CN102622286B - A kind of raid-array bitmap backup method and system - Google Patents
A kind of raid-array bitmap backup method and system Download PDFInfo
- Publication number
- CN102622286B CN102622286B CN201210043802.1A CN201210043802A CN102622286B CN 102622286 B CN102622286 B CN 102622286B CN 201210043802 A CN201210043802 A CN 201210043802A CN 102622286 B CN102622286 B CN 102622286B
- Authority
- CN
- China
- Prior art keywords
- control end
- raid
- bit pattern
- message bit
- controller
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000004044 response Effects 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000005538 encapsulation Methods 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 description 7
- 230000001360 synchronised effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000009977 dual effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000976 ink Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
Abstract
The invention discloses a kind of RAID bitmap backup method and system, relate to computer system and field of storage.Method disclosed by the invention comprises: when a certain region first time receives write request, main control end upgrades local bitmap, RAID information corresponding for this write request and backup command is sent to from control end; Receive described RAID information and backup command from control termination, preserve the RAID information obtained, define the memory headroom enough backing up bitmap according to obtained backup command, then to the response message of main control end feedback to described backup command; Main control end receives response message, is sent to by message bit pattern to back up from control end; Message bit pattern is received, under received message bit pattern being saved in corresponding RAID information from control termination.The invention also discloses a kind of RAID bitmap backup system, comprise master controller and from controller.Technical scheme improves the write performance of RAID greatly.
Description
Technical field
The present invention relates to computer system and field of storage, be specifically related to a kind of RAID (RedundantArraysofInexpensiveDisks, raid-array) bitmap backup method and system.
Background technology
Exist in the magnetic array 1 system of data redundancy at RAID5 etc., the data of the integrity demands redundancy of data will ensure consistent with the information of raw data.The write operation of magnetic battle array is a process, coils unsuccessfully, the abnormal conditions such as system power failure if occur in this process such as to write, will cause redundant data and raw data inconsistent.So successfully write data, whole band should be consistent, but write does not have successfully (or incomplete), and strip data is likely inconsistent.After system re-powers, if do not have recording mechanism, it can only suppose that all data all may be inconsistent, starts anew to carry out synchronize fully.This global data synchronization can cause system boot process very long.
If there is NVRAM (Nonvolatile memory), to a data block write operation at first, in NVRAM, preserve writing position information, after write operation terminates, in NVRAM, delete this information.Like this, when system boot, from NARAM, read the writing position information of preservation, these positional informations have recorded the data block of unsuccessful write, and system only needs to carry out synchronously these data blocks, and need not synchronous magnetic battle array total data.The magnetic battle array that we use software RAID to build at present, this has just drawn bitmap (bitmap) file, be appreciated that the effect of bitmap file is equal to the effect of above-mentioned magnetic battle array NVRAM, after power-down rebooting, can synchronizing thread be started, set can be judged whether by bitmap file, if there is no set, just illustrate that whole region is in that moment of power down, does not exist the data write, it is just passable directly to skip this region.
Be that, in time carrying out write operation, corresponding bitmap bits can be set to 1 by system at present to the method for bitmap file backup, synchronously write reserved area in all disks of magnetic battle array and go.Only have after the bitmap file Flushing success in disk, just start a normal data IO write operation.
Due to each band corresponding bitmap all will be waited first to write back disk after could be real carry out writing process, and the performance of disk and internal memory etc. are too wide in the gap, therefore very large to system performance loss.
Summary of the invention
Technical matters to be solved by this invention is, provides a kind of RAID bitmap backup method and system, to improve the write performance of RAID.
In order to solve the problems of the technologies described above, the invention discloses a kind of raid-array (RAID) bitmap backup method, comprising:
When a certain region first time receives write request, main control end upgrades local bitmap, RAID information corresponding for this write request and backup command is sent to from control end;
Describedly receive described RAID information and backup command from control termination, preserve the RAID information that obtains, define the memory headroom enough backing up bitmap according to obtained backup command, then feed back the response message to described backup command to described main control end;
Described main control end receives described response message, is sent to by message bit pattern to back up described from control end;
Described from control termination receipts institute bitmap information, under received message bit pattern being saved in corresponding RAID information.
Preferably, said method also comprises:
When creating RAID, main control end creates the bitmap that each RAID is corresponding.
Preferably, in said method, described main control end and from control end between send data time, according to main control end and from control end between network communication protocol become packet to re-send to opposite end the data encapsulation that will send.
Preferably, said method also comprises: arrange backup cycle, when backup cycle arrives, message bit pattern corresponding for the different RAID information of this locality sends to described from control end by described main control end, described from received message bit pattern is saved in corresponding RAID information by control end.
Preferably, said method also comprises: when described main control end lost efficacy, described RAID of restarting main control end from control end;
After RAID information in described main control end is restarted, if find, described end from control preserves message bit pattern, then this message bit pattern is write back disk, from control end, message bit pattern is not preserved if find, then from disk, read message bit pattern from control end, described from the message bit pattern of reading to be saved in corresponding RAID by control end.
Preferably, in said method, when described main control end does not receive the described response message from the transmission of control end in setting-up time, the bitmap of this locality is write back disk.
The invention also discloses a kind of raid-array (RAID) bitmap backup system, comprise master controller and from controller, wherein:
Described master controller, when a certain region first time receives write request, upgrade local bitmap, RAID information corresponding for this write request and backup command are sent to described from controller, and when receiving the described response message from controller feedback, message bit pattern to back up is sent to described from controller;
Described from control end, receive the packet that described master controller sends, therefrom obtain RAID information and backup command, preserve the RAID information obtained, the memory headroom enough backing up bitmap is defined according to obtained backup command, and to the response message of described master controller feedback to described backup command, and under the message bit pattern that described master controller sends being saved in corresponding RAID information.
Preferably, in said system, described master controller and from when sending data between controller, becomes packet to re-send to opposite end the data encapsulation that will send according to master controller with from the network communication protocol between controller.
Preferably, in said system, described master controller, also periodically sends to described from controller according to the backup cycle arranged by message bit pattern corresponding for the different RAID information of this locality;
Described from controller, the message bit pattern that periodic receipt master controller sends, and under received message bit pattern being saved in corresponding RAID information.
Preferably, in said system, when described master controller lost efficacy, described RAID of restarting from controller main control end;
After RAID information on described master controller is restarted, if preserve message bit pattern from controller described in finding, then this message bit pattern is write back disk, from control end, message bit pattern is not preserved if find, then from disk, read message bit pattern from controller, describedly the message bit pattern of reading to be saved in corresponding RAID from controller.
Technical scheme improves the write performance of RAID greatly.Especially for dividing more accurately, technical scheme not only promotes very large in random write, also has greatly improved, thus more have the meaning of practical application for sequential write.
Accompanying drawing explanation
Fig. 1 is the network architecture schematic diagram realizing RAID bitmap backup in the present embodiment;
Fig. 2 is the process flow diagram carrying out bitmap backup in the present embodiment;
Fig. 3 is the process flow diagram recovering in the present embodiment to take over;
Fig. 4 is the synchronous decision flow chart of the present embodiment Bitmap;
Fig. 5 (a) is for adopting the test result of technical scheme and prior art when carrying out sequential write for 1 bitmap page;
Fig. 5 (b) is for adopting the test result of technical scheme and prior art when carrying out random write for 1 bitmap page;
Fig. 6 (a) is for adopting the test result of technical scheme and prior art when carrying out sequential write for 15 bitmap pages;
Fig. 6 (b) is for adopting the test result of technical scheme and prior art when carrying out random write for 15 bitmap pages.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, hereafter will be described in further detail technical solution of the present invention by reference to the accompanying drawings.It should be noted that, when not conflicting, the feature in the embodiment of the application and embodiment can combine arbitrarily mutually.
Embodiment 1
The present embodiment provides a kind of RAID bitmap backup method, and it software PLC basis realizes in linux kernel based on dual control storage system.Wherein, inventor proposes when creating RAID, bitmap is created in main control end, bitmap can be backuped to simultaneously from control end according to the operation of write request subsequently, and main control end and between control end with transmitted data on network, compare the operation that existing bitmap writes disk like this, substantially increase bitmap backup rate, thus improve the write performance of RAID.Particularly, the realization of the method depends on the network architecture shown in Fig. 1.Wherein, client device is the main control end realizing the method, and this client device has a processing threads, and a communication sends thread and accepts thread with communicating.Server then for realize the method from control end, this server has multiple processing threads, comprises a communication and sends thread and communicate with one and accept thread.Introduce the implementation procedure of the method below in detail.
As shown in Figure 2, backup procedure comprises the steps:
1) when there being write request, if the first time in a region write, wake main control end back-up processing thread (master control is client) up, process number order, calling communication sends thread, namely sends RAID information (if RAID information spinner RAID sequence number, if there is multiple RAID in system, can be belong to which RAID by sequence number determination bitmap) and backup command to from control end
Wherein, main control end and from control hold between send data time what adopt is Internet Transmission, therefore need that the data that will send are packaged into packet according to network communication protocol and send to opposite end again.In addition, consider that Internet Transmission may exist time-out, therefore when network timeout, need bitmap to be write back disk to improve the reliability of bitmap backup.
2) accept thread from control end (server end) calling communication, accept the packet that main control end sends, according to packet, call processing threads, preserving RAID information, is which RAID in system with what determine to back up.
3) from control end, define the memory headroom enough backing up bitmap according to backup command, send response message corresponding to this backup command to main control end.
In this step, define according to backup command the memory headroom enough backing up bitmap and namely refer to, if first time backs up this bitmap, inquiry system internal memory, for later bitmap backup storage allocation, if not first time, bitmap is backed up, then show that this bitmap is assigned internal memory.
4) main control end accepts after thread receives response message, to wake main control end back-up processing thread up, carry out backup bitmap operation, and then wakes communication up and send thread, sends message bit pattern to back up to from control end.
With in like manner mentioned above, main control end and from control hold between send data time what adopt is Internet Transmission, therefore message bit pattern to back up is packaged into packet according to network communication protocol by main control end sends to from control end again.In addition, consider that Internet Transmission may exist time-out, therefore when network timeout (as all do not received response message in setting-up time), need bitmap to be write back disk to improve the reliability of bitmap backup.
5) accept thread from control end calling communication, receive packet, then call processing threads, according to step 2) the RAID information that receives, under the message bit pattern in received packet is kept at corresponding RAID.
6), after completing backup, Backup end response is sent from control end to main control end.
7) processing threads of main control end receives Backup end order, just completes the process of whole backup.
After completing backup, be exactly next the operational processes to band.Be articulated to below handle_list by the band queue below bitmap_list and go, realize the normal write operation of write request strip data.
Above-mentioned backup procedure is mainly to backed up in synchronization operation when bitmap set, and applicant is on the basis of backed up in synchronization, also periodic backups is proposed, this mainly considers the situation of bitmap clear 0, therefore, because clear 0 operation is not very urgent, so do not need synchronous, function class is similar to bitmap_daemon_work ().
In addition, in above-mentioned backup procedure, main control end can lose efficacy (as power-off or break down), therefore applicant proposes main control end when losing efficacy, and can hold the RAID of restarting in main control end, then carry out recovery adapter flow operations by from control, specifically as shown in Figure 3, comprise the steps:
301) when RAID starts, in function md_do_run, can inquire about and whether hold from control the bitmap whether having backup, if had, just perform 302) operation, if do not had, leap to the 303rd) step.
302) from control end, bitmap is write back disk.
303) read bitmap from controller from disk, in the internal memory from control end, create bitmap structure.
After aforesaid operations terminates, namely become main control end from control end, before opposite terminal controller starts, there is write request in this stage, is all write disk to get on to the operation of bitmap; After opposite end starts successfully, so just the mode that disk makes into back up to opposite end is write in stopping.
Just carry out when being noted that adapter is and only has a control end to stop.If when having at least a control end to be normal stopping in two control ends, so will call do_md_stop () function, inside this function, bitmap_flush () can carry out disk write operation to bitmap, after restarting, the information of disk bitmap record is exactly correct, does not now need to do what special processing.If but two all improper stoppings of control end, be just equivalent to do not have bitmap to back up this time, so to bitmap initialization, synchronize fully operation will be carried out.As Fig. 4, on codes implement, this situation will judge three conditions: judge whether normal stopping; Judge whether to enable backup (forbidding backup, write disk exactly, this time does not also need special processing); Judge whether the bitmap of backup.Being improper stopping when meeting dual controller, when enabling bitmap backup but there is no bitmap, with regard to initialization bitmap, making array carry out synchronize fully.
In addition, when finding to lose efficacy in opposite end, can backup being forbidden, namely stopping, to opposite end backup, not deleting as backing up the Backup Data retained from end.This function can Lookup protocol, and user area also can be allowed to pass on forbidding backup command by proc or ioctl to rdbk module.
Under double-control system default situations, be enable backup.Be exactly that a controller stops in addition, after being resumed, automatically can enable backup.This function can Lookup protocol, user area also can be allowed to be passed on to module by proc or ioctl and enable backup command.
Set up a RAID5 below, with Iometer, contrast test is carried out to mode in this paper and the mode originally writing disk, wherein, adopt non-covered WriteMode.
A position in bitmap is the state representing a region, if this region is less, just illustrate that this bitmap is more accurate, so synchronizing process just can skip more region, decreases synchronous process.So a bitmap page is the division of comparing coarseness, if think to show more accurately whether synchronous state, just needs thinner division, also just need the more bitmap page.
Test is first for a bitmap page, Fig. 5 (a) is depicted as sequential write test result, the backup scenario peak performance that the application proposes can reach 617M/s, and the existing mode writing disk the highest be also 617M/s, the mode just originally writing disk slightly declines in some data block, but both performances are more or less the same; Fig. 5 (b) is depicted as the result of random write, as seen from the figure, two kinds of modes differ obvious, the backup scenario peak performance that the application proposes can reach 141M/s, and the existing mode writing disk the highest be 89M/s, so for a bitmap page, the backup scenario that the application proposes has greatly improved in random write performance.
But, because a page is the division of a very coarseness, when reality uses, need thinner differentiation, otherwise restart just may do too many there is no need synchronous.Test with thinner division (15 pages) below, it is the sequential write test result of two kinds of modes shown in Fig. 6 (a), it is the random write test result of two kinds of modes shown in Fig. 6 (b), the existing mode writing disk, the highest 460M/s of sequential write, the highest 60M/s of random write; The new the highest 602M/s of backup mode sequential write, the highest 139M/s of random write.Visible, compared with a page, when 15 pages, the backup scenario of the application is relatively existing writes disk system, and sequential write and random write all have greatly improved.Its reason is that thinner division makes the operation of system to bitmap more frequent, originally the mode writing disk needs more to write with a brush dipped in Chinese ink disk, and the bottleneck that disk stores exactly, the backup scenario of the application eliminates this bottleneck, so its performance remains unchanged substantially.
Embodiment 2
The present embodiment introduces a kind of raid-array (RAID) bitmap backup system, and this system at least comprises master controller (also can claim not client) and from controller (also can be described as server), wherein:
Master controller, when a certain region first time receives write request, upgrade local bitmap, RAID information corresponding for this write request and backup command are sent to described from controller, and when receiving the described response message from controller feedback, message bit pattern to back up is sent to described from controller;
From control end, receive the packet that described master controller sends, therefrom obtain RAID information and backup command, preserve the RAID information obtained, the memory headroom enough backing up bitmap is defined according to obtained backup command, and to the response message of described master controller feedback to described backup command, and under the message bit pattern that described master controller sends being saved in corresponding RAID information.
Above-mentioned master controller and from when sending data between controller, becomes packet to re-send to opposite end the data encapsulation that will send according to master controller with from the network communication protocol between controller.
The backup carried out due to above-mentioned master controller mainly operates backed up in synchronization when bitmap set, therefore preferred version proposes, master controller, according to the backup cycle arranged, message bit pattern corresponding for the different RAID information of this locality periodically can also be sent to from controller, now, from controller, the message bit pattern that periodic receipt master controller sends, and under received message bit pattern being saved in corresponding RAID information.
In practical application, also can there is situation about losing efficacy in above-mentioned master controller, at this moment, and can by the RAID of restarting from controller in main control end.After RAID information on master controller is restarted, if preserve message bit pattern from controller described in finding, then this message bit pattern is write back disk, from control end, message bit pattern is not preserved if find, then from disk, read message bit pattern from controller, describedly the message bit pattern of reading to be saved in corresponding RAID from controller.Particularly, the processes such as the synchronize fully of the recovery adapter flow process after master controller lost efficacy and the improper stopping of dual controller all see the description of embodiment 1, can not repeat them here.
The all or part of step that one of ordinary skill in the art will appreciate that in said method is carried out instruction related hardware by program and is completed, and described program can be stored in computer-readable recording medium, as ROM (read-only memory), disk or CD etc.Alternatively, all or part of step of above-described embodiment also can use one or more integrated circuit to realize.Correspondingly, each module/unit in above-described embodiment can adopt the form of hardware to realize, and the form of software function module also can be adopted to realize.The application is not restricted to the combination of the hardware and software of any particular form.
As can be seen from above-described embodiment, existing writes disk system, due to each band corresponding bitmap all will be waited first to write back disk after could be real carry out writing process, and the performance of disk is the bottleneck stored, very large to performance loss, so technical scheme gets around disk, by network, bitmap is backuped to another controller from a controller, find that this bitmap backup mode makes write performance be greatly improved through test.Especially for dividing more accurately, technical scheme not only promotes very large in random write, also has greatly improved, thus more have the meaning of practical application for sequential write.
The above, be only preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.Within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a raid-array RAID bitmap backup method, is characterized in that, the method comprises:
When a certain region first time receives write request, main control end upgrades local bitmap, RAID information corresponding for this write request and backup command is sent to from control end;
Describedly receive described RAID information and backup command from control termination, preserve the RAID information that obtains, define the memory headroom enough backing up bitmap according to obtained backup command, then feed back the response message to described backup command to described main control end;
Described main control end receives described response message, is sent to by message bit pattern to back up described from control end, and wherein, described main control end sends message bit pattern to described from control end by network;
Described from control termination receipts institute bitmap information, under received message bit pattern being saved in corresponding RAID information;
Wherein, described main control end is comprised to the described process from control end transmission message bit pattern by network:
The data encapsulation that will send becomes packet to re-send to opposite end according to main control end with from the network communication protocol between control end by described main control end.
2. the method for claim 1, is characterized in that, the method also comprises:
When creating RAID, main control end creates the bitmap that each RAID is corresponding.
3. the method for claim 1, is characterized in that, described main control end is comprised to the described process from control end transmission message bit pattern by network:
The data encapsulation that will send becomes packet to re-send to opposite end according to main control end with from the network communication protocol between control end by described main control end.
4. method as claimed in claim 3, it is characterized in that, the method also comprises:
Arrange backup cycle, when backup cycle arrives, message bit pattern corresponding for the different RAID information of this locality sends to described from control end by described main control end, described from received message bit pattern is saved in corresponding RAID information by control end.
5. the method as described in any one of Claims 1-4, is characterized in that, the method also comprises:
When described main control end lost efficacy, described RAID of restarting main control end from control end;
After RAID information in described main control end is restarted, if find, described end from control preserves message bit pattern, then this message bit pattern is write back disk, from control end, message bit pattern is not preserved if find, then from disk, read message bit pattern from control end, described from the message bit pattern of reading to be saved in corresponding RAID by control end.
6. method as claimed in claim 5, is characterized in that, when described main control end does not receive the described response message from the transmission of control end in setting-up time, the bitmap of this locality is write back disk.
7. a raid-array RAID bitmap backup system, is characterized in that, this system comprises master controller and from controller, wherein:
Described master controller, when a certain region first time receives write request, upgrade local bitmap, RAID information corresponding for this write request and backup command are sent to described from controller, and when receiving the described response message from controller feedback, message bit pattern to back up is sent to described from controller by network;
Described from controller, receive the packet that described master controller sends, therefrom obtain RAID information and backup command, preserve the RAID information obtained, the memory headroom enough backing up bitmap is defined according to obtained backup command, and to the response message of described master controller feedback to described backup command, and under the message bit pattern that described master controller sends being saved in corresponding RAID information;
Wherein, message bit pattern to back up to be sent to by network and describedly to refer to from controller by described master controller, becomes packet to re-send to opposite end the data encapsulation that will send according to master controller with from the network communication protocol between controller.
8. system as claimed in claim 7, it is characterized in that, message bit pattern to back up to be sent to by network and describedly to refer to from controller by described master controller, becomes packet to re-send to opposite end the data encapsulation that will send according to master controller with from the network communication protocol between controller.
9. system as claimed in claim 7 or 8, is characterized in that,
Described master controller, also periodically sends to described from controller according to the backup cycle arranged by message bit pattern corresponding for the different RAID information of this locality;
Described from controller, the message bit pattern that periodic receipt master controller sends, and under received message bit pattern being saved in corresponding RAID information.
10. system as claimed in claim 9, is characterized in that,
When described master controller lost efficacy, described RAID of restarting from controller main control end;
After RAID information on described master controller is restarted, if preserve message bit pattern from controller described in finding, then this message bit pattern is write back disk, from control end, message bit pattern is not preserved if find, then from disk, read message bit pattern from controller, describedly the message bit pattern of reading to be saved in corresponding RAID from controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210043802.1A CN102622286B (en) | 2012-02-23 | 2012-02-23 | A kind of raid-array bitmap backup method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210043802.1A CN102622286B (en) | 2012-02-23 | 2012-02-23 | A kind of raid-array bitmap backup method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102622286A CN102622286A (en) | 2012-08-01 |
| CN102622286B true CN102622286B (en) | 2016-02-03 |
Family
ID=46562213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210043802.1A Active CN102622286B (en) | 2012-02-23 | 2012-02-23 | A kind of raid-array bitmap backup method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102622286B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103647781B (en) * | 2013-12-13 | 2017-05-17 | 大连理工计算机控制工程有限公司 | Mixed redundancy programmable control system based on equipment redundancy and network redundancy |
| CN104778018B (en) * | 2015-04-23 | 2018-06-05 | 南京道熵信息技术有限公司 | Wide band disk array and storage method based on asymmetric hybrid magnetic disk mirroring |
| 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 |
| CN106648473B (en) * | 2016-12-30 | 2019-09-24 | 郑州云海信息技术有限公司 | A kind of dual control RAID synchronous method and device |
| CN112114750B (en) | 2020-09-11 | 2023-01-10 | 苏州浪潮智能科技有限公司 | Metadata volume bitmap data conflict processing method and related components |
| CN113868246B (en) * | 2021-06-30 | 2024-01-19 | 苏州浪潮智能科技有限公司 | Bit map synchronization method, system and device in storage system and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794246A (en) * | 2010-02-24 | 2010-08-04 | 成都市华为赛门铁克科技有限公司 | Backup storage system, backup system, data backup method and recovery method |
| CN102012793A (en) * | 2010-11-12 | 2011-04-13 | 浪潮(北京)电子信息产业有限公司 | Mirror image implementing method and device |
| CN102169497A (en) * | 2011-04-13 | 2011-08-31 | 浪潮(北京)电子信息产业有限公司 | Method and device for managing metadata through bitmaps |
-
2012
- 2012-02-23 CN CN201210043802.1A patent/CN102622286B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794246A (en) * | 2010-02-24 | 2010-08-04 | 成都市华为赛门铁克科技有限公司 | Backup storage system, backup system, data backup method and recovery method |
| CN102012793A (en) * | 2010-11-12 | 2011-04-13 | 浪潮(北京)电子信息产业有限公司 | Mirror image implementing method and device |
| CN102169497A (en) * | 2011-04-13 | 2011-08-31 | 浪潮(北京)电子信息产业有限公司 | Method and device for managing metadata through bitmaps |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102622286A (en) | 2012-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102622286B (en) | A kind of raid-array bitmap backup method and system | |
| CN103814360B (en) | Data copy method and storage system | |
| US11397648B2 (en) | Virtual machine recovery method and virtual machine management device | |
| US10102076B2 (en) | System and method for implementing a block-based backup restart | |
| US7966463B2 (en) | Asynchronous remote copy system and control method for the same | |
| US7694177B2 (en) | Method and system for resynchronizing data between a primary and mirror data storage system | |
| JP5409159B2 (en) | Information processing apparatus, information processing apparatus control method, and program | |
| JP3968207B2 (en) | Data multiplexing method and data multiplexing system | |
| US20070006021A1 (en) | Reliability of diskless network-bootable computers using non-volatile memory cache | |
| US20070174673A1 (en) | Storage system and data restoration method thereof | |
| US6073221A (en) | Synchronization of shared data stores through use of non-empty track copy procedure | |
| EP1835392A2 (en) | Storage system issuing optimum I/O command to allocation-on-use enabled volume and controlling method therefor | |
| CN101878470B (en) | Apparatus and method for managing storage copy services systems | |
| US10078558B2 (en) | Database system control method and database system | |
| CN116204137B (en) | Distributed storage system, control method, device and equipment based on DPU | |
| CN112698987A (en) | On-line backup method, device, equipment and storage medium for snapshot-free operating system | |
| WO2020094063A1 (en) | Data storage method and device, storage medium and electronic device | |
| CN115586950A (en) | Method and device for realizing non-stop cloud-loading migration based on memory system | |
| CN111930707B (en) | Method and system for correcting drive letter of windows cloud migration | |
| CN107590024B (en) | Data storage method and data storage system | |
| CN102833096A (en) | Method and device for implementation of low-cost high-availability system | |
| CN107357536B (en) | Data modification and writing method and system for distributed storage system | |
| CN114077517A (en) | Data processing method, equipment and system | |
| CN113127151B (en) | Real-time copying method, system and medium for data in virtualization environment | |
| JP2004206239A (en) | Raid 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 | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |