WO2012109876A1 - 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统 - Google Patents

虚拟化数据备份方法、虚拟化数据重组方法、装置及系统 Download PDF

Info

Publication number
WO2012109876A1
WO2012109876A1 PCT/CN2011/077945 CN2011077945W WO2012109876A1 WO 2012109876 A1 WO2012109876 A1 WO 2012109876A1 CN 2011077945 W CN2011077945 W CN 2011077945W WO 2012109876 A1 WO2012109876 A1 WO 2012109876A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
node
software layer
virtualization software
virtual machine
Prior art date
Application number
PCT/CN2011/077945
Other languages
English (en)
French (fr)
Inventor
俞洲
王少勇
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN201180001517.7A priority Critical patent/CN102317910B/zh
Priority to PCT/CN2011/077945 priority patent/WO2012109876A1/zh
Publication of WO2012109876A1 publication Critical patent/WO2012109876A1/zh
Priority to US13/687,833 priority patent/US9547605B2/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/16Protection against loss of memory contents
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14Error detection or correction of the data by redundancy in operation
    • G06F11/1402Saving, restoring, recovering or retrying
    • G06F11/1446Point-in-time backing up or restoration of persistent data
    • G06F11/1458Management of the backup or restore process
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14Error detection or correction of the data by redundancy in operation
    • G06F11/1479Generic software techniques for error detection or fault masking
    • G06F11/1482Generic software techniques for error detection or fault masking by means of middleware or OS functionality
    • G06F11/1484Generic software techniques for error detection or fault masking by means of middleware or OS functionality involving virtual machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14Error detection or correction of the data by redundancy in operation
    • G06F11/1402Saving, restoring, recovering or retrying
    • G06F11/1446Point-in-time backing up or restoration of persistent data
    • G06F11/1456Hardware arrangements for backup

Definitions

  • the present invention relates to the field of communications technologies, and in particular, to a virtualized data migration or backup method, a virtualized data recombination method, apparatus, and system.
  • the virtualization technology is a technology that abstracts and reassembles the hardware of the computer system, and there is a layer of virtualization software layer running between the computer hardware platform and the operating system.
  • the virtualization software layer is generally referred to as a hypervisor, which can be implemented. Run multiple operating systems arbitrarily on multiple computer hardware platforms.
  • the inventors of the present invention have found that in the existing implementation manner, when each virtual machine in the data center has direct contact with each other, the operating state has a dependency relationship, if the data center is per A separate system (corresponding to a virtual machine) is backed up and then restored separately. The process is complicated and prone to operational errors, resulting in the data center of the backup being inconsistent with the original data center system.
  • the data center system may be composed of multiple computing nodes.
  • the dynamic data (memory information) of each virtual machine may be distributed on different computing nodes.
  • the backup data may be run by the virtual machine. Other virtual machines on the node have an impact. Summary of the invention
  • the embodiments of the present invention provide a virtualized data migration or backup method, a virtualized data reorganization method, device, and system, to solve the technical problem of uniformly backing up data on all virtual machines in a data center, so as to improve backup efficiency. .
  • an embodiment of the present invention provides a virtualized data migration or backup method, where the method includes: a virtualization software layer node receiving an instruction for data migration or backup; Exporting, by the virtualization software layer node, data stored on each virtual machine in the virtualization software layer node to a storage device according to the instruction;
  • the virtualization software layer node sends configuration information of each virtual machine to the backup management node, so that the backup management node recombines the data in the storage device according to the configuration information.
  • the embodiment of the present invention further provides a method for reorganizing a virtualized data, the method comprising: the backup management node acquiring configuration information of each virtual machine in at least one virtualization software layer node; and the backup management node according to the configuration information of the virtual machine
  • the data in the storage device connected thereto is recombined, wherein the storage device stores data stored on each of the at least one virtualization software layer node.
  • an embodiment of the present invention provides a virtualized data migration or backup apparatus, where the apparatus includes:
  • Receiving unit an instruction for receiving data migration or backup
  • an exporting unit configured to export, according to the instruction, data stored on each virtual machine in the virtualization software layer node to a storage device
  • a sending unit configured to send configuration information of each virtual machine to the backup management node, so that the backup management node recombines data in the storage device according to the configuration information.
  • the embodiment of the present invention further provides a virtualized data reorganization device, where the device is connected to a storage device, where the storage device is configured to store data stored on each virtual machine in at least one virtualization software layer node; :
  • An obtaining unit configured to acquire configuration information of each virtual machine in at least one virtualization software layer node
  • Recombining units for recombining data in the storage device according to the configuration information are Recombining units for recombining data in the storage device according to the configuration information.
  • the embodiment of the present invention further provides a virtualized data center system, where the system includes: a virtualization software layer node, configured to receive an instruction for data migration or backup, and according to the instruction, the virtualization software The data stored on each virtual machine in the layer node is exported to the storage device connected thereto;
  • a backup management node configured to acquire configuration information of each virtual machine in the virtualization software layer node, and recombine data in the storage device according to the configuration information.
  • the embodiment of the present invention can all virtual in a data center. So that you can not care about the order of virtual machine recovery when restoring data in the data center.
  • the stored data is exported from the virtualization software layer node, there is no need to notify the upper layer OS to perform backup, thereby improving data backup efficiency and reducing system logic complexity.
  • FIG. 1 is a flowchart of a virtualized data migration or backup method according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of an application example of memory data export in a virtualized data migration or backup method according to an embodiment of the present invention
  • FIG. 3 is a flowchart of a method for reorganizing data in a virtual data center according to an embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of collecting and backing up related configuration information in a virtual data center by a backup management node according to an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of a virtualized data migration or backup apparatus according to an embodiment of the present disclosure
  • FIG. 6 is a schematic structural diagram of a virtualized data recombining apparatus according to an embodiment of the present invention
  • FIG. 7 is a schematic structural diagram of a virtualized data center system according to an embodiment of the present invention. detailed description
  • the virtualized data center usually consists of two or more computing nodes, and each computing node runs a virtualization software layer (Hypervisor), which is called a virtualization software layer node, and the hypervisor calculates the data.
  • Hypervisor virtualization software layer
  • the physical memory, the processor, and the I/O resources on the node are abstracted and reassembled into multiple virtual computing nodes. Therefore, the hypervisor can be considered as a resource-converted conversion module.
  • the Hypervisor In a virtualized data center, only the Hypervisor has access to all compute node physical resources.
  • FIG. 1 is a flowchart of a method for virtualizing data migration or backup according to an embodiment of the present invention. the method includes:
  • Step 101 The virtualization software layer node receives an instruction for data migration or backup
  • the virtualization software layer node can receive the management node on the virtual machine, or
  • the data migration or backup command sent by the virtual machine operating system may also be an instruction for data migration or backup sent by other upper nodes.
  • Step 102 The virtualization software layer node exports the data stored in each virtual machine in the virtualization software layer node to the storage device according to the instruction.
  • the step specifically includes: the processor management unit in the virtualization software layer node stops scheduling the central processor on each virtual machine according to the instruction, and stores data on each virtual machine into the memory connected thereto;
  • the software layer node applies for a storage space in the storage device connected thereto, and records the node number of the virtualization software layer node in the storage space; and exports all the data in the memory to the storage space;
  • Step 103 The virtualization software layer node sends configuration information of each virtual machine to the backup management node, so that the backup management node recombines data in the storage device according to the configuration information.
  • all the data stored on each virtual machine under the virtualization software layer node may be exported to the storage device at one time. That is to say, the virtualization software layer node can back up the data stored on all the virtual machines in one data center at a time, so that the data center can be restored or migrated exactly the same as the original data center.
  • FIG. 2 is a schematic diagram of an application example of data storage in a virtualized data migration or backup method according to an embodiment of the present invention. The method is applied to a backup of data on a Hypervisor side in a virtual data center.
  • a data export unit (memory dump) is added to the Hypervisor, and the data export unit is used to perform the export operation on the stored data of the computing node managed by the Hypervisor.
  • this embodiment takes two computing nodes (ie, computing node 1 and computing node 2) as an example, wherein computing node 1 includes sequentially connected OS11 (ie, OS1 to OSn), Hypervisorl2, CPU13, and memory.
  • the memory unit 14 is also connected to the Hypervisor 12, wherein the Hypervisor 12 includes a data export unit 121.
  • the computing node 2 includes an OS 21 (ie, OS1 to OSn), a Hypervisor 22, and a CPU 23. memory unit 24, which are sequentially connected.
  • the memory unit 14 is also connected to the Hypervisor 12, wherein the Hypervisor 22 includes a data export unit 221.
  • the high speed storage device 3 is connected to all of the CPUs 1 and 2 in the computer 2.
  • the Hypervisor when the Hypervisor receives an instruction to migrate or back up the data sent by the OS (including any of OS1 to OSn), that is, when the system triggers the backup process; the processor management unit on the Hypervisor will stop the CPU. Scheduling, the memory unit on the Hypervisor writes all the buffered (Cache) data that is not written back on the virtual compute node back into the memory unit (Memory).
  • the Hypervisor requests a storage space in the storage device connected to it. First, write the node number where it resides into the storage space, and then export all the data in the memory unit to the storage space.
  • the storage space is recommended to use I/O storage directly connected by the CPU, that is, the high speed storage device in FIG. 2, because the server existing as the data center generally has a large amount of memory capacity, if the traditional channel is adopted.
  • the 10 Adapt is transmitted, inefficient, and takes a lot of time.
  • the storage space is not limited thereto, and may be other storage devices connected to the CPU.
  • FIG. 3 is a flowchart of a method for reorganizing a virtualized data according to an embodiment of the present invention. The method includes:
  • Step 301 The backup management node acquires configuration information of each virtual machine in at least one virtualization software layer node.
  • Step 302 The backup management node reassembles data in the storage device connected thereto according to the configuration information, where the storage device stores data stored on each virtual machine in at least one virtualization software layer node.
  • an acquisition manner is: the backup management node searches for data (ie, a memory memory file) exported from at least one virtualization software layer node, and obtains a node number of the virtualization software layer node from the memory file; Then, the backup management node obtains the node distribution information of the unified address allocation from the virtualization software layer configuration file of the virtualization software layer node according to the node number.
  • Another acquisition method is: the backup management node receives configuration information of each virtual machine that is periodically or real-time sent by at least one virtualization software layer node.
  • the re-combining the data in the storage device according to the configuration information includes: the backup management node accessing the storage device according to the memory segment address according to the obtained node distribution information of the unified address
  • the data is recombined, and the reassembled data includes the node number of the virtualization software layer node.
  • the recombination of the data in the storage device according to the memory segment address includes two recombination methods, one is to recombine the data of the storage space according to the order of the memory segment address from low to high; the other is according to the memory segment.
  • the order of the addresses from high to low recombines the data of the storage space.
  • the present invention is not limited thereto, and the data of the storage device may be re-executed from the middle of the memory segment address to the high end.
  • the foregoing embodiment is a process for exporting data of a memory by a hypervisor.
  • the backup management node (Backup Manager) needs to collect and back up related configuration information in the virtual data center, and simultaneously export data to each node. (that is, data stored in memory, also called memory data) is recombined.
  • each node that has a hypervisor is not necessarily a complete computer, it may be combined with other nodes to form a computer with a uniform address allocation. In this case, the node memory allocated by all the uniform addresses needs to be in accordance with the memory address. Space is recombined. See also Figure 4 for details.
  • FIG. 4 is a schematic structural diagram of collecting and backing up related configuration information in a virtual data center by a backup management node according to an embodiment of the present invention.
  • the backup manager 41 backs up the Hypervisor 42, the backup of the virtual machine (VM), and the backup of the network 44, wherein
  • the backup of the virtual machine (VM) 43 includes a backup of the OS image 431 and a backup of the VM profile 432.
  • the information is static information stored in the data center, and the VM is only The OS image and configuration information files can be started.
  • the backup of Hypervisor42 includes backup of CPU422 and backup of memory 421. It backs up the memory and CPU status managed by the hypervisor, which describes the dynamics of the data center. The state, that is, the running state at a certain moment, the state of the backup hypervisor can make the data center the same when it is restored.
  • the Network Backup 44 includes configuration information of the router and the switch (backup of Switch/Router profile 441 and backup of the intelligent network card configuration information 442.
  • the backup of the Switch/Router profile includes backups of their virtualized configurations. This is because each virtual machine in the data center is not independent. They often exchange data with each other through the network. If the configuration information of the network is not backed up. When the virtual machine in the data center recovers, it cannot access the network correctly. Moreover, the data center network may also be virtualized. The routers and switches seen in the virtual machine may not actually exist in the physical network. These virtual configuration information may exist in the physical switch and the physical router, and may also exist. In the intelligent network card in the data. Therefore, backing up the above information can be used to restore the network topology of the data center so that the virtual machine can access the network normally when it recovers.
  • the smart network card may also be used as a virtual switch and a virtual router carrier, it is also necessary to back up the smart network card configuration information.
  • the process of performing virtualized data migration or backup according to the information includes:
  • the virtualization software layer node hypervisor when receiving the instruction of data migration or backup, exports the data stored in each virtual machine in the virtualization software layer node to the storage device according to the instruction; the virtualization software layer node
  • the configuration information of each virtual machine is sent to the backup management node Backup Manager.
  • the configuration information of the virtual machine is the configuration information of the backup virtual machine, and may include the OS image of each virtual machine and the configuration information of the VM. It can also include other information, such as backup of Hypervisor42 and backup of Network.
  • the Backup Manager obtains configuration information of each virtual machine in at least one virtualization software layer node, that is, searches for a memory file exported by the Hypervisor, and reads the node number of the head of the memory file, that is, determines the node number where the Hypervisor is located.
  • Backup Manager Based on the node number, Backup Manager reads the node configuration information from the Hypervisor configuration file of the corresponding Hypervisor node, that is, the node distribution information of the unified address allocation.
  • the Backup Manager Based on the node configuration information, the Backup Manager reassembles the files according to the order of the memory segment addresses from low to high. The recombined files retain the node information at the time of backup and are used as reference information for recovery.
  • the Backup Manager reassembles the files according to the node configuration information in descending order of the memory segment addresses; but it is not limited thereto, and the files may be recombined in order from the middle to the high or low according to the memory segment addresses.
  • the memory segment is reorganized so that the backup can be restored to a compute node that is not the same as the original backup system memory size configuration.
  • a backup OS image may also be collected.
  • the configuration information of the virtual machine generally exists in the form of a configuration file and is stored in the same storage space as the OS image file.
  • Backup Manager needs to copy all virtual machine configuration files and OS image files to the backup storage device, and parse the virtual machine's configuration file, because each virtual machine's configuration file will describe the virtual machine's existing configuration.
  • the file stores the resources configured by the virtual machine, such as the number of CPUs, the size of the memory, the types of various I/O ports, and the connected storage devices. This information is used to restore the environment for use in the data center.
  • the information about the system hardware in the configuration file of the virtual machine is as follows:
  • Network (network configuration)
  • USB port USB port (USB port configuration)
  • the Backup Manager first determines the node number of the virtualization software layer node, obtains the configuration file of the virtual machine according to the virtualization software layer node corresponding to the node number, and then, according to the field description in the configuration file of the virtual machine, Collect all resource types and quantity information of all virtual machines and summarize them.
  • Backup Manager can access the local LAN of the virtual data center, obtain all the devices on the network by using the SNMP protocol, generate the topology map of the network, and store the topology map to the backup storage device. .
  • the topology of the network describes the logical network structure of the data center, and the logarithm of the structure It is very important that the virtual machine in the center can communicate normally. Under normal circumstances, when the network configuration information of all switches, routers, and intelligent network cards is restored, and all virtual machines are started, the restored data center should be backed up with the data center of the backup.
  • the network topology is the same. This network topology can be used to verify that the network is properly restored.
  • the Memory dump unit since the Memory dump unit is added to each Hypervisor, the unit can directly export the memory data from the Hypervisor, that is, the data on all the virtual machines in one data center can be simultaneously backed up.
  • the advantages are as follows:
  • the embodiment of the present invention further provides a virtualized data migration or backup device.
  • the structure of the device is shown in FIG. 5.
  • the device includes: a receiving unit 51, an exporting unit 52, and a sending unit 53, where
  • the receiving unit 51 is configured to receive an instruction for data migration or backup; that is, the management node on the virtual machine or the data migration or backup command sent by the virtual machine operating system may be received, but the other is not limited thereto.
  • the exporting unit 52 is configured to export data stored on each virtual machine in the virtualization software layer node to the storage device according to the instruction.
  • the method includes: a processor management unit, a plurality of memory units, a resource application unit, and a data export unit, where
  • the processor management unit is configured to stop scheduling of a central processor on each virtual machine according to the instruction
  • the plurality of memory units are configured to store data on each virtual machine separately when the processor management unit stops scheduling the central processor on each virtual machine;
  • the resource application unit is configured to apply for a storage space in a storage device connected to the virtualization software layer node, and record a node number of the virtualization software layer node in the storage space; Exporting data in the plurality of memory units into the storage space.
  • the embodiment of the present invention further provides a virtualized data reorganization device, which is shown in FIG. 6.
  • the device is connected to a storage device, and the storage device is configured to store each of at least one virtualization software layer node.
  • the data stored on the virtual machine; the device includes: an obtaining unit 61 and a recombining unit 62, wherein the obtaining unit 61 is configured to acquire configuration information of each virtual machine in the at least one virtualization software layer node;
  • the combining unit 62 is configured to re-combine data in the storage device according to the configuration information.
  • the obtaining unit includes: a searching unit and an address obtaining unit, where the searching unit is configured to search for data (such as a memory memory file) exported from a virtualization software layer node, and obtain virtualization software from the data.
  • the node number of the layer node is used to obtain the node distribution information of the unified address allocation from the virtualization software layer configuration file of the virtualization software layer node according to the node number.
  • the recombining unit is configured to recombine data of the storage device according to the memory segment address according to the acquired node distribution information of the unified address, and the recombined data includes the virtualization software layer node. Node number.
  • the embodiment of the present invention further provides a virtualized data center system, which is shown in FIG. 7.
  • the system includes: a virtualization software layer node 71 and a backup management node 72, where the virtualization software layer
  • the node 71 includes a virtualized data migration or backup device 711;
  • the backup management node 72 includes a virtualized data recombining device 721, wherein
  • the virtualization software layer node is configured to receive an instruction for data migration or backup, and export data stored in each virtual machine in the virtualization software layer node to the storage device according to the instruction; the backup management node And configured to obtain configuration information of each virtual machine in the virtualization software layer node, and recombine the data in the storage device according to the configuration information.
  • the virtualized data migration or backup device includes a receiving unit and a deriving unit, and the implementation process of the functions and functions of each unit is as described above, and details are not described herein.
  • the virtualized data recombining device includes an obtaining unit and a recombining unit, and the implementation process of the functions and functions of the respective units is as described above, and details are not described herein again.
  • the order of the virtual machine recovery may not be concerned.
  • the present invention can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in the case of more than 4, the former is better.
  • Implementation Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product in essence or in the form of a software product, which may be stored in a storage medium such as a ROM/RAM or a disk. , an optical disk, etc., includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present invention or portions of the embodiments.
  • a computer device which may be a personal computer, server, or network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种虚拟化数据迁移或备份方法、虚拟化数据重组方法、装置及系统,所述虚拟化数据迁移或备份方法包括:虚拟化软件层节点接收数据迁移或备份的指令;虚拟化软件层节点根据所述指令,将虚拟化软件层节点中的各个虚拟机上存储的数据导出到存储设备中;所述虚拟化软件层节点向备份管理节点发送各个虚拟机的配置信息,以使所述备份管理节点根据所述配置信息对所述存储设备中的数据进行重新组合。虚拟化数据重组方法包括:备份管理节点获取虚拟化软件层节点中各个虚拟机的配置信息;备份管理节点根据所述各个虚拟机的配置信息对存储空间中的数据进行重新组合。

Description

虛拟化数据^ 方法、 虚拟化数据重组方法、 装置及系统 技术领域
本发明涉及通信技术领域, 特别涉及一种虚拟化数据迁移或备份方法、虚 拟化数据重组方法、 装置及系统。
背景技术
随着通信技术的发展,越来越多的数据中心使用了虚拟化技术。 所述虚拟 化技术是一种对计算机系统硬件抽象后重新组合的技术,并且在计算机硬件平 台和操作系统之间都会有一层虚拟化软件层运行,该虚拟化软件层一般统称为 Hypervisor, 可以实现在多个计算机硬件平台上任意运行多个操作系统。
对于应用了虛拟化技术的数据中心, 不再是运行单一的操作系统 , 所以数 据中心的备份和部署也从操作系统 OS、 应用程序的备份和部署逐步变成对数 据中心上的虚拟机的备份和部署,在备份或者部署时通常采用依次备份或者部 署虚拟机的方式。 这种备份方式通常由数据中心管理软件, 通知虚拟机操作系 统来完成所有的操作。 但是, 这些备份仅限于各个虚拟机的备份, 无法备份到 虚拟机之间的关联关系。 也就是说, 各个虛拟机的备份操作都在各自虛拟机的 操作系统下完成的, 各个虚拟机的备份不存在任何的关联。
在对现有技术的研究和实践过程中, 本发明的发明人发现, 现有的实现方 式中,当数据中心的各个虚拟机间彼此存在直接联系,运行状态存在依赖关系, 如果将数据中心每个单独系统(对应一个虚拟机)备份出来, 然后在单独进行 恢复, 其过程比较复杂, 而且容易出现操作上的错误, 导致备份的数据中心和 原数据中心系统不完全一致。 此外, 数据中心系统可能由多个计算节点构成, 每个虚拟机的动态数据 (内存信息) 将可能会分布在不同的多个计算节点上, 由虚拟机来进行备份数据可能会对运行在同一节点上的其他虚拟机产生影响。 发明内容
有鉴于此, 本发明实施例提供一种虚拟化数据迁移或备份方法、虛拟化数 据重组方法、装置及系统, 以解决对数据中心上所有虛拟机上数据统一进行备 份的技术问题, 以提高备份效率。
为此,本发明实施例提供一种虚拟化数据迁移或备份方法,所述方法包括: 虚拟化软件层节点接收数据迁移或备份的指令; 所述虚拟化软件层节点根据所述指令,将所述虚拟化软件层节点中的各个 虚拟机上存储的数据导出到存储设备中;
所述虚拟化软件层节点向备份管理节点发送各个虚拟机的配置信息,以使 所述备份管理节点根据所述配置信息对所述存储设备中的数据进行重新组合。
本发明实施例还提供一种虚拟化数据重组方法, 所述方法包括: 备份管理节点获取至少一个虛拟化软件层节点中各个虛拟机的配置信息; 备份管理节点根据所述虚拟机的配置信息对与其连接的存储设备中的数 据进行重新组合, 其中, 所述存储设备中存储有至少一个虚拟化软件层节点中 的各个虚拟机上存储的数据。
相应的, 本发明实施例提供一种虚拟化数据迁移或备份装置, 所述装置包 括:
接收单元, 用于接收数据迁移或备份的指令
导出单元, 用于根据所述指令, 将所述虚拟化软件层节点中的各个虚拟机 上存储的数据导出到存储设备中;
发送单元, 用于向备份管理节点发送各个虚拟机的配置信息, 以使所述备 份管理节点根据所述配置信息对所述存储设备中的数据进行重新组合。
本发明实施例还提供一种虛拟化数据重组装置, 该装置与存储设备连接, 所述存储设备,用于存储至少一个虚拟化软件层节点中的各个虚拟机上存储的 数据; 所述装置包括:
获取单元, 用于获取至少一个虚拟化软件层节点中各个虚拟机的配置信 息;
重新组合单元,用于根据所述配置信息对所述存储设备中的数据进行重新 组合。
相应的, 本发明实施例还提供一种虚拟化数据中心系统, 所述系统包括: 虚拟化软件层节点, 用于接收数据迁移或备份的指令, 并根据所述指令, 将所述虚拟化软件层节点中的各个虚拟机上存储的数据导出到与其连接的存 储设备中;
备份管理节点, 用于获取所述虚拟化软件层节点中各个虚拟机的配置信 息, 并根据所述配置信息对所述存储设备中的数据进行重新组合。
由上述技术方案可知,本发明实施例可以将一个数据中心中的所有的虚拟 系,以便于在恢复数据中心的数据时可以不关心虚拟机恢复的先后顺序。同时, 在从虚拟化软件层节点中导出存储的数据时, 不需要再往上通知上层 OS来进 行备份, 从而提高了数据备份效率, 降低了系统逻辑复杂度。
附图说明
图 1为本发明实施例提供一种虛拟化数据迁移或备份方法的流程图; 图 2 为本发明实施例提供的一种虚拟化数据迁移或备份方法中内存数据 导出的应用实例图;
图 3为本发明实施例提供的一种虚拟化数据重组方法的流程图; 图 4 为本发明实施例提供的一种备份管理节点对虚拟数据中心中的相关 配置信息进行收集备份的结构示意图;
图 5 为本发明实施例提供的一种虚拟化数据迁移或备份装置的结构示意 图;
图 6为本发明实施例提供的一种虚拟化数据重组装置的结构示意图; 图 7为本发明实施例提供的一种虚拟化数据中心系统的结构示意图。 具体实施方式
为了使本技术领域的人员更好地理解本发明实施例的方案,下面结合附图 和实施方式对本发明实施例作进一步的详细说明。
为了并于本领域技术人员的理解, 在介绍本发明之前, 先简单的介绍一下 虚拟化的数据中心。
所述虚拟化的数据中心通常会由两个以上的计算节点构成,每个计算节点 上会运行一个虚拟化软件层(Hypervisor ), 本发明称为虚拟化软件层节点, 所 述 Hypervisor将该计算节点上的物理内存, 处理器, I/O资源抽象、 重组成多个 虚拟计算节点, 所以, 所述 Hypervisor 可以认为是一个资源归属的转换模块。 在虛拟化的数据中心中,只有 Hypervisor可以访问到所有的计算节点物理资源。
请参阅图 1 , 为本发明实施例提供一种虚拟化数据迁移或备份方法的流程 图; 所述方法包括:
步骤 101: 虚拟化软件层节点接收数据迁移或备份的指令;
其中, 该步骤中, 虚拟化软件层节点可以接收到虛拟机上的管理节点, 或 者虛拟机操作系统发送的数据迁移或备份指令,但并不限于此也可以是其他上 层节点发送的数据迁移或备份的指令。
步骤 102: 虚拟化软件层节点根据所述指令, 将该虚拟化软件层节点中的 各个虚拟机上存储的数据导出到存储设备中。
其中, 该步骤具体包括: 虚拟化软件层节点中的处理器管理单元根据所述 指令停止对各个虛拟机上的中央处理器的调度,并将各个虛拟机上的数据存储 到与其连接的内存中;虚拟化软件层节点在与其连接的存储设备中申请一段存 储空间, 并在所述存储空间中记录该虚拟化软件层节点的节点编号; 将所有内 存中的数据导出到所述存储空间中;
步骤 103: 所述虚拟化软件层节点向备份管理节点发送各个虚拟机的配置 信息,以使所述备份管理节点根据所述配置信息对所述存储设备中的数据进行 重新组合。
本发明实施例中, 当虚拟化软件层节点接收到数据迁移或备份指令时, 可 以一次将虚拟化软件层节点下的各个虚拟机上存储的数据全部导出到存储设 备中。也就是说,虚拟化软件层节点可以一次统一备份一个数据中心上所有的 虚拟机上存储的数据,以便于使数据中心的恢复或者迁移时能够与原数据中心 完全一致。
请参阅图 2, 为本发明实施例提供的一种虚拟化数据迁移或备份方法中内 存数据导出的应用实例图, 所述方法应用于对虚拟数据中心中 Hypervisor侧的 数据备份的示意图。 在该实施例中, 在 Hypervisor中增加一个数据导出单元 ( memory dump ),该数据导出单元用来对本 Hypervisor管理的计算节点的存储 数据进行导出操作。
如果图 2所示, 本实施例以两个计算节点 (即计算节点 1和计算节点 2 ) 为 例, 其中, 计算节点 1中包括依次连接的 OS11 (即 OS1至 OSn )、 Hypervisorl2、 CPU13、 内存单元 14, 同时, 内存单元 14还与 Hypervisorl2连接, 其中, Hypervisor 12包括数据导出单元 121。 计算节点 2中包括依次连接的 OS21(即 OS1至 OSn )、 Hypervisor22、 CPU23. 内存单元 24, 同时, 内存单元 14还与 Hypervisorl2连接, 其中, Hypervisor22 包括数据导出单元 221。
高速存储设备 3分别与计算机 1和计算机 2中的所有 CPU连接。
如图所示, 当 Hypervisor接收到 OS (包括 OS1至 OSn中的任意一个)发送 的数据迁移或备份的指令时, 即当系统触发备份流程时; Hypervisor上的处理 器管理单元将停止对 CPU的调度, Hypervisor上的内存单元将本虚拟计算节点 上未写回的緩冲 ( Cache )数据全部写回到内存单元 ( Memory ) 中。
Hypervisor在与其连接的存储设备中申请一段存储空间, 首先, 将其所在 的节点编号写入到该存储空间中, 然后将内存(Memory ) 单元中的数据全部 导出到该存储空间中。
其中, 所述存储空间建议采用 CPU直接连接的 I/O存储, 即图 2中的高速存 储设备 ( High Speed Storage ), 因为作为数据中心存在的服务器一般都具有海 量的内存容量, 如果采用传统通道的 10 Adapt进行传输, 效率低下, 耗费大量 的时间。 但所述存储空间不限于此, 也可以是其他与 CPU连接的存储设备。
还请参阅图 3,为本发明实施例提供的一种虚拟化数据重组方法的流程图, 在基于图 1所示实施例的基础上, 所述方法包括:
步骤 301: 备份管理节点获取至少一个虚拟化软件层节点中各个虛拟机的 配置信息;
步骤 302: 备份管理节点根据所述配置信息对与其连接的存储设备中的数 据进行重新组合, 其中, 所述存储设备中存储有至少一个虚拟化软件层节点中 的各个虛拟机上存储的数据。
其中, 步骤 301中, 一种获取方式为: 备份管理节点搜索至少一个虚拟化 软件层节点中导出的数据 (即内存 memory文件 ), 从所述 memory文件中获 取虚拟化软件层节点的节点编号; 然后, 备份管理节点根据所述节点编号, 从 该虚拟化软件层节点的虚拟化软件层配置文件中获取统一地址分配的节点分 布信息。 另一种获取方式为:备份管理节点定接收至少一个虚拟化软件层节点定期 或实时发送的各个虚拟机的配置信息。
步骤 302中,所述根据所述配置信息对所述存储设备中的数据进行重新组 合, 包括: 备份管理节点根据获取的所述统一地址分配的节点分布信息, 按照 内存段地址对所述存储设备的数据重新组合,重新组合后的数据中包括该虚拟 化软件层节点的节点编号。
其中,按照内存段地址对存储设备中的数据重新组合, 包括两种重新组合 方式, 一种是按照内存段地址从低到高的顺序对存储空间的数据重新组合; 另 一种是按照内存段地址从高到低的顺序对存储空间的数据重新组合。 当然, 并 不限于此,也可以从内存段地址的中间向高端顺序对所述存储设备的数据重新 本实例不作限制。
上述实施例为 Hypervisor对内存的数据的导出过程,在 Hypervisor对内存 的数据导出后, 备份管理节点( Backup Manager )需要对虚拟数据中心中的相 关配置信息进行收集备份,同时对各个节点导出的数据(即内存上存储的数据, 也可以称为内存数据 )进行重新组合。 因为每个存在 Hypervisor的节点并不一 定是一台完整的计算机,可能与其他的节点共同组成一台统一地址分配的计算 机, 在这种情况下, 需要将所有统一地址分配的节点内存按照内存地址空间重 新进行组合。 具体还请参阅图 4。
图 4 为本发明实施例提供的一种备份管理节点对虚拟数据中心中的相关 配置信息进行收集备份的结构示意图。
如图 4所示, 包括: Backup Manager41分别对 Hypervisor42的备份, 对虚 拟机(VM ) 的备份, 对网络(Network ) 44的备份, 其中,
所述对虚拟机( VM ) 43的备份包括对 OS镜像 ( OS image ) 431的备份 和对 VM的配置信息 ( VM profile ) 432的备份, 这些信息是存放了数据中心 的静态信息, VM在只有 OS镜像和配置信息文件的情况下可以启动运行; 对 Hypervisor42 的备份包括对 CPU422 的备份和对内存 (memory ) 421 的备份, 备份了 Hypervisor所管理的内存和 CPU状态, 即描述了数据中心的 动态状态, 也就是某一个时刻的运行状态,备份 Hypervisor的状态可以使数据 中心在恢复时完全跟备份的时候相同。 对 Network备份 44 包括对路由器、 交换机的配置信息 (Switch/Router profile441的备份和对智能网卡配置信息 442的备份。 其中,
对 Switch/Router profile的备份包括对它们的虚拟化配置情况的备份; 这 是因为数据中心中的各个虚拟机并不是独立的,它们经常通过网络互相交换数 据, 如果不对网络的配置信息进行备份的话, 当数据中心的虚拟机在恢复时就 无法正确的接入网络。 而且数据中心的网絡也可能是虛拟化的, 虛拟机中看到 的路由器、 交换机, 可能并不实际存在于物理网络中, 这些虚拟配置信息可能 存在与物理交换机和物理路由器中,也可能存在与数据中的智能网卡中。因此, 对上述这些信息进行备份可以用来恢复数据中心的网络拓朴结构,使虚拟机在 恢复的时候可以正常的接入网络。
对智能网卡配置信息 442的备份,由于智能网卡也可能会被用作虛拟交换 机, 虚拟路由器的载体, 因此, 也需要对智能网卡配置信息进行备份。
其中, 根据所述信息进行虚拟化数据迁移或备份的过程包括:
虚拟化软件层节点 Hypervisor在接收到数据迁移或备份的指令时,根据所 述指令,将所述虚拟化软件层节点中的各个虚拟机上存储的数据导出到存储设 备中; 虛拟化软件层节点向备份管理节点 Backup Manager发送各个虛拟机的 配置信息, 所述虚拟机的配置信息为备份的虚拟机的配置信息, 可以包括各个 虚拟机的 OS镜像和 VM的配置信息, 当然, 并不限于此, 还可以包括其他信 息, 比如 Hypervisor42的备份和对 Network备份等。
而所述 Backup Manager获取至少一个虚拟化软件层节点中各个虚拟机的 配置信息 , 即搜索 Hypervisor导出的 memory文件 , 并读取该 memory文件头 部的节点编号, 即确定 Hypervisor所在的节点编号。
Backup Manager才艮据该节点编号, 从对应 Hypervisor节点的 Hypervisor 配置文件中读取该节点配置信息, 即统一地址分配的节点分布信息。
Backup Manager根据所述节点配置信息, 按照内存段地址从低到高的顺 序重新组合文件, 重新组合的文件依然保留备份时的节点信息, 用作恢复时参 考信息。
当然, Backup Manager根据所述节点配置信息, 按照内存段地址从高到 低的顺序重新组合文件; 但并不限于此,还可以按照内存段地址从中间到高或 低的顺序重新组合文件。 在该实施例中, 重组内存段的作用, 以便于使恢复该备份时能恢复到与原 备份系统内存大小配置不相同的计算节点上。
此外, 本发明实施例中, 除了搜集备份虚拟机的配置信息 ( VM profile ) 外, 还可以搜集备份 OS镜像(OS image )。 其中, 虚拟机的配置信息一般以 配置文件的形式存在, 并与 OS镜像 ( OS image )文件存储在同一个存储空间 中。 Backup Manager需要拷贝所有的虛拟机的配置文件以及 OS image文件到 备份的存储设备中, 并对虚拟机的配置文件进行解析, 因为每一个虚拟机的配 置文件中会描述该虚拟机现有的配置文件中存储该虚拟机所配置的资源, 例 如: CPU的数量, Memory的大小, 各种 I/O端口的数量种类以及所连接的存 储设备等。 这些信息用以恢复数据中心时的环境验证使用。
一般情况下, 虚拟机的配置文件中与系统硬件相关的信息如下:
CD-settings (控制域配置节点)
Network (网络配置)
Floppy-drives (软盘驱动器)
IDE ( IDE硬盘驱动器)
Parallel ports (并行端口)
RAM (内存大小)
SCSI ( SCSI存储驱动器)
Serial ports (串行端口)
Sound (声卡配置)
USB port ( USB端口配置 )
CPU (虚拟 CPU数量)
也就是说, Backup Manager先确定虚拟化软件层节点的节点编号, 在根 据所述节点编号对应的虚拟化软件层节点获取虚拟机的配置文件, 然后,根据 虚拟机的配置文件中的字段描述,收集所有的虚拟机所有的资源种类和数量信 息, 并汇总。
之后, Backup Manager 可以接入虚拟数据中心的本地局域网, 通过使用 SNMP协议, 获取该网络上的所有设备, 并生成该网络的拓朴结构图, 并将拓 朴结构图存储到备份的存储设备中。
其中, 网络的拓朴结构描述了该数据中心的逻辑网络结构, 这个结构对数 据中心中的虛拟机能否正常进行通讯非常重要, 正常情况下, 当恢复了所有交 换机、 路由器、 智能网卡的网络配置信息, 并且启动所有虚拟机后, 恢复的数 据中心应当与备份的数据中心的网络拓朴结构相同。此时可以用这个网络拓朴 结构进行验证, 以确定网络得到了正确的恢复。
本发明实施例中,由于在每个 Hypervisor中均增力 P了 Memory dump单元, 该单元可以直接从 Hypervisor导出内存数据,即可以将一个数据中心中的所有 的虚拟机上的数据同时备份出来, 以便于 Backup Manager将不同虚拟计算节 点导出的内存数据进行重新组合, 其达到优点为:
1、 在数据迁移或备份时不需要关心数据中心上到底运行了多少虚拟机。 2、 数据迁移或备份时也同时备份了虚拟机之间的关联关系, 以便于恢复 数据中心在恢复数据时可以不关心虛拟机恢复的先后顺序。
3、 在直接从 Hypervisor中导出内存数据时, 不需要再向上层通知 OS来 进行数据备份, 提高了备份效率, 降低了系统逻辑复杂度。
基于上述方法的实现过程,本发明实施例还提供一种虚拟化数据迁移或备 份装置, 其结构示意图详见图 5 , 所述装置包括: 接收单元 51、 导出单元 52 和发送单元 53, 其中,
所述接收单元 51 , 用于接收数据迁移或备份的指令; 即可以接收到虚拟 机上的管理节点, 或者虚拟机操作系统发送的数据迁移或备份指令,但并不限 于此也可以是其他上层节点发送的数据迁移或备份的指令。
所述导出单元 52, 用于根据所述指令, 将该虚拟化软件层节点中的各个 虚拟机上存储的数据导出到存储设备中。 具体包括: 处理器管理单元、 多个内 存单元、 资源申请单元和数据导出单元, 其中,
所述处理器管理单元,用于根据所述指令停止对各个虚拟机上的中央处理 器的调度;
所述多个内存单元,用于在处理器管理单元停止对各个虚拟机上的中央处 理器的调度时, 分别存储各个虚拟机上的数据;
所述资源申请单元,用于在与虛拟化软件层节点连接的存储设备中申请一 段存储空间, 并在所述存储空间中记录该虚拟化软件层节点的节点编号; 所述数据导出单元,用于将所述多个内存单元中的数据导出到所述存储空 间中。 所述装置中各个单元的功能和作用的实现过程详见上述方法中对应的实 现过程, 在此不再赘述。
相应的, 本发明实施例还提供一种虚拟化数据重组装置, 其结构示意图详 见图 6, 该装置与存储设备连接, 所述存储设备, 用于存储至少一个虚拟化软 件层节点中的各个虚拟机上存储的数据; 所述装置包括: 获取单元 61和重新 组合单元 62 , 其中, 所述获取单元 61 , 用于获取至少一个虛拟化软件层节点 中各个虚拟机的配置信息; 所述重新组合单元 62, 用于根据所述配置信息对 所述存储设备中的数据进行重新组合。
其中, 所述获取单元包括: 搜索单元和地址获取单元, 其中, 所述搜索单 元, 用于搜索虚拟化软件层节点中导出的数据 (比如内存 memory文件), 从 所述数据中获取虛拟化软件层节点的节点编号; 所述地址获取单元, 用于根据 所述节点编号,从该虚拟化软件层节点的虛拟化软件层配置文件中获取统一地 址分配的节点分布信息。
所述重新组合单元,具体用于根据获取的所述统一地址分配的节点分布信 息,按照内存段地址对所述存储设备的数据重新组合, 重新组合后的数据中包 括该虚拟化软件层节点的节点编号。
所述装置中各个单元的功能和作用的实现过程详见上述方法中对应的实 现过程, 在此不再赘述。
相应的, 本发明实施例再提供一种虚拟化数据中心系统, 其结构示意图详 见图 7, 所述系统包括: 虚拟化软件层节点 71和备份管理节点 72, 其中, 所 述虚拟化软件层节点 71 包括虚拟化数据迁移或备份装置 711 ; 所述备份管理 节点 72包括虚拟化数据重组装置 721, 其中,
所述虚拟化软件层节点, 用于接收数据迁移或备份的指令, 并根据所述指 令, 将虚拟化软件层节点中的各个虚拟机上存储的数据导出到存储设备中; 所述备份管理节点, 用于获取虚拟化软件层节点中各个虚拟机的配置信 息, 并根据所述配置信息对所述存储设备中的数据进行重新组合。
其中, 所述虛拟化数据迁移或备份装置包括接收单元和导出单元, 其各个 单元的功能和作用的实现过程详见上述, 在此不再赘述。
虚拟化数据重组装置包括获取单元和重新组合单元,其各个单元的功能和 作用的实现过程详见上述, 在此不再赘述。 本发明实施例可以将一个数据中心中的所有的虛拟机上的内存数据同时 复数据中心的数据时可以不关心虚拟机恢复的先后顺序。 同时, 在直接从
Hypervisor中导出内存数据时, 不需要再往上通知上层 OS来进行备份, 从而 提高了数据备份效率, P 低了系统逻辑复杂度。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到本发明 可借助软件加必需的通用硬件平台的方式来实现, 当然也可以通过硬件,但 4艮 多情况下前者是更佳的实施方式。基于这样的理解, 本发明的技术方案本质上 或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机 软件产品可以存储在存储介质中, 如 ROM/RAM、 磁碟、 光盘等, 包括若干指 令用以使得一台计算机设备(可以是个人计算机, 服务器, 或者网络设备等) 执行本发明各个实施例或者实施例的某些部分所述的方法。
以上所述仅是本发明的优选实施方式, 应当指出, 对于本技术领域的普通 技术人员来说, 在不脱离本发明原理的前提下, 还可以作出若干改进和润饰, 这些改进和润饰也应视为本发明的保护范围。
+

Claims

权 利 要 求
1、 一种虚拟化数据迁移或备份方法, 其特征在于, 包括:
虚拟化软件层节点接收数据迁移或备份的指令;
所述虚拟化软件层节点根据所述指令,将所述虚拟化软件层节点中的各个 虛拟机上存储的数据导出到存储设备中;
所述虚拟化软件层节点向备份管理节点发送各个虚拟机的配置信息,以使 所述备份管理节点根据所述配置信息对所述存储设备中的数据进行重新组合。
2、 如权利要求 1所述的方法, 其特征在于, 所述虚拟化软件层节点根据 所述指令,将所述虚拟化软件层节点中的各个虚拟机上的内存数据导出到存储 设备中包括:
所述虚拟化软件层节点中的处理器管理单元根据所述指令停止对各个虚 拟机上的中央处理器的调度,并将各个虚拟机上的数据存储到与其连接的内存 中;
所述虚拟化软件层节点在与其连接的存储设备中申请一段存储空间,并在 所述存储空间中记录该虚拟化软件层节点的节点编号;
所述虚拟化软件层节点将所有内存中的数据导出到所述存储空间中。
3、 一种虚拟化数据重组方法, 其特征在于, 包括:
备份管理节点获取至少一个虚拟化软件层节点中各个虚拟机的配置信息; 备份管理节点根据所述虚拟机的配置信息对与其连接的存储设备中的数 据进行重新组合, 其中, 所述存储设备中存储有至少一个虚拟化软件层节点中 的各个虚拟机上存储的数据。
4、 如权利要求 3所述的方法, 其特征在于, 所述备份管理节点获取虚拟 化软件层节点中至少一个虚拟机的配置信息, 包括:
备份管理节点搜索至少一个虚拟化软件层节点中导出的数据,从所述数据 中获取虚拟化软件层节点的节点编号; 根据所述节点编号, 从该虚拟化软件层 节点的虛拟机的配置文件中获取统一地址分配的节点分布信息; 或者
备份管理节点定接收至少一个虚拟化软件层节点定期或实时发送的各个 虚拟机的配置信息。
5、 如权利要求 4所述的方法, 其特征在于, 所述备份管理节点根据所述 虚拟机的配置信息对与其连接的存储设备中的数据进行重新组合, 包括: 备份管理节点根据获取的所述统一地址分配的节点分布信息,按照内存段 地址对所述存储设备中的数据重新组合,重新组合后的数据中包括该虚拟化软 件层节点的节点编号。
6、 如权利要求 5所述的方法, 其特征在于, 所述按照内存段地址对所述 存储设备的数据重新组合具体包括:
按照内存段地址从低到高的顺序对存储设备的数据重新组合; 或者 按照内存段地址从高到低的顺序对存储设备的数据重新组合。
7、 一种虚拟化数据迁移或备份装置, 其特征在于, 包括:
接收单元, 用于接收数据迁移或备份的指令
导出单元, 用于根据所述指令, 将所述虛拟化软件层节点中的各个虛拟机 上存储的数据导出到存储设备中;
发送单元, 用于向备份管理节点发送各个虚拟机的配置信息, 以使所述备 份管理节点根据所述配置信息对所述存储设备中的数据进行重新组合。
8、 如权利要求 7所述的装置, 其特征在于, 所述导出单元包括: 处理器管理单元,用于根据所述指令停止对各个虚拟机上的中央处理器的 调度;
多个内存单元,用于在处理器管理单元停止对各个虚拟机上的中央处理器 的调度时, 分别存储与其连接的虚拟机上的数据;
资源申请单元,用于在与虚拟化软件层节点连接的存储设备中申请一段存 储空间, 并在所述存储空间中记录该虚拟化软件层节点的节点编号;
数据导出单元, 用于将所述多个内存单元中的数据导出到所述存储空间 中。
9、 一种虚拟化数据重组装置, 其特征在于, 该装置与存储设备连接, 所 述存储设备,用于存储至少一个虚拟化软件层节点中的各个虚拟机上存储的数 据; 所述装置包括:
获取单元, 用于获取至少一个虛拟化软件层节点中各个虚拟机的配置信 息;
重新组合单元,用于根据所述配置信息对所述存储设备中的数据进行重新 组合。
10、 如权利要求 9所述的装置, 其特征在于, 所述获取单元包括: 搜索单元, 用于搜索虚拟化软件层节点中导出的数据, 从所述数据中获取 虚拟化软件层节点的节点编号;
地址获取单元, 用于根据所述节点编号,从该虚拟化软件层节点的虚拟机 的配置文件中获取统一地址分配的节点分布信息。
11、 如权利要求 9或 10所述的装置, 其特征在于, 所述重新组合单元, 具体用于根据获取的所述统一地址分配的节点分布信息,按照内存段地址对存 储设备中的数据重新组合,重新组合后的数据中包括该虚拟化软件层节点的节 点编号。
12、 一种虚拟化数据中心系统, 其特征在于, 包括:
虚拟化软件层节点, 用于接收数据迁移或备份的指令, 并根据所述指令, 将所述虚拟化软件层节点中的各个虚拟机上存储的数据导出到与其连接的存 储设备中;
备份管理节点, 用于获取所述虚拟化软件层节点中各个虚拟机的配置信 息, 并根据所述配置信息对所述存储设备中的数据进行重新组合。
13、 如权利要求 12所述的系统 , 其特征在于 ,
所述虚拟化软件层节点包括: 虛拟化数据迁移或备份装置, 其中, 所述虚 拟化数据迁移或备份装置如权利要求 7至 8任一项所述的虚拟化数据迁移或备 份装置;
所述备份管理节点包括: 虚拟化数据重组装置, 其中, 所述虚拟化数据重 组装置如权利要求 9至 11任一项所述的虚拟化数据导出装置。
PCT/CN2011/077945 2011-08-03 2011-08-03 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统 WO2012109876A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201180001517.7A CN102317910B (zh) 2011-08-03 2011-08-03 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统
PCT/CN2011/077945 WO2012109876A1 (zh) 2011-08-03 2011-08-03 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统
US13/687,833 US9547605B2 (en) 2011-08-03 2012-11-28 Method for data backup, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2011/077945 WO2012109876A1 (zh) 2011-08-03 2011-08-03 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13/687,833 Continuation US9547605B2 (en) 2011-08-03 2012-11-28 Method for data backup, device and system

Publications (1)

Publication Number Publication Date
WO2012109876A1 true WO2012109876A1 (zh) 2012-08-23

Family

ID=45429412

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2011/077945 WO2012109876A1 (zh) 2011-08-03 2011-08-03 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统

Country Status (3)

Country Link
US (1) US9547605B2 (zh)
CN (1) CN102317910B (zh)
WO (1) WO2012109876A1 (zh)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9304873B2 (en) * 2012-08-23 2016-04-05 Vmware, Inc. Recovery system and method for recreating a state of a datacenter
US10313345B2 (en) 2013-03-11 2019-06-04 Amazon Technologies, Inc. Application marketplace for virtual desktops
US9148350B1 (en) 2013-03-11 2015-09-29 Amazon Technologies, Inc. Automated data synchronization
US10142406B2 (en) 2013-03-11 2018-11-27 Amazon Technologies, Inc. Automated data center selection
US9002982B2 (en) 2013-03-11 2015-04-07 Amazon Technologies, Inc. Automated desktop placement
US9479396B2 (en) * 2013-05-31 2016-10-25 Sungard Availability Services, Lp XML based generic UNIX discovery framework
CN104363976B (zh) * 2013-06-13 2019-01-08 华为技术有限公司 虚拟机组迁移方法及装置
US10623243B2 (en) 2013-06-26 2020-04-14 Amazon Technologies, Inc. Management of computing sessions
US10686646B1 (en) * 2013-06-26 2020-06-16 Amazon Technologies, Inc. Management of computing sessions
US9053216B1 (en) 2013-08-09 2015-06-09 Datto, Inc. CPU register assisted virtual machine screenshot capture timing apparatuses, methods and systems
US9092248B1 (en) * 2013-08-21 2015-07-28 Symantec Corporation Systems and methods for restoring distributed applications within virtual data centers
CN103593262B (zh) * 2013-11-15 2016-05-25 上海爱数信息技术股份有限公司 一种基于类别的虚拟机备份方法
CN105025067B (zh) * 2014-04-30 2018-12-25 中国银联股份有限公司 一种信息安全技术研究平台
CN104679579B (zh) * 2015-03-19 2018-10-09 新华三技术有限公司 一种集群系统中的虚拟机迁移方法和装置
CN106155831B (zh) * 2015-03-24 2019-04-23 联想(北京)有限公司 一种数据恢复方法及装置
CN105117246A (zh) * 2015-08-04 2015-12-02 晶晨半导体(上海)有限公司 电子设备快速启动的方法
CN107046810A (zh) * 2015-12-03 2017-08-15 华为技术有限公司 一种虚拟机备份信息迁移方法、装置和系统
CN106855834B (zh) * 2015-12-08 2020-11-10 华为技术有限公司 一种数据备份方法、装置和系统
US10270596B2 (en) 2016-09-16 2019-04-23 International Business Machnines Corporation Generating memory dumps
CN106850598B (zh) * 2016-12-06 2020-06-12 中国电子科技集团公司第三十二研究所 面向全舰计算环境的统一资源管理系统及方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1812345A (zh) * 2006-03-08 2006-08-02 杭州华为三康技术有限公司 虚拟化网络存储系统及其网络存储设备
CN101819545A (zh) * 2010-04-09 2010-09-01 济南银泉科技有限公司 一种利用虚拟化技术实现平台迁移的方法
US20100228934A1 (en) * 2009-03-03 2010-09-09 Vmware, Inc. Zero Copy Transport for iSCSI Target Based Storage Virtual Appliances
CN102096606A (zh) * 2011-02-21 2011-06-15 浪潮(北京)电子信息产业有限公司 虚拟机迁移方法、装置和系统

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3858182A (en) * 1972-10-10 1974-12-31 Digital Equipment Corp Computer program protection means
AU2001246799A1 (en) * 2000-04-18 2001-10-30 Storeage Networking Technologies Storage virtualization in a storage area network
JP4453323B2 (ja) 2003-10-02 2010-04-21 株式会社日立製作所 複製データの管理方法、装置、及びプログラム
US7779034B2 (en) 2005-10-07 2010-08-17 Citrix Systems, Inc. Method and system for accessing a remote file in a directory structure associated with an application program executing locally
US8607009B2 (en) * 2006-07-13 2013-12-10 Microsoft Corporation Concurrent virtual machine snapshots and restore
US20090037162A1 (en) 2007-07-31 2009-02-05 Gaither Blaine D Datacenter workload migration
US20090119233A1 (en) 2007-11-05 2009-05-07 Microsoft Corporation Power Optimization Through Datacenter Client and Workflow Resource Migration
US8189794B2 (en) 2008-05-05 2012-05-29 Sony Corporation System and method for effectively performing data restore/migration procedures
US8825984B1 (en) * 2008-10-13 2014-09-02 Netapp, Inc. Address translation mechanism for shared memory based inter-domain communication
US20100106764A1 (en) 2008-10-29 2010-04-29 The Go Daddy Group, Inc. Datacenter hosting multiple online data management solutions
US20100107085A1 (en) 2008-10-29 2010-04-29 The Go Daddy Group, Inc. Control panel for managing multiple online data management solutions
US20100106615A1 (en) 2008-10-29 2010-04-29 The Go Daddy Group, Inc. Providing multiple online data management solutions
US8103842B2 (en) 2008-11-17 2012-01-24 Hitachi, Ltd Data backup system and method for virtual infrastructure
US7904540B2 (en) 2009-03-24 2011-03-08 International Business Machines Corporation System and method for deploying virtual machines in a computing environment
US8117613B2 (en) 2009-04-08 2012-02-14 Microsoft Corporation Optimized virtual machine migration mechanism
US8255475B2 (en) * 2009-04-28 2012-08-28 Mellanox Technologies Ltd. Network interface device with memory management capabilities
US20110010268A1 (en) 2009-05-15 2011-01-13 De Marchi Filho Bruno Digital content management and usage system, a digital content supplying station, and a method of supplying digital content
US9047351B2 (en) * 2010-04-12 2015-06-02 Sandisk Enterprise Ip Llc Cluster of processing nodes with distributed global flash memory using commodity server technology
US8423646B2 (en) * 2010-07-09 2013-04-16 International Business Machines Corporation Network-aware virtual machine migration in datacenters
US8359453B2 (en) * 2010-09-13 2013-01-22 International Business Machines Corporation Real address accessing in a coprocessor executing on behalf of an unprivileged process

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1812345A (zh) * 2006-03-08 2006-08-02 杭州华为三康技术有限公司 虚拟化网络存储系统及其网络存储设备
US20100228934A1 (en) * 2009-03-03 2010-09-09 Vmware, Inc. Zero Copy Transport for iSCSI Target Based Storage Virtual Appliances
CN101819545A (zh) * 2010-04-09 2010-09-01 济南银泉科技有限公司 一种利用虚拟化技术实现平台迁移的方法
CN102096606A (zh) * 2011-02-21 2011-06-15 浪潮(北京)电子信息产业有限公司 虚拟机迁移方法、装置和系统

Also Published As

Publication number Publication date
CN102317910B (zh) 2014-08-20
US20130091334A1 (en) 2013-04-11
US9547605B2 (en) 2017-01-17
CN102317910A (zh) 2012-01-11

Similar Documents

Publication Publication Date Title
WO2012109876A1 (zh) 虚拟化数据备份方法、虚拟化数据重组方法、装置及系统
US11144415B2 (en) Storage system and control software deployment method
US11507466B2 (en) Method and apparatus of managing application workloads on backup and recovery system
US9928003B2 (en) Management of writable snapshots in a network storage device
US10050850B2 (en) Rack awareness data storage in a cluster of host computing devices
EP3287906B1 (en) Method, system, and apparatus for cloud application redundancy
US8996477B2 (en) Multiple node/virtual input/output (I/O) server (VIOS) failure recovery in clustered partition mobility
US9229749B2 (en) Compute and storage provisioning in a cloud environment
CN111506267A (zh) 分布式内存磁盘群集储存系统运作方法
US20120151095A1 (en) Enforcing logical unit (lu) persistent reservations upon a shared virtual storage device
US11550491B2 (en) Container-based application processing
US11513914B2 (en) Computing an unbroken snapshot sequence
US11899543B2 (en) High-frequency virtual machine restore points
WO2014101211A1 (zh) 一种虚拟设备重建方法与装置
Walters et al. A fault-tolerant strategy for virtualized HPC clusters
US11972284B2 (en) Virtual machine memory snapshots in persistent memory
US20240211013A1 (en) Hibernating and resuming nodes of a computing cluster
Cully Extending systems with virtual hardware aggregation
Ren et al. InfoStor: Highly Available Distributed Block Store
Shu The design and implementation of cloud-scale live migration

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 201180001517.7

Country of ref document: CN

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

Ref document number: 11858983

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: 11858983

Country of ref document: EP

Kind code of ref document: A1