CN104102554B - Data backup method and data backup device - Google Patents
Data backup method and data backup device Download PDFInfo
- Publication number
- CN104102554B CN104102554B CN201310117953.1A CN201310117953A CN104102554B CN 104102554 B CN104102554 B CN 104102554B CN 201310117953 A CN201310117953 A CN 201310117953A CN 104102554 B CN104102554 B CN 104102554B
- Authority
- CN
- China
- Prior art keywords
- data
- volume
- storage
- space
- storage volume
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 238000011084 recovery Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
Abstract
The embodiment of the invention provides a data backup method and a data backup device. The method is applied to storage equipment. The storage equipment comprises an original volume and a storage volume. The method comprises the following steps: writing-in request to the storage equipment is detected, wherein the writing-in request comprises first data written into the original volume; the storage equipment is judged to be at a working state; a time label is loaded on the first data to form second data; the writing-in request is redirected to the storage volume of the storage equipment; the second data is written into the storage volume; when the residual space of the storage volume is less than a pre-set space threshold value, at least one piece of second data is selected from the plurality of second data in the storage volume according to the sequence of the time label and is written into the original volume. When the storage equipment is at the working state and the writing-in request to the storage equipment is detected, the first data included in the writing-in request is loaded with the time label and then is written into the storage volume to form the second data, and the original volume of the storage equipment does not need to be subjected to writing operation; the writing performance is not reduced.
Description
Technical Field
The present invention relates to data management technologies, and in particular, to a data backup method and a data backup apparatus.
Background
With the development of information technology, users have made higher demands on the uninterrupted operation capability of information systems and information security in the face of emergencies, and disaster backup and data protection (recovery technology) become the focus of attention. Traditional disaster backup and recovery techniques can only resist physical damage to data, such as disk failure, file system damage, etc., while logical damage to data, such as the occurrence of erroneous data in a database or file, is overwhelmed. When system data is found to have errors, although a tape backup technology is adopted to recover to a nearest backup point through a plurality of backup points, a large amount of useful data is lost, the existing recovery technology essentially only has one backup point, namely the nearest backup point, and the same data logic errors necessarily exist in a copied data copy, so that the method cannot be applied to some occasions with high requirements on service continuity.
The existing disaster backup and recovery technology is limited in that only one or a few backup points with a relatively coarse time granularity are established, and no backup point is established for each change of data, Continuous Data Protection (CDP) aims to establish a backup point for each change of data, so as to realize lossless data recovery, and the definition of network Storage Industry Association (SNIA) on Continuous data protection is as follows: continuously tracking, capturing changes to the data and saving a log of changes to restore to any previous point in time. CDP technology has several key protection features: continuous backup, continuous capture of data changes, instant and instant recovery, greatly optimized recovery process, multipoint snapshot technology, instant availability of historical data and guarantee of continuous operation of the system. The CDP adopts an instant recovery technology and a refined data continuous capturing technology, the interval of data acquisition can be a continuous strategy and a snapshot based on time interval, the problem of the traditional recovery timeout is solved, and the instant availability is achieved. The system remote start-up technique of CDP ensures that system failure recovery capability is achieved when the data protection system is built.
Most manufacturers use a Copy-on-Write (COW) mode to implement CDP, a storage device receives a Write request to the storage device, a CDP module first puts the Write request into a waiting queue, starts a Copy process, copies a storage area pointed by the Write request onto a save volume, and then takes the Write request out of the waiting queue to cover the original storage area, so as to back up historical data.
The prior art has the problems that in the COW mode, the write performance of the storage device is greatly affected, especially in the case of continuous sequential write, IOPS and bandwidth consumption become 3 times of those in the case of no CDP start, COW directly causes the write performance to be reduced by about 70%, and even in a service operation environment, after the CDP module is added to the original RAID5 storage array, the front-end ORACLE database is significantly halted and even crashed in the access process.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a data backup method and a data backup apparatus, which are used to solve the defect that the write performance of the existing storage device supporting the COW mode is greatly reduced during the continuous write operation.
In order to solve the above technical problem, an embodiment of the present invention provides a data backup method, which is applied to a storage device, where the storage device includes a primary volume and a storage volume, and the method includes: detecting a write request to a storage device, wherein the write request comprises first data written to a primary volume; judging that the storage equipment is in a working state, and loading a time tag on the first data to form second data; redirecting the write request to a save volume of the storage device, and writing the second data into the save volume; when the remaining space of the storage volume is smaller than a set space threshold value, at least one second data is selected from the plurality of second data in the storage volume in the order of the time stamp and written to the primary volume.
In the method, redirecting the write request to the storage volume of the storage device further includes: and applying for a backup space in the storage volume, wherein the backup space comprises at least one meta-space with a first fixed granularity, and the capacity of the backup space is the sum of the capacities of all the meta-spaces and is larger than the size of the second data.
The method further comprises the following steps: and when the IO throughput of the primary volume is smaller than the flow threshold, searching third data associated with the second data from the primary volume, calling the third data into a backup space where the second data is located in the storage volume for completion, and forming a complete first effective data block in the backup space.
The method further comprises the following steps: and when the IO throughput of the primary volume is smaller than the flow threshold, searching fourth data associated with the second data from the storage volume, calling the fourth data into a backup space of the storage volume where the second data is located for completion, and forming a complete second effective data block in the backup space.
The method further comprises the following steps: when the IO throughput of the primary volume is smaller than the flow threshold value, searching fifth data associated with the second data from the primary volume, and searching sixth data associated with the second data from the storage volume; and calling the fifth data and the sixth data into a backup space where the second data is located in the storage volume for completion, and forming a complete third effective data block in the backup space.
The method further comprises the following steps: detecting a reading request to the storage device, redirecting the reading request to the storage volume, and reading second data in the storage volume; when reading the second data from the storage volume fails, redirecting the reading request to a primary volume of a storage device; the complete valid data block corresponding to the second data is read from the primary volume.
A data backup device is connected with a storage device, and comprises: a detection unit, configured to detect a write request to a storage device, where the write request includes first data written to a primary volume; the tag unit is used for judging that the storage equipment is in a working state and loading a time tag on the first data to form second data; the redirecting unit is used for redirecting the writing request to a storage volume of the storage device and writing the second data into the storage volume; and the interaction unit is used for selecting at least one second data from the plurality of second data in the storage volume according to the sequence of the time labels and writing the selected second data into the primary volume when the residual space of the storage volume is smaller than the set space threshold value.
The device further comprises: and the storage volume management unit is used for applying for a backup space in the storage volume, the backup space comprises at least one element space with a first fixed granularity, and the capacity of the backup space is the sum of the capacities of all the element spaces and is larger than the size of the second data.
The device further comprises: the effective data complementing unit is used for searching third data which is associated with the second data from the original volume when the IO throughput of the original volume is smaller than a flow threshold value, calling the third data into a backup space where the second data is located in the storage volume for complementing, and forming a complete first effective data block in the backup space; or when the IO throughput of the primary volume is smaller than the flow threshold, searching fourth data associated with the second data from the storage volume, calling the fourth data into a backup space of the storage volume where the second data is located for completion, and forming a complete second effective data block in the backup space; or when the IO throughput of the primary volume is smaller than the flow threshold, searching fifth data associated with the second data from the primary volume, and searching sixth data associated with the second data from the storage volume; and calling the fifth data and the sixth data into a backup space where the second data is located in the storage volume for completion, and forming a complete third effective data block in the backup space.
The device further comprises: the reading unit is used for detecting a reading request of the storage device, redirecting the reading request to the storage volume and reading a second data in the storage volume; when reading the second data from the storage volume fails, redirecting the reading request to a primary volume of a storage device; the complete valid data block corresponding to the second data is read from the primary volume.
The technical scheme of the invention has the following beneficial effects: when the storage device is in a working state, when a write-in request to the storage device is detected, the first data contained in the write-in request is loaded with a time tag and then written into the storage volume to form second data, the write operation is not required to be executed to the original volume of the storage device, the write performance is ensured not to be reduced, and because the remaining space of the storage volume is smaller than a set space threshold value, at least one second data is written into the original volume again, the storage device is ensured to be always capable of ensuring that the write performance is not reduced through redirection.
Drawings
FIG. 1 is a schematic diagram illustrating the operation of a data backup method;
FIG. 2 shows a schematic diagram of a ROW-CDP model of actual deployment;
FIG. 3 is a schematic diagram illustrating a completion process completing historical version data in a saveset;
FIG. 4 shows a schematic diagram of a mirrored deployment of storage devices.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides backup based on a given time point, and aims to solve the problem that the CDP in a copy-on-Write COW mode brings pressure on the Write performance of storage equipment.
An embodiment of the present invention provides a method for data backup, as shown in fig. 1, which is applied to a storage device, where the storage device includes a primary volume and a storage volume, and the method includes:
detecting a write request to a storage device, wherein the write request comprises first data written to a primary volume;
judging that the storage equipment is in a working state, and loading a time tag on the first data to form second data;
redirecting the write request to a save volume of the storage device, and writing the second data into the save volume;
when the remaining space of the storage volume is smaller than a set space threshold value, at least one second data is selected from the plurality of second data in the storage volume in the order of the time stamp and written to the primary volume.
By applying the provided technology, when the storage device is in a working state and a write request to the storage device is detected, the first data contained in the write request is written into the save volume after being loaded with the time tag to form second data, the write operation is not required to be executed to the original volume of the storage device, the write performance is ensured not to be reduced, and because the residual space of the save volume is smaller than the set space threshold value, at least one second data is written into the original volume again, the storage device is ensured to be always capable of ensuring that the write performance is not reduced through redirection.
The technology provided by the embodiment of the invention supports that the storage device adopts a redirection technology during writing, a plurality of second data in the storage volume are provided, and each second data has a time tag, so that the second data can be sequenced according to time. When the remaining space of the storage volume is smaller than the set space threshold, storing the oldest historical version data, namely one or more second data with the most advanced time, into the primary volume, so that the storage volume has more space to accept the write request subsequently, wherein the second data in the storage volume is also called the historical version data.
As shown in fig. 1, the write request is handled by an IO processing process/thread, and the IO processing process/thread receives the write request, where the write request includes first data written to the primary volume;
in order not to affect the writing performance, the writing request is redirected to a storage volume of the storage device, and second data is written into the storage volume, wherein the second data is formed by loading the time tag on the first data.
The embodiment of the invention provides backup based on a given time point, so when receiving a write-in request of a specified storage position in a storage volume, whether the specified storage position in the storage volume has history version data needs to be judged, if so, a time tag is printed to redirect the storage volume, otherwise, the storage volume is written into an original volume.
In an application scenario, at time T0, a first data needs to be written to the original volume, and thus a second data corresponding to the first data is formed by changing the designated storage location a of the storage volume, and if a write request for the designated storage location a is received again after time T0, it is first determined whether the second data exists in the storage volume, and if so, the earlier second data stored at time T0 needs to be overwritten with the new second data tagged with a time stamp; if no change has been made to the data in the specified storage location a since initialization, the write request only needs to write directly to the primary volume.
If there is again a write request to location A at time T1, the time stamp needs to be re-stamped. If there are any write requests to the location A between the two times (T0, T1), only the second data saved at time T0 is overwritten.
In a preferred embodiment, redirecting write requests to a storage volume of a storage device further comprises:
and applying for a backup space in the storage volume, wherein the backup space comprises at least one meta-space with a first fixed granularity, and the capacity of the backup space is larger than the size of the second data.
The second data (history version data) on the storage volume of the storage device is stored in a fixed granularity, so that disorder and disorder are avoided, the complexity and disorder of a metadata pointer are reduced, and the query efficiency is improved.
The ROW mode provides a technique for improving read performance on the basis of solving the problem of write performance.
Without loss of generality, the ROW mode adopts a 64KB granularity, if a certain write request includes 4KB of first data, and the second data corresponding to the 4KB of first data is usually also 4KB, a 64KB storage space is pre-allocated, and the 4KB of second data is written into the 64KB storage space and identifies corresponding valid bits, and at this time, only 4KB of valid data exists in the 64KB storage space. When the write request is less than 64KB, the storage volume will also pre-allocate 64KB of storage space, and similarly, when the write IO is greater than 64KB, the write IO request will be divided into N small write requests of 64KB in size.
The storage device receives a read request of 32KB for the storage space in the storage volume at a later time, at this time, a part of the second data located in 64KB is uncertain, the 32KB to be read may be located in the valid data area completely, may be located in the valid data area only partially, or is not located in the valid data area completely, the read size may also be various uncertain conditions such as 4KB, 8KB, etc., if the 32KB to be read is located in the valid data area completely, the complexity of the algorithm and the request response time are increased, and therefore, it is necessary to first complement the part of the data from the storage area of the second data or the original volume, and then perform the operation of the read request.
In a preferred embodiment, further comprising:
when the IO throughput of the primary volume is smaller than the flow threshold value, searching third data which is associated with the second data from the primary volume,
and calling the third data into a backup space where the second data is located in the storage volume for completion, and forming a complete first effective data block in the backup space.
Wherein the third data in the reel is earlier in time than the second data.
In a preferred embodiment, further comprising:
when the IO throughput of the primary volume is smaller than the flow threshold value, finding fourth data associated with the second data from the storage volume,
and calling the fourth data into a backup space where the second data is located in the storage volume for completion, and forming a complete second effective data block in the backup space.
Wherein the fourth data in the save volume is earlier in time than the second data.
In a preferred embodiment, further comprising:
when the IO throughput of the primary volume is smaller than the flow threshold value, searching fifth data associated with the second data from the primary volume, and searching sixth data associated with the second data from the storage volume;
and calling the fifth data and the sixth data into a backup space where the second data is located in the storage volume for completion, and forming a complete third effective data block in the backup space.
The fifth data in the original volume, the sixth data in the storage volume, is earlier in time than the second data.
In the process of writing data, whether the first data, the second data, the third data, the fourth data, or the fifth data and the sixth data are written, a bitmap is set at the start position of the backup space where the data are stored, a valid bit pointing to the valid data is marked in the bitmap, and an end character is set at the end position.
In an application scenario, to solve the influence on the read performance, the read-write request to the storage device is monitored, and when the IO throughput of the primary volume is smaller than the traffic threshold, a completion thread is started to complete all the non-valid data areas without influencing the primary volume performance, as shown in fig. 2, the method includes:
step 201, starting a completion process corresponding to the completion operation, as shown in fig. 3, where the completion process completes each second data (history version data) in the storage volume.
Step 202, inquiring a first valid data block of second data in the storage volume;
in step 203, it is queried whether an invalid data block exists after the first valid data block, which is passed to step 204, otherwise, it is passed to step 205.
Step 204, copying the process by the kernel, and executing specific completion operations, including:
finding third data from the primary roll that is associated with said second data,
or, finding fourth data associated with the second data from the save volume,
or, searching for fifth data associated with the existence of the second data from the original volume and searching for sixth data associated with the existence of the second data from a storage volume;
and calling the backup space where the second data in the storage volume is located for completion, and forming a complete effective data block in the backup space.
A bitmap is set at the start position of the backup space, in which the valid bits pointing to valid data blocks are marked, and an end symbol is set at the end position of the backup space.
Returning to step 202.
Step 205, the process ends after completion.
In a preferred embodiment, further comprising:
detecting a reading request to the storage device, redirecting the reading request to the storage volume, and reading second data in the storage volume;
when reading the second data from the storage volume fails, redirecting the reading request to a primary volume of a storage device;
the complete valid data block corresponding to the second data is read from the primary volume.
Detecting a reading request to a storage device, wherein the reading request requests to read a first data, searching and searching whether a corresponding position has a second data of the first data in a storage volume, and if so, redirecting the reading request to the storage volume; if not, the read request is redirected to the storage device's primary volume because: the storage volume does not have the second data corresponding to the first data from beginning to end, in other words, the first data is not modified since the initialization, so that the second data corresponding to the first data does not exist in the storage volume.
In an application scenario, the network backup storage device includes a primary volume and a CDP storage volume, and in actual deployment, as shown in fig. 4, a host of a service system performs mirror deployment on the storage device, and synchronizes data in a local volume to the network backup storage device in a mirror manner. The local volume and the primary volume are in a mirror image relationship, after deployment initialization is completed, the primary volume stores data which is the same as that in the local volume, the data version of the primary volume is the oldest, and the CDP storage volume stores all the initialized modified historical version data.
In order to reduce the influence on the reading performance of the storage device and the service system, a reading request is received, the reading request specifically requests to read one datum, the reading request is optimized at a logic level,
normally, the read request only reads to the local volume, which hardly affects the read performance of the business system,
when a local volume fails or data is recovered, the storage volume in the network backup storage device needs to be read, and since the completion process completes the historical version data corresponding to the data in the storage volume when the system is idle, the reading performance of the service system is hardly affected in the process of reading the storage volume, so that the continuous data protection function is realized under the condition that the reading and writing performance of the original service system is not affected to the maximum extent.
The at least one second data selected from the plurality of second data in the save volume according to the time tag sequence is written into the original volume, and the at least one second data is different second data corresponding to different first data and different versions of second data corresponding to the same first data. Since the embodiment of the present invention provides backup based on a given time point, for the same first data a, if the time T0 has backed up the second data a0 for it, if the time T1 is backed up again, the second data a1 is formed, and similarly, backup performed at the times T2 and T3 also forms different versions of the second data a2 and the second data a 3. And if and only if the residual space of the storage volume is not enough to store the historical version data, writing the oldest historical version data back to the primary volume and recycling the storage space.
The embodiment of the invention provides a data backup device, which is connected with a storage device, and comprises:
a detection unit, configured to detect a write request to a storage device, where the write request includes first data written to a primary volume;
the tag unit is used for judging that the storage equipment is in a working state and loading a time tag on the first data to form second data;
the redirecting unit is used for redirecting the writing request to a storage volume of the storage device and writing the second data into the storage volume;
and the interaction unit is used for selecting at least one second data from the plurality of second data in the storage volume according to the sequence of the time labels and writing the selected second data into the primary volume when the residual space of the storage volume is smaller than the set space threshold value.
In a preferred embodiment, the apparatus further comprises:
and the storage volume management unit is used for applying for a backup space in the storage volume, the backup space comprises at least one element space with a first fixed granularity, and the capacity of the backup space is the sum of the capacities of all the element spaces and is larger than the size of the second data.
In a preferred embodiment, the apparatus further comprises:
the effective data complementing unit is used for searching third data which is associated with the second data from the original volume when the IO throughput of the original volume is smaller than a flow threshold value, calling the third data into a backup space where the second data is located in the storage volume for complementing, and forming a complete first effective data block in the backup space;
or,
when the IO throughput of the primary volume is smaller than the flow threshold, searching fourth data associated with the second data from the storage volume, transferring the fourth data into a backup space of the storage volume where the second data is located for completion, and forming a complete second effective data block in the backup space;
or when the IO throughput of the primary volume is smaller than the flow threshold, searching fifth data associated with the second data from the primary volume, and searching sixth data associated with the second data from the storage volume; and calling the fifth data and the sixth data into a backup space where the second data is located in the storage volume for completion, and forming a complete third effective data block in the backup space.
In a preferred embodiment, the apparatus further comprises:
the reading unit is used for detecting a reading request of the storage device, redirecting the reading request to the storage volume and reading a second data in the storage volume;
when reading the second data from the storage volume fails, redirecting the reading request to a primary volume of a storage device;
the complete valid data block corresponding to the second data is read from the primary volume.
The advantages after adopting this scheme are: when the storage device is in a working state, when a write-in request to the storage device is detected, the first data contained in the write-in request is loaded with a time tag and then written into the storage volume to form second data, the write operation is not required to be executed to the original volume of the storage device, the write performance is ensured not to be reduced, and because the remaining space of the storage volume is smaller than a set space threshold value, at least one second data is written into the original volume again, the storage device is ensured to be always capable of ensuring that the write performance is not reduced through redirection.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. A method for backing up data, wherein the method is applied to a storage device, the storage device comprises a primary volume and a save volume, and the method comprises:
detecting a write request to a storage device, wherein the write request comprises first data written to a primary volume;
judging that the storage equipment is in a working state, and loading a time tag on the first data to form second data;
redirecting the write request to a save volume of the storage device, and writing the second data into the save volume;
when the remaining space of the storage volume is smaller than a set space threshold value, selecting at least one second data from the plurality of second data in the storage volume according to the sequence of the time labels and writing the selected second data into the primary volume;
and when the IO throughput of the primary volume is smaller than the flow threshold, searching third data associated with the second data from the primary volume, calling the third data into a backup space where the second data is located in the storage volume for completion, and forming a complete first effective data block in the backup space.
2. The method of claim 1, wherein redirecting the write request to a save volume of the storage device, further comprises:
and applying for a backup space in the storage volume, wherein the backup space comprises at least one meta-space with a first fixed granularity, and the capacity of the backup space is the sum of the capacities of all the meta-spaces and is larger than the size of the second data.
3. The method of claim 1, further comprising:
when the IO throughput of the primary volume is smaller than the flow threshold value, finding fourth data associated with the second data from the storage volume,
and calling the fourth data into a backup space where the second data is located in the storage volume for completion, and forming a complete second effective data block in the backup space.
4. The method of claim 1, further comprising:
when the IO throughput of the primary volume is smaller than the flow threshold value, searching fifth data associated with the second data from the primary volume, and searching sixth data associated with the second data from the storage volume;
and calling the fifth data and the sixth data into a backup space where the second data is located in the storage volume for completion, and forming a complete third effective data block in the backup space.
5. The method of claim 1, further comprising:
detecting a reading request to the storage device, redirecting the reading request to the storage volume, and reading second data in the storage volume;
when reading the second data from the storage volume fails, redirecting the reading request to a primary volume of a storage device;
the complete valid data block corresponding to the second data is read from the primary volume.
6. A data backup apparatus, connected to a storage device, the data backup apparatus comprising:
a detection unit, configured to detect a write request to a storage device, where the write request includes first data written to a primary volume;
the tag unit is used for judging that the storage equipment is in a working state and loading a time tag on the first data to form second data;
the redirecting unit is used for redirecting the writing request to a storage volume of the storage device and writing the second data into the storage volume;
the interaction unit is used for selecting at least one second data from the plurality of second data in the storage volume according to the sequence of the time labels and writing the selected second data into the original volume when the residual space of the storage volume is smaller than the set space threshold value;
and the effective data complementing unit is used for searching third data which is associated with the second data from the original volume when the IO throughput of the original volume is smaller than a flow threshold value, calling the third data into a backup space where the second data is located in the storage volume for complementing, and forming a complete first effective data block in the backup space.
7. The apparatus of claim 6, further comprising:
and the storage volume management unit is used for applying for a backup space in the storage volume, the backup space comprises at least one element space with a first fixed granularity, and the capacity of the backup space is the sum of the capacities of all the element spaces and is larger than the size of the second data.
8. The apparatus of claim 6, further comprising:
the valid data complementing unit is further configured to, when the IO throughput of the primary volume is smaller than the flow threshold, find fourth data associated with the second data from the storage volume, call the fourth data into a backup space in the storage volume where the second data is located, and complement the fourth data to form a complete second valid data block in the backup space;
or when the IO throughput of the primary volume is smaller than the flow threshold, searching fifth data associated with the second data from the primary volume, and searching sixth data associated with the second data from the storage volume; and calling the fifth data and the sixth data into a backup space where the second data is located in the storage volume for completion, and forming a complete third effective data block in the backup space.
9. The apparatus of claim 6, further comprising:
the reading unit is used for detecting a reading request of the storage device, redirecting the reading request to the storage volume and reading a second data in the storage volume;
when reading the second data from the storage volume fails, redirecting the reading request to a primary volume of a storage device;
the complete valid data block corresponding to the second data is read from the primary volume.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117953.1A CN104102554B (en) | 2013-04-07 | 2013-04-07 | Data backup method and data backup device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117953.1A CN104102554B (en) | 2013-04-07 | 2013-04-07 | Data backup method and data backup device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104102554A CN104102554A (en) | 2014-10-15 |
| CN104102554B true CN104102554B (en) | 2017-05-03 |
Family
ID=51670725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310117953.1A Active CN104102554B (en) | 2013-04-07 | 2013-04-07 | Data backup method and data backup device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104102554B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107608623B (en) * | 2016-07-11 | 2021-08-31 | 中兴通讯股份有限公司 | Asynchronous remote copying method, device and system |
| CN107329698B (en) * | 2017-06-29 | 2020-08-11 | 杭州宏杉科技股份有限公司 | Data protection method and storage device |
| CN111338843B (en) * | 2018-12-19 | 2023-08-15 | 中国移动通信集团云南有限公司 | Data backup method and device for production system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329642A (en) * | 2008-06-11 | 2008-12-24 | 华中科技大学 | Method for protecting and recovering continuous data based on time stick diary memory |
| CN101430657A (en) * | 2008-11-17 | 2009-05-13 | 华中科技大学 | Continuous data protection method |
| CN101667161A (en) * | 2008-09-02 | 2010-03-10 | 联想(北京)有限公司 | Method and device for protecting data of storage device and computer system |
| CN102096615A (en) * | 2011-01-25 | 2011-06-15 | 上海爱数软件有限公司 | Remote incremental backup method and system |
-
2013
- 2013-04-07 CN CN201310117953.1A patent/CN104102554B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329642A (en) * | 2008-06-11 | 2008-12-24 | 华中科技大学 | Method for protecting and recovering continuous data based on time stick diary memory |
| CN101667161A (en) * | 2008-09-02 | 2010-03-10 | 联想(北京)有限公司 | Method and device for protecting data of storage device and computer system |
| CN101430657A (en) * | 2008-11-17 | 2009-05-13 | 华中科技大学 | Continuous data protection method |
| CN102096615A (en) * | 2011-01-25 | 2011-06-15 | 上海爱数软件有限公司 | Remote incremental backup method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104102554A (en) | 2014-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7860836B1 (en) | Method and apparatus to recover data in a continuous data protection environment using a journal | |
| CN102024044B (en) | Distributed file system | |
| RU2596585C2 (en) | Method for sending data, data receiving method and data storage device | |
| US7966463B2 (en) | Asynchronous remote copy system and control method for the same | |
| CN101535961B (en) | Apparatus, system, and method for detection of mismatches in continuous remote copy using metadata | |
| CN104969168A (en) | Persistent storage device with NVRAM for staging writes | |
| CN100426247C (en) | Data recovery method | |
| CN109614276B (en) | Fault processing method and device, distributed storage system and storage medium | |
| US7395378B1 (en) | System and method for updating a copy-on-write snapshot based on a dirty region log | |
| US10303560B2 (en) | Systems and methods for eliminating write-hole problems on parity-based storage resources during an unexpected power loss | |
| US8260752B1 (en) | Systems and methods for change tracking with multiple backup jobs | |
| CN103516736A (en) | Data recovery method of distributed cache system and a data recovery device of distributed cache system | |
| CN102402471A (en) | Method and system for backing up data in real time based on snapshot function of memory array | |
| CN109656895B (en) | Distributed storage system, data writing method, device and storage medium | |
| CN101243446A (en) | Online page restore from a database mirror | |
| CN105144113A (en) | Recovery of application from snapshot | |
| CN103221925A (en) | Data processing method and storage equipment | |
| US7900003B2 (en) | System, method and computer program product for storing an information block | |
| WO2016095372A1 (en) | Method and apparatus for realizing image backup of transaction logs | |
| US20220179472A1 (en) | Managing ephemeral storage on a computing node | |
| WO2014075586A1 (en) | Method and device for automatically recovering storage of jbod array | |
| CN104102554B (en) | Data backup method and data backup device | |
| US11093339B2 (en) | Storage utilizing a distributed cache chain and a checkpoint drive in response to a data drive corruption | |
| CN110134551B (en) | Continuous data protection method and device | |
| CN109582497B (en) | Rapid emergency starting method based on dynamic data increment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 12 building, 1038 International Venture Center, Jincheng Road, Xiaoshan District, Zhejiang, Hangzhou, 311202 Applicant after: Hangzhou Xinhe Data Technology Co.,Ltd. Address before: 12 building, 1038 International Venture Center, Jincheng Road, Xiaoshan District, Zhejiang, Hangzhou, 311202 Applicant before: Hangzhou Xinhe Data Technology Co.,Ltd. |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A data backup method and data backup device Effective date of registration: 20200807 Granted publication date: 20170503 Pledgee: Hangzhou High-tech Financing Guarantee Co.,Ltd. Pledgor: Hangzhou Xinhe Data Technology Co.,Ltd. Registration number: Y2020330000602 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20210926 Granted publication date: 20170503 Pledgee: Hangzhou High-tech Financing Guarantee Co.,Ltd. Pledgor: Hangzhou Xinhe Data Technology Co.,Ltd. Registration number: Y2020330000602 |