CN104090729A - Method and device for repairing mirror image synchronization through service write operation - Google Patents

Method and device for repairing mirror image synchronization through service write operation Download PDF

Info

Publication number
CN104090729A
CN104090729A CN201410317976.1A CN201410317976A CN104090729A CN 104090729 A CN104090729 A CN 104090729A CN 201410317976 A CN201410317976 A CN 201410317976A CN 104090729 A CN104090729 A CN 104090729A
Authority
CN
China
Prior art keywords
mirror image
write
resources
fault
resource
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201410317976.1A
Other languages
Chinese (zh)
Other versions
CN104090729B (en
Inventor
石岩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Uniview Technologies Co Ltd
Original Assignee
Zhejiang Uniview Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Uniview Technologies Co Ltd filed Critical Zhejiang Uniview Technologies Co Ltd
Priority to CN201410317976.1A priority Critical patent/CN104090729B/en
Publication of CN104090729A publication Critical patent/CN104090729A/en
Application granted granted Critical
Publication of CN104090729B publication Critical patent/CN104090729B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention provides a method and device for repairing mirror image synchronization through a service write operation. The method includes the steps that when a synchronization task that main resource data are synchronized to mirror image resources is carried out, fault resource addresses of fault areas are recorded to a cache resource, and it is marked that main resources are not synchronous with a mirror image state of the mirror image resources, wherein the fault resource addresses include fault resource addresses of the fault areas where the mirror image resources cannot be written in due to unsuccessful reading of the main resources or the main resources are successfully read but the mirror image resources are not successfully written; when service data are written in, if the mirror image resources are successfully written, the successful writing area belongs to the fault area, a fault resource address corresponding to the successful writing area is wiped off; when the synchronization task is finished and no fault resource address exists in the cache resource, the mirror image state is marked to be synchronized. When the mirror image state is unsynchronized, the main resources can be replaced as long as writing service data of the mirror image resources are successful, and mirror image protection is provided for the service, and the utilization rate of the mirror image resources is maximized.

Description

Repair synchronous method and the device of mirror image by business write operation
Technical field
The present invention relates to technical field of memory, relate in particular to a kind of by synchronous method and the device of business write operation reparation mirror image.
Background technology
Mirror image technology is that data are write to two parts independently in disk simultaneously, as RAID1 (Redundant Array of Independent Disks1, Redundant Array of Independent Disks (RAID) 1), or writes in the volume resource being based upon on multiple physical resources.Wherein, a resource is called primary resource, and another resource, as the copy of primary resource, is called mirror image resources, in the time of primary resource fault, business can be switched to mirror image resources, does not interrupt with guarantee business.In the time setting up the mirror of primary resource and mirror image resources, by carry out synchronous task by all data Complete Synchronizations of primary resource to mirror image resources, in the time writing business datum, business datum is write to primary resource and mirror image resources simultaneously, to ensure the data consistent of the two.
In prior art, carrying out when synchronous task, if unsuccessfully cause the mirror image resources cannot data writing from primary resource reading out data, or when the data that read from primary resource are write to mirror image resources failure, think that the mirrored state of two resources is not for synchronous; Under synchronous regime not, even if mirror image resources can be write business datum success, also can be because of synchronous regime not, and mirror image protection cannot be provided in the time of primary resource fault, thus cause service disconnection.
Summary of the invention
The invention provides and a kind ofly repair mirror image synchronous method and device by business write operation, to solve in prior art under synchronous regime not, writing the successful mirror image resources of business datum cannot provide the problem of mirror image protection.
According to the first aspect of the embodiment of the present invention, provide a kind of and repair the synchronous method of mirror image by business write operation, described method is applied on memory device, on described memory device, cache resources is set, and described method comprises:
In the time that primary resource data are synchronized to the synchronous task of mirror image resources by execution, the fault resource address of fault zone is recorded to described cache resources, and mark primary resource with the mirrored state of mirror image resources for not synchronizeing, wherein, described fault resource address comprises that primary resource reads the unsuccessful fault resource address that causes the fault zone that mirror image resources cannot write, and/or primary resource is read as merit and mirror image resources is write the fault resource address of unsuccessful fault zone;
In the time writing business datum, judge whether mirror image resources is write successfully, if mirror image resources is write successfully, and write successfully region and belong to described fault zone, described in removing, write successfully fault resource address corresponding to region;
When described synchronous task completes, and while thering is no fault resource address in described cache resources, described mirrored state is labeled as synchronous.
According to the second aspect of the embodiment of the present invention, provide a kind of and repair the synchronous device of mirror image by business write operation, described application of installation, on memory device, arranges cache resources on described memory device, and described device comprises:
Synchronous task performance element, for in the time that primary resource data are synchronized to the synchronous task of mirror image resources by execution, the fault resource address of fault zone is recorded to described cache resources, and mark primary resource with the mirrored state of mirror image resources for not synchronizeing, wherein, described fault resource address comprises that primary resource reads the unsuccessful fault resource address that causes the fault zone that mirror image resources cannot write, and/or primary resource is read as merit and mirror image resources is write the fault resource address of unsuccessful fault zone;
Business is write maintenance unit, in the time writing business datum, judges whether mirror image resources is write successfully, if mirror image resources is write successfully, and writes successfully region and belongs to described fault zone, described in removing, writes successfully fault resource address corresponding to region;
Mirror image is synchronously repaired unit, for completing when described synchronous task, and while thering is no fault resource address in described cache resources, described mirrored state is labeled as synchronous.
The application embodiment of the present invention, while recording execution synchronous task by cache resources, on primary resource, reading the unsuccessful mirror image resources that causes cannot write, or primary resource is read as merit and mirror image resources is write the fault resource address of unsuccessful fault zone, when the mirrored state of primary resource and mirror image resources is when synchronous, as long as business writes mirror image resources success, just remove the fault resource address of corresponding fault zone, and synchronous task complete and cache resources in mirrored state can be updated to while thering is no fault resource address synchronous, thereby ensure as long as mirror image resources is write business datum success, just can replace primary resource, for business provides mirror image protection, thereby maximize the utilization factor of mirror image resources.
Brief description of the drawings
Accompanying drawing is herein merged in instructions and forms the part of this instructions, shows embodiment according to the invention, and is used from and explains principle of the present invention with instructions one.
Fig. 1 is the application scenarios schematic diagram of the embodiment of the present invention;
Fig. 2 is the process flow diagram that in one embodiment of the present invention, mirror image resources is carried out synchronous task;
Fig. 3 is the method flow diagram that recovers mirror image resources synchronous regime in one embodiment of the present invention;
Fig. 4 is the hardware environment Organization Chart that recovers the device operation of mirror image resources synchronous regime in one embodiment of the present invention;
Fig. 5 is the device block diagram that recovers mirror image resources synchronous regime in one embodiment of the present invention.
Embodiment
Mirror image technology in the present invention is that data are write to two parts independently in disk simultaneously, as RAID1, or writes in the volume resource being based upon on multiple physical resources.Referring to Fig. 1, the application scenarios schematic diagram for the embodiment of the present invention:
In Fig. 1, client device is by network and memory device communication, on memory device, be two independently resource relations that establish mirror image, one of them resource is primary resource, another resource is mirror image resources, storage space on primary resource and mirror image resources is divided according to the band of resource place array (block), and each band has corresponding resource address.In the time producing business datum on client device, by memory device, business datum is write in primary resource and mirror image resources.While writing business datum, can adopt synchronous mirror writing mode, business datum be write to primary resource and mirror image resources simultaneously; Also can adopt asynchronous mirroring writing mode, first write special cache (buffer memory) by business datum, and then business datum is write respectively to primary resource and mirror image resources from special cache.Writing mode to business datum in the present invention does not limit.
In the present invention, on memory device, be provided with cache resources, when being used for recording primary resource and mirror image resources and carrying out synchronous task, unsuccessfully cause the fault resource address of the fault zone that mirror image resources cannot write from primary resource reading out data.Preferably, can support for this cache resources provides UPS (Uninterruptible Power Supply, uninterrupted power source), can not lose because of memory device power down with the fault resource address that ensures to record in this cache resources.The fault resource address recording based on cache resources; in the time writing business datum; as long as business writes mirror image resources success; just remove the fault resource address of corresponding fault zone; and synchronous task complete and cache resources in mirrored state can be updated to while thering is no fault resource address synchronous, thereby ensure just can provide mirror image protection for business as long as mirror image resources is write business datum success.Below by specific embodiment, the present invention program is elaborated.
Referring to Fig. 2, the process flow diagram for mirror image resources execution synchronous task in one embodiment of the present invention:
Step 200: start to carry out the synchronous task that primary resource is synchronized to mirror image resources.
Step 201: order is synchronized to the data of a band on primary resource array on the corresponding band of mirror image resources place array.
Establishing mirror image for primary resource and mirror image resources while being related to, by carrying out synchronous task, primary resource data are synchronized to mirror image resources.In the time carrying out synchronous task, the data of the each band of the corresponding array of online primary resource are synchronized on the corresponding band of mirror image resources place array one by one, this synchronizing process comprises reading out data from primary resource, and data are write to mirror image resources.
Step 202: judge that whether primary resource is online, if so, perform step 203; Otherwise, execution step 208.
Step 203: judge that whether primary resource data are read as merit, if so, perform step 204; Otherwise, execution step 207.
Step 204: judge that whether mirror image resources is online, if so, perform step 205; Otherwise, execution step 208.
Step 205: judge when the data of reading from primary resource are write toward mirror image resources and whether write successfully, if so, perform step 206; Otherwise, execution step 207.
Step 206: judge whether synchronous task executes, if so, finish current flow process; Otherwise, return to step 201.
Step 207: primary resource is read unsuccessfully to cause mirror image resources to write or fault resource address that mirror image resources is write unsuccessful fault zone is recorded to cache resources, and mark primary resource with the mirrored state of mirror image resources for not synchronizeing, return to step 206.
In the present invention, on memory device, be provided with spatial cache, read unsuccessfully in primary resource data, or mirror image resources data write when unsuccessful, record unsuccessful fault resource address in cache resources.In the time of record trouble resource address, the corresponding LUN of fault resource (Logical Unit Number, the logical unit number) mark that combination can be calculated and the sector position of actual physical layout are as fault resource address.
Step 208: suspend synchronous task, finish current flow process.
Referring to Fig. 3, be to repair the synchronous method flow diagram of mirror image by business write operation in one embodiment of the present invention, this embodiment, based on synchronous implementation shown in Fig. 2, supposes that mirrored state is for having recorded fault resource address in not synchronous and cache resources:
Step 301: write business datum.
In the present invention, write business datum and can adopt synchronous writing mode, also can adopt asynchronous write mode.No matter adopt which kind of writing mode, all finally whether write the corresponding operation of successful result execution according to primary resource and mirror image resources.As a kind of example, whether the business that the present embodiment is described writes logical process and writes and successfully start judgement from mirror image resources, first judges the result of writing of mirror image resources, then judges the result of writing of primary resource; Similarly, whether business writes logical process and also can write and successfully start judgement from primary resource, first judges the result of writing of primary resource, then judges the result of writing of mirror image resources, and this present embodiment is repeated no more.
Step 302: judge that whether mirror image resources is write successfully, if so, performs step 303; Otherwise, execution step 309.
Step 303: in the time writing successfully region and belong to fault zone, remove that in buffer memory, this writes successfully fault resource address corresponding to region.
In the synchronous task implementation shown in Fig. 2, cache resources has recorded because the unsuccessful fault resource address that causes mirror image resources to write of primary resource read data, or primary resource is read as merit but mirror image resources is not write successful fault resource address.In business ablation process, in the time that business datum is written to fault zone corresponding to certain fault resource address, if mirror image resources is write successfully, can remove the fault resource address of this fault zone of recording in cache resources.
Step 304: synchronous task complete and cache resources in there is no fault resource address, mirrored state is labeled as synchronous.
In the present invention, business writes to occur in and carries out in synchronous task process, or after carrying out synchronous task and completing.Wherein, synchronous task complete and cache resources in while thering is no fault resource address, illustrate that the All Ranges on mirror image resources has all been write successfully correct data through repeatedly writing service data manipulating, now mirrored state is revised as to " synchronous " from " not synchronous ".
Step 305: judge that whether primary resource is write successfully, if so, performs step 308; Otherwise, execution step 306.
Step 306: mirror image resources is replaced to primary resource, and return to business success.
In the present embodiment, write successfully at mirror image resources, and primary resource is write when unsuccessful, because mirrored state is labeled as " synchronous ", therefore mirror image resources can be replaced primary resource at once, for business provides mirror image protection.
Step 307: the fault resource address of primary resource being write to unsuccessful fault zone is recorded to cache resources, and mark mirrored state is not for synchronous, finishes current flow process.
In step 306, mirror image resources is replaced after primary resource; former mirror image resources becomes new primary resource; and former primary resource becomes new mirror image resources; this stylish mirror image resources is because business is write unsuccessful; fault resource address need to be recorded to cache resources, because new mirror image resources cannot provide mirror image protection, therefore mirrored state be revised as to " not synchronous " again from " synchronous "; follow-uply can, according to existing synchronization mechanism, restart to carry out mirror image synchronous task.
Step 308: return to business success, finish current flow process.
Step 309: the fault resource address of mirror image resources being write to unsuccessful fault zone is recorded to cache resources, and etc. pending next synchronous task, finish current flow process.
Write unsuccessfully due to mirror image resources, therefore mirror image resources cannot provide mirror image protection for business, need to wait pending next synchronous task time, mirror image resources is repaired.
Step 310: judge that whether primary resource is write successfully, if so, performs step 308; Otherwise, execution step 311.
Step 311: return to service fail, finish current flow process.
Known in conjunction with the embodiment shown in Fig. 2 and Fig. 3, the present invention records to carry out by cache resources and on primary resource, reads when synchronous task unsuccessfully to cause mirror image resources to write or primary resource is read as merit but mirror image resources is not write the fault resource address of successful fault zone, when the mirrored state of primary resource and mirror image resources is when synchronous, as long as business writes mirror image resources success, just remove the fault resource address of corresponding fault zone, and synchronous task complete and cache resources in mirrored state can be updated to while thering is no fault resource address synchronous, thereby ensure as long as mirror image resources is write business datum success, just can replace primary resource, for business provides mirror image protection, thereby can maximize the utilization factor of mirror image resources.
Referring to Fig. 4, the hardware environment Organization Chart moving for recovering the device of mirror image resources synchronous regime in one embodiment of the present invention:
The embodiment that the present invention repairs the synchronous device of mirror image by business write operation can be applied on memory device.Device embodiment can realize by software, also can realize by the mode of hardware or software and hardware combining.Being embodied as example with software, as the device on a logical meaning, is by the CPU of its place equipment, computer program instructions corresponding in nonvolatile memory to be read to operation in internal memory to form.Say from hardware view; as shown in Figure 4; for the present invention is by a kind of hardware structure diagram of the synchronous device place equipment of business write operation reparation mirror image; except the CPU shown in Fig. 4, internal memory, network interface and nonvolatile memory, the equipment that installs place in embodiment can also comprise other hardware conventionally.
Referring to Fig. 5, be to repair the synchronous device block diagram of mirror image by business write operation in one embodiment of the present invention.
Described device comprises: synchronous task performance element 510, business write maintenance unit 520 and mirror image is synchronously repaired unit 530.
Wherein, synchronous task performance element 510, for in the time that primary resource data are synchronized to the synchronous task of mirror image resources by execution, the fault resource address of fault zone is recorded to described cache resources, and mark primary resource with the mirrored state of mirror image resources for not synchronizeing, wherein, described fault resource address comprises that primary resource reads the unsuccessful fault resource address that causes the fault zone that mirror image resources cannot write, or primary resource is read as merit and mirror image resources is write the fault resource address of unsuccessful fault zone;
Business is write maintenance unit 520, in the time writing business datum, judges whether mirror image resources is write successfully, if mirror image resources is write successfully, and writes successfully region and belongs to described fault zone, described in removing, writes successfully fault resource address corresponding to region;
Mirror image is synchronously repaired unit 530, for completing when described synchronous task, and while thering is no fault resource address in described cache resources, described mirrored state is labeled as synchronous.
Optionally, described business is write maintenance unit 520, can also be used in the time writing business datum, if mirror image resources is write successfully, and described mirrored state is for synchronous, judge whether primary resource is write successfully, if primary resource is write unsuccessful, described mirror image resources is replaced to described primary resource, and return to business success, and the fault resource address that described primary resource is write unsuccessful fault zone is recorded to described cache resources, and described in mark mirrored state for not synchronous; If primary resource is write successfully, return to business success.
Optionally, described business is write maintenance unit 520, can also be used in the time writing business datum, unsuccessful if mirror image resources is write, will write unsuccessful fault resource address and be recorded to described cache resources, and wait for that described synchronous task performance element carries out next synchronous task.
Optionally, described business is write maintenance unit 520, can also be used in the time writing business datum, unsuccessful if mirror image resources is write, and judges whether described primary resource is write successfully, if write successfully, returns to business success, if write unsuccessfully, returns to service fail.
In said apparatus, the implementation procedure of the function and efficacy of unit specifically refers to the implementation procedure of corresponding step in said method, does not repeat them here.
Those skilled in the art, considering instructions and putting into practice after invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised undocumented common practise or the conventional techniques means in the art of the present invention.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendments and change not departing from its scope.Scope of the present invention is only limited by appended claim.

Claims (10)

1. repair the synchronous method of mirror image by business write operation, it is characterized in that, described method is applied on memory device, on described memory device, cache resources is set, and described method comprises:
In the time that primary resource data are synchronized to the synchronous task of mirror image resources by execution, the fault resource address of fault zone is recorded to described cache resources, and mark primary resource with the mirrored state of mirror image resources for not synchronizeing, wherein, described fault resource address comprises that primary resource reads the unsuccessful fault resource address that causes the fault zone that mirror image resources cannot write, or primary resource is read as merit and mirror image resources is write the fault resource address of unsuccessful fault zone;
In the time writing business datum, judge whether mirror image resources is write successfully, if mirror image resources is write successfully, and write successfully region and belong to described fault zone, described in removing, write successfully fault resource address corresponding to region;
When described synchronous task completes, and while thering is no fault resource address in described cache resources, described mirrored state is labeled as synchronous.
2. method according to claim 1, is characterized in that, described method also comprises:
In the time writing business datum, if mirror image resources is write successfully, and described mirrored state is for synchronous, judges whether primary resource is write successfully, unsuccessful if primary resource is write, and described mirror image resources is replaced to described primary resource, and returns to business success;
The fault resource address of described primary resource being write to unsuccessful fault zone is recorded to described cache resources, and described in mark mirrored state for not synchronous.
3. method according to claim 2, is characterized in that, described method also comprises:
In the time writing business datum, if primary resource is write successfully, return to business success.
4. method according to claim 1, is characterized in that, described method also comprises:
In the time writing business datum, unsuccessful if mirror image resources is write, will write unsuccessful fault resource address and be recorded to described cache resources, and etc. pending next synchronous task.
5. method according to claim 4, is characterized in that, described method also comprises:
In the time writing business datum, unsuccessful if mirror image resources is write, judge whether described primary resource is write successfully, if write successfully, return to business success, if write unsuccessfully, return to service fail.
6. repair the synchronous device of mirror image by business write operation, it is characterized in that, described application of installation, on memory device, arranges cache resources on described memory device, and described device comprises:
Synchronous task performance element, for in the time that primary resource data are synchronized to the synchronous task of mirror image resources by execution, the fault resource address of fault zone is recorded to described cache resources, and mark primary resource with the mirrored state of mirror image resources for not synchronizeing, wherein, described fault resource address comprises that primary resource reads the unsuccessful fault resource address that causes the fault zone that mirror image resources cannot write, or primary resource is read as merit and mirror image resources is write the fault resource address of unsuccessful fault zone;
Business is write maintenance unit, in the time writing business datum, judges whether mirror image resources is write successfully, if mirror image resources is write successfully, and writes successfully region and belongs to described fault zone, described in removing, writes successfully fault resource address corresponding to region;
Mirror image is synchronously repaired unit, for completing when described synchronous task, and while thering is no fault resource address in described cache resources, described mirrored state is labeled as synchronous.
7. device according to claim 6, is characterized in that,
Described business is write maintenance unit, also in the time writing business datum, if mirror image resources is write successfully, and described mirrored state, for synchronous, judges whether primary resource is write successfully, unsuccessful if primary resource is write, described mirror image resources is replaced to described primary resource, and return to business success, and the fault resource address that described primary resource is write unsuccessful fault zone is recorded to described cache resources, and described in mark mirrored state for not synchronous.
8. device according to claim 7, is characterized in that,
Described business is write maintenance unit, also in the time writing business datum, if primary resource is write successfully, returns to business success.
9. device according to claim 6, is characterized in that,
Described business is write maintenance unit, also in the time writing business datum, unsuccessful if mirror image resources is write, and will write unsuccessful fault resource address and be recorded to described cache resources, and wait for that described synchronous task performance element carries out next synchronous task.
10. device according to claim 9, is characterized in that,
Described business is write maintenance unit, also in the time writing business datum, unsuccessful if mirror image resources is write, and judges whether described primary resource is write successfully, if write successfully, returns to business success, if write unsuccessfully, returns to service fail.
CN201410317976.1A 2014-07-04 2014-07-04 The method and device of mirror image synchronization is repaired by business write operation Active CN104090729B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410317976.1A CN104090729B (en) 2014-07-04 2014-07-04 The method and device of mirror image synchronization is repaired by business write operation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410317976.1A CN104090729B (en) 2014-07-04 2014-07-04 The method and device of mirror image synchronization is repaired by business write operation

Publications (2)

Publication Number Publication Date
CN104090729A true CN104090729A (en) 2014-10-08
CN104090729B CN104090729B (en) 2017-08-15

Family

ID=51638449

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410317976.1A Active CN104090729B (en) 2014-07-04 2014-07-04 The method and device of mirror image synchronization is repaired by business write operation

Country Status (1)

Country Link
CN (1) CN104090729B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915152A (en) * 2015-06-05 2015-09-16 浙江宇视科技有限公司 Device and method for guaranteeing s service validity in data mirroring
CN106708960A (en) * 2016-11-30 2017-05-24 浙江宇视科技有限公司 Restoration method for file system of NAS device and NAS device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1995000906A1 (en) * 1993-06-23 1995-01-05 Vinca Corporation Method for improving disk mirroring error recovery in a computer system including an alternate communication path
US20040162926A1 (en) * 2003-02-14 2004-08-19 Itzhak Levy Serial advanced technology attachment interface
CN1773443A (en) * 2004-11-08 2006-05-17 富士通株式会社 Disk array apparatus, method of data recovery, and computer product
CN102096615A (en) * 2011-01-25 2011-06-15 上海爱数软件有限公司 Remote incremental backup method and system
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

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1995000906A1 (en) * 1993-06-23 1995-01-05 Vinca Corporation Method for improving disk mirroring error recovery in a computer system including an alternate communication path
US20040162926A1 (en) * 2003-02-14 2004-08-19 Itzhak Levy Serial advanced technology attachment interface
CN1773443A (en) * 2004-11-08 2006-05-17 富士通株式会社 Disk array apparatus, method of data recovery, and computer product
CN102096615A (en) * 2011-01-25 2011-06-15 上海爱数软件有限公司 Remote incremental backup method and system
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

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915152A (en) * 2015-06-05 2015-09-16 浙江宇视科技有限公司 Device and method for guaranteeing s service validity in data mirroring
CN104915152B (en) * 2015-06-05 2018-09-14 浙江宇视科技有限公司 Ensure the method and apparatus of business validity when a kind of data image
CN106708960A (en) * 2016-11-30 2017-05-24 浙江宇视科技有限公司 Restoration method for file system of NAS device and NAS device
CN106708960B (en) * 2016-11-30 2021-05-28 浙江宇视科技有限公司 Repair method of NAS device file system and NAS device

Also Published As

Publication number Publication date
CN104090729B (en) 2017-08-15

Similar Documents

Publication Publication Date Title
US7966463B2 (en) Asynchronous remote copy system and control method for the same
US8473459B2 (en) Workload learning in data replication environments
US8285679B2 (en) Creating a buffer point-in-time copy relationship for a point-in-time copy function executed to create a point-in-time copy relationship
US9396121B2 (en) Managing sequentiality of tracks for asynchronous PPRC tracks on secondary
US20080065843A1 (en) Apparatus, system, and method for an improved synchronous mirror swap
CN110058791B (en) Storage system and corresponding method and computer readable medium
US10459813B2 (en) System and device for synchronizing data in a plurality of devices
CN105302667A (en) Cluster architecture based high-reliability data backup and recovery method
JP4491330B2 (en) Disk array device, data recovery method and data recovery program
CN111274065B (en) Disaster recovery method and device based on software
US9558084B2 (en) Recovery control in mirrored disks
CN103544081B (en) The management method of double base data server and device
US9430485B2 (en) Information processor and backup method
CN111158955A (en) High-availability system based on volume replication and multi-server data synchronization method
US10013171B2 (en) Reducing stress on RAIDS under rebuild
US7496724B2 (en) Load balancing in a mirrored storage system
CN104090729A (en) Method and device for repairing mirror image synchronization through service write operation
US10409504B2 (en) Soft-switch in storage system
JP2012509533A5 (en)
CN116204137A (en) Distributed storage system, control method, device and equipment based on DPU
CN100565467C (en) The backed up in synchronization apparatus and method that are used for storage device
JP4893214B2 (en) Storage control device, storage control method, and storage control program
CN107544868B (en) Data recovery method and device
CN110704239A (en) Data copying method and device and electronic equipment
JPH11353125A (en) Data restoring method for radio device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant