CN103116474B - A kind of raid card method for designing for data recovery and selfreparing - Google Patents
A kind of raid card method for designing for data recovery and selfreparing Download PDFInfo
- Publication number
- CN103116474B CN103116474B CN201310028448.XA CN201310028448A CN103116474B CN 103116474 B CN103116474 B CN 103116474B CN 201310028448 A CN201310028448 A CN 201310028448A CN 103116474 B CN103116474 B CN 103116474B
- Authority
- CN
- China
- Prior art keywords
- raid
- disk
- data
- slice
- write
- 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
- 238000011084 recovery Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000013461 design Methods 0.000 claims abstract description 9
- 238000012795 verification Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 6
- 238000000151 deposition Methods 0.000 claims description 5
- 238000013500 data storage Methods 0.000 claims description 4
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000006731 degradation reaction Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 230000007257 malfunction Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000002618 waking effect Effects 0.000 claims description 3
- 230000007474 system interaction Effects 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 claims 1
- 230000003993 interaction Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Signal Processing For Digital Recording And Reproducing (AREA)
- Debugging And Monitoring (AREA)
Abstract
The present invention provides a kind of raid card method for designing for data recovery and selfreparing, comprises the following steps that：When raid catastrophe failure occurs and needs human intervention and carry out data recovery, raid systems are interacted with data recovery system, facilitate data recovery work preferably to carry out to reach, and raid boards addition Functional Design is as follows：A, for raid systems are when normal operation, operating system need not be interacted with disk, and simply when breaking down, operating system just needs to interact with disk, in this case, raid card the Interface design being connected with system cpu into multiplexing port；B, the multiplexing port are realized with the following method, switched over using switch is pulled and connected, when switch is pushed a certain position, operating system can't see the disk of bottom, raid is can only see, the disk that system can not be docked on raid card is operated, when switch pushes another location, operating system sees raid and each disk on raid card simultaneously, and disk can be operated by related software.
Description
Technical field
It is the present invention relates to Computer Applied Technology field, specifically a kind of for data recovery and the raid of selfreparing
Card method for designing.
Background technology
Magnetic more and more extensive in the use of all trades and professions in present large storage facilities, using in storage device
Phenomenon of the disk in the form of single-deck is also more and more rare, and the overwhelming majority is understood polylith disk before writing data toward disk
It is newly-built into raid, so both expanded memory block and obtained capacity, also improved read or write speed（Except raid1）, what is also had improves
Security（Except raid0）.It is to magnetic using special raid card that Raid has hardware raid and two kinds of software raid, hardware raid
Disk is managed；Software raid is managed to disk using the raid modules of operating system, and which functions as a raid
Card hardware.Using software raid advantage of lower cost, but the burden of system cpu is the increase in, substantial amounts of cpu bandwidth can be expended.
And raid card hyperdisk is used, the performance of raising storage that comparatively can be larger reduces system burden, and this is deposited future
Storage system more and more can be used when design.
Existing raid card is defective in design, is mainly reflected in using after raid card, system can not directly with
Disk is interacted, and must could be communicated by raid card between both, namely raid for system the disk of bottom
Shielded.This can go wrong in raid data disks, band trouble when needing to carry out data recovery, or raid systems
System will be also not easily accomplished when needing human intervention.
When raid breaks down（Fall disk as one piece of disk occur in raid5 systems）If, it is hot standby having started setting up
Disk, raid can be rebuild.During raid rebuilds, the IO performances of raid can be had a strong impact on.When this is mainly raid reconstructions,
Substantial amounts of I/O bandwidth can be taken, and easily occurs rebuilding unsuccessful situation.Under many circumstances, after raid falls disk, raid weights
When building, keeper can disconnect storage service, and this can no doubt make to be stored in more difficult error when raid rebuilds,
But for large-scale data center, business is disconnected may affect the work of many users.
Present raid is typically all replaced original faulty disk when rebuilding completely, is totally rebuild, it is time-consuming compared with
It is many, and it is not that disk occurs in that the mistake that cannot be used that raid goes offline sometimes, it is possible to only disk is in read-write data
When occur in that time-out so that raid card could not receive the recovery of disk within the time of regulation, make raid think the magnetic
Disk occurs in that serious failure, and makes disk go offline.For disk goes offline, raid Problems of Reconstruction is carried out, it should disk of distinguishing one from the other
The order of severity for breaking down, then reselection whether rebuild or how to rebuild.
The content of the invention
The technical assignment of the present invention is to solve the deficiencies in the prior art, there is provided a kind of for data recovery and selfreparing
Raid card method for designing.
The technical scheme is that what is realized in the following manner, comprise the following steps that：
（One）When there is catastrophe failure and needs human intervention and carry out data recovery in raid, raid systems and data recovery
System interaction, facilitates data recovery work preferably to carry out to reach, and raid boards addition Functional Design is as follows：
A, for raid systems are when normal operation, operating system need not interact with disk, simply occur it is former
When barrier, operating system just needs to interact with disk, and in this case, raid card is connecing for being connected with system cpu
Mouth is designed to multiplexing port；
B, the multiplexing port realize with the following method, switched over using switch is pulled and connected, when switch is pushed a certain position
When, operating system can't see the disk of bottom, can only see raid, and the disk that system can not be docked on raid card is grasped
Make, when switch pushes another location, operating system sees raid and each disk on raid card simultaneously, and can be to magnetic
Disk is operated by related software；
C, when data recovery, existing data recovery software is run substantially under windows systems, extensive in data
When multiple engineer implements data recovery, it is only necessary to which related software is installed, data recovery is carried out in the machine related
Operation, to protect the safety of user data as much as possible；
D, for unix is used, the equipment of linux operating systems, the data disks in storage need to recover work with exogenous data
The computing device of Cheng Shi is connected, for convenience data recovery, and raid card preferably provides external such as the relevant interface of USB, should
Interface is not allowing to be attached equipment at ordinary times, and whether its foreign work, should be using pulling and connecting switch control rule, when needing raid
When card is by USB interface external connection, switches off raid card and main frame all logics and be connected by pulling and connecting；
By above-mentioned measure, raid systems provide for very big when raid once collapses and needs to carry out data recovery
Convenience；
（Two）When disk occur in raid systems, raid system maintenances one have the band list of write operation, raid systems
It is voluntarily quick to rebuild, comprise the steps；
A, there is disk for raid systems after, in the case where HotSpare disk is not provided with, raid occurs degradation,
At this moment the disk that goes offline will not carry out the read-write of data, and the read-write of all of data is undertaken by other disks, and start to safeguard a row
Table, and to record and write situation from fall each bands of raid that disk starts；
B, as under many circumstances, it is not that disk serious problems occurs that disk falls disk, it may be possible to which disk is being IO
Operation is the response that is not able to do in time, so that the raid system erroneous judgements disks cisco unity malfunction；
C therefore in order to reduce investment, raid systems recover normal as early as possible, and raid card should keep calling out the disk that goes offline
Wake up and operate, if after waking up repeatedly, disk is still correct to be responded, and at this moment raid card should be treated as the disk and occur in that
Serious failure, follow-up management person should allow the disk to completely disengage from raid, and disk situation is fallen, wake up situation, and dependent failure is examined
Disconnected situation, the measure write raid card log taken and system journal, while each bars of raid that disk starts what is safeguarded in the past
The write record situation of band is removed；
If d, wake-up pass through, raid card together with other member disks should be worked the disk for going offline originally, undertake number
According to read-write, i.e., all of disk in the middle of the data write raid of new write, the data during going offline originally are tieed up according to raid card
The list of shield re-starts all of disk of write by way of reading to rewrite, and thus avoids the need for adding again new building, totally
The situation of reconstruction；
It is exactly to fall the disk time period specifically to have the band content in which slice-group to be changed that raid needs the list safeguarded
Become, it is assumed that when raid completes the write of slice-group 4, then disk occurs in disk 3, and at this moment raid5 may be degraded into raid0, after
Continuous writes the data to disk 1 and disk 2, represents verification band with P, and the verification data of such as band 0 is represented with p0；Band 1
Verification data is represented with P1；The like.After disk 3 goes offline, data write disk 1, disk 2.Disk 3 is added to again
In the middle of raid, and carried out data storage together together with other disks, so namely only have slice-group 4 to slice-group n it
Between slice-group need to be recovered, therefore according to strip data structure, the data reconstruction for falling the disk time period just, so
The time of raid reconstructions is greatlyd save just；
（Three）Quick raid process of reconstruction realizes that raid systems are to be written and read scheduling according to priority, so that front end is
System can continue to be normally carried out when interacting with storage, and concrete reconstruction procedures are as follows：
Whether a, raid rebuild to start needs to be monitored the IO situations of present raid, if the IO of raid is very at this stage
It is busy, then temporarily cease reconstruction, namely the IO priority rebuild of raid be placed on it is minimum；
B, when the IO of raid is relatively idle, raid card system is write list according to the band above safeguarded and is found out
During raid falls disk, those bands are changed, and are then read out the disk of original operational excellence in one of slice-group
In data, as original raid types are raid5, fall raid after disk and may be degraded, become raid0, thus it is remaining that
The entirely data of storage, no verification data in the middle of the band of a little disks；
If c, will recover whole raid5 systems, it must be determined that in the middle of a slice-group, which stripe is used for depositing
Verification data is put, this needs scanning slice-group above, show that the data structure of raid systems is left synchronization on earth, it is left asynchronous,
Right synchronization, right asynchronous, conventional or unconventional data store organisation form, finally determines which stripe in slice-group
The data structure form of the raid for depositing verification data, is finally determined, will such as determine that the data for needing reconstruction part are deposited
Storage structure, determines how verification band is deposited, if scanning 4 slice-groups above, can just show that this is conventional left different
Step structure, also can start certainly the data store organisation of setting, calculate the data location mode of each slice-group according to raid；
D, define the version of data after, the data to reading just now calculate verification data, after the completion of each
Strip data this completes the band safeguarded in the middle of list according to data structure form write disk determined above
The reconstruction of group data, also needs to the slice-group to delete from the middle of the data list safeguarded after the completion of reconstruction；
E, according to above the step of carry out the process of reconstruction of next slice-group, the slice-group whole in safeguarding list
Recovery is completed.
Beneficial effects of the present invention：Can be gone out in data in hardware raid card and computer system by the method for the present invention
How preferably to interact to facilitate data reparation below, and reparation how is improved during data reparation when now damage
Speed.
Description of the drawings
Fig. 1 is raid board structure schematic diagrames；
Fig. 2 is that raid5 falls disk and is waken up situation schematic diagram.
Specific embodiment
Below in conjunction with the accompanying drawings the method for the present invention is described in further detail.
The present invention mainly proposes the raid network system realizations for data recovery and selfreparing in terms of 3.
（One）There is catastrophe failure in raid in realization, when needing human intervention and carrying out data recovery, raid systems and number
Interact according to recovery system.Data recovery work is facilitated preferably to carry out in order to reach, raid boards addition Functional Design
A, for raid systems are when normal operation, operating system need not interact with disk, simply occur it is former
When barrier, operating system just needs to interact with disk.In this case, raid card can be being connected with system cpu
Interface design into multiplexing port；
B, the multiplexing port can be realized with the following method, using pulling and connecting switch（Or related similar approach）, when pulling and connecting
Switch pushes a certain position（It is assumed to be location A）When, operating system can't see the disk of bottom, can only see raid, and system is not
The disk that can be docked on raid card is operated.When switch pushes another location（It is assumed to be B location）When, operating system can be with
See raid and each disk on raid card simultaneously, and disk can be operated by related software；
C, design above are practical for windows systematic comparisons, and when data recovery, existing data are extensive
Multiple software is run substantially under windows systems, when data recovery engineer facility data is recovered, it is only necessary to related
Software installation gets on, and data recovery associative operation is carried out in the machine.This can protect the safety of user data as far as possible；
D, because present many servers, the operating system of the equipment such as storage is all unix, the operating system such as linux, existing
Data recovery software can not temporarily operate above.And the data disks in many times storage are needed for and the external world
The computing device of data recovery engineer is connected, and for the convenience of data recovery, raid card preferably provides external such as USB etc.
Relevant interface.The interface is not allowed to being attached at ordinary times, and whether its foreign work is also using by above-mentioned group
Connect switch control rule.When pull and connect switch push be assumed to be location of C when raid card by USB interface external connection, and can disconnect
Raid card and main frame all logics are connected.
So for raid systems just can raid once collapse need to carry out data recovery when offer it is very big
It is convenient.
（Two）There is disk in raid systems, raid system maintenances one have the band list of write operation, according to data
There are raid systems voluntarily quickly to rebuild.（By taking raid5 as an example, because raid5 currently uses comparison many, security, performance each side
It is relatively all relatively good.）
A, there is disk for raid systems（Single disc falls disk）Afterwards, in the case where HotSpare disk is not provided with, raid
Degradation occurs, the disk that at this moment goes offline will not carry out the read-write of data, the read-write of all of data is undertaken by other disks.And start
Safeguard a list, and to record and situation is write from fall each bands of raid that disk starts；
B, as under many circumstances, it is not that disk serious problems occurs that disk falls disk, it may be possible to which disk is being IO
Operation is the response that is not able to do in time, so that raid systems think the disk cisco unity malfunction；
C therefore in order to reduce investment, raid systems are back to normal as early as possible, and raid card should keep calling out the disk that goes offline
Wake up operation, if after waking up repeatedly, such as 5 times, disk is still correct to be responded, and at this moment raid card should be worked as the disk
Into serious failure is occurred in that, allow the disk to completely disengage from raid, and disk situation is fallen, wake up situation, dependent failure diagnoses situation,
Measure write raid card log and system journal that follow-up management person should take.What disk started what is safeguarded in the past simultaneously
The write record situation of each bands of raid is removed；
If d, wake-up pass through, raid card together with other member disks should be worked the disk for going offline originally, undertake number
According to read-write.All of disk in the middle of the data write raid of i.e. new write, the data during going offline originally are tieed up according to raid card
The list of shield re-starts all of disk of write by way of reading to rewrite.Thus avoid the need for adding again new building, totally
The situation of reconstruction.
As schemed（2）, Raid need safeguard list be exactly fall the disk time period specifically have which slice-group in band content
Changed.Assume that then disk occurs in disk 3, and this is that raid5 may be degraded into when raid completes the write of slice-group 4
Raid0, continuation write the data to disk 1 and disk 2.Figure（2）Middle P represents verification band, and such as P0 represents the school of No. 0 slice-group
Test band.Numeral in form represents band logical order., by Suspend To Disk, disk 3 is again for slice-group n and later expression raid
Rejoin in the middle of raid, and data storage has been carried out together with other disks together, so namely only have slice-group 4 to arrive
Slice-group between slice-group n needs to be recovered, therefore according to strip data structure, the data reconstruction for falling the disk time period just
Row, thus greatlys save the time of raid reconstructions.
（Three）The concrete reconstruction procedures of quick raid process of reconstruction：Realize that raid systems are written and read tune according to priority
Degree, can continue to be normally carried out when interacting with storage so as to front end system.（It is not that the reconstruction is rebuild totally with existing frequently-used raid
With）
Whether a, raid rebuild to start needs to be monitored the io situations of present raid, if the IO of raid is very at this stage
It is busy, then temporarily cease reconstruction.Namely raid rebuild IO priority be placed on it is minimum；
B, when the io of raid is relatively idle, raid card system is write list according to the band above safeguarded and is found out
During raid falls disk, those bands are changed, and are then read out the disk of original operational excellence in one of slice-group
In data.As original raid types are raid5, fall raid after disk and may be degraded, become raid0, thus it is remaining that
The entirely data of storage, no verification data in the middle of the band of a little disks；
If c, will recover whole raid5 systems, it must be determined that in the middle of a slice-group, that stripe is used for depositing
Verification data is put, this needs scanning slice-group above, show that the data structure of raid systems is left synchronization on earth, it is left asynchronous,
Right synchronization, right asynchronous, conventional or unconventional data store organisation form, finally determines which stripe in slice-group
For depositing verification data, the data structure form of the raid is finally determined.As schemed（2）Shown, will such as determine needs to rebuild
Partial data store organisation, determines how verification band is deposited, and can such as scan 4 slice-groups above, it is possible to
It is conventional left asynchronous structure to go out this.The data store organisation of setting can certainly be started according to raid, each band is calculated
The data location mode of group；
D, define the version of data after, the data to reading just now calculate verification data, after the completion of each
Strip data is according to data structure form write disk determined above.This completes and safeguard a band in the middle of list
The reconstruction of group data, also needs to the slice-group to delete from the middle of the data list safeguarded after the completion of reconstruction；
E, according to above the step of carry out the process of reconstruction of next slice-group, the slice-group whole in safeguarding list
Recovery is completed.
The public office technology of those skilled in the art is in addition to technical characteristic disclosed in the specification of the present invention.
Claims (1)
1. a kind of raid card method for designing for data recovery and selfreparing, it is characterised in that comprise the following steps that：
（One）When there is catastrophe failure and needs human intervention and carry out data recovery in raid, raid systems and data recovery system
Interaction, facilitates data recovery work preferably to carry out to reach, and raid boards addition Functional Design is as follows：
A, for raid systems are when normal operation, operating system need not be interacted with disk, simply broken down
When, operating system just needs to interact with disk, and in this case, raid card sets the interface being connected with system cpu
Count into multiplexing port；
B, the multiplexing port are realized with the following method, are switched over using switch is pulled and connected, when switch is pushed a certain position, behaviour
The disk of bottom be can't see as system, raid is can only see, the disk that system can not be docked on raid card is operated, when opening
When pass pushes another location, operating system sees raid and each disk on raid card simultaneously, and disk can be passed through
Related software is operated；
C, when data recovery, existing data recovery software is run substantially under windows systems, in data recovery work
When Cheng Shi implements data recovery, it is only necessary to related software is installed, data recovery associative operation is carried out in the machine,
To protect the safety of user data as much as possible；
D, for unix is used, the equipment of linux operating systems, the data disks in storage need to recover engineer with exogenous data
Computing device be connected, data recovery for convenience, raid card can provide external such as the relevant interface of USB, and the interface is flat
When do not allow to be attached equipment, whether its foreign work to be, should be passed through when raid card is needed using pulling and connecting switch control rule
During USB interface external connection, switch off raid card and main frame all logics and be connected by pulling and connecting；
By above-mentioned measure, raid systems provide for very big side when needing to carry out data recovery once collapsing in raid
Just；
（Two）When disk occur in raid systems, raid system maintenances one have the band list of write operation, and raid systems are voluntarily
It is quick to rebuild, comprise the steps；
A, there is disk for raid systems after, in the case where HotSpare disk is not provided with, raid occurs degradation, at this moment falls
Drum will not carry out the read-write of data, and the read-write of all of data is undertaken by other disks, and start to safeguard a list, and remember
Record situation is write from fall each bands of raid that disk starts；
B, as under many circumstances, it is not that disk serious problems occurs that disk falls disk, it may be possible to which disk is doing I/O operation
Be the response that is not able to do in time so that the raid system erroneous judgements disks cisco unity malfunction；
C therefore in order to reduce investment, raid systems recover normal as early as possible, and raid card should keep carrying out wake-up behaviour to the disk that goes offline
Make, if after waking up repeatedly, disk is not still correct to be responded, and at this moment raid card should be serious as occurring in that the disk
Failure, follow-up management person should allow the disk to completely disengage from raid, and disk situation is fallen, wake up situation, dependent failure diagnosis feelings
Condition, the measure write raid card log and system journal taken, while it is former safeguard each bands of raid that disk starts
Write record situation is removed；
If d, wake-up pass through, raid card together with other member disks should be worked the disk for going offline originally, undertake data
Read-write, i.e., all of disk in the middle of the data write raid of new write, the data during going offline originally are safeguarded according to raid card
List re-starts all of disk of write by way of reading to rewrite, and thus avoids the need for adding again new building, rebuilds totally
Situation；
It is exactly to fall the disk time period specifically to have the band content in which slice-group to be changed that raid needs the list safeguarded, false
If when raid completes the write of slice-group 4, then there is disk in disk 3, and at this moment raid5 may be degraded into raid0, the handle of continuation
Data write disk 1 and disk 2, represent verification band with P, and the verification data of such as band 0 is represented with p0；The check number of band 1
According to being represented with P1；The like.After disk 3 goes offline, data write disk 1, disk 2., disk 3 is added to raid again
It is central, and data storage has been carried out together with other disks together, so namely there was only slice-group 4 between slice-group n
Slice-group needs to be recovered, therefore according to strip data structure, the data reconstruction for falling the disk time period just, thus greatly
Save greatly the time of raid reconstructions；
（Three）Quick raid process of reconstruction realizes that raid systems are to be written and read scheduling according to priority, so as to front end system and
Can continue to be normally carried out during storage interaction, concrete reconstruction procedures are as follows：
Whether a, raid rebuild to start needs to be monitored the IO situations of present raid, if the IO of raid is very numerous at this stage
It is busy, then temporarily cease reconstructions, namely the IO priority of raid reconstructions be placed on it is minimum；
B, when the IO of raid is relatively idle, raid card system is write list according to the band above safeguarded and is found out
During raid falls disk, which band is changed, and is then read out in the disk of original operational excellence in one of slice-group
Data, as original raid types are raid5, fall raid after disk and may be degraded, become raid0, thus it is remaining those
The entirely data of storage, no verification data in the middle of the band of disk；
If c, will recover whole raid5 systems, it must be determined that in the middle of a slice-group, which stripe is used for depositing school
Data are tested, this needs scanning slice-group above, show that the data structure of raid systems is left synchronization on earth, it is left asynchronous, it is right same
Step, right asynchronous, conventional or unconventional data store organisation form, finally determine in slice-group which stripe for
Storage verification data, finally determines the data structure form of the raid, will such as determine that the data storage for needing reconstruction part is tied
Structure, determines how verification band is deposited, if scanning 4 slice-groups above, can just show that this is conventional left asynchronous knot
Structure, also can start certainly the data store organisation of setting, calculate the data location mode of each slice-group according to raid；
D, define the version of data after, the data to reading just now calculate verification data, after the completion of each band
Data this completes the slice-group number safeguarded in the middle of list according to data structure form write disk determined above
According to reconstruction, also need to after the completion of reconstruction the slice-group from safeguard data list in the middle of delete；
E, according to above the step of carry out the process of reconstruction of next slice-group, the slice-group full recovery in safeguarding list
Complete.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310028448.XA CN103116474B (en) | 2013-01-25 | 2013-01-25 | A kind of raid card method for designing for data recovery and selfreparing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310028448.XA CN103116474B (en) | 2013-01-25 | 2013-01-25 | A kind of raid card method for designing for data recovery and selfreparing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103116474A CN103116474A (en) | 2013-05-22 |
| CN103116474B true CN103116474B (en) | 2017-03-29 |
Family
ID=48414866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310028448.XA Active CN103116474B (en) | 2013-01-25 | 2013-01-25 | A kind of raid card method for designing for data recovery and selfreparing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103116474B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301106A (en) * | 2017-06-28 | 2017-10-27 | 郑州云海信息技术有限公司 | The restoration methods and device of a kind of RAID system failure |
| CN108228098A (en) * | 2017-12-27 | 2018-06-29 | 创新科存储技术（深圳）有限公司 | The method that RAID0 disk groups are converted into RAID5 disk groups |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043685A (en) * | 2010-12-31 | 2011-05-04 | 成都市华为赛门铁克科技有限公司 | RAID (redundant array of independent disk) system and data recovery method thereof |
| CN102207895A (en) * | 2011-05-27 | 2011-10-05 | 杭州华三通信技术有限公司 | Data reconstruction method and device of redundant array of independent disk (RAID) |
| CN102520880A (en) * | 2011-12-01 | 2012-06-27 | 浪潮电子信息产业股份有限公司 | System raid management module design method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6640282B2 (en) * | 2000-01-25 | 2003-10-28 | Hewlett-Packard Development Company, L.P. | Hot replace power control sequence logic |
-
2013
- 2013-01-25 CN CN201310028448.XA patent/CN103116474B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043685A (en) * | 2010-12-31 | 2011-05-04 | 成都市华为赛门铁克科技有限公司 | RAID (redundant array of independent disk) system and data recovery method thereof |
| CN102207895A (en) * | 2011-05-27 | 2011-10-05 | 杭州华三通信技术有限公司 | Data reconstruction method and device of redundant array of independent disk (RAID) |
| CN102520880A (en) * | 2011-12-01 | 2012-06-27 | 浪潮电子信息产业股份有限公司 | System raid management module design method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103116474A (en) | 2013-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4606455B2 (en) | Storage management device, storage management program, and storage system | |
| US7457916B2 (en) | Storage system, management server, and method of managing application thereof | |
| CN102880522B (en) | Hardware fault-oriented method and device for correcting faults in key files of system | |
| CN110807064B (en) | Data recovery device in RAC distributed database cluster system | |
| JP2017084333A (en) | Method and system for monitoring virtual machine cluster | |
| US8738854B2 (en) | Storage apparatus and control method of storage apparatus | |
| US8667337B2 (en) | Storage apparatus and method of controlling the same | |
| JP2004038290A (en) | Information processing system and disk control method for use in same system | |
| CN103516736A (en) | Data recovery method of distributed cache system and a data recovery device of distributed cache system | |
| JP5938965B2 (en) | Node device and processing speed management method of multi-node storage system | |
| CN103744743A (en) | Heartbeat signal redundant configuration method based on RAC model of database | |
| CN104536698A (en) | Disk reconfiguration method based on RAID and related apparatus | |
| CN106155943B (en) | A kind of method and device of the power down protection of dual control storage equipment | |
| US20070101188A1 (en) | Method for establishing stable storage mechanism | |
| JP2002007077A (en) | System and method for diagnosing loop of disk array device | |
| CN108469996A (en) | A kind of system high availability method based on auto snapshot | |
| JPH07200191A (en) | Disk array device | |
| CN107918570A (en) | A kind of method that dual-active system shares arbitration disk | |
| US20070234107A1 (en) | Dynamic storage data protection | |
| CN103116474B (en) | A kind of raid card method for designing for data recovery and selfreparing | |
| CN111240903A (en) | Data recovery method and related equipment | |
| CN109117317A (en) | A kind of clustering fault restoration methods and relevant apparatus | |
| US20200097180A1 (en) | Storage system for remote replication | |
| CN102520880A (en) | System raid management module design method | |
| US8370682B2 (en) | Virtual tape system take-over-controlled by standby server computer |
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 |