CN105094712A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN105094712A CN105094712A CN201510642556.5A CN201510642556A CN105094712A CN 105094712 A CN105094712 A CN 105094712A CN 201510642556 A CN201510642556 A CN 201510642556A CN 105094712 A CN105094712 A CN 105094712A
- Authority
- CN
- China
- Prior art keywords
- data
- disk
- array
- new
- band
- 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
Abstract
The invention provides a data processing method and device. The method comprises the following steps: when a target disk is in failure in an array reconstruction process, inserting a new disk into an array to replace the target disk of responding to data read-write, and updating stripe attributes corresponding to the new array, wherein data on the new disk in an old data stripe is invalid data, data on the new disk in a new data stripe is valid data, the old data stripe and the new data stripe are stripes where the new disk is positioned, the old data stripe is the stripe where data, written in before the new disk is added, is positioned and the new data stripe is the stripe where data, written in after the new disk is added, is positioned; when a data reading request is received, carrying out data reading according to stripe attributes corresponding to the array. By adopting the method and device provided by the invention, under the circumstance that a large amount of redundant backup space or redundant equipment is not required to be reserved, normal read-write of new data can be realized, that old data is read as far as possible is realized and resource consumption of storage space is reduced.
Description
Technical field
The present invention relates to technical field of video monitoring, particularly relate to a kind of data processing method and device.
Background technology
In video surveillance applications field, when in array of storage devices during polylith disk failure, array may be caused to lose efficacy, and then cause normally to read and write video data.
For the problems referred to above, in prior art, usually adopt the mode of array backup or device backup, ensure the reliability of video data read-write, namely when array lost efficacy, by the Online Video service backup of this array on redundant array or redundance unit.
But practice finds, in the implementation of existing array backup or device backup, in order to ensure backup array or equipment consistent with the disk number of former array of storage devices number and array, need reserved a large amount of redundancy backup space even redundance unit, storage space resource consumption is excessive.
Summary of the invention
The invention provides a kind of data processing method and device, with solve existing array backup or device backup implementation in need reserved a large amount of redundancy backup space even redundance unit, the problem that storage space resource consumption is excessive.
According to the first aspect of the embodiment of the present invention, a kind of data processing method is provided, comprises:
When target disk occurring in array rebuild process and losing efficacy, in described array, add new disk, to substitute the read-write of described target disk response data, and upgrade band attribute corresponding to described array; Wherein, data on disk new described in old data strip are invalid data, data on disk new described in new data strip are valid data, described old data strip and described new data strip are described new disk place band, described old data strip is the data place band of write before described new disk adds, and described new data strip is the data place band that described new disk adds rear write;
When receiving data read request, the band attribute corresponding according to described array carries out digital independent.
According to the second aspect of the embodiment of the present invention, a kind of data processing equipment is provided, comprises:
Array rebuild unit, for when target disk occurring in array rebuild process and losing efficacy, adds new disk in described array, to substitute the read-write of described target disk response data, and upgrades band attribute corresponding to described array; Wherein, data on disk new described in old data strip are invalid data, data on disk new described in new data strip are valid data, described old data strip and described new data strip are described new disk place band, described old data strip is the data place band of write before described new disk adds, and described new data strip is the data place band that described new disk adds rear write;
Data-reading unit, for when receiving data read request, the band attribute corresponding according to described array carries out digital independent.
The application embodiment of the present invention, when target disk occurring in array rebuild process and losing efficacy, adds new disk in the array, to substitute the read-write of this target disk response data, ensures integrality and the data consistency of the data of new write; Simultaneously, by upgrading band attribute corresponding to array, when receiving data read request, the band attribute according to self record carries out digital independent, ensures that the data in new data strip normally read, data in old data strip read as far as possible, thus, when not needing reserved bulk redundancy backup space or redundance unit, achieve the normal read-write of new data, and the reading as far as possible of legacy data, reduce storage space resource consumption.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of a kind of data processing method that the embodiment of the present invention provides;
Fig. 2 A ~ 2F is disk failure or off-line scene schematic diagram in the RAID5 array that provides of the embodiment of the present invention;
Fig. 3 is treatment scheme schematic diagram when again there is disk failure in a kind of array of storage devices process of reconstruction of providing of the embodiment of the present invention;
Fig. 4 is the structural representation of a kind of data processing equipment that the embodiment of the present invention provides;
Fig. 5 is the structural representation of the another kind of data processing equipment that the embodiment of the present invention provides.
Embodiment
Technical scheme in the embodiment of the present invention is understood better in order to make those skilled in the art person, and enable the above-mentioned purpose of the embodiment of the present invention, feature and advantage become apparent more, below in conjunction with accompanying drawing, technical scheme in the embodiment of the present invention is described in further detail.
Refer to Fig. 1, the schematic flow sheet of a kind of data processing method that Fig. 1 provides for the embodiment of the present invention, as shown in Figure 1, this data processing method can comprise:
Step 101, when target disk occurring in array rebuild process and losing efficacy, add new disk in the array, with the read-write of alternative target disk response data, and upgrade band attribute corresponding to this array; Wherein, data in old data strip on this new disk are invalid data, data in new data strip on this new disk are valid data, new data strip and old data strip are this new disk place band, old data strip is the band at the data place of write before this new disk adds, and new data strip is the data place band that this new disk adds rear write.
In the embodiment of the present invention, said method can be applied to the memory device for store video monitor data in video surveillance applications field, for ease of describe, below for the executive agent of said method for memory device is described.
In the embodiment of the present invention, target disk does not refer in particular to a certain fixing disk, but can refer to arbitrary disk that array can be caused to lose efficacy when losing efficacy in array rebuild process.
In the embodiment of the present invention, when disk failures in array, and this fault does not cause array to lose efficacy (as RAID (RedundantArraysofIndependentDisks, disk array) there is single disk failure in 5) time, memory device can be determined to trigger copy according to the fault degree of the disk broken down and to rebuild or inspection is rebuild.
Such as, when disk failure is certain data block write error in disk, memory device can trigger array and carry out copy reconstruction, namely copy reconstruction dish is added in an array, to occurring that the data block of mistake is rebuild according to the verification attribute of array, other data block in this disk carries out copy migration data to copy reconstruction dish; When disk failure is whole disk failure, memory device can trigger array and carry out verification reconstruction, namely adds verification reconstruction dish in an array, and carries out verification reconstruction according to the verification attribute of array to the disk broken down.
In the embodiment of the present invention, when there is target disk in array rebuild (comprising copy to rebuild or verification reconstruction) process and losing efficacy, new disk can be added in the array, with alternative target disk response data read-write, and then, for the band at former target disk place, when needs carry out data write, can write data in the disk and this new disk do not broken down in former array, thus the integrality that data write and consistance can be ensured.
Meanwhile, in order to be optimized digital independent, in embodiments of the present invention, when adding new disk in an array and substituting the read-write of target disk response data, need to upgrade band attribute corresponding to this array (on this band of band attribute record, which data in magnetic disk is valid data); Wherein, in new disk place band this new disk add before write data place band (data strip hereinafter referred to as old) in, data on this new disk are invalid data (or being called misdata), in new disk place band this new disk add after write data place band (data strip hereinafter referred to as new) in, data on this new disk are valid data, thus, when memory device receives data read request, digital independent can be carried out by the band attribute corresponding according to the array of self record.
As a kind of embodiment, in embodiments of the present invention, if array rebuild is verification reconstruction, then, when target disk occurring in array rebuild process and losing efficacy, can also comprise:
Verification is stopped to rebuild; Wherein, having completed the data verified on reconstruction dish in the data strip of verification reconstruction is valid data, and the data do not completed in the data strip of verification reconstruction on this verification reconstruction dish are invalid data.
Concrete, in this embodiment, if array rebuild is verification reconstruction, then, when in array rebuild process, when target disk lost efficacy, the data in array cannot rebuild recovery by verification, and now, memory device needs to stop verification rebuilding; Wherein, for the data strip completing verification reconstruction, the data verified in this data strip on reconstruction dish are valid data, and for not completing the data strip of verification reconstruction, the data verified in this data strip on reconstruction dish are invalid data.
For example, for RAID5 array, suppose that this array comprises 4 disks (disk 1 ~ 4), when arbitrary in 4 disks (as disk 2) breaks down, memory device will carry out verification to this array and rebuild, if in checking procedure, disk 3 breaks down, now, there are 2 failed disk in RAID5 array, memory device cannot carry out verification and rebuild, thus stopping verification being rebuild by memory device.
As a kind of embodiment, in embodiments of the present invention, if target disk lost efficacy for off-line lost efficacy, then, when target disk occurring in array rebuild process and losing efficacy, can also comprise the following steps:
11), the mark of record object disk and Offtime;
12), judge whether target disk rejoins in array in Preset Time;
13) data copy, if so, then write in target disk off-line procedure by new disk, in target disk, kicks out of the disk that this is new from array, and upgrades band attribute corresponding to array; Wherein, the data in this target disk place band on this target disk are valid data.
Concrete, in this embodiment, consider in disk use procedure, the off-line reason such as pulling out and cause the disk short time may be mispluged due to user, therefore, when target disk off-line in array rebuild process lost efficacy, memory device first can not kick out of this target disk from array, but the disk mark of this target disk can be recorded, and the identified off-line of target disk, and judge this target disk whether in Preset Time (can according to concrete scene settings, as 1 minute, 2 minutes etc.) rejoin in array and (namely again reach the standard grade); Meanwhile, in target disk off-line procedure, memory device still can add new disk in an array and substitute target disk and respond digital independent.
If target disk rejoins in array in Preset Time, the data copy that new disk can write by memory device in target disk off-line procedure, in target disk, kicks out of the disk that this is new from array, and upgrades band attribute corresponding to this array; Wherein, when this new disk kicked out of by memory device from array, need to carry out initialization to this new disk, reuse the disk that this is new so that follow-up.
If target disk does not rejoin in array in Preset Time, then memory device can think that this target disk can not be reached the standard grade again again, thus, this target disk can be kicked out of by memory device from this array, and carries out subsequent treatment according to the processing mode identical with target disk malfunction and failure.
Step 102, when receiving data read request, the band attribute corresponding according to array carries out digital independent.
In the embodiment of the present invention, when memory device receives data read request, memory device can carry out digital independent according to the band attribute of self record.
Be valid data owing to recording which disk on band in band attribute, therefore, memory device can read the valid data in data strip according to this band attribute.
As the optional embodiment of one, in embodiments of the present invention, when array rebuild completes, invalid data can be comprised according to whether existing in band determined property array corresponding to array, and can carry out verifying the data strip rebuild; If exist, verification is carried out to this data strip and rebuilds.
For example, still for RAID5 array, then when array rebuild completes, whether memory device can according to including in band determined property array corresponding to array and only having the data in a disk to be the data strip of invalid data, then memory device can determine that this data strip can carry out verification and rebuild, and according to the verification attribute of RAID5 array, verification reconstruction is carried out to this data strip, namely according to the valid data on all the other disks in this data strip, the data that this comprises in the disk of invalid data are rebuild.
Visible, in the method flow described by Fig. 1, when target disk occurring in array rebuild process and losing efficacy, add new disk in the array, to substitute the read-write of this target disk response data, ensure integrality and the data consistency of the data of new write; Simultaneously, by upgrading band attribute corresponding to array, when receiving data read request, the band attribute according to self record carries out digital independent, ensures that the data in new data strip normally read, data in old data strip read as far as possible, thus, when not needing reserved bulk redundancy backup space or redundance unit, achieve the normal read-write of new data, and the reading as far as possible of legacy data, reduce storage space resource consumption.
The technical scheme understood the embodiment of the present invention better to make those skilled in the art and provide, is described the technical scheme that the embodiment of the present invention provides below in conjunction with concrete application scenarios.
In this embodiment, be described for the RAID5 array be made up of 4 disks.Be described with following four kinds of situations respectively below:
In situation one, copy process of reconstruction, target disk malfunction and failure
Refer to Fig. 2 A and 2B, in this case, to suppose in RAID5 array certain data block write error in the 4th blocks of data dish, triggering copy rebuilds (to occurring that the data block of mistake is pressed array verification attribute and rebuild, other data block copy moves on copy reconstruction dish), target disk (being assumed to be the 3rd blocks of data dish) malfunction and failure in process of reconstruction, now, memory device can kick out of faulty disk (the 3rd blocks of data dish) from array, and add new data disks in an array and substitute this faulty disk, copy is rebuild and is continued, and array keeps readable and writes state.
For the data strip (this band does not write new data after new data disks adds) completing copy reconstruction, its band attribute can be recorded as 0010 (in this embodiment, in band attribute 0 correspondence disk on the data that store be valid data, the data that the disk of 1 correspondence stores are invalid data), the data namely in this data strip in the 3rd blocks of data dish are misdata; When needing to write new video data, this video data can write in the disk of non-fault in array and the data strip of new disk formation, to ensure integrality and the consistance of new video data, and the band attribute record of this new data strip is 0000, the data namely in this data strip on each disk are valid data.
After copy reconstruction completes, memory device can kick out of the disk (i.e. the 4th blocks of data dish) of above-mentioned partial data block fault from array, and verification reconstruction is carried out to the data strip (namely have and only have the data on a disk to be the band of misdata) that band attribute is 0010, after having rebuild, the band attribute record of this data strip is 0000.
If when copying reconstruction and also not completing, again occur that disk (being assumed to be the 2nd blocks of data dish) lost efficacy:
1) if this disk is malfunction and failure, then memory device can kick out of this disk from array, and add new disk replacement, the band attribute being the data strip of 0000 by the band attribute of self record is updated to 0100 (data namely on the 2nd blocks of data dish are misdata), band attribute is that the band attribute of the data strip of 0010 is updated to 0110 (data namely on the 2nd blocks of data dish and the 3rd blocks of data dish are misdata), continue copy to rebuild, the band attribute record copying the data strip rebuild is 0110.
On the disk do not broken down in new video data write array and new disk, to ensure integrality and the consistance of new video data, to ensure integrality and the consistance of new video data, and the band attribute record of this new data strip is 0000; After copy reconstruction completes, kick out of the disk of above-mentioned partial data block fault from array, and carry out verification reconstruction to the data strip that band attribute is 0100, the band attribute record of the data strip after having rebuild is 0000.Wherein, be the data strip of 0110 for band attribute, owing to comprising the disk number of misdata more than 1 piece, therefore, verification cannot be carried out and rebuild.
2) lost efficacy if this disk is off-line, then can record mark and the Offtime of this disk, and add new data disks in an array, copy is rebuild and is continued, new video data write is in an array on the disk of non-fault and new disk, and the bar reel number at record new write data place.If off-line disk is not got back in array in Preset Time, memory device can kick out of this off-line disk from array, checkout time mark, upgrade band attribute, wherein, the band attribute record that new disk adds the data place band of rear write is 0000, former band attribute record be 0000 data strip be revised as 0100, former band attribute record be 0010 data strip be revised as 0110.
If off-line disk is got back in array in Preset Time, then according to the bar reel number of self record (the bar reel number of new write data place band) by the data copy that writes in off-line disk off-line procedure in new disk in this off-line disk, after having copied, kick out of this new disk (disk namely newly added for the second time), and be 0000 by the band attribute record of the data place band of copy.
In situation two, copy process of reconstruction, target disk off-line lost efficacy
Refer to Fig. 2 A and Fig. 2 C, in this case, to suppose in RAID5 array certain data block write error in the 4th blocks of data dish, trigger copy to rebuild, target disk (being assumed to be the 3rd blocks of data dish) off-line in process of reconstruction, now, memory device can record mark and the Offtime of this off-line disk, and add new data disks in an array and substitute this off-line dish and carry out reading and writing data response, copy is rebuild and is continued, new video data write is in an array on the disk of non-fault and new disk, to ensure integrality and the consistance of new video data, and record the bar reel number of new video data place data strip.
If disk is got back in array in Preset Time, according to record bar reel number by the data copy on new disk on former off-line disk, after having copied, kick out of new disk (disk namely newly added), and be 0000 by the band attribute record of the data place band of copy;
If disk is not got back in array in Preset Time, then from array, kick out of this off-line disk, checkout time marks, and follow-up processing flow is identical with the processing mode in above-mentioned copy process of reconstruction during target data dish malfunction and failure, does not repeat them here.
If occur on the basis of the above, one piece of dish lost efficacy again, and its disposition is with copy process of reconstruction, and processing mode when there is the 2nd piece of disk failure is identical, does not repeat them here.
In situation three, verification process of reconstruction, target data dish malfunction and failure
Refer to Fig. 2 D and 2E, in this case, suppose that in RAID5 array, the 4th blocks of data checks and regulates a disk failure inefficacy, trigger verification to rebuild, target disk (being assumed to be the 3rd blocks of data dish) malfunction and failure in process of reconstruction, now, memory device can kick out of faulty disk (the 3rd blocks of data dish) from array, and add new data disks in an array and substitute this faulty disk, verification is stopped to rebuild, the band attribute that record has completed the data strip that verification is rebuild is 0010, the band attribute not completing the data strip of data reconstruction is 0011, array keeps readable and writes state.
In new video data write array on the disk of non-fault and new disk, to ensure integrality and the consistance of new video data, the band attribute of corresponding data strip is 0000.
For the data strip (namely have and only have the data on a disk to be the band of misdata) that band attribute is 0010, can carry out verification and rebuild, after having rebuild, the band attribute record of this data strip is 0000.
On the basis of the above, then occur that disk (being assumed to be the 1st blocks of data dish) lost efficacy if:
1), if this disk is malfunction and failure, then memory device can kick out of this disk from array, and add new disk replacement, the band attribute being the data strip of 0000 by the band attribute of self record is updated to 1000 (data namely on the 1st blocks of data dish are misdata), band attribute is that the band attribute of the data strip of 0010 is updated to 1010 (data namely on the 1st blocks of data dish and the 3rd blocks of data dish are misdata), band attribute is that the band attribute of the data strip of 0011 is updated to 1011 (i.e. the 1st blocks of data dishes, data on 3rd blocks of data dish and the 4th blocks of data dish are misdata).
On the disk do not broken down in new video data write array and new disk, to ensure integrality and the consistance of new video data, and the band attribute record of this new data strip is 0000; Carry out verification reconstruction to the data strip that band attribute is 1000, the band attribute record of the data strip after having rebuild is 0000.Wherein, be the data strip of 1010 or 1011 for band attribute, owing to comprising the disk number of misdata more than 1 piece, therefore, verification cannot be carried out and rebuild.
2) lost efficacy if this disk is off-line, then can record mark and the Offtime of this disk, and adding new data disks in an array, new video data write is in an array on the disk of non-fault and new disk, and the bar reel number at record new write data place.If off-line disk is not got back in array in Preset Time, memory device can kick out of this off-line disk from array, checkout time marks, upgrade band attribute, wherein, the band attribute record that new disk adds the data place band of rear write is 0000, former band attribute record be 0000 data strip be revised as 1000, former band attribute record be 0010 data strip be revised as 1010, former band attribute record be 0011 data strip be revised as 1011.
If off-line disk is got back in array in Preset Time, then according to the bar reel number of self record by the data copy that writes in off-line disk off-line procedure in new disk in this off-line disk, after having copied, kick out of this new disk (disk that second time newly adds), and be 0000 by the band attribute record of the data place band of copy.
In situation four, verification process of reconstruction, target disk off-line lost efficacy
Refer to Fig. 2 D and 2F, in this case, suppose that in RAID5 array, the 4th blocks of data checks and regulates a disk failure, trigger verification to rebuild, target disk (being assumed to be the 3rd blocks of data dish) off-line in process of reconstruction, now, memory device can record mark and the Offtime of this off-line disk, and add new data disks in an array and substitute this off-line dish and carry out reading and writing data response, verification is rebuild and is suspended, array keeps readable and writes state, new video data write is in an array on the disk of non-fault and new disk, to ensure integrality and the consistance of new video data, and record the bar reel number of new video data place data strip.
If disk is got back in array in Preset Time, according to record bar reel number by the data copy on new disk on former off-line disk, after having copied, kick out of new disk (disk namely newly added), and be 0000 by the band attribute record of the data place band of copy, continue former verification and rebuild;
If disk is not got back in array in Preset Time, then from array, kick out of this off-line disk, checkout time marks, and follow-up processing flow is identical with the processing mode in above-mentioned verification process of reconstruction during target data dish malfunction and failure, does not repeat them here.
If occur on the basis of the above, one piece of dish lost efficacy again, and its disposition is with verification process of reconstruction, and processing mode when there is the 2nd piece of disk failure is identical, does not repeat them here.
Wherein, treatment scheme schematic diagram when again there is disk failure in array of storage devices process of reconstruction can see Fig. 3.
In this embodiment, when memory device receives video data read requests, video data reading can be carried out according to the band attribute of self record; Wherein, new disk adds the disk of video data non-fault from array of rear write and new disk reads, and video data can normal play without loss; The video data of write before new disk adds, then reading as much as possible in existing disk from array, may there is frame losing jump second phenomenon in video data, but whole video can not be caused to play.
By describing above and can finding out, in the technical scheme that the embodiment of the present invention provides, when target disk occurring in array rebuild process and losing efficacy, add new disk in the array, to substitute the read-write of this target disk response data, ensure integrality and the data consistency of the data of new write; Simultaneously, by upgrading band attribute corresponding to array, when receiving data read request, the band attribute according to self record carries out digital independent, ensures that the data in new data strip normally read, data in old data strip read as far as possible, thus, when not needing reserved bulk redundancy backup space or redundance unit, achieve the normal read-write of new data, and the reading as far as possible of legacy data, reduce storage space resource consumption.
Refer to Fig. 4, be the structural representation of a kind of data processing equipment that the embodiment of the present invention provides, wherein, this data processing equipment can be applied in the memory device in above-mentioned video monitoring system, and as shown in Figure 4, this data processing equipment can comprise:
Array rebuild unit 410, for when target disk occurring in array rebuild process and losing efficacy, adds new disk in described array, to substitute the read-write of described target disk response data, and upgrades band attribute corresponding to described array; Wherein, data on disk new described in old data strip are invalid data, data on disk new described in new data strip are valid data, described old data strip and described new data strip are described new disk place band, described old data strip is the data place band of write before described new disk adds, and described new data strip is the data place band that described new disk adds rear write;
Data-reading unit 420, for when receiving data read request, the band attribute corresponding according to described array carries out digital independent.
In an alternative embodiment, described array rebuild unit 410, if can also be used for described array rebuild for verification reconstruction, then, when target disk occurring in array rebuild process and losing efficacy, stops verification rebuilding; Wherein, having completed the data verified on reconstruction dish in the band of verification reconstruction is valid data, and not completing the data verified on reconstruction dish in the band of verification reconstruction is invalid data.
Please also refer to Fig. 5, be the structural representation of the another kind of data processing equipment that the embodiment of the present invention provides, this embodiment is on aforementioned basis embodiment illustrated in fig. 4, and described data processing equipment can also comprise: record cell 430 and judging unit 440; Wherein:
Record cell 430, if lost efficacy for off-line lost efficacy for described target disk, then, when target disk occurring in described array rebuild process and losing efficacy, recorded mark and the Offtime of described target disk;
Judging unit 440, judges whether described target disk rejoins in described array in Preset Time;
Correspondingly, described array rebuild unit 410, can also be used for when described judging unit 440 is judged as YES, the data copy write in described target disk off-line procedure by described new disk is in described target disk, from described array, kick out of described new disk, and upgrade band attribute corresponding to described array; Wherein, the data on target disk described in the band of described target disk place are valid data.
In an alternative embodiment, described record cell 430, can also be used for when described judging unit 440 is judged as NO, and removes mark and the Offtime of the described target disk of record;
Described array rebuild unit 410, can also be used for, when described judging unit 440 is judged as NO, from described array, kicking out of described target disk.
In an alternative embodiment, described array rebuild unit 410, can also be used for after array rebuild completes, and comprises invalid data according to whether existing in array described in the band determined property that described array is corresponding, and can carry out verifying the band rebuild; If exist, verification is carried out to this band and rebuilds.
In said apparatus, the implementation procedure of the function and efficacy of unit specifically refers to the implementation procedure of corresponding step in said method, does not repeat them here.
For device embodiment, because it corresponds essentially to embodiment of the method, so relevant part illustrates see the part of embodiment of the method.Device embodiment described above is only schematic, the wherein said unit illustrated as separating component or can may not be and physically separates, parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of module wherein can be selected according to the actual needs to realize the object of the present invention program.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
As seen from the above-described embodiment, when target disk occurring in array rebuild process and losing efficacy, add new disk in the array, to substitute the read-write of this target disk response data, ensure integrality and the data consistency of the data of new write; Simultaneously, by upgrading band attribute corresponding to array, when receiving data read request, the band attribute according to self record carries out digital independent, ensures that the data in new data strip normally read, data in old data strip read as far as possible, thus, when not needing reserved bulk redundancy backup space or redundance unit, achieve the normal read-write of new data, and the reading as far as possible of legacy data, reduce storage space resource consumption.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the present invention or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.
Claims (10)
1. a data processing method, is characterized in that, comprising:
When target disk occurring in array rebuild process and losing efficacy, in described array, add new disk, to substitute the read-write of described target disk response data, and upgrade band attribute corresponding to described array; Wherein, data on disk new described in old data strip are invalid data, data on disk new described in new data strip are valid data, described old data strip and described new data strip are described new disk place band, described old data strip is the data place band of write before described new disk adds, and described new data strip is the data place band that described new disk adds rear write;
When receiving data read request, the band attribute corresponding according to described array carries out digital independent.
2. method according to claim 1, is characterized in that, if described array rebuild is verification reconstruction, then, when target disk occurring in array rebuild process and losing efficacy, described method also comprises:
Verification is stopped to rebuild; Wherein, having completed the data verified on reconstruction dish in the band of verification reconstruction is valid data, and not completing the data verified on reconstruction dish in the band of verification reconstruction is invalid data.
3. method according to claim 1, is characterized in that, if described target disk lost efficacy for off-line lost efficacy, then, when target disk occurring in array rebuild process and losing efficacy, described method also comprised:
Record mark and the Offtime of described target disk;
Judge whether described target disk rejoins in described array in Preset Time;
If so, the data copy then write in described target disk off-line procedure by described new disk, in described target disk, kicks out of described new disk from described array, and upgrades band attribute corresponding to described array; Wherein, the data on target disk described in the band of described target disk place are valid data.
4. method according to claim 3, is characterized in that, described method also comprises:
If described target disk does not rejoin in described array in Preset Time, then remove mark and the Offtime of the described target disk of record, and kick out of described target disk from described array.
5. method according to claim 1, is characterized in that, described method also comprises:
After array rebuild completes, comprise invalid data according to whether existing in array described in the band determined property that described array is corresponding, and can carry out verifying the band rebuild;
If exist, verification is carried out to this band and rebuilds.
6. a data processing equipment, is characterized in that, comprising:
Array rebuild unit, for when target disk occurring in array rebuild process and losing efficacy, adds new disk in described array, to substitute the read-write of described target disk response data, and upgrades band attribute corresponding to described array; Wherein, data on disk new described in old data strip are invalid data, data on disk new described in new data strip are valid data, described old data strip and described new data strip are described new disk place band, described old data strip is the data place band of write before described new disk adds, and described new data strip is the data place band that described new disk adds rear write;
Data-reading unit, for when receiving data read request, the band attribute corresponding according to described array carries out digital independent.
7. device according to claim 6, is characterized in that,
Described array rebuild unit, if also rebuild for verifying for described array rebuild, then when target disk occurring in array rebuild process and losing efficacy, stops verification reconstruction; Wherein, having completed the data verified on reconstruction dish in the band of verification reconstruction is valid data, and not completing the data verified on reconstruction dish in the band of verification reconstruction is invalid data.
8. device according to claim 6, is characterized in that, described device comprises:
Record cell, if lost efficacy for off-line lost efficacy for described target disk, then, when target disk occurring in described array rebuild process and losing efficacy, recorded mark and the Offtime of described target disk;
Judging unit, judges whether described target disk rejoins in described array in Preset Time;
Described array rebuild unit, also for when described judging unit is judged as YES, the data copy write in described target disk off-line procedure by described new disk, in described target disk, kicks out of described new disk from described array, and upgrades band attribute corresponding to described array; Wherein, the data on target disk described in the band of described target disk place are valid data.
9. device according to claim 8, is characterized in that,
Described record cell, also for when described judging unit is judged as NO, removes mark and the Offtime of the described target disk of record;
Described array rebuild unit, also for when described judging unit is judged as NO, kicks out of described target disk from described array.
10. device according to claim 6, is characterized in that,
Described array rebuild unit, also for after array rebuild completes, comprises invalid data according to whether existing in array described in the band determined property that described array is corresponding, and can carry out verifying the band rebuild; If exist, verification is carried out to this band and rebuilds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510642556.5A CN105094712B (en) | 2015-09-30 | 2015-09-30 | A kind of data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510642556.5A CN105094712B (en) | 2015-09-30 | 2015-09-30 | A kind of data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105094712A true CN105094712A (en) | 2015-11-25 |
| CN105094712B CN105094712B (en) | 2019-01-11 |
Family
ID=54575272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510642556.5A Active CN105094712B (en) | 2015-09-30 | 2015-09-30 | A kind of data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105094712B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630415A (en) * | 2015-12-24 | 2016-06-01 | 创新科软件技术（深圳）有限公司 | RAID5 system and method for continuing to write data after RAID5 system failure |
| CN110321058A (en) * | 2018-03-29 | 2019-10-11 | 杭州海康威视数字技术股份有限公司 | A kind of data processing method and its device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050283654A1 (en) * | 2004-05-24 | 2005-12-22 | Sun Microsystems, Inc. | Method and apparatus for decreasing failed disk reconstruction time in a raid data storage system |
| 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 |
| CN102184129A (en) * | 2011-04-27 | 2011-09-14 | 杭州华三通信技术有限公司 | Fault tolerance method and device for disk arrays |
-
2015
- 2015-09-30 CN CN201510642556.5A patent/CN105094712B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050283654A1 (en) * | 2004-05-24 | 2005-12-22 | Sun Microsystems, Inc. | Method and apparatus for decreasing failed disk reconstruction time in a raid data storage system |
| 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 |
| CN102184129A (en) * | 2011-04-27 | 2011-09-14 | 杭州华三通信技术有限公司 | Fault tolerance method and device for disk arrays |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630415A (en) * | 2015-12-24 | 2016-06-01 | 创新科软件技术（深圳）有限公司 | RAID5 system and method for continuing to write data after RAID5 system failure |
| CN105630415B (en) * | 2015-12-24 | 2019-04-30 | 创新科软件技术（深圳）有限公司 | A kind of RAID5 system and in the subsequent method for continuing data of RAID5 thrashing |
| CN110321058A (en) * | 2018-03-29 | 2019-10-11 | 杭州海康威视数字技术股份有限公司 | A kind of data processing method and its device |
| CN110321058B (en) * | 2018-03-29 | 2023-08-25 | 杭州海康威视数字技术股份有限公司 | Data processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105094712B (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9189311B2 (en) | Rebuilding a storage array | |
| US7783922B2 (en) | Storage controller, and storage device failure detection method | |
| US7779294B2 (en) | Power-safe disk storage apparatus, systems, and methods | |
| US20130185587A1 (en) | Controlling a Solid State Disk (SSD) Device | |
| US9104604B2 (en) | Preventing unrecoverable errors during a disk regeneration in a disk array | |
| JP6307847B2 (en) | Information processing apparatus, control apparatus, and control program | |
| US20150378858A1 (en) | Storage system and memory device fault recovery method | |
| US20130024723A1 (en) | Disk storage system with two disks per slot and method of operation thereof | |
| US20070101188A1 (en) | Method for establishing stable storage mechanism | |
| CN104503781A (en) | Firmware upgrading method for hard disk and storage system | |
| CN104461791B (en) | Information processing method and device | |
| CN111984365B (en) | Virtual machine virtual disk dual-live implementation method and system | |
| CN102999399A (en) | Method and device of automatically restoring storage of JBOD (just bundle of disks) array | |
| CN103678517A (en) | Method for fixing logical errors of hard disk and controller | |
| CN108170375B (en) | Overrun protection method and device in distributed storage system | |
| CN105094712A (en) | Data processing method and device | |
| CN104850359B (en) | A kind of RAID array method for reconstructing and device | |
| US9104598B2 (en) | Systems and methods for medium error reporting and handling in storage devices | |
| CN102147714B (en) | A kind of management method of network store system and device | |
| CN102158538B (en) | Management method and device of network storage system | |
| CN102981921A (en) | Restoring method and device for failure reading of IO (image orthicon) by Raid5 array | |
| JP2005293119A (en) | Disk array control device, processing method applied to this device upon detection of data defect, and program | |
| US8930748B2 (en) | Storage apparatus and controller | |
| JP2008084168A (en) | Information processor and data restoration method | |
| CN112463019A (en) | Data reading method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |