CN110442298A - Store unit exception detection method and device, distributed memory system - Google Patents
Store unit exception detection method and device, distributed memory system Download PDFInfo
- Publication number
- CN110442298A CN110442298A CN201810411648.6A CN201810411648A CN110442298A CN 110442298 A CN110442298 A CN 110442298A CN 201810411648 A CN201810411648 A CN 201810411648A CN 110442298 A CN110442298 A CN 110442298A
- Authority
- CN
- China
- Prior art keywords
- storage
- storage region
- data
- verification data
- profile
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0619—Improving the reliability of storage systems in relation to data integrity, e.g. data losses, bit errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0644—Management of space entities, e.g. partitions, extents, pools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of storage unit exception detection method and device, distributed memory system, belong to technical field of memory.The described method includes: n profile is written into n storage region, first profile is any profile in n profile, the first storage region is written in first profile, and the first profile includes: first object data and its first verification data;In the read operation success to the first storage region, the second verification data of the second target data read from the first storage region are generated;In the second verification data and third verification data difference, the first storage region exception is determined;When determining at least m storage region exception in n storage region, storage unit exception, 1≤m≤n are determined.The problem of present application addresses when storing unit exception, management equipment can not be learnt.The application is used to store the detection of unit exception.
Description
Technical field
This application involves technical field of memory, in particular to a kind of storage unit exception detection method and device, distribution
Storage system.
Background technique
With the development of network communication technology, distributed memory system is widely used.Distributed memory system
It may include: management equipment and multiple storage equipment of the management equipment management.Client can by the management equipment and
Store equipment storing data in distributed memory system.
In the related technology, management equipment can be by the multiple storage equipment of network insertion, and data can be stored respectively
In multiple storage equipment.When user need the storing data in the distributed memory system when, can by client to
Management equipment sends data to be stored, so that management equipment writes the data into storage equipment.
Due in the related technology, when a certain storage unit exception (as storage equipment goes offline or damages), management equipment without
Method learns the storage unit exception, if data are written in the storage equipment in management equipment at this time, will lead to data generation
Lose, therefore, need a kind of detection store equipment whether Yi Chang method.
Summary of the invention
This application provides a kind of storage unit exception detection method and device, distributed memory system, can solve
The problem of management equipment can not be learnt when storing unit exception.The technical solution is as follows:
On the one hand, a kind of storage unit exception detection method is provided, is applied to management equipment, in the storage equipment
Partial memory area domain includes n storage region, n >=1, which comprises
N profile is written into the n storage region, wherein the first profile is in n profile
Any profile, the first profile be written the first storage region, first profile include: first object data and
Its first verification data;
In the read operation success to first storage region, second read from first storage region is generated
Second verification data of target data, second target data is to the first object number in first storage region
The data obtained according to read operation is carried out;
In second check number and third verification data difference, the storage unit exception is determined, wherein described
Third verification data are to carry out the data that read operation obtains to the first verification data in first storage region;
When determining at least m storage region exception in the n storage region, the storage unit exception is determined, 1
≤m≤n。
Optionally, the method also includes:
It is identical as the second verification data in the verification data read from first storage region, and by described the
When the first verification data failure described in two verification data covers in the first storage region, first storage region is determined
It is abnormal.
Optionally, the method also includes:
In the read operation failure to first storage region, determine that first storage region is abnormal.
Optionally, the first verification data handle to the first object data using default processing mode
It arrives, the second verification data are handled to obtain using the default processing mode to the second target data.
Optionally, n >=3, the storage equipment have continuous multiple storage address, and the n storage region includes institute
State head, middle part and the tail portion in multiple storage address.
Optionally, the storage equipment includes raid-array RAID, the size of the profile be greater than or
Person is equal to the size of a band in the RAID.
Optionally, the storage equipment has other storage regions in addition to the n storage region, and the method is also
Include:
Every preset time period carries out the read operation to first storage region;
Alternatively, when other described storage regions satisfaction judges trigger condition, to described in first storage region progress
Read operation, the judgement trigger condition includes: the failure of the read operation to other storage regions, from other described storage regions
In the file error that reads, and at least one of the write operation failure of other storage regions condition.
Optionally, m=n.
On the other hand, a kind of storage unit exception detection device is provided, is applied to management equipment, in the storage equipment
Partial memory area domain include n storage region, n >=1, the storage unit exception detection device includes:
N profile is written in Xiang Suoshu n storage region for writing module, wherein the first profile be n in advance
Any profile in file is set, the first storage region is written in the first profile, and first profile includes: first
Target data and its first verification data;
Generation module, for generating the of the second target data in the read operation success to first storage region
Two verification data, second target data are to carry out read operation to the first object data in first storage region
Obtained data;
First determining module, for determining described first in the second verification data and third verification data difference
Storage region is abnormal, wherein the third verification data be to the first verification data in first storage region into
The data that row read operation obtains;
Second determining module, for determining when determining at least m storage region exception in the n storage region
The storage unit exception, 1≤m≤n.
Optionally, the storage unit exception detection device further include:
Third determining module, in the verification data and second check number read from first storage region
According to identical, and when by the first verification data failure in the first storage region described in the second verification data cover, really
Fixed first storage region is abnormal.
Optionally, the storage unit exception detection device further include:
4th determining module, for determining first storage in the read operation failure to first storage region
Region is abnormal.
Optionally, the first verification data handle to the first object data using default processing mode
It arrives, the second verification data are handled to obtain using the default processing mode to second target data.
Optionally, n >=3, the storage equipment have continuous multiple storage address, and the n storage region includes institute
State head, middle part and the tail portion in multiple storage address.
Optionally, the storage equipment includes raid-array RAID, the size of the profile be greater than or
Person is equal to the size of a band in the RAID.
Optionally, the storage equipment has other storage regions in addition to the n storage region, and the storage is set
Standby abnormal detector further include:
First read module carries out the read operation to first storage region for every preset time period;
Alternatively,
Second read module, for being stored to described first when other described storage regions satisfaction judges trigger condition
Region carries out the read operation, and the judgement trigger condition includes: that the read operation to other storage regions fails, from described
The file error read in other storage regions, and at least one of the write operation failure to other storage regions
Condition.
Optionally, m=n.
In another aspect, provide a kind of distributed memory system, the distributed memory system includes management equipment and more
A storage equipment, the management equipment include above-mentioned storage unit exception detection device.
Technical solution bring beneficial effect provided by the present application includes at least:
This application provides a kind of storage unit exception detection method, device and distributed memory systems, mention in the application
It, can be pre- in n storage region write-in n in the partial memory area domain in storage equipment in the unit exception detection method of confession
File is set, and the first profile is any profile in n profile, the first memory block is written in the first profile
Domain, the first profile include: first object data and its first verification data.In the read operation success to the first storage region
When, generate the second verification data of the second target data read from the first storage region.It is to first that third, which verifies data,
The first verification data in storage region carry out the data that read operation obtains, and verify data not with second in third verification data
Meanwhile it can determine the first storage region exception.When determining at least m storage region exception in n storage region, determine
Unit exception is stored, and then realizes the detection to storage unit exception.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of structural schematic diagram of distributed memory system provided in an embodiment of the present invention;
Fig. 2 is a kind of flow chart for storing unit exception detection method provided in an embodiment of the present invention;
Fig. 3 is a kind of schematic diagram for storing equipment provided in an embodiment of the present invention;
Fig. 4 is the schematic diagram of another storage equipment provided in an embodiment of the present invention;
Fig. 5 is the schematic diagram of another storage equipment provided in an embodiment of the present invention;
Fig. 6 is the schematic diagram of another storage equipment provided in an embodiment of the present invention;
Fig. 7 is a kind of flow chart of first storage region method for detecting abnormality provided in an embodiment of the present invention;
Fig. 8 is a kind of structural schematic diagram of raid-array provided in an embodiment of the present invention;
Fig. 9 is a kind of structural schematic diagram for storing unit exception detection device provided in an embodiment of the present invention;
Figure 10 is the structural schematic diagram of another storage unit exception detection device provided in an embodiment of the present invention;
Figure 11 is the structural schematic diagram of another storage unit exception detection device provided in an embodiment of the present invention;
Figure 12 is the structural schematic diagram of another storage unit exception detection device provided in an embodiment of the present invention;
Figure 13 be another embodiment of the present invention provides a kind of storage unit exception detection device structural schematic diagram;
Figure 14 is a kind of structural schematic diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application embodiment party
Formula is described in further detail.
With the development of network communication technology, distributed memory system is widely used.Fig. 1 shows a kind of point
The structural schematic diagram of cloth storage system, the distributed memory system 10 may include: that management equipment 101 and the management are set
Multiple storage equipment 102 of standby 101 management.Client 103 can be distributed by the management equipment 101 and storage equipment 102
Storing data in formula storage system 10.
Exemplary, multiple storage equipment may include: disk (English DISK), solid state hard disk (English: Solid
State Drives;Referred to as: SSD), raid-array (English: Redundant Array of Independent
Disks;Referred to as: RAID), storage area network (English: Storage Area Network;Referred to as: SAN, also referred to as IP
SAN), fiber storage area network (English: Fibre Channel Storage Area Network;Referred to as: FC SAN) with
And network attached storage (English: Network Attached Storage;The storage equipment such as referred to as: NAS).Client 103 can
To dispose at the terminal, terminal can set for electronics such as mobile phone, laptop, desktop computer, tablet computer, intelligent TV sets
It is standby.Management equipment 101 can be a server or management equipment 101 can be the server set of multiple servers composition
Group.
It should be noted that illustrating only three storage equipment 102 in distributed memory system 10 in Fig. 1, actually answer
It may include four, five in, in distributed memory system or more store equipment, the embodiment of the present invention does not make this
It limits.Cable network or wireless network connection can be passed through between client and management equipment, wherein cable network can wrap
It includes but is not limited to: universal serial bus (English: Universal Serial Bus;Referred to as: USB), wireless network may include
But it is not limited to: Wireless Fidelity (English: Wireless Fidelity;Referred to as: WIFI), bluetooth, infrared, purple honeybee (English:
Zigbee), data etc..
User, can be by client 103 to management equipment in needing the distributed memory system 10 when storing data
101 send data to be stored, so that management equipment 101 writes the data into storage equipment 102.If a certain storage equipment is different
Often (as storage equipment goes offline or damages), then management equipment can not correctly read the data in the storage equipment, or can not incite somebody to action
The storage equipment, which is written, in data leads to loss of data.Distributed memory system is come accordingly, it is determined that whether storage equipment is abnormal
It says most important.
Fig. 2 is a kind of method flow diagram for storing unit exception detection method provided in an embodiment of the present invention.This method can
With for the management equipment in Fig. 1, as shown in Fig. 2, this method comprises:
N storage region n profile of write-in in step 201, from the partial memory area domain to storage equipment, n >=
1.Execute step 202.
It should be noted that the storage equipment being related in the embodiment of the present invention can be distributed storage shown in FIG. 1
Any one storage equipment in system.Storage equipment can have continuous multiple storage address, it is assumed that a storage region
Including at least one storage address, then the multiple storage address stored in equipment can form multiple storage regions.It deposits the part
Storage area domain may include n storage region in multiple storage region, and n >=1, in step 201, management equipment can be to n
N profile is written in a storage region, that is to say, management equipment can be to each memory block in the n storage region
A profile is written in domain.
It should be noted that assuming that the first profile is any profile in the n profile, then first is pre-
Set file be written n storage region in the first storage region, first profile may include: first object data and its
First verification data, and the first verification data are the number handled using default processing mode first object data
According to.Exemplary, default processing mode can be (the English: Message-Digest Algorithm of message digest algorithm the 5th edition
5;Referred to as: MD5), in step 201, management equipment can be used MD5 and handle first object data, obtain this first
The MD5 code of target data that is to say the first verification data, and the first verification data be written first with the target data and are deposited
Storage area domain.For example, first object data can be written into the first area in the first storage region, the first verification data be can be written into
Second area in first storage region.
Optionally, in n >=3, which can be respectively stored in multiple storage address by management equipment
Head, middle part and tail portion.It should be noted that the head and tail portion in multiple storage address are respectively in multiple storage address
Two parts storage address positioned at both ends, the middle part in multiple storage address are head and tail portion in multiple storage address
Between a part of storage address, and in head, middle part and the tail portion in multiple storage address, two parts of arbitrary neighborhood are stored
Address gaps have at least one storage address.
Exemplary, as shown in figure 3, storage equipment 30 has continuous multiple storage address a, management equipment can be more at this
Three profiles are written (such as in partial memory area domain in multiple storage regions (not marking in Fig. 3) of a storage address composition
Profile F1, profile F2 and profile F3) so that profile F1 is stored in the head of multiple storage address,
Profile F2 is stored in the middle part of multiple storage address, and profile F3 is stored in the tail portion of multiple storage address, this
When, multiple profile can be uniformly distributed in multiple storage address.In Fig. 3 only with head, middle part and tail portion
Including a storage address, and in head, middle part and tail portion, each part is only stored with a profile, and this three pre-
It sets for file is uniformly distributed.
In practical application, these three profiles can be file of different sizes, and head, middle part and tail portion can wrap
More than one storage address is included, for example, as shown in figure 4, profile F1, which is stored in multiple storage address, is located at the two of head
A storage address, profile F3 are stored in two storage address for being located at tail portion in multiple storage address, and profile F2 is deposited
Store up a storage address for being located at middle part in multiple storage address.
Alternatively, multiple profile can not also be uniformly distributed in multiple storage address, for example, as shown in figure 5,
The quantity of storage address between profile F1 and profile F2 can be more than between profile F2 and profile F3
Storage address quantity.
Again alternatively, also only a profile can be written into storage equipment in management equipment, for example, a profile
F1 can be positioned at the head (as shown in Figure 6) of multiple storage address of storage equipment or the profile or positioned at this
The other parts (such as middle part or tail portion) of multiple storage address, it is not limited in the embodiment of the present invention.
Step 202 determines whether at least m storage region in n storage region be abnormal, 1≤m≤n.It is stored at n
When at least m storage region exception in region, step 203 is executed;The number of abnormal storage region in n storage region
When less than m, step 202 is continued to execute.
Exemplary, the first storage region is any storage region in n storage region, as shown in fig. 7, management equipment is true
Whether Yi Chang process may include: fixed first storage region
Step 2021 carries out read operation to the first storage region.In read operation success, step 2022 is executed;It is reading to grasp
When failing, step 2026 is executed.
Management equipment can be read the first storage region, and whether successfully carry out first according to the read operation
Storage region whether Yi Chang judgement.
Second verification data of the second target data that step 2022, generation are read from the first storage region.Execute step
Rapid 2023.
If to the read operation of the first storage region success, can be read from the first storage region the second target data and
Third verifies data, and second target data is that the first object data in the first storage region are carried out with what read operation obtained
Data, third verification data are to carry out the data that read operation obtains to the first verification data in first storage region.
It is that second target data is the data that the first area from the first storage region is read, third verification data are
The data read from the second area in the first storage region.The second target data is read from first area in management equipment
Later, it can be handled to obtain the second verification data to the second target data is read using default processing mode.
It should be noted that the second target data read may be identical as the first object data of actual storage, it should
Second target data may also be different from the first object data of actual storage, and the third read verifies data and may be with reality
First verification data of border storage are identical, which verifies data may also be different from the first verification data of actual storage, this
Inventive embodiments are not construed as limiting this.
Step 2023 judges whether the second verification data and third verification data are identical.In the second verification data and third
When verification data are identical, step 2024 is executed;In the second verification data and third verification data difference, step 2026 is executed.
Management equipment can read third by the second verification data and from second area after obtaining the second verification data
Verification data are compared, and to judge whether the second verification data and third verification data are identical, and then determine from the first storage
Whether the data that region is read are correct.
It should be noted that due to two schools handled using default processing mode two identical data
Test that data are also identical, the two verification data handled using default processing mode to two different data are not yet
Together.
If third verifies identical (namely the secondth area from the first storage region of the first verification data of data and actual storage
The data that domain is read are correct), then can whether identical according to the second verification data and third verification data, determine the second number of targets
According to whether identical as the first object data of actual storage.If the second verification data are identical as third verification data, can recognize
It is identical as first object data for the second target data, it that is to say the data of the first area reading from the first storage region just
Really, and then determine that the data read from the first storage region are correct;It is on the contrary, then it is assumed that the data read from first area are wrong
Accidentally, and then the error in data read from the first storage region is determined.
If the second target data it is identical as the first object data of actual storage (namely from second area read data just
Really), then the second verification data are identical as the first verification data, determine whether the second verification data and third verification data are identical,
It that is to say determine whether the first verification data and third verification data are identical.If the first verification data verify data phase with third
Together, it is determined that the data read from second area are correct, and then determine that the data read from the first storage region are correct;Instead
It, then it is assumed that the error in data read from second area, and then determine the error in data read from the first storage region.
Since the second target data is different from first object data, and the first verification data and third verify data also not
Together, but the second verification data and third verifies data that identical a possibility that happening is very little, therefore can be the
When two verification data are identical as third verification data, it is believed that the data read from the first storage region are correct;In the second school
When testing data and third verification data difference, it is believed that the error in data read from the first storage region.
Step 2024 carries out covering operation to the first verification data in the first storage region with the second verification data.If
Covering operates successfully, thens follow the steps 2025;If covering operation failure, 2026 are thened follow the steps.
It should be noted that if management equipment determines that the second verification data verify data phase with third in step 2023
Together, it may be considered that read data from the first storage region correct, it that is to say and determine that first storage region can normally be read
Access evidence, then management equipment may determine that in first storage region whether data can be normally written.
Exemplary, management equipment can carry out write operation to the first storage region, as management equipment can use the second school
It tests data and covering operation is carried out to the first verification data in the first storage region, that is to say and write-in is executed to the second verification data
The operation of second area in first storage region.If the covering operation failure, management equipment can determine the second check number
According to can not be written second area, and then determines in the first storage region data can not be written;If the covering operates successfully, manage
Equipment can determine that the second verification data are successfully written second area, and then data can be written in determining first storage region.
And due at this time second verification data with read from second area third verification data it is identical, it may be considered that third verification
Data and the second verification data of presently written second area are identical as the first verification data of actual storage, in step 205
Covering operation can't change the data stored in the first storage region.
Step 2025 determines that the first storage region is normal.
For management equipment in the read operation success to the first storage region, the data read from the first storage region are correct, and
When successful to the write operation of the first storage region, it can determine that the first storage region is normal.
Step 2026 determines the first storage region exception.
Management equipment is in the read operation failure to the first storage region, from the error in data of the first storage region reading, or
When person fails to the write operation of the first storage region, the first storage region exception can be determined.
It should be noted that after step 201, management equipment can with every preset time period to the first storage region into
Row read operation, or other storage regions in addition to the n storage region meet when judging trigger condition in storing equipment,
Read operation is carried out to the first storage region.It that is to say in step 202, management equipment can determine n with every preset time period
Whether at least m storage region in storage region be abnormal.The judgement trigger condition may include: to other storage regions
Read operation failure, the file error read from other storage regions, and the write operation of other storage regions is lost
At least one of lose condition.
It is exemplary, if management equipment fails to the read operation of other storage regions in storage equipment, management equipment
It can determine that storage equipment satisfaction judges trigger condition.If read operation success, management equipment, which may determine that, to be read
File whether mistake, if the file error read, management equipment can determine the storage equipment satisfaction judge trigger condition;
If the file read is correct, management equipment can determine that the storage equipment is unsatisfactory for judging trigger condition.In addition, if management
Equipment is to write operation failure is executed in other storage regions in storage equipment, then management equipment can also determine that the storage is set
Standby satisfaction judges trigger condition;If write operation success, management equipment can determine that the storage equipment is unsatisfactory for judgement triggering
Condition.
Step 203 determines storage unit exception.
Management equipment is when determining at least m storage region exception in n storage region, so that it may determine that the storage is set
Standby abnormal, then management equipment can forbid carrying out reading and writing data on a storage device.Optionally, management equipment can also be true
Surely it notifies staff to repair storage equipment after storing unit exception, or reads and writes number in the storage equipment to request
According to client send prompting message or management equipment and can also carry out other operations, the embodiment of the present invention does not limit this
It is fixed.
It should be noted that store in equipment when m=1 and be stored with profile in only one storage region, if
One storage region exception, then management equipment can determine entire storage unit exception;When 2≤m≤n, storage is set
There are profile is stored in multiple storage regions in standby, management equipment is determining that at least m in n storage region are deposited
When the exception of storage area domain, so that it may determine that the storage unit exception, the value of the m can voluntarily be determined by user.In addition, due at this
Storage equipment may can also continue to using therefore m can also be equal to when a part of storage region exception in n storage region
N that is to say that management equipment can just determine storage unit exception, when determining that the n storage region is abnormal to improve determination
Store equipment whether Yi Chang precision.
In the related technology, distributed memory system is to be attached management equipment and multiple storage equipment by network,
The case where storing unit exception generally includes: storage equipment goes offline (namely disconnecting with management equipment), stores equipment damage
(that is to say that storage equipment is unavailable) and storage equipment rear end storage exception (that is to say the error in data of storage, can read and write
Data but read and write data it is abnormal) situations such as at least one of situation.Occur going offline in storage equipment, damage or after
When the situation of end storage exception, management equipment is unable to learn in time.At this point, if management equipment needs to write data into the storage and sets
Standby, then management equipment can write the data into the address at the offline preceding place of the storage equipment, in turn result in loss of data;If management
Equipment needs read data from the storage equipment, then management equipment can address where when the storage equipment is not offline carry out
Read operation, and then possibly can not read data or read the data of mistake, so that reading the efficiency of correct data
It is lower.
In the embodiment of the present invention, management equipment can be to n storage region in the partial memory area domain in storage equipment
Middle n profile of write-in, and can be with every preset time period or when storage equipment satisfaction judges trigger condition, judgement should
Whether at least m storage region in n storage region be abnormal, and at least m storage region in the n storage region
When abnormal, storage unit exception is determined, and then realize the detection to storage unit exception.
It should be noted that storage equipment in the embodiment of the present invention can for DISK, SSD, RAID, SAN, FC SAN,
Any one storage equipment in the storage equipment such as NAS, cloud storage and object storage.Wherein, RAID is by multiple independent hard
The hard disk groups (being also called logic hard disk) formed is combined in different ways in disk (being also called physical hard disk), RAID's
Storage performance is higher than single hard disk, and can carry out data backup.Each hard disk in RAID can for disk (English:
disk).In n profile of n storage region in step 201 in management equipment write-in RAID, each profile
Size needs to be more than or equal to the size of a band (also referred to as stripe) in RAID, so that by judging n storage
Whether at least m storage region in region be abnormal, can accurately determine whether RAID is abnormal.
It should be noted that assume that RAID includes x disk altogether, each disk include multiple memory blocks (also referred to as
Chunk), then each band in RAID may include: x memory block in x disk, that is, the band includes each magnetic
One memory block of disk.And in x memory block in the band, for storing data, remaining one stores x-1 memory block
Block is used to store the verification information of the data, and the size of the band is the size of the data stored in the x-1 memory block.
Exemplary, each disk in RAID may include i memory block, i >=2.Referring to FIG. 8, if RAID is by three
Three disks in a kind of RAID5 (RAID5 is RAID) of a disk composition, the RAID5 are disk A, B and C shown in Fig. 8,
Assuming that each disk in the RAID5 includes five memory blocks (that is to say i=5), if disk A includes memory block A1、A2、A3、
A4、A5, disk B includes memory block B1、B2、B3、B4、B5, disk C includes memory block C1、C2、C3、C4、C5.It should be noted that should
The address of each memory block can be a storage address of storage equipment, and continuous multiple storage address of the RAID can be with
Are as follows: A1、B1、C1、A2、B2、C2、A3、B3、C3、A4、B4、C4、A5、B5And C5Address.
For example, it is assumed that memory block C in Fig. 81、B2、A3、C4And B5Storage address in be stored with the verification informations of data,
Then three profiles f1, f2 and f3 can be written in other storage address into the RAID5 in management equipment, and three preset
The size of file f 1, f2 and f3 is the size of a band.As memory block A can be written in profile f1 by management equipment1
Storage address and memory block B1Storage address, by profile f2 be written memory block B3Storage address and memory block C3's
Memory block A is written in profile f3 by storage address5Storage address and memory block C5Storage address.So that preset text
Head that part f1 is stored in multiple storage address, profile f2 are stored in middle part in multiple storage address, profile
F3 is stored in the tail portion in multiple storage address.Optionally, the target data in each profile can store at two
The storage address of memory block.
In addition, the embodiment of the present invention is only to store equipment as RAID, and RAID is made of three independent disks
RAID5, each disk are written for three profiles including 5 memory blocks, into RAID, in practical application, store equipment
Can also include four, five perhaps each disk of more disks can also include eight, nine or more storage
Block, four can be also written or five profiles, the embodiment of the present invention are not construed as limiting this by storing in equipment.
It should be noted that management equipment into RAID be written data when, if the size of the data be greater than a band
Size, then management equipment can be sequentially written in multiple storage address according to multiple bands are divided that data into.
In conclusion in unit exception detection method provided in an embodiment of the present invention, it can be in the part in storage equipment
N profile is written in n storage region in storage region, and the first profile is any pre- in n profile
File is set, the first storage region is written in the first profile, and the first profile includes: first object data and its first verification
Data.In the read operation success to the first storage region, the second target data read from the first storage region is generated
Second verification data.Third verification data are to carry out the number that read operation obtains to the first verification data in the first storage region
According to, and in the second verification data and third verification data difference, it can determine the first storage region exception.Determining that n are deposited
When at least m storage region exception in storage area domain, storage unit exception, 1≤m≤n can be determined, and then realize to storage
The detection of unit exception.When determining a certain storage unit exception, management equipment can no longer write data into the storage equipment,
Management equipment is prevented to write data into loss of data caused by abnormal storage equipment.
Fig. 9 is a kind of structural schematic diagram for storing unit exception detection device provided in an embodiment of the present invention.The storage is set
Standby abnormal detector is applied to management equipment, and storing the partial memory area domain in equipment includes n storage region, n >=1, such as
Shown in Fig. 9, which includes:
Writing module 901, for n profile to be written into n storage region, wherein the first profile is n
The first storage region is written in any profile in profile, the first profile, and the first profile includes: the first mesh
Mark data and its first verification data.
Generation module 902, for generating and being read from the first storage region in the read operation success to the first storage region
The second target data arrived second verification data, the second target data be to the first object data in the first storage region into
The data that row read operation obtains;
First determining module 903, for determining the first memory block in the second verification data and third verification data difference
Domain is abnormal, wherein third verification data are to carry out the data that read operation obtains to the first verification data in the first storage region.
Second determining module 904, for when determining at least m storage region exception in n storage region, determination to be deposited
Store up unit exception, 1≤m≤n.
In conclusion writing module can store in storage unit exception detection device provided in an embodiment of the present invention
N profile is written in n storage region in partial memory area domain in equipment, and the first profile is n preset texts
The first storage region is written in any profile in part, the first profile, and the first profile includes: first object data
And its first verification data;Generation module can be generated in the success of the read operation to the first storage region from the first memory block
Second verification data of the second target data that domain is read.It is the first check number in the first storage region that third, which verifies data,
The data obtained according to read operation is carried out;First determining module can be in the second verification data and third verification data difference, can
To determine that the first storage region is abnormal, the second determining module is determining that at least m storage region in n storage region is abnormal
When, determine storage unit exception, and then realize the detection to storage unit exception.
Figure 10 is the structural schematic diagram of another storage unit exception detection device provided in an embodiment of the present invention.Such as Figure 10
It is shown, on the basis of Fig. 9, the storage unit exception detection device further include:
Third determining module 905, in the verification data read from the first storage region and the second verification data phase
When together, and by second verifying the first verification data failure in the first storage region of data cover, determine that the first storage region is different
Often.
Optionally, Figure 11 is the structural representation of another storage unit exception detection device provided in an embodiment of the present invention
Figure.As shown in figure 11, on the basis of Fig. 9, the storage unit exception detection device further include:
4th determining module 906, for determining that the first storage region is different in the read operation failure to the first storage region
Often.
Optionally, the first verification data are handled to obtain using default processing mode to first object data, the second school
Data are tested the second target data is handled to obtain using default processing mode.
Optionally, n >=3, storage equipment have continuous multiple storage address, and n storage region includes multiple storage ground
Head, middle part and tail portion in location.
Optionally, storage equipment includes raid-array RAID, and the size of profile is more than or equal to
The size of a band in RAID.
Optionally, storage equipment has other storage regions in addition to n storage region, as shown in figure 12, Fig. 9's
On the basis of, store unit exception detection device further include:
First read module 907 carries out read operation to the first storage region for every preset time period.
Alternatively, as shown in figure 12, on the basis of Fig. 9, storing unit exception detection device further include:
Second read module 908, for other storage regions satisfaction judge trigger condition when, to the first storage region into
Row read operation judges that trigger condition includes: the read operation failure to other storage regions, reads from other storage regions
File error, and at least one of the write operation failure of other storage regions condition.
Optionally, m=n.
In conclusion writing module can store in storage unit exception detection device provided in an embodiment of the present invention
N profile is written in n storage region in partial memory area domain in equipment, and the first profile is n preset texts
The first storage region is written in any profile in part, the first profile, and the first profile includes: first object data
And its first verification data;Generation module can be generated in the success of the read operation to the first storage region from the first memory block
Second verification data of the second target data that domain is read.It is the first check number in the first storage region that third, which verifies data,
The data obtained according to read operation is carried out;First determining module can be in the second verification data and third verification data difference, can
To determine that the first storage region is abnormal, the second determining module is determining that at least m storage region in n storage region is abnormal
When, determine storage unit exception, and then realize the detection to storage unit exception.
The embodiment of the invention provides a kind of distributed memory system, which can be shown in FIG. 1
Distributed memory system, the distributed memory system include management equipment and multiple storage equipment, which may include
Unit exception detection device is stored shown in Fig. 8 to Figure 13 is any.
Figure 14 is a kind of structural schematic diagram of computer equipment provided in an embodiment of the present invention, which can use
Management equipment in distributed memory system, as shown in figure 14, computer equipment 000 include central processing unit (CPU)
It 001, include the system storage 004 of random access memory (RAM) 002 and read-only memory (ROM) 003, and connection system
The system bus 005 of system memory 004 and central processing unit 001.The server 000 further includes each in help computer
The basic input/output (I/O system) 006 of information is transmitted between a device, and for storage program area 013, application
The mass-memory unit 007 of program 014 and other program modules 015.
The basic input/output 006 includes display 008 for showing information and inputs letter for user
The input equipment 009 of such as mouse, keyboard etc of breath.Wherein the display 008 and input equipment 009 are all by being connected to
The input and output controller 010 of system bus 005 is connected to central processing unit 001.The basic input/output 006
Can also include input and output controller 010 with for receive and handle from keyboard, mouse or electronic touch pen etc. it is multiple its
The input of his equipment.Similarly, input and output controller 010 also provides output to display screen, printer or other kinds of defeated
Equipment out.
The mass-memory unit 007 is by being connected to the bulk memory controller (not shown) of system bus 005
It is connected to central processing unit 001.The mass-memory unit 007 and its associated computer-readable medium are server
000 provides non-volatile memories.That is, the mass-memory unit 007 may include such as hard disk or CD-ROM
The computer-readable medium (not shown) of driver etc.
Without loss of generality, the computer-readable medium may include computer storage media and communication media.Computer
Storage medium includes information such as computer readable instructions, data structure, program module or other data for storage
The volatile and non-volatile of any method or technique realization, removable and irremovable medium.Computer storage medium includes
RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storages its technologies, CD-ROM, DVD or other optical storages, tape
Box, tape, disk storage or other magnetic storage devices.Certainly, skilled person will appreciate that the computer storage medium
It is not limited to above-mentioned several.Above-mentioned system storage 004 and mass-memory unit 007 may be collectively referred to as memory.
According to various embodiments of the present invention, the server 000 can also be arrived by network connections such as internets
Remote computer operation on network.Namely server 000 can be by the network interface that is connected on the system bus 005
Unit 011 is connected to network 012, in other words, Network Interface Unit 011 also can be used be connected to other kinds of network or
Remote computer system (not shown).
The memory further includes that one or more than one program, the one or more programs are stored in
In memory, central processing unit 001 realizes unit exception detection shown in Fig. 2 by executing one or more programs
Method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory of instruction, above-metioned instruction can be executed as the processor of server to complete shown in each embodiment of the present invention
Store unit exception detection method.For example, the non-transitorycomputer readable storage medium can be ROM, arbitrary access is deposited
Reservoir (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..
It should be understood that storage unit exception detection device provided by the above embodiment stores unit exception in detection
When, only the example of the division of the above functional modules, in practical application, it can according to need and divide above-mentioned function
With being completed by different functional modules, i.e., the internal structure for storing unit exception detection device is divided into different function moulds
Block, to complete all or part of the functions described above.
It should be noted that embodiment of the method provided in an embodiment of the present invention can mutually join with corresponding Installation practice
It examines, it is not limited in the embodiment of the present invention.The sequencing of embodiment of the method step provided in an embodiment of the present invention can be into
Row appropriate adjustment, step also according to circumstances can accordingly be increased and decreased, and anyone skilled in the art is in this Shen
In the technical scope that please be disclosed, the method that can readily occur in variation should all cover within the scope of protection of this application, therefore not
It repeats again.
The foregoing is merely the alternative embodiments of the application, not to limit the application, it is all in spirit herein and
Within principle, any modification, equivalent replacement, improvement and so on be should be included within the scope of protection of this application.
Claims (17)
1. a kind of storage unit exception detection method, which is characterized in that be applied to management equipment, the part in the storage equipment
Storage region includes n storage region, n >=1, which comprises
N profile is written into the n storage region, wherein the first profile is any in n profile
The first storage region is written in profile, the first profile, and first profile includes: first object data and its
One verification data;
In the read operation success to first storage region, the second verification data of the second target data are generated, described the
Two target datas are to carry out the data that read operation obtains to the first object data in first storage region;
In the second verification data and third verification data difference, determine that first storage region is abnormal, wherein described
Third verification data are to carry out the data that read operation obtains to the first verification data in first storage region;
When determining at least m storage region exception in the n storage region, the storage unit exception, 1≤m are determined
≤n。
2. the method according to claim 1, wherein the method also includes:
It is identical as the second verification data in the verification data read from first storage region, and by second school
When testing the first verification data failure in the first storage region described in data cover, determine that first storage region is different
Often.
3. method according to claim 1 or 2, which is characterized in that the method also includes:
In the read operation failure to first storage region, determine that first storage region is abnormal.
4. the method according to claim 1, wherein the first verification data are using default processing mode to institute
It states first object data to be handled to obtain, the second verification data are using the default processing mode to second target
Data are handled to obtain.
5. the method according to claim 1, wherein n >=3, the storage equipment has continuous multiple storages
Address, the n storage region include head, middle part and tail portion in the multiple storage address.
6. the method according to claim 1, wherein the storage equipment includes raid-array
RAID, the size of the profile are more than or equal to the size of a band in the RAID.
7. the method according to claim 1, wherein the storage equipment have except the n storage region it
Other outer storage regions, the method also includes:
Every preset time period carries out the read operation to first storage region;
Alternatively, carrying out the reading when other described storage regions satisfaction judges trigger condition to first storage region and grasping
Make, the judgement trigger condition includes: the failure of the read operation to other storage regions, is read from other described storage regions
The file error got, and at least one of the write operation failure of other storage regions condition.
8. the method according to claim 1, wherein m=n.
9. a kind of storage unit exception detection device, which is characterized in that be applied to management equipment, the part in the storage equipment
Storage region includes n storage region, n >=1, and the storage unit exception detection device includes:
Writing module, for n profile to be written into the n storage region, wherein the first profile is n pre-
Any profile in file is set, the first storage region is written in the first profile, and first profile includes: first
Target data and its first verification data;
Generation module, for generating the second school of the second target data in the read operation success to first storage region
Data are tested, second target data is to carry out read operation to the first object data in first storage region to obtain
Data;
First determining module, for determining first storage in the second verification data and third verification data difference
Region is abnormal, wherein the third verification data are to read the first verification data in first storage region
Operate obtained data;
Second determining module, described in determining when determining at least m storage region exception in the n storage region
Store unit exception, 1≤m≤n.
10. storage unit exception detection device according to claim 9, which is characterized in that the storage unit exception inspection
Survey device further include:
Third determining module, in the verification data read from first storage region and the second verification data phase
Together, when and described first in the first storage region described in the second verification data cover being verified data failure, institute is determined
State the first storage region exception.
11. storage unit exception detection device according to claim 9 or 10, which is characterized in that the storage equipment is different
Normal detection device further include:
4th determining module, for determining first storage region in the read operation failure to first storage region
It is abnormal.
12. storage unit exception detection device according to claim 9, which is characterized in that the first verification data are adopted
The first object data are handled to obtain with default processing mode, the second verification data use the default processing
Mode is handled to obtain to second target data.
13. storage unit exception detection device according to claim 9, which is characterized in that n >=3, the storage equipment tool
There are continuous multiple storage address, the n storage region includes head, middle part and tail in the multiple storage address
Portion.
14. storage unit exception detection device according to claim 9, which is characterized in that the storage equipment includes only
Vertical redundant array of inexpensive disk RAID, the size of the profile are more than or equal to the size of a band in the RAID.
15. storage unit exception detection device according to claim 8, which is characterized in that the storage equipment, which has, to be removed
Other storage regions except the n storage region, the storage unit exception detection device further include:
First read module carries out the read operation to first storage region for every preset time period;
Alternatively,
Second read module is used for when other described storage regions satisfaction judges trigger condition, to first storage region
Carry out the read operation, the judgement trigger condition includes: the failure of the read operation to other storage regions, from it is described other
The file error read in storage region, and at least one of the write operation failure of other storage regions item
Part.
16. storage unit exception detection device according to claim 9, which is characterized in that m=n.
17. a kind of distributed memory system, which is characterized in that the distributed memory system includes management equipment and multiple storages
Equipment, the management equipment include: any storage unit exception detection device of claim 9-16.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810411648.6A CN110442298B (en) | 2018-05-02 | 2018-05-02 | Storage equipment abnormality detection method and device and distributed storage system |
PCT/CN2019/085128 WO2019210844A1 (en) | 2018-05-02 | 2019-04-30 | Anomaly detection method and apparatus for storage device, and distributed storage system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810411648.6A CN110442298B (en) | 2018-05-02 | 2018-05-02 | Storage equipment abnormality detection method and device and distributed storage system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110442298A true CN110442298A (en) | 2019-11-12 |
CN110442298B CN110442298B (en) | 2021-01-12 |
Family
ID=68386976
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810411648.6A Active CN110442298B (en) | 2018-05-02 | 2018-05-02 | Storage equipment abnormality detection method and device and distributed storage system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110442298B (en) |
WO (1) | WO2019210844A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112380046A (en) * | 2020-11-10 | 2021-02-19 | 北京灵汐科技有限公司 | Calculation result checking method, system, device, equipment and storage medium |
CN112395129A (en) * | 2020-11-10 | 2021-02-23 | 北京灵汐科技有限公司 | Storage verification method and device, computing chip, computer equipment and storage medium |
CN113312294A (en) * | 2020-02-27 | 2021-08-27 | 瑞昱半导体股份有限公司 | Electronic device and communication method |
WO2022100576A1 (en) * | 2020-11-10 | 2022-05-19 | 北京灵汐科技有限公司 | Verification method, system, and apparatus, computing chip, computer device, and medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1746854A (en) * | 2004-09-10 | 2006-03-15 | 富士通株式会社 | The device, method and the program that are used for control store |
CN101060015A (en) * | 2007-05-23 | 2007-10-24 | 北京芯技佳易微电子科技有限公司 | A multi-bit flash memory and its error detection and remedy method |
CN101783955A (en) * | 2010-03-24 | 2010-07-21 | 杭州华三通信技术有限公司 | Data recovering method when data is abnormal and equipment thereof |
US20110026326A1 (en) * | 2006-09-06 | 2011-02-03 | Samsung Electronics Co., Ltd. | Memory system including flash memory and method of operating the same |
CN104914815A (en) * | 2015-04-15 | 2015-09-16 | 北汽福田汽车股份有限公司 | Processor monitoring method, device and system |
CN105824717A (en) * | 2016-03-16 | 2016-08-03 | 硅谷数模半导体(北京)有限公司 | Method and device for controlling chip operation and chip |
CN106373616A (en) * | 2015-07-23 | 2017-02-01 | 深圳市中兴微电子技术有限公司 | Method and apparatus for detecting failure of random access memory, and network processor |
CN108121615A (en) * | 2016-11-28 | 2018-06-05 | 中国科学院沈阳自动化研究所 | A kind of date storage method based on redundancy fault-tolerant mechanism |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10335978B4 (en) * | 2003-08-06 | 2006-02-16 | Infineon Technologies Ag | Hub module for connecting one or more memory modules |
DE102006016499B4 (en) * | 2006-04-07 | 2014-11-13 | Qimonda Ag | Memory module control, memory control and corresponding memory arrangement and method for error correction |
CN104269190B (en) * | 2014-08-26 | 2017-10-17 | 上海华虹宏力半导体制造有限公司 | The data verification method of memory |
-
2018
- 2018-05-02 CN CN201810411648.6A patent/CN110442298B/en active Active
-
2019
- 2019-04-30 WO PCT/CN2019/085128 patent/WO2019210844A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1746854A (en) * | 2004-09-10 | 2006-03-15 | 富士通株式会社 | The device, method and the program that are used for control store |
US20110026326A1 (en) * | 2006-09-06 | 2011-02-03 | Samsung Electronics Co., Ltd. | Memory system including flash memory and method of operating the same |
CN101060015A (en) * | 2007-05-23 | 2007-10-24 | 北京芯技佳易微电子科技有限公司 | A multi-bit flash memory and its error detection and remedy method |
CN101783955A (en) * | 2010-03-24 | 2010-07-21 | 杭州华三通信技术有限公司 | Data recovering method when data is abnormal and equipment thereof |
CN104914815A (en) * | 2015-04-15 | 2015-09-16 | 北汽福田汽车股份有限公司 | Processor monitoring method, device and system |
CN106373616A (en) * | 2015-07-23 | 2017-02-01 | 深圳市中兴微电子技术有限公司 | Method and apparatus for detecting failure of random access memory, and network processor |
CN105824717A (en) * | 2016-03-16 | 2016-08-03 | 硅谷数模半导体(北京)有限公司 | Method and device for controlling chip operation and chip |
CN108121615A (en) * | 2016-11-28 | 2018-06-05 | 中国科学院沈阳自动化研究所 | A kind of date storage method based on redundancy fault-tolerant mechanism |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113312294A (en) * | 2020-02-27 | 2021-08-27 | 瑞昱半导体股份有限公司 | Electronic device and communication method |
CN112380046A (en) * | 2020-11-10 | 2021-02-19 | 北京灵汐科技有限公司 | Calculation result checking method, system, device, equipment and storage medium |
CN112395129A (en) * | 2020-11-10 | 2021-02-23 | 北京灵汐科技有限公司 | Storage verification method and device, computing chip, computer equipment and storage medium |
WO2022100576A1 (en) * | 2020-11-10 | 2022-05-19 | 北京灵汐科技有限公司 | Verification method, system, and apparatus, computing chip, computer device, and medium |
CN112380046B (en) * | 2020-11-10 | 2023-12-22 | 北京灵汐科技有限公司 | Calculation result verification method, system, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110442298B (en) | 2021-01-12 |
WO2019210844A1 (en) | 2019-11-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110442298A (en) | Store unit exception detection method and device, distributed memory system | |
US10204017B2 (en) | Variable drive health determination and data placement | |
JP4894922B2 (en) | RAID group conversion apparatus, RAID group conversion method, and RAID group conversion program | |
CN102937922B (en) | Inquiry and repair data | |
US9372743B1 (en) | System and method for storage management | |
CN110413205B (en) | Method, apparatus and computer readable storage medium for writing to disk array | |
US7895162B2 (en) | Remote copy system, remote environment setting method, and data restore method | |
US10229023B2 (en) | Recovery of storage device in a redundant array of independent disk (RAID) or RAID-like array | |
KR101107564B1 (en) | Method of managing data storage service based on analysis of log and computer-readable medium having thereon program performing function embodying the same | |
US10235278B2 (en) | Software testing using statistical error injection | |
CN105144074A (en) | Block storage using a hybrid memory device | |
CN108509156A (en) | Method for reading data, device, equipment and system | |
CN110399247A (en) | A kind of data reconstruction method, device, equipment and computer readable storage medium | |
JP2005004753A (en) | Method and device of performing data version checking | |
JP5352027B2 (en) | Computer system management method and management apparatus | |
CN112115001B (en) | Data backup method and device, computer storage medium and electronic equipment | |
CN115359834B (en) | Disk arbitration region detection method, device, equipment and readable storage medium | |
US11115056B2 (en) | Location selection based on erasure code techniques | |
CN109542671A (en) | Verify data creation method and solid state hard disk | |
CN112328182B (en) | RAID data management method, device and computer readable storage medium | |
JP6556980B2 (en) | Storage control device, storage control method, and storage control program | |
US9053074B2 (en) | Computer product, writing control method, writing control apparatus, and system | |
CN112162699A (en) | Data reading and writing method, device and equipment and computer readable storage medium | |
US8214589B2 (en) | Data storage system redundancy scheme verification | |
CN110008064A (en) | A kind of RAID restoration methods, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |