CN102981778A - Redundant array of independent disks (RAID) array reconstruction method and device thereof - Google Patents
Redundant array of independent disks (RAID) array reconstruction method and device thereof Download PDFInfo
- Publication number
- CN102981778A CN102981778A CN201210461849XA CN201210461849A CN102981778A CN 102981778 A CN102981778 A CN 102981778A CN 201210461849X A CN201210461849X A CN 201210461849XA CN 201210461849 A CN201210461849 A CN 201210461849A CN 102981778 A CN102981778 A CN 102981778A
- Authority
- CN
- China
- Prior art keywords
- data
- reconstruction
- dish
- band
- raid array
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention provides a redundant array of independent disks (RAID) array reconstruction method and a device with the redundant array of independent disks (RAID) array reconstruction method. The method includes when preset reconstruction triggering event happens, confirming a reconstructed disc, setting the reconstructed disc to be in an offline state, changing a RAID array state into a degraded state, writing data which need to be written into a stripe into a current member disc, and recording the stripe with identification into an offline service table, copying data in the reconstructed disc into a reconstructing disc, and executing local reconstruction after the copying, traversing the offline service table, aiming at each stripe in the offline service table and reading data of each data block of the member disc on the strip, and calculating corresponding data of the reconstructing disc according to a check algorithm which corresponds to the RAID array. The redundant array of independent disks (RAID) array reconstruction method and a device with the redundant array of independent disks (RAID) array reconstruction method can effectively avoid the influence on the performance of online storage service caused by copying and reconstructing, and can sharply shortcut copying and reconstructing time.
Description
Technical field
The present invention relates to network storage field, relate in particular to a kind of RAID array rebuild method and device of novelty.
Background technology
When a RAID array that is in normal condition runs into write error or other preset trigger condition, rebuild if exist HotSpare disk then can trigger copy.Online copy is rebuild, for rebuilding disk and rebuilt disk, and the order of should managing business, again processing reconstructed order will increase the randomness of disk read-write like this, on professional and rebuild performance larger impact is arranged.In the RAID array, to copy the time that reconstruction consumes in the service traffics situation quite long existing for jumbo disk, especially when LBA address corresponding to professional order with rebuild when ordering corresponding LBA address the difference between the address is larger on same video disc, can greatly increase the addressing time of disk, thereby reduce professional overall performance.This reconstruction is called as online copy with professional parallel reconstruction mode and rebuilds.
The disk distribution example of RAID array when please refer to the online copy reconstruction of Fig. 1, wherein the RAID array comprises 6 disks (Disk1-Disk6).When one of them disk writing error from occurring, rebuild if exist HotSpare disk then can trigger copy, wherein the disk of writing error from occurring is called rebuilt dish (such as Disk6), and the disk of application is called HotSpare disk or reconstruction dish again.Rebuild in the simultaneous situation of order when business order and copy, will increase the read-write randomness of reconstruction dish and rebuilt dish.Please refer to Fig. 2, online copy is rebuild flow process and is generally included following steps:
1) issuing service order in upper strata is after the RAID module, and the order that the RAID module issues the upper strata splits into the band order, and hangs the professional processing queue chained list of waiting for;
2) if need copy reconstruction, then the structure copy is rebuild order and is hung to copy to rebuild and wait for the processing queue chained list;
3) rebuild in the simultaneous situation of order at business order and copy, data channel needs to issue which kind of order according to corresponding rule arbitration.
In above-mentioned flow process, reconstruction order and professional order can mix to be issued in the disk to be processed, and the read-write IO randomness that causes like this rebuilding disk and rebuilt disk increases greatly, and the IOPS processing power of disk descends.
Summary of the invention
In view of this, the invention provides a kind of RAID array rebuild device, be applied on the network storage equipment, wherein this network storage equipment comprises at least one RAID array, and described RAID array comprises a plurality of member's disks; This device comprises the condition monitoring unit, rebuilds administrative unit and Service Processing Unit, wherein:
The condition monitoring unit is used for determining rebuilt dish rebuilt dish to be set to off-line state when predetermined reconstruction trigger event occurs, and the RAID array status is changed to degrading state, and notice is rebuild administrative unit and copied reconstruction;
Service Processing Unit is used for when the RAID array becomes degradation, the data that need to write this moment in the RAID array band are write in the data block corresponding in the current member's disk of RAID array, and with this band identification record in the offline business table;
Rebuild administrative unit, be used for the data copy on the rebuilt dish to the reconstruction dish, and after the copy end, carry out partial reconstruction, described partial reconstruction comprises: further travel through described offline business table, for each band that records in the offline business table, rebuild administrative unit and read the data on each data block of member's disk on this band, and calculate data corresponding on the reconstruction dish according to checking algorithm corresponding to RAID array, the data that calculate are written in the data block corresponding on the reconstruction dish.
The present invention also provides a kind of RAID array rebuild method, is applied on the network storage equipment, and wherein this network storage equipment comprises at least one RAID array, and described RAID array comprises a plurality of member's disks; The method comprises the steps:
Steps A, predeterminedly determine rebuilt dish rebuilt dish to be set to off-line state when rebuilding trigger event occuring, the RAID array status is changed to degrading state;
Step B, become when degradation at the RAID array, the data that need to write this moment in the RAID array band write in the data block corresponding in the current member's disk of RAID array, and with this band identification record in the offline business table;
Step C, after the RAID array becomes degrading state, with the data copy on the rebuilt dish to the reconstruction dish, and after the copy end, carry out partial reconstruction, described partial reconstruction comprises: further travel through described offline business table, for each band that records in the offline business table, read the data on each data block of member's disk on this band, and calculate on the reconstruction dish corresponding data according to checking algorithm corresponding to RAID array, the data that calculate are written in the data block corresponding on the reconstruction dish.
The present invention can effectively avoid copying the impact of rebuilding the on-line storage service feature, and can significantly shorten the time that copy is rebuild.
Description of drawings
Fig. 1 is the logical schematic that a kind of RAID array copies reconstruction online in the prior art.
Fig. 2 is the processing flow chart that a kind of RAID array copies reconstruction online in the prior art.
Fig. 3 is RAID array rebuild device building-block of logic in one embodiment of the present invention.
Fig. 4 is the processing flow chart of RAID array rebuild method in one embodiment of the present invention.
Embodiment
Take bulk business datum sequential storage in main applied environment, in using such as this typical multi-medium data storage of video monitoring, from the business order on upper strata usually can be constantly in the RAID array order data writing.This order writes the write performance that can give full play to disk, can seriously upset this order and is written in advantage on the performance yet copy online process of reconstruction.The relation of failing in the prior art to take into full account between application and the disk performance designs reconstruction mode.
In copy reconstruction process flow process provided by the invention, allow reconstruction disk and rebuilt disk off-line copy.So, other disks can continue to give full play to the sequential write performance of disk in the RAID array in multimedia service storage, simultaneously can also be in copy be rebuild the sequence of play write performance.Deng copy rebuild finish after, replenish again during this period of time that original this write the data of reconstruction dish, so neither affect original service feature, greatly shortened again the copy reconstruction time.Below by embodiment more specifically the implementation procedure that offline copies is rebuild is described.
Please refer to Fig. 3 and Fig. 4, a kind of RAID array rebuild device is provided in one embodiment of the present invention, this application of installation is on the network storage equipment, and this network storage equipment comprises a RAID array at least.This device comprises the condition monitoring unit, rebuilds administrative unit and Service Processing Unit.Be embodied as example with computer program, this device operates in the following processing procedure of execution on the network storage equipment.
Step 101, when predetermined reconstruction trigger event occured, the rebuilt dish of reconstruction need to be determined in the condition monitoring unit, and notice is rebuild administrative unit and is carried out the copy reconstruction, and rebuilt dish is set to off-line state and the RAID array is changed to degrading state;
Step 102, the reconstruction administrative unit is obtained the HotSpare disk as the reconstruction dish from system, carry out copy and rebuild with the data copy on the rebuilt dish that will be in off-line state to the reconstruction dish;
Step 103, when the data on a certain data block of rebuilt dish can't read, rebuild administrative unit and obtain the data on other data blocks on this data block place band, and calculate data on this data block according to RAID algorithm corresponding to RAID array, and the data that calculate are written in the data block corresponding on the reconstruction dish;
Step 104, before the copy reconstruction is finished, when Service Processing Unit write order in the business of receiving, the data that needs are write in the band write in the data block corresponding in the current member's disk of RAID array, and recorded the sign of this band in the offline business table;
Step 105, after the copy reconstruction is finished, rebuild administrative unit and carry out partial reconstruction, travel through described offline business table, for each band that goes on record, rebuild administrative unit and read the data on each data block of member's disk on this band, and calculate data corresponding on the reconstruction dish according to checking algorithm corresponding to RAID array, the data that calculate are written in the data block corresponding on the reconstruction dish.
Step 106, the reconstruction administrative unit is given to the reconstruction dish with the RAID identity information of rebuilt dish, the reconstruction dish is joined in the RAID array, and the reconstruction dish is set to presence.
In the RAID array, depositing of business datum is that striping is deposited, and data parallel can be written in a plurality of member's disks like this, greatly promotes the writing speed of business datum, and the redundancy of storage can be provided.Please refer to table 1, the rank of supposing the RAID array is RAID5, and it comprises 6 member's disks (D1-D6).A band (Stripe) comprises six data blocks, comprises Block1-Block6 such as band 1, and it lays respectively on the D1-D6.Have a Block among six Block and be used for depositing checking data, may have more Block in the RAID of other higher levels deposits checking data certainly.For this rank of RAID5, its RAID algorithm (being also referred to as " checking algorithm ") is the XOR algorithm:
Wherein B1-B6 represents respectively the data among the Block1-Block6.When the corrupted data among any one Block, can by the data among other Block it be calculated by using the RAID algorithm, that is to say that RAID5 can tolerate the damage of member's disk and not lose business datum.
D1 | D2 | D3 | D4 | D5 | D6 | D6' | |
Stripe1 | Block1 | Block2 | Block3 | Block4 | Block5 | Block6 | Block6' |
Stripe2 | Block7 | Block8 | Block9 | Block10 | Block11 | Block12 | Block12' |
Stripe3 | Block13 | Block14 | Block15 | Block16 | Block17 | Block18 | Block18' …… …… …… …… …… …… …… …… …… …… …… …… …… …… …… …… |
Stripen | Block(6n-5) | Block(6n-4) | Block(6n-3) | Block(6n-2) | Block(6n-1) | Block6n | Block6n' |
Table 1
Any one member's disk writing error from occurring (such as D6) in six member's disk D1-D6 in the RAID array, the condition monitoring unit can find that the event of makeing mistakes appears writing in D6, it can be with this event notice to rebuilding administrative unit.Rebuild administrative unit and can copy reconstruction as the reconstruction dish to rebuilt dish D6 by corresponding application HotSpare disk D6'.If certainly do not have HotSpare disk in the system, then can't rebuild, rebuild administrative unit and can send corresponding alarm to the supvr.
Have under the background that business datum continues to write at the network storage equipment, rebuild the administrative unit application behind HotSpare disk D6', D6 and D6' are done as a wholely to separate separately; Namely D6 is set to off-line state, so-called off-line state is provisional off-line state, mainly is to make D6 at least no longer participate in the business datum ablation process.Next, rebuild administrative unit D6 is gone up the data copy of each data block to D6'.On specific implementation, rebuild administrative unit and can make up reading order and read data from D6, and then make up and write order and write data on the D6'.If when running into upper certain data block of D6 and can't read, rebuild administrative unit and can read the data in other data blocks on this data block band, then calculate data on this data block by checking algorithm, again with this data copy to D6'.Such as the data B12 on the Block12 can't read, and can read first the data on the Block7-Block11 this moment, then uses checking algorithm to calculate
Because D6 is set to off-line state, only be left five member disk D1-D5s in the RAID array this moment, and the RAID array is in degrading state, has temporarily lost redundancy.But because D6, D6' separate with D1-D5, this moment, the data copy characteristic that the disk order can be write speed of D6 and D6' performed to very high level, can do not write institute by business datum and " bother " and produce and cross over significantly the space, location and carry out the situation that data write, therefore will there be great shortening the time (T1) of whole data copy than prior art.Correspondingly, it is shorter that the RAID array is in the time of degrading state, and for major applications, especially the application that writes of multimedia service data can be tolerated.
After the D6 write fault occurred became rebuilt dish, Service Processing Unit was processed only need to process according to degrading state for the read-write of normal business datum and is got final product.For the data read command, if it was to leave on certain data block of rebuilt dish originally that business datum is arranged, but because the RAID array becomes degrading state, this moment, Service Processing Unit can read the data on other data blocks of this data block place band, and calculated data on this data block according to the RAID checking algorithm.What Service Processing Unit needed special processing is, for the operation that business datum writes band, Service Processing Unit can be split as the write operation for band the write operation for upper 5 Block of D1-D5, in each Block that writes data into D1-D5, the bar tape identification that also needs to be written into (such as the band numbering) is recorded in the offline business table, is used for recording the situation that data that the T1 time occurs write.So that after copy is rebuild and is finished, can coil D6' to reconstruction and carry out partial reconstruction, it does not have off-line if should write rebuilt certain Block(of dish D6 during being equivalent to copy rebuild) the new business data upgrade again and write among the upper corresponding Block of D6'.
After the copy reconstruction is finished, rebuild administrative unit and need to carry out partial reconstruction.Rebuild administrative unit traversal offline business table this moment, if record the band that needs partial reconstruction in the offline business table, then illustrate within the off-line time (namely T1), carried out the write operation of business datum at this band on the RAID array.Need to upgrade the upper corresponding data of D6' this moment by partial reconstruction.Supposing that band 3 occurs in data occured during the T1 and write, rebuild administrative unit this moment and read then the interior data of the upper B13-B17 of D1 ~ D5 calculate B18 by checking algorithm data, then the data that calculate are written to override among Block corresponding to D6' in the copy reconstruction and write this Block data, thereby finish the renewal of data, guarantee redundancy and the consistance of band.
The reconstruction administrative unit can just join D6' after the copy reconstruction is finished and substitute D6 in the RAID array as the newcomer's disk in the array, wherein the identity information of D6' in the RAID array is consistent such as sequence number (index) and the sequence number (index) of original D6 in the RAID group.Partial reconstruction and business processing can walk abreast and carry out this moment, its treatment mechanism is as follows: rebuild administrative unit finish for the partial reconstruction of certain band after with this band record deletion, and Service Processing Unit all traveled through current offline business table at every turn before certain band data writing, if this band has record in the offline business table, the record of corresponding this band of deletion after writing data into this band then.In the situation of only a few, to rebuild administrative unit and Service Processing Unit and may operate simultaneously a band, the problem of the conflict that may generating routine process this moment can be considered to introduce common Mechanism of Conflict Among and solve; But because this situation probability of happening is very little, therefore also can ignore above-mentioned collision problem.
The time of in the present invention whole reconstruction is copy reconstruction time T1 and partial reconstruction time T 2 sums.At first, because the copy reconstruction is off-line mode, therefore can allow to greatest extent the disk execution sequence read and write, therefore the speed of copy reconstruction can be very quick, this means that this time of T1 is shorter.Because the T1 time is shorter, the business that then occurs in the T1 time writes also just relatively less, this so that the T2 time usually also can be very short.In the application of multimedia service data storage, in video surveillance applications, the advantage of the present invention on performance is very obvious.
The above only is preferred embodiment of the present invention, and is in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of making, is equal to replacement, improvement etc., all should be included within the scope of protection of the invention.
Claims (10)
1. a RAID array rebuild device is applied on the network storage equipment, and wherein this network storage equipment comprises at least one RAID array, and described RAID array comprises a plurality of member's disks; This device comprises the condition monitoring unit, rebuilds administrative unit and Service Processing Unit, it is characterized in that:
The condition monitoring unit is used for determining rebuilt dish rebuilt dish to be set to off-line state when predetermined reconstruction trigger event occurs, and the RAID array status is changed to degrading state, and notice is rebuild administrative unit and copied reconstruction;
Service Processing Unit is used for when the RAID array becomes degradation, the data that need to write this moment in the RAID array band are write in the data block corresponding in the current member's disk of RAID array, and with this band identification record in the offline business table;
Rebuild administrative unit, be used for the data copy on the rebuilt dish to the reconstruction dish, and after the copy end, carry out partial reconstruction, described partial reconstruction comprises: further travel through described offline business table, for each band that records in the offline business table, rebuild administrative unit and read the data on each data block of member's disk on this band, and calculate data corresponding on the reconstruction dish according to checking algorithm corresponding to RAID array, the data that calculate are written in the data block corresponding on the reconstruction dish.
2. device as claimed in claim 1 is characterized in that, described reconstruction administrative unit, be used for the RAID identity information of rebuilt dish is given to the reconstruction dish, the reconstruction dish is joined in the RAID array, and the reconstruction dish is set to presence, the RAID array status is revised as normal condition.
3. device as claimed in claim 2 is characterized in that, described reconstruction administrative unit be further used for copy rebuild finish after partial reconstruction described reconstruction dish is added in the RAID array before beginning.
4. device as claimed in claim 3 is characterized in that, described reconstruction administrative unit is used for deleting the record of this band in the offline business table after finishing the partial reconstruction of certain band; Described Service Processing Unit is further used for all traveling through current offline business table before certain band data writing during the partial reconstruction at every turn, if having record in the offline business table, this band after writing data into this band, correspondingly deletes the record of this band.
5. device as claimed in claim 1, it is characterized in that, rebuilding administrative unit is further used for when the data copy on the rebuilt dish being run into the data in the data block read unsuccessfully on the rebuilt dish in the reconstruction dish process, read the data on other data blocks of this data block place band, and calculate data on this data block according to the RAID checking algorithm, and the data that calculate are written in this data block on the reconstruction dish.
6. a RAID array rebuild method is applied on the network storage equipment, and wherein this network storage equipment comprises at least one RAID array, and described RAID array comprises a plurality of member's disks; It is characterized in that the method comprises the steps:
Steps A, predeterminedly determine rebuilt dish rebuilt dish to be set to off-line state when rebuilding trigger event occuring, the RAID array status is changed to degrading state;
Step B, become when degradation at the RAID array, the data that need to write this moment in the RAID array band write in the data block corresponding in the current member's disk of RAID array, and with this band identification record in the offline business table;
Step C, after the RAID array becomes degrading state, with the data copy on the rebuilt dish to the reconstruction dish, and after the copy end, carry out partial reconstruction, described partial reconstruction comprises: further travel through described offline business table, for each band that records in the offline business table, read the data on each data block of member's disk on this band, and calculate on the reconstruction dish corresponding data according to checking algorithm corresponding to RAID array, the data that calculate are written in the data block corresponding on the reconstruction dish.
7. method as claimed in claim 6, it is characterized in that described step C further comprises: the RAID identity information of rebuilt dish is given to the reconstruction dish, the reconstruction dish is joined in the RAID array, and the reconstruction dish is set to presence, the RAID array status is revised as normal condition.
8. method as claimed in claim 7 is characterized in that, described step C further comprises: partial reconstruction adds described reconstruction dish in the RAID array before beginning after the copy reconstruction is finished.
9. method as claimed in claim 8 is characterized in that, described step C further comprises: after finishing the partial reconstruction of certain band, delete the record of this band in the offline business table; Described step B further comprises: all traveling through current offline business table before certain band data writing during the partial reconstruction at every turn, if having record in the offline business table, this band after writing data into this band, correspondingly deletes the record of this band.
10. method as claimed in claim 6, it is characterized in that, described step C further comprises: when the data copy on the rebuilt dish being run into the data in the data block read unsuccessfully on the rebuilt dish in the reconstruction dish process, read the data on other data blocks of this data block place band, and calculate data on this data block according to the RAID checking algorithm, and the data that calculate are written in this data block on the reconstruction dish.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210461849.XA CN102981778B (en) | 2012-11-15 | 2012-11-15 | A kind of RAID array method for reconstructing and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210461849.XA CN102981778B (en) | 2012-11-15 | 2012-11-15 | A kind of RAID array method for reconstructing and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102981778A true CN102981778A (en) | 2013-03-20 |
CN102981778B CN102981778B (en) | 2016-11-16 |
Family
ID=47855854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210461849.XA Active CN102981778B (en) | 2012-11-15 | 2012-11-15 | A kind of RAID array method for reconstructing and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102981778B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488547A (en) * | 2013-09-24 | 2014-01-01 | 浪潮电子信息产业股份有限公司 | Rapid reconstruction method of RAID group fault hard disk |
CN103513942A (en) * | 2013-10-21 | 2014-01-15 | 华为技术有限公司 | Method and device for reconstructing independent redundancy array of inexpensive disks |
CN104268028A (en) * | 2014-09-22 | 2015-01-07 | 浙江宇视科技有限公司 | Magnetic disk data reading method and device based on magnetic disk read error category |
CN104571965A (en) * | 2015-01-19 | 2015-04-29 | 浪潮集团有限公司 | Raid reconstruction optimizing method |
CN104636082A (en) * | 2014-12-30 | 2015-05-20 | 曙光信息产业股份有限公司 | Disk array RAID control method and device |
CN106980468A (en) * | 2017-03-03 | 2017-07-25 | 杭州宏杉科技股份有限公司 | Trigger the method and device that RAID array is rebuild |
CN106990918A (en) * | 2017-03-03 | 2017-07-28 | 杭州宏杉科技股份有限公司 | Trigger the method and device that RAID array is rebuild |
CN109725827A (en) * | 2017-10-27 | 2019-05-07 | 伊姆西Ip控股有限责任公司 | Manage the method, system and computer program product of storage system |
CN109962857A (en) * | 2017-12-26 | 2019-07-02 | 中国电信股份有限公司 | Flow control methods, device and computer readable storage medium |
CN111522505A (en) * | 2020-04-03 | 2020-08-11 | 杭州宏杉科技股份有限公司 | Data processing method and device in RAID reconstruction process |
CN112543920A (en) * | 2019-07-22 | 2021-03-23 | 华为技术有限公司 | Data reconstruction method, device, computer equipment, storage medium and system |
CN113849123A (en) * | 2021-08-14 | 2021-12-28 | 苏州浪潮智能科技有限公司 | Data processing method, system, equipment and medium for slow disk |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006019643A1 (en) * | 2004-08-04 | 2006-02-23 | Dot Hill Systems Corporation | Performing a preemptive reconstruct of a fault-tolerant raid array |
CN101609420A (en) * | 2009-07-17 | 2009-12-23 | 杭州华三通信技术有限公司 | Realize method and the redundant arrays of inexpensive disks and the controller thereof of rebuilding of disc redundant array |
CN102012847A (en) * | 2010-12-06 | 2011-04-13 | 创新科存储技术有限公司 | Improved disk array reconstruction method |
-
2012
- 2012-11-15 CN CN201210461849.XA patent/CN102981778B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006019643A1 (en) * | 2004-08-04 | 2006-02-23 | Dot Hill Systems Corporation | Performing a preemptive reconstruct of a fault-tolerant raid array |
CN101609420A (en) * | 2009-07-17 | 2009-12-23 | 杭州华三通信技术有限公司 | Realize method and the redundant arrays of inexpensive disks and the controller thereof of rebuilding of disc redundant array |
CN102012847A (en) * | 2010-12-06 | 2011-04-13 | 创新科存储技术有限公司 | Improved disk array reconstruction method |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488547A (en) * | 2013-09-24 | 2014-01-01 | 浪潮电子信息产业股份有限公司 | Rapid reconstruction method of RAID group fault hard disk |
CN103513942A (en) * | 2013-10-21 | 2014-01-15 | 华为技术有限公司 | Method and device for reconstructing independent redundancy array of inexpensive disks |
WO2015058542A1 (en) * | 2013-10-21 | 2015-04-30 | 华为技术有限公司 | Reconstruction method and device for redundant array of independent disks |
CN103513942B (en) * | 2013-10-21 | 2016-06-29 | 华为技术有限公司 | The reconstructing method of raid-array and device |
CN104268028A (en) * | 2014-09-22 | 2015-01-07 | 浙江宇视科技有限公司 | Magnetic disk data reading method and device based on magnetic disk read error category |
CN104636082A (en) * | 2014-12-30 | 2015-05-20 | 曙光信息产业股份有限公司 | Disk array RAID control method and device |
CN104636082B (en) * | 2014-12-30 | 2019-02-22 | 曙光信息产业股份有限公司 | The control method and device of disk array RAID |
CN104571965A (en) * | 2015-01-19 | 2015-04-29 | 浪潮集团有限公司 | Raid reconstruction optimizing method |
CN106980468A (en) * | 2017-03-03 | 2017-07-25 | 杭州宏杉科技股份有限公司 | Trigger the method and device that RAID array is rebuild |
CN106990918A (en) * | 2017-03-03 | 2017-07-28 | 杭州宏杉科技股份有限公司 | Trigger the method and device that RAID array is rebuild |
CN109725827A (en) * | 2017-10-27 | 2019-05-07 | 伊姆西Ip控股有限责任公司 | Manage the method, system and computer program product of storage system |
CN109725827B (en) * | 2017-10-27 | 2022-05-13 | 伊姆西Ip控股有限责任公司 | Method, system and computer program product for managing a storage system |
CN109962857A (en) * | 2017-12-26 | 2019-07-02 | 中国电信股份有限公司 | Flow control methods, device and computer readable storage medium |
CN109962857B (en) * | 2017-12-26 | 2022-08-30 | 中国电信股份有限公司 | Flow control method, flow control device and computer readable storage medium |
CN112543920A (en) * | 2019-07-22 | 2021-03-23 | 华为技术有限公司 | Data reconstruction method, device, computer equipment, storage medium and system |
CN112543920B (en) * | 2019-07-22 | 2023-02-10 | 华为技术有限公司 | Data reconstruction method, device, computer equipment, storage medium and system |
CN111522505A (en) * | 2020-04-03 | 2020-08-11 | 杭州宏杉科技股份有限公司 | Data processing method and device in RAID reconstruction process |
CN111522505B (en) * | 2020-04-03 | 2022-08-02 | 杭州宏杉科技股份有限公司 | Data processing method and device in RAID reconstruction process |
CN113849123A (en) * | 2021-08-14 | 2021-12-28 | 苏州浪潮智能科技有限公司 | Data processing method, system, equipment and medium for slow disk |
CN113849123B (en) * | 2021-08-14 | 2023-08-25 | 苏州浪潮智能科技有限公司 | Method, system, equipment and medium for processing data of slow disk |
Also Published As
Publication number | Publication date |
---|---|
CN102981778B (en) | 2016-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102981778A (en) | Redundant array of independent disks (RAID) array reconstruction method and device thereof | |
CN109725822B (en) | Method, apparatus and computer program product for managing a storage system | |
CN101916173B (en) | RAID (Redundant Array of Independent Disks) based data reading and writing method and system thereof | |
US8726070B2 (en) | System and method for information handling system redundant storage rebuild | |
CN104035830B (en) | A kind of data reconstruction method and device | |
US8566673B2 (en) | Method for improving performance in RAID systems | |
CN102033786B (en) | Method for repairing consistency of copies in object storage system | |
US20130047028A1 (en) | Storage system, storage control device, and storage control method | |
US20080126840A1 (en) | Method for reconstructing data in case of two disk drives of raid failure and system therefor | |
US8032784B2 (en) | Duplication combination management program, duplication combination management apparatus, and duplication combination management method | |
CN111124264B (en) | Method, apparatus and computer program product for reconstructing data | |
CN103793182A (en) | Scalable storage protection | |
CN105531677A (en) | Raid parity stripe reconstruction | |
US20180246793A1 (en) | Data stripping, allocation and reconstruction | |
CN102681794A (en) | Method and system for realizing redundant array protection of a disk based on double controllers | |
JPH04230512A (en) | Method and apparatus for updating record for dasd array | |
US9529674B2 (en) | Storage device management of unrecoverable logical block addresses for RAID data regeneration | |
CN107391297B (en) | System and method for improving data refresh in flash memory | |
CN102521058A (en) | Disk data pre-migration method of RAID (Redundant Array of Independent Disks) group | |
CN101609420A (en) | Realize method and the redundant arrays of inexpensive disks and the controller thereof of rebuilding of disc redundant array | |
US20090113237A1 (en) | Storage control device, storage control method and storage control program | |
CN111124262B (en) | Method, apparatus and computer readable medium for managing Redundant Array of Independent Disks (RAID) | |
CN101866307A (en) | Data storage method and device based on mirror image technology | |
CN102164165B (en) | Management method and device for network storage system | |
US8886993B2 (en) | Storage device replacement method, and storage sub-system adopting storage device replacement method |
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 |