CN106528338A - Remote data replication method, storage equipment and storage system - Google Patents
Remote data replication method, storage equipment and storage system Download PDFInfo
- Publication number
- CN106528338A CN106528338A CN201610971200.0A CN201610971200A CN106528338A CN 106528338 A CN106528338 A CN 106528338A CN 201610971200 A CN201610971200 A CN 201610971200A CN 106528338 A CN106528338 A CN 106528338A
- Authority
- CN
- China
- Prior art keywords
- controller
- data
- replication task
- replication
- file
- 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
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
- G06F11/1461—Backup scheduling policy
-
- 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
- G06F11/1448—Management of the data involved in backup or backup restore
Abstract
The invention discloses a remote data replication method, storage equipment and a storage system. A first controller detects whether a replication task exists in the local or not; when a replication task is not available in the first controller, the first controller sends a request message to a second controller, wherein the request message is used for applying for a replication task from the second controller; the second controller comprises at least two replication tasks; the second controller reads data corresponding to the first replication task and sends the data to the first controller according to the request message; the first controller receives the data corresponding to the first replication task, and sends the data corresponding to the first replication task to a disaster recovery array; and the second controller sends the data corresponding to the second replication task to the disaster recovery array. Therefore, the purpose of parallel data replication in a multi-control system is achieved.
Description
Technical field
The present embodiments relate to technical field of memory, particularly a kind of duplicating remote data method, storage device and deposit
Storage system.
Background technology
Data disaster tolerance, is also called duplicating remote data technology, refers to the data system for setting up a strange land, and the system is this
One available duplication of ground data.When disaster occur in local data and whole application system, system is at least preserved in strange land
The data of a available key business.
Typical data disaster tolerance system includes the production center and Disaster Preparation Center.The heart, is deployed with main frame, storage battle array aborning
Row, for normal service operation;In Disaster Preparation Center, main frame, storage array are deployed with, disaster occurs for the heart aborning
Afterwards, take over its business.In mass storage system (MSS), the storage array of the production center and the storage array of Disaster Preparation Center are generally all
Storage array comprising multiple controllers.Different controllers can be write and be changed to same file respectively, in order to
The file of file and the production center that guarantee copies to Disaster Preparation Center is consistent, the write that each controller is carried out to this document
Operation needs serial to copy to Disaster Preparation Center, have impact on duplicating efficiency.
The content of the invention
A kind of duplicating remote data method and storage system are present embodiments provided, can concomitantly be held in many control systems
Row replication task.
A kind of first aspect, there is provided duplicating remote data method.Methods described is applied in storage system, the storage
System includes producing array and calamity for array, and the production array at least includes the first controller and second controller.First control
Whether device detection processed locally has replication task, when no replication task, sends request message to second controller.The request
Message is for the second controller application replication task, second controller at least includes two replication tasks.Second control
Device gives first controller according to the request message, the corresponding Data Concurrent of first replication task of reading.First control
Device processed receives the corresponding data of first replication task, will be first replication task corresponding data is activation standby to calamity
Array, second controller also by second replication task corresponding data is activation to the calamity for array.
In the present embodiment, the first controller does not have replication task, and in idle condition, and second controller at least includes
Two replication tasks, in busy state.Therefore, the first controller can send request message to second controller, to apply
Replication task.At least two two replication tasks of oneself are distributed one to the according to the request message by second controller
One controller, so as to the first controller and second controller can each perform a replication task, has reached parallel processing
Purpose, improve duplicating efficiency.
In the first embodiment of first aspect, the second controller safeguards there is replication queue, the duplication team
Row include at least two replication task.Therefore, second controller obtains first again specifically from the replication queue
Task processed, and the first controller is given by first replication task corresponding data is activation.In addition, second controller is also from described
The second replication task is obtained in replication queue, by second replication task corresponding data is activation to the calamity for array.
With reference in a first aspect, and first aspect the first embodiment, in second embodiment, first is multiple
Task processed and second replication task are the replication tasks for same file.Thus achieve same file simultaneously
Row is replicated.
With reference to second embodiment of first aspect, in the third embodiment, the file has unique text
Part name, the corresponding data of first replication task include the filename, the primary data of the file, and it is described just
The write time of beginning data, the corresponding data of second replication task include the filename, the modification number of the file
According to, and the write time of the modification data, when the write time of the modification data is later than the write of the primary data
Between.
With reference to the third embodiment of first aspect, in the 4th kind of embodiment, the calamity is for described in array received
The corresponding data of first replication task, create the backup file of the file, by primary data write described backup text
Part, the filename of the backup file are identical with the filename of the file.First replication task pair is received described
After the data answered, the calamity is for the corresponding data of second replication task described in array received.The calamity determines institute for array
State the corresponding filename of second replication task it is identical with the filename of the backup file when, judge described to change writing for data
Whether the angle of incidence is later than the write time of the primary data.When the calamity determines the write time of the modification data for array
When being later than the write time of the primary data, by the modification data write described backup file.In this embodiment
In, if calamity first receives primary data for array, then modification data are received, can be by modification data write backup file.I.e.
Make modification data cover primary data, it is inconsistent for the data of array and production array also not result in calamity.
With reference to the third embodiment of first aspect, in the 5th kind of embodiment, the calamity is for described in array received
The corresponding data of second replication task, create the backup file of the file, by the modification data write described backup text
Part, the filename of the backup file are identical with the filename of the file.Second replication task pair is received described
After the data answered, the calamity is for the corresponding data of first replication task described in array received.The calamity determines institute for array
State the corresponding filename of first replication task it is identical with the filename of the backup file when, judge writing for the primary data
Whether the angle of incidence is later than the write time of the modification data.When the calamity determines the write time of the primary data for array
Earlier than it is described modification data write time when, do not perform by the primary data write it is described backup file in operation.
In this embodiment, if calamity first receives modification data for array, then primary data is received, then do not perform and primary data is write
Enter to back up the operation of file, it is inconsistent for the data of array and production array to prevent calamity.
Second aspect present invention provides a kind of storage device, the method to perform first aspect offer.
Third aspect present invention provides a kind of storage device, the method to perform first aspect offer.
Description of the drawings
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below by to be used attached needed for embodiment
Figure is briefly described.
Fig. 1 is system architecture schematic diagram provided in an embodiment of the present invention;
Fig. 2 is the structure chart of controller provided in an embodiment of the present invention;
Fig. 3 is the schematic flow sheet of duplicating remote data method provided in an embodiment of the present invention.
Specific embodiment
A kind of duplicating remote data method, storage device and storage system are present embodiments provided, can be in many control systems
In be executed concurrently replication task.
Fig. 1 is the system architecture schematic diagram of duplicating remote data method provided in an embodiment of the present invention, as shown in figure 1, raw
Product center includes producing main frame, connection equipment and production array 20;The system architecture of Disaster Preparation Center is similar with the production center, including
Calamity is for main frame, connection equipment and calamity for array 30.In embodiments of the present invention, Disaster Preparation Center can be with more than one.Wherein, produce
Center can be entered by IP (Internet Protocol) or FC (Fiber Chanel) or other agreements with Disaster Preparation Center
Row data transfer.
Production main frame and calamity may each be any computing device, such as server, desk computer etc. for main frame.In main frame
Inside, is provided with operating system and other application programs.
Connection equipment can be any interface between storage device and main frame, such as optical fiber switch, or other are current
The switch having known to technology.
Production array 20 and calamity may each be storage device for array 30, such as independent hard disk redundancy array (Redundant
Arrays of Inexpensive Disks, RAID), hard disk cluster (Just a Bunch Of Disks, JBOD), be directly accessed
The hard disk drive of one or more interconnection of memorizer (Direct Access Storage Device, DASD), such as magnetic
The fc tape storage device FC of tape pool, one or more memory element.
Production array 20 and calamity in the present embodiment is the storage device with file system for array 30, that is,
Say, the data preserved in storage medium are to be managed in units of file and accessed.File system is a kind of storage and group
The method of organization data, it causes the access to data and lookup to become easy, and file system is taken out using file and directory tree
As logical concept instead of the concept of the data block that the physical equipments such as hard disk are used.Production array 20 is protected using file system
After deposit data, it is in how many data blocks that user need not be concerned about that data are actually stored in the address of hard disk, it is only necessary to remember this
The affiliated catalogue of file and filename.Likewise, before write new data, user need not be concerned about that block address on hard disk
It is not used, storage space management (the distribution and release) function on hard disk is automatically performed by file system, and user only needs to
Remember which file is data have been written in.
Production array 20 and calamity are identicals for the hardware configuration of array 30.Fig. 2 is embodiment of the present invention production array 20
Structural representation, Fig. 3 is structural representation of the embodiment of the present invention calamity for array 30.
As shown in Fig. 2 production array 20 at least includes controller 21, controller 22 and several hard disks 31.Controller 21
Any computing device, such as server, desk computer etc. can be included.Inside controller, be provided with file system and
Other application programs.Controller 21 is used to performing various operations related to file, such as establishment file, creaties directory, reads text
Part operation, operating writing-file, transmission data copy request etc..Controller 22 is similar with the structure of controller 21, and function phase is same.
Several hard disks 31 that production array 20 is included are used to provide memory space preservation file.It should be noted that 21 He of controller
Controller 22 is only the example of the embodiment of the present invention, can also include other controllers, the present embodiment in embodiments of the present invention
The quantity of controller is not defined.
Controller 21 mainly includes processor (processor) 118, caching (cache) 120, memorizer (memory)
122nd, communication bus (abbreviation bus) 126 and communication interface (Communication Interface) 128.Processor 118,
Caching 120, memorizer 122 and communication interface 128 complete mutual communication by communication bus 126.
Communication interface 128, for communicating for array and hard disk 31 with production main frame, calamity.In addition, communication interface 128 is also
For communicating with controller 22.
Memorizer 122, for depositing program 124, memorizer 122 may include high-speed RAM memorizer, it is also possible to also include
Nonvolatile memory (non-volatile memory), for example, at least one harddisk memory.It is understood that storage
Device 122 can be random access memory (Random-Access Memory, RAM), magnetic disc, hard disk, CD, solid state hard disc (Solid
State Disk, SSD) or nonvolatile memory etc. is various can be with the non-transitory (non-of store program codes
Transitory) machine readable media.
Program 124 can include program code, and described program code includes file system described above and other journeys
Sequence code.
Data or the data read from hard disk that 120 (Cache) of caching are received from production main frame for caching.Caching
120 can be that RAM, ROM, flash memory (Flash memory) or solid state hard disc (Solid State Disk, SSD) etc. are various can be with
Non-transitory (non-transitory) machine readable media of data storage, here are not limited.
In addition, memorizer 122 and caching 120 can close and set or be provided separately, the embodiment of the present invention is not limited to this.
The possibly central processor CPU of processor 118, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement one or more integrated electricity of the embodiment of the present invention
Road.
Calamity is identical with production array 20 for the structure of array 30, its effect be when producing array 20 and breaking down, can be with
Take over production array 20 and continue with business.
With reference to Fig. 1 and Fig. 2, a kind of duplicating remote data method of the embodiment of the present invention is described.The method is applied in Fig. 1
In the scene of shown asynchronous remote copy, performed for array 30 by production array 20 and calamity.As described in Figure 3, methods described can
To comprise the following steps:
Step 1:First controller 21 is detected and locally whether have replication task.
Replication task refer to by data from production array 20 copy to calamity for array 30 task.Exemplary, the first control
A replication queue is preserved in the caching of device processed, multiple replication tasks in the replication queue, can be included, each replicates appoints
Business can be described with information such as filename, the write times of file data.First controller can be by checking the duplication
The information included by queue is determining whether with replication task.In addition, queue is of the embodiment of the present invention showing
Example, the present embodiment can also adopt other data structures, and such as heap, stack etc. preserve replication task.
Step 2:When first 21 no replication task of controller, request message is sent to second controller 22.
The request message is for the application replication task of second controller 22.It is understood that in production array 20
Other controllers may be included, some controllers are in idle condition (no replication task), and some controllers are likely to be at
Busy state (includes multiple pending replication tasks), then the controller in idle condition can be in busy state
Controller application replication task.Describe for convenience, the present embodiment is with control that second controller 22 is in busy state
As a example by device, the second controller 22 at least includes two replication tasks.
In actual applications, the first controller 21 can send inquiry to each controller in production array 20 respectively and disappear
Breath, the replication task pending to obtain each controller.A controller in busy state, Xiang Qi are selected again therefrom
Send request message.Or, a controller, the duplication pending for gathering each controller are determined in production array 20
The quantity of task, and notify that the first controller 21 is currently at the controller of busy state.
Step 3:Second controller 22 distributes one or more replication tasks to the first controller according to the request message
21。
It is similar with the first controller 21, a replication queue, the duplication team are also preserved in the caching of second controller
Multiple replication tasks can be included in row.One or more of replication tasks can be distributed to the first control by second controller
Device processed 21, to ensure the task balance between each controller.Specifically, second controller 22 can be according to the original of first in first out
Then, one or more replication tasks earliest into the queue are distributed to into the first controller 21.So-called distribution replication task
To the first controller 21, can be specifically to the first controller 21 by the replication task corresponding data is activation.The duplication
The corresponding data of task include it is to be copied to calamity for array 30 data, the embodiment of the present invention by it is to be copied to calamity for array 30
Data are referred to as file data, that is, the corresponding data block of file.As the replication task can be described with filename, because
This can obtain file data by the filename and corresponding metadata, and be sent to the first controller 21.In addition, removing
Outside the file data, the corresponding data of the replication task also include the filename of the file belonging to the file data
And the write time of the file data.The write time of the file data refers to that the file data writes the production
The time of array, it is probably a specific time point, it is also possible to be intended to indicate that the time interval of a period of time scope, also
It is likely to be the version number of the version information for representing the file.The present embodiment implication and form not to the said write time
Any restriction is carried out, as long as can show that file data writes the priority of the production array by the contrast of each write time
Order.
Multiple replication tasks inside one queue, it may be possible to which (these replicate and appoint the replication task for same file
The filename of business is identical), it is also possible to for the replication task of different files.With the multiple replication tasks for same file
As a example by, multiple write operations of the plurality of replication task correspondence for the file.The embodiment of the present invention can utilize one
Serial number is recording the multiple write operations to file.For example, when a file is just created, that is, execution is write for the first time
When entering to operate, its Serial No. 1;When the file is changed, that is, is performed second write operation, its Serial No. 2.
The file corresponding multiple write operations are namely synchronized to calamity for multiple replication tasks of a file by so-called execution
Standby array.Therefore, each replication task can correspond to a unique serial number.
Describe for convenience, the replication task that second controller 22 distributes to the first controller 21 is referred to as by the present embodiment
One replication task, outside second controller 22 is distributed to the replication task of the first controller 21, in queue, remaining duplication is appointed
Business is referred to as the second replication task.For example, first replication task and second replication task can include following information respectively:
Filename | Serial number | The write time of file data |
0X100 | 001 | 2016.1.1 |
0X100 | 002 | 2016.1.2 |
As shown above, the corresponding data of first replication task belong to the filename of the entitled 0X100 of file, the data
Write time be 2016.1.1, the serial number of first replication task is 001;The corresponding data of second replication task
Belong to the filename of the entitled 0X100 of file, the write time of the data is 2016.1.2, the sequence of second replication task
Row number is 002.
Step 4:The corresponding data of first controller 21, first replication task of reception, and send the data to calamity
Standby array 30.
Specifically, second controller 22 can obtain file data according to filename and corresponding metadata, will be described
The write time of file data, filename, serial number and the file data is sent to the first controller 21.By the first control
Device 21 performs the replication task, that is to say, that by writing for the file data, filename, serial number and the file data
The angle of incidence is sent to calamity for array 30.
Step 5:Second controller 22 is by second replication task corresponding data is activation to calamity for array 30.
Specifically, second controller 22 is recorded according to second replication task filename and corresponding metadata
File data is obtained, and the write time of the file data, filename and the file data is sent to into calamity for battle array
Row 30.
By the embodiment shown in Fig. 3, the controller in idle condition can be to the controller in busy state
Application replication task, the controller in busy state is by the replication task distribution part of oneself to the control in idle condition
Device processed, thus, each controller can concurrently process replication task, improve duplicating efficiency.
Be described below when each controller parallel processing replication task, how to ensure calamity for array file with production battle array
The concordance of the file of row.
As shown in Figure 3, the first controller 21 performs first replication task, by first replication task corresponding number of files
Calamity is given for array 30 according to duplication;Second controller 22 performs second replication task, by second replication task corresponding text
Number of packages gives calamity for array 30 according to duplication.Describe for convenience, first replication task corresponding file data is referred to as counted
According to A, second replication task corresponding file data is referred to as into data B.Although the first controller 21 and second controller 22
It is that to be performed in parallel the two replication tasks, but calamity be not often while the time of receiving data A and data B for array 30
's.
Situation 1:Calamity is for first receiving data A of array 30, then receiving data B.
Calamity can also receive and preserve the filename of the file belonging to data A for array 30 in the lump in receiving data A, the
The write time of the serial number and data A of one replication task.Calamity can travel through the filename of local file for array, it is determined that
Data A are not belonging to any one local file.So as to, a new file is created, the new file is data A in production array
The backup file of affiliated file.The filename of the backup file can (data A be in the text belonging to production array with source file
Part) it is consistent.Subsequently, data A are write the Backup Data, and the write time of record data A, said write for array 30 by calamity
Time is identical with the write time of data A that production array 20 sends.
After calamity is for 30 receiving data A of array, receiving data B.Due to the filename of the file belonging to data B and above-mentioned
The filename of backup file is identical, and calamity is not required to create new file again for array 30.Next, calamity is for 30 record data B of array
Corresponding write time, said write time are identical with the write time of data B that production array 20 sends.Calamity compares for array 30
Compared with the write time and the write time of data A of data B, determine that the write time of data B is later than the write time of data A, because
This data A is the primary data of the backup file, and data B are the modification data of the backup file.Modification data can be with
Primary data is covered, calamity is performed the operation of the write of data B described backup file for array.
Situation 2:Calamity is for first receiving data B of array 30, then receiving data A.
Calamity in receiving data B, travels through the filename of local file, determines that data B are not belonging to local for array 30
Any one file.So as to, a new file is created, the new file is backup of data B in the file belonging to production array
File.The filename of the backup file can be consistent with source file (data B are in the file belonging to production array).Subsequently, calamity
Data B are write the Backup Data, and the write time of record data B, said write time and production array by standby array 30
The write time of 20 data B for sending is identical.
After calamity is for 30 receiving data B of array, receiving data A.Due to the filename of the file belonging to data A and above-mentioned
The filename of backup file is identical, and calamity is not required to create new file again for array 30.Next, calamity is for 30 record data A of array
Corresponding write time, said write time are identical with the write time of data A that production array 20 sends.Calamity compares for array 30
Compared with the write time and the write time of data A of data B, the write time of the write time earlier than data B of data A is determined, because
This data A is the primary data of the backup file, and data B are the modification data of the backup file.Primary data can not
To cover modification data, calamity is not performed the operation of the write of data A described backup file for array.
Thus, calamity for array 30 receive for same file multiple data when, can writing according to each data
The angle of incidence judges whether to perform the write operation to backing up file, and its principle is the data cover that the write time can only be used later
Write time data earlier, thereby ensure that the concordance of file.
In addition, when the file in array 20 is produced is deleted, in order to be consistent, calamity is for the backup file in array 30
It is also required to be deleted.Specifically, produce array 20 and can send the instruction for deleting file to calamity for array, the instruction includes institute
State the filename of file, and newest serial number (the corresponding serial number of last time write operation).Calamity is received for array 30
After the instruction for deleting file, according to the filename lookup to corresponding backup file, the backup file is judged
Whether newest serial number is identical with the serial number that production array 20 sends.If identical, calamity is performed for array 30 deletes described
The operation of backup file;Otherwise, the operation for deleting the backup file is not performed.
Finally it should be noted that:Various embodiments above only to illustrate technical scheme, rather than a limitation.
Claims (16)
1. a kind of duplicating remote data method, it is characterised in that methods described is applied in storage system, the storage system bag
Production array and calamity are included for array, the production array at least includes the first controller and second controller, methods described includes:
Whether the first controller detection locally has replication task;
When no replication task in first controller, first controller sends request to the second controller and disappears
Breath, the request message is for the second controller application replication task, the second controller is at least multiple including two
Task processed;
The second controller reads the corresponding Data Concurrent of first replication task and gives described the according to the request message
One controller;
First controller receives the corresponding data of first replication task, will be first replication task corresponding
Data is activation is to the calamity for array;
The second controller is by second replication task corresponding data is activation to the calamity for array.
2. method according to claim 1, it is characterised in that the second controller safeguards there is replication queue, described multiple
Queue processed includes at least two replication task;
The second controller reads the corresponding Data Concurrent of first replication task and gives described the according to the request message
One controller includes:The second controller obtains first replication task from the replication queue, by described first
The corresponding data is activation of individual replication task gives first controller;
Second replication task corresponding data is activation is included for array by the second controller to the calamity:
The second controller obtains the second replication task from the replication queue, by second replication task corresponding number
According to being sent to the calamity for array.
3. method according to claim 1 and 2, it is characterised in that first replication task and it is described second it is multiple
Task processed is the replication task for same file.
4. method according to claim 3, it is characterised in that the file has unique filename, described first
When the corresponding data of replication task include the write of the filename, the primary data of the file, and the primary data
Between, the corresponding data of second replication task include the filename, the modification data of the file, and the modification
The write time of data, the write time of the modification data are later than the write time of the primary data.
5. method according to claim 4, it is characterised in that methods described also includes:
The calamity creates the backup file of the file, by institute for the corresponding data of first replication task described in array received
State primary data and write the backup file, the filename of the backup file is identical with the filename of the file;
After the corresponding data of the reception first replication task, the calamity is for second duplication described in array received
The corresponding data of task;
For array, the calamity determines that the corresponding filename of second replication task is identical with the filename of the backup file
When, judge whether the write time of the modification data is later than the write time of the primary data;
When for array, the calamity determines that the write time of the modification data is later than the write time of the primary data, by institute
State in the modification data write backup file.
6. method according to claim 4, it is characterised in that methods described also includes:
The calamity creates the backup file of the file, by institute for the corresponding data of second replication task described in array received
State modification data and write the backup file, the filename of the backup file is identical with the filename of the file;
After the corresponding data of the reception second replication task, the calamity is for first duplication described in array received
The corresponding data of task;
For array, the calamity determines that the corresponding filename of first replication task is identical with the filename of the backup file
When, judge whether the write time of the primary data is later than the write time of the modification data;
When the calamity for array determine write time of the primary data earlier than the modification data write time when, do not hold
The operation being about in the primary data write backup file.
7. a kind of storage device, it is characterised in that the storage device at least includes the first controller and second controller,
First controller, locally whether have replication task for detecting, when no replication task in first controller
When, first controller sends request message to the second controller, and the request message is for the described second control
Device application replication task, the second controller at least include two replication tasks;
The second controller, for according to the request message, the corresponding Data Concurrent of first replication task of reading is given
First controller;
First controller, is additionally operable to receive the corresponding data of first replication task, described first is replicated and is appointed
Corresponding data is activation of being engaged in gives other storage devices;
The second controller, is additionally operable to second replication task corresponding data is activation to described other storage devices.
8. storage device according to claim 7, it is characterised in that the second controller safeguards there is replication queue, institute
Stating replication queue includes at least two replication task;
The second controller, specifically for first replication task is obtained from the replication queue, by described first
The corresponding data is activation of individual replication task gives first controller;And the second duplication times is obtained from the replication queue
Described other storage devices are given in business, the corresponding data is activation of second replication task.
9. the storage device according to claim 7 or 8, it is characterised in that first replication task and described second
Individual replication task is the replication task for same file.
10. storage device according to claim 9, it is characterised in that the file has unique filename, described
The corresponding data of one replication task include writing for the filename, the primary data of the file, and the primary data
The angle of incidence, the corresponding data of second replication task include the filename, the modification data of the file, and described
The write time of modification data, the write time of the modification data is later than the write time of the primary data.
11. a kind of storage systems, it is characterised in that including production array and calamity for array, the production array at least includes the
One controller and second controller,
First controller, locally whether have replication task for detecting;When no replication task in first controller
When, first controller sends request message to the second controller, and the request message is for the described second control
Device application replication task, the second controller at least include two replication tasks;
The second controller, for according to the request message, the corresponding Data Concurrent of first replication task of reading is given
First controller;
First controller, is additionally operable to receive the corresponding data of first replication task, described first is replicated and is appointed
Corresponding data is activation of being engaged in is to the calamity for array;
The second controller, is additionally operable to second replication task corresponding data is activation to the calamity for array.
12. storage systems according to claim 11, it is characterised in that the second controller safeguards there is replication queue,
The replication queue includes at least two replication task;
The second controller, specifically for first replication task is obtained from the replication queue, by described first
The corresponding data is activation of individual replication task gives first controller;And the second duplication times is obtained from the replication queue
Business, the corresponding data is activation of second replication task is to the calamity for array.
13. storage systems according to claim 11 or 12, it is characterised in that first replication task and described
Two replication tasks are the replication tasks for same file.
14. storage systems according to claim 13, it is characterised in that the file has unique filename, described
The corresponding data of first replication task include the filename, the primary data of the file, and the primary data
Write time, the corresponding data of second replication task include the filename, the modification data of the file, Yi Jisuo
The write time of modification data is stated, the write time of the modification data is later than the write time of the primary data.
15. storage systems according to claim 14, it is characterised in that
The calamity is additionally operable to receive the corresponding data of first replication task for array, creates the backup text of the file
The primary data is write the backup file by part, and the filename of the backup file is identical with the filename of the file;
After the corresponding data of the reception first replication task, the corresponding data of second replication task are received;
When determining that the corresponding filename of second replication task is identical with the filename of the backup file, the modification number is judged
According to write time whether be later than write time of the primary data;When the calamity determines writing for the modification data for array
When the angle of incidence is later than the write time of the primary data, by the modification data write described backup file.
16. storage systems according to claim 14, it is characterised in that
The calamity is additionally operable to receive the corresponding data of second replication task for array, creates the backup text of the file
The modification data are write the backup file by part, and the filename of the backup file is identical with the filename of the file;
After the corresponding data of the reception second replication task, the corresponding data of first replication task are received;
When determining that the corresponding filename of first replication task is identical with the filename of the backup file, the initial number is judged
According to write time whether be later than it is described modification data write time;When the calamity determines writing for the primary data for array
The angle of incidence earlier than it is described modification data write time when, do not perform by the primary data write it is described backup file in behaviour
Make.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610971200.0A CN106528338B (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
CN202010780943.6A CN112068992A (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
PCT/CN2017/081341 WO2018076633A1 (en) | 2016-10-28 | 2017-04-21 | Remote data replication method, storage device and storage system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610971200.0A CN106528338B (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010780943.6A Division CN112068992A (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106528338A true CN106528338A (en) | 2017-03-22 |
CN106528338B CN106528338B (en) | 2020-08-14 |
Family
ID=58325810
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610971200.0A Active CN106528338B (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
CN202010780943.6A Pending CN112068992A (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010780943.6A Pending CN112068992A (en) | 2016-10-28 | 2016-10-28 | Remote data copying method, storage device and storage system |
Country Status (2)
Country | Link |
---|---|
CN (2) | CN106528338B (en) |
WO (1) | WO2018076633A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018076633A1 (en) * | 2016-10-28 | 2018-05-03 | 华为技术有限公司 | Remote data replication method, storage device and storage system |
CN109164985A (en) * | 2018-08-27 | 2019-01-08 | 华为技术有限公司 | For the method for replicate data, main equipment and from equipment |
CN109491980A (en) * | 2018-11-02 | 2019-03-19 | 郑州云海信息技术有限公司 | A kind of remote replication method of file system, device, equipment and storage medium |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109960613B (en) * | 2019-03-11 | 2023-05-12 | 中国银联股份有限公司 | Data batch processing method and device |
CN115277376B (en) * | 2022-09-29 | 2022-12-23 | 深圳华锐分布式技术股份有限公司 | Disaster recovery switching method, device, equipment and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7624134B2 (en) * | 2006-06-12 | 2009-11-24 | International Business Machines Corporation | Enabling access to remote storage for use with a backup program |
CN102799475A (en) * | 2012-06-29 | 2012-11-28 | 东南大学 | Multi-replication fault-tolerant parallel task scheduling method based on task replication |
CN103617098A (en) * | 2013-12-03 | 2014-03-05 | 上海爱数软件有限公司 | Intelligent backup method and system based on data changes |
CN105988901A (en) * | 2013-12-12 | 2016-10-05 | 华为技术有限公司 | Data copying method and storage system |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8548944B2 (en) * | 2010-07-15 | 2013-10-01 | Delphix Corp. | De-duplication based backup of file systems |
CA2868247C (en) * | 2013-07-26 | 2017-04-04 | Ji Ouyang | Data sending method, data receiving method, and storage device |
CN107133132B (en) * | 2013-07-26 | 2020-11-17 | 华为技术有限公司 | Data sending method, data receiving method and storage device |
CN105550367A (en) * | 2015-06-30 | 2016-05-04 | 巫立斌 | Asynchronous remote copy method for memory |
CN105404564A (en) * | 2015-12-16 | 2016-03-16 | 浪潮(北京)电子信息产业有限公司 | Data remote disaster tolerance method and apparatus |
CN106528338B (en) * | 2016-10-28 | 2020-08-14 | 华为技术有限公司 | Remote data copying method, storage device and storage system |
-
2016
- 2016-10-28 CN CN201610971200.0A patent/CN106528338B/en active Active
- 2016-10-28 CN CN202010780943.6A patent/CN112068992A/en active Pending
-
2017
- 2017-04-21 WO PCT/CN2017/081341 patent/WO2018076633A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7624134B2 (en) * | 2006-06-12 | 2009-11-24 | International Business Machines Corporation | Enabling access to remote storage for use with a backup program |
CN102799475A (en) * | 2012-06-29 | 2012-11-28 | 东南大学 | Multi-replication fault-tolerant parallel task scheduling method based on task replication |
CN103617098A (en) * | 2013-12-03 | 2014-03-05 | 上海爱数软件有限公司 | Intelligent backup method and system based on data changes |
CN105988901A (en) * | 2013-12-12 | 2016-10-05 | 华为技术有限公司 | Data copying method and storage system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018076633A1 (en) * | 2016-10-28 | 2018-05-03 | 华为技术有限公司 | Remote data replication method, storage device and storage system |
CN109164985A (en) * | 2018-08-27 | 2019-01-08 | 华为技术有限公司 | For the method for replicate data, main equipment and from equipment |
CN109164985B (en) * | 2018-08-27 | 2020-07-07 | 华为技术有限公司 | Method for copying data, master device and slave device |
CN109491980A (en) * | 2018-11-02 | 2019-03-19 | 郑州云海信息技术有限公司 | A kind of remote replication method of file system, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106528338B (en) | 2020-08-14 |
WO2018076633A1 (en) | 2018-05-03 |
CN112068992A (en) | 2020-12-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11829607B2 (en) | Enabling data integrity checking and faster application recovery in synchronous replicated datasets | |
CN106407040B (en) | A kind of duplicating remote data method and system | |
US8370302B2 (en) | Method and apparatus for block based volume backup | |
US10114581B1 (en) | Creating a virtual access point in time on an object based journal replication | |
EP3062226B1 (en) | Data replication method and storage system | |
EP1814033B1 (en) | Storage system and data restoration method thereof | |
TWI514249B (en) | Method for remote asynchronous replication of volumes and apparatus therefor | |
US10223007B1 (en) | Predicting IO | |
JP6525491B2 (en) | System and method for distributed processing of files in chunks | |
US20170185323A1 (en) | Low overhead resynchronization snapshot creation and utilization | |
CN106528338A (en) | Remote data replication method, storage equipment and storage system | |
CN107924354A (en) | Dynamic mirror | |
JP4988370B2 (en) | Method, system, and program for integrating session information for a cluster of sessions in a coupled session environment | |
WO2018098972A1 (en) | Log recovery method, storage device and storage node | |
US9830237B2 (en) | Resynchronization with compliance data preservation | |
JP2008097290A (en) | Storage system and data management method | |
US11768624B2 (en) | Resilient implementation of client file operations and replication | |
CN107046811A (en) | One introduces a collection storage device sends the clone file of source file and source file to the method, source storage device and backup storage device of backup storage device | |
JP2015527620A (en) | Computer system, server, and data management method | |
CN106873902B (en) | File storage system, data scheduling method and data node | |
CN101937378B (en) | Method for carrying out back-up protection on data of storage equipment and computer system | |
JP2006331076A (en) | Data storage system and storage method | |
JP6070146B2 (en) | Information processing apparatus and backup method | |
US11003541B2 (en) | Point-in-time copy on a remote system | |
JP2013161383A (en) | Information processing device, information processing method, program and information processing system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |