Control method and device of storage system

Abstract

The invention provides a control method and device for a storage system, and the method comprises the steps: detecting a current target equipment state of target storage equipment in the storage system according to a plurality of pieces of detection information corresponding to a plurality of detection items, the target equipment state is used for indicating the possibility that the current running state of the target storage equipment on each detection item causes the fault of the target storage equipment; obtaining a current target fault state of the target storage device according to a target association relationship and the target device state, wherein the target association relationship is a relationship between the device state of the target storage device and the fault state of the target storage device in a historical time period before the current moment; and under the condition that the target probability indicated by the target fault state is greater than or equal to the target probability threshold, executing data protection operation on the data stored in the target storage equipment. Through the data access method and device, the problem that the data access efficiency of the storage system is low is solved, and the effect of improving the data access efficiency of the storage system is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, to a control method and device for a storage system. Background Art

[0002] With the development of computer technology and network technology, data is growing at an explosive rate. The storage demand for massive information poses a huge challenge to storage devices and storage systems. Currently, an erasure code fault-tolerant technology is used to deal with the problem of storage device failure that is prone to occur in storage systems. When storing data, multiple copies of encoding information corresponding to the data of the storage device are stored on other storage devices respectively, so that in the event of a storage device failure, these multiple copies of encoding information can be obtained from other storage devices to repair the data stored on the failed storage device. However, this approach involves cross-device data transmission between multiple storage devices and complex data repair operations. The operation is difficult, occupies a lot of resources, and takes a long time, which seriously affects the data access efficiency of the storage system. Summary of the invention

[0003] The embodiments of the present application provide a storage system control method and device to at least solve the problem of low data access efficiency of the storage system in the related art.

[0004] According to an embodiment of the present application, a storage system control method is provided, including:

[0005] Detecting a current target device state of a target storage device in a storage system according to a plurality of detection information corresponding to a plurality of detection items, wherein the detection information is used to indicate an operating state of the target storage device on the corresponding detection item, and the target device state is used to indicate a possibility that a current operating state of the target storage device on each of the detection items causes a failure of the target storage device;

[0006] Acquire the current target fault state of the target storage device according to the target association relationship and the target device state, wherein the target association relationship is the relationship between the device state of the target storage device and the fault state of the target storage device in a historical time period before a current moment, and the fault state is used to indicate the probability that the target storage device will fail;

[0007] In a case where the target probability indicated by the target failure state is greater than or equal to a target probability threshold, a data protection operation is performed on the data stored in the target storage device.

[0008] In an exemplary embodiment, the acquiring the current target failure state of the target storage device according to the target association relationship and the target device state includes:

[0009] Extracting a first fault state corresponding to the target device state from the target association relationship;

[0010] The first fault state is adjusted toward a second fault state of the target storage device to obtain the target fault state, wherein the second fault state is a fault state detected on the target storage device before the current moment.

[0011] In an exemplary embodiment, adjusting the first fault state to the second fault state of the target storage device to obtain the target fault state includes:

[0012] The target probability is calculated by the following formula:

[0013] ,

[0014] Where P is the target probability, P n is the first probability indicated by the first fault state, P n-1 is the second probability indicated by the second failure state detected on the target storage device during the last detection, is the weight coefficient corresponding to the first probability, is the weight coefficient corresponding to the second probability.

[0015] In an exemplary embodiment, before acquiring the current target failure state of the target storage device according to the target association relationship and the target device state, the method further includes:

[0016] Detecting the fault information of the target storage device at multiple time points within the historical time period, and collecting the device status of the target storage device at the multiple time points to obtain multiple groups of status association information, wherein the fault information is used to indicate whether the target storage device has a fault, and the status association information includes the fault information and the device status having a corresponding relationship;

[0017] The first failure probability of the target storage device failing under each of the device states is calculated according to the multiple groups of state association information to obtain the target association relationship, wherein the failure state includes the first failure probability.

[0018] In an exemplary embodiment, the calculating, according to the multiple groups of state association information, a first failure probability of the target storage device failing in each of the device states includes:

[0019] The first failure probability corresponding to each of the device states is calculated by the following formula:

[0020] F=N1 / N 2 ,

[0021] Where F is the first failure probability corresponding to the reference equipment state, N 2 is the number of the reference device states in the plurality of device states, N 1 The corresponding fault information in the plurality of device states is used to indicate the number of the reference device states in which the target storage device has failed.

[0022] In an exemplary embodiment, detecting the current target device state of a target storage device in a storage system according to multiple detection information corresponding to multiple detection items includes:

[0023] Determining, according to the reference range corresponding to each of the detection items and a plurality of project parameters, the associated parameters corresponding to each of the detection items, wherein the plurality of detection information includes the plurality of project parameters, and the associated parameters are used to indicate the probability that the operating state of the target storage device on the corresponding detection item will cause the target storage device to fail;

[0024] Arrange the plurality of associated parameters in a target order to obtain a target feature vector, wherein the target device state includes the target feature vector.

[0025] In an exemplary embodiment, determining the associated parameters corresponding to each of the detection items according to the reference ranges corresponding to each of the detection items and a plurality of project parameters includes:

[0026] Detecting whether each of the project parameters falls within the corresponding reference range;

[0027] In the case where it is detected that the item parameter falls within the corresponding reference range, determining the associated parameter to be a first associated parameter, wherein the first associated parameter is used to indicate that the operating state of the target storage device on the corresponding detection item causes a low probability that the target storage device will fail;

[0028] When it is detected that the project parameter does not fall within the corresponding reference range, the associated parameter is determined to be a second associated parameter, wherein the second associated parameter is used to indicate that the operating status of the target storage device on the corresponding detection item has a high probability of causing a failure of the target storage device.

[0029] In an exemplary embodiment, before determining the associated parameters corresponding to each of the detection items according to the reference ranges corresponding to each of the detection items and a plurality of project parameters, the method further includes:

[0030] Detecting target parameters of the target storage device corresponding to the target detection item and fault information of the target storage device according to the target frequency within a reference time period before the current moment, and obtaining multiple sets of reference association information, wherein the target parameter is used to indicate the operating state of the target storage device on the target detection item, and the fault information is used to indicate whether the target storage device fails, the reference association information includes the fault information and the target parameter having a corresponding relationship, and the multiple detection items include the target detection item;

[0031] Calculating, according to the multiple sets of reference association information, a second failure probability that the target storage device fails when the target parameter is less than each parameter threshold, to obtain multiple sets of intermediate association information, wherein the intermediate association information includes the parameter threshold and the second failure probability having a corresponding relationship;

[0032] The target sub-range of the target detection item is determined according to the multiple groups of intermediate correlation information and the detection probability threshold of the target detection item, wherein the reference range includes the target sub-range, and the second fault probability corresponding to the operating state indicated by the target parameter within the target sub-range is less than or equal to the detection probability threshold.

[0033] In an exemplary embodiment, determining a target subrange of the target detection item according to the multiple groups of intermediate association information and a detection probability threshold of the target detection item includes:

[0034] Determining a cumulative distribution function of the target detection item according to the multiple groups of intermediate association information;

[0035] Determine, from the plurality of parameter thresholds, a parameter threshold whose corresponding second fault probability is less than or equal to the detection probability threshold according to the cumulative distribution function and the detection probability threshold, and obtain a target parameter threshold;

[0036] The target subrange is determined to be zero to the target parameter threshold.

[0037] In an exemplary embodiment, the distributed storage system includes a backup storage device and a plurality of in-use storage devices, the plurality of in-use storage devices include the target storage device, and the plurality of in-use storage devices and the backup storage device are connected to each other;

[0038] The performing a data protection operation on the data stored in the target storage device includes:

[0039] Copying the data stored in the target storage device to the backup storage device;

[0040] The access to the target storage device in the distributed storage system is converted into the access to the backup storage device, and the access to the target storage device is prohibited in the distributed storage system.

[0041] In an exemplary embodiment, after performing a data protection operation on the data stored in the target storage device, the method further includes:

[0042] Detecting the failure risk cause of the target storage device according to the multiple detection information, wherein the failure risk cause is a cause that causes the target probability to be greater than or equal to the target probability threshold, and the failure risk cause includes a hardware cause and a software cause;

[0043] In the case where it is detected that the cause of the failure risk is the software cause, searching for a software recovery operation corresponding to the software cause; performing the software recovery operation on the target storage device; detecting the relationship between a reference probability of the target storage device after the software recovery operation is performed and the target probability threshold, wherein the reference probability is the probability that the target storage device will fail after the software recovery operation is performed; in the case where it is detected that the reference probability is less than the target probability threshold, restoring the data stored in the backup storage device to the target storage device, and restoring the access to the backup storage device in the distributed storage system to the access to the target storage device; clearing the data stored on the backup storage device;

[0044] When it is detected that the cause of the failure risk is the hardware reason, or when it is detected that the reference probability is greater than or equal to the target probability threshold, the target storage device is replaced with a reference storage device, wherein no data is stored in the reference storage device; and the reference storage device is determined as the backup storage device.

[0045] According to another embodiment of the present application, a control device of a storage system is provided, including:

[0046] A first detection module, configured to detect a current target device state of a target storage device in a storage system according to a plurality of detection information corresponding to a plurality of detection items, wherein the detection information is used to indicate an operating state of the target storage device on the corresponding detection item, and the target device state is used to indicate a possibility that a failure of the target storage device may occur due to the current operating state of the target storage device on each of the detection items;

[0047] a second detection module, configured to obtain a current target fault state of the target storage device according to a target association relationship and the target device state, wherein the target association relationship is a relationship between a device state of the target storage device and a fault state of the target storage device in a historical time period before a current moment, and the fault state is used to indicate a probability that the target storage device will fail;

[0048] An execution module is used to perform a data protection operation on the data stored in the target storage device when the target probability indicated by the target failure state is greater than or equal to a target probability threshold.

[0049] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0050] 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.

[0051] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0052] Through the present application, the possibility of the target storage device failing due to the current running state of the target storage device on each detection item is detected according to the running state of the target storage device in the storage system on each detection item, and then the probability of the target storage device failing is detected according to such possibility and the relationship between the possibility detected in the historical event segment before the current moment and the probability of the storage device failing. The influence of the performance of multiple detection items in the historical time period on whether the target storage device fails is combined to detect the probability of the current target storage device failing, which is more accurate. Then, when the detected target probability of failure is greater than or equal to the target probability threshold, a data protection operation is performed on the data stored in the target storage device, that is, based on the accurate prediction of the failure, a data protection operation is performed in advance on the data stored in the target storage device that is about to fail, thereby realizing active protection of the storage system, avoiding the need to use complex cross-storage device data repair operations when the failure has already occurred, reducing the occupation of the storage system's operating resources, and leaving more resources for data access to the storage system. Therefore, the problem of low data access efficiency of the storage system can be solved, and the effect of improving the data access efficiency of the storage system can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a hardware structure block diagram of a server device of a storage system control method according to an embodiment of the present application;

[0054] Figure 2 is a flow chart of a control method of a storage system according to an embodiment of the present application;

[0055] Figure 3 is a schematic diagram of a distributed storage system according to an embodiment of the present application;

[0056] Figure 4 is a flow chart of a use process according to an embodiment of the present application;

[0057] Figure 5 It is a structural block diagram of a control device of a storage system according to an embodiment of the present application. DETAILED DESCRIPTION

[0058] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0059] It should be noted that the terms "first", "second", etc. in the specification 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.

[0060] 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 1 is a hardware structure block diagram of a server device of a storage system control method according to an embodiment of the present application. Figure 1 As shown, the server device may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned server device may also include a transmission device 106 and an input / output device 108 for communication functions. It can 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 as shown, or with Figure 1 Different configurations shown.

[0061] 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 control method of the storage system 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, to implement 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 examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote 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.

[0062] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the server device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0063] In this embodiment, a storage system control method is provided. Figure 2 is a flow chart of a control method of a storage system according to an embodiment of the present application. Figure 2As shown, the process includes the following steps:

[0064] Step S202, detecting the current target device state of the target storage device in the storage system according to multiple detection information corresponding to the multiple detection items, wherein the detection information is used to indicate the operating state of the target storage device on the corresponding detection item, and the target device state is used to indicate the possibility that the operating state of the current target storage device on each detection item causes a failure of the target storage device;

[0065] Step S204, obtaining the current target fault state of the target storage device according to the target association relationship and the target device state, wherein the target association relationship is the relationship between the device state of the target storage device and the fault state of the target storage device in the historical time period before the current moment, and the fault state is used to indicate the probability that the target storage device will fail;

[0066] Step S206: When the target probability indicated by the target failure state is greater than or equal to the target probability threshold, a data protection operation is performed on the data stored in the target storage device.

[0067] Through the above steps, the possibility of the target storage device failing due to the current running state of the target storage device on each detection item is detected according to the running state of the target storage device in the storage system on each detection item, and then the probability of the target storage device failing is detected according to such possibility and the relationship between the possibility detected in the historical event segment before the current moment and the probability of the storage device failing. The probability of the current target storage device failing is detected by combining the influence of the performance of multiple detection items on whether the target storage device fails in the historical time period, which is more accurate. Then, when the detected target probability of failure is greater than or equal to the target probability threshold, a data protection operation is performed on the data stored in the target storage device, that is, based on the accurate prediction of the failure, a data protection operation is performed on the data stored in the target storage device that is about to fail in advance, thereby realizing active protection of the storage system, avoiding the need to use complex cross-storage device data repair operations when the failure has already occurred, reducing the occupation of the storage system's operating resources, and leaving more resources for data access to the storage system. Therefore, the problem of low data access efficiency of the storage system can be solved, and the effect of improving the data access efficiency of the storage system can be achieved.

[0068] In the embodiment provided in step S202, the target storage device is any storage device in the storage system, including but not limited to a data storage medium for storing data, which may include but is not limited to a hard disk drive (HDD), a solid state drive (SSD), a flash drive, a tape storage, and a memory device (such as NVDIMM). By monitoring the health status and potential failure risks of the target storage device through the above method, it is possible to timely perceive the impending failure of the target storage device and take corresponding protection operations to protect the security of the data stored on the data storage medium.

[0069] Optionally, in an embodiment of the present application, the detection items may be, but are not limited to, key indicators for evaluating the health status of storage devices and predicting potential failures, which reflect the operating status of storage devices in different aspects. The detection information may be, but is not limited to, used to characterize the operating status of the target storage device on the corresponding detection items, and the detection information may be, but is not limited to, SMART data, error count data, and workload data. More specifically, the detection items include, but are not limited to, the number of media errors, the number of data errors (Pending and Uncorrectable sectors), the number of reallocated sectors (Reallocated error), the number of Program (Write) / Erase (Erase) errors, the cumulative power-on time of the disk, the total number of NAND Writes, and the total number of NAND Read+Writes.

[0070] Optionally, in an embodiment of the present application, including but not limited to collecting the operating status of the target storage device on multiple detection items according to a preset period to obtain multiple detection information, wherein the specific selection of the preset period may vary with reference to the device type of the target storage device, or may be set with reference to the importance of the data stored on the target storage device. For example, for a target storage device whose operating status is prone to change, a shorter preset period may be selected to timely discover changes in the operating status of the target storage device. Or, for example, for a target storage device that stores important data, a shorter preset period may be selected.

[0071] Optionally, in an embodiment of the present application, the target device state includes but is not limited to indicating the operating state of the current target storage device on each detection item. The target device state includes but is not limited to a sequence or vector that can be represented as a combination of probabilities of the target storage device failing due to the operating states corresponding to multiple detection information. For example, when the detection items are detection item A and detection item B, the detection information corresponding to detection item A is a, and the detection information corresponding to detection item B is b. According to the statistical analysis of the failure of the target storage device in the early stage, it is determined that the failure probability of the target storage device when the detection information corresponding to detection item A is a is P. a, and based on the previous statistical analysis of the target storage device's failure conditions, it is determined that when the detection information corresponding to detection item B is b, the failure probability of the target storage device is P b , then the device status of the target storage device can be expressed as [P a ,P b ].

[0072] Optionally, in the embodiment of the present application, the target device state includes but is not limited to a sequence or vector that can be represented by a combination of indicators of the possibility that the operating state corresponding to multiple detection information will cause the target storage device to fail. For example, when the detection items are detection item A and detection item B, the detection information corresponding to detection item A is a, and the detection information corresponding to detection item B is b. According to the statistical analysis of the failure of the target storage device in the early stage, it is determined that when the detection information a corresponding to detection item A is greater than A, the detection information a corresponding to detection item B is greater than B. 1 When there is a possibility that the target storage device fails (which can also be called a high possibility of causing the target storage device to fail), the probability index corresponding to the detection item A is marked as 1, and the detection information a corresponding to the detection item A is less than or equal to A 1 When there is no possibility of causing the target storage device to fail (it can also be called the possibility of causing the target storage device to fail is low), the possibility index corresponding to the detection item A is marked as 0; similarly, according to the previous statistical analysis of the failure of the target storage device, it is determined that the detection information b corresponding to the detection item B is greater than B 1 When there is a possibility that the target storage device fails (which can also be called a high possibility of causing the target storage device to fail), the probability index corresponding to the detection item B is marked as 1, and the detection information b corresponding to the detection item B is less than or equal to B 1 When there is no possibility of causing the target storage device to fail (also known as the possibility of causing the target storage device to fail is low), the possibility index corresponding to the marked detection item B is 0. Under such a setting, the target device state includes but is not limited to being represented as [0,0] or [0,1] or [1,0] or [0,0].

[0073] In the embodiment provided in step S204, the target association relationship is the relationship between the possibility that the target storage device fails due to the operation status of the target storage device on each detection item in the historical time period before the current moment and the probability that the target storage device will fail. Referring to the representation form of the target device status mentioned in the above example, when the target device status is represented as [P a ,P b ], or the probability that the target storage device will fail when [0,0] or [0,1] or [1,0] or [0,0].

[0074] Optionally, in an embodiment of the present application, the target association relationship may be, but is not limited to, corresponding to a target storage device. The correspondence here does not mean that the target association relationship corresponds only to a specific storage device in the storage system, but rather to a class of storage devices in the storage system. This class of storage devices has the same target association relationship. For example, multiple storage devices with the same manufacturer, the same capacity, and the same storage medium type can share a target association relationship. Correspondingly, this target association relationship can also be formed based on the operating data of these multiple storage devices.

[0075] Optionally, in an embodiment of the present application, obtaining the current target fault state of the target storage device based on the target association relationship and the target device state includes but is not limited to searching for the target device state in the target association relationship, and when the target device state is found, obtaining the fault state corresponding to the target device state in the target association relationship as the target fault state.

[0076] In the embodiment provided in step S206, the target probability threshold includes but is not limited to being determined based on the statistical analysis of the failure conditions of the target storage device in the early stage, or it may also be preset based on the experience of the engineer. The target probability threshold may be fixed in multiple failure handling processes, or it may be continuously adjusted based on the accuracy of the failure prediction, for example, when the number of unpredicted failures of the target storage device within the target time period exceeds the allowable value, the value of the target probability threshold is reduced.

[0077] Optionally, in the embodiment of the present application, performing data protection operations on the data stored in the target storage device includes but is not limited to copying the data stored in the target storage device to another storage device in the storage system. In a distributed storage system, the data stored in the target storage device can also be migrated to other storage devices, which can also ensure that the data originally stored in the target storage device in the distributed storage system will not be lost.

[0078] Optionally, the control method of the storage system provided in the present application may be applied to a distributed storage system, but is not limited to, to address the problem of high data repair overhead in the distributed storage system. The various storage devices in the distributed storage system may be divided into multiple target storage devices according to the manufacturer, capacity, and type of the storage devices, and the multiple target storage devices correspond to multiple target association relationships.

[0079] As an optional implementation, the current target fault state of the target storage device is obtained according to the target association relationship and the target device state, including: extracting a first fault state corresponding to the target device state from the target association relationship; adjusting the first fault state to a second fault state of the target storage device to obtain the target fault state, wherein the second fault state is a fault state detected on the target storage device before the current moment.

[0080] Optionally, in an embodiment of the present application, the second fault state is a fault state detected on the target storage device before the current moment based on the device state of the target storage device at a historical moment before the current moment, wherein the device state of the target storage device at the historical moment may be consistent with the target device state or may be inconsistent with the target device state.

[0081] Optionally, in an embodiment of the present application, the second fault state may be one or more, and the number of second fault states may be determined with reference to the detection capability of the detection items of the target storage device. For example, when the detection capability is weak, that is, abnormal data is prone to occur, multiple second fault states may be selected; when the detection capability is strong, that is, abnormal data is not prone to occur, only the fault state corresponding to the previous detection before the current detection is selected as the second fault state.

[0082] Optionally, in an embodiment of the present application, because in actual applications there may be abnormal mutations in the detection information of the detection items and there may be one or several detection information detection errors, if no intervention is taken when such abnormalities occur, it will seriously affect the difference between the target failure probability detected by the method provided by the present application and the actual situation, thereby making it impossible to timely and accurately judge the failure risk of the target storage device.

[0083] Through the above steps, the target fault state of the target storage device is determined by combining the currently detected first fault state and the second fault state detected before the current moment, thereby reducing the adverse effects of abnormal jumps in detection information or abnormal detection of detection information on fault monitoring and ensuring the accuracy of the prediction of the fault state.

[0084] Optionally, in an embodiment of the present application, adjusting a first fault state to a second fault state of a target storage device includes: detecting a target transition parameter of the second fault state, wherein the target transition parameter is used to indicate the degree of fluctuation of the probability that the target storage device indicated by the second fault state will fail over time; matching a target selection scheme for the target transition parameter from transition parameters and selection information having a corresponding relationship, wherein the selection information is used to indicate the target number of second fault states selected in chronological order from the current moment; selecting a target number of second fault states in chronological order from the current moment to obtain one or more reference fault states; calculating an average of one or more probabilities indicated by one or more reference fault states to obtain a reference probability; calculating an adjustment parameter based on difference information between the reference probability and the first probability indicated by the first fault state, wherein the difference information is used to indicate the difference between the first probability and the reference probability, the adjustment parameter is proportional to the difference parameter in the difference information, and the difference parameter is used to indicate the degree of difference between the first probability and the reference probability; adjusting the difference parameter of the first probability in the difference direction to obtain a target probability, wherein the difference information includes the difference direction. Through the above steps, by detecting the target transition parameter of the second fault state, that is, the degree of fluctuation of the fault probability over time, the accuracy of the current fault prediction can be identified, and different numbers of second fault states are selected according to different degrees of accuracy, that is, different probability correction degrees are selected according to different degrees of accuracy, and then the average value (reference probability) of the probability corresponding to the second fault state is calculated, and the difference information between the first probability and the reference probability is calculated. Based on this, the adjustment parameters are modified to reduce false alarms (that is, incorrectly predicting that the device will fail) and missed alarms (that is, failing to predict the impending failure of the device), thereby improving the accuracy of the failure risk prediction of the target storage device.

[0085] As an optional implementation, adjusting the first fault state to the second fault state of the target storage device to obtain the target fault state includes: calculating the target probability by the following formula:

[0086] ,

[0087] Where P is the target probability, P n is the first probability indicated by the first fault state, P n-1 is the second probability indicated by the second failure state detected on the target storage device during the last detection, is the weight coefficient corresponding to the first probability, is the weight coefficient corresponding to the second probability.

[0088] Optionally, in the embodiments of the present application, and Including but not limited to determining whether the target storage device will fail based on the accuracy of predicting whether the target storage device will fail using the first probability. For example, when there are multiple cases where the first probability is greater than or equal to the target probability threshold, the target storage device does have a failure that will cause the target storage device to be unusable, then the target storage device can be increased. And reduce .

[0089] Through the above steps, the probability for predicting that the current target storage device will fail is determined based on the first probability and the second probability in a weighted manner in a comprehensive and focused manner, so that the basis for prediction is more comprehensive and the result of prediction is more accurate.

[0090] As an optional implementation, before obtaining the current target fault state of the target storage device based on the target association relationship and the target device state, the method also includes: detecting fault information of the target storage device at multiple time points within a historical time period, and collecting the device state of the target storage device at multiple time points to obtain multiple groups of state association information, wherein the fault information is used to indicate whether a fault occurs in the target storage device, and the state association information includes fault information and device state with a corresponding relationship; calculating a first failure probability of the target storage device failing under each device state based on the multiple groups of state association information to obtain a target association relationship, wherein the fault state includes the first failure probability.

[0091] Optionally, in the embodiment of the present application, the historical time period includes but is not limited to any time period pre-selected before the current moment. In order to improve the accuracy of the failure risk prediction of the target storage device, the longer the historical time period is, the better.

[0092] Optionally, in the embodiment of the present application, multiple time points for detecting fault information and device status are selected within the historical time period according to a preset collection cycle. In order to improve the accuracy of the fault risk prediction of the target storage device, the more dense the time points are, the better.

[0093] Optionally, in an embodiment of the present application, including but not limited to presetting the synchronization duration, when the device status and fault information of the target storage device are collected at multiple time points, if the fault information collected at a certain time point is used to indicate that the target storage device has failed, then the fault information corresponding to the device status of the target storage device collected at that time point and during the synchronization duration period before that time point are all determined as fault information used to indicate that the target storage device has failed. In the above manner, the scope of the prediction of the failure risk of the storage device is improved, and the risk of the failure of the storage device can be predicted as early as possible within the necessary scope, reducing the occurrence of situations where the storage device actually fails and cannot be used.

[0094] Through the above steps, by detecting and recording fault information and equipment status at multiple time points in the historical time period, a large amount of historical data can be accumulated. Based on these historical data, the potential correlation between equipment status and faults can be learned, thereby improving the accuracy and reliability of detecting the current target fault status.

[0095] As an optional implementation, calculating the first failure probability of the target storage device failing in each device state according to the multiple sets of state association information includes: calculating the first failure probability corresponding to each device state by the following formula:

[0096] F=N 1 / N 2 ,

[0097] Where F is the first failure probability corresponding to the reference equipment state, N 2 is the number of reference device states among multiple device states, N 1 The corresponding fault information in the multiple device states is used to indicate the number of reference device states in which the target storage device has failed.

[0098] As an optional implementation, detecting the current target device state of a target storage device in a storage system according to multiple detection information corresponding to multiple detection items includes: determining an associated parameter corresponding to each detection item according to a reference range corresponding to each detection item and multiple project parameters, wherein the multiple detection information includes multiple project parameters, and the associated parameter is used to indicate the possibility that the operating state of the target storage device on the corresponding detection item will cause a failure of the target storage device; arranging the multiple associated parameters in a target order to obtain a target feature vector, wherein the target device state includes the target feature vector.

[0099] Optionally, in an embodiment of the present application, the reference range corresponding to each detection item includes but is not limited to a range of detection information used to characterize that the target storage device will fail (or a high possibility of failure), or a range of detection information used to characterize that the target storage device will not fail (or a low possibility of failure).

[0100] Optionally, in an embodiment of the present application, each project parameter among the multiple project parameters includes but is not limited to a one-to-one correspondence with each detection item, including but not limited to assigning associated parameters to each detection item by detecting whether each project parameter falls within a reference range corresponding to the project parameter.

[0101] Optionally, in an embodiment of the present application, the associated parameters corresponding to each detection item are determined based on the reference range corresponding to each detection item and multiple project parameters, including but not limited to a method of selecting and determining the associated parameters based on the detection item. For detection items that are more likely to cause failure of the target storage device, the corresponding project parameters are directly determined as the associated parameters, or the ratio between the corresponding project parameters and a preset interval is calculated, and the ratio is rounded off to obtain the associated parameters; for detection items that are not so sensitive to causing failure of the target storage device, the first associated parameters or the second associated parameters are assigned to them based on whether the corresponding project parameters fall within the corresponding reference range.

[0102] Optionally, in an embodiment of the present application, the target order is the order in which the associated parameters are arranged in the feature vector, and the order in which the associated parameters in all device states detected by the target storage device at any time are arranged in the feature vector should be fixed, that is, they are all arranged in the target order. This setting can prevent the detection information of multiple detection items from being confused when using multiple detection items to comprehensively predict the risk of failure, thereby avoiding the occurrence of erroneous predictions.

[0103] Through the above content, the operating status and fault risk of the equipment are comprehensively evaluated from multiple dimensions through the associated parameters corresponding to multiple detection items, avoiding the misjudgment or omission that may be caused by single indicator evaluation. This makes the fault prediction more comprehensive and comprehensive, and improves the accuracy and reliability of the prediction.

[0104] As an optional implementation, the associated parameters corresponding to each detection item are determined based on the reference range corresponding to each detection item and multiple project parameters, including: detecting whether each project parameter falls within the corresponding reference range; when it is detected that the project parameter falls within the corresponding reference range, determining the associated parameter to be a first associated parameter, wherein the first associated parameter is used to indicate that the operating state of the target storage device on the corresponding detection item has a low probability of causing a malfunction of the target storage device; when it is detected that the project parameter does not fall within the corresponding reference range, determining the associated parameter to be a second associated parameter, wherein the second associated parameter is used to indicate that the operating state of the target storage device on the corresponding detection item has a high probability of causing a malfunction of the target storage device.

[0105] Optionally, in the embodiment of the present application, it includes but is not limited to setting 0 as the first associated parameter and setting 1 as the second associated parameter.

[0106] Through the above steps, the detection information of each detection item is converted into correlation parameters, which is essentially to quantify the operating status of the device and directly associate it with the probability of failure. This method can not only clearly show the impact of each detection item on device failure, but also establish a more accurate fault prediction mechanism based on the quantified correlation parameters, thereby improving the accuracy of fault prediction for the target storage device.

[0107] As an optional implementation, before determining the associated parameters corresponding to each detection item according to the reference range corresponding to each detection item and multiple project parameters, the method also includes: detecting the target parameters of the target storage device corresponding to the target detection item and the fault information of the target storage device according to the target frequency within a reference time period before the current moment, and obtaining multiple sets of reference associated information, wherein the target parameter is used to indicate the operating status of the target storage device on the target detection item, and the fault information is used to indicate whether the target storage device fails, the reference associated information includes fault information and target parameters with a corresponding relationship, and the multiple detection items include the target detection item; calculating the second failure probability of the target storage device failing when the target parameter is less than each parameter threshold according to the multiple sets of reference associated information, and obtaining multiple sets of intermediate associated information, wherein the intermediate associated information includes parameter thresholds with a corresponding relationship and the second failure probability; determining the target sub-range of the target detection item according to the multiple sets of intermediate associated information and the detection probability threshold of the target detection item, wherein the reference range includes the target sub-range, and the second failure probability corresponding to the operating status indicated by the target parameter within the target sub-range is less than or equal to the detection probability threshold.

[0108] Optionally, in the embodiment of the present application, the reference time period includes but is not limited to any time period before the preset current moment, and the selection of the reference time period is not affected by the selection of the historical time period. In order to improve the accuracy of the failure risk prediction of the target storage device, the longer the reference time period, the better.

[0109] Optionally, in the embodiment of the present application, the target frequency is used to indicate the timing of detecting the target parameter and the fault information within the reference time period. In order to improve the accuracy of the fault risk prediction of the target storage device, the larger the target frequency, the better.

[0110] Optionally, in an embodiment of the present application, including but not limited to presetting the second synchronization duration, when the target parameters of the target storage device corresponding to the target detection items and the fault information of the target storage device are detected at the target frequency, if the fault information collected at a certain time point is used to indicate that the target storage device has failed, then the fault information corresponding to the target parameters of the target storage device detected at that time point and in the time period of the second synchronization duration before that time point are all determined as the fault information used to indicate that the target storage device has failed. In the above manner, the scope of the prediction of the failure risk of the storage device can be improved, and the risk of the failure of the storage device can be predicted as early as possible within the necessary scope.

[0111] Optionally, in the embodiment of the present application, after obtaining multiple sets of reference association information, the third failure probability of the target storage device failing under each operating state indicated by each target parameter can also be calculated based on the multiple sets of reference association information to obtain multiple sets of indirect association information, wherein the indirect association information includes target parameters and third failure probabilities with corresponding relationships; the target sub-range is determined based on the multiple sets of indirect association information and the detection probability threshold, wherein the third failure probability corresponding to the operating state indicated by the target parameter within the target sub-range is less than or equal to the detection probability threshold. That is, by calculating the target parameters as 0, E 1 、E 2 、E 3 , ..., E N The third failure probability of the target storage device failing when E 1 <E 2 <E 3 < ... <E N In order to simplify the preliminary preparation process of risk prediction, it is also possible to calculate the target parameter falling into [0, E 1 ]、[E 1 , E 2 ]、[E 2 , E 3 ], ..., [E N-1 , E N ] The third failure probability of the target storage device failing when these parameter intervals are obtained indirectly associated, where E 1 <E 2 <E 3 < ... <E N-1 <E N .

[0112] Optionally, in the embodiment of the present application, the second failure probability of the target storage device failing when the target parameter is less than each parameter threshold is calculated based on multiple sets of reference association information, which may be but is not limited to respectively calculating the target parameter falling within [0, E 1], [0, E 2 ], [0, E 3 ], ..., [0, E N ] The second failure probability of the target storage device failing when these parameter intervals are, where E 1 <E 2 <E 3 < ... <E N .

[0113] Optionally, in the embodiment of the present application, the detection probability threshold of each detection item includes but is not limited to being different due to the different sensitivity of each detection item to causing the target storage device failure.

[0114] Through the above content, by calculating the second failure probability when the target parameter is less than each parameter threshold, a more detailed failure risk prediction can be constructed for each detection item. This not only quantifies the possibility of failure under different operating conditions, but also identifies the low-risk state of the equipment when it is running under a specific parameter threshold, providing a more accurate basis for subsequent status monitoring and fault warning.

[0115] As an optional implementation, a target sub-range of a target detection item is determined based on multiple groups of intermediate correlation information and a detection probability threshold of the target detection item, including: determining a cumulative distribution function of the target detection item based on multiple groups of intermediate correlation information; determining a parameter threshold whose corresponding second fault probability is less than or equal to the detection probability threshold from multiple parameter thresholds based on the cumulative distribution function and the detection probability threshold to obtain a target parameter threshold; and determining the target sub-range to be zero to the target parameter threshold.

[0116] Optionally, in the embodiment of the present application, the Cumulative Distribution Function (CDF) is a function used in probability theory to describe the probability that a random variable value is less than or equal to a specific value. In the scenario of predicting the state of a storage device, CDF can be used to quantify the probability of a storage device failing when a certain state indicator (such as the number of media errors, cumulative power-on time, etc.) reaches or exceeds a specific value. For example, CDF(1) can be equal to the proportion of hard disks that eventually fail among all hard disks when the number of media errors is 0 or 1.

[0117] As an optional implementation, the distributed storage system includes a backup storage device and multiple storage devices in use, the multiple storage devices in use include a target storage device, and the multiple storage devices in use and the backup storage device are interconnected; data protection operations are performed on the data stored in the target storage device, including: copying the data stored in the target storage device to the backup storage device; converting access to the target storage device in the distributed storage system to access to the backup storage device, and prohibiting access to the target storage device in the distributed storage system.

[0118] Optionally, in the embodiments of the present application, Figure 3 is a schematic diagram of a distributed storage system according to an embodiment of the present application, such as Figure 3 As shown, the distributed storage system includes a backup storage device and multiple in-use storage devices, wherein the in-use storage device is a storage device in the distributed storage system that is currently used to store data and accepts external data access to the distributed storage system, and correspondingly, the backup storage device is a redundant storage device arranged in the distributed system that does not store data temporarily, and the backup storage device does not accept external data access to the distributed storage system.

[0119] Through the above content, data is copied to the backup storage device, ensuring that even if the target storage device fails, there is still a copy of the data in the system, and data can be quickly read from the backup storage device, avoiding long-term data unavailability. Converting the access path to the backup storage device and prohibiting access to the target storage device helps to achieve load balancing within the system. When the target storage device is about to fail or has failed, its tasks will be reallocated to healthy or low-risk backup storage devices, which avoids the failed device from becoming a performance bottleneck and improves the overall data processing capacity and efficiency of the system.

[0120] As an optional implementation, after performing a data protection operation on the data stored in the target storage device, the method further includes: detecting the failure risk cause of the target storage device according to multiple detection information, wherein the failure risk cause is the cause that causes the target probability to be greater than or equal to the target probability threshold, and the failure risk cause includes a hardware cause and a software cause; in the case where it is detected that the failure risk cause is a software cause, searching for a software recovery operation corresponding to the software cause; performing a software recovery operation on the target storage device; detecting the relationship between the reference probability of the target storage device after the software recovery operation is performed and the target probability threshold, wherein the reference probability is the probability that the target storage device will fail after the software recovery operation is performed; in the case where it is detected that the reference probability is less than the target probability threshold, restoring the data stored in the backup storage device to the target storage device, and restoring the access to the backup storage device in the distributed storage system to the access to the target storage device; clearing the data stored on the backup storage device; in the case where it is detected that the failure risk cause is a hardware cause, or in the case where it is detected that the reference probability is greater than or equal to the target probability threshold, replacing the target storage device with a reference storage device, wherein no data is stored in the reference storage device; determining the reference storage device as a backup storage device.

[0121] Optionally, in the embodiment of the present application, the hardware reason is that the target storage device is about to fail due to a hardware failure, and the software reason is that the target storage device is about to fail due to a software failure. Hardware failures usually involve physical components of the storage device, such as the disk surface, magnetic head, motor, circuit board, etc. Such failures may be caused by physical damage, wear, manufacturing defects or environmental factors, for example: disk scratches or head damage: scratches appear on the magnetic coating of the hard disk, or the magnetic head is damaged due to contact with the disk, and the data cannot be read correctly. Motor failure: The motor of the hard disk cannot start or rotate normally, causing the disk to fail to rotate, affecting data reading and writing. Circuit board damage: component failure or poor connection on the circuit board of the hard disk affects the power supply and signal processing of the hard disk. Foreign matter inside the disk: foreign matter such as dust and water vapor enters the hard disk, affecting its normal operation. For hardware failures, due to the physical damage to the hard disk, it is usually impossible to repair it by software means. The most direct way to deal with it is to replace the faulty hard disk. In some cases, professional data recovery services may be able to try to recover data without replacing the hard disk, but this is usually costly and cannot guarantee a 100% data recovery rate. Software failures are usually related to software-level problems such as the data structure, file system, driver, or operating system of the storage device. For example: File system corruption: Due to unexpected power outages, software errors, or virus attacks, the metadata or super block of the file system is damaged, making the files inaccessible. Driver problem: There is an error in the hard disk driver, which affects the normal communication between the hard disk and the computer system. Logical error: The data blocks or sectors on the hard disk are marked as bad sectors, but no physical damage has actually occurred. The data blocks can be recovered by repairing logical errors. Configuration error: The configuration settings of the hard disk are incorrect, such as RAID configuration errors. The problem can be solved by reconfiguring. For software failures, it is usually possible to recover or repair them through software operations, such as: File system repair tools: Use file system check and repair tools to repair file system errors and make data accessible. Driver update or reinstall: Update or reinstall the hard disk driver to solve compatibility issues or driver errors. Bad sector scanning and marking: Use bad sector scanning tools to detect and mark bad sectors to prevent the system from using these unstable areas when reading and writing. Data recovery software can try to recover data when the file system is damaged but the hardware is not damaged. Configuration and reinitialization: Reconfigure the hard disk or RAID array to ensure the correct settings and operating status of the hard disk.

[0122] As an optional implementation, the present application also provides a solid-state disk risk prediction and control method for a distributed storage system. The method first digitizes the solid-state disk symptoms, and then designs a solid-state disk failure prediction model to detect high-risk solid-state disks. The system backs up data of high-risk solid-state disks in advance, thereby converting data repair into replication, effectively reducing the data repair overhead and system performance fluctuations of erasure code fault-tolerant technology, thereby ensuring stable output of system performance.

[0123] Optionally, the solid-state disk risk prediction and control method provided in this application involves two aspects, namely the early data preparation process and the use process after it is put into use. A good early preparation process can provide accurate prediction basis for the use process, ensuring the accuracy of the failure risk prediction of the solid-state disk.

[0124] Specifically, the preparation process includes the following steps:

[0125] Step SZ1, classify the solid state disks into multiple disk models (ie, multiple target storage devices) according to manufacturer, capacity and type. Assume that there are M solid state disk models.

[0126] Step SZ2, for different disk models, collect the state data of the solid state disk according to different preset cycles, including: SMART data, error count data and workload data. The state data (i.e. the aforementioned target parameters and fault information) at least includes: the number of media errors, the number of data errors (Pending and Uncorrectablesector), the number of reallocated sectors (Reallocated error), the number of Program / Erase errors, the cumulative power-on time of the disk, the total number of NAND Writes, the total number of NAND Read+Writes and the failure status (i.e. the aforementioned fault information), etc.

[0127] Step SZ3, for different disk models, statistically analyze the collected status data to obtain the cumulative distribution function (CDF) of each status indicator (i.e., the aforementioned detection item) and the failure probability. Analysis of the status data collected in step SZ2 can obtain: the cumulative distribution function of the number of medium errors and the disk failure probability, the cumulative distribution function of the number of data errors and the disk failure probability, the cumulative distribution function of the number of reallocated sectors and the disk failure probability, the cumulative distribution function of the number of Program / Erase errors and the disk failure probability, the cumulative distribution function of the disk power-on time and the disk failure probability, the cumulative distribution function of the total number of NAND Writes and the disk failure probability, and the cumulative distribution function of the total number of NAND Read+Writes and the disk failure probability.

[0128] Step SZ4: preset the failure probability threshold P corresponding to the number of medium errors media , calculate the corresponding media error number threshold TH based on the cumulative distribution function of the number of media errors and the probability of disk failure media ; Preset the failure probability threshold P corresponding to the number of data errors data , calculate the corresponding data error number threshold TH based on the cumulative distribution function of the number of data errors and the probability of disk failure data ; Preset the failure probability threshold P corresponding to the number of reallocated sectors RS , according to the cumulative distribution function of the number of reallocated sectors and the probability of disk failure, the corresponding threshold of the number of reallocated sectors TH is calculated RS ; Preset the failure probability threshold P corresponding to the number of Program / Erase errors PE , calculate the corresponding Program / Erase error number threshold TH based on the cumulative distribution function of the Program / Erase error number and the disk failure probability PE ; Preset the failure probability threshold P corresponding to the total number of NAND Write times write , calculate the total NAND Write times threshold TH based on the total NAND Write times and the disk failure probability cumulative distribution function write ; Preset the failure probability threshold P corresponding to the total number of NAND Read+Write times RW Calculate the total NAND Read+Write times threshold TH based on the total NAND Read+Write times and the disk failure probability cumulative distribution function RW ; Preset the failure probability threshold P corresponding to the disk power-on time life , the disk power-on time threshold TH is calculated based on the disk power-on time and the disk failure probability cumulative distribution function life .

[0129] Step SZ5, pre-process the state data of the solid state disk and use feature vectors to represent it: X T =[ x type ,x media , x data , x RS , x PE , x write , x RW , x life ], where x type Indicates which disk type this feature vector belongs to (that is, which target storage device this feature vector corresponds to), and the value range is 1-M; when the disk medium error count is less than TH media When x media0; when the disk medium error count is greater than or equal to TH media When x media 1; when the disk data error count is less than TH data When x data 0; when the disk data error count is greater than or equal to TH data When x data 1; when the number of disk reallocation sectors is less than TH RS When x RS 0; when the number of disk reallocation sectors is greater than or equal to TH RS When x RS 1; when the number of Program / Erase errors is less than TH PE When x PE 0; when the number of Program / Erase errors is greater than or equal to TH RS When x PE 1; when the total number of NAND Write times is less than TH write When x PE 0; when the total number of NAND Write times is greater than or equal to TH write When x PE 1; when the total number of NAND Read+Write times is less than TH RW When x RW 0; when the total number of NAND Write times is greater than or equal to TH RW When x RW is 1; calculate x life =round(disk power-on time / T life ), where T life is the preset time, x life The maximum value is N = round(TH life / T life For example, the feature vector [5,0,0,1,1,1,0,25] represents the disk status data of a disk belonging to disk model 5, and the disk medium error count of this disk is less than TH media , the disk data error count is less than TH media , the number of disk reallocation sectors is greater than TH RS , the number of Program / Erase errors is greater than TH PE , the total number of NAND Write times is greater than TH write , the total number of NAND Read+Write is greater than TH RW , the disk power-on time is about 25* T life .

[0130] Step SZ6, perform histogram statistics on the disk status feature vector to obtain a failure probability multidimensional array, each member of which represents the disk status at a preset time T life The data format of the multidimensional array is F[M][2][2][2][2][2][2][2][N], where the first dimension represents the solid state disk model; the second dimension represents the disk medium error status; the third dimension represents the disk data error count status; the fourth dimension represents the reallocation sector count status; the fifth dimension represents the Program / Erase error count status; the sixth dimension represents the NAND Write total count status; the seventh dimension represents the NAND Read+Write total count status; and the eighth dimension represents the disk power-on time status.

[0131] Among them, F[M][2][2][2][2][2][2][2][N]=N 1 / N 2 , N 1 is the disk status data feature vector and is the feature vector X T0 And at the preset time T life The number of internal failures, N 2 is the disk status data feature vector and is the feature vector X T0 The number of

[0132] Figure 4 is a flow chart of a use process according to an embodiment of the present application, such as Figure 4 As shown, based on the preparation process, the use process includes the following steps:

[0133] Step SS1, collects the status data of the solid-state disk, including: SMART data, error count data and workload data, more specifically including: disk manufacturer, model, number of media errors, number of data errors (Pending and Uncorrectable sector), number of reallocated sectors (Reallocated error), number of Program / Erase errors, disk power-on time, total number of NAND Writes, total number of NAND Read+Writes and failure status, etc.

[0134] Step SS2: When the failure state of the solid-state disk is failure, the erasure code fault tolerance technology is used to restore the data in the failed solid-state disk using the coded data stored in other solid-state disks in the distributed storage system. When the failure state of the solid-state disk is not failure, the currently collected disk state data is converted into a state feature vector representation, X T2 =[ x type ,x media , xdata , x RS , x PE , x write , x RW , x life ] (i.e. the target device status mentioned above), where: x type Indicates which disk type this feature vector belongs to (i.e., which target storage device this feature vector corresponds to), determined based on the collected disk manufacturer and disk model; when the disk medium error count is less than TH media When x media 0; when the disk medium error count is greater than or equal to TH media When x media 1; when the disk data error count is less than TH data When x data 0; when the disk data error count is greater than or equal to TH data When x data 1; when the number of disk reallocation sectors is less than TH RS When x RS 0; when the number of disk reallocation sectors is greater than or equal to TH RS When x RS 1; when the number of Program / Erase errors is less than TH PE When x PE 0; when the number of Program / Erase errors is greater than or equal to TH RS When x PE 1; when the total number of NAND Write times is less than TH write When x PE 0; when the total number of NAND Writes is greater than or equal to TH write When x PE 1; when the total number of NAND Read+Write times is less than TH RW When x RW 0; when the total number of NAND Write times is greater than or equal to TH RW When x RW is 1; calculate x life =round(disk power-on time / T life ), where T life The preset time.

[0135] Step SS3, based on the solid state hard disk state feature vector X Tn =[ x type ,x media , x data , x RS , x PE , xwrite ,x RW , x life ], and then find out the failure probability P of the current disk data in its current state according to the failure probability multidimensional array F[M][2][2][2][2][2][2][N] n , the current hard disk status feature vector X Tn And the corresponding failure probability P n save.

[0136] Step SS4, calculate the failure probability P of the current disk (i.e. the aforementioned target probability) according to the following formula:

[0137] ,

[0138] Among them, P n-1 It is the number corresponding to X found last time based on the failure probability multidimensional array F[M][2][2][2][2][2][2][N] T（n-1） The failure probability, and is the weight coefficient.

[0139] Step SS5: compare the current failure probability P of the disk with the preset failure probability threshold P thres (i.e., the aforementioned target probability threshold) is compared. If P is greater than P thres , the disk is considered to be in a high-risk state; if P is less than P thres , the disk is considered not to be in a high-risk state.

[0140] Step SS6, when the management system of the distributed storage system finds a disk in a high-risk state, the management system selects a new disk node; then uses a replication method to back up the data of the high-risk disk to the new node; the management system enables the new node and takes the old node offline.

[0141] 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 software plus a 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, disk, CD), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0142] In this embodiment, a control device for a storage system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0143] Figure 5 is a structural block diagram of a control device of a storage system according to an embodiment of the present application, such as Figure 5 As shown, the device comprises:

[0144] A first detection module 502 is used to detect the current target device state of the target storage device in the storage system according to multiple detection information corresponding to multiple detection items, wherein the detection information is used to indicate the operating state of the target storage device on the corresponding detection item, and the target device state is used to indicate the possibility that the operating state of the current target storage device on each detection item causes a failure of the target storage device;

[0145] The second detection module 504 is used to obtain the current target fault state of the target storage device according to the target association relationship and the target device state, wherein the target association relationship is the relationship between the device state of the target storage device and the fault state of the target storage device in the historical time period before the current moment, and the fault state is used to indicate the probability that the target storage device will fail;

[0146] The execution module 506 is used to perform a data protection operation on the data stored in the target storage device when the target probability indicated by the target failure state is greater than or equal to the target probability threshold.

[0147] Through the above steps, the possibility of the target storage device failing due to the current running state of the target storage device on each detection item is detected according to the running state of the target storage device in the storage system on each detection item, and then the probability of the target storage device failing is detected according to such possibility and the relationship between the possibility detected in the historical event segment before the current moment and the probability of the storage device failing. The probability of the current target storage device failing is detected by combining the influence of the performance of multiple detection items in the historical time period on whether the target storage device fails, which is more accurate. Then, when the detected target probability of failure is greater than or equal to the target probability threshold, a data protection operation is performed on the data stored in the target storage device, that is, based on the accurate prediction of the failure, a data protection operation is performed in advance on the data stored in the target storage device that is about to fail, thereby realizing active protection of the storage system, avoiding the need to use complex cross-storage device data repair operations when the failure has already occurred, reducing the occupation of the storage system's operating resources, and leaving more resources for data access to the storage system. Therefore, the problem of low data access efficiency of the storage system can be solved, and the effect of improving the data access efficiency of the storage system can be achieved.

[0148] As an optional implementation, the second detection module includes: an extraction unit, used to extract a first fault state corresponding to the target device state from the target association relationship; an adjustment unit, used to adjust the first fault state to a second fault state of the target storage device to obtain a target fault state, wherein the second fault state is a fault state detected on the target storage device before the current moment.

[0149] Optionally, the adjustment unit is further used to calculate the target probability by the following formula:

[0150] ,

[0151] Where P is the target probability, P n is the first probability indicated by the first fault state, P n-1 is the second probability indicated by the second failure state detected on the target storage device during the last detection, is the weight coefficient corresponding to the first probability, is the weight coefficient corresponding to the second probability.

[0152] As an optional implementation, the control device of the storage system also includes: a third detection module, which is used to detect fault information of the target storage device at multiple time points within a historical time period, and collect the device status of the target storage device at multiple time points to obtain multiple groups of status association information, wherein the fault information is used to indicate whether the target storage device has a fault, and the status association information includes fault information and device status with a corresponding relationship; a calculation module, which is used to calculate the first failure probability of the target storage device failing under each device state based on the multiple groups of status association information to obtain a target association relationship, wherein the fault status includes the first failure probability.

[0153] Optionally, the calculation module includes: a first calculation unit, configured to calculate a first failure probability corresponding to each device state by using the following formula:

[0154] F=N 1 / N 2 ,

[0155] Where F is the first failure probability corresponding to the reference equipment state, N 2 is the number of reference device states among multiple device states, N 1 The corresponding fault information in the multiple device states is used to indicate the number of reference device states in which the target storage device has failed.

[0156] As an optional implementation, the first detection module includes: a first determination unit, used to determine the associated parameters corresponding to each detection item based on a reference range corresponding to each detection item and multiple project parameters, wherein the multiple detection information includes multiple project parameters, and the associated parameters are used to indicate the possibility that the operating status of the target storage device on the corresponding detection item will cause the target storage device to fail; an arrangement unit, used to arrange the multiple associated parameters in a target order to obtain a target feature vector, wherein the target device status includes the target feature vector.

[0157] Optionally, the first determination unit is further used to: detect whether each project parameter falls within a corresponding reference range; when it is detected that the project parameter falls within the corresponding reference range, determine the associated parameter to be a first associated parameter, wherein the first associated parameter is used to indicate that the operating state of the target storage device on the corresponding detection item has a low probability of causing a failure of the target storage device; when it is detected that the project parameter does not fall within the corresponding reference range, determine the associated parameter to be a second associated parameter, wherein the second associated parameter is used to indicate that the operating state of the target storage device on the corresponding detection item has a high probability of causing a failure of the target storage device.

[0158] Optionally, the first detection module also includes: a detection unit, which is used to detect target parameters of the target storage device corresponding to the target detection item and fault information of the target storage device according to the target frequency within a reference time period before the current moment, and obtain multiple sets of reference association information, wherein the target parameter is used to indicate the operating status of the target storage device on the target detection item, and the fault information is used to indicate whether the target storage device fails, the reference association information includes fault information and target parameters with a corresponding relationship, and the multiple detection items include the target detection item; a second calculation unit, which is used to calculate the second failure probability of the target storage device failing when the target parameter is less than each parameter threshold according to the multiple sets of reference association information, and obtain multiple sets of intermediate association information, wherein the intermediate association information includes parameter thresholds with a corresponding relationship and the second failure probability; a second determination unit, which is used to determine the target sub-range of the target detection item according to the multiple sets of intermediate association information and the detection probability threshold of the target detection item, wherein the reference range includes the target sub-range, and the second failure probability corresponding to the operating status indicated by the target parameter within the target sub-range is less than or equal to the detection probability threshold.

[0159] Optionally, the second determination unit is also used to: determine the cumulative distribution function of the target detection item based on multiple groups of intermediate correlation information; determine the parameter threshold whose corresponding second fault probability is less than or equal to the detection probability threshold from multiple parameter thresholds based on the cumulative distribution function and the detection probability threshold, to obtain the target parameter threshold; determine the target sub-range to be zero to the target parameter threshold.

[0160] As an optional implementation, the distributed storage system includes a backup storage device and multiple storage devices in use, the multiple storage devices in use include a target storage device, and the multiple storage devices in use and the backup storage device are interconnected; the execution module includes: a copying unit, used to copy the data stored in the target storage device to the backup storage device; a conversion unit, used to convert access to the target storage device in the distributed storage system to access to the backup storage device, and prohibit access to the target storage device in the distributed storage system.

[0161] Optionally, the control device of the storage system also includes: a fourth detection module, which is used to detect the failure risk cause of the target storage device according to multiple detection information, wherein the failure risk cause is the cause that causes the target probability to be greater than or equal to the target probability threshold, and the failure risk cause includes hardware reasons and software reasons; a search module, which is used to search for the software recovery operation corresponding to the software reason when it is detected that the failure risk cause is a software reason; perform the software recovery operation on the target storage device; detect the relationship between the reference probability of the target storage device after the software recovery operation is performed and the target probability threshold, wherein the reference probability is the probability that the target storage device will fail after the software recovery operation is performed; when it is detected that the reference probability is less than the target probability threshold, restore the data stored in the backup storage device to the target storage device, and restore the access to the backup storage device in the distributed storage system to the access to the target storage device; clear the data stored on the backup storage device; a replacement module, which is used to replace the target storage device with a reference storage device when it is detected that the failure risk cause is a hardware reason, or when it is detected that the reference probability is greater than or equal to the target probability threshold, wherein no data is stored in the reference storage device; determine the reference storage device as a backup storage device.

[0162] It should be noted that the above modules can be implemented by 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.

[0163] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0164] 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.

[0165] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0166] 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.

[0167] 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 of the above method embodiments are implemented.

[0168] An embodiment of the present application further provides another computer program product, including 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 in any of the above method embodiments are implemented.

[0169] 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 in any one of the above method embodiments.

[0170] 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 herein.

[0171] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that 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 executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0172] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A storage system control method, characterized in that: include: Detecting a current target device state of a target storage device in a storage system according to a plurality of detection information corresponding to a plurality of detection items, wherein the detection information is used to indicate an operating state of the target storage device on the corresponding detection item, and the target device state is used to indicate a possibility that a current operating state of the target storage device on each of the detection items causes a failure of the target storage device; Acquire the current target fault state of the target storage device according to the target association relationship and the target device state, wherein the target association relationship is the relationship between the device state of the target storage device and the fault state of the target storage device in a historical time period before a current moment, and the fault state is used to indicate the probability that the target storage device will fail; In a case where the target probability indicated by the target failure state is greater than or equal to a target probability threshold, a data protection operation is performed on the data stored in the target storage device.

2. The method according to claim 1, characterized in that The obtaining the current target fault state of the target storage device according to the target association relationship and the target device state includes: Extracting a first fault state corresponding to the target device state from the target association relationship; The first fault state is adjusted toward a second fault state of the target storage device to obtain the target fault state, wherein the second fault state is a fault state detected on the target storage device before the current moment.

3. The method according to claim 2, characterized in that The adjusting the first fault state to the second fault state of the target storage device to obtain the target fault state includes: The target probability is calculated by the following formula: ， Where P is the target probability, P n is the first probability indicated by the first fault state, P n-1 is the second probability indicated by the second failure state detected on the target storage device during the last detection, is the weight coefficient corresponding to the first probability, is the weight coefficient corresponding to the second probability.

4. The method according to claim 1, characterized in that: Before acquiring the current target fault state of the target storage device according to the target association relationship and the target device state, the method further includes: Detecting the fault information of the target storage device at multiple time points within the historical time period, and collecting the device status of the target storage device at the multiple time points to obtain multiple groups of status association information, wherein the fault information is used to indicate whether the target storage device has a fault, and the status association information includes the fault information and the device status having a corresponding relationship; The first failure probability of the target storage device failing under each of the device states is calculated according to the multiple groups of state association information to obtain the target association relationship, wherein the failure state includes the first failure probability.

5. The method according to claim 4, characterized in that The calculating, according to the plurality of groups of state association information, a first failure probability of the target storage device failing under each of the device states comprises: The first failure probability corresponding to each of the device states is calculated by the following formula: F=N1 / N2, Among them, F is the first failure probability corresponding to the reference device state, N2 is the number of the reference device states in the multiple device states, and N1 is the number of the reference device states whose corresponding failure information in the multiple device states is used to indicate that the target storage device has failed.

6. The method according to claim 1, characterized in that The detecting the current target device state of the target storage device in the storage system according to the multiple detection information corresponding to the multiple detection items includes: Determining, according to the reference range corresponding to each of the detection items and a plurality of project parameters, the associated parameters corresponding to each of the detection items, wherein the plurality of detection information includes the plurality of project parameters, and the associated parameters are used to indicate the probability that the operating state of the target storage device on the corresponding detection item will cause the target storage device to fail; Arrange the plurality of associated parameters in a target order to obtain a target feature vector, wherein the target device state includes the target feature vector.

7. The method according to claim 6, characterized in that Determining the associated parameters corresponding to each of the detection items according to the reference ranges corresponding to each of the detection items and the multiple project parameters includes: Detecting whether each of the project parameters falls within the corresponding reference range; In the case where it is detected that the item parameter falls within the corresponding reference range, determining the associated parameter to be a first associated parameter, wherein the first associated parameter is used to indicate that the operating state of the target storage device on the corresponding detection item causes a low probability that the target storage device will fail; When it is detected that the project parameter does not fall within the corresponding reference range, the associated parameter is determined to be a second associated parameter, wherein the second associated parameter is used to indicate that the operating status of the target storage device on the corresponding detection item has a high probability of causing a failure of the target storage device.

8. The method according to claim 6, characterized in that Before determining the associated parameters corresponding to each of the detection items according to the reference ranges corresponding to each of the detection items and a plurality of project parameters, the method further includes: Detecting target parameters of the target storage device corresponding to the target detection item and fault information of the target storage device according to the target frequency within a reference time period before the current moment, and obtaining multiple sets of reference association information, wherein the target parameter is used to indicate the operating state of the target storage device on the target detection item, and the fault information is used to indicate whether the target storage device fails, the reference association information includes the fault information and the target parameter having a corresponding relationship, and the multiple detection items include the target detection item; Calculating, according to the multiple sets of reference association information, a second failure probability that the target storage device fails when the target parameter is less than each parameter threshold, to obtain multiple sets of intermediate association information, wherein the intermediate association information includes the parameter threshold and the second failure probability having a corresponding relationship; The target sub-range of the target detection item is determined according to the multiple groups of intermediate correlation information and the detection probability threshold of the target detection item, wherein the reference range includes the target sub-range, and the second fault probability corresponding to the operating state indicated by the target parameter within the target sub-range is less than or equal to the detection probability threshold.

9. The method according to claim 8, characterized in that The determining the target sub-range of the target detection item according to the multiple groups of intermediate association information and the detection probability threshold of the target detection item includes: Determining a cumulative distribution function of the target detection item according to the multiple groups of intermediate association information; Determine, from the plurality of parameter thresholds, a parameter threshold whose corresponding second fault probability is less than or equal to the detection probability threshold according to the cumulative distribution function and the detection probability threshold, and obtain a target parameter threshold; The target subrange is determined to be zero to the target parameter threshold.

10. The method according to claim 1, characterized in that The distributed storage system includes a backup storage device and a plurality of in-use storage devices, wherein the plurality of in-use storage devices include the target storage device, and the plurality of in-use storage devices and the backup storage device are connected to each other; The performing a data protection operation on the data stored in the target storage device includes: Copying the data stored in the target storage device to the backup storage device; The access to the target storage device in the distributed storage system is converted into the access to the backup storage device, and the access to the target storage device is prohibited in the distributed storage system.

11. The method according to claim 10, characterized in that After performing the data protection operation on the data stored in the target storage device, the method further includes: Detecting the failure risk cause of the target storage device according to the multiple detection information, wherein the failure risk cause is a cause that causes the target probability to be greater than or equal to the target probability threshold, and the failure risk cause includes a hardware cause and a software cause; In the case where it is detected that the cause of the failure risk is the software cause, searching for a software recovery operation corresponding to the software cause; performing the software recovery operation on the target storage device; detecting the relationship between a reference probability of the target storage device after the software recovery operation is performed and the target probability threshold, wherein the reference probability is the probability that the target storage device will fail after the software recovery operation is performed; in the case where it is detected that the reference probability is less than the target probability threshold, restoring the data stored in the backup storage device to the target storage device, and restoring the access to the backup storage device in the distributed storage system to the access to the target storage device; clearing the data stored on the backup storage device; When it is detected that the cause of the failure risk is the hardware reason, or when it is detected that the reference probability is greater than or equal to the target probability threshold, the target storage device is replaced with a reference storage device, wherein no data is stored in the reference storage device; and the reference storage device is determined as the backup storage device.

12. A control device for a storage system, characterized in that: include: A first detection module, configured to detect a current target device state of a target storage device in a storage system according to a plurality of detection information corresponding to a plurality of detection items, wherein the detection information is used to indicate an operating state of the target storage device on the corresponding detection item, and the target device state is used to indicate a possibility that a failure of the target storage device may occur due to the current operating state of the target storage device on each of the detection items; a second detection module, configured to obtain a current target fault state of the target storage device according to a target association relationship and the target device state, wherein the target association relationship is a relationship between a device state of the target storage device and a fault state of the target storage device in a historical time period before a current moment, and the fault state is used to indicate a probability that the target storage device will fail; An execution module is used to perform a data protection operation on the data stored in the target storage device when the target probability indicated by the target failure state is greater than or equal to a target probability threshold.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 11 when executed by a processor.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 11 are implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 11 are implemented.

Images