN data recovery module to recover memory data when the SAN network recovers. Figure 2 In this context, Application refers to the host system application, Database refers to the database, Disk Driver refers to the disk drive, HBA adapter Driver refers to the host bus adapter driver, HBA adapter refers to the host bus adapter, SAN Switch refers to the SAN storage network switch, SAN Storage refers to the target storage device, iSCSI Driver refers to the iSCSI driver, NIC adapter refers to the network interface card, Network switch refers to the Ethernet switch, iSCSI storage refers to the iSCSI storage system, and NAS storage refers to the dedicated data storage server.

[0056] The data storage method of the present invention adds a preset storage device, such as an iSCSI device or an NFS network file system, to the system, and then improves the operating system by setting an IO scheduling module. This allows the operating system to write data to the preset storage device when it finds that the SAN network cannot write memory data to the target storage device. When it is determined that the SAN network has recovered, the data in the preset storage device can be synchronized to the target storage device. This method enhances the data reliability and integrity in SAN storage device failure scenarios.

[0057] In some implementations, the step of encapsulating target data and caching the encapsulated target data to an external preset storage device includes: encapsulating the target data into a structured data packet; caching the encapsulated target data to an external preset storage device according to preset configuration information; wherein the target data includes metadata and memory data, the preset configuration information includes IP address, timeout period, backup storage device IP address and available space alarm threshold, and the preset storage device includes one of NFS file system and iSCSI storage system.

[0058] In some implementations, once an IO request returns an error or fails, the IO scheduling module immediately encapsulates the target data related to the affected IO request, such as... Figure 2 As shown in "Circle 1", the target data includes metadata and DATA (raw information stored in the computer) of the IO request. Metadata includes the request ID, path information, timestamp, and request status, while DATA is the data content to be written to the target storage device, i.e., in-memory data. Metadata encapsulation includes structured format encapsulation, including JSON, XML, or binary structures. DATA encapsulation includes associating DATA with metadata and then compressing, encoding, or performing integrity checks on the data content. Metadata and DATA are encapsulated into structured data packets for easy storage and transmission. The metadata can be saved as IO log records, uniquely identified by the request ID, facilitating subsequent retrieval and matching of the corresponding DATA during recovery. The IO scheduling module transmits the encapsulated metadata and DATA to a preset storage device via Ethernet for temporary storage according to the preset configuration information. The operating system provides a preset configuration file for the IO scheduling module. The preset configuration file can determine whether to enable the enhanced functions of the IO scheduling module, obtain the IP address of the target storage device, obtain the timeout period to determine the data storage time limit, obtain the IP address of the backup storage device to determine whether there is a backup external storage device, and obtain the available space alarm threshold to trigger an alarm when space is insufficient.

[0059] The data storage method of this invention allows the operating system to temporarily save incomplete memory data to network storage spaces such as NFS or iSCSI storage via Ethernet when a SAN network failure prevents external target storage devices from writing data. This facilitates the operating system to synchronously store this memory data in the target storage after the SAN network recovers, thereby effectively improving data reliability and integrity in SAN storage failure scenarios.

[0060] In some implementations, the step of determining whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request includes: real-time monitoring of read / write requests sent to the target storage device, and determining whether the received response message is a success response message returned by the target storage device; in response to the received response message being a success response message returned by the target storage device, determining that the network path corresponding to the read / write request is in a healthy state; in response to the received response message not being a success response message returned by the target storage device, determining that the network path corresponding to the read / write request is in a fault state.

[0061] In some implementations, the I / O requests managed by the MPIO multipath software are monitored in real time. This monitoring includes checking whether the I / O requests return errors or fail. When the received response message is a success message from the target storage device, it indicates that the I / O request has been successfully completed, and the PATH path corresponding to the I / O request is in a normal transmission state, i.e., a healthy state. When the received response message is an error or failure message, i.e., a success message from the target storage device, the PATH path corresponding to the I / O request or the target storage device is in a fault state.

[0062] The data storage method of the present invention adopts a real-time monitoring mechanism for IO requests, and can quickly detect SAN network anomalies by responding to messages, which is conducive to timely saving unwritten memory data to temporary data storage space via Ethernet.

[0063] In some implementations, the step of storing memory data corresponding to a read / write request to a target storage device based on a preset storage device includes: loading memory data from the preset storage device to restore the read / write request according to metadata; rescheduling the restored read / write request to send it to a network path; and storing the memory data corresponding to the read / write request to the target storage device via the network path.

[0064] In some implementations, the IO scheduling module locates the corresponding DATA data for an IO request based on the IO request log records (i.e., metadata) in the NFS file system or iSCSI storage system, loads the DATA data from the NFS file system or iSCSI storage system into the operating system's physical memory, thereby restoring the IO request and rescheduling the IO request to the MPIO multipath software, such as... Figure 2 As shown in "Circle 2". The MPIO multipath software then re-controls the write operation of the IO request according to its original mode or algorithm, and completes the storage of the corresponding memory data to the target storage device.

[0065] The data storage method of the present invention, in the recovery phase, loads memory data into the physical memory of the operating system after reading the IO request log records. This ensures that after the SAN network is restored, unfinished IO requests can be accurately scheduled and rewritten to the target storage device, guaranteeing data integrity and consistency. It effectively solves the problem of data corruption or loss caused by the loss of IO requests in traditional failure scenarios, ensuring business continuity.

[0066] In some implementations, the step of obtaining target data based on read / write requests includes: obtaining metadata and stored data corresponding to the read / write requests, and using the metadata and stored data together as target data.

[0067] In some implementations, the step of monitoring whether the corresponding network path has recovered to a healthy state includes: sending test commands to the corresponding network path at intervals and monitoring whether the corresponding network path receives a success response message returned by the target storage device; and confirming that the network path has recovered to a healthy state in response to receiving a success response message returned by the target storage device.

[0068] In some embodiments, the data storage method of the present invention further includes: storing memory data corresponding to a read / write request to a target storage device, and deleting the target data cached in a preset storage device.

[0069] In some implementations, the IO scheduling module continuously and periodically checks the faulty PATH after a SAN network or storage failure, such as through the HealthCheck function in the MPIO software. HealthCheck refers to the process where, when one or more PATHs on a disk fail, their status typically changes to unavailable. The MPIO multipath software then periodically issues test commands to the unavailable PATHs until they recover. Once a PATH is found to have recovered and its status is stable, the network path is considered to have returned to a healthy state.

[0070] In some implementations, when the PATH fault is recovered and its corresponding IO request is successfully completed, the IO scheduling module will delete the relevant data and records in the preset storage device to complete the fault recovery.

[0071] In some implementations, in addition to ensuring the timeliness and availability of the IO scheduling module, the IO scheduling module will also periodically perform IO read / write tests and available space checks on the configured preset storage devices. Once problems such as insufficient available space, IO errors, or large IO delays are found, an alarm will be generated and saved to the operating system's error log.

[0072] The data storage method of this invention employs a real-time monitoring mechanism for read and write requests. By responding to messages, it quickly detects SAN network anomalies. For read and write requests on faulty network paths, the corresponding target data is temporarily stored in a preset storage device to provide additional data security protection and avoid data loss. When the faulty network path recovers, the temporarily stored target data is restored as a read and write request and rescheduled to the network path to correctly write the memory data in the read and write request to the target storage device. This avoids data errors or missing data caused by the fault and enhances the data reliability and integrity in SAN storage device failure scenarios.

[0073] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 3 As shown, embodiments of the present invention also provide a data storage system, including:

[0074] The fault monitoring unit 110 is configured to determine whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request.

[0075] Data acquisition unit 120 is configured to acquire target data based on read / write requests in response to a fault in the corresponding network path.

[0076] Encapsulated data unit 130 is configured to encapsulate target data and cache the encapsulated target data to an external preset storage device;

[0077] The health monitoring unit 140 is configured to monitor whether the corresponding network path has recovered to a healthy state.

[0078] The recovery data unit 150 is configured to restore a healthy state in response to the corresponding network path, and to store the memory data corresponding to the read / write request to the target storage device based on the preset storage device.

[0079] The data storage system of this invention employs a real-time monitoring mechanism for read and write requests. By responding to messages, it quickly detects SAN network anomalies. For read and write requests on faulty network paths, the corresponding target data is temporarily stored in a preset storage device to provide additional data security protection and avoid data loss. When the faulty network path recovers, the temporarily stored target data is restored as a read and write request and rescheduled to the network path to correctly write the memory data in the read and write request to the target storage device. This avoids data errors or missing data caused by the fault and enhances the data reliability and integrity in SAN storage device failure scenarios.

[0080] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 4 As shown, an embodiment of the present invention also provides a computer device 30, which includes a processor 310 and a memory 320. The memory 320 stores a computer program 321 that can be run on the processor. When the processor 310 executes the program, it performs the steps of the method described above.

[0081] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 5 As shown, embodiments of the present invention also provide a computer-readable storage medium 40, which stores a computer program 410 that, when executed by a processor, performs the methods described above.

[0082] Finally, it should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium for the program can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The above computer program embodiments can achieve the same or similar effects as any of the corresponding foregoing method embodiments.

[0083] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the functionality of various illustrative components, blocks, modules, circuits, and steps has been generally described. Whether this functionality is implemented as software or as hardware depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art can implement the functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the embodiments disclosed herein.

[0084] The above are exemplary embodiments disclosed in this invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments of this invention as defined by the claims. The functions, steps, and / or actions of the methods according to the disclosed embodiments described herein do not need to be performed in any particular order. The sequence numbers of the disclosed embodiments of this invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. Furthermore, although the elements disclosed in the embodiments of this invention may be described or claimed individually, they may be understood as multiple unless explicitly limited to a singular number.

[0085] It should be understood that, as used herein, the singular form “a” is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, “and / or” refers to any and all possible combinations of one or more of the associated listed items.

[0086] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A data storage method, characterized in that, Applied to the IO scheduling module, including: Based on the response message corresponding to the read / write request, determine whether the network path corresponding to the read / write request is in a fault state; In response to a fault in the corresponding network path, the target data is obtained based on the read / write request; The target data is encapsulated and cached to an external preset storage device. This includes: encapsulating the target data into a structured data packet; and caching the encapsulated target data to the external preset storage device according to preset configuration information. The target data includes metadata and memory data. The metadata includes a request ID, path information, timestamp, and request status. The metadata can be stored as an IO log record and uniquely identified by the request ID. The memory data includes the data content to be written to the target storage device. The preset configuration information includes an IP address, timeout period, backup storage device IP address, and available space alarm threshold. The preset storage device includes either an NFS file system or an iSCSI storage system. Test commands are sent to the corresponding network path at intervals, and the corresponding network path is monitored to see if it receives a success response message from the target storage device, so as to monitor whether the corresponding network path has recovered to a healthy state. In response to the network path recovering to a healthy state, the memory data corresponding to the read / write request is stored in the target storage device based on the preset storage device. This includes: the IO scheduling module finding the memory data corresponding to the read / write request according to the metadata in the IO log record, loading the memory data from the preset storage device to restore the read / write request, rescheduling the restored read / write request to send it to the network path, and storing the memory data corresponding to the read / write request in the target storage device through the network path.

2. The data storage method according to claim 1, characterized in that, The step of determining whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request includes: The system monitors the read and write requests sent to the target storage device in real time and determines whether the received response message is a success response message returned by the target storage device. In response to the received response message being a success response message returned by the target storage device, the network path corresponding to the read / write request is determined to be in a healthy state; If the received response message is not a success response message returned by the target storage device, the network path corresponding to the read / write request is determined to be in a fault state.

3. The data storage method according to claim 1, characterized in that, The step of obtaining the target data based on the read / write request includes: Obtain the metadata and stored data corresponding to the read / write request, and use the metadata and stored data together as the target data.

4. The data storage method according to claim 1, characterized in that, The step of monitoring whether the corresponding network path has returned to a healthy state includes: Test commands are sent to the corresponding network path at intervals, and the corresponding network path is monitored to see if it receives a success response message from the target storage device. Upon receiving a success response message from the target storage device, it is confirmed that the network path has returned to a healthy state.

5. The data storage method according to claim 1, characterized in that, Also includes: In response to the read / write request, the memory data corresponding to the read / write data is stored in the target storage device, and the target data cached in the preset storage device is deleted.

6. A data storage system, characterized in that, include: The fault monitoring unit is configured to determine whether the network path corresponding to the read / write request is in a fault state based on the response message corresponding to the read / write request. A data acquisition unit is configured to acquire target data based on the read / write request in response to a fault in the corresponding network path. A data encapsulation unit is configured to encapsulate the target data and cache the encapsulated target data to an external preset storage device. A health monitoring unit is configured to periodically send test commands to the corresponding network path and monitor whether the corresponding network path receives a successful response message returned by the target storage device, so as to monitor whether the corresponding network path has recovered to a healthy state. The data recovery unit is configured to restore a healthy state in response to the corresponding network path, and to store the memory data corresponding to the read / write request to the target storage device based on the preset storage device. The encapsulation data unit is also configured to: encapsulate the target data into a structured data packet; According to the preset configuration information, the encapsulated target data is cached to an external preset storage device; wherein, the target data includes metadata and memory data, the metadata includes request ID, path information, timestamp and request status, wherein the metadata can be saved as IO log records and uniquely identified by request ID, the memory data includes the data content to be written to the target storage device, the preset configuration information includes IP address, timeout period, backup storage device IP address and available space alarm threshold, and the preset storage device includes one of NFS file system and iSCSI storage system; The recovery data unit is further configured to: the IO scheduling module finds the memory data corresponding to the read / write request based on the metadata in the IO log record, loads the memory data from the preset storage device to recover the read / write request, reschedules the recovered read / write request to send it to the network path, and stores the memory data corresponding to the read / write request to the target storage device through the network path.

7. A computer device, comprising: At least one processor; as well as A memory storing a computer program executable on the processor, characterized in that the processor executes the program by performing the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it performs the steps of the method as described in any one of claims 1 to 5.

Images