CN100454265C - Image recovery method, storage equipment and network system - Google Patents
Image recovery method, storage equipment and network system Download PDFInfo
- Publication number
- CN100454265C CN100454265C CNB2007101086368A CN200710108636A CN100454265C CN 100454265 C CN100454265 C CN 100454265C CN B2007101086368 A CNB2007101086368 A CN B2007101086368A CN 200710108636 A CN200710108636 A CN 200710108636A CN 100454265 C CN100454265 C CN 100454265C
- Authority
- CN
- China
- Prior art keywords
- memory device
- location records
- data
- master file
- upgrade
- 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.)
- Active
Links
Images
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
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2053—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant
- G06F11/2056—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant by mirroring
- G06F11/2082—Data synchronisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This invention discloses an image resuming method including: obtaining position registration of updated data of a first storage device registering the updated states of data at different positions, comparing the position registration of the second device with that of the first to get different data positions of them then copying data corresponding to the positions to the first device. This invention also provides a storage device, which mainly compares the position registration for updating data recorded by a registration unit with that of another storage device obtained by the obtaining unit to get the positions itself and another storage device and copies the data corresponding to these positions onto another storage device. This invention also provides a network system.
Description
Technical field
The present invention relates to technical field of the computer network, be specifically related to a kind of image recovery method, memory device and network system.
Background technology
The disaster-tolerant backup technology is important further at present.Remote Switched Port Analyzer is wherein a kind of technology of setting up the disaster-tolerant backup system.Mirror image is the information stores process that produces the mirror image view of same data on two or more memory devices.Remote Switched Port Analyzer can be divided into synchronous Remote Switched Port Analyzer and asynchronous remote mirror image.
Synchronously Remote Switched Port Analyzer (synchronization replication technology) is meant that the applied host machine of main website whenever sends a write request, must wait pending data write fully main storage device master file and from memory device after volume, could continue execution.Remote Switched Port Analyzer generally is applicable to the situation (in common tens kilometers) that communication link is short synchronously.Asynchronous remote mirror image (asynchronous replication technology), be that the applied host machine of main website is when sending continuously a plurality of write request, only need wait pending data can continue execution after writing the master file of main storage device, after this again by the master file of main storage device with from memory device from involving in the continuous repeatedly data sync of row, promptly allow a plurality of operations that lag behind between two memory devices.The asynchronous remote mirror image is applicable to the long situation of communication link (be generally hundreds of even go up a thousand li).
The asynchronous remote mirrored procedure relates to the image recovery problem.In asynchronous Remote Switched Port Analyzer, the more new data on the master file periodically sends to from volume and upgrades.In the renewal process, master file temporarily lost efficacy, and was new master file from being rolled into, and after former master file recovers, the data of new master file was copied to former master file fully, finished image recovery.
Seeing also Fig. 1, is prior art asynchronous remote image recovery process flow diagram.
The recovery technology of existing asynchronous remote mirror image is after master file lost efficacy, and from the business of cigarette pipe master file, becomes new master file.After after a while, master file is restored, and service needed is switched back former master file from new master file.At this moment, the data of new master file are copied to former master file fully get on, then business is switched back former master file.
Specifically comprise step among the figure:
Steps A 1, master file more new data send to from involving in the row renewal;
Applied host machine sends write request to the master file of main storage device, after the asynchronous remote image program of main storage device is received write request, write in the master file of main storage device according to the more new data of the position that requires in the write request to write write request, and the sign of position corresponding in the bitmap is changed to " 1 ", represent that the data of this position upgrade, if being designated of certain position in the bitmap " 0 " represents that then the data of this position are not upgraded.Bitmap just refers to a string binary sequence, and each on the sequence is " 0 " or " 1 ", represents two kinds of different states respectively.
After master file is finished Data Update, when arrive synchronizing cycle, be sent to from volume, after receiving, upgrade from cigarette according to the more new data of the information that writes down in the bitmap with correspondence position.
Steps A 2, master file temporarily lost efficacy, and became new master file from cigarette pipe business;
When master file temporarily lost efficacy, the clustered software of process applied host machine cooperated with the asynchronous remote image program of master/slave memory device, and the business of master file switches to from involving in row and takes over, and is new master file from being rolled into.
From being rolled into, write down the position that Data Update takes place by bitmap equally to behind the new master file.
Steps A 3, former master file are recovered, and the data of new master file are all copied to former master file.
Whether the former master file that regularly detects main storage device from memory device is normal, if it is normal to detect former master file, thinks that then former master file recovers.After former master file recovers, the data of new master file are all copied to former master file get on, promptly new master file sends to former master file with total data, and former master file upgrades after receiving, thereby finishes image recovery.Then, the clustered software of process applied host machine cooperates with the asynchronous remote image program of master/slave memory device, and business switches to former master file by new master file again.
The inventor finds that image recovery speed is slow in the existing image recovery process in realizing process of the present invention, spended time is long, can not satisfy the demanding application of disaster tolerance rank.
Summary of the invention
The technical matters that the embodiment of the invention will solve is the slow problem of image recovery speed in existing image recovery method, memory device and the network system.
For solving the problems of the technologies described above, the embodiment of the invention is to be achieved through the following technical solutions:
The embodiment of the invention provides a kind of image recovery method, comprising: after first memory device recovered normally, second memory device obtained the location records that described first memory device carries out Data Update, and described location records writes down the update mode of data on each position; The location records of second memory device and the location records of described first memory device that obtains are compared, obtain the position that second memory device and first memory device contain different pieces of information; The data of described position correspondence are copied to first memory device.
The embodiment of the invention provides a kind of memory device, comprising: acquiring unit, be used for after another memory device recovers normally, obtaining the location records that described another memory device carries out Data Update, and described location records writes down the update mode of data on each position; Record cell is used to write down the location records of described memory device local terminal; Comparing unit, be used for the location records of the described memory device of described recording unit records and the location records of described another memory device that described acquiring unit obtains are compared, obtain the position that described memory device and described another memory device contain different pieces of information; Data transmission unit, the data that are used for described position correspondence that described comparing unit is obtained send to described another memory device.
The embodiment of the invention provides a kind of network system, comprising: first memory device, be used to send the location records that carries out Data Update, and the reception data are also upgraded, and described location records writes down the update mode of data on each position; Second memory device is used for obtaining the location records that described first memory device sends after first memory device recovers normally; The location records of described second memory device and the location records of described first memory device that obtains are compared, obtain the position that described second memory device and described first memory device contain different pieces of information; The data of described position correspondence are sent to first memory device.
Above technical scheme as can be seen, the technical scheme that the embodiment of the invention provides is: obtain the location records that first memory device carries out Data Update, described location records writes down the update mode of data on each position; The location records of second memory device and the location records of described first memory device are compared, obtain the position that second memory device and first memory device contain different pieces of information; The data of described position correspondence are copied to first memory device.Because in the embodiment of the invention scheme, by increasing by second memory device is carried out the process that the location records of Data Update and location records that described first memory device carries out Data Update compare, draw second memory device and first memory device and contain the position of different pieces of information, the data of these position correspondences just really need copy to the data that first memory device is finished image recovery, total data is duplicated the prior art with regard to not needing to resemble like this, thereby improved image recovery speed, also make the asynchronous remote mirror image can be applied to the high environment of disaster tolerance rank, and the data that need duplicate have reduced, also alleviate the burden of link, improved the fault-tolerance of system.
Description of drawings
Fig. 1 is a prior art asynchronous remote image recovery process flow diagram;
Fig. 2 is an applied environment synoptic diagram of embodiment of the invention image recovery method;
Fig. 3 is the embodiment of the invention one an image recovery method process flow diagram;
Fig. 4 is the embodiment of the invention two image recovery method process flow diagrams;
Fig. 5 is the structural representation of embodiment of the invention memory device;
Fig. 6 is the structural representation of embodiment of the invention network system.
Embodiment
The image recovery speed of existing image recovery method is slow, and the embodiment of the invention provides a kind of image recovery method, can improve image recovery speed.
Seeing also Fig. 2, is an applied environment synoptic diagram of embodiment of the invention image recovery method.
Wherein a kind of networking situation of asynchronous remote mirror image has been described among Fig. 2, comprising two applied host machines, they are interconnected by wide area network WAN (Wide Area Network) or LAN (Local Area Network) LAN (Local AreaNetwork), on two applied host machines clustered software are installed and are constituted the environment of a high available test HA (High Availability).The business of moving on the applied host machine can be enterprise-level applications such as database service, mail service and file service.Also comprise two memory devices in the networking, i.e. main storage device and from memory device.The business datum of applied host machine be kept at main storage device master file and from memory device from the volume.Applied host machine is interconnected by storage area network SAN (Storage Area Network) and master and slave memory device, the agreement of carrying can be FC agreement (Fibre Channel, optical-fibre channel), iSCSI (internet SCSI, the internet scsi technology) agreement and SAS agreement (Serial Attached SCSI, serial SCSI technology) etc.SCSI is that the English of Small Computer System Interface is write a Chinese character in simplified form, and Chinese is commonly referred to as small computer system interface.The business datum of applied host machine is first written in the master file of main storage device, then by master file again with data image to from memory device from the volume.Main storage device and can be FC (Fibre Channel from the data link of memory device, optical-fibre channel), DWDM (DenseWave length Division Multiplexing, dense wave division multipurpose), ATM (AsynchronousTransfer Mode, asynchronous transfer mode) or IP transmission lines such as (Internet Protocol, Internet protocols).
In the asynchronous Remote Switched Port Analyzer, the more new data on the master file periodically sends to from volume and upgrades.Master file writes down the position that needs in synchronizing cycle to from the volume data updated by daily record.Therefore, daily record also can be regarded location records as, and this location records has write down update mode of each data on the position of new data more and the position etc.Location records can adopt the bitmap mode to write down usually but be not limited to this, also can adopt other modes.Can represent that the data of this position upgrade with " 1 " in the bitmap, represent that with " 0 " data of this position do not upgrade.In a synchronizing cycle, it is multiple to need the location mode of data updated to have, and can be to preserve in the mode of master file snapshot, also can be directly to save the data in the daily record volume.
The Remote Switched Port Analyzer restoration methods of the embodiment of the invention is the bitmap by newer master file and former master file record, after drawing real needs and carrying out position that data recover, the more new data of these positions is copied on the former master file, finish image recovery, avoided needing total data is copied on the former master file, thereby improved image recovery speed.
Seeing also Fig. 3, is the embodiment of the invention one image recovery method process flow diagram.
Specifically comprise step among the figure:
Step B1, master file more new data send to from involving in the row renewal;
Applied host machine sends write request to the master file of main storage device, after the asynchronous remote image program of main storage device is received write request, write in the master file of main storage device according to the data of the position that requires in the write request to write write request, and in location records, carry out record, for example when adopting the bitmap mode in bitmap the sign of corresponding position be changed to " 1 ", represent that the data of this position are upgraded.If being designated of certain position in the bitmap " 0 " represents that then this position do not upgrade.
After master file is finished Data Update, when arrive synchronizing cycle, be sent to from volume, after receiving, upgrade from cigarette according to the more new data of the information that writes down in the bitmap with correspondence position.When master file is sent to the more new data of correspondence position behind volume, the sign of master file correspondence position is changed to " 0 " from " 1 ".
In a synchronizing cycle, master file only need get final product needing after upgrading in this cycle to be synchronized to send to from volume from the data of volume, if in this synchronizing cycle, master file upgrades again, these data updated will be waited until and be sent to from volume next synchronizing cycle again so, be consistent with regard to the data that guaranteed interior transmission synchronizing cycle like this.
Step B2, master file temporarily lost efficacy, and became new master file from cigarette pipe business;
When master file temporarily lost efficacy, the clustered software of process applied host machine cooperated with the asynchronous remote image program of master/slave memory device, and the business of master file switches to from involving in row and takes over, and is new master file from being rolled into.
From being rolled into, write down the position that Data Update takes place by bitmap equally to behind the new master file.The sign of the location records of new master file initially all is to be changed to " 0 ", accepts applied host machine after new master file sends write request when new master file, and when the data of new master file took place to upgrade, the sign of the position that data are updated was changed to " 1 ".
Step B3, former master file recover, and new master file obtains the bitmap that former master file writes down from former master file before inefficacy;
The described obtain manner here can be regularly to receive the bitmap that carries out Data Update that described former master file sends, and also can be to send request to obtain the bitmap that former master file carries out Data Update to former master file.
Be after former master file recovers in the present embodiment, new master file sends request to former master file, and the bitmap of record sent to new master file before the bitmap that writes down before inefficacy in the former master file of acquisition request, former master file will lose efficacy.
Step B4, new master file carry out an exclusive disjunction with the bitmap of self record and the bitmap of reception, obtain former master file has different pieces of information at this moment with new master file position;
Give an example, if the data of former master file are A, B, C, the bitmap of record is 011, and be that the data of new master file are A, D, F from volume, the bitmap of record is 011, the result who carries out so behind the exclusive disjunction is exactly 011, and the data of two the position correspondences in expression back are different, D, F should be copied to former master file from volume and upgrade.
Step B5, according to operation result, data of corresponding positions in the new master file bitmap is copied to former master file.
According to operation result, data of corresponding positions in the bitmap of new master file record is copied to former master file, promptly new master file sends to former master file with data of corresponding positions in the bitmap, and former master file upgrades after receiving, thereby finishes image recovery.Then, the clustered software of process applied host machine cooperates with the asynchronous remote image program of master/slave memory device, and business switches to former master file by new master file again.
Seeing also Fig. 4, is the embodiment of the invention two image recovery method process flow diagrams.The key distinction of embodiment two and embodiment one is that " 1 " is different with the implication of " 0 " expression in the bitmap, and the comparison procedure of corresponding back adopts position and computing.
Specifically comprise step among the figure:
Step C1, master file more new data send to from involving in the row renewal;
Applied host machine sends write request to the master file of main storage device, after the asynchronous remote image program of main storage device is received write request, write in the master file of main storage device according to the data of the position that requires in the write request to write write request, and in location records, carry out record, for example when adopting the bitmap mode in bitmap the sign of corresponding position be changed to " 0 ", represent that the data of this position are upgraded.If being designated of certain position in the bitmap " 1 " represents that then this position do not upgrade.
After master file is finished Data Update, when arrive synchronizing cycle, be sent to from volume, after receiving, upgrade from cigarette according to the more new data of the information that writes down in the bitmap with correspondence position.When master file is sent to the more new data of correspondence position behind volume, the sign of master file correspondence position is changed to " 1 " from " 0 ".
In a synchronizing cycle, master file only need get final product needing after upgrading in this cycle to be synchronized to send to from volume from the data of volume, if in this synchronizing cycle, master file upgrades again, these data updated will be waited until and be sent to from volume next synchronizing cycle again so, be consistent with regard to the data that guaranteed interior transmission synchronizing cycle like this.
Step C2, master file temporarily lost efficacy, and became new master file from cigarette pipe business;
When master file temporarily lost efficacy, the clustered software of process applied host machine cooperated with the asynchronous remote image program of master/slave memory device, and the business of master file switches to from involving in row and takes over, and is new master file from being rolled into.
From being rolled into, write down the position that Data Update takes place by bitmap equally to behind the new master file.The sign of the location records of new master file initially all is to be changed to " 1 ", accepts applied host machine after new master file sends write request when new master file, and when the data of new master file took place to upgrade, the sign of the position that data are updated was changed to " 0 ".
Step C3, former master file recover, and new master file obtains the bitmap that former master file writes down from former master file before inefficacy;
The described obtain manner here can be regularly to receive the bitmap that carries out Data Update that described former master file sends, and also can be to send request to obtain the bitmap that former master file carries out Data Update to former master file.
Be after former master file recovers in the present embodiment, new master file sends request to former master file, and the bitmap of record sent to new master file before the bitmap that writes down before inefficacy in the former master file of acquisition request, former master file will lose efficacy.
Step C4, new master file carry out position and computing with the bitmap of self record and the bitmap of reception, obtain former master file has different pieces of information at this moment with new master file position;
Give an example, if the data of former master file are A, B, C, the bitmap of record is 011, and be that the data of new master file are D, F, C from volume, the bitmap of record is 001, carrying out position and calculated result so is exactly 001, and the data of two the position correspondences in expression front are different, D, F should be copied to former master file from volume and upgrade.
Step C5, according to operation result, data of corresponding positions in the new master file bitmap is copied to former master file.
According to operation result, data of corresponding positions in the bitmap of new master file record is copied to former master file, promptly new master file sends to former master file with data of corresponding positions in the bitmap, and former master file upgrades after receiving, thereby finishes image recovery.Then, the clustered software of process applied host machine cooperates with the asynchronous remote image program of master/slave memory device, and business switches to former master file by new master file again.
Need to prove, the position of Data Update and the update mode of position corresponding data take place with the bitmap record in above-mentioned two embodiment, and obtain the position that former master file and new master file have different pieces of information by bitmap relatively, and then only needing that data of corresponding positions is copied to former master file, to finish image recovery be that example describes but is not limited to this, also can carry out record with other daily record modes, and obtain former master file by the record of this daily record mode relatively and the position of different pieces of information is arranged, and then only need that data of corresponding positions is copied to former master file and finish image recovery with new master file.
Foregoing describes the image recovery method of the embodiment of the invention in detail, and corresponding, the embodiment of the invention provides a kind of memory device and network system.
Seeing also Fig. 5, is the structural representation of embodiment of the invention memory device.
As shown in the figure, this memory device comprises: acquiring unit 100, record cell 200, comparing unit 300 and data transmission unit 400.
Acquiring unit 100 is used to obtain the location records that another memory device carries out Data Update, can be regularly to receive the location records that carries out Data Update that described another memory device sends.Described location records writes down the update mode of data on each position.
Comparing unit 300, the location records that is used for another memory device that the location records that carries out Data Update of described record cell 200 records and described acquiring unit 100 obtain is carried out Data Update compares, and acquisition memory device self and another memory device contain the position of different pieces of information.
Comparing unit 300 further comprises first comparing unit 301 and second comparing unit 302, or includes only one of them unit.
First comparing unit 301, be used for the location records that another memory device that location records that carries out Data Update and described acquiring unit 100 with described record cell 200 records obtain carries out Data Update and carry out an exclusive disjunction, obtain the position that memory device self and another memory device contain different pieces of information, described location records is to adopt 1 expression data to upgrade, adopts 0 expression data not upgrade.
Second comparing unit 302, be used for the location records that another memory device that location records that carries out Data Update and described acquiring unit 100 with described record cell 200 records obtain carries out Data Update and carry out position and computing, obtain the position that memory device self and another memory device contain different pieces of information, described location records is to adopt 0 expression data to upgrade, adopts 1 expression data not upgrade.
Memory device further comprises request unit 500, be used for sending request to another memory device, another memory device of acquisition request location records that line data upgrades that advances that lost efficacy, and receive inefficacy that another memory devices the return location records that line data upgrades that advances by acquiring unit 100.
Seeing also Fig. 6, is the structural representation of embodiment of the invention network system.
This network system comprises that first memory device 10 and second memory device, 20, the first memory devices 10 can be meant main storage device, and second memory device 20 can be meant from memory device.Second memory device 20 has structure shown in Figure 5, comprise acquiring unit 100, record cell 200, comparing unit 300, data transmission unit 400 and request unit 500, comparing unit 300 comprises first comparing unit 301 and second comparing unit 302, or includes only one of them unit.
Described second memory device 20 comprises first comparing unit 301 and second comparing unit 302, or includes only one of them unit.
First comparing unit 301, be used for that second memory device 20 is carried out the location records of Data Update and location records that described first memory device 10 carries out Data Update carries out an exclusive disjunction, obtain the position that second memory device 20 and first memory device 10 contain different pieces of information, described location records is to adopt 1 expression data to upgrade, adopts 0 expression data not upgrade.
Second comparing unit 302, be used for that second memory device 20 is carried out the location records of Data Update and location records that described first memory device 10 carries out Data Update carries out position and computing, obtain the position that second memory device 20 and first memory device 10 contain different pieces of information, described location records is to adopt 0 expression data to upgrade, adopts 1 expression data not upgrade.
Above technical scheme as can be seen, the technical scheme that the embodiment of the invention provides is: obtain the location records that first memory device carries out Data Update, described location records writes down the update mode of data on each position; Second memory device is carried out the location records of Data Update and location records that described first memory device carries out Data Update compares, obtain the position that second memory device and first memory device contain different pieces of information; The pairing data in position that obtain are copied to first memory device.Because in the embodiment of the invention scheme, by increasing by second memory device is carried out the process that the location records of Data Update and location records that described first memory device carries out Data Update compare, draw second memory device and first memory device and contain the position of different pieces of information, the data of these position correspondences just really need copy to the data that first memory device is finished image recovery, so just overcome the defective that total data need be duplicated in the prior art, thereby improved image recovery speed, also make the asynchronous remote mirror image can be applied to the high environment of disaster tolerance rank, and the data that need duplicate have reduced, also alleviate the burden of link, improved the fault-tolerance of system.
Further, the location records that carries out Data Update at the location records that second memory device is carried out Data Update and described first memory device compares in the process, can adopt an exclusive disjunction, also can adopt position and computing,, represent that with 0 data do not upgrade if adopt 1 expression data to upgrade in the bitmap, what then adopt is an exclusive disjunction, if adopt 0 expression data to upgrade in the bitmap, represent that with 1 data do not upgrade, what then adopt is and computing.
More than image recovery method, memory device and network system that the embodiment of the invention provided are described in detail, used specific case herein the principle and the embodiment of the embodiment of the invention are set forth, the explanation of above embodiment just is used to help to understand the method and the core concept thereof of the embodiment of the invention; Simultaneously, for one of ordinary skill in the art, according to the thought of the embodiment of the invention, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (12)
1, a kind of image recovery method is characterized in that, comprising:
After first memory device recovered normally, second memory device obtained the location records that described first memory device carries out Data Update, and described location records writes down the update mode of data on each position;
The location records of second memory device and the location records of described first memory device that obtains are compared, obtain the position that second memory device and first memory device contain different pieces of information;
The data of described position correspondence are copied to first memory device.
2, image recovery method according to claim 1 is characterized in that:
Described comparing is specially: the location records of described second memory device and the location records of described first memory device are carried out an exclusive disjunction, described location records is the state that adopts 1 expression data of corresponding positions to upgrade, the state that adopts 0 expression data of corresponding positions not upgrade.
3, image recovery method according to claim 1 is characterized in that:
Described comparing is specially: the location records of described second memory device and the location records of described first memory device are carried out position and computing, described location records is the state that adopts 0 expression data of corresponding positions to upgrade, the state that adopts 1 expression data of corresponding positions not upgrade.
4, according to claim 1,2 or 3 described image recovery methods, it is characterized in that:
Describedly obtain the location records that first memory device carries out Data Update and be specially:
Described second memory device sends the request of obtaining the location records before described first memory device lost efficacy to described first memory device;
Described second memory device receives the preceding location records of inefficacy that first memory device sends.
5, image recovery method according to claim 1 is characterized in that:
The location records of the location records of described second memory device and first memory device adopts bitmap to carry out record.
6, a kind of memory device is characterized in that, comprising:
Acquiring unit is used for obtaining the location records that described another memory device carries out Data Update after another memory device recovers normally, and described location records writes down the update mode of data on each position;
Record cell is used to write down the location records of described memory device local terminal;
Comparing unit, be used for the location records of the described memory device of described recording unit records and the location records of described another memory device that described acquiring unit obtains are compared, obtain the position that described memory device and described another memory device contain different pieces of information;
Data transmission unit, the data that are used for described position correspondence that described comparing unit is obtained send to described another memory device.
7, memory device according to claim 6 is characterized in that:
Described comparing unit comprises first comparing unit, be used for the location records of the described memory device of described recording unit records and the location records of described another memory device that described acquiring unit obtains are carried out an exclusive disjunction, obtain the position that described memory device and described another memory device contain different pieces of information, described location records is the state that adopts 1 expression data of corresponding positions to upgrade, the state that adopts 0 expression data of corresponding positions not upgrade.
8, according to claim 6 or 7 described memory devices, it is characterized in that:
Described comparing unit comprises second comparing unit, be used for the location records of the described memory device of described recording unit records and the location records of described another memory device that described acquiring unit obtains are carried out position and computing, obtain the position that described memory device and described another memory device contain different pieces of information, described location records is the state that adopts 0 expression data of corresponding positions to upgrade, the state that adopts 1 expression data of corresponding positions not upgrade.
9, according to claim 6 or 7 described memory devices, it is characterized in that described memory device also comprises:
Request unit is used for the location records before described another memory device of acquisition request lost efficacy, and receives inefficacy that described another memory device the returns location records that line data upgrades that advances by described acquiring unit.
10, a kind of network system is characterized in that, comprising:
First memory device is used to send the location records that carries out Data Update, and the reception data are also upgraded, and described location records writes down the update mode of data on each position;
Second memory device is used for obtaining the location records that described first memory device sends after first memory device recovers normally; The location records of described second memory device and the location records of described first memory device that obtains are compared, obtain the position that described second memory device and described first memory device contain different pieces of information; The data of described position correspondence are sent to first memory device.
11, network system according to claim 10 is characterized in that:
Described second memory device comprises first comparing unit, be used for the location records of second memory device and the location records of described first memory device are carried out an exclusive disjunction, obtain the position that second memory device and first memory device contain different pieces of information, described location records is the state that adopts 1 expression data of corresponding positions to upgrade, the state that adopts 0 expression data of corresponding positions not upgrade.
12, according to claim 10 or 11 described network systems, it is characterized in that:
Described second memory device comprises second comparing unit, be used for the location records of second memory device and the location records of described first memory device are carried out position and computing, obtain the position that second memory device and first memory device contain different pieces of information, described location records is the state that adopts 0 expression data of corresponding positions to upgrade, the state that adopts 1 expression data of corresponding positions not upgrade.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007101086368A CN100454265C (en) | 2007-06-07 | 2007-06-07 | Image recovery method, storage equipment and network system |
| PCT/CN2008/070879 WO2008148319A1 (en) | 2007-06-07 | 2008-05-05 | Image recovery method, storage equipment and network system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007101086368A CN100454265C (en) | 2007-06-07 | 2007-06-07 | Image recovery method, storage equipment and network system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101067796A CN101067796A (en) | 2007-11-07 |
| CN100454265C true CN100454265C (en) | 2009-01-21 |
Family
ID=38880358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007101086368A Active CN100454265C (en) | 2007-06-07 | 2007-06-07 | Image recovery method, storage equipment and network system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN100454265C (en) |
| WO (1) | WO2008148319A1 (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100454265C (en) * | 2007-06-07 | 2009-01-21 | 华为技术有限公司 | Image recovery method, storage equipment and network system |
| CN101808137B (en) * | 2010-03-29 | 2014-09-03 | 成都市华为赛门铁克科技有限公司 | Data transmission method, device and system |
| CN102306115B (en) * | 2011-05-20 | 2014-01-08 | 华为数字技术（成都）有限公司 | Asynchronous remote copying method, system and equipment |
| CN102662800A (en) * | 2012-04-20 | 2012-09-12 | 浪潮电子信息产业股份有限公司 | Method for ensuring interrupted remote asynchronous mirroring service |
| 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 |
| CN105988901B (en) * | 2013-12-12 | 2019-06-18 | 华为技术有限公司 | Data copy method and storage system |
| EP3358466B1 (en) | 2013-12-12 | 2019-11-13 | Huawei Technologies Co., Ltd. | Data replication method and storage system |
| CN105208104B (en) * | 2015-08-26 | 2018-10-02 | 浪潮(北京)电子信息产业有限公司 | A kind of remote mirroring data consistency detecting method and device |
| US10416905B2 (en) * | 2017-02-09 | 2019-09-17 | Hewlett Packard Enterprise Development Lp | Modifying membership of replication groups via journal operations |
| CN107038091B (en) * | 2017-03-29 | 2019-07-26 | 国网山东省电力公司信息通信公司 | A kind of Information Security protection system and electric power application system data guard method based on asynchronous remote mirror image |
| CN107329701A (en) * | 2017-06-29 | 2017-11-07 | 郑州云海信息技术有限公司 | Creation method, the apparatus and system of dual-active volume in a kind of storage system |
| CN109828950A (en) * | 2019-01-29 | 2019-05-31 | 深圳前海达闼云端智能科技有限公司 | Data protection method, management system, server and readable storage medium |
| CN110990191B (en) * | 2019-11-01 | 2022-06-17 | 武汉船舶通信研究所（中国船舶重工集团公司第七二二研究所） | Data recovery method and system based on mirror image storage |
| 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 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1057533A (en) * | 1990-06-21 | 1992-01-01 | 国际商业机器公司 | Recover the method and apparatus of parity protected data |
| JP2004145854A (en) * | 2002-06-11 | 2004-05-20 | Hitachi Ltd | Method and system for data backup and recovery |
| CN1205550C (en) * | 2000-06-07 | 2005-06-08 | 处理存储器有限公司 | A method and system for highly-parallel logging and recovery operation in main-memory transaction processing systems |
| CN1742262A (en) * | 2003-01-31 | 2006-03-01 | 松下电器产业株式会社 | Differential data creating device and method, updated data recovery device and method, and program |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100454265C (en) * | 2007-06-07 | 2009-01-21 | 华为技术有限公司 | Image recovery method, storage equipment and network system |
-
2007
- 2007-06-07 CN CNB2007101086368A patent/CN100454265C/en active Active
-
2008
- 2008-05-05 WO PCT/CN2008/070879 patent/WO2008148319A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1057533A (en) * | 1990-06-21 | 1992-01-01 | 国际商业机器公司 | Recover the method and apparatus of parity protected data |
| CN1205550C (en) * | 2000-06-07 | 2005-06-08 | 处理存储器有限公司 | A method and system for highly-parallel logging and recovery operation in main-memory transaction processing systems |
| JP2004145854A (en) * | 2002-06-11 | 2004-05-20 | Hitachi Ltd | Method and system for data backup and recovery |
| CN1742262A (en) * | 2003-01-31 | 2006-03-01 | 松下电器产业株式会社 | Differential data creating device and method, updated data recovery device and method, and program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101067796A (en) | 2007-11-07 |
| WO2008148319A1 (en) | 2008-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100454265C (en) | Image recovery method, storage equipment and network system | |
| US10565071B2 (en) | Smart data replication recoverer | |
| JP4668763B2 (en) | Storage device restore method and storage device | |
| US7945730B2 (en) | Systems and methods for recovering from configuration data mismatches in a clustered environment | |
| US8271447B1 (en) | Mirroring metadata in a continuous data protection environment | |
| US8904231B2 (en) | Synchronous local and cross-site failover in clustered storage systems | |
| US9235632B1 (en) | Synchronization of replication | |
| US9501542B1 (en) | Methods and apparatus for volume synchronization | |
| US8335761B1 (en) | Replicating in a multi-copy environment | |
| CN101706795B (en) | Method for synchronizing data of database in active/standby server | |
| US6643671B2 (en) | System and method for synchronizing a data copy using an accumulation remote copy trio consistency group | |
| CN101755257B (en) | Managing the copying of writes from primary storages to secondary storages across different networks | |
| CN103077242B (en) | The method of a kind of fulfillment database server two-node cluster hot backup | |
| CN101808137B (en) | Data transmission method, device and system | |
| US9639383B1 (en) | Volume moving | |
| KR20180101941A (en) | Apparatus and method for replicating changed data in a source database management system to a target database management system in real time | |
| CN104378423A (en) | Metadata cluster distribution storage system and storage data reading and writing method | |
| KR20100063739A (en) | Virtual tape device at original center, virtual tape device at duplicate center, virtual library system and virtual tape control method | |
| CN103902405A (en) | Quasi-continuity data replication method and device | |
| WO2017014814A1 (en) | Replicating memory volumes | |
| CN111597197A (en) | Data reconciliation method and device between databases, storage medium and electronic equipment | |
| US20060265431A1 (en) | Information processing system, replication method, difference information holding apparatus and program | |
| CN110489491B (en) | Full data synchronization device suitable for A/B network double clusters | |
| JP6056408B2 (en) | Fault tolerant system | |
| CN113905054B (en) | RDMA (remote direct memory access) -based Kudu cluster data synchronization method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |