WO2019210844A1

WO2019210844A1 - Anomaly detection method and apparatus for storage device, and distributed storage system

Info

Publication number: WO2019210844A1
Application number: PCT/CN2019/085128
Authority: WO
Inventors: 叶敏; 林鹏; 林起芊; 汪渭春
Original assignee: 杭州海康威视***技术有限公司
Priority date: 2018-05-02
Filing date: 2019-04-30
Publication date: 2019-11-07
Also published as: CN110442298B; CN110442298A

Abstract

An anomaly detection method and apparatus for a storage device, and a distributed storage system, relating to the technical field of storage. The method comprises: writing n preset files into n storage areas, a first preset file being any of the n preset files, the first preset file being written into a first storage area, and the first preset file comprising first target data and first check data thereof; when a read operation on the first storage area succeeds, generating second check data of second target data read from the first storage area; if the second check data is different from third check data, determining that the first storage area is abnormal; and when it is determined that at least m storage areas in the n storage areas are abnormal, determining that the storage device is abnormal, wherein 1≤m≤n. The invention solves the problem of being unable to know an anomaly of a storage device by a management device, and is used for detecting an anomaly of the storage device.

Description

存储设备异常检测方法及装置、分布式存储***Storage device abnormality detecting method and device, distributed storage system

本申请要求于2018年05月02日提交的申请号为201810411648.6、发明名称为“存储设备异常检测方法及装置、分布式存储***”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。The present application claims priority to Chinese Patent Application No. 201810411648.6, entitled "Storage Device Anomaly Detection Method and Apparatus, Distributed Storage System", filed on May 2, 2018, the entire contents of which are incorporated herein by reference. In the application.

技术领域Technical field

本申请涉及存储技术领域，特别涉及一种存储设备异常检测方法及装置、分布式存储***。The present application relates to the field of storage technologies, and in particular, to a storage device abnormality detecting method and apparatus, and a distributed storage system.

背景技术Background technique

随着存储技术的发展，分布式存储***得到了广泛的应用。分布式存储***可以包括：管理设备，以及该管理设备管理的多个存储设备。客户端能够通过该管理设备和存储设备在分布式存储***中存储数据。With the development of storage technology, distributed storage systems have been widely used. The distributed storage system may include: a management device, and a plurality of storage devices managed by the management device. The client can store data in the distributed storage system through the management device and the storage device.

相关技术中，管理设备可以通过网络接入多个存储设备，并可以将数据分别存储在该多个存储设备中。当用户需要在该分布式存储***中存储数据时，可以通过客户端向管理设备发送待存储的数据，以使得管理设备将该数据写入存储设备。In the related art, the management device can access multiple storage devices through the network, and can store data in the multiple storage devices. When the user needs to store data in the distributed storage system, the data to be stored may be sent by the client to the management device, so that the management device writes the data to the storage device.

由于相关技术中，当某一存储设备异常(如存储设备掉线或损坏)时，管理设备无法得知该存储设备异常，若此时管理设备在该存储设备上写入数据，则会导致该数据发生丢失，因此，亟需一种检测存储设备是否异常的方法。In the related art, when a storage device is abnormal (for example, the storage device is dropped or damaged), the management device cannot know that the storage device is abnormal. If the management device writes data on the storage device at this time, the Data is lost, so there is a need for a way to detect if a storage device is abnormal.

发明内容Summary of the invention

本申请提供了一种存储设备异常检测方法及装置、分布式存储***，可以解决管理设备无法得知存储设备异常的问题。所述技术方案如下：The present invention provides a storage device abnormality detecting method and device, and a distributed storage system, which can solve the problem that the management device cannot know the abnormality of the storage device. The technical solution is as follows:

一方面，提供了一种存储设备异常检测方法，应用于管理设备，所述存储设备中的部分存储区域包括n个存储区域，n≥1，所述方法包括：In one aspect, a storage device anomaly detection method is provided, which is applied to a management device, where a part of the storage area includes n storage areas, n≥1, and the method includes:

向所述n个存储区域中写入n个预置文件，其中，第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，所述第一预置文件包括：第一目标数据及其第一校验数据；Writing n preset files to the n storage areas, where the first preset file is any one of n preset files, and the first preset file is written into the first storage area. The first preset file includes: first target data and first calibration data thereof;

在对所述第一存储区域的读操作成功时，生成从所述第一存储区域读取到的第二目标数据的第二校验数据，所述第二目标数据为对所述第一存储区域中的所述第一目标数据进行读操作得到的数据；And generating, when the read operation on the first storage area is successful, second check data of the second target data read from the first storage area, where the second target data is for the first storage Data obtained by the read operation of the first target data in the area;

在所述第二校验数与第三校验数据不同时，确定所述存储设备异常，其中，所述第三校验数据为对所述第一存储区域中的所述第一校验数据进行读操作得到的数据；Determining, when the second check number is different from the third check data, the storage device abnormality, where the third check data is the first check data in the first storage area The data obtained by the read operation;

在确定所述n个存储区域中的至少m个存储区域异常时，确定所述存储设备异常，1≤m≤n。When it is determined that at least m storage areas of the n storage areas are abnormal, the storage device is determined to be abnormal, 1≤m≤n.

可选的，所述方法还包括：Optionally, the method further includes:

在从所述第一存储区域读取到的校验数据与所述第二校验数据相同，且采用所述第二校验数据覆盖所述第一存储区域中的所述第一校验数据失败时，确定所述第一存储区域异常。The check data read from the first storage area is the same as the second check data, and the second check data is used to cover the first check data in the first storage area When it fails, it is determined that the first storage area is abnormal.

可选的，所述方法还包括：Optionally, the method further includes:

在对所述第一存储区域的读操作失败时，确定所述第一存储区域异常。When the read operation on the first storage area fails, the first storage area is determined to be abnormal.

可选的，所述第一校验数据采用预设处理方式对所述第一目标数据进行处理得到，所述第二校验数据采用所述预设处理方式对第二目标数据进行处理得到。Optionally, the first verification data is processed by using the preset processing manner to obtain the first target data, and the second verification data is processed by using the preset processing manner to process the second target data.

可选的，n≥3，所述存储设备具有连续的多个存储地址，所述n个存储区域包括所述多个存储地址中的头部、中部以及尾部。Optionally, n≥3, the storage device has a plurality of consecutive storage addresses, and the n storage areas include a head, a middle, and a tail of the plurality of storage addresses.

可选的，所述存储设备包括独立冗余磁盘阵列RAID，所述预置文件的大小大于或者等于所述RAID中一个条带的大小。Optionally, the storage device includes an independent redundant disk array RAID, and the size of the preset file is greater than or equal to a size of one strip in the RAID.

可选的，所述存储设备包括除所述n个存储区域之外的其他存储区域，所述方法还包括：Optionally, the storage device includes a storage area other than the n storage areas, and the method further includes:

每隔预设时间段对所述第一存储区域进行所述读操作；Performing the read operation on the first storage area every preset time period;

或者，在所述其他存储区域满足判断触发条件时，对所述第一存储区域进行所述读操作，所述判断触发条件包括：对所述其他存储区域的读操作失败，从所述其他存储区域中读取到的文件错误，以及对所述其他存储区域的写操作失败中的至少一种条件。Or performing the read operation on the first storage area when the other storage area satisfies the judgment trigger condition, where the determining trigger condition includes: a read operation on the other storage area fails, from the other storage At least one of a file error read in the area and a write operation failure to the other storage area.

可选的，m＝n。Optional, m=n.

另一方面，提供了一种存储设备异常检测装置，应用于管理设备，所述存储设备中的部分存储区域包括n个存储区域，n≥1，所述存储设备异常检测装置包括：On the other hand, a storage device abnormality detecting device is provided, which is applied to a management device, and a part of the storage area of the storage device includes n storage areas, n≥1, and the storage device abnormality detecting device includes:

写入模块，向所述n个存储区域中写入n个预置文件，其中，第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，所述第一预置文件包括：第一目标数据及其第一校验数据；Writing to the module, writing n preset files to the n storage areas, wherein the first preset file is any one of n preset files, and the first preset file is written first a storage area, the first preset file includes: first target data and first calibration data thereof;

生成模块，用于在对所述第一存储区域的读操作成功时，生成第二目标数据的第二校验数据，所述第二目标数据为对所述第一存储区域中的所述第一目标数据进行读操作得到的数据；a generating module, configured to generate second verification data of the second target data when the read operation on the first storage area is successful, where the second target data is the first in the first storage area Data obtained by reading a target data;

第一确定模块，用于在所述第二校验数据与第三校验数据不同时，确定所述第一存储区域异常，其中，所述第三校验数据为对所述第一存储区域中的所述第一校验数据进行读操作得到的数据；a first determining module, configured to determine that the first storage area is abnormal when the second check data is different from the third check data, where the third check data is for the first storage area Data obtained by the first verification data in the read operation;

第二确定模块，用于在确定所述n个存储区域中的至少m个存储区域异常时，确定所述存储设备异常，1≤m≤n。And a second determining module, configured to determine that the storage device is abnormal when determining that at least m storage areas of the n storage areas are abnormal, 1≤m≤n.

可选的，所述存储设备异常检测装置还包括：Optionally, the storage device abnormality detecting device further includes:

第三确定模块，用于在从所述第一存储区域读取到的校验数据与所述第二校验数据相同，且采用所述第二校验数据覆盖所述第一存储区域中的所述第一校验数据失败时，确定所述第一存储区域异常。a third determining module, configured to: the check data read from the first storage area is the same as the second check data, and use the second check data to cover the first storage area When the first verification data fails, the first storage area is determined to be abnormal.

第四确定模块，用于在对所述第一存储区域的读操作失败时，确定所述第一存储区域异常。And a fourth determining module, configured to determine that the first storage area is abnormal when a read operation on the first storage area fails.

可选的，所述第一校验数据采用预设处理方式对所述第一目标数据进行处理得到，所述第二校验数据采用所述预设处理方式对所述第二目标数据进行处理得到。Optionally, the first verification data is processed by using the preset processing manner, and the second verification data is processed by using the preset processing manner. get.

可选的，所述存储设备包括除所述n个存储区域之外的其他存储区域，所述存储设备异常检测装置还包括：Optionally, the storage device includes a storage area other than the n storage areas, and the storage device abnormality detecting device further includes:

第一读取模块，用于每隔预设时间段对所述第一存储区域进行所述读操作；a first reading module, configured to perform the reading operation on the first storage area every preset time period;

或者，or,

第二读取模块，用于在所述其他存储区域满足判断触发条件时，对所述第一存储区域进行所述读操作，所述判断触发条件包括：对所述其他存储区域的读操作失败，从所述其他存储区域中读取到的文件错误，以及对所述其他存储区域的写操作失败中的至少一种条件。a second reading module, configured to perform the read operation on the first storage area when the other storage area satisfies a judgment trigger condition, where the determining trigger condition comprises: a read operation on the other storage area fails At least one of a file error read from the other storage area and a write operation failure to the other storage area.

可选的，m＝n。Optional, m=n.

再一方面，提供了一种分布式存储***，所述分布式存储***包括管理设备与多个存储设备，所述管理设备包括上述的存储设备异常检测装置。In still another aspect, a distributed storage system is provided, the distributed storage system including a management device and a plurality of storage devices, and the management device includes the storage device abnormality detecting device described above.

又一方面，提供了一种计算机设备，包括：In yet another aspect, a computer device is provided, comprising:

一个或多个处理器；和One or more processors; and

存储器；Memory

所述存储器存储有一个或多个程序，所述一个或多个程序被配置成由所述一个或多个处理器执行，以执行上述的存储设备异常检测方法。The memory stores one or more programs, the one or more programs being configured to be executed by the one or more processors to perform the storage device anomaly detection method described above.

又一方面，提供了一种计算机可读存储介质，所述存储介质中存储有代码指令，所述代码指令由处理器执行，以执行上述的存储设备异常检测方法。In still another aspect, a computer readable storage medium is provided having stored therein code instructions for execution by a processor to perform the storage device anomaly detection method described above.

又一方面，提供了一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得计算机执行上述的存储设备异常检测方法。In still another aspect, a computer program product is provided that, when executed on a computer, causes the computer to perform the storage device anomaly detection method described above.

又一方面，提供了一种芯片，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片运行时用于实现上述存储设备异常检测方法。In yet another aspect, a chip is provided that includes programmable logic circuitry and/or program instructions for implementing the above described memory device anomaly detection method when the chip is in operation.

本申请提供的技术方案带来的有益效果至少包括：The beneficial effects brought by the technical solutions provided by the present application include at least:

本申请提供了一种存储设备异常检测方法、装置及分布式存储***，在本申请提供的设备异常检测方法中，可以在存储设备中的部分存储区域中的n个存储区域写入n个预置文件，且第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，第一预置文件包括：第一目标数据及其第一校验数据。在对第一存储区域的读操作成功时，生成从第一存储区域读取到的第二目标数据的第二校验数据。第三校验数据为对第一存储区域中的第一校验数据进行读操作得到的数据，且在第三校验数据与第二校验数据不同时，可以确定第一存储区域异常。在确定n个存储区域中的至少m个存储区域异常时，确定存储设备异常，进而实现了对存储设备异常的检测。The present application provides a storage device abnormality detecting method, device, and distributed storage system. In the device abnormality detecting method provided by the present application, n pre-writes can be written in n storage areas in a partial storage area in the storage device. Setting a file, and the first preset file is any one of the n preset files, the first preset file is written into the first storage area, and the first preset file includes: the first target data and the first Verify the data. When the read operation on the first storage area is successful, the second check data of the second target data read from the first storage area is generated. The third verification data is data obtained by performing a read operation on the first verification data in the first storage area, and when the third verification data is different from the second verification data, the first storage area abnormality may be determined. When it is determined that at least m storage areas in the n storage areas are abnormal, the storage device is abnormal, thereby detecting the abnormality of the storage device.

附图说明DRAWINGS

为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings may also be obtained from those of ordinary skill in the art in light of the inventive work.

图1是本申请实施例提供的一种分布式存储***的结构示意图；1 is a schematic structural diagram of a distributed storage system according to an embodiment of the present application;

图2是本申请实施例提供的一种存储设备异常检测方法的流程图；2 is a flowchart of a method for detecting an abnormality of a storage device according to an embodiment of the present application;

图3是本申请实施例提供的一种存储设备的示意图；3 is a schematic diagram of a storage device according to an embodiment of the present application;

图4是本申请实施例提供的另一种存储设备的示意图；4 is a schematic diagram of another storage device provided by an embodiment of the present application;

图5是本申请实施例提供的又一种存储设备的示意图；FIG. 5 is a schematic diagram of still another storage device according to an embodiment of the present disclosure;

图6是本申请实施例提供的再一种存储设备的示意图；FIG. 6 is a schematic diagram of still another storage device according to an embodiment of the present application; FIG.

图7是本申请实施例提供的一种第一存储区域异常检测方法的流程图；FIG. 7 is a flowchart of a method for detecting an abnormality of a first storage area according to an embodiment of the present application;

图8是本申请实施例提供的一种独立冗余磁盘阵列的结构示意图；FIG. 8 is a schematic structural diagram of an independent redundant disk array according to an embodiment of the present disclosure;

图9是本申请实施例提供的一种存储设备异常检测装置的结构示意图；FIG. 9 is a schematic structural diagram of a storage device abnormality detecting apparatus according to an embodiment of the present application;

图10是本申请实施例提供的另一种存储设备异常检测装置的结构示意图；FIG. 10 is a schematic structural diagram of another storage device abnormality detecting apparatus according to an embodiment of the present disclosure;

图11是本申请实施例提供的再一种存储设备异常检测装置的结构示意图；FIG. 11 is a schematic structural diagram of still another storage device abnormality detecting apparatus according to an embodiment of the present application;

图12是本申请实施例提供的又一种存储设备异常检测装置的结构示意图；FIG. 12 is a schematic structural diagram of still another storage device abnormality detecting apparatus according to an embodiment of the present application;

图13是本申请另一实施例提供的一种存储设备异常检测装置的结构示意图；FIG. 13 is a schematic structural diagram of a storage device abnormality detecting apparatus according to another embodiment of the present disclosure;

图14是本申请实施例提供的一种计算机设备的结构示意图。FIG. 14 is a schematic structural diagram of a computer device according to an embodiment of the present application.

具体实施方式detailed description

为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。In order to make the objects, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

随着存储技术的发展，分布式存储***得到了广泛的应用。图1示出了一种分布式存储***的结构示意图，该分布式存储***10可以包括：管理设备101，以及该管理设备101管理的多个存储设备102。客户端103能够通过该管理设备101和存储设备102在分布式存储***10中存储数据。With the development of storage technology, distributed storage systems have been widely used. FIG. 1 shows a schematic structural diagram of a distributed storage system 10. The distributed storage system 10 may include: a management device 101, and a plurality of storage devices 102 managed by the management device 101. The client 103 is capable of storing data in the distributed storage system 10 through the management device 101 and the storage device 102.

示例的，该多个存储设备可以包括：磁盘(英文DISK)、固态硬盘(英文：Solid State Drives；简称：SSD)、独立冗余磁盘阵列(英文：Redundant Array of Independent Disks；简称：RAID)、存储局域网络(英文：Storage Area Network；简称：SAN，也称为IP SAN)、光纤存储区域网络(英文：Fibre Channel Storage Area Network；简称：FC SAN)以及网络附属存储(英文：Network Attached Storage；简称：NAS)等存储设备。客户端103可以部署在终端上，终端可以为手机、笔记本电脑、台式电脑、平板电脑或智能电视机等电子设备。管理设备101可以为一个服务器，或者管理设备101可以为多个服务器组成的服务器集群。For example, the multiple storage devices may include: a disk (English DISK), a solid state disk (English: Solid State Drives; SSD), and an independent redundant disk array (English: Redundant Array of Independent Disks; RAID). Storage area network (English: Storage Area Network; referred to as: SAN, also known as IP SAN), fiber storage area network (English: Fibre Channel Storage Area Network; referred to as: FC SAN) and network attached storage (English: Network Attached Storage; Abbreviation: NAS) and other storage devices. The client 103 can be deployed on the terminal, and the terminal can be an electronic device such as a mobile phone, a notebook computer, a desktop computer, a tablet computer or a smart TV. The management device 101 can be a server, or the management device 101 can be a server cluster composed of a plurality of servers.

需要说明的是，图1中仅示出了分布式存储***10中的三个存储设备102，可选地，分布式存储***中可以包括四个、五个或者更多的存储设备，本申请实施例对此不作限定。客户端与管理设备之间可以通过有线网络或者无线网络连接，其中，有线网络可以包括但不限于：通用串行总线(英文：Universal Serial Bus；简称：USB)，无线网络可以包括但不限于：无线保真(英文：Wireless Fidelity；简称：WIFI)、蓝牙、红外、紫蜂(英文：Zigbee)、数据网络等。It should be noted that only three storage devices 102 in the distributed storage system 10 are shown in FIG. 1 . Optionally, four, five or more storage devices may be included in the distributed storage system. The embodiment does not limit this. The connection between the client and the management device may be through a wired network or a wireless network. The wired network may include, but is not limited to, a universal serial bus (English: Universal Serial Bus; USB). The wireless network may include but is not limited to: Wireless Fidelity (English: Wireless Fidelity; abbreviation: WIFI), Bluetooth, infrared, Zigbee (English: Zigbee), data network, etc.

用户需要在该分布式存储***10中存储数据时，可以通过客户端103向管理设备101发送待存储的数据，以使得管理设备101将该数据写入存储设备102。若某一存储设备异常(如存储设备掉线或损坏)，则管理设备无法正确读取该存储设备上的数据，或者无法将数据写入该存储设备导致数据丢失。因此，确定存储设备是否异常对于分布式存储***来说至关重要。When the user needs to store data in the distributed storage system 10, the data to be stored may be sent to the management device 101 through the client 103, so that the management device 101 writes the data to the storage device 102. If a storage device is abnormal (such as the storage device is dropped or damaged), the management device cannot read the data on the storage device correctly, or the data cannot be written to the storage device, resulting in data loss. Therefore, determining whether a storage device is abnormal is critical to a distributed storage system.

图2是本申请实施例提供的一种存储设备异常检测方法的方法流程图。该方法可以用于图1中的管理设备101，如图2所示，该方法包括：FIG. 2 is a flowchart of a method for detecting an abnormality of a storage device according to an embodiment of the present application. The method can be used in the management device 101 in FIG. 1, as shown in FIG. 2, the method includes:

步骤201、向存储设备中的部分存储区域中的n个存储区域写入n个预置文件，n≥1。执行步骤202。Step 201: Write n preset files to n storage areas in a partial storage area in the storage device, n≥1. Go to step 202.

需要说明的是，本申请实施例中涉及到的存储设备可以为图1所示的分布式存储***中的任意一个存储设备。存储设备可以具有连续的多个存储地址，该多个存储地址可以划分为多个存储区域，每个存储区域包括至少一个存储地址。该部分存储区域可以包括该多个存储区域中的n个存储区域，n≥1，在步骤201中，管理设备可以向n个存储区域中写入n个预置文件，也即是，管理设备可以向该n个存储区域中的每个存储区域中均写入一个预置文件。It should be noted that the storage device involved in the embodiment of the present application may be any one of the distributed storage systems shown in FIG. 1 . The storage device may have a plurality of consecutive storage addresses, which may be divided into a plurality of storage areas, each storage area including at least one storage address. The part of the storage area may include n storage areas of the plurality of storage areas, n≥1. In step 201, the management device may write n preset files to the n storage areas, that is, the management device. A preset file can be written to each of the n storage areas.

需要说明的是，假设第一预置文件为该n个预置文件中的任一预置文件，则第一预置文件写入n个存储区域中的第一存储区域，该第一预置文件可以包括：第一目标数据及其第一校验数据，且第一校验数据为采用预设处理方式对第一目标数据进行处理得到的数据。It should be noted that, if the first preset file is any one of the n preset files, the first preset file is written into the first storage area in the n storage areas, the first preset The file may include: first target data and first calibration data thereof, and the first verification data is data obtained by processing the first target data by using a preset processing manner.

示例的，预设处理方式可以为信息摘要算法第五版(英文：Message-Digest Algorithm 5；简称：MD5)，在步骤201中，管理设备可以使用MD5对第一目标数据进行处理，得到该第一目标数据的MD5码，也即是第一校验数据，并将该第一校验数据与该目标数据均写入第一存储区域。例如，第一存储区域包括第一区域与第二区域，第一目标数据可以写入第一存储区域中的第一区域，第一校验数据可以写入第一存储区域中的第二区域。For example, the preset processing mode may be the fifth version of the message digest algorithm (English: Message-Digest Algorithm 5; MD5 for short). In step 201, the management device may process the first target data by using MD5 to obtain the first An MD5 code of a target data, that is, a first parity data, and the first parity data and the target data are both written into the first storage area. For example, the first storage area includes a first area and a second area, the first target data may be written into the first area in the first storage area, and the first verification data may be written into the second area in the first storage area.

可选的，在n≥3时，管理设备可以将该n个预置文件分别存储在该多个存储地址的头部、中部以及尾部。需要说明的是，多个存储地址中的头部和尾部分别为多个存储地址中位于两端的两部分存储地址，多个存储地址中的中部为位于多个存储地址中的头部和尾部之间的一部分存储地址，且多个存储地址中的头部、中部和尾部中，任意相邻的两部分存储地址间隔有至少一个存储地址。Optionally, when n≥3, the management device may store the n preset files in the head, the middle, and the tail of the multiple storage addresses, respectively. It should be noted that the head and the tail of the plurality of storage addresses are respectively two-part storage addresses located at two ends of the plurality of storage addresses, and the middle of the plurality of storage addresses is the head and the tail located in the plurality of storage addresses. A portion of the storage address, and among the header, the middle, and the tail of the plurality of storage addresses, any two adjacent storage address intervals have at least one storage address.

示例的，如图3所示，存储设备30具有连续的多个存储地址a，管理设备可以在该多个存储地址划分成的多个存储区域(图3中未标出)中的部分存储区域写入三个预置文件(如预置文件F1、预置文件F2和预置文件F3)，以使得预置文件F1存储在多个存储地址的头部，预置文件F2存储在该多个存储地址的中部，预置文件F3存储在该多个存储地址的尾部，此时，该多个预置文件可以在该多个存储地址中均匀的分布。图3中以头部、中部和尾部均仅包括一个存储地址，且头部、中部和尾部中每个部分均仅存储有一个预置文件，且该三个预置文件在存储设备的多个存储地址中均匀分布为例。For example, as shown in FIG. 3, the storage device 30 has a plurality of consecutive storage addresses a, and a part of the storage areas in which the management device can be divided into a plurality of storage areas (not shown in FIG. 3) Write three preset files (such as preset file F1, preset file F2 and preset file F3) such that the preset file F1 is stored in the header of a plurality of storage addresses, and the preset file F2 is stored in the plurality of In the middle of the storage address, the preset file F3 is stored at the end of the plurality of storage addresses. At this time, the plurality of preset files may be evenly distributed among the plurality of storage addresses. In FIG. 3, only one storage address is included in the head, the middle, and the tail, and only one preset file is stored in each of the head, the middle, and the tail, and the three preset files are in the storage device. The uniform distribution in the storage address is an example.

可选地，这三个预置文件可以为大小不同的文件，且头部、中部和尾部可以包括不止一个存储地址，例如，如图4所示，预置文件F1存储在多个存储地址中位于头部的两个存储地址，预置文件F3存储在多个存储地址中位于尾部的两个存储地址，预置文件F2存储在多个存储地址中位于中部的一个存储地址。Optionally, the three preset files may be files of different sizes, and the head, the middle, and the tail may include more than one storage address. For example, as shown in FIG. 4, the preset file F1 is stored in multiple storage addresses. Two storage addresses located at the head, the preset file F3 stores two storage addresses at the tail among the plurality of storage addresses, and the preset file F2 stores one storage address located at the middle among the plurality of storage addresses.

或者，该多个预置文件也可以不在该多个存储地址中均匀分布，例如，如图5所示，预置文件F1与预置文件F2之间的存储地址的数量可以多于预置文件F2与预置文件F3之间的存储地址的数量。Alternatively, the plurality of preset files may not be evenly distributed among the plurality of storage addresses. For example, as shown in FIG. 5, the number of storage addresses between the preset file F1 and the preset file F2 may be more than the preset file. The number of storage addresses between F2 and the preset file F3.

再或者，管理设备也仅可向存储设备中写入一个预置文件，该一个预置文件可以被写入存储设备中任一存储地址，或者任意连续的多个存储地址。例如，该一个预置文件F1可以位于存储设备的多个存储地址的头部(如图6所示)，或者该预置文件也可以位于该多个存储地址的其他部分(如中部或尾部)，本申请实施例对此不做限定。Still further, the management device can only write a preset file to the storage device, and the one preset file can be written to any storage address in the storage device, or any contiguous plurality of storage addresses. For example, the one preset file F1 may be located at the head of a plurality of storage addresses of the storage device (as shown in FIG. 6), or the preset file may also be located in other parts of the plurality of storage addresses (such as the middle or the tail). This embodiment of the present application does not limit this.

步骤202、确定n个存储区域中的至少m个存储区域是否异常，1≤m≤n。在 n个存储区域中的至少m个存储区域异常时，执行步骤203；在n个存储区域中异常的存储区域的个数小于m时，继续执行步骤202。Step 202: Determine whether at least m storage areas in the n storage areas are abnormal, 1≤m≤n. When at least m storage areas of the n storage areas are abnormal, step 203 is performed; when the number of abnormal storage areas in the n storage areas is less than m, step 202 is continued.

示例的，第一存储区域为n个存储区域中的任一存储区域，如图7所示，管理设备确定第一存储区域是否异常的过程可以包括：For example, the first storage area is any one of the n storage areas. As shown in FIG. 7, the process of determining whether the first storage area is abnormal by the management device may include:

步骤2021、对第一存储区域进行读操作。在读操作成功时，执行步骤2022；在读操作失败时，执行步骤2026。Step 2021: Perform a read operation on the first storage area. When the read operation is successful, step 2022 is performed; when the read operation fails, step 2026 is performed.

管理设备可以对第一存储区域进行读操作，并根据该读操作是否成功进行第一存储区域是否异常的判断，其中，对第一存储区域进行读操作也即是读取第一存储区域中存储的数据的操作。The management device may perform a read operation on the first storage area, and determine whether the first storage area is abnormal according to whether the read operation succeeds, wherein the reading operation on the first storage area is to read the storage in the first storage area. The operation of the data.

步骤2022、生成从第一存储区域读取到的第二目标数据的第二校验数据。执行步骤2023。Step 2022: Generate second verification data of the second target data read from the first storage area. Go to step 2023.

若对第一存储区域的读操作成功，则可以从第一存储区域读取到第二目标数据及第三校验数据，且该第二目标数据为对第一存储区域中的第一目标数据进行读操作得到的数据，该第三校验数据为对该第一存储区域中的第一校验数据进行读操作得到的数据。也即是，该第二目标数据为从第一存储区域中的第一区域读取到的数据，该第三校验数据为从第一存储区域中的第二区域读取到的数据。在管理设备从第一区域读取到第二目标数据之后，可以采用预设处理方式对读取到第二目标数据进行处理得到第二校验数据。If the read operation on the first storage area is successful, the second target data and the third check data may be read from the first storage area, and the second target data is the first target data in the first storage area. And performing data obtained by the read operation, wherein the third verification data is data obtained by performing a read operation on the first verification data in the first storage area. That is, the second target data is data read from the first area in the first storage area, and the third verification data is data read from the second area in the first storage area. After the management device reads the second target data from the first area, the second target data may be processed by using a preset processing manner to obtain the second verification data.

需要说明的是，读取到的第二目标数据可能与实际存储的第一目标数据相同，该第二目标数据也可能与实际存储的第一目标数据不同，读取到的第三校验数据与可能与实际存储的第一校验数据相同，该第三校验数据也可能与实际存储的第一校验数据不同，本申请实施例对此不作限定。It should be noted that the read second target data may be the same as the actually stored first target data, and the second target data may also be different from the actually stored first target data, and the read third check data may be The third check data may be different from the first check data that is actually stored, which may be different from the first check data that is actually stored.

步骤2023、判断第二校验数据与第三校验数据是否相同。在第二校验数据与第三校验数据相同时，执行步骤2024；在第二校验数据与第三校验数据不同时，执行步骤2026。Step 2023: Determine whether the second verification data and the third verification data are the same. When the second verification data is the same as the third verification data, step 2024 is performed; when the second verification data is different from the third verification data, step 2026 is performed.

管理设备在得到第二校验数据后，可以将第二校验数据与从第一存储区域中的第二区域读取到的第三校验数据进行比对，以判断第二校验数据与第三校验数据是否相同，进而确定从第一存储区域读取到的数据是否正确。After obtaining the second verification data, the management device may compare the second verification data with the third verification data read from the second area in the first storage area to determine the second verification data and Whether the third parity data is the same, thereby determining whether the data read from the first storage area is correct.

需要说明的是，采用预设处理方式对两个相同的数据进行处理得到的两个校验数据也相同，采用预设处理方式对两个不同的数据进行处理得到的两个校验数据也不同。It should be noted that the two verification data obtained by processing two identical data by using the preset processing manner are also the same, and the two verification data obtained by processing two different data by using the preset processing manner are also different. .

若第三校验数据与实际存储的第一校验数据相同(也即从第一存储区域中的第二区域读取的数据正确)，则可以根据第二校验数据与第三校验数据是否相同，确定第二目标数据与实际存储的第一目标数据是否相同。若第二校验数据与第三校验数据相同，则可以认为第二目标数据与第一目标数据相同，也即是从第一存储区域中的第一区域读取的数据正确，进而确定从第一存储区域读取到的数据均正确；若第二校验数据与第三校验数据不同，则认为从第一区域读取的数据错误，进而确定从第一存储区域读取的数据错误。If the third check data is the same as the actually stored first check data (that is, the data read from the second area in the first storage area is correct), the second check data and the third check data may be used. Whether they are the same, it is determined whether the second target data is identical to the actually stored first target data. If the second verification data is the same as the third verification data, the second target data may be considered to be the same as the first target data, that is, the data read from the first area in the first storage area is correct, thereby determining The data read by the first storage area is correct; if the second verification data is different from the third verification data, it is considered that the data read from the first area is incorrect, thereby determining the data error read from the first storage area. .

若第二目标数据与实际存储的第一目标数据相同(也即从第二区域读取的数据正确)，则第二校验数据与第一校验数据相同，确定第二校验数据与第三校验数据是否相同，也即是确定第一校验数据与第三校验数据是否相同。若第一校验数据与第三校验数据相同，则确定从第二区域读取的数据正确，进而确定从第一存储区域读取到的数据均正确；若第一校验数据与第三校验数据不同，则认为从第二区域读取的数据错误，进而确定从第一存储区域读取的数据错误。If the second target data is the same as the actually stored first target data (that is, the data read from the second region is correct), the second parity data is the same as the first parity data, and the second parity data is determined Whether the third check data is the same, that is, whether the first check data and the third check data are the same. If the first check data is the same as the third check data, determining that the data read from the second area is correct, and determining that the data read from the first storage area is correct; if the first check data and the third If the verification data is different, it is considered that the data read from the second area is incorrect, thereby determining the data error read from the first storage area.

由于第二目标数据与第一目标数据不同，且第一校验数据与第三校验数据也不同，但是第二校验数据与第三校验数据相同的情况发生的可能性微乎其微，因此可以在第二校验数据与第三校验数据相同时，认为从第一存储区域读取到的数据均正确；在第二校验数据与第三校验数据不同时，认为从第一存储区域读取到的数据错误。Since the second target data is different from the first target data, and the first check data is different from the third check data, the possibility that the second check data and the third check data are the same is unlikely, so When the second verification data is the same as the third verification data, it is considered that the data read from the first storage area is correct; when the second verification data is different from the third verification data, it is considered to be from the first storage area. The data read is incorrect.

步骤2024、用第二校验数据对第一存储区域中的第一校验数据进行覆盖操作。若覆盖操作成功，则执行步骤2025；若覆盖操作失败，则执行步骤2026。Step 2024: Perform a coverage operation on the first verification data in the first storage area by using the second verification data. If the overlay operation is successful, step 2025 is performed; if the overlay operation fails, step 2026 is performed.

需要说明的是，若管理设备在步骤2023中确定第二校验数据与第三校验数据相同，则可以认为从第一存储区域读取到数据正确，也即是确定从该第一存储区域可以正常读取数据，接着管理设备可以判断该第一存储区域中是否可以正常写入数据。It should be noted that, if the management device determines in step 2023 that the second verification data is the same as the third verification data, it may be considered that the data is correctly read from the first storage area, that is, it is determined from the first storage area. The data can be read normally, and then the management device can determine whether the data can be normally written in the first storage area.

示例的，管理设备可以对第一存储区域进行写入操作，也即是执行将数据存储入第一存储区域的操作。如管理设备可以用第二校验数据对第一存储区域中的第一校验数据进行覆盖操作，也即是对第二校验数据执行写入第一存储区域中的第二区域的操作。若该覆盖操作失败，则管理设备可以确定第二校验数据无法写入第二区域，进而确定第一存储区域中无法写入数据；若该覆盖操作成功，则管理设备可以确定第二校验数据成功写入第二区域，进而确定第一存储区域中能够写入数据。且由于此时第二校验数据与从第二区域读取到的第三校验数据相同，则可以认为第三校验数据和当前写入第二区域的第二校验数据均与实际存储的第一校验数据相同，步骤205中的覆盖操作并不会更改第一存储区域中存储的数据。For example, the management device may perform a write operation on the first storage area, that is, an operation of storing data into the first storage area. For example, the management device may perform the overlay operation on the first check data in the first storage area by using the second check data, that is, the operation of writing the second area in the first storage area to the second check data. If the overlay operation fails, the management device may determine that the second verification data cannot be written to the second area, thereby determining that the data cannot be written in the first storage area; if the overlay operation is successful, the management device may determine the second check The data is successfully written to the second area, thereby determining that data can be written in the first storage area. And since the second check data is the same as the third check data read from the second area at this time, it can be considered that the third check data and the second check data currently written in the second area are both actually stored. The first check data is the same, and the overlay operation in step 205 does not change the data stored in the first storage area.

步骤2025、确定第一存储区域正常。Step 2025: Determine that the first storage area is normal.

管理设备在对第一存储区域的读操作成功，从第一存储区域读取的数据正确，且对第一存储区域的写操作成功时，可以确定第一存储区域正常。The management device succeeds in the read operation on the first storage area, the data read from the first storage area is correct, and when the write operation to the first storage area is successful, the first storage area may be determined to be normal.

步骤2026、确定第一存储区域异常。Step 2026: Determine that the first storage area is abnormal.

管理设备在对第一存储区域的读操作失败，从第一存储区域读取的数据错误，或者对第一存储区域的写操作失败时，均可以确定第一存储区域异常。The management device may determine that the first storage area is abnormal when the read operation to the first storage area fails, the data read from the first storage area is incorrect, or the write operation to the first storage area fails.

需要说明的是，在步骤201之后，管理设备可以每隔预设时间段对第一存储区域进行读操作，或者在存储设备中除该n个存储区域之外的其他存储区域满足判断触发条件时，对第一存储区域进行读操作。也即是在步骤202中，管理设备可以每隔预设时间段确定n个存储区域中的至少m个存储区域是否异常。该判断触发条件可以包括：对该其他存储区域的读操作失败，从该其他存储区域中读取到的文件错误，以及对该其他存储区域的写操作失败中的至少一种条件。It should be noted that, after step 201, the management device may perform a read operation on the first storage area every preset time period, or when the storage area other than the n storage areas in the storage device meets the judgment trigger condition , the first storage area is read. That is, in step 202, the management device may determine whether at least m storage areas in the n storage areas are abnormal every predetermined time period. The determining trigger condition may include: a read operation to the other storage area, a file error read from the other storage area, and at least one of a write operation failure to the other storage area.

示例的，若管理设备对存储设备中的该其他存储区域的读操作失败，则管理设备可以确定该存储设备满足判断触发条件。若该读操作成功，则管理设备可以判断读取到的文件是否错误，若读取到的文件错误，则管理设备可以确定该存储设备满足判断触发条件；若读取到的文件正确，则管理设备可以确定该存储设备不满足判断触发条件。另外，若管理设备对存储设备中的该其他存储区域中执行写操作失败，则管理设备也可以确定该存储设备满足判断触发条件；若该写操作成功，则管理设备可以确定该存储设备不满足判断触发条件。For example, if the management device fails to read the other storage area in the storage device, the management device may determine that the storage device satisfies the judgment trigger condition. If the read operation is successful, the management device may determine whether the read file is incorrect. If the read file is incorrect, the management device may determine that the storage device satisfies the judgment trigger condition; if the read file is correct, then the management The device can determine that the storage device does not satisfy the judgment trigger condition. In addition, if the management device fails to perform a write operation on the other storage area in the storage device, the management device may also determine that the storage device satisfies the judgment trigger condition; if the write operation is successful, the management device may determine that the storage device is not satisfied. Determine the trigger condition.

步骤203、确定存储设备异常。Step 203: Determine that the storage device is abnormal.

管理设备在确定n个存储区域中的至少m个存储区域异常时，就可以确定该存储设备异常，接着管理设备可以禁止在存储设备上进行数据读写。可选的，管理设备还可以在确定存储设备异常后通知工作人员对存储设备进行维修，或者向请求在该存储设备上读写数据的客户端发送提示消息，或者管理设备还可以进行其他操作，本申请实施例对此不做限定。When the management device determines that at least m storage areas in the n storage areas are abnormal, the storage device may be abnormal, and then the management device may prohibit data reading and writing on the storage device. Optionally, the management device may notify the worker to repair the storage device after determining the abnormality of the storage device, or send a prompt message to the client requesting to read or write data on the storage device, or the management device may perform other operations. This embodiment of the present application does not limit this.

需要说明的是，在m＝1的时候，存储设备中仅一个存储区域中存储有预置文件，若该一个存储区域异常，则管理设备可以确定整个存储设备异常；在 2≤m≤n的时候，存储设备中存在多个存储区域中均存储有预置文件，管理设备在确定n个存储区域中的至少m个存储区域异常时，就可以确定该存储设备异常，该m的值可以由用户自行确定。另外，由于在该n个存储区域中的一部分存储区域异常时存储设备可能还可以继续使用，因此m也可以等于n，也即是管理设备可以在确定该n个存储区域均异常时，才确定存储设备异常，以提高确定存储设备是否异常的精准度。It should be noted that, when m=1, a preset file is stored in only one storage area in the storage device. If the storage area is abnormal, the management device may determine that the entire storage device is abnormal; at 2≤m≤n When a storage device stores a preset file in a plurality of storage areas, the management device determines that the storage device is abnormal when determining that at least m storage areas in the n storage areas are abnormal, and the value of the m can be determined by The user determines it by himself. In addition, since the storage device may continue to be used when a part of the storage areas of the n storage areas are abnormal, m may also be equal to n, that is, the management device may determine that the n storage areas are abnormal. The storage device is abnormal to improve the accuracy of determining whether the storage device is abnormal.

相关技术中，分布式存储***是通过网络将管理设备与多个存储设备进行连接的***，存储设备异常的情况通常包括：存储设备掉线(也即与管理设备断开连接)、存储设备损坏(也即是存储设备不可用)以及存储设备后端存储异常(也即是存储的数据错误，可以读写数据但是读写的数据不正常)等情况中的至少一种情况。在存储设备出现掉线、损坏或者后端存储异常的情况时，管理设备无法及时获知。此时，若管理设备需要将数据写入该存储设备，则管理设备会将该数据写入该存储设备下线前所在的地址，进而造成数据丢失；若管理设备需要从该存储设备上读取数据，则管理设备会在该存储设备未下线时所在的地址进行读取操作，进而可能无法读取到数据或者读取到错误的数据，使得读取到正确数据的效率较低。In the related art, a distributed storage system is a system for connecting a management device to multiple storage devices through a network. The abnormality of the storage device usually includes: the storage device is disconnected (that is, disconnected from the management device), and the storage device is damaged. (that is, the storage device is not available) and at least one of the storage device backend storage exception (that is, the stored data error, the data can be read or written but the data read and written is not normal). When the storage device is disconnected, damaged, or the backend storage is abnormal, the management device cannot be known in time. At this time, if the management device needs to write data to the storage device, the management device writes the data to the address before the storage device goes offline, thereby causing data loss; if the management device needs to read from the storage device, Data, the management device will read at the address where the storage device is not offline, and may not be able to read the data or read the wrong data, so that the efficiency of reading the correct data is low.

本申请实施例中，管理设备可以向存储设备中的部分存储区域中的n个存储区域中写入n个预置文件，并可以每隔预设时间段或者在存储设备满足判断触发条件时，判断该n个存储区域中的至少m个存储区域是否均异常，并在该n个存储区域中的至少m个存储区域异常时，确定存储设备异常，进而实现了对存储设备异常的检测。In the embodiment of the present application, the management device may write n preset files to n storage areas in a part of the storage area of the storage device, and may complete the preset trigger period or when the storage device satisfies the judgment trigger condition. It is determined whether at least m storage areas of the n storage areas are abnormal, and when at least m storage areas of the n storage areas are abnormal, the storage device abnormality is determined, thereby detecting the abnormality of the storage device.

需要说明的是，本申请实施例中的存储设备可以为DISK、SSD、RAID、SAN、FC SAN、NAS、云存储以及对象存储等存储设备中任意一种存储设备。其中，RAID为由多个独立的硬盘(也叫作物理硬盘)按不同的方式组合起来形成的一个硬盘组(也叫作逻辑硬盘)，RAID的存储性能比单个硬盘更高，且可以进行数据备份。RAID中的每个硬盘可以为磁盘(英文：disk)。步骤201中管理设备写入RAID中的n个存储区域的n个预置文件中，每个预置文件的大小需要大于或者等于RAID中一个条带(也称为stripe)的大小，以使得通过判断n个存储区域中的至少m个存储区域是否异常，可以准确的确定RAID是否异常。It should be noted that the storage device in the embodiment of the present application may be any storage device such as a DISK, SSD, RAID, SAN, FC SAN, NAS, cloud storage, and object storage. Among them, RAID is a hard disk group (also called a logical hard disk) formed by combining different independent hard disks (also called physical hard disks) in different ways. The storage performance of RAID is higher than that of a single hard disk, and data can be performed. Backup. Each hard disk in RAID can be a disk (English: disk). In step 201, the management device writes n preset files of n storage areas in the RAID, and the size of each preset file needs to be greater than or equal to the size of one stripe (also called stripe) in the RAID, so as to pass It is determined whether at least m storage areas in the n storage areas are abnormal, and it is possible to accurately determine whether the RAID is abnormal.

示例地，假设RAID共包括x个磁盘，每个磁盘包括多个存储块(也称为 chunk)，则RAID中的每个条带可以包括：x个磁盘中的x个存储块，也即，该条带包括每个磁盘的一个存储块。条带中的x个存储块中，x-1个存储块用于存储数据，剩余的一个存储块用于存储该数据的验证信息，该条带的大小为该x-1个存储块中能够存储的数据量。By way of example, assuming that a RAID includes a total of x disks, each disk including a plurality of storage blocks (also referred to as chunks), each stripe in the RAID may include: x of the x disks, that is, The strip includes one memory block per disk. Among the x memory blocks in the stripe, x-1 memory blocks are used to store data, and the remaining one memory block is used to store verification information of the data, and the size of the stripe is the size of the x-1 memory blocks. The amount of data stored.

RAID中的每个磁盘可以包括i个存储块，i≥2。请参考图8，若RAID为由三个磁盘组成的RAID5(RAID5为一种RAID)，该RAID5中的三个磁盘为图8示出的磁盘A、B和C，假设该RAID5中的每个磁盘均包括五个存储块(也即是i＝5)，如磁盘A包括存储块A ₁、A ₂、A ₃、A ₄、A ₅，磁盘B包括存储块B ₁、B ₂、B ₃、B ₄、B ₅，磁盘C包括存储块C ₁、C ₂、C ₃、C ₄、C ₅。需要说明的是，该每个存储块的地址可以为存储设备的一个存储地址，且该RAID的连续的多个存储地址可以为：A ₁、B ₁、C ₁、A ₂、B ₂、C ₂、A ₃、B ₃、C ₃、A ₄、B ₄、C ₄、A ₅、B ₅以及C ₅的地址。 Each disk in the RAID can include i storage blocks, i≥2. Referring to FIG. 8, if RAID is a RAID 5 composed of three disks (RAID 5 is a RAID), three disks in the RAID 5 are disks A, B, and C shown in FIG. 8, assuming each of the RAID 5 Each disk includes five storage blocks (that is, i=5). For example, disk A includes storage blocks A ₁ , A ₂ , A ₃ , A ₄ , and A ₅ , and disk B includes storage blocks B ₁ , B ₂ , and B _{3 .} , B ₄ , B ₅ , the disk C includes memory blocks C ₁ , C ₂ , C ₃ , C ₄ , C ₅ . It should be noted that the address of each storage block may be a storage address of the storage device, and consecutive storage addresses of the RAID may be: A ₁ , B ₁ , C ₁ , A ₂ , B ₂ , C ₂ , A ₃ , B ₃ , C ₃ , A ₄ , B ₄ , C ₄ , A ₅ , B ₅ and C ₅ addresses.

例如，假设图8中存储块C ₁、B ₂、A ₃、C ₄以及B ₅的存储地址中存储有数据的验证信息，则管理设备可以向该RAID5中的其他存储地址中写入三个预置文件f1、f2和f3，且三个预置文件f1、f2和f3的大小均为一个条带的大小。如管理设备可以将预置文件f1写入存储块A ₁的存储地址与存储块B ₁的存储地址，将预置文件f2写入存储块B ₃的存储地址和存储块C ₃的存储地址，将预置文件f3写入存储块A ₅的存储地址和存储块C ₅的存储地址。进而使得预置文件f1存储在多个存储地址中的头部、预置文件f2存储在多个存储地址中的中部、预置文件f3存储在多个存储地址中的尾部。可选的，每个预置文件中的目标数据均可以存储在两个存储块的存储地址中。 For example, assuming that the verification information of the data is stored in the storage addresses of the storage blocks C ₁ , B ₂ , A ₃ , C _{4 ,} and B ₅ in FIG. 8 , the management device can write three to the other storage addresses in the RAID 5 . The preset files f1, f2, and f3, and the sizes of the three preset files f1, f2, and f3 are all the size of one stripe. The file management apparatus may f1 preset memory addresses written into the memory block A and the block B ₁ is stored in memory address _1, the file f2 preset memory addresses written into the memory block and the memory block B ₃ C ₃ is the memory address, The preset file f3 is written to the memory address of the memory block A _{5 and} the memory address of the memory block C ₅ . Further, the preset file f1 is stored in the header of the plurality of storage addresses, the preset file f2 is stored in the middle of the plurality of storage addresses, and the preset file f3 is stored in the tail of the plurality of storage addresses. Optionally, the target data in each preset file can be stored in the storage address of the two storage blocks.

另外，本申请实施例仅以存储设备为RAID，且RAID为由三个独立的磁盘组成的RAID5、每个磁盘包括5个存储块、向RAID中写入三个预置文件为例，可选地，存储设备还可以包括四个、五个或者更多的磁盘，每个磁盘还可以包括八个、九个或者更多的存储块，存储设备中可以还写入四个或者五个预置文件，本申请实施例对此不作限定。In addition, the embodiment of the present application only uses the storage device as a RAID, and the RAID is a RAID 5 composed of three independent disks, each disk includes five storage blocks, and three preset files are written into the RAID as an example. The storage device may also include four, five or more disks, each of which may also include eight, nine or more storage blocks, and four or five presets may also be written in the storage device. The document is not limited in this embodiment.

需要说明的是，管理设备在向RAID中写入数据时，若该数据的数据量大于一个条带的大小，则管理设备可以按照将该数据分为多个条带依次写入该多个存储地址。It should be noted that, when the management device writes data to the RAID, if the data volume of the data is greater than the size of one stripe, the management device may sequentially write the data into the plurality of storages according to the stripe. address.

综上所述，本申请实施例提供的设备异常检测方法中，可以在存储设备中的部分存储区域中的n个存储区域写入n个预置文件，且第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，第一预置文件包括：第一目标数据及其第一校验数据。在对第一存储区域的读操作成功时，生成从第一存储区域读取到的第二目标数据的第二校验数据。第三校验数据为对第一存储区域中的第一校验数据进行读操作得到的数据，且在第二校验数据与第三校验数据不同时，可以确定第一存储区域异常。在确定n个存储区域中的至少m个存储区域异常时，可以确定存储设备异常，1≤m≤n，进而实现了对存储设备异常的检测。当确定某一存储设备异常时，管理设备可以不再将数据写入该存储设备，防止了管理设备将数据写入异常的存储设备而导致的数据丢失。In summary, in the device abnormality detecting method provided by the embodiment of the present application, n preset files may be written in n storage areas in a partial storage area in the storage device, and the first preset file is n pre-prepared files. The first preset file is written into the first storage area, and the first preset file includes: the first target data and the first check data thereof. When the read operation on the first storage area is successful, the second check data of the second target data read from the first storage area is generated. The third verification data is data obtained by performing a read operation on the first verification data in the first storage area, and when the second verification data is different from the third verification data, the first storage area abnormality may be determined. When it is determined that at least m storage areas in the n storage areas are abnormal, the storage device abnormality may be determined, 1≤m≤n, thereby implementing detection of the storage device abnormality. When it is determined that a certain storage device is abnormal, the management device may no longer write data to the storage device, preventing data loss caused by the management device writing data to the abnormal storage device.

图9是本申请实施例提供的一种存储设备异常检测装置的结构示意图。该存储设备异常检测装置应用于图1中的管理设备101，存储设备中的部分存储区域包括n个存储区域，n≥1，如图9所示，该存储设备异常检测装置90包括：FIG. 9 is a schematic structural diagram of a storage device abnormality detecting apparatus according to an embodiment of the present application. The storage device abnormality detecting device 90 is applied to the management device 101 in FIG. 1. The partial storage area in the storage device includes n storage areas, n≥1. As shown in FIG. 9, the storage device abnormality detecting device 90 includes:

写入模块901，用于向n个存储区域中写入n个预置文件，其中，第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，第一预置文件包括：第一目标数据及其第一校验数据。The writing module 901 is configured to write n preset files to the n storage areas, where the first preset file is any preset file among the n preset files, and the first preset file is written into the first preset file. a storage area, the first preset file includes: first target data and first calibration data thereof.

生成模块902，用于在对第一存储区域的读操作成功时，生成从第一存储区域读取到的第二目标数据的第二校验数据，第二目标数据为对第一存储区域中的第一目标数据进行读操作得到的数据；a generating module 902, configured to generate second verification data of the second target data read from the first storage area when the read operation on the first storage area is successful, where the second target data is in the first storage area The data obtained by the first target data for the read operation;

第一确定模块903，用于在第二校验数据与第三校验数据不同时，确定第一存储区域异常，其中，第三校验数据为对第一存储区域中的第一校验数据进行读操作得到的数据。The first determining module 903 is configured to determine that the first storage area is abnormal when the second check data is different from the third check data, where the third check data is the first check data in the first storage area The data obtained by the read operation.

第二确定模块904，用于在确定n个存储区域中的至少m个存储区域异常时，确定存储设备异常，1≤m≤n。The second determining module 904 is configured to determine that the storage device is abnormal when determining that at least m storage areas in the n storage areas are abnormal, 1≤m≤n.

综上所述，本申请实施例提供的存储设备异常检测装置中，写入模块可以在存储设备中的部分存储区域中的n个存储区域写入n个预置文件，且第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，第一预置文件包括：第一目标数据及其第一校验数据；生成模块可以在对第一存储区域的读操作成功时，生成从第一存储区域读取到的第二目标数据的第二校验数据。第三校验数据为第一存储区域中的第一校验数据进行读操作得到的数据；第一确定模块可以在第二校验数据与第三校验数据不同时，可以确定第一存储区域异常，第二确定模块在确定n个存储区域中的至少m个存储区域异常时，确定存储设备异常，进而实现了对存储设备异常的检测。In summary, in the storage device abnormality detecting apparatus provided by the embodiment of the present application, the writing module may write n preset files in n storage areas in a part of the storage area in the storage device, and the first preset file For any preset file of the n preset files, the first preset file is written into the first storage area, the first preset file includes: first target data and first calibration data thereof; and the generation module may be in the pair When the read operation of the first storage area is successful, the second check data of the second target data read from the first storage area is generated. The third verification data is data obtained by performing a read operation on the first verification data in the first storage area; the first determining module may determine the first storage area when the second verification data is different from the third verification data. If the abnormality is determined, the second determining module determines that the storage device is abnormal when at least m storage areas of the n storage areas are abnormal, thereby detecting the abnormality of the storage device.

图10是本申请实施例提供的另一种存储设备异常检测装置的结构示意图。如图10所示，在图9的基础上，该存储设备异常检测装置还包括：FIG. 10 is a schematic structural diagram of another storage device abnormality detecting apparatus according to an embodiment of the present application. As shown in FIG. 10, on the basis of FIG. 9, the storage device abnormality detecting apparatus further includes:

第三确定模块905，用于在从第一存储区域读取到的校验数据与第二校验数据相同，且采用第二校验数据覆盖第一存储区域中的第一校验数据失败时，确定第一存储区域异常。The third determining module 905 is configured to: when the check data read from the first storage area is the same as the second check data, and the second check data is used to cover the first check data in the first storage area, failing , determining that the first storage area is abnormal.

可选的，图11是本申请实施例提供的再一种存储设备异常检测装置的结构示意图。如图11所示，在图9的基础上，该存储设备异常检测装置还包括：Optionally, FIG. 11 is a schematic structural diagram of still another storage device abnormality detecting apparatus according to an embodiment of the present application. As shown in FIG. 11, on the basis of FIG. 9, the storage device abnormality detecting apparatus further includes:

第四确定模块906，用于在对第一存储区域的读操作失败时，确定第一存储区域异常。The fourth determining module 906 is configured to determine that the first storage area is abnormal when the read operation on the first storage area fails.

可选的，第一校验数据采用预设处理方式对第一目标数据进行处理得到，第二校验数据采用预设处理方式对第二目标数据进行处理得到。Optionally, the first verification data is processed by using a preset processing manner to obtain the first target data, and the second verification data is processed by using a preset processing manner to process the second target data.

可选的，n≥3，存储设备具有连续的多个存储地址，n个存储区域包括多个存储地址中的头部、中部以及尾部。如头部包括该多个存储地址中前30％的存储地址，尾部包括该多个存储地址中后30％的存储地址，中部包括该多个存储地址中头部和尾部之间的存储地址中的部分存储地址。Optionally, n≥3, the storage device has a plurality of consecutive storage addresses, and the n storage areas include a head, a middle, and a tail of the plurality of storage addresses. If the header includes the first 30% of the plurality of storage addresses, the tail includes the last 30% of the plurality of storage addresses, and the middle portion includes the storage address between the head and the tail of the plurality of storage addresses. Part of the storage address.

管理设备可以将该n个预置文件分别存储在该多个存储地址的头部、中部以及尾部。存储于头部的任一预置文件的存储地址可以为头部中的任一存储地址或任意多个连续的存储地址，存储于中部的任一预置文件的存储地址可以为中部中的任一存储地址或任意多个连续的存储地址，存储于尾部的任一预置文件的存储地址可以为尾部中的任一存储地址或任意多个连续的存储地址。The management device may store the n preset files in the head, middle, and tail of the plurality of storage addresses, respectively. The storage address of any preset file stored in the header may be any storage address in the header or any number of consecutive storage addresses, and the storage address of any preset file stored in the middle may be any in the middle. A storage address or any number of consecutive storage addresses, the storage address of any of the preset files stored at the tail may be any storage address in the tail or any number of consecutive storage addresses.

可选的，存储设备包括独立冗余磁盘阵列RAID，预置文件的大小大于或者等于RAID中一个条带的大小。Optionally, the storage device includes an independent redundant disk array RAID, and the size of the preset file is greater than or equal to the size of one stripe in the RAID.

需要说明的是，通常会对存储设备中的磁盘进行条带化，也即是将要存储在磁盘中的连续的数据分成多个数据块，并把得到的数据块分别存储到不同磁盘中。每个磁盘包括多个存储块，每个数据块存储于一个存储块中，且相邻数据块存储于不同磁盘的存储块中。存储设备中的一个条带包括存储设备中每个磁盘中的一个存储块，一个条带中存储有连续的数据，一个条带的大小为该条带能够存储的数据量。It should be noted that the disk in the storage device is usually striped, that is, the continuous data to be stored in the disk is divided into a plurality of data blocks, and the obtained data blocks are separately stored in different disks. Each disk includes a plurality of memory blocks, each of which is stored in one memory block, and adjacent data blocks are stored in memory blocks of different disks. A stripe in the storage device includes one of each of the disks in the storage device. One strip stores continuous data, and the size of one strip is the amount of data that the strip can store.

可选的，存储设备具有除n个存储区域之外的其他存储区域，如图12所示，在图9的基础上，存储设备异常检测装置还包括：Optionally, the storage device has a storage area other than the n storage areas. As shown in FIG. 12, the storage device abnormality detecting apparatus further includes:

第一读取模块907，用于每隔预设时间段对第一存储区域进行读操作。The first reading module 907 is configured to perform a read operation on the first storage area every preset time period.

或者，如图12所示，在图9的基础上，存储设备异常检测装置还包括：Or, as shown in FIG. 12, on the basis of FIG. 9, the storage device abnormality detecting apparatus further includes:

第二读取模块908，用于在其他存储区域满足判断触发条件时，对第一存储区域进行读操作，判断触发条件包括：对其他存储区域的读操作失败，从其他存储区域中读取到的文件错误，以及对其他存储区域的写操作失败中的至少一种条件。The second reading module 908 is configured to perform a read operation on the first storage area when the other storage area satisfies the determination trigger condition, and determine that the trigger condition includes: the read operation to the other storage area fails, and is read from the other storage area. File error, and at least one of the failures of write operations to other storage areas.

可选的，m＝n。也即是，管理设备可以在确定存储设备中的部分存储区域(也即n个存储区域)均异常时，才确定存储设备异常，进而可以提高确定存储设备是否异常的精准度。Optional, m=n. That is, the management device can determine that the storage device is abnormal when it is determined that some storage areas (that is, n storage areas) in the storage device are abnormal, thereby improving the accuracy of determining whether the storage device is abnormal.

本申请实施例提供了一种分布式存储***，该分布式存储***可以为图1所示的分布式存储***，该分布式存储***包括管理设备与多个存储设备，该管理设备可以包括图8至图13任一所示的存储设备异常检测装置。The embodiment of the present application provides a distributed storage system, which may be the distributed storage system shown in FIG. 1 , where the distributed storage system includes a management device and multiple storage devices, and the management device may include a map. 8 to the storage device abnormality detecting device shown in any of FIG.

图14是本申请实施例提供的一种计算机设备的结构示意图，该计算机设备可以用于分布式存储***中的管理设备，如图14所示，计算机设备000包括中央处理单元(CPU)001、包括随机存取存储器(RAM)002和只读存储器(ROM)003的***存储器004，以及连接***存储器004和中央处理单元001的***总线005。所述服务器000还包括帮助计算机内的各个器件之间传输信息的基本输入/输出***(I/O***)006，和用于存储操作***013、应用程序014和其他程序模块015的大容量存储设备007。14 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure. The computer device can be used in a management device in a distributed storage system. As shown in FIG. 14, the computer device 000 includes a central processing unit (CPU) 001. A system memory 004 including random access memory (RAM) 002 and read only memory (ROM) 003, and a system bus 005 connecting system memory 004 and central processing unit 001. The server 000 also includes a basic input/output system (I/O system) 006 that facilitates transfer of information between various devices within the computer, and mass storage for storing operating system 013, applications 014, and other program modules 015. Device 007.

所述基本输入/输出***006包括有用于显示信息的显示器008和用于用户输入信息的诸如鼠标、键盘之类的输入设备009。其中所述显示器008和输入设备009都通过连接到***总线005的输入输出控制器010连接到中央处理单元001。所述基本输入/输出***006还可以包括输入输出控制器010以用于接收和处理来自键盘、鼠标、或电子触控笔等多个其他设备的输入。类似地，输入输出控制器010还提供输出到显示屏、打印机或其他类型的输出设备。The basic input/output system 006 includes a display 008 for displaying information and an input device 009 such as a mouse, a keyboard for inputting information by a user. The display 008 and the input device 009 are both connected to the central processing unit 001 through an input/output controller 010 connected to the system bus 005. The basic input/output system 006 can also include an input output controller 010 for receiving and processing input from a plurality of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 010 also provides output to a display screen, printer, or other type of output device.

所述大容量存储设备007通过连接到***总线005的大容量存储控制器(未示出)连接到中央处理单元001。所述大容量存储设备007及其相关联的计算机可读介质为服务器000提供非易失性存储。也就是说，所述大容量存储设备007可以包括诸如硬盘或者CD-ROM驱动器之类的计算机可读介质(未示出)。The mass storage device 007 is connected to the central processing unit 001 by a mass storage controller (not shown) connected to the system bus 005. The mass storage device 007 and its associated computer readable medium provide non-volatile storage for the server 000. That is, the mass storage device 007 can include a computer readable medium (not shown) such as a hard disk or a CD-ROM drive.

不失一般性，所述计算机可读介质可以包括计算机存储介质和通信介质。计算机存储介质包括以用于存储诸如计算机可读指令、数据结构、程序模块或其他数据等信息的任何方法或技术实现的易失性和非易失性、可移动和不可移动介质。计算机存储介质包括RAM、ROM、EPROM、EEPROM、闪存或其他固态存储其技术，CD-ROM、DVD或其他光学存储、磁带盒、磁带、磁盘存储或其他磁性存储设备。当然，本领域技术人员可知所述计算机存储介质不局限于上述几种。上述的***存储器004和大容量存储设备007可以统称为存储器。Without loss of generality, the computer readable medium can include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid state storage technologies, CD-ROM, DVD or other optical storage, tape cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage medium is not limited to the above. The system memory 004 and the mass storage device 007 described above may be collectively referred to as a memory.

根据本申请的各种实施例，所述服务器000还可以通过诸如因特网等网络连接到网络上的远程计算机运行。也即服务器000可以通过连接在所述***总线005上的网络接口单元011连接到网络012，或者说，也可以使用网络接口单元011来连接到其他类型的网络或远程计算机***(未示出)。According to various embodiments of the present application, the server 000 can also be operated by a remote computer connected to the network through a network such as the Internet. That is, the server 000 can be connected to the network 012 through the network interface unit 011 connected to the system bus 005, or the network interface unit 011 can be used to connect to other types of networks or remote computer systems (not shown). .

所述存储器还包括一个或者一个以上的程序，所述一个或者一个以上程序存储于存储器中，中央处理器001通过执行该一个或一个以上程序来实现图2所示的设备异常检测方法。The memory further includes one or more programs, the one or more programs being stored in a memory, and the central processor 001 implementing the device anomaly detection method illustrated in FIG. 2 by executing the one or more programs.

在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器，上述指令可由服务器的处理器执行以完成本申请各个实施例所示的存储设备异常检测方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium comprising instructions, such as a memory comprising instructions executable by a processor of a server to perform the storage device illustrated in various embodiments of the present application Anomaly detection method. For example, the non-transitory computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.

本申请实施例还提供了一种计算机程序产品，当计算机程序产品在计算机上运行时，使得计算机执行上述存储设备异常检测方法。The embodiment of the present application further provides a computer program product, when the computer program product is run on a computer, causing the computer to execute the above-mentioned storage device abnormality detecting method.

本申请实施例还提供了一种芯片，该芯片包括可编程逻辑电路和/或程序指令，当芯片运行时用于实现上述存储设备异常检测方法。The embodiment of the present application further provides a chip, which includes programmable logic circuits and/or program instructions, and is used to implement the above-mentioned storage device abnormality detecting method when the chip is running.

需要说明的是：上述实施例提供的存储设备异常检测装置在检测存储设备异常时，仅以上述各功能模块的划分进行举例说明，可选地，可以根据需要而将上述功能分配由不同的功能模块完成，即将存储设备异常检测装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。It should be noted that, when the storage device abnormality detecting device provided by the foregoing embodiment detects the abnormality of the storage device, only the division of each functional module is described as an example. Alternatively, the foregoing function may be assigned to different functions according to requirements. The module is completed, that is, the internal structure of the storage device abnormality detecting device is divided into different functional modules to complete all or part of the functions described above.

需要说明的是，本申请实施例提供的方法实施例能够与相应的装置实施例相互参考，本申请实施例对此不做限定。本申请实施例提供的方法实施例步骤的先后顺序能够进行适当调整，步骤也能够根据情况进行相应增减，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化的方法，都应涵盖在本申请的保护范围之内，因此不再赘述。It should be noted that the embodiment of the method provided by the embodiment of the present application can refer to the corresponding device embodiment, and the embodiment of the present application does not limit this. The sequence of the steps of the method embodiments provided by the embodiments of the present application can be appropriately adjusted, and the steps can be correspondingly increased or decreased according to the situation. Any person skilled in the art can easily think of changes within the technical scope disclosed in the present application. The method should be covered by the scope of protection of the present application, and therefore will not be described again.

以上所述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。The above description is only an optional embodiment of the present application, and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application are included in the protection of the present application. Within the scope.

Claims

一种存储设备异常检测方法，其特征在于，应用于管理设备，所述存储设备中的部分存储区域包括n个存储区域，n≥1，所述方法包括：A storage device abnormality detecting method is applied to a management device, and a part of the storage area of the storage device includes n storage areas, n≥1, and the method includes:

向所述n个存储区域中写入n个预置文件，其中，第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，所述第一预置文件包括：第一目标数据及其第一校验数据；Writing n preset files to the n storage areas, where the first preset file is any one of n preset files, and the first preset file is written into the first storage area. The first preset file includes: first target data and first calibration data thereof;

在对所述第一存储区域的读操作成功时，生成第二目标数据的第二校验数据，所述第二目标数据为对所述第一存储区域中的所述第一目标数据进行读操作得到的数据；And generating, when the read operation on the first storage area is successful, second check data of the second target data, where the second target data is to read the first target data in the first storage area Operational data;

在所述第二校验数据与第三校验数据不同时，确定所述第一存储区域异常，其中，所述第三校验数据为对所述第一存储区域中的所述第一校验数据进行读操作得到的数据；Determining that the first storage area is abnormal when the second check data is different from the third check data, wherein the third check data is the first school in the first storage area Data obtained by reading data;

在确定所述n个存储区域中的至少m个存储区域异常时，确定所述存储设备异常，1≤m≤n。When it is determined that at least m storage areas of the n storage areas are abnormal, the storage device is determined to be abnormal, 1≤m≤n.
根据权利要求1所述的方法，其特征在于，所述方法还包括：The method of claim 1 further comprising:

在从所述第一存储区域读取到的校验数据与所述第二校验数据相同，且采用所述第二校验数据覆盖所述第一存储区域中的所述第一校验数据失败时，确定所述第一存储区域异常。The check data read from the first storage area is the same as the second check data, and the second check data is used to cover the first check data in the first storage area When it fails, it is determined that the first storage area is abnormal.
根据权利要求1或2所述的方法，其特征在于，所述方法还包括：The method according to claim 1 or 2, wherein the method further comprises:

在对所述第一存储区域的读操作失败时，确定所述第一存储区域异常。When the read operation on the first storage area fails, the first storage area is determined to be abnormal.
根据权利要求1所述的方法，其特征在于，所述第一校验数据采用预设处理方式对所述第一目标数据进行处理得到，所述第二校验数据采用所述预设处理方式对所述第二目标数据进行处理得到。The method according to claim 1, wherein the first verification data is processed by using a preset processing manner, and the second verification data is processed by the preset processing manner. The second target data is processed.
根据权利要求1所述的方法，其特征在于，n≥3，所述存储设备具有连续的多个存储地址，所述n个存储区域包括所述多个存储地址中的头部、中部以及尾部。The method according to claim 1, wherein n≥3, said storage device has a plurality of consecutive storage addresses, said n storage areas including a head, a middle, and a tail of said plurality of storage addresses .
根据权利要求1所述的方法，其特征在于，所述存储设备包括独立冗余磁盘阵列RAID，所述预置文件的大小大于或者等于所述RAID中一个条带的大小。The method according to claim 1, wherein the storage device comprises an independent redundant disk array RAID, and the size of the preset file is greater than or equal to a size of one strip in the RAID.
根据权利要求1所述的方法，其特征在于，所述存储设备包括除所述n个存储区域之外的其他存储区域，所述方法还包括：The method of claim 1, wherein the storage device comprises a storage area other than the n storage areas, the method further comprising:

每隔预设时间段对所述第一存储区域进行所述读操作；Performing the read operation on the first storage area every preset time period;

或者，在所述其他存储区域满足判断触发条件时，对所述第一存储区域进行所述读操作，所述判断触发条件包括：对所述其他存储区域的读操作失败，从所述其他存储区域中读取到的文件错误，以及对所述其他存储区域的写操作失败中的至少一种条件。Or performing the read operation on the first storage area when the other storage area satisfies the judgment trigger condition, where the determining trigger condition includes: a read operation on the other storage area fails, from the other storage At least one of a file error read in the area and a write operation failure to the other storage area.
根据权利要求1所述的方法，其特征在于，m＝n。The method of claim 1 wherein m = n.
一种存储设备异常检测装置，其特征在于，应用于管理设备，所述存储设备中的部分存储区域包括n个存储区域，n≥1，所述存储设备异常检测装置包括：A device for detecting abnormality of a storage device, which is applied to a management device, wherein a part of the storage area of the storage device includes n storage areas, n≥1, and the storage device abnormality detecting device includes:

写入模块，用于向所述n个存储区域中写入n个预置文件，其中，第一预置文件为n个预置文件中的任一预置文件，第一预置文件写入第一存储区域，所述第一预置文件包括：第一目标数据及其第一校验数据；a writing module, configured to write n preset files to the n storage areas, where the first preset file is any one of n preset files, and the first preset file is written a first storage area, the first preset file includes: first target data and first calibration data thereof;

生成模块，用于在对所述第一存储区域的读操作成功时，生成第二目标数据的第二校验数据，所述第二目标数据为对所述第一存储区域中的所述第一目标数据进行读操作得到的数据；a generating module, configured to generate second verification data of the second target data when the read operation on the first storage area is successful, where the second target data is the first in the first storage area Data obtained by reading a target data;

第一确定模块，用于在所述第二校验数据与第三校验数据不同时，确定所述第一存储区域异常，其中，所述第三校验数据为对所述第一存储区域中的所述第一校验数据进行读操作得到的数据；a first determining module, configured to determine that the first storage area is abnormal when the second check data is different from the third check data, where the third check data is for the first storage area Data obtained by the first verification data in the read operation;

第二确定模块，用于在确定所述n个存储区域中的至少m个存储区域异常时，确定所述存储设备异常，1≤m≤n。And a second determining module, configured to determine that the storage device is abnormal when determining that at least m storage areas of the n storage areas are abnormal, 1≤m≤n.
根据权利要求9所述的存储设备异常检测装置，其特征在于，所述存储设备异常检测装置还包括：The storage device abnormality detecting device according to claim 9, wherein the storage device abnormality detecting device further comprises:

第三确定模块，用于在从所述第一存储区域读取到的校验数据与所述第二校验数据相同，且采用所述第二校验数据覆盖所述第一存储区域中的所述第一校验数据失败时，确定所述第一存储区域异常。a third determining module, configured to: the check data read from the first storage area is the same as the second check data, and use the second check data to cover the first storage area When the first verification data fails, the first storage area is determined to be abnormal.
根据权利要求9或10所述的存储设备异常检测装置，其特征在于，所述存储设备异常检测装置还包括：The storage device abnormality detecting device according to claim 9 or 10, wherein the storage device abnormality detecting device further comprises:

第四确定模块，用于在对所述第一存储区域的读操作失败时，确定所述第一存储区域异常。And a fourth determining module, configured to determine that the first storage area is abnormal when a read operation on the first storage area fails.
根据权利要求9所述的存储设备异常检测装置，其特征在于，所述第一校验数据采用预设处理方式对所述第一目标数据进行处理得到，所述第二校验数据采用所述预设处理方式对所述第二目标数据进行处理得到。The storage device abnormality detecting device according to claim 9, wherein the first verification data is processed by using a preset processing manner, and the second verification data is obtained by using the The preset processing manner is obtained by processing the second target data.
根据权利要求9所述的存储设备异常检测装置，其特征在于，n≥3，所述存储设备具有连续的多个存储地址，所述n个存储区域包括所述多个存储地址中的头部、中部以及尾部。The storage device abnormality detecting apparatus according to claim 9, wherein n≥3, said storage device has a plurality of consecutive storage addresses, and said n storage areas include a head of said plurality of storage addresses , middle and tail.
根据权利要求9所述的存储设备异常检测装置，其特征在于，所述存储设备包括独立冗余磁盘阵列RAID，所述预置文件的大小大于或者等于所述RAID中一个条带的大小。The storage device abnormality detecting apparatus according to claim 9, wherein the storage device comprises an independent redundant disk array RAID, and the size of the preset file is greater than or equal to a size of one strip in the RAID.
根据权利要求8所述的存储设备异常检测装置，其特征在于，所述存储设备包括除所述n个存储区域之外的其他存储区域，所述存储设备异常检测装置还包括：The storage device abnormality detecting device according to claim 8, wherein the storage device includes a storage area other than the n storage areas, and the storage device abnormality detecting device further includes:

第一读取模块，用于每隔预设时间段对所述第一存储区域进行所述读操作；a first reading module, configured to perform the reading operation on the first storage area every preset time period;

或者，or,

第二读取模块，用于在所述其他存储区域满足判断触发条件时，对所述第一存储区域进行所述读操作，所述判断触发条件包括：对所述其他存储区域的读操作失败，从所述其他存储区域中读取到的文件错误，以及对所述其他存储区域的写操作失败中的至少一种条件。a second reading module, configured to perform the read operation on the first storage area when the other storage area satisfies a judgment trigger condition, where the determining trigger condition comprises: a read operation on the other storage area fails At least one of a file error read from the other storage area and a write operation failure to the other storage area.
根据权利要求9所述的存储设备异常检测装置，其特征在于，m＝n。A storage device abnormality detecting apparatus according to claim 9, wherein m = n.
一种分布式存储***，其特征在于，所述分布式存储***包括管理设备与多个存储设备，所述管理设备包括：权利要求9-16任一所述的存储设备异常检测装置。A distributed storage system, comprising: a management device and a plurality of storage devices, the management device comprising: the storage device abnormality detecting device according to any one of claims 9-16.
一种计算机设备，其特征在于，包括：A computer device, comprising:

一个或多个处理器；和One or more processors; and

存储器；Memory

所述存储器存储有一个或多个程序，所述一个或多个程序被配置成由所述一个或多个处理器执行，以执行权利要求1-8任一所述的存储设备异常检测方法。The memory stores one or more programs, the one or more programs being configured to be executed by the one or more processors to perform the storage device anomaly detection method of any of claims 1-8.
一种非易失性的计算机可读存储介质，其特征在于，所述存储介质中存储有代码指令，所述代码指令由处理器执行，以执行权利要求1-8任一所述的存储设备异常检测方法。A non-transitory computer readable storage medium, wherein the storage medium stores code instructions, the code instructions being executed by a processor to perform the storage device of any of claims 1-8 Anomaly detection method.