CN108121497B - Storage method and storage system - Google Patents
Storage method and storage system Download PDFInfo
- Publication number
- CN108121497B CN108121497B CN201611066907.3A CN201611066907A CN108121497B CN 108121497 B CN108121497 B CN 108121497B CN 201611066907 A CN201611066907 A CN 201611066907A CN 108121497 B CN108121497 B CN 108121497B
- Authority
- CN
- China
- Prior art keywords
- disk
- physical
- physical disk
- virtual
- matrix
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0619—Improving the reliability of storage systems in relation to data integrity, e.g. data losses, bit errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
- G06F3/0664—Virtualisation aspects at device level, e.g. emulation of a storage device or system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0689—Disk arrays, e.g. RAID, JBOD
Abstract
The invention discloses a storage method and a storage system, and relates to the technical field of computer storage. In the invention, the physical disks belonging to different servers in the storage cluster can be managed in a unified way through the virtual disks, a mode of randomly selecting the virtual disks is adopted when the objects are stored, and the physical disks corresponding to the virtual disks are also randomly selected, so that all the servers have equal opportunity to write data, the data are uniformly stored on all the servers, the load balance of all the servers is ensured, the effective management of the disks in the storage cluster is realized, in addition, because different copies of the same object are stored on different servers, the problem that the copies of some objects are completely lost and cannot be recovered due to the damage of some server can be avoided.
Description
Technical Field
The present invention relates to the field of computer storage technologies, and in particular, to a storage method and a storage system.
Background
The object storage is a cloud storage service with high mass, elasticity, availability and cost performance. In an object storage system, data is typically stored in multiple copies on different disks.
For a storage cluster with a certain scale, how to manage the disks in the cluster has a crucial influence on the reliability of data, the performance of the whole system and the operation cost.
Disclosure of Invention
One object to be achieved by the present invention is: a new storage method is provided to effectively manage the disks in the storage cluster.
According to an aspect of the present invention, there is provided a storage method, including: randomly selecting a virtual disk from a disk matrix for a storage object to be written; respectively writing each copy of the storage object to be written into each physical disk corresponding to the virtual disk; and each physical disk corresponding to the same virtual disk is randomly selected from the physical disks of each server in the storage cluster.
In one embodiment, the method further comprises: counting each position of a failed physical disk in a disk matrix; randomly selecting a substitute physical disk from the storage cluster for the fault physical disk at each position, wherein the substitute physical disk at each position and a normal physical disk corresponding to a virtual disk to which the fault physical disk at the position belongs belong to different physical disks; and restoring the copy of the storage object corresponding to the virtual disk to which the failure physical disk of each position belongs to the substitute physical disk of the position.
In one embodiment, the method further comprises: selecting the physical disk with the most occurrence times in each row of the disk matrix to determine as a high-frequency physical disk; and replacing the high-frequency physical disk with a new physical disk according to a preset proportion.
In one embodiment, replacing the high frequency physical disk with the new physical disk according to the preset ratio includes: selecting a replacement position of a high-frequency physical disk in each column of the disk matrix according to a preset proportion; and restoring the copy of the storage object corresponding to the high-frequency physical disk at the replacement position to the new physical disk.
In one embodiment, the method further comprises: determining the number of rows and columns of a disk matrix, and setting a virtual disk in each row; randomly selecting a physical disk from a storage cluster for each virtual disk, and putting the physical disk into a row of the virtual disk; and establishing the corresponding relation between each physical disk of each row and the virtual disk of the row to form a disk matrix.
According to another aspect of the present invention, there is provided a storage system including: the virtual disk selecting module is used for randomly selecting a virtual disk from the disk matrix for the storage object to be written; the copy writing module is used for respectively writing each copy of the storage object to be written into each physical disk corresponding to the virtual disk; and each physical disk corresponding to the same virtual disk is randomly selected from the physical disks of each server in the storage cluster.
In one embodiment, the system further comprises: and the failed disk replacement module is used for counting the positions of the failed physical disks in the disk matrix, randomly selecting a substitute physical disk from the storage cluster for the failed physical disk of each position, wherein the substitute physical disk of each position and the normal physical disk corresponding to the virtual disk to which the failed physical disk of the position belongs belong to different physical disks, and restoring the copy of the storage object corresponding to the virtual disk to which the failed physical disk of each position belongs to the substitute physical disk of the position.
In one embodiment, the system further comprises: and the new disk online module is used for selecting the physical disk with the largest occurrence frequency in each row of the disk matrix to be determined as the high-frequency physical disk, and replacing the high-frequency physical disk with the new physical disk according to a preset proportion.
In an embodiment, the new online disk module is configured to select a replacement position of the high-frequency physical disk in each column of the disk matrix according to a preset ratio, and restore the copy of the storage object corresponding to the replacement position of the high-frequency physical disk to the new physical disk.
In one embodiment, the system further comprises: and the disk matrix construction module is used for determining the number of rows and the number of columns of the disk matrix, setting a virtual disk in each row, randomly selecting a physical disk from the storage cluster for each virtual disk, putting the physical disk into the column of the row in which the virtual disk is positioned, and establishing the corresponding relation between each physical disk in each row and the virtual disk in the row so as to form the disk matrix.
In the invention, the physical disks belonging to different servers in the storage cluster can be managed in a unified way through the virtual disks, a mode of randomly selecting the virtual disks is adopted when the objects are stored, and the physical disks corresponding to the virtual disks are also randomly selected, so that all the servers have equal opportunity to write data, the data are uniformly stored on all the servers, the load balance of all the servers is ensured, the effective management of the disks in the storage cluster is realized, in addition, because different copies of the same object are stored on different servers, the problem that the copies of some objects are completely lost and cannot be recovered due to the damage of some server can be avoided.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 shows a flow diagram of a storage method according to an embodiment of the invention.
Fig. 2 shows a schematic flow chart of a storage method according to another embodiment of the present invention.
Fig. 3 shows a flow chart of a storage method according to another embodiment of the invention.
Fig. 4 shows a schematic structural diagram of a storage system according to an embodiment of the present invention.
Fig. 5 shows a schematic structural diagram of a memory system according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a new storage method, which can realize effective management of disks in a storage cluster.
The storage method of the present invention is described below with reference to fig. 1.
FIG. 1 is a flow chart of one embodiment of a storage method of the present invention. As shown in fig. 1, the method of this embodiment includes:
step S102, a virtual disk is randomly selected from the disk matrix for the storage object to be written.
The disk matrix is arranged to facilitate management of each physical disk in the storage cluster, and the physical disks included in the virtual disk and the storage objects corresponding to each physical disk belonging to the same virtual disk can be more intuitively represented in the form of the matrix. One form of a disk matrix is shown, for example, in table 1, where each row represents a different physical disk corresponding to the same virtual disk.
| Virtual disk | Column 1 | Column 2 | Column 3 | …… |
| Virtual disk 0 | Physical disk 1 | Physical disk 2 | Physical disk 3 | …… |
| Virtual disk 1 | Physical disk 2 | Physical disk 3 | Physical disk 1 | …… |
| Virtual disk 2 | Physical disk 3 | Physical disk 2 | Physical disk 1 | …… |
| …… | …… | …… | …… | …… |
TABLE 1
The disk matrix can be constructed by the following method: determining the number of rows and columns of the disk matrix, setting a virtual disk in each row, randomly selecting a physical disk from a storage cluster for each virtual disk, putting the physical disk into the column of the row in which the virtual disk is positioned, and establishing a corresponding relation between each physical disk in each row and the virtual disk in the row to form the disk matrix. The number of columns of the disk matrix can be determined according to the number of copies of the storage object, and the number of virtual disks, that is, the number of rows of the disk matrix, is determined according to the storage capacity of each physical disk and the number of physical disks. After the number of rows and the number of columns are determined, one physical disk of the storage cluster is randomly selected at each position and placed at the position, and each physical disk in the same row of the disk matrix is ensured not to be repeated, so that the physical disks corresponding to the same virtual disk belong to different servers at a high probability, meanwhile, multiple copies of the same storage object cannot be stored on one physical disk, and when one physical disk is damaged, one copy of the storage object is lost at most.
Step S104, respectively writing each copy of the storage object to be written into each physical disk corresponding to the virtual disk.
And each physical disk corresponding to the same virtual disk is randomly selected from the physical disks of each server in the storage cluster.
After each storage object is written into the virtual disk, the mapping relationship between the storage object and the virtual disk is established, and further the physical disk where the storage object is located can be obtained more simply and rapidly through the disk matrix.
One application example of the above method: 3 copies of an object need to be stored, and a virtual disk 2 is randomly selected from table 1, then the first copy of the object is written into the physical disk 3, the second copy is written into the physical disk 2, and the third copy is written into the physical disk 1.
According to the method of the embodiment, the physical disks belonging to different servers in the storage cluster can be uniformly managed through the virtual disks, a mode of randomly selecting the virtual disks is adopted when the objects are stored, and the physical disks corresponding to the virtual disks are also randomly selected, so that all the servers have equal chances to be written with data, the data are uniformly stored on all the servers, the load balance of all the servers is ensured, the effective management of the disks in the storage cluster is realized, and the problem that all copies of some objects are lost and cannot be recovered due to the damage of some servers can be avoided.
In the prior art, when a disk of a certain server is damaged, data is restored to other physical disks of the same server. The recovered data are concentrated on one server, so that the available space of a physical disk on some servers is obviously lower than that of other servers, and the effective space of the whole cluster is reduced by times. In addition, this approach may result in a high load on a single server when data is recovered. In order to solve this problem, the present invention further provides a processing scheme for a failed physical disk, which is described below with reference to fig. 2.
FIG. 2 is a flow chart of another embodiment of the storage method of the present invention. As shown in fig. 2, the method of the present invention further comprises after step S104:
step S206, counting each position of the fault physical disk in the disk matrix.
By determining the position of the failed physical disk in the disk matrix, the virtual disk to which the failed physical disk belongs can be determined, and further, the object stored by the failed physical disk is determined.
Step S208, randomly selecting a substitute physical disk from the storage cluster for the failed physical disk at each location.
The replacement disk at each position and the normal physical disk corresponding to the virtual disk to which the failed physical disk at the position belongs belong to different physical disks, that is, the replacement disk cannot be repeated with other disks in the same row after being placed in the disk matrix.
Step S210, restoring the copy of the storage object corresponding to the virtual disk to which the failed physical disk at each location belongs to the substitute physical disk at the location.
For a failed physical disk, the failed physical disk appears in a plurality of different positions in a disk matrix, the storage objects corresponding to each position are different, and the selected substitute physical disk is also a plurality of, that is, the stored contents of the failed physical disk are respectively restored to different substitute physical disks, because the substitute physical disks are randomly selected and belong to different servers at a high probability, the stored contents of the failed physical disk are respectively restored to different servers. During recovery, copies of storage objects corresponding to other normal disks in the virtual disk, which belong to the same virtual disk as the failed physical disk, that is, which are located in the same row of the disk matrix, can be recovered to the substitute physical disk.
An application example of the above method is described below with reference to tables 2 and 3.
The storage cluster includes 10 servers, each having 60 disks. The cluster uses a three-copy mode to store objects, setting the disk matrix to 3 columns, 6000 rows. The constructed disk matrix is shown in table 2.
TABLE 2
In the subsequent operation process, the physical disk 1 fails, and at this time, a replacement process of the failed disk needs to be executed. Comparing table 2 with table 3, in column 1, the physical disk 1 in the virtual disk 0 is replaced by the randomly selected physical disk 78, and the copy of the storage object corresponding to the physical disk 2 or 3 in the virtual disk 0 can be restored to the physical disk 78; the physical disk 1 in the virtual disk 3 is replaced by the randomly selected physical disk 2, and the copy of the physical disk 622 or 124 in the storage object corresponding to the virtual disk 3 can be restored to the physical disk 2; the physical disk 1 in the virtual disk 4 is replaced by the randomly selected physical disk 181, the copy of the storage object corresponding to the row of the physical disk 8 or 99 may be restored to the physical disk 2, and similarly, the physical disks 1 in the 2 nd column and the 3 rd column are replaced by the same method.
| Virtual disk | Column 1 | Column 2 | Column 3 |
| Virtual disk 0 | Physical disk 78 | Physical disk 2 | Physical disk 3 |
| VirtualizationMagnetic disk 1 | Physical disk 2 | Physical disk 3 | Physical disk 99 |
| Virtual disk 2 | Physical disk 3 | Physical disk 2 | Physical disk 127 |
| Virtual disk 3 | Physical disk 2 | Physical disk 62 | Physical disk 124 |
| Virtual disk 4 | Physical disk 181 | Physical disk 8 | Physical disk 99 |
| Virtual disk 5 | Physical disk 544 | Physical disk 4 | Physical disk 58 |
| …… | …… | …… | …… |
TABLE 3
According to the method, the plurality of alternative physical disks are randomly selected from the storage cluster to replace the failed physical disk, the content stored by the failed physical disk is respectively restored to the plurality of alternative physical disks, the alternative physical disks are randomly selected, the probability that each server is selected is equal, the load balance of each server during data restoration is guaranteed, and the phenomenon that the load of the disk on a single server is too high is avoided. In addition, since the other physical disks in the virtual disk corresponding to the replaced physical disk and the failed physical disk are different, when one disk is damaged, at most one copy of one object is lost.
After the failed physical disk is offline, a new physical disk is added to the storage cluster, and the new physical disk online process of the present invention is described below with reference to fig. 3.
FIG. 3 is a flow chart of another embodiment of the storage method of the present invention. As shown in fig. 3, after step S210, the method of the present invention further comprises:
in step S312, the physical disk with the largest occurrence frequency in each column of the disk matrix is selected and determined as the high-frequency physical disk.
When a disk matrix is constructed, all physical disks are uniformly distributed in all columns, and the times of occurrence of some physical disks in the disk matrix are increased due to the fact that failed physical disks are replaced, and further the load of the physical disks is heavier, so that the load balance of all the disks can be guaranteed by selecting the physical disks with higher occurrence frequency for replacement.
And step S314, replacing the high-frequency physical disk with a new physical disk according to a preset proportion.
Specifically, a replacement position of the high-frequency physical disk is selected in each column of the disk matrix according to a preset proportion, and a copy of a storage object corresponding to the high-frequency physical disk at the replacement position is restored to the new physical disk. For example, starting from the first position where each column of high-frequency physical disks appears, new disks are sequentially used for replacement until the times of the high-frequency physical disks are equal to or differ by 1 from the new physical disks, the high-frequency physical disks in each column are replaced by the new physical disks, and if a plurality of new physical disks exist, the disks in the disk matrix are replaced once by each new physical disk according to the steps.
An application example of the above method is described below with reference to tables 3 and 4. The new physical disk is 601, as shown in table 4, the number of occurrences of the physical disk 2 is the largest in column 1, so a preset proportion of the physical disks 2 in column 1 are replaced with the physical disks 601, and the number of occurrences of the physical disks 4 is the largest in column 2, so a preset proportion of the physical disks 4 in column 2 are replaced with the physical disks 601, and the number of occurrences of the physical disks 99 is the largest in column 3, but since the physical disks 2 belonging to the virtual disk 1 have been replaced with the physical disks 601, the physical disks 99 of the virtual disk 1 in column 3 cannot be replaced with the physical disks 601, and the physical disks 99 of other rows are selected for replacement.
| Virtual disk | Column 1 | Column 2 | Column 3 |
| Virtual disk 0 | Physical disk 78 | Physical disk 2 | Physical disk 3 |
| Virtual disk 1 | Physical disk 601 | Physical disk 3 | Physical disk 99 |
| Virtual disk 2 | Physical disk 3 | Physical disk 2 | Physical disk 127 |
| Virtual disk 3 | Physical disk 601 | Physical disk 62 | Physical disk 124 |
| Virtual disk 4 | Physical disk 181 | Physical disk 8 | Physical disk 601 |
| Virtual disk 5 | Physical disk 544 | Physical disk 601 | Physical disk 58 |
| …… | …… | …… | …… |
TABLE 4
In the method of the above embodiment, the new physical disk is used to replace the physical disk with the largest number of times of occurrence in each list in the disk matrix, so that the load of each disk can be more balanced, and in addition, because the other physical disks in the virtual disk corresponding to the replaced physical disk and the failed physical disk are different, when one disk is damaged, at most one copy of an object is lost.
The present invention also provides a storage system, described below in conjunction with FIG. 4.
FIG. 4 is a block diagram of one embodiment of a memory system of the present invention. As shown in fig. 4, the system 40 includes:
a virtual disk selecting module 402, configured to randomly select a virtual disk from the disk matrix for the storage object to be written.
A copy writing module 404, configured to write each copy of the storage object to be written into each physical disk corresponding to the virtual disk.
And each physical disk corresponding to the same virtual disk is randomly selected from the physical disks of each server in the storage cluster.
The storage system of the present invention can also implement the replacement of the failed physical disk and the online process of the new physical disk, which is described below with reference to fig. 5.
FIG. 5 is a block diagram of another embodiment of the memory system of the present invention. As shown in fig. 5, the system 40 further includes:
a failed disk replacement module 506, configured to count positions of the failed physical disk in the disk matrix, randomly select a replacement physical disk from the storage cluster for the failed physical disk at each position, where the replacement physical disk at each position and a normal physical disk corresponding to the virtual disk to which the failed physical disk at the position belongs belong to different physical disks, and restore the copy of the storage object corresponding to the virtual disk to which the failed physical disk at each position belongs to the replacement physical disk at the position.
In one embodiment, the storage system 40 further comprises: the new disk on-line module 508 is,
and selecting the physical disk with the most occurrence times in each column of the disk matrix to determine as the high-frequency physical disk, and replacing the high-frequency physical disk with a new physical disk according to a preset proportion.
Specifically, the new disk online module 508 is configured to select a replacement position of the high-frequency physical disk in each column of the disk matrix according to a preset ratio, and restore the copy of the storage object corresponding to the replacement position of the high-frequency physical disk to the new physical disk.
In one embodiment, the storage system 40 further comprises: the disk matrix constructing module 510 is configured to determine the number of rows and columns of the disk matrix, where each row is provided with one virtual disk, randomly select a physical disk from the storage cluster for each virtual disk, place the physical disk in the row where the virtual disk is located, and establish a corresponding relationship between each physical disk in each row and the virtual disk in the row, so as to form the disk matrix.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A storage method, comprising:
determining the number of rows and columns of a disk matrix, and setting a virtual disk in each row;
randomly selecting a physical disk from a storage cluster for each virtual disk, and putting the physical disk into a row of the virtual disk;
establishing a corresponding relation between each physical disk of each row and the virtual disk of the row to form the disk matrix;
randomly selecting a virtual disk from a disk matrix for a storage object to be written;
respectively writing each copy of the storage object to be written into each physical disk corresponding to the virtual disk;
and each physical disk corresponding to the same virtual disk is randomly selected from the physical disks of each server in the storage cluster.
2. The method of claim 1, further comprising:
counting each position of a failed physical disk in a disk matrix;
randomly selecting a substitute physical disk from the storage cluster for the fault physical disk at each position, wherein the substitute physical disk at each position and a normal physical disk corresponding to a virtual disk to which the fault physical disk at the position belongs belong to different physical disks;
and restoring the copy of the storage object corresponding to the virtual disk to which the failure physical disk of each position belongs to the substitute physical disk of the position.
3. The method of claim 1 or 2, further comprising:
selecting the physical disk with the most occurrence times in each row of the disk matrix to determine as a high-frequency physical disk;
and replacing the high-frequency physical disk with a new physical disk according to a preset proportion.
4. The method of claim 3,
the replacing the high-frequency physical disk with a new physical disk according to a preset proportion comprises:
selecting a replacement position of the high-frequency physical disk in each column of the disk matrix according to a preset proportion;
and restoring the copy of the storage object corresponding to the high-frequency physical disk at the replacement position to the new physical disk.
5. A storage system, comprising:
the disk matrix construction module is used for determining the number of rows and the number of columns of the disk matrix, each row is provided with a virtual disk, each virtual disk randomly selects a physical disk from a storage cluster to be placed in the row column of the virtual disk, and the corresponding relation between each physical disk in each row and the virtual disk in the row is established to form the disk matrix;
the virtual disk selecting module is used for randomly selecting a virtual disk from the disk matrix for the storage object to be written;
the copy writing module is used for respectively writing each copy of the storage object to be written into each physical disk corresponding to the virtual disk;
and each physical disk corresponding to the same virtual disk is randomly selected from the physical disks of each server in the storage cluster.
6. The system of claim 5, further comprising:
and the failed disk replacement module is used for counting the positions of the failed physical disks in the disk matrix, randomly selecting a substitute physical disk from the storage cluster for the failed physical disk of each position, wherein the substitute physical disk of each position and the normal physical disk corresponding to the virtual disk to which the failed physical disk of the position belongs belong to different physical disks, and restoring the copy of the storage object corresponding to the virtual disk to which the failed physical disk of each position belongs to the substitute physical disk of the position.
7. The system of claim 5 or 6, further comprising:
and the new disk online module is used for selecting the physical disk with the largest occurrence frequency in each row of the disk matrix to be determined as the high-frequency physical disk, and replacing the high-frequency physical disk with the new physical disk according to a preset proportion.
8. The system of claim 7,
and the new disk online module is used for selecting a replacement position of the high-frequency physical disk in each column of the disk matrix according to a preset proportion, and restoring the copy of the storage object corresponding to the replacement position of the high-frequency physical disk into the new physical disk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611066907.3A CN108121497B (en) | 2016-11-29 | 2016-11-29 | Storage method and storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611066907.3A CN108121497B (en) | 2016-11-29 | 2016-11-29 | Storage method and storage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108121497A CN108121497A (en) | 2018-06-05 |
| CN108121497B true CN108121497B (en) | 2021-04-30 |
Family
ID=62224104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611066907.3A Active CN108121497B (en) | 2016-11-29 | 2016-11-29 | Storage method and storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108121497B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111338559B (en) * | 2018-12-19 | 2023-11-10 | 深圳市茁壮网络股份有限公司 | Data processing method, user module, information management module and system |
| CN110795261B (en) * | 2019-09-26 | 2022-06-17 | 北京浪潮数据技术有限公司 | Virtual disk fault detection method and device |
| CN112000282A (en) * | 2020-08-07 | 2020-11-27 | 北京浪潮数据技术有限公司 | Storage double-live method, device and related components |
| CN113515233A (en) * | 2021-05-24 | 2021-10-19 | 锐捷网络股份有限公司 | Block group building method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101566931A (en) * | 2003-08-14 | 2009-10-28 | 克姆佩棱特科技公司 | Virtual disk drive system and method |
| CN101604226A (en) * | 2009-07-14 | 2009-12-16 | 浪潮电子信息产业股份有限公司 | A kind of method that makes up raising performance of storage system in dynamic buffering pond based on virtual RAID |
| CN104375784A (en) * | 2014-11-17 | 2015-02-25 | 浙江宇视科技有限公司 | Method and device for lowering complexity of virtual disk management |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136114B (en) * | 2011-11-30 | 2015-11-25 | 华为技术有限公司 | Storage means and memory storage |
-
2016
- 2016-11-29 CN CN201611066907.3A patent/CN108121497B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101566931A (en) * | 2003-08-14 | 2009-10-28 | 克姆佩棱特科技公司 | Virtual disk drive system and method |
| CN101604226A (en) * | 2009-07-14 | 2009-12-16 | 浪潮电子信息产业股份有限公司 | A kind of method that makes up raising performance of storage system in dynamic buffering pond based on virtual RAID |
| CN104375784A (en) * | 2014-11-17 | 2015-02-25 | 浙江宇视科技有限公司 | Method and device for lowering complexity of virtual disk management |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108121497A (en) | 2018-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107807794B (en) | Data storage method and device | |
| CN108121497B (en) | Storage method and storage system | |
| CN109725822B (en) | Method, apparatus and computer program product for managing a storage system | |
| US8417989B2 (en) | Method and system for extra redundancy in a raid system | |
| CN108052655B (en) | Data writing and reading method | |
| US11150823B2 (en) | Method, device and computer program product for splitting disk set | |
| US20090063807A1 (en) | Data redistribution in shared nothing architecture | |
| US20140164329A1 (en) | Dynamically Varying the Number of Database Replicas | |
| US10949314B2 (en) | Method and apparatus for failure recovery of storage device | |
| US11314426B2 (en) | Method, system, and apparatus for allocating hard disks to placement group, and storage medium | |
| US8954783B2 (en) | Two-tier failover service for data disaster recovery | |
| US10922201B2 (en) | Method and device of data rebuilding in storage system | |
| CN106293492B (en) | Storage management method and distributed file system | |
| US7100004B2 (en) | Method for scrubbing regions in central storage | |
| CN108540315A (en) | Distributed memory system, method and apparatus | |
| CN111488127B (en) | Data parallel storage method and device based on disk cluster and data reading method | |
| US20160253247A1 (en) | Method and device for restoring system file indexes | |
| CN115202589B (en) | Placement group member selection method, device and equipment and readable storage medium | |
| CN115756955A (en) | Data backup and data recovery method and device and computer equipment | |
| US20220091769A1 (en) | Method, device and computer program product for managing storage pool | |
| CN104572350B (en) | A kind of metadata processing method and device | |
| US8782364B2 (en) | Determining availability of data elements in a storage system | |
| CN113391937A (en) | Method, electronic device and computer program product for storage management | |
| CN111061712A (en) | Data connection operation processing method and device | |
| JP6197872B2 (en) | Data processing system, data processing method, and data processing program |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220126 Address after: 100007 room 205-32, floor 2, building 2, No. 1 and No. 3, qinglonghutong a, Dongcheng District, Beijing Patentee after: Tianyiyun Technology Co.,Ltd. Address before: No.31, Financial Street, Xicheng District, Beijing, 100033 Patentee before: CHINA TELECOM Corp.,Ltd. |
|
| TR01 | Transfer of patent right |