CN109254873A - Data back up method, relevant apparatus and system - Google Patents

Data back up method, relevant apparatus and system Download PDF

Info

Publication number
CN109254873A
CN109254873A CN201810931053.3A CN201810931053A CN109254873A CN 109254873 A CN109254873 A CN 109254873A CN 201810931053 A CN201810931053 A CN 201810931053A CN 109254873 A CN109254873 A CN 109254873A
Authority
CN
China
Prior art keywords
storage unit
storage
array
data center
data
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN201810931053.3A
Other languages
Chinese (zh)
Other versions
CN109254873B (en
Inventor
刘军民
邹锋哨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Cloud Computing Technologies Co Ltd
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 CN201810931053.3A priority Critical patent/CN109254873B/en
Publication of CN109254873A publication Critical patent/CN109254873A/en
Application granted granted Critical
Publication of CN109254873B publication Critical patent/CN109254873B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14—Error detection or correction of the data by redundancy in operation
    • G06F11/1402—Saving, restoring, recovering or retrying
    • G06F11/1446—Point-in-time backing up or restoration of persistent data
    • G06F11/1458—Management of the backup or restore process
    • G06F11/1464—Management of the backup or restore process for networked environments
    • 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
    • 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
    • G06F3/0671—In-line storage system
    • G06F3/0683—Plurality of storage devices
    • G06F3/0689—Disk arrays, e.g. RAID, JBOD

Landscapes

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

Abstract

This application discloses data back up method, relevant apparatus and system, this method can include: data center controller determines that the second storage unit, the second storage unit have second identifier in the second storage array；The corresponding relationship of data center controller record first identifier and second identifier；Data center controller sends the first configuration information to the array control unit of the first storage array, first configuration information includes the corresponding relationship, wherein, the first configuration information is used to indicate the array control unit of the first storage array and the first host is written to the data backup of the first storage unit to the second storage unit according to the corresponding relationship.Implement the application, the second storage unit can back up the data of the first storage unit in the case where not interrupting customer service.

Description

Data back up method, relevant apparatus and system
Technical field
This application involves cloud computing and field of computer technology, in particular to data back up method, relevant apparatus and system.
Background technique
In big data era, constantly improve and develop with information-based, the data of data center are with unprecedented speed Spend explosive growth.
In the various kinds of equipment of data center, storage equipment is for storing user (such as enterprise, government and financial unit Deng) the core application data of the Various types of data based on data center, especially user.Since storage equipment is a large amount of for storing User data need to meet the disaster tolerance requirement of highly reliable High Availabitity.That is, even if storage equipment itself break down or When person's other accidents cause to store device fails, also to guarantee the safety of user data, also, also to guarantee user's Business is interrupted less or even is not interrupted.
Currently, the development of Internet technology is in from traditional platform to using cloud computing as the technological evolvement process of representative In, data center will be by the cloud data center of the service of conventional data centers fast steering, resource pool, software definition.Cloud number A kind of calculating based on cloud computing framework, storage and Internet resources coupled system according to center, to server, storage resource, Computing resource, Internet resources, application resource etc. are virtualized, and user is allow to call various resources on demand.
In cloud data center, Disaster Tolerant Scheme how is constructed, how to realize unbroken across the storing data migration of business and is deposited The problem of storing up equipment on-line replacement, being current urgent need to resolve.
Summary of the invention
This application provides data back up method, relevant apparatus and systems, can be standby in the case where not interrupting customer service Part data.
In a first aspect, this application provides a kind of data back up method, it is applied to data center, the first of the data center Host is mounted with the first storage unit, and the first storage unit is located at the first storage array, and the first storage unit has first identifier, Data center further includes data center controller；This method is applied to data center controller side, it may include: data center's control Device determines that the second storage unit, the second storage unit have second identifier in the second storage array；Data center controller note Record the corresponding relationship of first identifier and second identifier；Data center controller sends the to the array control unit of the first storage array One configuration information, the first configuration information include the corresponding relationship, wherein the first configuration information is used to indicate the first storage array The first host is written to the data backup of the first storage unit to the second storage unit according to the corresponding relationship for array control unit.
The method for implementing first aspect, can be by the data backup of the first storage unit to the second storage unit.Also, due to First storage unit is mounted to the first host, and the first storage unit can always be customer service service, is written in the first host During the data backup of first storage unit to the second storage unit, customer service can be not disrupted.
With reference to first aspect, in the first possible implementation of the first aspect, data center controller can be The storage unit being in idle condition is selected in two storage arrays；And the selection and first in the storage unit being in idle condition Storage unit has the storage unit of identical capacity as the second storage unit.In another alternative embodiment, data center's control Device processed can also select to make with the storage unit than the first storage unit larger capacity in the storage unit being in idle condition For the second storage unit.Above two optional way can make the capacity of the second storage unit back up the first storage enough single The data of member.
With reference to first aspect with the first possible implementation of first aspect, second in first aspect is possible In implementation, second identifier is identical as first identifier.Here, first identifier is used between the first host and the first storage array Data transmission, second identifier between the first host and the second storage array data transmission.In second identifier and first It identifies in identical situation, the first storage unit and the second storage unit can share the same mark, i.e., the first host is in number According in center, with two groups of data storage paths, (1 group is the physical access path for being directed toward the first storage unit, and another 1 group is direction The physical access path of second storage unit).
With reference to first aspect, the possible implementation of the first of first aspect and second of possible implementation, The method of first aspect in the third possible implementation of first aspect further include: data center controller is stored to second The array control unit of array sends the second configuration information, and the second configuration information includes the corresponding relationship, wherein the second configuration information The first host is written to the second storage unit according to the corresponding relationship for the array control unit for being used to indicate the second storage array Data backup is to the first storage unit.By above-mentioned alternative embodiment, the data that the second storage unit is written in the first host can be standby Part to the first storage unit, i.e. the first storage unit and the second storage unit can be used in storing the data from the first host. When the first storage unit breaks down, the second storage unit can be used as disaster tolerance storage unit, continue as customer service progress Service can avoid the interruption of customer service, guarantee the reliability of data center.
With reference to first aspect, the possible implementation of the first of first aspect, second of possible implementation and Three kinds of possible implementations, the in a fourth possible implementation of the first aspect method of first aspect further include: First host is sent to the data backup of the first storage unit to the second storage unit by the array control unit of the first storage array Later, data center controller unloads the first storage unit from the first host.After unloading the first storage unit, the first host it is complete Portion's data access request is responsible for processing by the second storage unit, and customer service clothes can be continued as by being equivalent to the second storage unit Business.By above-mentioned optional step, data can be moved to from the first storage unit in the case where not interrupting customer service Two storage units can complete the online replacement of storage array.
Second aspect, this application provides a kind of data back up method, this method is applied to data center, data center First host is mounted with the first storage unit, and the first storage unit is located at the first storage array, and the first storage unit has first Mark, which further includes data center controller；This method is applied to array control unit side, comprising: the first storage battle array The array control units of column receives the first configuration information that data center controller is sent, the first configuration information include first identifier with The corresponding relationship of the second identifier of second storage unit, wherein the second storage unit is by data center controller in the second storage It is determined in array；The first host is written to the first storage unit according to the corresponding relationship for the array control unit of first storage array Data backup to the second storage unit.
The method for implementing second aspect, when the data full backup stored in the first storage unit to the second storage unit Afterwards, the second storage unit has full dose data identical with the first storage unit.When the first storage unit breaks down, second Storage unit can be used as disaster tolerance storage unit, continues as customer service and is serviced, and can avoid the interruption of customer service, guarantee The reliability of data center.
In conjunction with second aspect, in the first possible embodiment of second aspect, the second storage unit is deposited with first Storage unit has identical capacity.
In conjunction with the possible embodiment of the first of second aspect and second aspect, second in second aspect is possible In embodiment, second identifier is identical as first identifier.
In conjunction with the first possible embodiment and second of possible embodiment of second aspect, second aspect, In the third possible embodiment of second aspect, the method for second aspect further include: the antenna array control of the second storage array Device receives the second configuration information that data center controller is sent, and the second configuration information includes the corresponding relationship；Second storage battle array The array control unit of column according to the corresponding relationship by the first host be written to the data backup of the second storage unit to first storage Unit.
The third aspect, this application provides a kind of data center controller, which may include multiple function Energy module, for any in method provided by execution first aspect accordingly or the possible embodiment of first aspect Method provided by a kind of.
Fourth aspect, this application provides a kind of array control unit, which may include multiple functional modules, use The method provided by execution second aspect accordingly or any one in the possible embodiment of second aspect are provided Method.
5th aspect, this application provides a kind of data center controller, the data for executing first aspect description are standby Part method.The data center controller can include: processing unit and communication interface.Wherein: the communication interface be used for Other equipment (such as array control unit) communication, any one may for executing first aspect or first aspect for the processing unit Embodiment described in data back up method realization code, i.e., execution first aspect provided by method or first Method provided by any one possible embodiment of aspect.
6th aspect, this application provides a kind of array control units, for executing the data backup side of second aspect description Method.The array control unit can include: processing unit and communication interface.Wherein: the communication interface is used for and other equipment (such as the first storage array) communication, the processing unit is for executing second aspect or second aspect any one possible implementation The realization code of data back up method described in mode, i.e. method or second aspect provided by execution second aspect are appointed Method provided by a kind of possible embodiment of anticipating.
7th aspect, this application provides a kind of computer readable storage medium, is stored on the readable storage medium storing program for executing Instruction, when run on a computer, so that computer executes the data back up method of above-mentioned first aspect description.
Eighth aspect, this application provides a kind of computer program products comprising instruction, when it runs on computers When, so that computer executes the data back up method of above-mentioned first aspect description.
9th aspect, this application provides a kind of computer readable storage medium, is stored on the readable storage medium storing program for executing Instruction, when run on a computer, so that computer executes the data back up method of above-mentioned second aspect description.
Tenth aspect, this application provides a kind of computer program products comprising instruction, when it runs on computers When, so that computer executes the data back up method of above-mentioned second aspect description.
Implement the application, the second storage unit can back up the first storage unit in the case where not interrupting customer service Data.In addition, the second storage unit can be used as disaster tolerance storage unit, continue as when the first storage unit breaks down Customer service is serviced, and be can avoid the interruption of customer service, is guaranteed the reliability of data center.
Detailed description of the invention
Figure 1A-Fig. 1 C is the schematic diagram of a scenario for the data back up method that the prior art provides；
Fig. 2 is the structural schematic diagram of data center provided by the present application；
Carry relational graph of the Fig. 3 between storage array provided by the present application and virtual machine；
Fig. 4 is a kind of flow diagram of data back up method provided by the present application；
Fig. 5 is the flow diagram of another data back up method provided by the present application；
Fig. 6 is the schematic diagram of dual-active pair provided by the present application；
Fig. 7 is the flow diagram of another data back up method provided by the present application；
Fig. 8 is the structural schematic diagram of data center controller provided by the present application；
Fig. 9 is the structural schematic diagram of array control unit provided by the present application；
Figure 10 is the functional block diagram of data center controller provided by the present application；
Figure 11 is the functional block diagram of array control unit provided by the present application.
Specific embodiment
The term that presently filed embodiment part uses is only used for explaining the specific embodiment of the application, rather than It is intended to limit the application.
Currently, mainly there is the following three kinds data back up method for being directed to data center:
(1) Data Migration is realized using the function that software provides.
Specifically, in the data center, the Data Migration function that the application software at availability data center provides realizes number According to migration.By taking oracle database as an example, oracle database software provides RMAN Backup and Restore function, can by the function Realize that data store the data duplication between equipment and target storage device (i.e. newly storage equipment) in source.Referring to Figure 1A, RMAN The process of Backup Data is divided into that data initial synchronisation is synchronous with variance data, in order to guarantee the consistency and integrality of data, Variance data synchronous phase customer service needs to interrupt.Further, since the migration that (1) kind moving method is provided based on system software Technology realizes Data Migration using the shift function of specific application, therefore this method applies function dependent on system itself Can, different systems runs different applications, it is difficult to general to arrive all data centers or system.
(2) Data Migration is realized using Storage Virtualization gateway.
It is the schematic diagram of a scenario that Data Migration is realized using Storage Virtualization gateway referring to Figure 1B, Figure 1B.As shown, When data center needs migrating data, by Storage Virtualization gateway accessing to data center, (process need to suspend user's industry first Business), and by the total data in Storage Virtualization gateway management source storage equipment.After accessing Storage Virtualization gateway, The data of host are issued to source storage equipment via gateway.Target storage device can be closed with source storage device configurations at data image System, and by the Data Migration of gateway completion source storage equipment to target storage device.
It is above-mentioned it is found that by (2) plant method migrating data when, customer service need to be interrupted.In addition, Storage Virtualization gateway The access point of all storage equipment can be become, the path of data distributing is elongated, affects the performance of data center, reduces entirety The reliability of scheme, also, the access procedure of the Storage Virtualization gateway is complicated, at high cost, it is difficult to and it is a wide range of to realize.
(3) function based on storage equipment itself realizes Data Migration.
Specifically, part storage equipment can provide the functions such as duplicating remote data, data center can be real based on these functions Data Migration now across storage equipment.Referring to Fig. 1 C, in (3) kind method, target storage device is now linked into data center, And establish source storage equipment and target storage device between Data Replication Link, by the link by source store equipment in number According to copying in target storage device.After the completion of data initial synchronisation, customer service is interrupted, it is synchronous to carry out variance data.
It is above-mentioned it is found that by (3) plant method migrating data when, customer service need to be interrupted, it is complicated for operation, be easy error.
Based on above-mentioned the deficiencies in the prior art, present applicant proposes a kind of data back up method, relevant apparatus and systems, can Data Migration is completed in the case where not interrupting customer service, also, this method is suitable for cloud data center, it can be achieved that cloud data The highly reliable disaster tolerance requirement at center.
In order to better describe the application, the data center of the application is introduced first.
Referring to fig. 2, Fig. 2 is a kind of system architecture schematic diagram of data center provided by the present application.In the data of the application The heart can be cloud data center, cloud data center be support cloud computing service infrastructure, to server, storage resource, Internet resources, application resource etc. are virtualized, and user is allow to call various resources on demand.As shown in Fig. 2, the data center 200 can include: data center controller 101, the first storage array 102, the array control unit 103 of the first storage array 102, Two storage arrays 104, the array control unit 105 of the second storage array 104 and one or more physical machines 106.Data center's control Device 101 processed connects the first storage array 102, array control unit 103, the second storage array 104, data center controller 105, object Reason machine 106.Wherein:
Physical machine 106 is entity computer, and deployment thereon (running) has one or more virtual machine (virtual Machine, VM), each virtual machine occupies a part of physical resource, such as CPU, memory etc. of physical machine 106.Here, virtually Machine refers to be had the function of complete hardware system and operates in the complete computation in a completely isolated environment by what software was simulated Machine system can provide all kinds of services, such as calculating, object storage, mirroring service, identity service, block storage, database for user Service etc..It in physical machine 106, is mutually isolated between each virtual machine, the service that each virtual machine provides is to resource Demand is often different, such as some demands of service to CPU are higher, some demands of service to memory are higher, it will thus provide different The virtual machine of service is integrated into physical machine 106, and maximum resource utilization rate improves the computing capability of data center 200.
First storage array 102 and the second storage array 104 can be the storage mediums such as hard disk, disk.In order to store number According to the memory space in the first storage array 102 and the second storage array 104 is divided into several small units to be made to physical machine With these small storage resources can be described as storage unit, and storage unit is the minimum memory object of physical machine identification, belong to logic Object.That is, the first storage array 102 and the second storage array 104 may include multiple storage units, here, Mei Gecun Storage unit is identified by logical unit number (logical unit number, LUN).
First storage array 102 is for storing the data from physical machine 106.A kind of possibility is shown referring to Fig. 3, Fig. 3 Physical machine and the first storage array between resource impact relationship.As shown, being deployed with multiple virtual machines in physical machine (such as Virtual machine 1, virtual machine 2, virtual machine 3 in Fig. 3), the first storage array includes multiple storage units (LUN1- in such as Fig. 3 LUN8), storage unit can be mounted on virtual machine, be mounted to the storage unit on virtual machine for storing from the virtual machine Data.For example, LUN1, LUN2 and LUN3 are for storing the data for carrying out self virtualizing machine 1.Here, the battle array of the first storage array 102 Column controller 103 is used to manage the data interaction between the first storage array 102 and other equipment.
Second storage array 104 is used for and the first storage array 102 is configured to storage dual-active or replication relation, completes to deposit With postponing, the second storage array 104 can migrate the data in the first storage array 102 online, and can for storage dual-active or replication relation Synchronous newly-increased data of the storage from physical machine 106.Here, the array control unit 105 of the second storage array 104 is for managing the Data interaction between two storage arrays 104 and other equipment.
Data center controller 101 is used to dispatch all kinds of resources in data center 200, such as storage resource, calculating money Source, application resource etc..For example, data center controller 101 can be created when dispatching storage resource on storage array Storage volume (volume), storage volume and storage unit correspond, and data center controller 101 can be by physical machine 106 and wound The storage volume built carries out resource impact, i.e., the storage volume of the creation is for storing the data from physical machine 106.
Based on above-mentioned data center, present applicant proposes a kind of data back up method, can not interrupt customer service In the case of complete data backup.
Referring to fig. 4, Fig. 4 is the flow diagram of data back up method provided by the present application.This method can be applied to Fig. 2 institute The data center shown the data center controller in data center can execute as shown in Figure 2.As shown, the data backup side Method may include following steps:
S101, data center controller determine that the second storage unit, the second storage unit have in the second storage array Second identifier.
Specifically, data center controller is located at data center.The data center further includes the first storage array, second deposits Store up array and the first host.First host is mounted with the first storage unit, and the first storage unit is located at the first storage array, the One storage unit has first identifier.
Here, first identifier can pass through for the data transmission between the first host and the first storage array, the first host First identifier writes data into the first storage unit or reads data from the first storage unit.The first identifier can be first The logical unit number of storage unit identifies or the unique name (world wide name, WWN) in the whole world, or other identifier, The application is with no restrictions.
Wherein, the first storage array, the second storage array can be respectively the first storage array of data center shown in Fig. 2 102, the second storage array 104.In an alternative embodiment, the second storage unit and the first storage unit can be located at same storage Array, that is to say, that the first storage array and the second storage array can be same storage array.That is, the data of the application are standby Part method can carry out between the different storage units in same storage array.In another alternative embodiment, the second storage is single Member and the first storage unit can be located at different storage arrays, that is to say, that the first storage array and the second storage array can be with For different storage arrays.That is, the data back up method of the application can carry out between the storage unit in different storage arrays.
Wherein, the first host can be physical machine (such as physical machine 106 of data center shown in Fig. 2), or empty The quasi- machine virtual machine of carry (such as in the physical machine 106 of data center shown in Fig. 2), the application is with no restriction.It is intelligible, when When first host is physical machine, the storage unit for being mounted to the virtual machine disposed on first host also can be regarded as being mounted to On first host.Here, the first storage unit on the first host and first host are mounted to there are resource impact relationship, I.e. first storage unit is for storing the data from first host.
Optionally, data center controller in the second storage array determine the second storage unit when, specifically can by with Lower step is realized: creating storage volume (volume) on the second storage array, which is corresponding with storage unit (LUN), will The corresponding storage unit is as the second storage unit.In a specific embodiment, if the data center controller is based on The realization of OpenStack cloud computing platform, the component Cinder which can call for realizing block storage service, By in Cinder for create storage volume application programming interfaces (application programming interface, API), storage volume (storage volume of creation can be described as dual-active occupy-place volume) is created on storage array, the storage volume is corresponding to deposit Storage unit is the second storage unit (second storage unit can be described as dual-active LUN).Here, the second storage unit has second Mark, second identifier is for the data transmission between the first host and the second storage array.The second identifier can deposit for second The logical unit number of storage unit identifies or the unique name in the whole world, or other identifier, the application is with no restrictions.
In an alternative embodiment, second identifier is identical with first identifier, i.e. the first storage unit and the second storage unit can To share the same mark.
It optionally, can be in the second storage when data center controller determines the second storage unit in the second storage array The storage unit being in idle condition is selected in array, and selection and the first storage are single in the storage unit being in idle condition Member has the storage unit of identical capacity as the second storage unit.In another alternative, data center controller may be used also It selects to deposit with the storage unit than the first storage unit larger capacity as second in the storage unit being in idle condition Storage unit.By above two optional way, the capacity of the second storage unit can be made to back up the first storage unit enough Data.
Optionally, multi-path software can be disposed in the first host, and (multi-path software can be used for managing the first host and deposit Store up the data storage path between array).Since the first storage unit is mounted to the first host, multi-path software can obtain Know the physical access path of the first storage unit in the first storage array.Here, the first identifier characterization the of the first storage unit The physical access path of first storage unit in one storage array.It needs that data or needs are written to storage array in the first host When reading data from storage array, multi-path software can choose the physical access path by first identifier, will be main from first The data of machine are stored to the first storage unit, alternatively, the data from the first host are read from the first storage unit.
After data center controller determines the second storage unit in the second storage array, multi-path software would know that second The physical access path of second storage unit in storage array.Here, the second storage of second identifier characterization of the second storage unit The physical access path of second storage unit in array.It in the first host needs that data are written to storage array or need from storage When array reads data, multi-path software can choose the physical access path by second identifier, by the number from the first host According to storage to the second storage unit, alternatively, the data from the first host are read from the second storage unit.
That is, the data from the first host at least have 2 groups of store paths in the data center, (1 group is direction The physical access path of first storage unit, another 1 group is the physical access path for being directed toward the second storage unit).That is, coming from first The data of host can be stored by first identifier to the first storage unit, can also be stored by second identifier to the second storage Unit.In addition, the first host both can by first identifier from the first storage unit read data, can also by second identifier from Second storage unit reads data.
The corresponding relationship of S102, data center controller record first identifier and second identifier.
S103, data center controller send the first configuration information to the array control unit of the first storage array, and first matches Confidence breath includes the corresponding relationship, wherein the first configuration information is used to indicate the array control unit of the first storage array according to this First host is written to the data backup of the first storage unit to the second storage unit corresponding relationship.
Specifically, after the corresponding relationship of data center controller storage first identifier and second identifier, to the first storage The array control unit of array sends the first configuration information, which includes the corresponding relationship.First storage array First host can be written to the first storage according to the first identifier of storage and the corresponding relationship of second identifier by array control unit The data backup of unit is to the second storage unit.Here, data biography can be established between the second storage unit and the first storage unit Defeated channel, the first storage unit can be single to the second storage by the data backup that the first host is written the data transmission channel Member.Here, the first host be written the first storage unit data can include: data center controller determine the second storage unit it Existing primary data in preceding first storage unit, and, data center controller determines after the second storage unit that first deposits Newly-increased data in storage unit.
Optionally, in step s 103, the array control unit of the first storage array is according to the corresponding relationship by the first host After write-in to the data backup to the second storage unit of the first storage unit, the second storage unit can be returned to the first storage unit Successful feedback message is written, the first storage unit returns to the first host successful feedback message is written again.First host base The data are successfully written in feedback message determination.
Implement data back up method shown in Fig. 4, it can be by the data backup of the first storage unit to the second storage unit.And And since the first storage unit is mounted to the first host, the first storage unit can always be customer service service, main first During the data backup to the second storage unit of the first storage unit is written in machine, customer service can be not disrupted.
Referring to Fig. 5, Fig. 5 is the flow diagram of another data back up method provided by the present application.This method can be by Fig. 2 Data center controller in shown data center executes.Method shown in method and Fig. 4 shown in Fig. 5 the difference is that, number Configuration information can be sent to the array control unit of the second storage array according to master controller, the second storage unit will be connect The data backup from the first host received is to the first storage unit.
As shown, the data back up method may include following steps:
S201, data center controller determine the second storage unit, second storage unit in the second storage array With second identifier.
S202, data center controller record the corresponding relationship of the first identifier and the second identifier.
S203, data center controller send the first configuration information, institute to the array control unit of first storage array Stating the first configuration information includes the corresponding relationship, wherein first configuration information is used to indicate first storage array Array control unit according to the corresponding relationship by first host be written to first storage unit data backup extremely Second storage unit.
Here, the realization of step S201-S203 is identical with the realization of the step S101-S103 in method shown in Fig. 4, can join According to associated description.
S204, data center controller send the second configuration information to the array control unit of the second storage array, and second matches Confidence breath includes the corresponding relationship, wherein the second configuration information is used to indicate the array control unit of the second storage array according to this First host is written to the data backup of the second storage unit to the first storage unit corresponding relationship.
Specifically, after the corresponding relationship of data center controller storage first identifier and second identifier, to the second storage The array control unit of array sends the second configuration information, which includes the corresponding relationship.Second storage array First host can be written to the second storage according to the first identifier of storage and the corresponding relationship of second identifier by array control unit The data backup of unit is to the first storage unit.Here, data biography can be established between the second storage unit and the first storage unit Defeated channel, the second storage unit can be single to the first storage by the data backup that the first host is written the data transmission channel Member.Here, the first host be written the second storage unit data can include: data center controller determine the second storage unit it Afterwards, the data in the second storage unit are written in the first host.
Optionally, in step S204, the array control unit of the second storage array is according to the corresponding relationship by the first host After write-in to the data backup to the first storage unit of the second storage unit, the first storage unit can be returned to the second storage unit Successful feedback message is written, the second storage unit returns to the first host successful feedback message is written again.First host base The data are successfully written in feedback message determination.
S203 and S204 through the above steps, data center controller records first identifier and the corresponding of second identifier is closed System, and the corresponding relationship is sent respectively to the array control unit of the first storage array, the array control unit of the second storage array, It may make the first host that the data backup of the first storage unit is written to the second storage unit, so that the first host write-in second is deposited The data backup of storage unit is to the first storage unit.In addition, the first host both can read data from the first storage unit, it can also To read data from the second storage unit.That is, the first storage unit and the second storage unit can be used in processing first The data access request of host.
Implement data back up method shown in fig. 5, when the data full backup stored in the first storage unit to second is deposited After storage unit, the second storage unit has full dose data identical with the first storage unit.It breaks down in the first storage unit When, the second storage unit can be used as disaster tolerance storage unit, continues as customer service and is serviced, and can avoid in customer service It is disconnected, guarantee the reliability of data center.
Optionally, method shown in Fig. 4 or Fig. 5 can comprise the further steps of: multiple dual-actives to being added to same dual-active one In cause property group, the splitting time of the dual-active pair in same dual-active consistency group is identical；Each dual-active is to including at least two storages Unit, wherein multiple dual-actives to including dual-active pair that the first storage unit and the second storage unit form, each dual-active centering Storage unit is mounted to the first host；And/or the storage unit of multiple dual-active pair is mounted to the first host or second respectively Host, the first host and the second host belong to the same service groups of data center.
Specifically, introducing dual-active first to (pair) and dual-active consistency group.
Dual-active is formed to by least two storage units, is originated from the storage array for being configured with dual-active relationship.This two In a storage unit, when having data that any one storage unit is written, storage unit meeting data to be written is synchronously written into Another internal storage unit of dual-active.That is, the data that the storage unit of dual-active centering is stored are synchronous.
The splitting time that each dual-active pair in same dual-active consistency group is added is identical.Here, in some storage unit When failure, it is synchronous that remaining memory cell no longer carries out data with the fault memory cell, remaining memory cell and the failure Storage unit carries out the time point that data synchronize no longer as splitting time.In order to guarantee the consistency of data, dual-active consistency group In each dual-active pair splitting time it is identical.Optionally, the splitting time of each dual-active pair in same dual-active consistency group For the earliest practical splitting time of each dual-active pair.
For example, if in a dual-active consistency group include 2 dual-actives pair: dual-active to 1 (including LUN1 and LUN1 '), Dual-active breaks down to 2 (including LUN2 and LUN2 '), LUN1 in 10:00, and LUN1 ' stops synchronous with LUN1 progress data at this time, LUN2 breaks down in 10:02, and LUN2 ' stops synchronous with LUN2 progress data at this time.That is, practical splitting time of the dual-active to 1 For 10:00, dual-active is 10:02 to 2 practical splitting time.Due to dual-active to 1 and dual-active to 2 in same dual-active consistency group In, in order to guarantee the consistency of data, dual-active is consistent 2 and dual-active to 1, dual-active completed number when also taking 10:00 to 2 According to synchronization.That is, even if dual-active just breaks down to LUN2 in 2 in 10:02, LUN2 ' takes available when also only taking 10:00 Data.
In the application, data center controller can be multiple by multiple dual-actives to being added in same dual-active consistency group Dual-active centering includes pair of the first storage unit referred in embodiment of the method shown in Fig. 4 or Fig. 5 and the second storage unit composition Living pair.Optionally, data center controller can by following two strategy by multiple dual-actives to being added to same dual-active consistency In group:
(1) storage unit of multiple dual-active centering is mounted to the first host.
Specifically, the data of multiple storage units in same host are in storage array failure, it may be necessary to keep one Cause property.Data center controller can be by the corresponding dual-active of these storage units to being added in same dual-active consistency group.
For example, referring to Fig. 6, it is assumed that include the first storage array and the second storage array in data center, first deposits Storing up includes 5 storage units: LUN1, LUN2, LUN3, LUN4, LUN5 on array, includes corresponding 5 on the second storage array Storage unit: LUN1 ', LUN2 ', LUN3 ', LUN4 ', LUN5 '.Wherein, LUN1 and LUN1 ' composition dual-active to 1, LUN2 and LUN2 ' forms dual-active to 2, LUN3 and LUN3 ' dual-active is formed to 3, LUN4 and LUN4 ' dual-active is formed to 4, LUN5 and LUN5 ' group At dual-active to 5.Wherein, LUN1, LUN2, LUN3, LUN1 ', LUN2 ', LUN3 ' be mounted to the virtual machine 1 disposed in physical machine, LUN4, LUN5, LUN4 ', LUN5 ' be mounted to the virtual machine 2 disposed in physical machine.So, can by dual-active to 1, dual-active to 2 and double Work is added to dual-active consistency group 1 to 3, and dual-active is added to dual-active consistency group 2 to 5 to 4 and dual-active.
(2) storage unit of multiple dual-active centering is mounted to the first host or the second host respectively, the first host and Second host belongs to the same service groups of data center.
Specifically, may also include the second host in data center, the first host and the second host can belong to same service groups, That is, the first host and the second host may need to cooperate operation, the data of the data of the first host and the second host need to keep Consistency.Therefore, data center controller can be by the corresponding dual-active of storage unit on the first host and the second host to all adding It is added in same dual-active consistency group, here, the storage unit of dual-active centering is mounted to the first host or the second host.
For example, it is identical with the example in above-mentioned (1) kind strategy referring to Fig. 6, if virtual machine 1 and virtual machine 2 belong to Dual-active then can be added to same dual-active consistency to 5 to 4 and dual-active to 3, dual-active to 2, dual-active to 1, dual-active by same service groups Group.
By the step in above-mentioned optional way, data center controller is consistent to same dual-active is added to by multiple dual-actives Property group in, it is ensured that storage failure when, multiple dual-actives to division when data consistency.
Optionally, method shown in Fig. 4 or Fig. 5 can comprise the further steps of: the array control unit general in the first storage array First host is sent to after the data backup to the second storage unit of the first storage unit, and data center controller is main from first Machine unloads the first storage unit.
Specifically, implement Fig. 4 or Fig. 5 shown in method, the first storage unit by the data backup from the first host extremely After second storage unit, i.e. after the data stored in the second storage unit are consistent with the first storage unit, data center controller The first storage unit can be unloaded from the first host.After unloading the first storage unit, the total data access request of the first host is equal Processing is responsible for by the second storage unit, customer service service can be continued as by being equivalent to the second storage unit.
By above-mentioned optional step, data can be moved from the first storage unit in the case where not interrupting customer service The second storage unit is moved on to, the online replacement of storage array can be completed.Therefore, implement above scheme, even if in the first storage When unit breaks down, the data access request of the first host can also be continued in the case where not interrupting customer service, The high reliability disaster tolerance requirement of data center can be met.
Optionally, in the method shown in Fig. 4 or Fig. 5, the first memory cell arrangements can be main memory by data center controller Second memory cell arrangements are from storage unit by storage unit.Before executing above-mentioned optional step, i.e. data center controller Before unloading the first storage unit from the first host, data center controller can by the first storage unit and the second storage unit into Row role exchanges, i.e., is from storage unit by the first memory cell arrangements, is main memory unit by the second memory cell arrangements.Number The first storage unit can be unloaded from storage unit by unloading according to master controller, here, data center controller unloading first The concrete operations of storage unit can refer to subsequent descriptions.
Optionally, in the method shown in Fig. 4 or Fig. 5, if data center controller stores the first storage unit and second The dual-active of unit composition is to joined in dual-active consistency group, then data center controller is stored from the first host unloading first Before unit, the dual-active that can form first storage unit and the second storage unit is to the removal dual-active consistency group.
In the application, it specifically may include following operation that data center controller, which unloads the first storage unit from the first host: Data center controller releases the carry relationship of the first storage unit to the first host, i.e. the first storage unit and the first host it Between there is no the mapping relations of storage resource, the first storage unit is no longer used to store the data from the first host.Here, if First storage unit is configured as from storage unit, which can be regarded as to dual-active occupy-place volume.It is specific at one Embodiment in, if the data center controller based on OpenStack cloud computing platform realize, the data center controller is adjustable With for realizing the component N ova for calculating service, expansion interface is rolled up by the online reconnection of Nova, delete the first storage unit and The mapping relations of first host.
Optionally, after data center controller unloads the first storage unit from the first host, data center controller The data stored in the first storage unit can be deleted.Here, for the first storage unit after the unloading of the first host, the first storage is single Still it is stored with user data in member, deletes the user data stored in the first storage unit, it can be ensured that data safety.
Referring to Fig. 7, Fig. 7 is the flow diagram of another data back up method provided by the present application.Method shown in Fig. 7 can Applied to data center, which includes the first host, and the first host is mounted with the first storage unit, the first storage unit Positioned at the first storage array, the first storage unit has first identifier, which further includes data center controller.The party Method the array control unit of the first storage array in data center and the array control unit of the second storage array can be held as shown in Figure 2 Row.
As shown, the data back up method may include following steps:
First configuration information of the array control unit reception data center controller transmission of S301, the first storage array, the One configuration information includes the corresponding relationship of the second identifier of first identifier and the second storage unit, wherein the second storage unit by Data center controller determines in the second storage array.
S302, the first storage array array control unit the first host is written according to the corresponding relationship it is single to the first storage The data backup of member is to the second storage unit.
Intelligible, the realization of step S301-S302 can refer to the associated description of embodiment of the method shown in Fig. 4, herein not It repeats.
Optionally, method shown in Fig. 7 can comprise the further steps of:
Second configuration information of the array control unit reception data center controller transmission of S303, the second storage array, the Two configuration informations include the corresponding relationship.
S304, the second storage array array control unit the first host is written according to the corresponding relationship it is single to the second storage The data backup of member is to the first storage unit.
Intelligible, the realization of step S303-S304 can refer to the associated description of embodiment of the method shown in Fig. 4, herein not It repeats.
Implement method shown in Fig. 7, after data full backup to the second storage unit stored in the first storage unit, Second storage unit has full dose data identical with the first storage unit.When the first storage unit breaks down, second is deposited Storage unit can be used as disaster tolerance storage unit, continues as customer service and is serviced, and can avoid the interruption of customer service, guarantee number According to the reliability at center.
The foregoing detailed description data back up method of the application, in order to better implement the present processes, correspondingly, The device of the application is provided below.
Referring to Fig. 8, Fig. 8 is the structural schematic diagram of data center controller 800 provided by the present application.Data center controller 800 can be implemented as the data center controller 101 of data center shown in Fig. 2, can also be method shown in Fig. 4, Fig. 5 and Fig. 7 Data center controller in embodiment.
As shown in figure 8, data center controller 800 may include: processing unit 801 and communication interface 802, in which:
Processing unit 801 is for executing the operating system run on data center controller 800 and various software programs Defined function, for example, the function that data center controller is realized in above-mentioned Fig. 4 and Fig. 5 embodiment.Specifically, for example, Processing unit is used to determine the second storage unit in the second storage array, records first identifier and the corresponding of second identifier is closed System sends first configuration information etc. to the array control unit of the first storage array.
Communication interface 802 is used to carry out communication interaction with other calculate nodes, and other equipment can be array control unit, the One host etc..Specifically, communication interface 802 can be adapter.
Optionally, which can also include input/output interface 803, input/output interface 803 It is connected with input-output apparatus, information for receiving input exports operating result.Input/output interface 803 can be mouse Mark, keyboard, display or CD-ROM drive etc..
Optionally, which can also include additional storage 804, also commonly referred to as external memory, auxiliary The storage medium of memory 804 can be magnetic medium (for example, floppy disk, hard disk, tape), optical medium (such as CD) or Semiconductor medium (such as solid state hard disk) etc..
Optionally, processing unit 801 can there are many specific implementation forms, such as processing unit 801 may include processing Device 8011 and memory 8012, processor 8011 execute relevant operation according to the realization program stored in memory 8012.Here, interior Data back up method that one or more embodiments that the realization program that stores in 8012 is the application provide is deposited in data center The realization program of controller side.Wherein, processor 8011 can be central processing unit (CPU) or image processor (graphics Processing unit, GPU), processor 8011 can be single core processor or multi-core processor.Processing unit 801 can also be with It is individually realized using the logical device of built-in processing logic, such as field programmable gate array (field programmable Gate array, FPGA) or digital signal processor (digital signal processor, DSP) etc..
In addition, Fig. 8 is only an example of a data center controller 800, data center controller 800 may packet Containing the more perhaps less component shown compared to Fig. 8 or there is different component Configuration modes.
Referring to Fig. 9, Fig. 9 is the structural schematic diagram of array control unit 900 provided by the present application.Array control unit 900 can be with It is embodied as the array control unit 103 of data center shown in Fig. 2, can also is the battle array in embodiment of the method shown in Fig. 4, Fig. 5 and Fig. 7 Column controller.
As shown in figure 9, array control unit 900 may include: processing unit 901 and communication interface 902, in which:
Processing unit 901 is used to execute the operating system run on array control unit 900 and various software programs are determined The function of justice, for example, the function that array control unit is realized in above-mentioned Fig. 7 embodiment.Specifically, for example, processing unit is used for The first host is written to the data backup of the first storage unit to second according to the corresponding relationship of first identifier and second identifier Storage unit etc..
Communication interface 902 is used to carry out communication interaction with other calculate nodes, and other equipment can be data center's control Device, first storage array etc..Specifically, communication interface 902 can be adapter.
Optionally, which can also include input/output interface 903, and input/output interface 903 connects There is input-output apparatus, information for receiving input exports operating result.Input/output interface 903 can be mouse, key Disk, display or CD-ROM drive etc..
Optionally, which can also include additional storage 904, also commonly referred to as external memory, auxiliary storage The storage medium of device 904 can be magnetic medium (for example, floppy disk, hard disk, tape), optical medium (such as CD) or partly lead Body medium (such as solid state hard disk) etc..
Optionally, processing unit 901 can there are many specific implementation forms, such as processing unit 901 may include processing Device 9011 and memory 9012, processor 9011 execute relevant operation according to the realization program stored in memory 9012.Here, interior Data back up method that one or more embodiments that the realization program that stores in 9012 is the application provide is deposited in antenna array control The realization program of device side.Wherein, processor 9011 can be CPU or GPU, and processor 9011 can be single core processor or multicore Processor.Processing unit 901 can also be realized individually using the logical device of built-in processing logic, such as FPGA or DSP etc..
In addition, Fig. 9 is only an example of an array control unit 900, array control unit 900 may comprising compared to The more perhaps less component or have different component Configuration modes that Fig. 9 is shown.
Referring to Figure 10, Figure 10 is the functional block diagram of data center controller 1000 provided by the present application.Data center's control Device 1000 can be implemented as the data center controller 101 of data center shown in Fig. 2, can also be side shown in Fig. 4, Fig. 5 and Fig. 7 Data center controller in method embodiment.Data center controller 1000 is located at data center, and data center includes first main Machine, the first host are mounted with the first storage unit, and the first storage unit is located at the first storage array, and the first storage unit has the One mark.As shown, data center controller 1000 can include: MMU memory management unit 1001, wherein
MMU memory management unit 1001, for determining the second storage unit, the second storage unit tool in the second storage array There is second identifier；Record the corresponding relationship of first identifier and second identifier；The is sent to the array control unit of the first storage array One configuration information, the first configuration information include the corresponding relationship, wherein the first configuration information is used to indicate the first storage array The first host is written to the data backup of the first storage unit to the second storage unit according to the corresponding relationship for array control unit.
Optionally, it when MMU memory management unit 1001 determines the second storage unit in the second storage array, can be deposited second The storage unit being in idle condition is selected in storage array；Selection and the first storage are single in the storage unit being in idle condition Member has the storage unit of identical capacity as the second storage unit.
Optionally, second identifier is identical as first identifier.
Optionally, MMU memory management unit 1001, it may also be used for: second, which is sent, to the array control unit of the second storage array matches Confidence breath, the second configuration information includes the corresponding relationship, wherein the second configuration information is used to indicate the array of the second storage array The first host is written to the data backup of the second storage unit to the first storage unit according to the corresponding relationship for controller.
Optionally, data center controller 1000 may also include unloading unit 1002, and unloading unit 1002 is used for: first First host is sent to after the data backup to the second storage unit of the first storage unit by the array control unit of storage array, The first storage unit is unloaded from the first host.
It is intelligible, the specific implementation for each functional unit that data center controller 1000 includes can refer to earlier figures 4, The associated description of embodiment of the method shown in Fig. 5 and Fig. 7, which is not described herein again.
In data center, using data center controller 1000 shown in Fig. 10, the second storage unit can be used for backing up The data stored in second storage unit.In addition, the second storage unit can be used as appearance when the first storage unit breaks down Calamity storage unit continues as customer service and is serviced, and can avoid the interruption of customer service, guarantees the reliability of data center.
Referring to Figure 11, Figure 11 is the functional block diagram of array control unit 1100 provided by the present application.Array control unit 1100 can It, can also be in embodiment of the method shown in Fig. 4, Fig. 5 and Fig. 7 to be embodied as the array control unit 103 of data center shown in Fig. 2 The array control unit of first storage array.Array control unit 1100 is used for the first storage array, has the on the first storage array One storage unit, for the first storage unit carry on the first host of data center, the first storage unit has first identifier, should Data center further includes data center controller；Array control unit 1100 includes: receiving unit 1101 and backup units 1102,
Receiving unit 1101, the first configuration information that master controller is sent for receiving data, the first configuration information packet Include the corresponding relationship of the second identifier of first identifier and the second storage unit, wherein the second storage unit is controlled by data center Device determines in the second storage array；
Backup units 1102, for the first host to be written to the data backup of the first storage unit according to the corresponding relationship To the second storage unit.
Optionally, the second storage unit has identical capacity with the first storage unit.
Optionally, second identifier is identical as first identifier.
Intelligible, the specific implementation for each functional unit that array control unit 1100 includes can refer to earlier figures 4, Fig. 5 And the associated description of embodiment of the method shown in Fig. 7, which is not described herein again.
To sum up, implement technical solution provided by the present application, the second storage unit can be used for backing up the first storage unit Data, in addition, the second storage unit can be used as disaster tolerance storage unit, continue as using when the first storage unit breaks down Family business is serviced, and be can avoid the interruption of customer service, is guaranteed the reliability of data center.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or It partly generates according to process described herein or function.The computer can be general purpose computer, special purpose computer, meter Calculation machine network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or It is transmitted from a computer readable storage medium to another computer readable storage medium, for example, the computer instruction can To pass through wired (such as coaxial cable, optical fiber, digital subscriber from a web-site, computer, server or data center Line) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or data center into Row transmission.The computer readable storage medium can be any usable medium or include one that computer can access Or the data storage devices such as integrated server, data center of multiple usable mediums.The usable medium can be magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid State Disk) etc..

Claims (19)

1. a kind of data back up method, which is characterized in that the first host of data center is mounted with the first storage unit, and described One storage unit is located at the first storage array, and first storage unit has first identifier, and the data center further includes number According to master controller；The described method includes:
The data center controller determines that the second storage unit, second storage unit have the in the second storage array Two marks；
The data center controller records the corresponding relationship of the first identifier and the second identifier；
The data center controller to the array control unit of first storage array send the first configuration information, described first Configuration information includes the corresponding relationship, wherein first configuration information is used to indicate the array of first storage array First host is written to the data backup of first storage unit to described according to the corresponding relationship for controller Two storage units.
2. the method according to claim 1, wherein the data center controller is true in the second storage array Fixed second storage unit, comprising:
The data center controller selects the storage unit being in idle condition in second storage array；
The data center controller selects to have with first storage unit in the storage unit being in idle condition There is the storage unit of identical capacity as second storage unit.
3. method according to claim 1 or 2, which is characterized in that the second identifier is identical as the first identifier.
4. method according to claim 1-3, which is characterized in that the method also includes:
The data center controller to the array control unit of second storage array send the second configuration information, described second Configuration information includes the corresponding relationship, wherein second configuration information is used to indicate the array of second storage array First host is written to the data backup of second storage unit to described according to the corresponding relationship for controller One storage unit.
5. method according to any of claims 1-4, which is characterized in that the method also includes:
First host is sent to the data of first storage unit in the array control unit of first storage array It backs up to after second storage unit, the data center controller is single from first host unloading, first storage Member.
6. a kind of data back up method, which is characterized in that the first host of data center is mounted with the first storage unit, and described One storage unit is located at the first storage array, and first storage unit has first identifier, and the data center further includes number According to master controller；The described method includes:
The array control unit of first storage array receives the first configuration information that the data center controller is sent, described First configuration information includes the corresponding relationship of the second identifier of the first identifier and the second storage unit, wherein described second Storage unit is determined in the second storage array by the data center controller；
First host is written to described first according to the corresponding relationship for the array control unit of first storage array The data backup of storage unit is to second storage unit.
7. according to the method described in claim 6, it is characterized in that, second storage unit and first storage unit have There is identical capacity.
8. method according to claim 6 or 7, which is characterized in that the second identifier is identical as the first identifier.
9. according to the described in any item methods of claim 6-8, which is characterized in that the method also includes:
The array control unit of second storage array receives the second configuration information that the data center controller is sent, described Second configuration information includes the corresponding relationship；
First host is written to described second according to the corresponding relationship for the array control unit of second storage array The data backup of storage unit is to first storage unit.
10. a kind of data center controller, which is characterized in that the data center controller is located at data center, data center The first host be mounted with the first storage unit, first storage unit is located at the first storage array, and first storage is single Member has first identifier；The data center controller includes: MMU memory management unit；
The MMU memory management unit, is used for:
Determine that the second storage unit, second storage unit have second identifier in the second storage array；
Record the corresponding relationship of the first identifier and the second identifier；
The first configuration information is sent to the array control unit of first storage array, first configuration information includes described right It should be related to, wherein first configuration information is used to indicate the array control unit of first storage array according to the correspondence First host is written to the data backup of first storage unit to second storage unit relationship.
11. data center controller according to claim 10, which is characterized in that described to be determined in the second storage array Second storage unit, comprising:
The storage unit being in idle condition is selected in second storage array；
The storage list that there is identical capacity with first storage unit is selected in the storage unit being in idle condition Member is used as second storage unit.
12. data center controller described in 0 or 11 according to claim 1, which is characterized in that the second identifier and described the One mark is identical.
13. the described in any item data center controllers of 0-12 according to claim 1, which is characterized in that the storage management list Member is also used to:
The second configuration information is sent to the array control unit of second storage array, second configuration information includes described right It should be related to, wherein second configuration information is used to indicate the array control unit of second storage array according to the correspondence First host is written to the data backup of second storage unit to first storage unit relationship.
14. the described in any item data center controllers of 0-13 according to claim 1, which is characterized in that data center's control Device processed further includes unloading unit, and the unloading unit is used for:
First host is sent to the data of first storage unit in the array control unit of first storage array It backs up to after second storage unit, unloads first storage unit from first host.
15. a kind of array control unit, which is characterized in that the array control unit is used for the first storage array, first storage There is the first storage unit, on the first host of data center, described first deposits the first storage unit carry on array Storage unit has first identifier, and the data center further includes data center controller；The array control unit includes: to receive list Member and backup units,
The receiving unit, the first configuration information sent for receiving the data center controller, described first matches confidence Breath includes the corresponding relationship of the second identifier of the first identifier and the second storage unit, wherein second storage unit by The data center controller determines in the second storage array；
The backup units, for first host to be written to the number of first storage unit according to the corresponding relationship According to backing up to second storage unit.
16. array control unit according to claim 15, which is characterized in that second storage unit is deposited with described first Storage unit has identical capacity.
17. array control unit according to claim 15 or 16, which is characterized in that the second identifier and first mark It is sensible same.
18. a kind of calculating equipment, which is characterized in that the calculating equipment includes processor and memory, the processor operation Computer instruction in the memory, for realizing method described in claim 1-5.
19. a kind of calculating equipment, which is characterized in that the calculating equipment includes processor and memory, the processor operation Computer instruction in the memory, for realizing method described in claim 6-9.
CN201810931053.3A 2018-08-15 2018-08-15 Data backup method, related device and system Active CN109254873B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810931053.3A CN109254873B (en) 2018-08-15 2018-08-15 Data backup method, related device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810931053.3A CN109254873B (en) 2018-08-15 2018-08-15 Data backup method, related device and system

Publications (2)

Publication Number Publication Date
CN109254873A true CN109254873A (en) 2019-01-22
CN109254873B CN109254873B (en) 2022-04-22

Family

ID=65048753

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810931053.3A Active CN109254873B (en) 2018-08-15 2018-08-15 Data backup method, related device and system

Country Status (1)

Country Link
CN (1) CN109254873B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113010259A (en) * 2019-12-20 2021-06-22 上海云轴信息科技有限公司 Storage method and device of two-node ultra-fusion all-in-one machine
CN113691342A (en) * 2021-09-13 2021-11-23 上海云轴信息科技有限公司 Method and system for time synchronization of virtualization platform
CN116166477A (en) * 2022-11-30 2023-05-26 贵州华谊联盛科技有限公司 Dual-activity gateway system and method for storing different brands of objects

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101937378A (en) * 2009-07-01 2011-01-05 联想(北京)有限公司 Method for carrying out back-up protection on data of storage equipment and computer system
CN102929748A (en) * 2012-11-08 2013-02-13 华为技术有限公司 Method and device for data backup
CN103064763B (en) * 2012-12-27 2015-12-02 华为技术有限公司 A kind of data back up method and relevant device, system
CN106855834A (en) * 2015-12-08 2017-06-16 华为技术有限公司 A kind of data back up method, device and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101937378A (en) * 2009-07-01 2011-01-05 联想(北京)有限公司 Method for carrying out back-up protection on data of storage equipment and computer system
CN102929748A (en) * 2012-11-08 2013-02-13 华为技术有限公司 Method and device for data backup
CN103064763B (en) * 2012-12-27 2015-12-02 华为技术有限公司 A kind of data back up method and relevant device, system
CN106855834A (en) * 2015-12-08 2017-06-16 华为技术有限公司 A kind of data back up method, device and system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113010259A (en) * 2019-12-20 2021-06-22 上海云轴信息科技有限公司 Storage method and device of two-node ultra-fusion all-in-one machine
CN113691342A (en) * 2021-09-13 2021-11-23 上海云轴信息科技有限公司 Method and system for time synchronization of virtualization platform
CN116166477A (en) * 2022-11-30 2023-05-26 贵州华谊联盛科技有限公司 Dual-activity gateway system and method for storing different brands of objects
CN116166477B (en) * 2022-11-30 2024-02-13 郭东升 Dual-activity gateway system and method for storing different brands of objects

Also Published As

Publication number Publication date
CN109254873B (en) 2022-04-22

Similar Documents

Publication Publication Date Title
US9671967B2 (en) Method and system for implementing a distributed operations log
CN114341792B (en) Data partition switching between storage clusters
CN106528327B (en) A kind of data processing method and backup server
US10614096B2 (en) Disaster recovery of mobile data center via location-aware cloud caching
CN100530124C (en) System and method for relocating running applications to topologically remotely located computing systems
US9733989B1 (en) Non-disruptive load-balancing of virtual machines between data centers
TWI414992B (en) Method for remote asynchronous replication of volumes and apparatus therefor
CN106708603B (en) Virtual machine quick recovery method and device
US11647075B2 (en) Commissioning and decommissioning metadata nodes in a running distributed data storage system
CN107402722B (en) Data migration method and storage device
CN101084481A (en) A method to perform parallel data migration in a clustered storage environment
JP2009157785A (en) Method for adding standby computer, computer and computer system
US10534796B1 (en) Maintaining an active-active cloud across different types of cloud storage services
CN109254873A (en) Data back up method, relevant apparatus and system
CN103019804B (en) The virtualized VPS quick migration method of OpenVZ
US8682852B1 (en) Asymmetric asynchronous mirroring for high availability
CN105740052A (en) Method, device and system for online migration of virtual machines of non-shared memories
CN112328365A (en) Virtual machine migration method, device, equipment and storage medium
CN107402839A (en) A kind of method and system of Backup Data
CN110413369A (en) System and method for the backup in virtualized environment
US11681443B1 (en) Durable data storage with snapshot storage space optimization
CN105488139B (en) The method of cross-platform storing data migration based on power information acquisition system
US10803010B2 (en) Message affinity in geographically dispersed disaster restart systems
WO2023061266A1 (en) Logical volume construction method and apparatus, and device, readable storage medium and program product
US10891205B1 (en) Geographically dispersed disaster restart multitenancy systems

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20220207

Address after: 550025 Huawei cloud data center, jiaoxinggong Road, Qianzhong Avenue, Gui'an New District, Guiyang City, Guizhou Province

Applicant after: Huawei Cloud Computing Technology Co.,Ltd.

Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen

Applicant before: HUAWEI TECHNOLOGIES Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant