CN105094696B - Based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device - Google Patents
Based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device Download PDFInfo
- Publication number
- CN105094696B CN105094696B CN201510390976.9A CN201510390976A CN105094696B CN 105094696 B CN105094696 B CN 105094696B CN 201510390976 A CN201510390976 A CN 201510390976A CN 105094696 B CN105094696 B CN 105094696B
- Authority
- CN
- China
- Prior art keywords
- subregion
- raid4
- back end
- raid1
- brd
- 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
Abstract
The present invention relates to computer field of storage, the present invention proposes to include based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device, this method：Obtain the space-consuming value of BRD in check-node, when the space-consuming value reaches given threshold, region where the BRD is added into suspend_area lists, the region is converted to the subregion of corresponding multiple back end, and send pending operation request to the subregion, after the back end receives the pending operation request, the write request of the subregion is hung up；RAID4 verification calculating, the verification data write-in logical volume equipment of generation are carried out to the data of the subregion, and is sent to the back end and remaps request, the BRD of the subregion is remapped to ARP by the back end, to complete data conversion.The present invention reduces the probability that RAID1 interacts in a short time to the process that RAID4 is changed with I/O operation, it is ensured that the asynchronization degree of flow path switch and write operation.
Description
Technical field
The present invention relates to computer field of storage, more particularly to based on RAID1 and RAID4 mixed structure transfer process data
Reliability Assurance device.
Background technology
RAID (raid-array) technology is a kind of storage side for providing enhancing redundancy, capacity and storage performance
Method, there are stronger manageability, reliabilty and availability.By redundant computation, RAID technique can meet that reliability will
The capacity overhead of system is reduced on the premise of asking, the research that RAID technique is applied to network store system experienced from centralization
Distributed AC servo system is controlled, from single RAID mode to the evolution of mixing RAID mode, RAID1 technologies have highly reliable
Property, RAID1 mirror images enable write operation to have two parts of data, even if one of node failure, copy also can guarantee that portion just
True data, RAID4 redundancies take less redundant space storage check information, can tolerate any single node failure,
And the data lost can be recovered by the data and check information of other nodes, system reliability is relatively good.
Need to consider influence of the complex network environment to performance in large scale network storage system, so some storage systems
System is using mixing RAID mode.Most recently used data are placed in the high performance hard disk stored with RAID1 by AutoRAID, will
Less conventional data are placed on in the hard disk of the economical and efficient of RAID5 storages.DPGADR has used similar to AutoRAID
Structure, but distributed network storage environment is more suitable for, systematic function is improved using the method replicated and delay check block generates.
The Chinese patent of Patent No. 201410033455.3 ---《RAID1 and RAID4 mixed structures network store system and method》
The method that the redundant management node in rear end carries out concentrating Redundancy Management to back end is provided, by redundant management node from number
The rear end of storage device is moved on to according to the front end of passage so that read-write requests can directly access memory node, reduce redundancy meter
Calculate the influence to system write performance.
RAID1 separates storage with RAID5 data in AutoRAID, in a network environment by bulk data from RAID1
Move on RAID5, huge network bandwidth and Disk bandwidth can be brought to consume, be not suitable for using under distributed environment.And
RAID5 parts are degraded mode storages in DPGADR, and the readwrite performance of cold data is poor.Patent No. 201410033455.3
Chinese patent ---《RAID1 and RAID4 mixed structures network store system and method》The rear end redundancy centralized management side of proposition
Formula solves the problems, such as centralized Redundancy Management mode performance bottleneck, but data synchronization process and writes I/O operation and can influence each other,
RAID1 data conversions can not be ensured into the uniformity of data in RAID4 data procedures.
Following limitation is also had based on above-mentioned analysis mixing RAID structure Network storage technology at present：Data conversion process
I/O operation is write in influence, can not ensure the uniformity of data conversion.
For considerations above, the present invention is in Chinese patent《RAID1 and RAID4 mixed structures network store system and method》
On the basis of (system architecture as shown 1 and diagram 2), propose a kind of transfer process data based on RAID1 and RAID4 mixed structures
Uniformity ensuring method.
The content of the invention
In view of the shortcomings of the prior art, the present invention proposes that one kind is based on RAID1 and RAID4 mixed structure transfer process data
Reliability Assurance device.
The present invention proposes that one kind is based on RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods, wraps
Include：
Step is hung up, the space-consuming value of BRD in check-node is obtained, when the space-consuming value reaches given threshold
When, the region where the BRD is added into suspend_area lists, the region is converted into corresponding multiple back end
Subregion, and send pending operation request to the subregion, after the back end receives pending operation request, hang
Play the write request of the subregion；
Switch process, RAID4 verification calculating, the verification data write-in logical volume of generation are carried out to the data of the subregion
Equipment, and sent to the back end and remap request, the BRD of the subregion is remapped to by the back end
ARP, to complete data conversion.
It is described based on RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods, the switch process
Including：RAID4 verifications are carried out to the subregion of successful execution pending operation to calculate, and to the son of the successful execution pending operation
Back end belonging to region, which is sent, remaps request.
It is described based on RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods, the hang-up step
Also include：The pending operation of subregion is sent to corresponding back end by Multi-task Concurrency.
It is described based on RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods, the hang-up step
Also include：If now the subregion has write request and is carrying out, after waiting all write requests to terminate, into the conversion
Step.
Described is walked based on RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods, in addition to reset
Suddenly：After the back end completes remapping operation, the region where the BRD is moved from the suspend_area chained lists
Remove；The write request for the subregion being suspended in the back end is issued.
The present invention also proposes a kind of based on RAID1 and RAID4 mixed structure transfer processes data reliability guarantee device, bag
Include：
Suspension module, for obtaining the space-consuming value of BRD in check-node, when the space-consuming value reaches setting threshold
During value, the region where the BRD is added into suspend_area lists, the region is converted into corresponding multiple data sections
The subregion of point, and pending operation request is sent to the subregion, after the back end receives the pending operation request,
Hang up the write request of the subregion；
Modular converter, calculated for carrying out RAID4 verifications to the data of the subregion, the verification data write-in of generation is patrolled
Volume volume equipment, and sent to the back end and remap request, the back end is by the BRD replays of the subregion
ARP is mapped to, to complete data conversion.
Described ensures device, the suspension module based on RAID1 and RAID4 mixed structure transfer processes data reliability
Also include：The pending operation of subregion is sent to corresponding back end by Multi-task Concurrency.
Described ensures device, the modular converter based on RAID1 and RAID4 mixed structure transfer processes data reliability
Including：RAID4 verifications are carried out to the subregion of successful execution pending operation to calculate, and to the son of the successful execution pending operation
Back end belonging to region, which is sent, remaps request.
Described ensures device, the suspension module based on RAID1 and RAID4 mixed structure transfer processes data reliability
Also include：If now the subregion has write request and is carrying out, after waiting all write requests to terminate, the conversion is performed
Module.
Described ensures device based on RAID1 and RAID4 mixed structure transfer processes data reliability, in addition to resets mould
Block, after completing remapping operation for the back end, by the region where the BRD from the suspend_area chained lists
Middle removal；The write request for the subregion being suspended in the back end is issued.
Invented more than, the advantage of the invention is that：
The present invention reduces the probability that RAID1 interacts in a short time to the process that RAID4 is changed with I/O operation, really
Protect flow path switch and write the asynchronization degree of I/O operation；
On the premise of not influenceing to write I/O performances, the data consistency of R1 to R4 conversions ensure that.
Brief description of the drawings
Fig. 1 is the redundancy group schematic diagram of RAID1 and RAID4 mixed structures；
Fig. 2 is the system construction drawing of mixing RAID in redundancy group；
Fig. 3 is back end suspend operating process schematic diagrams；
Fig. 4 is back end resume operating process schematic diagrams；
Fig. 5 is that check-node sends suspend and resume operating process schematic diagrams；
Fig. 6 is that back end write request issues querying flow schematic diagram；
Fig. 7 is flow path switch suspend phase flow schematic diagrames；
Fig. 8 is that flow path switch changes phase flow schematic diagram；
Fig. 9 is flow path switch resume phase flow schematic diagrames.
Embodiment
It is the specific steps of the inventive method below, it is as follows：
Step is hung up, the space-consuming value of BRD in check-node is obtained, when the space-consuming value reaches given threshold
When, the region where the BRD is added into suspend_area lists, the region is converted into corresponding multiple back end
Subregion, and send pending operation request to the subregion, after the back end receives pending operation request, hang
Play the write request of the subregion；
Switch process, RAID4 verification calculating, the verification data write-in logical volume of generation are carried out to the data of the subregion
Equipment, and sent to the back end and remap request, the BRD of the subregion is remapped to by the back end
ARP, to complete data conversion.
The switch process includes：RAID4 verifications are carried out to the subregion of successful execution pending operation to calculate, and to described
Back end belonging to the subregion of successful execution pending operation, which is sent, remaps request.
The hang-up step also includes：The hang-up that subregion is sent to corresponding back end by Multi-task Concurrency is grasped
Make.
The hang-up step also includes：If now the subregion has write request and is carrying out, wait all write please
After asking end, into the switch process.
Also include reset process：After the back end completes remapping operation, by the region where the BRD from described
Removed in suspend_area chained lists；The write request for the subregion being suspended in the back end is issued.
Apparatus of the present invention are included with lower module, as follows：
Suspension module, for obtaining the space-consuming value of BRD in check-node, when the space-consuming value reaches setting threshold
During value, the region where the BRD is added into suspend_area lists, the region is converted into corresponding multiple data sections
The subregion of point, and pending operation request is sent to the subregion, after the back end receives the pending operation request,
Hang up the write request of the subregion；
Modular converter, calculated for carrying out RAID4 verifications to the data of the subregion, the verification data write-in of generation is patrolled
Volume volume equipment, and sent to the back end and remap request, the back end is by the BRD replays of the subregion
ARP is mapped to, to complete data conversion.
The suspension module also includes：The hang-up that subregion is sent to corresponding back end by Multi-task Concurrency is grasped
Make.
The modular converter includes：RAID4 verifications are carried out to the subregion of successful execution pending operation to calculate, and to described
Back end belonging to the subregion of successful execution pending operation, which is sent, remaps request.
The suspension module also includes：If now the subregion has write request and is carrying out, wait all write please
After asking end, into the switch process.
Reseting module, after completing remapping operation for the back end, by the region where the BRD from described
Removed in suspend_area chained lists；The write request for the subregion being suspended in the back end is issued.
The specific embodiment of the present invention is given below, and detailed description is made that to the present invention with reference to accompanying drawing.Present invention bag
Include two parts of system conversion dependency structure and flow path switch.
System changes dependency structure
The composition of RAID1 and RAID4 mixed structures is described first.As shown shown in the dotted line frame in 1 intermediate layer, the present invention
RAID1 and RAID4 mixed structures the redundancy group that is made up of one group of data structure node and a check-node of unit.Figure
Show 2 for the system architecture in a redundancy group, the back end in redundancy group is single by data transmit-receive program, buffer unit, mapping
The logical volume of member and actual storage data composition；Check-node in redundancy group is by data transmit-receive program, buffer unit, mapping
Unit, Cache modules (cache module), Suspend modules, be responsible for group in RAID calculate redundant computation unit and storage
The logical volume composition of check information.
Now part main in system is explained and illustrated：Suspend modules (suspension module)：At this module
In check-node, a suspend_area list (hang-up zone list) is recorded；If the module adds a region
Suspend_area lists, then Suspend modules can pass through MP (Multi Path, multipath) notify corresponding region where number
The write request in this region is hung up according to node；Until the region is removed list by Suspend modules, write request just normally issues (number
Querying flow is issued according to node write request as shown 6).
Map unit：Map unit includes BRD and ARD equipment, and the data of mapping are respectively Mirror (mirror image) and R4 numbers
According to.
BRD：Before Raid Device, mirroring device.Current data is carry, while is also that will carry out RAID to turn
Change the equipment of the Prev-RAID consistent datas of data；That is correspond to not change into R4 also in the logical volume for the mapping relations that BRD is safeguarded
R1 data.
ARD：After Raid Device, calibration equipment.Carry the Post-RAID for the data for having completed RAID conversions
The equipment of consistent data；That is it correspond to change into R4 data in the logical volume for the mapping relations that ARD is safeguarded.
It is below the flow path switch of the present invention, it is as follows：
Flow path switch can be divided into three phases, be respectively：Suspend stages, conversion stage and Resume stages.
The Suspend stages (hanging up the stage) (as shown 7)：
Cache modules in check-node find the BRD space-consumings of check-node to reach a given threshold that (threshold value is
Consider the factors such as system logic volume size, cache size decision) more than when, Cache modules notice Suspend modules should
Region adds suspend_area lists, carries out suspend operations；
After Suspend modules receive suspend operations, the region is converted to the sub-district of corresponding multiple back end
Domain, by MP (Multi Path, multipath, refer to from suspend module multipaths and be sent to each node) concomitantly to corresponding number
The suspend that subregion is sent according to node is operated；
After back end receives suspend operations, the write request of follow-up corresponding region (subregion) is hung up, if now
The region has write request to be carrying out, then after waiting all write requests to terminate, into the conversion stage；
The conversion stage (as shown 8)：
Cache modules carry out RAID4 verifications to the data for performing the successful regions of suspend and calculated；
After verification calculates, the verification data write-in logical volume equipment of generation, and by WR, (Write Remap, will
Data are remapping in ARD in BRD) notify each back end to carry out remapping operation to the data area for participating in calculating；
After back end receives the remapping operation that WR is sent, the data of corresponding region are remapped to ARP from BRP, institute
After having back end to complete remapping operation, the conversion stage terminates；
The Resume stages (reseting stage) (as shown 9)：
After all back end complete remapping operations, Cache modules notify Suspend modules by the region from
Removed in suspend_area chained lists；
Suspend modules notify each back end to carry out resume behaviour to suspend_area corresponding to original by MP
Make；
After completing resume, the write request for the corresponding region hung up in back end is issued, flow path switch terminates.
Claims (10)
1. one kind is based on RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods, it is characterised in that including：
Step is hung up, the space-consuming value of mirroring device BRD in check-node is obtained, when the space-consuming value reaches setting threshold
During value, the region where the mirroring device BRD is added and hangs up zone list suspend_area, the region is converted to
The subregion of corresponding multiple back end, and pending operation request is sent to the subregion, the back end receives institute
After stating pending operation request, the write request of the subregion is hung up；
Switch process, RAID4 verification calculating is carried out to the data of the subregion, the verification data write-in logical volume of generation is set
It is standby, and sent to the back end and remap request, the back end is heavy by the mirroring device BRD of the subregion
Calibration equipment ARP is mapped to, to complete data conversion.
2. RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods are based on as claimed in claim 1, its
It is characterised by, the switch process includes：RAID4 verifications are carried out to the subregion of successful execution pending operation to calculate, and to institute
State the transmission of the back end belonging to the subregion of successful execution pending operation and remap request.
3. RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods are based on as claimed in claim 1, its
It is characterised by, the hang-up step also includes：The hang-up that subregion is sent to corresponding back end by Multi-task Concurrency is grasped
Make.
4. RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods are based on as claimed in claim 1, its
It is characterised by, the hang-up step also includes：If now the subregion has write request and is carrying out, wait all write please
After asking end, into the switch process.
5. RAID1 and RAID4 mixed structure transfer process data reliability ensuring methods are based on as claimed in claim 1, its
It is characterised by, in addition to reset process：After the back end completes remapping operation, by where the mirroring device BRD
Region removes from the suspend_area lists；The write request for the subregion being suspended in the back end is entered
Row issues.
6. one kind ensures device based on RAID1 and RAID4 mixed structure transfer processes data reliability, it is characterised in that including：
Suspension module, for obtaining the space-consuming value of mirroring device BRD in check-node, set when the space-consuming value reaches
When determining threshold value, the region where the mirroring device BRD is added and hangs up zone list suspend_area, the region is turned
The subregion of multiple back end corresponding to being changed to, and pending operation request is sent to the subregion, the data section is checked and accepted
After being asked to the pending operation, the write request of the subregion is hung up；
Modular converter, calculated for carrying out RAID4 verifications to the data of the subregion, the verification data write-in logical volume of generation
Equipment, and sent to the back end and remap request, the back end is by the mirroring device BRD of the subregion
Calibration equipment ARP is remapped to, to complete data conversion.
7. device is ensured based on RAID1 and RAID4 mixed structure transfer processes data reliability as claimed in claim 6, its
It is characterised by, the suspension module also includes：The hang-up that subregion is sent to corresponding back end by Multi-task Concurrency is grasped
Make.
8. device is ensured based on RAID1 and RAID4 mixed structure transfer processes data reliability as claimed in claim 6, its
It is characterised by, the modular converter includes：RAID4 verifications are carried out to the subregion of successful execution pending operation to calculate, and to institute
State the transmission of the back end belonging to the subregion of successful execution pending operation and remap request.
9. device is ensured based on RAID1 and RAID4 mixed structure transfer processes data reliability as claimed in claim 6, its
It is characterised by, the suspension module also includes：If now the subregion has write request and is carrying out, wait all write please
After asking end, the modular converter is performed.
10. device is ensured based on RAID1 and RAID4 mixed structure transfer processes data reliability as claimed in claim 6, its
It is characterised by, in addition to reseting module, after completing remapping operation for the back end, by the mirroring device BRD institutes
Region removed from the suspend_area lists；Please by writing for the subregion being suspended in the back end
Ask and issued.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510390976.9A CN105094696B (en) | 2015-07-06 | 2015-07-06 | Based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510390976.9A CN105094696B (en) | 2015-07-06 | 2015-07-06 | Based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105094696A CN105094696A (en) | 2015-11-25 |
| CN105094696B true CN105094696B (en) | 2018-02-06 |
Family
ID=54575256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510390976.9A Active CN105094696B (en) | 2015-07-06 | 2015-07-06 | Based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105094696B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843560B (en) * | 2016-04-08 | 2018-08-10 | 中国科学院计算技术研究所 | A kind of method and system for safeguarding the soft Raid6 consistency of master-slave mode dual control |
| CN106027638B (en) * | 2016-05-18 | 2019-04-12 | 华中科技大学 | A kind of hadoop data distributing method based on hybrid coding |
| CN109032513B (en) * | 2018-07-16 | 2020-08-25 | 山东大学 | RAID (redundant array of independent disks) architecture based on SSD (solid State disk) and HDD (hard disk drive) and backup and reconstruction methods thereof |
| US10691353B1 (en) | 2018-11-30 | 2020-06-23 | International Business Machines Corporation | Checking of data difference for writes performed via a bus interface to a dual-server storage controller |
| CN113420341B (en) * | 2021-06-11 | 2023-08-25 | 联芸科技(杭州)股份有限公司 | Data protection method, data protection equipment and computer system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488432A (en) * | 2013-09-16 | 2014-01-01 | 哈尔滨工程大学 | Hybrid disk array, deferred write verification method for hybrid disk array, and data recovery method for hybrid disk array |
| CN103761058A (en) * | 2014-01-23 | 2014-04-30 | 天津中科蓝鲸信息技术有限公司 | RAID1 and RAID4 hybrid structure network storage system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9032146B2 (en) * | 2010-11-30 | 2015-05-12 | Lenovo Enterprise Solutions (Singapore) Pte. Ltd. | Dynamic use of raid levels responsive to workload requirements |
-
2015
- 2015-07-06 CN CN201510390976.9A patent/CN105094696B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488432A (en) * | 2013-09-16 | 2014-01-01 | 哈尔滨工程大学 | Hybrid disk array, deferred write verification method for hybrid disk array, and data recovery method for hybrid disk array |
| CN103761058A (en) * | 2014-01-23 | 2014-04-30 | 天津中科蓝鲸信息技术有限公司 | RAID1 and RAID4 hybrid structure network storage system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105094696A (en) | 2015-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105094696B (en) | Based on RAID1 and RAID4 mixed structures transfer process data reliability ensuring method and device | |
| US8639969B2 (en) | Fast data recovery from HDD failure | |
| US9378093B2 (en) | Controlling data storage in an array of storage devices | |
| US8898385B2 (en) | Methods and structure for load balancing of background tasks between storage controllers in a clustered storage environment | |
| US8356126B2 (en) | Command-coalescing RAID controller | |
| EP0768599B1 (en) | On-line disk array reconfiguration | |
| US10896089B2 (en) | System level data-loss protection using storage device local buffers | |
| JP4817783B2 (en) | RAID system and rebuild / copyback processing method thereof | |
| TWI639118B (en) | Scheduling and management of compute tasks with different execution priority levels | |
| CN103761058B (en) | RAID1 and RAID4 mixed structure network store system and method | |
| CN104407933B (en) | A kind of backup method and device of data | |
| US8775733B2 (en) | Distribution design for fast raid rebuild architecture based on load to limit number of redundant storage devices | |
| CN104503923B (en) | A kind of asymmetric disk array cache dispatching method | |
| US9836223B2 (en) | Changing storage volume ownership using cache memory | |
| US20080091916A1 (en) | Methods for data capacity expansion and data storage systems | |
| KR19980021384A (en) | Storage system for improving data input / output performance and data recovery information cache implementation method accordingly | |
| WO2021139166A1 (en) | Error page identification method based on three-dimensional flash storage structure | |
| JP2013196274A (en) | Node device for multi-node storage system and processing speed management method | |
| CN107729536A (en) | A kind of date storage method and device | |
| JP2003029934A (en) | Storage controller and control method therefor | |
| CN112379825A (en) | Distributed data storage method and device based on data feature sub-pools | |
| US20200341873A1 (en) | Data access method, apparatus and computer program product | |
| KR20240025451A (en) | Method and device for data caching | |
| US20120304016A1 (en) | Storage control device, storage device, and diagnostic method | |
| US20210326052A1 (en) | System and Method for Variable Sparing in RAID Groups Based on Drive Failure Probability |
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 |