WO2022151856A1 - 一种异构存储卷在线接管的方法、系统、设备及介质 - Google Patents

一种异构存储卷在线接管的方法、系统、设备及介质 Download PDF

Info

Publication number
WO2022151856A1
WO2022151856A1 PCT/CN2021/134548 CN2021134548W WO2022151856A1 WO 2022151856 A1 WO2022151856 A1 WO 2022151856A1 CN 2021134548 W CN2021134548 W CN 2021134548W WO 2022151856 A1 WO2022151856 A1 WO 2022151856A1
Authority
WO
WIPO (PCT)
Prior art keywords
storage
volume
host
label
data
Prior art date
Application number
PCT/CN2021/134548
Other languages
English (en)
French (fr)
Inventor
孙先宁
Original Assignee
苏州浪潮智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州浪潮智能科技有限公司 filed Critical 苏州浪潮智能科技有限公司
Priority to US18/026,945 priority Critical patent/US11972131B2/en
Publication of WO2022151856A1 publication Critical patent/WO2022151856A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
    • G06F3/0647—Migration mechanisms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0604—Improving or facilitating administration, e.g. storage management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0604—Improving or facilitating administration, e.g. storage management
    • G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0614—Improving the reliability of storage systems
    • G06F3/0619—Improving the reliability of storage systems in relation to data integrity, e.g. data losses, bit errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
    • G06F3/0656—Data buffering arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0662—Virtualisation aspects
    • G06F3/0665—Virtualisation aspects at area level, e.g. provisioning of virtual or logical volumes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/0671—In-line storage system
    • G06F3/0683—Plurality of storage devices

Definitions

  • the present application relates to the technical field of storage devices, and in particular, to a method, system, device and medium for online takeover of heterogeneous storage volumes.
  • the layer realizes the online migration of data LUN (Logical Unit Number, logical unit number), and takes into account the uniqueness of SCSI (Small Computer System Interface, small computer system interface) device number, establishes the mapping of the corresponding relationship, and ensures that the host can identify The new storage system, but this method still needs to update the SCSI device number when the mapping relationship is established and the upper-layer business is processed. Therefore, a method is proposed to realize the change of the access storage volume at the application layer, replacing the active link. Switching avoids the conflict problem caused by the multi-path compatibility of different storage devices, and has better applicability than the prior art.
  • LUN Logical Unit Number, logical unit number
  • SCSI Small Computer System Interface
  • a technical solution adopted in this application is to provide a method for online takeover of heterogeneous storage volumes, including:
  • Execute service The host executes the upper-layer service data access through the second volume label of the second-stored storage volume. At this time, the data accessed by the upper-layer service in the second-stored storage volume enters the host's memory and becomes cached data, that is, the host side cache data;
  • Generate a volume label in response to the second storage mapping the storage volume of the second storage to the first storage according to the first mapping relationship, the first storage takes over the storage volume of the second storage, and the first storage is generated for the storage volume that has been taken over a first tag and sending the first tag to the host;
  • Flush data flush the host-side cache data corresponding to the second-stored storage volume to the second-stored storage volume, so that the host executes the upper-layer service according to the second-stored storage volume;
  • the first storage accesses the storage volume of the second storage according to the first mapping relationship, and maps the taken over storage volume of the second storage to the host according to the second mapping relationship, and the host according to the first mapping relationship and the second mapping relationship
  • the relationship between the host-side cache data corresponding to the storage volume of the second storage is flushed to the storage volume of the second storage. After the data flushing is completed, when the upper-layer service accesses the storage volume of the second storage again, the data is no longer temporarily stored on the host. Cache is performed in memory.
  • the storage volume of the second storage has the complete data required by the upper-layer business, and the host skips the host cache and directly passes the data.
  • the storage volume of the second storage performs upper-layer services.
  • switch directory switch the directory information of the upper-layer service running by the host.
  • Storage migration when the directory information of the upper-layer service is switched, migrate the data of the storage volume in the second storage to the first storage.
  • the step of storage migration may be: determining the directory information of the upper-layer service after switching is completed, and migrating the data of the storage volume in the second storage to the first storage based on the above determination.
  • the step of generating a volume label includes: the first storage enables an API function, and in response to the second storage mapping a storage volume of the second storage to the first storage according to a first mapping relationship, converting the first storage The storage volume of the second storage is taken over and a first volume label is generated for the storage volume of the second storage that has been taken over, and the first volume label is sent to the host.
  • the host-side cache data corresponding to the storage volume of the second storage includes first data and second data, and the first data is: the first storage takes over all the storage volume of the second storage.
  • the step of flushing data includes: the host scans the storage volume of the second storage that has been taken over by the first storage, and flushes the first data to the storage volume of the second storage.
  • the step of switching directories includes:
  • the host initiates the directory information switching, and based on the above determination, the first volume label is disabled, and the second volume label is enabled.
  • the first volume label is switched to the directory information of the upper layer service, and the second volume label is disabled;
  • the first volume label is enabled and the second volume label is disabled.
  • the step of migrating the storage includes: migrating the second data of the storage volume of the second storage to the first storage, and flashing the second data to the second storage The first data in the storage volume is sent to the first storage.
  • the step of migrating the storage volume of the second storage to the first storage further comprises: revoking the second volume label of the storage volume of the second storage.
  • the present application also provides a system for online takeover of heterogeneous storage volumes, which is applied to the first storage, the second storage and the host, and includes: a flashing module, a mounting module and a permission module;
  • the second storage is electrically connected to the host, the first storage is respectively connected to the second storage and the host, and the host is provided with the flashing module, the mounting module and the authority module;
  • the second storage is provided with a storage volume, and a second volume label is generated according to the storage volume;
  • the first storage takes over the storage volume and generates a first volume label for the storage volume that has been taken over, and sends the first volume label to the host;
  • the flashing module controls the host to flash the cache information corresponding to the storage volume to the storage volume of the second storage;
  • the mounting module controls the replacement of directory information of upper-layer services running on the host
  • the authority module is used to control the authority of the first volume label and the second volume label, and to control the switching of directory information for upper-layer services.
  • the permission module before the mount module initiates the replacement of the directory information of the upper-layer service, the permission module enables the second volume label, the upper-layer service realizes data interaction through the second volume label, and the permission module disables the first volume label ;
  • the authority module disables the second volume label, and switches the first volume label to the directory information of the upper-layer service
  • the authority module disables the second volume label and enables the first volume label.
  • the mount module is before the directory information replacement of the upper-layer service is initiated, and based on the above determination, the authority module enables the second label, the upper-layer service realizes data interaction through the second label, and the authority module disables the second label.
  • a volume label it is determined that the mount module initiates the replacement of the directory information of the upper-layer service, and based on the above determination, the authority module disables the second volume label, and switches the first volume label to the directory information of the upper-layer service;
  • the mounting module completes the replacement of the directory information of the upper-layer service, and based on the above determination, the authority module disables the second volume label and enables the first volume label.
  • the present application also provides a computer device, comprising a memory and one or more processors, wherein the memory stores computer-readable instructions, and the computer-readable instructions, when executed by the one or more processors, cause all The one or more processors execute the steps of any of the above-mentioned methods for online takeover of heterogeneous storage volumes.
  • the present application also provides one or more non-transitory computer-readable storage media having computer-readable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to Perform the steps of any of the methods for online takeover of heterogeneous storage volumes as described above.
  • FIG. 1 is a schematic diagram of a method for online takeover of heterogeneous storage volumes according to one or more embodiments of the present application
  • FIG. 2 is a schematic diagram of a system for online takeover of heterogeneous storage volumes according to one or more embodiments of the present application;
  • FIG. 3 is a schematic diagram of a computer device according to one or more embodiments of the present application.
  • LUN Logical Unit Number
  • SCSI Small Computer System Interface
  • SAN Storage Area Network
  • API Application Programming Interface
  • An embodiment of the present application provides a method for online takeover of heterogeneous storage volumes. Please refer to FIG. 1.
  • the above method may specifically include the following steps;
  • the host can execute the upper-layer service through the second volume label of the storage volume in the second storage when the host performs the upper-layer service, specifically, the data of the storage volume is stored in the second volume label of the second storage.
  • the upper-layer service accesses the data
  • the accessed data will first go to the cache of the host, that is, become the cached data in the host, and then the host will read and write access to the cached data.
  • the upper-layer application may be stopped or delayed, and the method provided in this embodiment can migrate the data of the storage volume of the second storage to the first storage without stopping the upper-layer application.
  • the first storage is the newly introduced storage, hereinafter referred to as the takeover storage
  • the second storage is the original storage, hereinafter referred to as the taken over storage
  • the upper-layer business may be the application-layer data read and write access business, such as database business, file system business, etc. That is to say, the host performs read and write access to data in the originally stored storage volume based on the volume label of the original stored storage volume.
  • the takeover storage When the takeover storage opens the API interface to the taken over storage, the taken over storage maps the heterogeneous storage volumes to take over storage through the SAN line, the takeover storage receives the mapping relationship of the heterogeneous storage volumes, and the takeover storage is completed through the mapping relationship Read and write data on heterogeneous storage volumes, take over storage, manage the storage volumes that have been taken over storage, and map the managed storage volumes to the host.
  • the host When the host receives the storage volume mapping relationship, it scans the storage disk that takes over the storage, the host starts to use the storage volume that has been taken over for storage, and starts to flush the cached data of the storage volume in the host memory. In this way, the host can process upper-layer applications.
  • the volume migration process is not completed, the upper-layer application is not stopped, and the cached data in the host memory of the flushed storage volume is stored in the second storage.
  • the volume migration process When the volume migration process is not completed, the host's memory will no longer process the upper-layer application.
  • data of heterogeneous storage volumes is incomplete.
  • the host Before the upper-layer application volume label replacement command is initiated, the host will disable the storage volume that takes over the storage managed by mapping the storage volume of the host to the storage volume label of the host, and enable the read and write permissions of the storage volume corresponding to the storage volume that is directly mapped to the host's storage volume;
  • the host When the upper-layer application volume label replacement command is initiated, the host will disable the storage volume corresponding to the storage volume directly mapped to the host by the takeover storage, and write the storage volume mapped to the host through the takeover storage into the upper-layer application directory;
  • the read and write permissions of the storage volume corresponding to the storage volume label mapped to the host through the takeover storage are activated, and the read and write permissions corresponding to the storage volume label of the taken over storage directly mapped to the host are prohibited.
  • the takeover storage After completing the entry of the storage volume label in the upper-layer application directory of S3, the takeover storage uses the volume migration function to make the taken over storage migrate the storage volume. After the volume migration is completed, the volume takeover process ends. The memory of the host restarts to cache the interaction data between the storage volume and the upper-layer service.
  • the migration of the entire heterogeneous storage volume can be completed without interrupting the upper-layer service, and the upper-layer application can identify the storage volume label, and there is no need to communicate the label of the SCSI device with the host.
  • the method for online takeover of heterogeneous storage volumes provided in the above-mentioned embodiments can realize switching at the application layer instead of switching at the link layer, avoid the conflict problem caused by the multi-path compatibility of storage devices between different manufacturers, and in the host computer. Brushing the data of the storage volume can avoid the stoppage or delay of the upper-layer application caused by switching the storage cluster.
  • An embodiment of the present application provides a system for online takeover of heterogeneous storage volumes, please refer to FIG. 2 , including;
  • the refresh module 201 is used to refresh the cache in the memory of the upper-layer application running host. It should be noted that at this time, the taken over storage and the host perform storage volume mapping, and the taken over storage and the host also perform storage volume mapping, but these two The mapping of the corresponding relationship is not the same, because the taken over storage performs the storage volume mapping by taking over the storage. The label of each SCSI device is different, so the mapping relationship is also different.
  • the taken over storage is completed, the managed storage is taken over.
  • the host scans the storage disk that takes over the storage, and the host undertakes the upper-layer business processing and data caching that takes over the storage. In this way, the upper-layer business can be uninterrupted and the data integrity of the heterogeneous storage volume during the migration process is guaranteed. sex.
  • the mount module 202 is used to change the storage volume label recorded in the upper-layer service directory, because the upper-layer service needs to use the storage volume label to perform the corresponding task when executing, otherwise the upper-layer service cannot know the reading position and storage position of the data, When the location of the storage volume changes from being taken over to taking over storage, the storage volume label changes. Therefore, it is necessary to let the upper-layer application change the previously saved storage volume label. In this way, the storage volume label of the upper-layer business storage directory can be switched.
  • the steps require the cooperation of the authority module 203;
  • the permission module 203 prohibits the use of the storage volume label mapped to the host through the storage management, and enables the storage volume mapped to the host through the storage management;
  • the storage volume label of the storage volume directly mapped to the host is stopped from being used, and the storage volume label of the storage volume managed by the takeover storage is switched to the directory of the upper-layer application. , completes the mapping relationship of the upper-layer application to identify the storage volume that takes over the storage management;
  • the permission module 203 starts to take over the read and write permissions of the storage volume managed by the storage, and prohibits the read and write permissions of the storage volume directly from the taken over storage to the host.
  • the system for online takeover of heterogeneous storage volumes provided in the above embodiment can realize switching of different volume labels corresponding to different mapping relationships of storage volumes in different storage clusters, and management of permissions, and can perfectly realize the upper-layer application.
  • the directory information is switched to different labels, and the upper-layer application does not need to be stopped.
  • FIG. 3 An embodiment of the present application also provides a computer device, please refer to FIG. 3 , which includes a memory 301 and one or more processors 302 .
  • the memory 301 stores computer-readable instructions, and the computer-readable instructions are When the one or more processors 302 are executed, the one or more processors 302 are caused to execute the steps of any of the above-mentioned methods for online takeover of heterogeneous storage volumes.
  • a host adapter card such as a network card, a Fibre Channel card, etc., for connecting to a third-party storage system and connecting to a host server.
  • the computer device provided in the above embodiment can realize the generation of storage volume labels of storage volumes in different storage scenarios, and can migrate the storage volumes from the second storage to the storage volume after the directory information of the upper-layer application completes the volume label switching. first store.
  • the embodiments of the present application further provide one or more non-volatile computer-readable storage media storing computer-readable instructions, wherein the computer-readable instructions are stored by one or more non-volatile computer-readable storage media.
  • the one or more processors are caused to execute the steps of any of the foregoing methods for online takeover of heterogeneous storage volumes.
  • the non-volatile computer-readable storage medium provided in the above embodiment can switch the directory information of the upper-layer application, and switch the first volume label to the directory information.
  • the storage medium can be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种异构存储卷在线接管的方法，包括：执行业务：主机通过第二存储的存储卷的第二卷标执行上层业务数据访问；生成卷标：第一存储接管第二存储的存储卷，为已接管的存储卷生成第一卷标；下刷数据：下刷第二存储的存储卷对应的主机端缓存数据至第二存储的存储卷；切换目录：切换主机运行的上层业务的目录信息；存储迁移：当完成切换上层业务的目录信息时，将上述存储卷的数据迁移至第一存储。

Description

一种异构存储卷在线接管的方法、系统、设备及介质
相关申请的交叉引用
本申请要求于2021年1月13日提交中国专利局，申请号为202110044015.8，申请名称为“一种异构存储卷在线接管的方法、系统、设备及介质”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。
技术领域
本申请涉及存储设备技术领域，特别是涉及一种异构存储卷在线接管的方法、系统、设备及介质。
背景技术
针对异构存储卷在线数据迁移，存在一种技术：将与主机连接的新存储系统连接至原存储系统，并获取原存储系统的设备信息，将原存储系统的设备信息映射到主机，并将新存储系统与主机连接的链路设置为活动链路，实现数据通过活动链路在原存储系统到主机的在线迁移，实现原存储系统的数据在线迁移至新存储系统，此技术方案在数据链路层实现了数据LUN(Logical Unit Number，逻辑单元号)的在线迁移，并考虑到了SCSI(Small Computer System Interface，小型计算机系统接口)设备编号的唯一性，建立对应关系的映射，保证了主机可以识别新存储系统，但是此方法在建立完成映射关系完成上层业务的处理时，还是要进行SCSI设备编号的更新，所以提出一种方法，在应用层实现访问存储卷的变更，替代了活动链路的切换，避免了不同存储设备多路径兼容导致的冲突问题，相比于现有技术，可适用性更好。
发明内容
本申请采用的一个技术方案是：提供一种异构存储卷在线接管的方法，包括：
执行业务：主机通过第二存储的存储卷的第二卷标执行上层业务数据访问，此时，上层业务在第二存储的存储卷中访问的数据进入主机的内存成为缓存数据，也即主机侧缓存数据；
生成卷标：响应于第二存储根据第一映射关系将第二存储的存储卷映射到第一存 储，第一存储接管所述第二存储的存储卷，第一存储为已接管的存储卷生成第一卷标并将该第一卷标发送至所述主机；
下刷数据：下刷所述第二存储的存储卷对应的主机侧缓存数据至第二存储的存储卷，以使主机根据第二存储的存储卷执行所述上层业务；
其中，第一存储根据第一映射关系对第二存储的存储卷进行访问，并根据第二映射关系将已接管的第二存储的存储卷映射到主机，主机根据第一映射关系和第二映射关系将第二存储的存储卷对应的主机侧缓存数据下刷至第二存储的存储卷，下刷数据完成后，上层业务再次访问第二存储的存储卷时，不再将数据临时放在主机内存中进行缓存，此时，上层业务需访问的所有数据都来自第二存储的存储卷，也就是说，第二存储的存储卷具备上层业务所需的完整数据，主机跳过主机缓存直接通过第二存储的存储卷执行上层业务。
切换目录：切换所述主机运行的所述上层业务的目录信息；及
存储迁移：当完成切换所述上层业务的目录信息时，将所述第二存储的存储卷的数据迁移至第一存储。
即存储迁移的步骤可以为：确定切换完成所述上层业务的目录信息，基于上述确定，将第二存储的存储卷的数据迁移至第一存储。
在一些实施例中，所述生成卷标的步骤包括：所述第一存储开启API功能，响应于第二存储根据第一映射关系将第二存储的存储卷映射到第一存储，将所述第二存储的存储卷进行接管并为已接管的第二存储的存储卷生成第一卷标，及将第一卷标发送到所述主机。
在一些实施例中，所述第二存储的存储卷对应的主机侧缓存数据包括第一数据和第二数据，所述第一数据为：在所述第一存储接管所述第二存储的所述存储卷后，所述存储卷接收的数据；所述第二数据为：在所述第一存储接管所述第二存储的所述存储卷前，所述存储卷接收的数据；所述下刷数据的步骤包括：所述主机扫描所述第一存储已接管的所述第二存储的所述存储卷，并将所述第一数据下刷到所述第二存储的存储卷中。
在一些实施例中，所述切换目录的步骤包括：
当所述主机发起所述目录信息切换时，禁用所述第一卷标，并启用所述第二卷标；
即确定所述主机发起所述目录信息切换，基于上述确定，禁用所述第一卷标，并启用所述第二卷标。
当所述主机开始所述目录信息切换时，将所述第一卷标切换到所述上层业务的所述 目录信息中，并禁用所述第二卷标；及
当所述主机完成所述目录信息切换时，启用所述第一卷标，并禁用所述第二卷标。
也就是说，确定所述主机开始所述目录信息切换，基于上述确定，将所述第一卷标切换到所述上层业务的所述目录信息中，并禁用所述第二卷标；以及，确定所述主机完成所述目录信息切换，基于上述确定，启用所述第一卷标，并禁用所述第二卷标。
在一些实施例中，所述存储迁移的步骤包括：将所述第二存储的所述存储卷的所述第二数据迁移至所述第一存储，并将已下刷至所述第二存储的存储卷中的所述第一数据发送至所述第一存储。
在一些实施例中，所述将所述第二存储的所述存储卷迁移至所述第一存储的步骤还包括：撤销所述第二存储的所述存储卷的所述第二卷标。
本申请还提供一种异构存储卷在线接管的系统，应用于第一存储、第二存储和主机，包括：下刷模块、挂载模块和权限模块；
所述第二存储与所述主机电连接，所述第一存储分别与所述第二存储和所述主机相连，所述主机设有所述下刷模块、挂载模块和权限模块；
所述第二存储设有存储卷，并根据存储卷生成第二卷标；
所述第一存储接管所述存储卷且为已接管的所述存储卷生成第一卷标，并将所述第一卷标发送至主机；
所述下刷模块控制主机下刷所述存储卷对应的缓存信息至所述第二存储的存储卷；
所述挂载模块控制所述主机上运行的上层业务的目录信息更换；
所述权限模块用于控制第一卷标和第二卷标的权限，并控制上层业务实现目录信息的切换。
在一些实施例中，当挂载模块发起上层业务的目录信息更换前，所述权限模块启用第二卷标，上层业务通过第二卷标实现数据的交互，所述权限模块禁用第一卷标；
当挂载模块发起上层业务的目录信息更换时，所述权限模块禁用第二卷标，并将第一卷标切换到所述上层业务的目录信息中；及
当挂载模块完成上层业务的目录信息更换时，所述权限模块禁用第二卷标，并启用第一卷标。
也就是说，确定挂载模块处于发起上层业务的目录信息更换前，基于上述确定，所述权限模块启用第二卷标，上层业务通过第二卷标实现数据的交互，所述权限模块禁用第一卷标；确定挂载模块发起上层业务的目录信息更换，基于上述确定，所述权限模块禁用第二卷标，并将第一卷标切换到所述上层业务的目录信息中；及
确定挂载模块完成上层业务的目录信息更换，基于上述确定，所述权限模块禁用第二卷标，并启用第一卷标。
本申请还提供一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行如上所述的任一种异构存储卷在线接管的方法的步骤。本申请还提供一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如上所述的任一种异构存储卷在线接管的方法的步骤。本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施方式，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。
图1是本申请的一个或多个实施例所述的异构存储卷在线接管的方法的示意图；
图2是本申请的一个或多个实施例所述的异构存储卷在线接管的系统的示意图；
图3是本申请的一个或多个实施例所述的计算机设备的示意图。
具体实施方式
下面将结合附图对本申请的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
需要说明的是，在本申请的描述中，如LUN(Logical Unit Number)是逻辑单元号、SCSI(Small Computer System Interface)是小型计算机系统接口、SAN(Storage Area Network)是存储区域网络、API(Application Programming Interface)是应用程序编程接口。
实施例1
本申请的实施例提供一种异构存储卷在线接管的方法，请参阅图1，上述方法具体可包括以下步骤；
S1、接管存储开启API接口，实现不同存储设备的异构；
由于主机在执行上层业务时，可以通过第二存储的存储卷的第二卷标执行上层业务，具体地，存储卷的数据存放在第二存储的第二卷标中，当上层业务访问数据时，被访问的这部分数据会先到主机的缓存中，即成为主机中的缓存数据，然后主机对该缓存数据进行读写访问。如果此时切换存储集群，可能会导致上层应用的停止或延迟，而采用本实施例中提供的方法可以将第二存储的存储卷的数据迁移到第一存储上，而且不需要停止上层应用。
其中，第一存储为新引入的存储，以下称为接管存储，第二存储为原有的存储，以下称为被接管存储；上层业务可为应用层数据读写访问业务，如数据库业务、文件系统业务等。也就是说，主机基于原有存储的存储卷的卷标对原有存储的存储卷中的数据进行读写访问。
需要说明的是，如何通过API接口，实现接管存储到被接管存储异构虚拟化功能，实现接管存储于被接管存储通过SAN线路进行数据交互，此方法为现有技术，不需要进行讨论；
当接管存储对被接管存储开启API接口后，被接管存储通过SAN线路，将需要进行异构的存储卷映射至接管存储，接管存储接收到异构存储卷的映射关系，接管存储通过映射关系完成对异构存储卷的数据读写，接管存储将被接管存储的存储卷进行纳管，并将纳管后的存储卷映射到主机。
S2、主机下刷存储卷缓存；
主机接收到存储卷映射关系时，扫描接管存储的存储磁盘，主机开始使用被接管存储的储存卷，并开始下刷存储卷在主机内存中的缓存数据，通过这种方式实现了主机处理上层应用时，不停止上层应用，将下刷的存储卷在主机内存中的缓存数据存储至第二存储中，在未完成卷迁移过程时，主机的内存不再进行上层应用的处理，，防止在卷迁移过程中，出现异构存储卷数据不完整的现象。
S3、上层应用卷标更换；
需要说明的是，本步骤与S2几乎同时进行，但是为了描述更加清楚，将S3作为独立的步骤，所以S2和S3的步骤不分先后，同样要说明的是，S2和S3步骤的先后顺序并不是本申请需要保护的范畴，在主机接收到存储卷映射时，主机发起上层应用卷标更换指令；
在上层应用卷标更换指令发起前，主机将接管存储纳管的存储卷映射到主机的存储卷标禁用，将被接管存储直接映射到主机的存储卷标对应的存储卷开启读写权限；
在上层应用卷标更换指令发起时，主机将被接管存储直接映射到主机的存储卷标对应的存储卷禁用，将通过接管存储映射到主机的存储卷标写入上层应用目录中；
在上层应用卷标更换指令发起完成后，启动通过接管存储映射到主机的存储卷标对应存储卷的读写权限，禁止被接管存储直接映射到主机的存储卷标对应的读写权限。
S4、卷迁移；
当完成S3的上层应用的目录对于存储卷标的录入后，接管存储使用卷迁移功能令被接管存储将存储卷迁移，在完成卷迁移后，卷接管过程结束。主机的内存重新开始缓存存储卷与上层业务的交互数据。
通过上述步骤，实现了不中断上层业务，完成整个异构存储卷的迁移，而且上层应用可以识别存储卷标，可以不需要另外与主机沟通SCSI设备的标号。
上述实施例中提供的一种异构存储卷在线接管的方法，可以实现在应用层的切换替代了链路层的切换，避免了不同厂商间存储设备多路径兼容导致的冲突问题，而且在主机进行对存储卷的数据进行下刷，可以避免上层应用因切换存储集群造成的停止，或者延迟。
实施例2
本申请的实施例提供一种异构存储卷在线接管的系统，请参阅图2，包括；
下刷模块201、挂载模块202和权限模块203；
下刷模块201用于下刷上层应用运行主机的内存中的缓存，需要说明的是，此时被接管存储与主机进行存储卷的映射，接管存储与主机也进行存储卷的映射，但是这两种对应关系的映射是不相同的，因为被接管存储通过接管存储进行了存储卷的映射，每一个SCSI设备的标号是不同的，所以映射关系也是不同的，当接管存储完成纳管被接管存储的存储卷时，主机扫描接管存储的存储磁盘，主机承接接管存储的上层业务处理与数据缓存，通过这种方式，可以使上层业务不中断，保证了异构存储卷在迁移过程中的数据完整性。
挂载模块202用于更改上层业务目录所记录的存储卷标，因为上层业务在执行时，需要用到存储卷标来执行相应的任务，否则上层业务无法知道数据的读取位置以及存储位置，当存储卷所在位置由被接管存储到接管存储转变时，存储卷标发生变化，所以，需要让上层应用更改以前保存的存储卷标，通过这种方式实现上层业务存目录储卷标的切换，具体步骤需要权限模块203进行配合；
首先在主机发起存储卷标切换之前，权限模块203将通过存储纳管映射主机的存储卷标禁止使用，将通过被存储纳管映射到主机的存储卷标可使用；
然后在主机发起存储卷标切换时，被接管存储直接映射到主机的储存卷标停止使用，将被接管存储通过接管存储纳管的存储卷的存储卷标切换到上层应用的目录中，此时，完成了上层应用识别接管存储纳管的存储卷的映射关系；
最后在主机存储卷标切换完成后，权限模块203启动接管存储纳管的存储卷的读写权限，禁止被接管存储直接到主机的存储卷的读写权限。
上述实施例中提供的一种异构存储卷在线接管的系统，可以实现对存储卷在不同存储集群的不同映射关系对应的不同卷标的切换，以及权限的管理，并且可以完美的实现上层应用的目录信息对于不同卷标的切换，并且不需要停止上层应用。
实施例3
本申请的实施例还提供的一种计算机设备，请参阅图3，包括存储器301及一个或多个处理器302，所述存储器301中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器302执行时，使得所述一个或多个处理器302执行如上所述的任一种异构存储卷在线接管的方法的步骤。
除了上述存储器301和处理器302之外，还包括主机适配卡，如网卡、Fibre Channel卡等用于连接第三方存储系统和连接主机服务器。
上述实施例中提供的一种计算机设备，可以实现在不同存储场景的存储卷的存储卷卷标的生成，而且可以在上层应用的目录信息完成卷标切换后，将存储卷由第二存储迁移至第一存储。
基于与前述实施例中方法同样的发明构思，本申请的实施例还提供一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如上所述的任一种异构存储卷在线接管的方法的步骤。
上述实施例中提供的一种非易失性计算机可读存储介质，可以实现切换上层应用的目录信息，将第一卷标切换到目录信息中。
上述本申请实施例公开实施例序号仅仅为了描述，不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上所述仅为本申请的实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (10)

  1. 一种异构存储卷在线接管的方法，其特征在于，包括：
    执行业务：主机通过第二存储的存储卷的第二卷标执行上层业务，所述上层业务在所述第二存储的存储卷中所访问的数据进入所述主机的内存成为主机侧缓存数据；
    生成卷标：响应于所述第二存储根据第一映射关系将所述第二存储的存储卷映射到第一存储，所述第一存储接管所述第二存储的存储卷，所述第一存储为已接管的所述第二存储的存储卷生成第一卷标并将所述第一卷标发送至所述主机；
    下刷数据：所述第一存储根据所述第一映射关系对所述第二存储的存储卷进行访问，并根据第二映射关系将已接管的所述第二存储的存储卷映射到所述主机，所述主机根据所述第一映射关系和所述第二映射关系将所述第二存储的存储卷对应的主机侧缓存数据下刷至所述第二存储的存储卷，所述主机跳过主机缓存直接通过所述第二存储的存储卷执行所述上层业务；
    切换目录：切换所述主机运行的所述上层业务的目录信息；及
    存储迁移：当完成切换所述上层业务的目录信息时，将所述第二存储的存储卷的数据迁移至所述第一存储。
  2. 根据权利要求1所述的方法，其特征在于：所述生成卷标的步骤包括：所述第一存储开启API功能，响应于所述第二存储根据第一映射关系将所述第二存储的存储卷映射到所述第一存储，将所述第二存储的存储卷进行接管，为已接管的所述第二存储的存储卷生成第一卷标，及将所述第一卷标发送到所述主机。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第二存储的存储卷对应的主机侧缓存数据包括第一数据和第二数据，所述第一数据为：在所述第一存储接管所述第二存储的存储卷后，所述存储卷接收的数据；所述第二数据为：在所述第一存储接管所述第二存储的存储卷前，所述存储卷接收的数据；所述下刷数据的步骤包括：所述主机扫描所述第一存储已接管的所述第二存储的存储卷，并将所述第一数据下刷到所述第二存储的存储卷中。
  4. 根据权利要求1-3任意一项所述的方法，其特征在于：所述切换目录的步骤包括：
    当所述主机发起所述目录信息切换时，禁用所述第一卷标，并启用所述第二卷标；
    当所述主机开始所述目录信息切换时，将所述第一卷标切换到所述上层业务的所述目录信息中，并禁用所述第二卷标；及
    当所述主机完成所述目录信息切换时，启用所述第一卷标，并禁用所述第二卷标。
  5. 根据权利要求3所述的方法，其特征在于：所述存储迁移的步骤包括：将所述第二存储的存储卷的所述第二数据迁移至所述第一存储，并将已下刷至所述第二存储的存储卷中的所述第一数据发送至所述第一存储。
  6. 根据权利要求5所述的方法，其特征在于：所述将所述第二存储的存储卷的所述第二数据迁移至所述第一存储，还包括：撤销所述第二存储的存储卷的所述第二卷标。
  7. 一种异构存储卷在线接管的系统，应用于第一存储、第二存储和主机，其特征在于，包括：下刷模块、挂载模块和权限模块；
    所述第二存储与所述主机电连接，所述第一存储分别与所述第二存储和所述主机相连，所述主机设有所述下刷模块、挂载模块和权限模块；
    所述第二存储设有存储卷，并根据所述存储卷生成第二卷标；
    所述第一存储接管所述存储卷且为已接管的所述存储卷生成第一卷标，并将所述第一卷标发送至所述主机；
    所述下刷模块控制所述主机下刷所述存储卷对应的缓存信息至所述第二存储的存储卷；
    所述挂载模块控制所述主机上运行的上层业务的目录信息更换；
    所述权限模块用于控制所述第一卷标和所述第二卷标的权限，并控制所述上层业务实现所述目录信息的切换。
  8. 根据权利要求7所述的系统，其特征在于：当所述挂载模块发起所述上层业务的所述目录信息更换前，所述权限模块启用所述第二卷标，所述上层业务通过所述第二卷标实现数据的交互，所述权限模块禁用所述第一卷标；
    当所述挂载模块发起所述上层业务的所述目录信息更换时，所述权限模块禁用所述第二卷标，并将所述第一卷标切换到所述上层业务的所述目录信息中；及
    当所述挂载模块完成所述上层业务的所述目录信息更换时，所述权限模块禁用所述第二卷标，启用所述第一卷标。
  9. 一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行如权利要求1-6任意一项所述方法的步骤。
  10. 一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如权利要求1-6任意一项所述方法的步骤。
PCT/CN2021/134548 2021-01-13 2021-11-30 一种异构存储卷在线接管的方法、系统、设备及介质 WO2022151856A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/026,945 US11972131B2 (en) 2021-01-13 2021-11-30 Online takeover method and system for heterogeneous storage volume, device, and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110044015.8 2021-01-13
CN202110044015.8A CN112732195B (zh) 2021-01-13 2021-01-13 一种异构存储卷在线接管的方法、系统、设备及介质

Publications (1)

Publication Number Publication Date
WO2022151856A1 true WO2022151856A1 (zh) 2022-07-21

Family

ID=75592501

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/134548 WO2022151856A1 (zh) 2021-01-13 2021-11-30 一种异构存储卷在线接管的方法、系统、设备及介质

Country Status (3)

Country Link
US (1) US11972131B2 (zh)
CN (1) CN112732195B (zh)
WO (1) WO2022151856A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112732195B (zh) 2021-01-13 2022-09-20 苏州浪潮智能科技有限公司 一种异构存储卷在线接管的方法、系统、设备及介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1367440A (zh) * 2001-07-31 2002-09-04 智权第一公司 在使用卷标的管线化微处理器中执行结合写入的装置及方法
US20200034077A1 (en) * 2018-07-30 2020-01-30 EMC IP Holding Company LLC Unified approach to import, replication, and migration of a storage volume
CN111078368A (zh) * 2019-12-26 2020-04-28 浪潮电子信息产业股份有限公司 云计算平台虚拟机的内存快照方法、装置及可读存储介质
CN111259020A (zh) * 2020-01-10 2020-06-09 苏州浪潮智能科技有限公司 一种校验多存储卷拷贝一致性的方法、系统、设备及介质
CN111580753A (zh) * 2020-04-30 2020-08-25 中国工商银行股份有限公司 存储卷级联架构、批量作业处理系统和电子设备
CN112732195A (zh) * 2021-01-13 2021-04-30 苏州浪潮智能科技有限公司 一种异构存储卷在线接管的方法、系统、设备及介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5819296A (en) * 1996-10-31 1998-10-06 Veritas Software Corporation Method and apparatus for moving large numbers of data files between computer systems using import and export processes employing a directory of file handles
US6832289B2 (en) * 2001-10-11 2004-12-14 International Business Machines Corporation System and method for migrating data
US7424592B1 (en) * 2004-07-30 2008-09-09 Symantec Operating Corporation System and method for implementing volume sets in a storage system
US9058119B1 (en) * 2010-01-11 2015-06-16 Netapp, Inc. Efficient data migration
WO2012011157A1 (en) * 2010-07-23 2012-01-26 Hitachi, Ltd. Data storage system and method for controlling a data storage system
CN107704206B (zh) * 2017-10-09 2020-09-18 苏州浪潮智能科技有限公司 在线迁移异构系统数据的方法、装置、设备和存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1367440A (zh) * 2001-07-31 2002-09-04 智权第一公司 在使用卷标的管线化微处理器中执行结合写入的装置及方法
US20200034077A1 (en) * 2018-07-30 2020-01-30 EMC IP Holding Company LLC Unified approach to import, replication, and migration of a storage volume
CN111078368A (zh) * 2019-12-26 2020-04-28 浪潮电子信息产业股份有限公司 云计算平台虚拟机的内存快照方法、装置及可读存储介质
CN111259020A (zh) * 2020-01-10 2020-06-09 苏州浪潮智能科技有限公司 一种校验多存储卷拷贝一致性的方法、系统、设备及介质
CN111580753A (zh) * 2020-04-30 2020-08-25 中国工商银行股份有限公司 存储卷级联架构、批量作业处理系统和电子设备
CN112732195A (zh) * 2021-01-13 2021-04-30 苏州浪潮智能科技有限公司 一种异构存储卷在线接管的方法、系统、设备及介质

Also Published As

Publication number Publication date
CN112732195B (zh) 2022-09-20
US20230359384A1 (en) 2023-11-09
US11972131B2 (en) 2024-04-30
CN112732195A (zh) 2021-04-30

Similar Documents

Publication Publication Date Title
JP5459811B2 (ja) 仮想ストレージ移行のための方法およびシステム、ならびに仮想マシンモニタ
US7269667B2 (en) Disk array system and method for migrating from one storage system to another
US9043560B2 (en) Distributed cache coherency protocol
US8924664B2 (en) Logical object deletion
CN110998562B (zh) 在分布式集群系统中隔开节点
KR101250574B1 (ko) 네트워크 부트 시스템
JP4808275B2 (ja) ネットワークブートシステム
US8131671B2 (en) Uninterrupted data access during the migration of data between physical file systems
US9652471B1 (en) Intelligent file system with transparent storage tiering
US20070156763A1 (en) Storage management system and method thereof
US11314639B2 (en) Protecting against data loss during garbage collection
US11188231B2 (en) Data placement on storage devices
WO2022151856A1 (zh) 一种异构存储卷在线接管的方法、系统、设备及介质
US10120578B2 (en) Storage optimization for write-in-free-space workloads
US10025521B2 (en) Obtaining additional data storage from another data storage system
CN112711469A (zh) 云主机迁移方法、装置、计算机设备和存储介质
CN111913664B (zh) 一种数据写入方法及装置
CN107944010A (zh) 一种分布式文件系统中读写文件的方法和装置
CN113590309B (zh) 一种数据处理方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21919047

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21919047

Country of ref document: EP

Kind code of ref document: A1