CN102081580A - Magnetic disc data protection method - Google Patents
Magnetic disc data protection method Download PDFInfo
- Publication number
- CN102081580A CN102081580A CN 201110045707 CN201110045707A CN102081580A CN 102081580 A CN102081580 A CN 102081580A CN 201110045707 CN201110045707 CN 201110045707 CN 201110045707 A CN201110045707 A CN 201110045707A CN 102081580 A CN102081580 A CN 102081580A
- Authority
- CN
- China
- Prior art keywords
- sector
- data
- copy
- disk
- vector
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000013598 vector Substances 0.000 abstract 16
- 238000012423 maintenance Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000001360 synchronised effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000003716 rejuvenation Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Abstract
The invention discloses a magnetic disc data protection method, which comprises: receiving a magnetic disc operation request, and counting the degree of access heat of a requested vector; when the degree of the access heat of the requested vector meets a hot point requirement, copy is unavailable and the free space of the magnetic disc is greater than a preset free space threshold, generating a copy of the requested vector; and when the data in the requested vector and the data in the copy of the requested vector are consistent during reading and writing operation, selecting a vector which is at the shortest distance to the current position of a magnetic head for operation, or when the data in the requested vector and the data of the copy of the requested vector are inconsistent, selecting the vector with the latest data from the two vectors for operation. When the hot vector or the copy of the hot vector has a fault, data in a mirror sector are used for restoring the failed vector. In the invention, the fault probability of the hot vector is reduced by reducing the reading and writing times of the vector and the reliability of the data in the hot vector is guaranteed; meanwhile, while the system request is responded to, the data at the shortest distance to the magnetic head are fed back, so higher reading and writing performance are provided.
Description
Technical field
The invention belongs to computer memory technical field, a kind of hard disk data protection method for preventing to cause loss of data to provide by sector fails in disk or the disk array is provided.
Background technology
Along with keeping falling of hard disk price, the big capacity hard disk of 2TB is day by day popularized.Yet the use of jumbo hard disk can bring reliability aspect problem, because because technological reason, all there is certain bit error rate in each hard disk, when the bit error rate is under the situation of fixed value, and when the single-deck capacity strengthened, the probability that potential sector fails takes place hard disk also can increase.When disk failure occurring in the storage system that adopts disk array RAID technology, the reconstruction thread of RAID is called.But when occurring sector fails or potential data corruption fault in the process of reconstruction, some data block can not successfully be recovered, and therefore loss of data takes place.
In order to prevent the appearance of this situation, researchers have proposed the disk scanning technology and have surveyed sector fails, proposed in the disk that redundancy is recovered since the loss of data that sector fails causes (specifically referring to A.Dholakia et al.Analysis of a New Intra-Disk Redundancy Scheme forHigh-Reliability RAID Storage Systems in the Presence of Unrecoverable Errors.IBM Research Report RZ 3652, March 16,2006).The disk scanning technology utilizes medium scanning and data scanning to come potential sector mistake and no sign variable in the detection of stored system to degenerate the intertwining mistake of equimagnetic.Redundancy then is divided into several sections to each stripe cell among the RAID in the disk, and a part of space is used to store normal data in each section, and the storage of a part of in addition space is used for the redundant data of parity checking.When sector fails takes place, can utilize redundant data to recover.
This scheme has improved the reliability of storage system greatly.But also there is limitation in this method.The one, performance issue, be similar to the small letter problem among the RAID5, in disk in the redundancy scheme, the data of each stripe cell are carried out write operation all need to calculate and revise check information, therefore, though redundancy scheme can obtain very high reliability in the disk, it has brought influence inevitably for the performance of storage system.The 2nd, integrity problem.At first, the disk sector mistake has a correlativity.When break down in a sector, the possibility that breaks down in contiguous sector is also very high.If during the scheme of the interior redundancy of employing disk, might data can break down simultaneously with its parity bit information of closing on.Therefore, redundancy scheme can not solve the loss of data that is produced by the sector mistake fully in the disk.Secondly, potential sector fails rate is relevant with the load on it.Many more to certain blocks of data read-write number of times, so, the possibility that this data block lost efficacy is big more.Therefore, in the redundancy scheme, if write operation is many, the possibility of depositing the sector fails of check information just increases greatly in disk, thereby also can cause near the increase of the possibility of the sector fails this sector.
Summary of the invention
The object of the present invention is to provide a kind of hard disk data protection method, this method reduces the probability that breaks down in the focus sector by the read-write number of times that reduces the focus sector, when improving the hot spot data reliability, has also improved the access performance of hot spot data.
A kind of hard disk data protection method provided by the invention, the method includes the steps of:
(1) receives the disk operating request, the visit temperature of statistics request sector;
(2) judge to ask the visit temperature of sector whether to reach the focus requirement, to be then to enter step (3); , then do not change step (6) over to;
(3) judging whether the request sector exists copy, is then to change step (5) over to; , then do not enter step (4);
(4) judge that disk slack space whether greater than predefined freespace threshold, is, then generate the copy of request sector, enter step (5); , then do not change step (6) over to;
(5) judge whether the request sector is consistent with these two sectors of data of copy of request sector, is, then selects any one sector in two sectors to operate, and changes step (7) then over to; Not, then do not select in two sectors the up-to-date sector of data to operate, change step (7) then over to;
(6) operation requests sector;
(7) this disk operating finishes;
(8) repeated execution of steps (1)-(7) are out of service until disk.
This method further comprises: when these two sectors of data of copy of asking sector and request sector are consistent, select to operate from the nearest sector of magnetic head current location in two sectors in the step (5).
This method further comprises: select in two sectors from the nearest sector of magnetic head current location according to following step:
(a) calculate the visit time-delay that current magnetic head is visited one of them sector;
(b) calculate the visit time-delay that current magnetic head is visited another sector;
(c) the more current magnetic head visit time-delay of visiting the visit time-delay of one of them sector and visiting another sector, the minimum sector of visit time-delay is from the nearest sector of magnetic head current location.
This method further comprises: when disk is idle, judging that whether to have the data of any one sector and sector copy in the disk inconsistent, is then to carry out data sync; Not, then do not process.
This method further comprises: when any one sector fails of disk, judge whether the inefficacy sector exists the mirror image sector, is, then the mirror image sector data is write a new sector of free time; Not, then do not process; Sector and sector copy mirror image sector each other wherein.
This method further comprises: when disk slack space during less than predefined freespace threshold, in having the sector of copy, select the minimum sector of temperature, delete the copy of the minimum sector of described temperature, until disk slack space greater than predefined freespace threshold.
The present invention is based on a ubiquitous phenomenon, it is big more promptly the possibility of sector fails to be occurred by the sector of frequent access in the disk.Different with redundancy scheme in the disk, the present invention distinguishes the possibility of sector fails, the focus and the position of dynamic tracking application system visit sector, thereby judge which data and zone are important area and high failure rate zone, provide the safeguard measure of higher level then to important focus sector; Promptly generate the copy of focus sector on the disk, by reducing read-write number of times to the focus sector to reduce the probability that breaks down in this sector.In the focus sector or its copy when breaking down, recover the inefficacy sector with its mirror image sectors of data, thereby ensured the reliability of focus sector data.When the operation response request, utilize the head position technology, return from the nearest sector of magnetic head current location, thereby higher readwrite performance is provided.Therefore in addition, the present invention does not need disk is made any change, and does not change the raw data layout on the disk yet, can be used for the optimal Storage system very easily, is applicable to that structure has the storage system based on disk array of high-performance, high reliability.
Description of drawings
Fig. 1 is the process flow diagram of hard disk data protection method of the present invention;
Fig. 2 is the process flow diagram of a data synchronization process of the present invention;
Fig. 3 is the process flow diagram of once lost efficacy sector inspection and rejuvenation of the present invention;
Fig. 4 is the process flow diagram of a free space monitor procedure of the present invention;
Fig. 5 is the computing method process flow diagram of visit time-delay of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments the present invention is described in further detail.
Hard disk data protection method of the present invention relates to following tables of data:
Temperature district chained list: the address of this table record sector and visit temperature, every record is made of 4 data item, and each data item is followed successively by the address of sevtor address, visit temperature, a last record, the address of next bar record; If application system visits first to certain sector, then in temperature district chained list, add the record of this sector, and the visit temperature of putting this sector is 1; If not renewal is then write down in visit first, the visit temperature of this sector is added 1.Wherein visit temperature and refer to this sector accessed number of times in certain time period, this time period length is provided with by the system manager, can be one day, a week, January even endless time.
Consistency maintenance tabulation: the address and the sync id of this table essential record focus sector and focus sector copy, every record is made of 6 data item, and each data item is followed successively by sevtor address, copy address, sector, sector-size, visit temperature, sector sync id, sector copies synchronized sign.Whether sync id mark sector is modified, if be modified, then value is 1, otherwise is 0; Wherein, the focus sector refers to visit the sector that temperature reaches the focus requirement, focus requires to refer to visit temperature greater than predefined heat degree threshold, the obtaining value method of this heat degree threshold is: suppose that temperature district chained list has N bar record, and by the descending sort of visit temperature value, heat degree threshold is in the temperature district chained list the so
The temperature value of (result of α * N rounds downwards) individual element, α is set by the system manager, it be one greater than 0 less than 1 number.
The seek time table: magnetic head moves to access time of any one goal track from any one initial magnetic track in this table record disk, and every record is made of 3 data item, and each data item is followed successively by starting track number, goal track number, seek time.
When moving first, creates by disk the sky table of above three tables of data.
Hard disk data protection method of the present invention as shown in Figure 1, may further comprise the steps:
(1) receives the disk operating request, the visit temperature of statistics request sector;
Concretely, when this time visit is the visit first of this sector, add the record of request sector in temperature district chained list, the visit temperature of putting the request sector is 1; When this time visit when visiting first, is upgraded the record of this sector in the temperature district chained list for non-, visit temperature that will the request sector adds 1.
(2) judge to ask the visit temperature of sector whether to reach the focus requirement, to be then to enter step (3); , then do not change step (6) over to;
Concretely, whether the visit temperature of judging the request sector reaches the method that focus requires: the visit temperature that reads the request sector from temperature district chained list, when the visit temperature surpasses predefined heat degree threshold, think that then the visit temperature of request sector has reached the focus requirement.
(3) judging whether the request sector exists copy, is then to change step (5) over to; , then do not enter step (4);
Concretely, judge whether the request sector exists the method for copy to be: read the consistency maintenance tabulation, judge the record whether the request sector is arranged in this table,, then ask the sector not have copy if do not have; If have, then ask the sector to have copy.
(4) judge that disk slack space whether greater than predefined freespace threshold, is, then generate request sector copy, enter step (5); , then do not change step (6) over to; Wherein, freespace threshold is set by the system manager, half that general value is a disk size or bigger.
Further, after generating request sector copy, in the consistency maintenance tabulation, add the record of a request sector, be about to ask sevtor address, request copy address, sector, sector-size, visit temperature to be saved in the consistency maintenance tabulation, and the sector sync id and the sector copies synchronized of putting this record are designated 0.
(5) judge whether the request sector is consistent with these two sectors of data of copy of request sector, is, then selects any one sector in two sectors to operate, and enters step (7) then; Not, then do not select in two sectors the up-to-date sector of data to operate, enter step (7) then;
Concretely, judge whether consistent method is with request sector these two sectors of data of copy in the request sector: read the consistency maintenance tabulation, find the record of request sector, judge whether sector sync id and sector copies synchronized sign is 0 in this record, be then to think and ask sector and the data consistent of asking the sector copy; , then not inconsistent;
If the sector sync id is 1, then ask sectors of data up-to-date; If the sector copies synchronized is designated 1, then ask the data of sector copy up-to-date;
If operation requests is a write request, after asking the sector to carry out write operation, putting the sector sync id is 1; After asking the sector copy to carry out write operation, put the sector copies synchronized and be designated 1;
If operation requests is a read request, do not revise sync id;
Further, when asking the data consistent of sector and request sector copy, can preferentially select to operate from the nearest sector of magnetic head current location in two sectors.
(6) operation requests sector;
(7) this disk operating finishes;
(8) repeated execution of steps (1)-(7) are out of service until disk.
The method of the invention is regularly carried out data synchronization process, inefficacy sector rejuvenation and free space monitor procedure simultaneously in the process that receives and carry out the disk operating request.
Figure 2 shows that the process flow diagram of a data synchronization process, promptly when disk is idle, read the consistency maintenance tabulation, whether judge in the tabulation exists sector sync id or sector copies synchronized to be designated 1 record, if have, show that then the sector that this record is put down in writing is inconsistent with the data of sector copy, be that 1 sectors of data writes its mirror image sector at this moment with sync id, carry out data sync, and to put this sector sync id be 0; If do not have, then do not do any operation; Sector and sector copy mirror image sector each other wherein.
Figure 3 shows that once lost efficacy sector inspection and rejuvenation process flow diagram, the method of the invention regularly lost efficacy, and the sector is checked and rejuvenation, check promptly whether focus sector and copy thereof lost efficacy, if generation sector fails, then read the consistency maintenance tabulation, if there is the record of inefficacy sector in the tabulation, think that then there is the mirror image sector in the inefficacy sector, write a free time new sector with the mirror image sectors of data this moment, the record of deletion inefficacy sector in the consistency maintenance tabulation, add the record of a new sector, be about to new sevtor address, the mirror image sevtor address, sector-size, the visit temperature is saved in the consistency maintenance tabulation, and the sector sync id and the sector copies synchronized of putting this record are designated 0.The bad track inspection that is similar in the disk is carried out, and the triggered time of this process is also determined by the system manager.
The process flow diagram that is depicted as a free space monitor procedure shown in Figure 4, the method of the invention is regularly carried out the free space monitor procedure, promptly when disk slack space during less than predefined freespace threshold, read the consistency maintenance tabulation, the copy of the sector that the record of the sector that temperature is minimum in the tabulation of deletion consistency maintenance and described temperature are minimum is until the freespace threshold of current disk slack space greater than setting.When if the sector record that temperature is minimum has many, delete for optional one.
Hard disk data protection method of the present invention, select in two sectors from the nearest sector of magnetic head current location according to following step:
(a) calculate the visit time-delay that current magnetic head is visited one of them sector;
(b) calculate the visit time-delay that current magnetic head is visited another sector;
(c) the more current magnetic head visit time-delay of visiting the visit time-delay of one of them sector and visiting another sector, the minimum sector of visit time-delay is from the nearest sector of magnetic head current location.
The computing method of the visit time-delay of wherein current magnetic head access destination sector as shown in Figure 5, may further comprise the steps:
(A) judge that this visit time-delay calculates whether to be the visit time-delay first time after disk starts calculate, be, then carry out initialization step, execution in step (B) again, not, direct execution in step (B) then; Initialization step specifically comprises the sector number SPT that obtains on each magnetic track of disk, mapping relations, the tracking time-delay of magnetic head between any two magnetic tracks that logical address arrives physical address, and deposits the tracking time-delay of magnetic head between any two magnetic tracks in the seek time table; The time-delay RT that disc rotates a circle
0The initial value that the error compensation value Ad of disk current accessed time-delay is set is 0; Wherein SPT is a nonnegative integer, RT
0Be positive rational number, Ad is a rational number.
(B) according to the magnetic track at the place, sector of the magnetic track at current magnetic head place and needs visit, search the seek time table, obtain the seek time ST of current magnetic head access destination magnetic track, wherein ST is a nonnegative number;
(C) parameter S PT and the RT that gets access to according to initialization step
0, current magnetic head place sector T
0And target sector T
1, by rotation time-delay computing formula
Calculate rotation time-delay RT;
(D) obtain the error compensation value Ad that the disk current accessed is delayed time;
(E), calculate the visit time-delay of current magnetic head access destination sector by the computing formula AT=RT+ST+Ad of visit time-delay.
Wherein the error compensation value Ad initial value of disk current accessed time-delay is 0, the Ad regular update, and update method is:
(a) send repeatedly read request continuously to predefined reference sector at set intervals, obtain the actual value of each read request visit time-delay; This time interval determined by the system manager, time value more hour, offset is accurate more, but can produce more extra I/O request, recommended value is 3 minutes; Reference sector can be any one sector in the disk.
(b) computing method of delaying time by the visit of above-mentioned current magnetic head access destination sector calculate the calculated value that current magnetic head is visited the visit time-delay of reference sector;
(c) calculate the actual value of visit time-delay of each read request and the difference between the calculated value, obtain repeatedly a plurality of differences of read request;
(d) calculate the mean value of all differences, this mean value is the error compensation value Ad of disk current accessed time-delay.
The present invention not only is confined to above-mentioned embodiment; persons skilled in the art are according to content disclosed by the invention; can adopt other multiple embodiment to implement the present invention; therefore; every employing project organization of the present invention and thinking; do some simple designs that change or change, all fall into the scope of protection of the invention.
Claims (6)
1. hard disk data protection method is characterized in that the method includes the steps of:
(1) receives the disk operating request, the visit temperature of statistics request sector;
(2) judge to ask the visit temperature of sector whether to reach the focus requirement, to be then to enter step (3); , then do not change step (6) over to;
(3) judging whether the request sector exists copy, is then to change step (5) over to; , then do not enter step (4);
(4) judge that disk slack space whether greater than predefined freespace threshold, is, then generate the copy of request sector, enter step (5); , then do not change step (6) over to;
(5) judge whether the request sector is consistent with these two sectors of data of copy of request sector, is, then selects any one sector in two sectors to operate, and changes step (7) then over to; Not, then do not select in two sectors the up-to-date sector of data to operate, change step (7) then over to;
(6) operation requests sector;
(7) this disk operating finishes;
(8) repeated execution of steps (1)-(7) are out of service until disk.
2. hard disk data protection method according to claim 1 is characterized in that, when these two sectors of data of copy of asking sector and request sector are consistent, selects to operate from the nearest sector of magnetic head current location in two sectors in the step (5).
3. hard disk data protection method according to claim 2 is characterized in that, selects in two sectors from the nearest sector of magnetic head current location according to following step:
(3.1) calculate the visit time-delay that current magnetic head is visited one of them sector;
(3.2) calculate the visit time-delay that current magnetic head is visited another sector;
(3.3) the more current magnetic head visit time-delay of visiting the visit time-delay of one of them sector and visiting another sector, the minimum sector of visit time-delay is from the nearest sector of magnetic head current location.
4. hard disk data protection method according to claim 1 and 2 is characterized in that, when disk is idle, judges that whether to have the data of any one sector and sector copy in the disk inconsistent, is then to carry out data sync; Not, then do not process.
5. hard disk data protection method according to claim 1 and 2 is characterized in that, when any one sector fails of disk, judges whether the sector of losing efficacy exists the mirror image sector, is then the mirror image sector data to be write a new sector of free time; Not, then do not process.
6. hard disk data protection method according to claim 1 and 2; it is characterized in that; when disk slack space during less than predefined freespace threshold; in having the sector of copy, select the minimum sector of temperature; delete the copy of the minimum sector of described temperature, until disk slack space greater than predefined freespace threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100457070A CN102081580B (en) | 2011-02-24 | 2011-02-24 | Magnetic disc data protection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100457070A CN102081580B (en) | 2011-02-24 | 2011-02-24 | Magnetic disc data protection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102081580A true CN102081580A (en) | 2011-06-01 |
| CN102081580B CN102081580B (en) | 2012-07-04 |
Family
ID=44087553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100457070A Expired - Fee Related CN102081580B (en) | 2011-02-24 | 2011-02-24 | Magnetic disc data protection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102081580B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999399A (en) * | 2012-11-13 | 2013-03-27 | 浙江宇视科技有限公司 | Method and device of automatically restoring storage of JBOD (just bundle of disks) array |
| CN103593302A (en) * | 2013-11-22 | 2014-02-19 | 华为技术有限公司 | Super block information processing method, super block information processing device and server |
| WO2018086101A1 (en) * | 2016-11-14 | 2018-05-17 | 华为技术有限公司 | Method for determining hotspot address, and device using same |
| CN108604231A (en) * | 2016-12-13 | 2018-09-28 | 华为技术有限公司 | Mirror processing method and computing device |
| CN116149577A (en) * | 2023-04-24 | 2023-05-23 | 杭州炬华科技股份有限公司 | Data processing method, system and readable storage medium based on rotary pool |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1658171A (en) * | 2003-12-19 | 2005-08-24 | 雷克萨媒体公司 | Faster write operations to nonvolatile memory by manipulation of frequently accessed sectors |
| US20070101096A1 (en) * | 2005-10-27 | 2007-05-03 | Sandisk Corporation | Non-volatile memory with adaptive handling of data writes |
| CN101645928A (en) * | 2009-08-26 | 2010-02-10 | 成都市华为赛门铁克科技有限公司 | Content resource caching method, device and system |
-
2011
- 2011-02-24 CN CN2011100457070A patent/CN102081580B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1658171A (en) * | 2003-12-19 | 2005-08-24 | 雷克萨媒体公司 | Faster write operations to nonvolatile memory by manipulation of frequently accessed sectors |
| US20070101096A1 (en) * | 2005-10-27 | 2007-05-03 | Sandisk Corporation | Non-volatile memory with adaptive handling of data writes |
| CN101645928A (en) * | 2009-08-26 | 2010-02-10 | 成都市华为赛门铁克科技有限公司 | Content resource caching method, device and system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999399A (en) * | 2012-11-13 | 2013-03-27 | 浙江宇视科技有限公司 | Method and device of automatically restoring storage of JBOD (just bundle of disks) array |
| CN102999399B (en) * | 2012-11-13 | 2016-08-03 | 浙江宇视科技有限公司 | The method and apparatus that a kind of JBOD array is automatically renewed |
| US9697078B2 (en) | 2012-11-13 | 2017-07-04 | Zhejiang Uniview Technologies Co., Ltd | Method and device for auto recovery storage of JBOD array |
| CN103593302A (en) * | 2013-11-22 | 2014-02-19 | 华为技术有限公司 | Super block information processing method, super block information processing device and server |
| CN103593302B (en) * | 2013-11-22 | 2017-09-05 | 华为技术有限公司 | A kind of processing method, device and the server of super block message |
| WO2018086101A1 (en) * | 2016-11-14 | 2018-05-17 | 华为技术有限公司 | Method for determining hotspot address, and device using same |
| CN108604231A (en) * | 2016-12-13 | 2018-09-28 | 华为技术有限公司 | Mirror processing method and computing device |
| US11080909B2 (en) | 2016-12-13 | 2021-08-03 | Huawei Technologies Co., Ltd. | Image layer processing method and computing device |
| CN108604231B (en) * | 2016-12-13 | 2022-01-14 | 华为技术有限公司 | Mirror image processing method and computing device |
| CN116149577A (en) * | 2023-04-24 | 2023-05-23 | 杭州炬华科技股份有限公司 | Data processing method, system and readable storage medium based on rotary pool |
| CN116149577B (en) * | 2023-04-24 | 2023-07-07 | 杭州炬华科技股份有限公司 | Data processing method, system and readable storage medium based on rotary pool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102081580B (en) | 2012-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schwarz et al. | Disk scrubbing in large archival storage systems | |
| US7640452B2 (en) | Method for reconstructing data in case of two disk drives of RAID failure and system therefor | |
| JP5887757B2 (en) | Storage system, storage control device, and storage control method | |
| KR100985444B1 (en) | Data storage array | |
| US8589724B2 (en) | Rapid rebuild of a data set | |
| CN101566924B (en) | Data read-write method of disk array | |
| US5572661A (en) | Methods and system for detecting data loss in a hierarchic data storage system | |
| US20130275802A1 (en) | Storage subsystem and data management method of storage subsystem | |
| US7565573B2 (en) | Data-duplication control apparatus | |
| US7143305B2 (en) | Using redundant spares to reduce storage device array rebuild time | |
| CN102081580B (en) | Magnetic disc data protection method | |
| CN103294412A (en) | Implementing large block random write hot spare SSD for SMR RAID | |
| CN102929750A (en) | Nonvolatile media dirty region tracking | |
| CN103699336B (en) | A kind of data of magnetic disk array distribution and method for reconstructing and system | |
| US11128535B2 (en) | Computer system and data management method | |
| JP2007035217A (en) | Data saving processing method of disk storage device and disk storage system | |
| US20180024741A1 (en) | Storage media performance management | |
| CN102968361A (en) | RAID (Redundant Array of Independent Disk) data self-repairing method | |
| US10642508B2 (en) | Method to limit impact of partial media failure of disk drive and detect/report the loss of data for objects due to partial failure of media | |
| US20060215456A1 (en) | Disk array data protective system and method | |
| US20150347224A1 (en) | Storage control apparatus and method therefor | |
| JP2014041471A (en) | Storage system, storage control method, and storage control program | |
| CN102063438A (en) | Recovery method and device for damaged files | |
| JP6260193B2 (en) | Storage system and storage program | |
| CN101169705B (en) | Method for implementing file class mirror-image under multiple hard disk based on nude file system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120704 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |