CN113568788A - Snapshot method, system and storage medium for Linux non-logical volume block device - Google Patents
Snapshot method, system and storage medium for Linux non-logical volume block device Download PDFInfo
- Publication number
- CN113568788A CN113568788A CN202111126898.3A CN202111126898A CN113568788A CN 113568788 A CN113568788 A CN 113568788A CN 202111126898 A CN202111126898 A CN 202111126898A CN 113568788 A CN113568788 A CN 113568788A
- Authority
- CN
- China
- Prior art keywords
- snapshot
- block
- copy
- bio
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/11—File system administration, e.g. details of archiving or snapshots
- G06F16/128—Details of file system snapshots on the file-level, e.g. snapshot creation, administration, deletion
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a snapshot method, a snapshot system and a storage medium of Linux non-logical volume block equipment, and belongs to the technical field of storage disaster recovery. The method comprises the following steps: the method comprises the steps of basic information acquisition, file creation and basic information transmission, preprocessing, first acquisition, calculation, first judgment, data copying and first transmission. The system comprises: the system comprises a basic information acquisition module, a file creation and basic information sending module, a preprocessing module, a first capturing module, a calculation module, a first judgment module, a data copying module and a first sending module. The invention intercepts and captures the general block layer I/O (bio) request of the snapshot source equipment after the snapshot equipment is established and makes COW, and under the condition that one snapshot or a plurality of snapshots exist, the writing efficiency of the source equipment is less influenced, and the snapshot data is complete and consistent; the snapshot data can be stored on the source block device, and no additional block device is needed, so that the storage cost and the operation cost are saved.
Description
Technical Field
The invention belongs to the technical field of storage disaster recovery, and particularly relates to a snapshot method, a snapshot system and a storage medium of a Linux non-logical volume block device.
Background
The Linux block device refers to a device capable of randomly accessing a fixed-size data block in a Linux system. A snapshot is a fully copyable image of a given data set at a point in time, which can be used as a backup method to effectively protect the data in the system. Common snapshot implementation methods include copy-on-write (COW) and redirect-on-write (ROW), both of which can implement online snapshot and generate snapshot volumes.
At present, aiming at a snapshot method of a Linux non-logical volume block device, an official Linux operating system only has a snapshot creation function of the logical volume block device, but does not have the snapshot creation function of the non-logical volume block device, so that multi-file timing backup on the non-logical volume block device lacks consistency guarantee. In the market, the open-source software dattobd can realize the snapshot of the non-logical volume block device and store snapshot data in the snapshot source device by using a virtual file system read-write method based on the block layer, but the snapshot source device has low write efficiency after the open-source software dattobd creates the snapshot, and has a large influence on actual production.
Therefore, it is an urgent need to solve the problem of providing an efficient snapshot method, system and storage medium for Linux non-logical volume block devices.
Disclosure of Invention
In order to solve the technical problems in the background art, the present invention provides a snapshot method, a snapshot system, and a storage medium for a Linux non-logical volume block device. The technical scheme is as follows:
in a first aspect, a snapshot method of a Linux non-logical volume block device is provided, the method comprising the steps of:
a basic information acquisition step, wherein a user layer acquires basic information, wherein the basic information comprises the equipment number, the mounting point, the equipment size and the initial sector number of the source block equipment;
creating a Bitmap file and a snapshot data file under a source block device mounting point of a user layer, and sending the logic sector distribution of the Bitmap file, the logic sector distribution of the snapshot data file and the basic information to a kernel layer;
a preprocessing step, wherein a kernel layer creates a filter positioned in a general block layer, creates snapshot equipment and initializes the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information;
a first capturing step, wherein when the source block equipment has an I/O request, the kernel layer captures a write request bio through the filter;
calculating, namely calculating a destination address of copy block copy storage and a copy block address of a data block pointed by the write request bio by a kernel layer according to the distribution of the logic sectors of the snapshot data file and the intercepted write request bio;
a first judgment step, according to the copy block address and the initialized Bitmap file, the kernel layer judges whether the copy block has a copy record, if so, the intercepted write request bio is forwarded back to the source block device; if not, executing the data copying step and the first sending step;
a data copying step, namely, according to the copy block address and the destination address of the copy storage, the kernel layer reads and writes data from and into the source block device;
and a first sending step, wherein the kernel layer forwards the intercepted write request bio to the source block device.
In one embodiment, the preprocessing step includes:
an entry function obtaining step, in which the kernel layer obtains an entry function of the universal block layer according to the basic information;
a filter creating step, namely replacing an inlet function of the universal block layer with a filter function to create a filter;
creating a snapshot device chain, wherein a kernel layer creates the snapshot device chain;
creating a snapshot device, namely creating a memory block device as a snapshot device in a kernel layer, adding the memory block device to a snapshot device chain, and finishing creation;
and a Bitmap file initialization step, namely initializing the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information.
In one embodiment, the data copying step includes:
a data reading step, namely constructing a read request bio by the kernel layer according to the copy block address, and sending the constructed read request bio to the source block device;
and a data writing step, namely, according to the destination address of the copy block copy storage, the kernel layer constructs a write request bio and sends the constructed write request bio to the source block device.
In one embodiment, the first determining step includes: according to the copy block address and the initialized Bitmap file, the kernel layer judges whether the copy block has a copy record, and if so, the intercepted write request bio is forwarded back to the source block device; if not, firstly executing a step of modifying the Bitmap file, and then executing a step of copying the data and a first sending step;
modifying the Bitmap file, namely writing the destination address copied and stored by the copy block back to the initialized Bitmap file to form a modified Bitmap file;
the snapshot method further comprises the steps of:
a second interception step, the kernel layer intercepts the bio sent to the snapshot device;
a second judgment step, the kernel layer judges whether the bio sent to the snapshot device is a read request bio, if so, a third judgment step is executed; if not, ending;
a third judging step, according to the modified Bitmap file, the kernel layer judges whether the copy block where the bio sent to the snapshot device is located has a copy record, if so, the address obtaining step is executed to the second sending step; if not, sending the bio sent to the snapshot device to the source block device;
an address obtaining step, obtaining a copy destination address of a data block according to the bio sent to the snapshot device and the modified Bitmap file, wherein the data block is a data block pointed by the bio sent to the snapshot device;
modifying the address, namely modifying the source address of the data block pointed by the bio sent to the snapshot equipment into the copy destination address of the data block by the kernel layer;
and a second sending step, forwarding the bio sent to the snapshot device to the source block device.
In one embodiment, the snapshot method further includes the steps of:
a step of receiving a deletion command, in which a user layer receives a snapshot deletion command;
a fourth judgment step of judging whether the deleted object exists, if so, executing the deleted object name transmission step to the second deletion step; if not, the deletion is completed;
a deleted object name transmission step, wherein the user layer transmits the name of the deleted object to the kernel layer;
a first deletion step, wherein according to the name of the deleted object, the kernel layer inquires the snapshot equipment corresponding to the deleted object and deletes the deleted object from the kernel;
and in the second deleting step, the user layer deletes the Bitmap file and the snapshot data file corresponding to the deleted objects respectively.
In a second aspect, a snapshot system of a Linux non-logical volume block device is further provided, the system including:
the basic information acquisition module is used for acquiring basic information by a user layer, wherein the basic information comprises the equipment number, the mounting point, the equipment size and the initial sector number of the source block equipment;
the file creating and basic information sending module is used for creating a Bitmap file and a snapshot data file under a source block device mounting point of a user layer and sending the logic sector distribution of the Bitmap file, the logic sector distribution of the snapshot data file and the basic information to the kernel layer;
the preprocessing module is used for the kernel layer to create a filter positioned in a general block layer, create snapshot equipment and initialize the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information;
the first intercepting module is used for intercepting the write request bio by the kernel layer through the filter when the source block device has the I/O request;
the calculation module is used for calculating a destination address of copy block copy storage and a copy block address of a data block pointed by the write request bio by a kernel layer according to the write request bio which is distributed and captured by the logic sector of the snapshot data file;
the first judgment module is used for judging whether the copy block has a copy record or not according to the copy block address and the initialized Bitmap file, and if so, forwarding the intercepted write request bio to the source block device; if not, executing the data copying module and the first sending module;
the data copying module is used for reading and writing data from and into the source block device by the kernel layer according to the copy block address and the destination address of the copy storage;
and the first sending module is used for forwarding the intercepted write request bio to the source block device by the kernel layer.
In one embodiment, the preprocessing module includes:
an entry function obtaining unit, configured to obtain, by the kernel layer, an entry function of the generic block layer according to the basic information;
the filter creating unit is used for replacing the inlet function of the universal block layer with a filtering function and creating a filter;
the snapshot device chain creating unit is used for creating a snapshot device chain by the kernel layer;
a snapshot device creating unit, configured to create, in the kernel layer, a memory block device as a snapshot device, add the memory block device to a snapshot device chain, and complete creation;
and the Bitmap file initialization unit is used for initializing the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information.
In one embodiment, the first determining module is configured to determine, according to the copy block address and the initialized Bitmap file, whether a copy record exists in the copy block by the kernel layer, and if so, forward the intercepted write request bio to the source block device; if not, firstly executing a Bitmap file modification module, and then executing a data copying module and a first sending module;
a modified Bitmap file module, configured to write back the destination address stored in the copy block copy to the initialized Bitmap file, so as to form a modified Bitmap file;
the snapshot system further comprises:
the second interception module is used for intercepting the bio sent to the snapshot device by the kernel layer;
the second judging module is used for judging the type of the bio sent to the snapshot device by the kernel layer, and if the bio sent to the snapshot device is a read request bio, executing the third judging module; if the write request bio is received, ending;
a third judging module, configured to, according to the modified Bitmap file, judge, by the kernel layer, whether a copy record exists in a copy block where the bio sent to the snapshot device is located, and if so, execute the address obtaining module to the second sending module; if not, sending the bio sent to the snapshot device to the source block device;
an address obtaining module, configured to obtain a copy destination address of a data block according to the bio sent to the snapshot device and the modified Bitmap file, where the data block is a data block pointed by the bio sent to the snapshot device;
the address modification module is used for modifying the source address of the data block pointed by the bio sent to the snapshot equipment into the copy destination address of the data block by the kernel layer;
and the second sending module is used for forwarding the bio sent to the snapshot device to the source block device.
In one embodiment, the snapshot system further comprises:
a deleting command receiving module used for receiving the deleting snapshot command by the user layer;
the fourth judging module is used for judging whether the deleted object exists or not, and if yes, the deleted object name transferring module is executed to the second deleting module; if not, the deletion is completed;
the deleted object name transmission module is used for transmitting the name of the deleted object to the kernel layer by the user layer;
the first deleting module is used for inquiring the snapshot equipment corresponding to the deleted object by the kernel layer according to the name of the deleted object and deleting the deleted object from the kernel;
and the second deleting module is used for deleting the Bitmap file and the corresponding snapshot data file which respectively correspond to the deleted objects by the user layer.
In a third aspect, a computer-readable storage medium is also provided, on which a computer program is stored, which when executed by a processor implements the snapshot method of the Linux non-logical volume block device described above.
The invention has the beneficial effects that:
(1) the method is based on intercepting and capturing a universal block layer I/O (bio) request of a snapshot source device and making a COW, and under the condition of a single snapshot, the lowest influence on the newly added write performance of the snapshot source device is lower than 10%; under the condition that a plurality of snapshots in a certain range exist, the newly added write performance of the source block equipment is kept good;
(2) the snapshot of the non-logical volume block device created by the system can ensure the consistency of data in the process of timed backup, thereby ensuring the data backup and laying a foundation for data recovery;
(3) according to the invention, the snapshot data is stored on the source block device, and no additional block device is required to be added, so that the storage cost is saved, and the use is convenient;
(4) the invention also makes up the defect that the native Linux operating system can not create the snapshot for the non-logical volume block device.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart illustrating a snapshot method of a Linux non-logical volume block device according to the present invention.
Fig. 2 is a diagram of a Bitmap storage structure in the snapshot method of the present invention.
Fig. 3 is a schematic flow chart of snapshot data acquisition operation performed by the snapshot method of the present invention.
Fig. 4 is a schematic flow chart of a snapshot deletion operation performed by the snapshot method of the present invention.
FIG. 5 is a schematic diagram of a snapshot system of a Linux non-logical volume block device according to the present invention.
FIG. 6 is a schematic diagram of a pre-processing module according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The method provided by the invention can be applied to the following environments: in the Linux operating system, the snapshot implementation process is written by C language, and the block device is a non-logical volume block device.
Interpretation of terms:
(1) non-logical volume: in a Linux operating system, a Logical Volume Management (LVM) is used for managing block devices, wherein the block devices which are added to the LVM for management are logical volumes, and the block devices which are not added to the LVM for management are non-logical volumes;
(2) bio (block input output), also called as input/output of the block device, is a core data structure of a general block layer in the linux kernel, which describes the I/O operation of the block device and links the memory buffer with the block device;
(3) a data block, wherein the data block refers to a unit for reading and writing data in the file io in Linux, and the size of one data block is usually 4KB;
(4) and copying blocks, wherein the copying blocks refer to a continuous data area, the size of the data area is defined by user, and the data to be copied is stored in the data area.
Example one
In one embodiment, as shown in fig. 1, a snapshot method of a Linux non-logical volume block device is provided, the snapshot method comprising the steps of:
s1, a user layer acquires basic information, wherein the basic information comprises the equipment number, the mounting point, the equipment size and the initial sector number of the source block equipment.
It is noted that, in general, the device information includes a device number of the source device, a device mount point, a start logical sector number of the device, and a device size. The device number uniquely identifies the block device, and the device object of the block device can be obtained through the device number; the device mounting point is a certain directory in the operating system, and data in the block device can be accessed through the directory; the device start logical sector number identifies the block device from which to start storing data; the device size is how many sectors a block device contains, one sector occupying 512 bytes.
It is understood that the device number, the mounting point, the device size, and the device start sector number of the source block device refer to the device number of the source block device, the mounting point of the source block device, the device size of the source block device, and the device start sector number of the source block device.
And S2, creating a Bitmap file and a snapshot data file under a source block device mounting point of a user layer, and sending the logic sector distribution of the Bitmap file, the logic sector distribution of the snapshot data file and the basic information to a kernel layer.
The method comprises the steps of creating a snapshot file directory under a source block device mounting point of a user layer, creating a Bitmap file and a snapshot data file under the snapshot file directory, wherein the Bitmap file and the snapshot data file are both hole files, pre-distribution of the files can be achieved through the hole files, and physical support of data storage is provided for a copy module. The size of the Bitmap file is calculated according to the size of the block device, and the size of the snapshot data file is calculated according to the free space. The logical sector numbers of the file distributed on the block device can be obtained using a file system method.
And S3, the kernel layer creates a filter positioned in the universal block layer, creates snapshot equipment and initializes the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information.
Optionally, the step S3 includes:
s301, according to the basic information, the kernel layer obtains an entry function of the universal block layer;
s302, replacing an entry function of the universal block layer with a filtering function, and creating a filter;
s303, establishing a snapshot equipment chain by the kernel layer;
s304, establishing memory block equipment as snapshot equipment in a kernel layer, adding the memory block equipment to a snapshot equipment chain, and finishing establishment;
s305, initializing the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information.
And S4, when the source block equipment has an I/O request, the kernel layer intercepts and captures a write request bio through the filter.
It should be noted that the filter intercepts the bio, and firstly classifies the bio, and forwards the bio directly back to the source block device for the read request bio, and performs the copy-on-write process of steps S5 to S7 for the write request bio.
And S5, according to the distribution of the logic sectors of the snapshot data file and the intercepted write request bio, calculating a destination address of copy block copy storage and a copy block address of a data block pointed by the write request bio by a kernel layer.
And calculating the copy destination address and the copy block address of the data block to know the reading position and the writing position of the data, and establishing a mapping relation between the address before copying and the address after copying in the Bitmap file to finish logical copying.
To facilitate understanding, in particular, an example of operation is provided:
the block address of the data block to be sent by the current bio is sector, the copy block is 4MB, the size of the data block is 4KB, and then the block address of the copy block where the data block pointed by the current bio is located is sector/8192.
The snapshot file has a starting sector number of start _ sec and a copied copy block number of b, and the destination address of the copy storage of the copy block is start _ sec + b × 8192.
S6, according to the block address of the copy block and the initialized Bitmap file, judging whether the copy block has a copy record or not by the kernel layer, and if so, forwarding the intercepted write request bio back to the source block device; if not, step S7 and step S8 are executed.
According to the copy block address (the copy block is the copy block where the data block to which the bio is going to be sent is), the copy source address can be calculated, and then the flag bit of the Bitmap record where the copy source address is located is inquired from the initialization Bitmap, so that the copy-on-write situation can be known, for example: if the mark bit of the Bitmap record is 1, the copy-on-write block is copied, and the intercepted write request bio is forwarded back to the source block device; if the flag bit of the Bitmap record is 0, indicating that the copy-on-write block has not been copied, the steps S7 and S8 are performed.
It should be noted that, as shown in fig. 2, one Bitmap record occupies 18 bytes, the 1 st byte from the left is used as a flag bit for marking whether a current copy block (how much data is copied by COW once, the size is customized, and the data block is different from the data block of the operating system) has a copy record, the 2 nd to 9 th bytes are used for recording a logical sector number of the copy block in the snapshot source device, that is, a copy source address, the 10 th byte is a reserved bit, and the 11 th to 18 th bytes are used for recording a logical sector number after the copy block is copied, that is, a copy destination address. And after the Bitmap initialization is finished, storing the Bitmap in a logical sector corresponding to the Bitmap file. The copy mark and copy address mapping of the original copy block can be recorded through the Bitmap storage structure. Thus, the Bitmap records copy map information in the block device.
And S7, according to the copy block address and the destination address of the copy storage, the kernel layer reads and writes data from and into the source block device.
Optionally, the step S7 includes:
s701, constructing a read request bio by the kernel layer according to the copy block address, and sending the constructed read request bio to a source block device to finish data reading;
s702, according to the destination address of the copy block copy storage, the kernel layer constructs a write request bio and sends the constructed write request bio to the source block device to complete the data writing.
To facilitate understanding, in particular, an example of operation is provided:
construct read request bio: the method comprises the steps of reading data with a copy block size of 4MB, setting a copy source address of the copy block as a and setting a constructed single bio as 4KB, setting a constructed target device for reading the bio as a source block device, and setting a data block address pointed by the constructed read bio as a copy source address a, constructing the next read bio, setting the target device as the source block device and the pointed data block address as a + 8; by analogy, 1024 bio's are constructed.
Construct write request bio: the difference from constructing the read request bio is that the bio is constructed as a write bio in the construction process, and the address of the data block pointed to by the write bio is set as the copy destination address.
And S8, forwarding the intercepted write request bio to the source block equipment by the kernel layer.
Optionally, as shown in fig. 3, the step S6 includes: according to the copy block address and the initialized Bitmap file, the kernel layer judges whether the copy block has a copy record, and if so, the intercepted write request bio is forwarded back to the source block device; if not, step S100 is executed first, and then step S7 and step S8 are executed.
S100, writing the destination address copied and stored by the copy block back to the initialized Bitmap file to form a modified Bitmap file.
The snapshot method further comprises the steps of:
the S9 kernel layer intercepts the bio sent to the snapshot device.
S10, the kernel layer judges whether the bio sent to the snapshot equipment is a read request bio, and if so, a third judgment step is executed; if not, the process is ended.
To facilitate understanding, in particular, an example of operation is provided: the intercepted bio points to a data block address of sector, a copy block of 4MB, a data block size of 4KB, and the calculated copy block address is copy _ sector, which is the same as the calculation method in step S5. And finding the corresponding record of the copy block in the Bitmap, reading the zone bit of the record and judging whether the copy record exists.
S11, according to the modified Bitmap file, the kernel layer judges whether the copy block where the bio sent to the snapshot device is located has a copy record, and if so, the steps S12 to S14 are executed; and if not, sending the bio sent to the snapshot device to the source block device.
S12, according to the bio sent to the snapshot device and the modified Bitmap file, obtaining a copy destination address of a data block, wherein the data block is the data block pointed by the bio sent to the snapshot device.
And S13, the kernel layer modifies the source address of the data block pointed by the bio sent to the snapshot equipment into the copy destination address of the data block.
S14, the bio sent to the snapshot device is forwarded to the source block device.
Through steps 9 to 14, the embodiment can effectively extract snapshot data, which is beneficial to realizing the timed backup of files.
Optionally, as shown in fig. 4, the snapshot method further includes the steps of:
and S15, the user layer receives a snapshot deleting command.
S16, judging whether the deleted object exists or not, and if so, executing the deleted object name transferring step to a second deleting step; if not, the deletion is complete.
And S17, the user layer transmits the name of the deleted object to the kernel layer.
And S18, inquiring the snapshot equipment corresponding to the deleted object by the kernel layer according to the name of the deleted object, and deleting the deleted object from the kernel.
And S19, deleting the Bitmap file and the snapshot data file respectively corresponding to the deleted objects by the user layer.
According to the technical scheme, a user layer analyzes a snapshot creating or deleting command of a user and transmits the snapshot creating or deleting command to a universal block layer part, the universal block layer part creates or deletes snapshot equipment, and captures a universal block layer I/O (bio) request of snapshot source equipment and makes COW (chip on Board) after the snapshot equipment is created, so that the influence on the source block equipment is small, the data consistency is good, and the method can be used for making timed backup on files; meanwhile, the snapshot data is conveniently stored on the source block device, additional block devices do not need to be added, and the storage cost and the operation cost are saved.
Example two
In one embodiment, as shown in fig. 5, there is further provided a snapshot system of a Linux non-logical volume block device, the system including:
a basic information obtaining module 1001, configured to obtain basic information by a user layer, where the basic information includes a device number, a mount point, a device size, and a device start sector number of a source block device;
a file creating and basic information sending module 1002, configured to create a Bitmap file and a snapshot data file at a source block device mount point of a user layer, and send logic sector distribution of the Bitmap file, logic sector distribution of the snapshot data file, and the basic information to a kernel layer;
a preprocessing module 1003, configured to create, by a kernel layer, a filter located in a general block layer, create snapshot equipment, and initialize a Bitmap file according to the logical sector distribution of the Bitmap file and the basic information;
a first intercepting module 1004, configured to, when the source block device has an I/O request, intercept, by the kernel layer, a write request bio through the filter;
a calculating module 1005, configured to calculate, according to the distribution of the logical sectors of the snapshot data file and the intercepted write request bio, a destination address of copy block copy storage and a copy block address of a data block to which the write request bio points by a kernel layer;
a first judging module 1006, configured to judge, by the kernel layer, whether there is a copy record in the copy block according to the copy block address and the initialized Bitmap file, and if there is a copy record in the copy block, forward the intercepted write request bio to the source block device; if not, the data copy module 1008 and the first sending module 1009 are executed;
a data copy module 1008, configured to perform data reading and data writing on the source block device by the kernel layer according to the copy block address and the destination address of the copy storage;
a first sending module 1009, configured to forward the intercepted write request bio to the source block device by the kernel layer.
Optionally, as shown in fig. 6, the preprocessing module 1003 includes:
an entry function obtaining unit 10031, configured to, according to the basic information, obtain, by the kernel layer, an entry function of the generic block layer;
a filter creating unit 10032, configured to replace an entry function of the generic block layer with a filter function to create a filter;
a snapshot device chain creating unit 10033, configured to create a snapshot device chain by the kernel layer;
a snapshot device creating unit 10034, configured to create, in the kernel layer, a memory block device as a snapshot device, add the memory block device to the snapshot device chain, and complete the creation;
a Bitmap file initializing unit 10035, configured to initialize a Bitmap file according to the logical sector distribution of the Bitmap file and the basic information.
Optionally, as shown in fig. 5, the first determining module 1006 is configured to determine, according to the copy block address and the initialized Bitmap file, whether a copy record exists in the copy block by the kernel layer, and if so, forward the intercepted write request bio to the source block device; if not, the Bitmap file modifying module 1007 is executed first, and then the data copying module 1008 and the first sending module 1009 are executed;
a modified Bitmap file module 1007, configured to write back the destination address stored in the copy block copy to the initialized Bitmap file, to form a modified Bitmap file;
the snapshot system further comprises:
a second interception module 1010, configured to intercept, by the kernel layer, a bio sent to the snapshot device;
a second determining module 1011, configured to determine, by the kernel layer, the type of the bio sent to the snapshot device, and if the bio sent to the snapshot device is a read request bio, execute a third determining module 1012; if the write request bio is received, ending;
a third determining module 1012, configured to determine, according to the modified Bitmap file, whether a copy record exists in a copy block where the bio sent to the snapshot device is located by the kernel layer, and if so, execute the address obtaining module 1013 to the second sending module 1015; if not, sending the bio sent to the snapshot device to the source block device;
an address obtaining module 1013, configured to obtain a copy destination address of a data block according to the bio sent to the snapshot device and the modified Bitmap file, where the data block is a data block pointed by the bio sent to the snapshot device;
an address modification module 1014, configured to modify, by the kernel layer, the source address of the bio-pointed data block sent to the snapshot device to a copy destination address of the data block;
a second sending module 1015, configured to forward the bio sent to the snapshot device to the source block device.
Optionally, as shown in fig. 5, the snapshot system further includes:
a delete command receiving module 1016, configured to receive a delete snapshot command by the user layer;
a fourth determining module 1017, configured to determine whether the deleted object exists, and if so, execute the deleted object name transferring module 1018 to the second deleting module; if not, the deletion is completed;
a deleted object name transfer module 1018 for the user layer to transfer the name of the deleted object to the kernel layer;
a first deleting module 1019, configured to query, by the kernel layer, the snapshot device corresponding to the deleted object according to the name of the deleted object, and delete the deleted object from the kernel;
a second deleting module 1020, configured to delete, by the user layer, the Bitmap file and the snapshot data file corresponding to the deleted objects respectively.
In the technical scheme of this embodiment, the file creating and basic information sending module 1002 is configured to create a Bitmap file and a snapshot data file, and send the logical sector distribution and the basic information of the Bitmap file and the snapshot data file to the kernel layer; the preprocessing module 1003 is used for the kernel layer to create a filter located in the general block layer, create snapshot equipment and initialize a Bitmap file; a first intercepting module 1004, configured to, when the source block device has an I/O request, intercept, by the kernel layer, a write request bio through the filter; a calculating module 1005, configured to calculate, by the kernel layer, a destination address of copy block copy storage and a copy block address of a data block pointed by the write request bio; a first judging module 1006, configured to judge, by the kernel layer, whether the copy block has a copy record; a data copy module 1008, configured to perform data reading and data writing on the source block device by the kernel layer; a first sending module 1009, configured to forward the intercepted write request bio to the source block device by the kernel layer. The system can correctly create and delete the snapshot, has the lowest influence on the newly added write performance of the snapshot source device lower than 10%, and has smaller influence on the newly added write of the source block device.
In the following, we provide a set of comparative experiments to further illustrate the present example, as follows:
the experimental environment of this experiment is shown in table 1, all experiments are performed in a virtualized environment, data is written into a file on a block device in a direct I/O manner, the size of a single I/O block file is 4KB, wherein the block device 1 is named as/dev/sdb 1, the block device is a non-logical volume block device, and the mount point is/sdb 1. The block device 2 is named as/dev/sdc 1 and is a logical volume block device, and the logical volume is/dev/vg _1/lv _ test. The comparative example also has open source software dattobd.
(1) Conformance testing
In the experiment, a 1GB file test _1G is created under a mount point/sdb 1 directory before a snapshot is created on the block device/dev/sdb 1, and the MD5 of the file is calculated. After creating a snapshot for/dev/sdb 1, modifying the test _1G file, and then hanging the generated snapshot device/dev/sdb 1-snap 1 under the/snap directory, and calculating the MD5 of the test _1G file under the/snap directory. The MD5 record is shown in table 2.
Table 2 document MD5 table
| Filename | MD5 value |
| /sdb1/test_1G | b2e0c41ec875aec1ec538935590c3c7b |
| /snap/test_1G | b2e0c41ec875aec1ec538935590c3c7b |
As can be seen from table 2, the MD5 value of the test _1G file in the snapshot device/dev/sdb 1-snapshot1 after creating the snapshot for/dev/sdb 1 is consistent with the MD5 value of the test _1G file in the snapshot source device before the snapshot, which indicates that the file content in the snapshot device is consistent with the file content before the snapshot source device snapshot, and further proves that the non-logical volume block device snapshot created by the present system can ensure data consistency.
(2) Single-snapshot newly-added write rate and loss test
In the experiment, 1 snapshot is created by using the system and the dattobd respectively for the block device/dev/sdb 1, then a 1GB file is newly added and written into the snapshot, 1 snapshot is created for the logical volume/dev/vg _1/lv _ test, then the 1GB file is newly added and written into the snapshot, the newly added writing rate of the snapshot source device under the condition that the created snapshots of the block device/dev/sdb is existed is recorded, the rate loss is calculated, and the experiment result is shown in table 3.
TABLE 3 influence of snapshots under different systems on the new write rate
| System for controlling a power supply | 0 Snapshot write Rate (MB/s) | Single snapshot write rate (MB/s) | Rate loss (%) |
| The system | 20.25 | 18.86 | 6.68 |
| dattobd | 20.25 | 12.79 | 36.83 |
| Logical volume | 19.79 | 8.73 | 55.89 |
As can be seen from table 3, in the case of creating only one snapshot, the system has a new write rate loss of less than 7% for the snapshot source device, a rate loss of the open source software dattobd is greater than 35%, and a rate loss of the logical volume is greater than 55%. The system performs COW on a general block layer, performs COW on a dattobd and a logical volume respectively on a virtual file system layer and a logical volume management layer, and has higher levels in a Linux kernel than the general block layer, so that the I/O (input/output) disk drop rate of the general block layer is far higher than that of the upper layer, the system has good new write rate and lower loss rate on snapshot source equipment.
(3) Multi-snapshot new write rate and loss test
In the experiment, 6 snapshots are created for the block device/dev/sdb 1 and newly added write is performed, the size of a newly added write file is 1GB, the newly added write rate and the loss percentage of the snapshot source device under different numbers of snapshots are recorded to further measure the system performance, and the experiment result is shown in Table 4.
As can be seen from table 4, as the number of snapshots increases, the new write rate of the snapshot source device decreases, which is caused by the increase of the number of snapshots and the increase of the number of COW times, and belongs to normal attenuation. When the number of the snapshots is 1, the loss of the newly increased write rate is lower than 7%; when the number of the snapshots is 4, the loss of the newly added write rate is lower than 31 percent; when the number of snapshots is 6, the loss of the newly added write rate exceeds 50%. Therefore, when the number of snapshots is 1, the performance of the system is optimal, and when the number of snapshots is less than 5, the performance is good.
EXAMPLE III
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the snapshot method of the Linux non-logical volume block device of embodiment one.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A snapshot method of a Linux non-logical volume block device is characterized in that the snapshot method comprises the following steps:
a basic information acquisition step, wherein a user layer acquires basic information, wherein the basic information comprises the equipment number, the mounting point, the equipment size and the initial sector number of the source block equipment;
creating a Bitmap file and a snapshot data file under a source block device mounting point of a user layer, and sending the logic sector distribution of the Bitmap file, the logic sector distribution of the snapshot data file and the basic information to a kernel layer;
a preprocessing step, wherein a kernel layer creates a filter positioned in a general block layer, creates snapshot equipment and initializes the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information;
a first capturing step, wherein when the source block equipment has an I/O request, the kernel layer captures a write request bio through the filter;
calculating, namely calculating a destination address of copy block copy storage and a copy block address of a data block pointed by the write request bio by a kernel layer according to the distribution of the logic sectors of the snapshot data file and the intercepted write request bio;
a first judgment step, according to the copy block address and the initialized Bitmap file, the kernel layer judges whether the copy block has a copy record, if so, the intercepted write request bio is forwarded back to the source block device; if not, executing the data copying step and the first sending step;
a data copying step, namely, according to the copy block address and the destination address of the copy storage, the kernel layer reads and writes data from and into the source block device;
and a first sending step, wherein the kernel layer forwards the intercepted write request bio to the source block device.
2. The snapshot method of the Linux non-logical volume block device of claim 1, wherein the preprocessing step comprises:
an entry function obtaining step, in which the kernel layer obtains an entry function of the universal block layer according to the basic information;
a filter creating step, namely replacing an inlet function of the universal block layer with a filter function to create a filter;
creating a snapshot device chain, wherein a kernel layer creates the snapshot device chain;
creating a snapshot device, namely creating a memory block device as a snapshot device in a kernel layer, adding the memory block device to a snapshot device chain, and finishing creation;
and a Bitmap file initialization step, namely initializing the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information.
3. The snapshot method of the Linux non-logical volume block device of claim 1, wherein the data copying step comprises:
a data reading step, namely constructing a read request bio by the kernel layer according to the copy block address, and sending the constructed read request bio to the source block device;
and a data writing step, namely, according to the destination address of the copy block copy storage, the kernel layer constructs a write request bio and sends the constructed write request bio to the source block device.
4. The snapshot method of the Linux non-logical volume block device according to any one of claims 1 to 3, wherein the first determining step comprises: according to the copy block address and the initialized Bitmap file, the kernel layer judges whether the copy block has a copy record, and if so, the intercepted write request bio is forwarded back to the source block device; if not, firstly executing a step of modifying the Bitmap file, and then executing a step of copying the data and a first sending step;
modifying the Bitmap file, namely writing the destination address copied and stored by the copy block back to the initialized Bitmap file to form a modified Bitmap file;
the snapshot method further comprises the steps of:
a second interception step, the kernel layer intercepts the bio sent to the snapshot device;
a second judgment step, the kernel layer judges whether the bio sent to the snapshot device is a read request bio, if so, a third judgment step is executed; if not, ending;
a third judging step, according to the modified Bitmap file, the kernel layer judges whether the copy block where the bio sent to the snapshot device is located has a copy record, if so, the address obtaining step is executed to the second sending step; if not, sending the bio sent to the snapshot device to the source block device;
an address obtaining step, obtaining a copy destination address of a data block according to the bio sent to the snapshot device and the modified Bitmap file, wherein the data block is a data block pointed by the bio sent to the snapshot device;
modifying the address, namely modifying the source address of the data block pointed by the bio sent to the snapshot equipment into the copy destination address of the data block by the kernel layer;
and a second sending step, forwarding the bio sent to the snapshot device to the source block device.
5. The snapshot method of the Linux non-logical volume block device according to any one of claims 1 to 3, characterized in that the snapshot method further comprises the steps of:
a step of receiving a deletion command, in which a user layer receives a snapshot deletion command;
a fourth judgment step of judging whether the deleted object exists, if so, executing the deleted object name transmission step to the second deletion step; if not, the deletion is completed;
a deleted object name transmission step, wherein the user layer transmits the name of the deleted object to the kernel layer;
a first deletion step, wherein according to the name of the deleted object, the kernel layer inquires the snapshot equipment corresponding to the deleted object and deletes the deleted object from the kernel;
and in the second deleting step, the user layer deletes the Bitmap file and the snapshot data file corresponding to the deleted objects respectively.
6. A snapshot system of a Linux non-logical volume block device, the system comprising:
the basic information acquisition module is used for acquiring basic information by a user layer, wherein the basic information comprises the equipment number, the mounting point, the equipment size and the initial sector number of the source block equipment;
the file creating and basic information sending module is used for creating a Bitmap file and a snapshot data file under a source block device mounting point of a user layer and sending the logic sector distribution of the Bitmap file, the logic sector distribution of the snapshot data file and the basic information to the kernel layer;
the preprocessing module is used for the kernel layer to create a filter positioned in a general block layer, create snapshot equipment and initialize the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information;
the first intercepting module is used for intercepting the write request bio by the kernel layer through the filter when the source block device has the I/O request;
the calculation module is used for calculating a destination address of copy block copy storage and a copy block address of a data block pointed by the write request bio by a kernel layer according to the write request bio which is distributed and captured by the logic sector of the snapshot data file;
the first judgment module is used for judging whether the copy block has a copy record or not according to the copy block address and the initialized Bitmap file, and if so, forwarding the intercepted write request bio to the source block device; if not, executing the data copying module and the first sending module;
the data copying module is used for reading and writing data from and into the source block device by the kernel layer according to the copy block address and the destination address of the copy storage;
and the first sending module is used for forwarding the intercepted write request bio to the source block device by the kernel layer.
7. The snapshot system of the Linux non-logical volume block device of claim 6, wherein the preprocessing module comprises:
an entry function obtaining unit, configured to obtain, by the kernel layer, an entry function of the generic block layer according to the basic information;
the filter creating unit is used for replacing the inlet function of the universal block layer with a filtering function and creating a filter;
the snapshot device chain creating unit is used for creating a snapshot device chain by the kernel layer;
a snapshot device creating unit, configured to create, in the kernel layer, a memory block device as a snapshot device, add the memory block device to a snapshot device chain, and complete creation;
and the Bitmap file initialization unit is used for initializing the Bitmap file according to the logic sector distribution of the Bitmap file and the basic information.
8. The snapshot system of the Linux non-logical volume block device of claim 6, wherein the first determining module is configured to determine whether the copy block has a copy record according to the copy block address and the initialized Bitmap file, and if so, forward the intercepted write request bio to the source block device; if not, firstly executing a Bitmap file modification module, and then executing a data copying module and a first sending module;
a modified Bitmap file module, configured to write back the destination address stored in the copy block copy to the initialized Bitmap file, so as to form a modified Bitmap file;
the snapshot system further comprises:
the second interception module is used for intercepting the bio sent to the snapshot device by the kernel layer;
the second judging module is used for judging the type of the bio sent to the snapshot device by the kernel layer, and if the bio sent to the snapshot device is a read request bio, executing the third judging module; if the write request bio is received, ending;
a third judging module, configured to, according to the modified Bitmap file, judge, by the kernel layer, whether a copy record exists in a copy block where the bio sent to the snapshot device is located, and if so, execute the address obtaining module to the second sending module; if not, sending the bio sent to the snapshot device to the source block device;
an address obtaining module, configured to obtain a copy destination address of a data block according to the bio sent to the snapshot device and the modified Bitmap file, where the data block is a data block pointed by the bio sent to the snapshot device;
the address modification module is used for modifying the source address of the data block pointed by the bio sent to the snapshot equipment into the copy destination address of the data block by the kernel layer;
and the second sending module is used for forwarding the bio sent to the snapshot device to the source block device.
9. The snapshot system of the Linux non-logical volume block device of claim 6, further comprising:
a deleting command receiving module used for receiving the deleting snapshot command by the user layer;
the fourth judging module is used for judging whether the deleted object exists or not, and if yes, the deleted object name transferring module is executed to the second deleting module; if not, the deletion is completed;
the deleted object name transmission module is used for transmitting the name of the deleted object to the kernel layer by the user layer;
the first deleting module is used for inquiring the snapshot equipment corresponding to the deleted object by the kernel layer according to the name of the deleted object and deleting the deleted object from the kernel;
and the second deleting module is used for deleting the Bitmap file and the corresponding snapshot data file which respectively correspond to the deleted objects by the user layer.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing a snapshot method for the Linux non-logical volume block device of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111126898.3A CN113568788B (en) | 2021-09-26 | 2021-09-26 | Snapshot method, system and storage medium for Linux non-logical volume block device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111126898.3A CN113568788B (en) | 2021-09-26 | 2021-09-26 | Snapshot method, system and storage medium for Linux non-logical volume block device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113568788A true CN113568788A (en) | 2021-10-29 |
| CN113568788B CN113568788B (en) | 2021-11-30 |
Family
ID=78174553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111126898.3A Active CN113568788B (en) | 2021-09-26 | 2021-09-26 | Snapshot method, system and storage medium for Linux non-logical volume block device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113568788B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115826878A (en) * | 2023-02-14 | 2023-03-21 | 浪潮电子信息产业股份有限公司 | Copy-on-write method, device, equipment and computer readable storage medium |
| CN117724905A (en) * | 2024-02-05 | 2024-03-19 | 成都云祺科技有限公司 | Real-time copying method, system and recovery method of file system under Linux |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105659213A (en) * | 2013-10-18 | 2016-06-08 | 日立数据***工程英国有限公司 | Target-driven independent data integrity and redundancy recovery in a shared-nothing distributed storage system |
| CN106844095A (en) * | 2016-12-27 | 2017-06-13 | 上海爱数信息技术股份有限公司 | File backup method, system and the client with the system |
| US20180039547A1 (en) * | 2013-03-14 | 2018-02-08 | EMC IP Holding Company LLC | Excluding files in a block based backup |
| CN108845891A (en) * | 2018-04-07 | 2018-11-20 | 长沙开雅电子科技有限公司 | It is a kind of novel based on the quick disaster recovery backup implementation method of snapshot realization |
| US10353780B1 (en) * | 2015-03-31 | 2019-07-16 | EMC IP Holding Company LLC | Incremental backup in a distributed block storage environment |
| CN110058959A (en) * | 2018-01-18 | 2019-07-26 | 伊姆西Ip控股有限责任公司 | Data back up method, equipment and computer program product |
| CN110837441A (en) * | 2019-11-14 | 2020-02-25 | 北京京航计算通讯研究所 | KVM virtual machine backup method based on dirty data bitmap and network block equipment |
| CN111158955A (en) * | 2019-12-30 | 2020-05-15 | 航天壹进制(南京)数据科技有限公司 | High-availability system based on volume replication and multi-server data synchronization method |
| CN111552437A (en) * | 2020-04-22 | 2020-08-18 | 上海天玑科技股份有限公司 | Snapshot method and snapshot device applied to distributed storage system |
| CN111722962A (en) * | 2020-06-19 | 2020-09-29 | 艾索信息股份有限公司 | Storage system and method for CDP data |
| CN112380050A (en) * | 2020-10-22 | 2021-02-19 | 中科热备(北京)云计算技术有限公司 | Method for using snapshot in system backup |
| CN112527562A (en) * | 2020-12-15 | 2021-03-19 | 北京华胜天成科技股份有限公司 | Data backup method and device of distributed storage system and computer equipment |
-
2021
- 2021-09-26 CN CN202111126898.3A patent/CN113568788B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180039547A1 (en) * | 2013-03-14 | 2018-02-08 | EMC IP Holding Company LLC | Excluding files in a block based backup |
| CN105659213A (en) * | 2013-10-18 | 2016-06-08 | 日立数据***工程英国有限公司 | Target-driven independent data integrity and redundancy recovery in a shared-nothing distributed storage system |
| US10353780B1 (en) * | 2015-03-31 | 2019-07-16 | EMC IP Holding Company LLC | Incremental backup in a distributed block storage environment |
| CN106844095A (en) * | 2016-12-27 | 2017-06-13 | 上海爱数信息技术股份有限公司 | File backup method, system and the client with the system |
| CN110058959A (en) * | 2018-01-18 | 2019-07-26 | 伊姆西Ip控股有限责任公司 | Data back up method, equipment and computer program product |
| CN108845891A (en) * | 2018-04-07 | 2018-11-20 | 长沙开雅电子科技有限公司 | It is a kind of novel based on the quick disaster recovery backup implementation method of snapshot realization |
| CN110837441A (en) * | 2019-11-14 | 2020-02-25 | 北京京航计算通讯研究所 | KVM virtual machine backup method based on dirty data bitmap and network block equipment |
| CN111158955A (en) * | 2019-12-30 | 2020-05-15 | 航天壹进制(南京)数据科技有限公司 | High-availability system based on volume replication and multi-server data synchronization method |
| CN111552437A (en) * | 2020-04-22 | 2020-08-18 | 上海天玑科技股份有限公司 | Snapshot method and snapshot device applied to distributed storage system |
| CN111722962A (en) * | 2020-06-19 | 2020-09-29 | 艾索信息股份有限公司 | Storage system and method for CDP data |
| CN112380050A (en) * | 2020-10-22 | 2021-02-19 | 中科热备(北京)云计算技术有限公司 | Method for using snapshot in system backup |
| CN112527562A (en) * | 2020-12-15 | 2021-03-19 | 北京华胜天成科技股份有限公司 | Data backup method and device of distributed storage system and computer equipment |
Non-Patent Citations (4)
| Title |
|---|
| DY2903: ""数据保护与备份技术"", 《HTTPS://WWW.CNBLOGS.COM/DY2903/P/8449683.HTML》 * |
| JIANXIN LI: ""Towards an efficient snapshot approach for virtual machines in clouds"", 《INFORMATION SCIENCES》 * |
| 杨皓森: ""面向OpenStack/Ceph的虚拟机备份***研究"", 《计算机***应用》 * |
| 赵瑞君: ""基于网络的连续数据保护***设计与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115826878A (en) * | 2023-02-14 | 2023-03-21 | 浪潮电子信息产业股份有限公司 | Copy-on-write method, device, equipment and computer readable storage medium |
| CN117724905A (en) * | 2024-02-05 | 2024-03-19 | 成都云祺科技有限公司 | Real-time copying method, system and recovery method of file system under Linux |
| CN117724905B (en) * | 2024-02-05 | 2024-04-19 | 成都云祺科技有限公司 | Real-time copying method, system and recovery method of file system under Linux |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113568788B (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11068455B2 (en) | Mapper tree with super leaf nodes | |
| US10430286B2 (en) | Storage control device and storage system | |
| US8521949B2 (en) | Data deleting method and apparatus | |
| US7694087B2 (en) | Duplicate data storing system, duplicate data storing method, and duplicate data storing program for storage device | |
| US9501231B2 (en) | Storage system and storage control method | |
| US7725673B2 (en) | Storage apparatus for preventing falsification of data | |
| CN113568788B (en) | Snapshot method, system and storage medium for Linux non-logical volume block device | |
| US20100049754A1 (en) | Storage system and data management method | |
| JP5320557B2 (en) | Storage system | |
| CN107423233B (en) | Writable snapshot implementation method and device | |
| CN104360914A (en) | Incremental snapshot method and device | |
| KR20170010810A (en) | Method, device and user equipment for reading/writing data in nand flash | |
| CN111427514B (en) | View migration method and device | |
| CN110147296B (en) | Data processing method, device, equipment and readable storage medium | |
| US20160283148A1 (en) | Backup control device, backup control method, and recording medium | |
| US7152147B2 (en) | Storage control system and storage control method | |
| CN108431784A (en) | Access request processing method, device and computer system | |
| KR20090031102A (en) | Method and apparatus for formatting for a potable storage device | |
| US20100174880A1 (en) | Method for fast format of a fully allocated volume when copied from a space efficient volume | |
| US20150161009A1 (en) | Backup control device, backup control method, disk array apparatus, and storage medium | |
| US11436105B2 (en) | Data processing method and memory controller utilizing the same | |
| US20210303212A1 (en) | Data processing method and memory controller utilizing the same | |
| US11531474B1 (en) | Storage system and data replication method in storage system | |
| CN112597074B (en) | Data processing method and device | |
| CN114880277B (en) | Block device snapshot method, system and storage 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 |