CN108874918A - A kind of data processing equipment, database all-in-one machine and its data processing method - Google Patents
A kind of data processing equipment, database all-in-one machine and its data processing method Download PDFInfo
- Publication number
- CN108874918A CN108874918A CN201810543101.1A CN201810543101A CN108874918A CN 108874918 A CN108874918 A CN 108874918A CN 201810543101 A CN201810543101 A CN 201810543101A CN 108874918 A CN108874918 A CN 108874918A
- Authority
- CN
- China
- Prior art keywords
- node
- memory
- data block
- backup
- memory node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F11/1458—Management of the backup or restore process
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of data processing equipment, database all-in-one machine and its data processing methods.Data processing equipment is set in each backup node of database all-in-one machine, and the address and data block information of this memory node are stored in each memory node of database all-in-one machine, which includes：Memory module, for storing data in the all-in-one machine of library each memory node address；Detection module, for detecting the working condition of each memory node；Processing module, for when detection module detects that the first memory node breaks down, data block in second memory node is backuped in specified backup node, which is to be stored with the memory node of part or all data blocks in the first memory node.The embodiment of the present invention can improve the reliability of data block in memory node on the basis of guaranteeing memory space effective use.
Description
Technical field
This application involves but be not limited to computer and database technical field, espespecially a kind of data processing equipment, database
All-in-one machine and its data processing method.
Background technique
With the development of computer and database technology, big data has penetrated into all trades and professions and operation function field, by
Gradually become indispensable data resource.
Big data all-in-one machine (Big Data Appliance, referred to as：It BDA is) at a kind of analysis for aiming at mass data
The product of the soft and hardware combination of reason and design, what is be widely used is, for example, based on fusion calculation, storage, high speed network sum number
According to the high-performance data library all-in-one machine in library.The Typical Disposition of current database all-in-one machine is, for example,：2 calculate node+3 are deposited
Node is stored up, the data block of memory node is typically designed as two copy redundancies, may be designed in three copy redundancies.Wherein, two is secondary
This redundancy can only tolerate a memory node delay machine, if a memory node delay machine, the data block in delay machine memory node is only
There are a copies, the risk of data single-point occur；Although three copy redundancies can tolerate two memory node delay machines, design
When for three copy redundancies, the memory space of each memory node is had a greatly reduced quality, and the effective storage capacity of memory space is only 1/3.
In conclusion database all-in-one machine in the prior art is difficult to the reliability of data block in compatible memory node and deposits
Store up the effective use in space.
Summary of the invention
In order to solve the above-mentioned technical problem, the embodiment of the invention provides a kind of data processing equipments, database all-in-one machine
And its data processing method, it can be on the basis of guaranteeing memory space effective use, data block can in raising memory node
By property.
The embodiment of the present invention provides a kind of database all-in-one machine, is set in each backup node of database all-in-one machine,
The address and data block information of this memory node are stored in each memory node of the database all-in-one machine, at the data
Managing device includes：
Memory module, for storing data in the all-in-one machine of library each memory node address；
Detection module, it is each in database all-in-one machine described in the address detected for being stored according to the memory module described in
The working condition of memory node；
Processing module, for when the detection module detects that the first memory node breaks down, according to except described the
The address of other memory nodes obtains the data block information of other memory nodes except one memory node, and the second storage is saved
The data block of point backups in backup node belonging to the processing module, and second memory node is to be stored with described first
The memory node of part or all data blocks in memory node.
The embodiment of the present invention also provides a kind of database all-in-one machine, including：At least one backup node, and with each institute
The memory node that backup node is respectively communicated with is stated, is configured at data as described in any one of the above embodiments in each backup node
Device is managed, the address and data block information of this memory node are stored in each memory node.
The embodiment of the present invention also provides a kind of data processing method of database all-in-one machine, using database as described above
All-in-one machine executes the data processing method, the method includes：
Backup node database all-in-one machine according to the address detected of each memory node stored in this backup node
In each memory node working condition；
The backup node is when detecting that the first memory node breaks down, according in addition to first memory node
The address of other memory nodes obtains the data block information of other memory nodes, and the data block in the second memory node is standby
Part is into the backup node, wherein second memory node is to be stored in first memory node partly or entirely
The memory node of data block.
The embodiment of the present invention also provides a kind of computer equipment, including：Memory and processor；
The memory, for saving executable instruction；
The processor, for realizing such as any of the above-described when executing the executable instruction that the memory saves
The data processing method of the database all-in-one machine.
The embodiment of the present invention also provides a kind of computer readable storage medium, and the computer-readable recording medium storage has
Executable instruction is realized when the executable instruction is executed by processor such as the database all-in-one machine as described in any one of above-mentioned
Data processing method.
Data processing equipment, database all-in-one machine and its data processing method provided in an embodiment of the present invention, data processing
In device, backup node passes through the address of the storage of each memory node stored in memory module, using detection module to every
A memory node working condition is detected, when detecting the first memory node failure, by processing module according to memory node
Address obtains the data block information of other memory nodes in addition to failed storage node, and will be former with generation in the second memory node
The identical data block of the first memory node of barrier backups in the backup node, so as to avoid two copy Redundancy Design of data block
Database all-in-one machine in, some memory node delay machine and occur data block single-point risk the problem of, while ensure that storage
The effective use of memory space in node.Data processing equipment provided in an embodiment of the present invention can have guaranteeing memory space
On the basis of effect utilizes, the reliability of data block in memory node is improved.
Detailed description of the invention
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is a kind of structural schematic diagram of database all-in-one machine in the prior art；
Fig. 2 is a kind of structural schematic diagram of data processing equipment provided in an embodiment of the present invention；
Fig. 3 is a kind of application scenarios schematic diagram of data processing equipment provided in an embodiment of the present invention；
Fig. 4 is another application scenarios schematic diagram of data processing equipment provided in an embodiment of the present invention；
Fig. 5 is a kind of flow chart of the data processing method of database all-in-one machine provided in an embodiment of the present invention；
Fig. 6 is the flow chart of the data processing method of another database all-in-one machine provided in an embodiment of the present invention；
Fig. 7 is the flow chart of the data processing method of another database all-in-one machine provided in an embodiment of the present invention；
Fig. 8 is a kind of structural schematic diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
Step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions
It executes.Also, although logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable
Sequence executes shown or described step.
The present invention provides following specific embodiment and can be combined with each other, for the same or similar concept or process
It may be repeated no more in some embodiments.
Include that database software is installed in current database all-in-one machine, the server of the functions such as calculating is provided, such as
It further include that the function such as data storage, data filtering, load shedding are provided in database all-in-one machine including 2 or more
The server of energy, for example including 3 or more, the number of memory node is typically greater than calculate node, calculate node
Redundant ability can be provided with memory node, that is, any one node delay machine is required all to will not influence the offer of database all-in-one machine
Normal service.Fig. 1 is a kind of structural schematic diagram of database all-in-one machine in the prior art, and database all-in-one machine shown in Fig. 1 is with 2
It is shown for the Typical Disposition of+3 memory nodes of a calculate node, in example shown in Fig. 1, is stored in each memory node
There are two data blocks, and memory node is designed as two copy redundancies, and data block A is stored in memory node 1 and memory node 2,
Data block B is stored in memory node 1 and memory node 3, and data block C is stored in memory node 2 and memory node 3, can be with
Find out, in the memory node of two copy redundancies, identical block is not in the same node.For number shown in FIG. 1
According to library all-in-one machine, if 1 delay machine of memory node, data block in the memory node 1, i.e. content in data block A and data block B are only
Next copy is remained, i.e. single-point risk occur in data block A and data block B.It is secondary for two of memory node in database all-in-one machine
This Redundancy Design needs to propose at present the method for data single-point risk occur when a kind of one memory node delay machine of solution.
Fig. 2 is a kind of structural schematic diagram of data processing equipment provided in an embodiment of the present invention.Number provided in this embodiment
It is set in each backup node of database all-in-one machine according to processing unit 100, the database all-in-one machine in the embodiment of the present invention
Including memory node and backup node, the address and data block information of this memory node, this hair are stored in each memory node
Data processing equipment 100 in bright embodiment may include：Memory module 110, detection module 120 and processing module 130.
Wherein, memory module 110, for storing data in the all-in-one machine of library each memory node address；
Detection module 120, in the address detected database all-in-one machine for being stored according to the memory module 110 of backup node
The working condition of each memory node.
In embodiments of the present invention, data processing equipment 100 can be to be configured in the backup node of database all-in-one machine
Software program, for example, agency's (Agent) software, the function of the Agent software realization configured in backup node is data
The function of each module in processing unit 100, in each memory node can configured with for the Agent software in backup node
The software that (i.e. data processing equipment 100) is communicated, the software may be Agent software, configure in memory node
It can store the address and data block information of this memory node in Agent software, which can be the interconnection of memory node
FidonetFido (Internet Protocol, referred to as：IP) address, data block information are for example recorded in Automatic Storage Management
(Automatic Storage Management, referred to as：ASM) or subscriber proxy server (User Agent Server,
Referred to as：UAS in block table (block table)), which for example may include：Size, the quantity of data block,
And position of the data block in its affiliated memory node.For example, if the data processing equipment 100 in backup node uses
Agent software, the Agent software installation are simultaneously configured in each memory node and backup node, each memory node storage
This address of node and data block information can recorde in the configuration file of the Agent software of this memory node installation, each
The address of each memory node in database all-in-one machine is stored in the configuration file of the Agent software of backup node installation.
In embodiments of the present invention, the data processing equipment 100 being configured in each backup node, due to these backup sections
The memory module 110 of point stores the address of each memory node, and detection module 120 can be deposited according to its memory module 110
The working condition of each memory node of address real-time detection of storage, the implementation of detection can be：Backup node is matched by it
Agent software (each storage configured on the Agent software (IP address for being stored with each memory node) and memory node set
The IP address of this node is stored on node), use each memory node IP address ping (" ping " for detect two networks
The means whether network between node is connected to) these memory nodes, after some memory node failure, in backup node
Agent software by the IP address of failed storage node can not ping lead to the failed storage node, then detect the memory node
It breaks down.Any backup node is according to each memory node in the testing result database all-in-one machine of detection module 120
Working condition.
Fig. 3 is a kind of application scenarios schematic diagram of data processing equipment provided in an embodiment of the present invention, and Fig. 3 is equally with data
Library all-in-one machine be+3 memory nodes of 2 calculate nodes Typical Disposition for shown, include in the database all-in-one machine
Two calculate nodes 230 and three memory nodes (i.e. memory node 210a, memory node 210b and memory node 210c), can be with
Find out, unlike database all-in-one machine in the prior art, is increased in the database all-in-one machine of the embodiment of the present invention hard
Part configuration, i.e., backup node 220 usually requires that the hardware of backup node 220 and memory node in configuration database all-in-one machine
Configuration consistency can not such as find the backup node 220 of same configuration really, then keep not differing too in hardware configuration as far as possible
Greatly, but the hard disk performance of backup node and capacity requirement are consistent with memory node, i.e., the backup node 220 is actually also to deposit
Store up node.Fig. 3 is shown for being configured with a backup node 220.
As shown in figure 3, data processing equipment 100 is configured in each memory node and backup node 220, it can be by this
Data processing equipment 100 realizes being in communication with each other between backup node 220 and each memory node, for example, database all-in-one machine
When memory node 210a delay machine in 20, backup node 220 is deposited by delay machine known to its internal data processing equipment 100 configured
Store up the current state of node (i.e. memory node 210a).
It should be noted that data processing equipment 100 provided in an embodiment of the present invention also can be applied to other configurations
In database all-in-one machine, for example,+6 memory nodes of 4 calculate nodes or+7 memory nodes of 4 calculate nodes or 2
The database all-in-one machine of+7 memory nodes of a calculate node, the i.e. embodiment of the present invention do not limit making for data processing equipment 100
Use range；In addition, the quantity of also unlimited backup node processed of the embodiment of the present invention, can be one or more.
Processing module 130, for when detection module 120 detects that the first memory node breaks down, according to removing first
The address of other memory nodes obtains the data block information of other memory nodes except memory node, by the second memory node
Data block backups in backup node belonging to processing module 130, wherein the second memory node is to be stored with the first memory node
The memory node of middle part or all data blocks.
In embodiments of the present invention, above-mentioned it is stated that be stored with each memory node address in memory module 110, and handle
Module 130 can be that is, other in addition to the first memory node according to the logical memory node not broken down of these addresses ping
Memory node can ping it is logical, since the data block in memory node is designed as two copy redundancy backups, failed storage
Data block copy in node (i.e. the first memory node) there remains a copy in other memory nodes, the place in backup node
Managing module 130 can be according to the configuration file of Agent software in other memory nodes of the address scan of other memory nodes
The data block information in other memory nodes is obtained, and the data block of only one data copy can be finally obtained, only one
The data block of data copy is exactly the data block in the first memory node, and the object backed up.That is, according to sweeping
Retouching result can know which other memory node is the data block in the first memory node also store in, deposit with the first memory node
The node for containing identical block is the second memory node.Therefore, in backup node data processing equipment 100 processing module
Data block identical with the first memory node in second memory node can be backuped to the backup section according to above- mentioned information by 130
Point in.The implementation backed up in present invention implementation can be remote synchronization data block or asynchronous replication of data block, only at certain
The operation of remote backup data block is just triggered when a memory node breaks down；In addition, detection module 120 detects some storage section
The standard that point breaks down, that is, the condition for triggering backup can be：Detect that some memory node cannot respond in x seconds (s),
I.e. the IP address of the memory node can not ping it is logical, the length of the x can be set by administrator.
It should be noted that can be had by scanning the data block for obtaining only one data copy in the embodiment of the present invention by one
Or it is multiple, when to be multiple, it is likely distributed in multiple second memory nodes；In addition, the quantity of the second memory node can be
One or more, when the data block of the first memory node to break down is stored entirely in another memory node, second is deposited
Storing up node is this memory node, and in this scenario, backup node is by all data blocks of this second memory node
It backups in the backup node；When the data block of the first memory node to break down is stored in multiple memory nodes, these
The partial data block of the first memory node, example as shown in Figure 3, delay machine memory node 210a (are only stored in memory node
One memory node) in data block A be stored in memory node 210b, data block B is stored in memory node 210c, is deposited at this time
Storing up node 210b and memory node 210c is all the second memory node, and in this scenario, backup node is deposited each second respectively
Partial data block identical with the first memory node backups in the backup node in storage node.
Existing design is in the database all-in-one machine of two copy redundancies, if delay machine occurs for a memory node, and can not be extensive
It is multiple, then the data block in the memory node on normal storage node by only one copy, as shown in Figure 1, data block C is also
There are two copy, there is the list of data block at this time in data block A in delay machine memory node 1 and data block B only one copy
Point risk, if there is another memory node delay machine, data block A or data block B be will be lost.The prior art does not have also
It is provided with an effective method and there was only two copy redundancies to solve memory node, and in the case where breaking down a memory node,
There is the problem of single-point risk in data block.In contrast, data processing equipment 100 provided in an embodiment of the present invention is set to data
In the backup node that each of library all-in-one machine additionally configures, pass through data processing equipment 100 in backup node and each storage
Software (for example, Agent software) on node realizes the intercommunication of backup node and each memory node, so as in some storage
When nodes break down, data block identical with delay machine memory node in other memory nodes can be backuped into backup node
In, that is, in the application scenarios that avoid two copy redundancies, the data block single-point risk problem that one memory node of delay machine occurs, with
The application scenarios of three copy redundancies are compared, and also ensure the effective use of memory space.
Data processing equipment 100 provided in an embodiment of the present invention, backup node is by each of storing in memory module 110
Each memory node working condition is detected using detection module 120 in the address of the storage of memory node, is detecting
When one memory node failure, other storages in addition to failed storage node are obtained according to memory node address by processing module 130
The data block information of node, and data block identical with the first memory node to break down in the second memory node is backuped to
In the backup node, in the database all-in-one machine so as to avoid two copy Redundancy Design of data block, some memory node delay machine
And the problem of data block single-point risk of appearance, while ensure that the effective use of memory space in memory node.The present invention is real
The data processing equipment 100 of example offer is provided, number in memory node can be improved on the basis of guaranteeing memory space effective use
According to the reliability of block.
Being had been described above in database all-in-one machine in above-described embodiment can save configured with a backup node or multiple backups
Point.
In a kind of possible implementation of the embodiment of the present invention, a backup section is only configured in database all-in-one machine
Point, in the application scenarios, memory module 110 is also used to store the address of a backup node；Correspondingly, processing module
The implementation of 130 Backup Data blocks can be：When detection module 120 detects that the first memory node breaks down, according to
Data block information of the address scan that memory module 110 stores in addition to the first memory node in other memory nodes, and according to
The address of scanning result and backup node backups to the data block in the second memory node in the backup node.Due to only
One backup node, the address of the backup node stored in memory module 110 are the destination address backed up, can be in Agent
The IP address that destination address is the backup node is set in configuration file.
It is standby that at least two are configured in the alternatively possible implementation of the embodiment of the present invention, in database all-in-one machine
Part node, in the application scenarios, memory module 110 is also used to store address and the storage priority of each backup node；Phase
The implementation of Ying Di, 130 Backup Data block of processing module can be：Detect that the first memory node is sent out in detection module 120
When raw failure, the address scan stored according to memory module 110 removes backup node belonging to the first memory node and processing module 130
Except data block information in other nodes, and according to the address of scanning result and each backup node, according to storage priority
Data block in second memory node is backuped into storage highest priority and in currently empty backup node.
Data processing equipment 100 provided in an embodiment of the present invention is illustrated in the application scenarios below by way of an implementation
In processing mode, Fig. 4 be data processing equipment provided in an embodiment of the present invention another application scenarios schematic diagram, Fig. 4 with
For database all-in-one machine to be shown for the configuration of+6 memory nodes of 4 calculate nodes, which includes four
A calculate node 230 and 6 memory node (210a, 210b, 210c, 210d, 210e and 210f), also configure there are two backup section
Point, i.e. backup node 220a and backup node 220b, wherein data block same design is two copy redundancies, and data block is each
Distribution in memory node as shown in figure 4, in addition, be configured with data processing equipment 100 in each memory node and backup node,
In the data processing equipment 100 of each memory node configuration, the IP address sum number of this memory node is stored in memory module 110
It according to block message, is configured in data processing equipment 100 in each backup node, each storage section is stored in memory module 110
Point IP address, the IP address (address including backup node 220a and backup node 220b) of each backup node and this
The storage priority of two backup nodes, the storage priority can be ranked up with the hardware configuration performance of backup node, example
Hardware configuration such as backup node 220a is identical with memory node, the hardware configuration and memory node ratio of backup node 220b
It is closer to, then stores being set as priority：Backup node 220a is level-one, and backup node 220b is second level.Based on above-mentioned number
According to the configuration of library all-in-one machine, when memory node 210b delay machine, there is single-point wind in data block A and data block C only one copy
Danger, can by with memory node 210b have identical block other memory nodes (including memory node 210a and storage section
Point 210c) in identical data block backup in one of backup node, at this point, the data processing in two backup nodes fills
Memory node 210b delay machine can be detected by setting 100, and other memory nodes are determining to be had with delay machine memory node by scanning
There is the second memory node (i.e. memory node 210a and memory node 210c) of identical block, and can also be standby according to two
The storage priority and current working status of part node, using one of backup node as target backup node, if backup section
Point 220a is currently empty, then using backup node 220a as target backup node, if backup node 220a is currently at work shape
State is stored with other data blocks, then, then, will be in memory node 210a using backup node 220b as target backup node
Data block A and memory node 210c in data block C backup in the selected target backup node.Fig. 4 will be will back up section
Point 220a is shown for the backup as target backup node progress data block.
Optionally, in data processing equipment 100 provided in an embodiment of the present invention, processing module 130 is also used to real time scan
Data block information in second memory node, when the data block backed up in determining the second memory node updates,
Updated data block is backuped in backup node again.In embodiments of the present invention, data processing equipment 100 can be real-time
Judge the update status of data block, is updated if having backuped to the data block in backup node and having had in the second memory node
When, data block that can again after backup updating, to achieve the purpose that data block has high availability.
Optionally, in data processing equipment 100 provided in an embodiment of the present invention, processing module 130 is also used in detection mould
When block 120 detects that the first memory node restores normal operating conditions, the data block in backup node is deleted.Implement in the present invention
In example, although backup node has the hardware configuration identical or close with memory node, and the redundancy of data block may be implemented
Storage capacity, but since only in database all-in-one machine there are in the case where a memory node delay machine, just triggering backup is saved
Point realizes the redundant storage of data block, and data processing equipment 100 is detecting that delay machine memory node (i.e. the first memory node) is extensive
It is multiple work normally after, can actively delete the data block stored in the backup node, it is other so as to follow-up data library all-in-one machine
When memory node delay machine, which can continue to execute the redundancy backup operation of data block.
Optionally, in embodiments of the present invention, data block information may include：Position of the data block in affiliated node,
And the size and number of the data block, when the data processing equipment 100 of backup node backs up data block, Ke Yikao
Whether the size for considering data block allows to backup on this node, can be with when this backup node is unsatisfactory for the hsrdware requirements of backup
It is backed up by data block of other backup nodes to delay machine memory node.In addition, identical block in the embodiment of the present invention
Quantity is usually two, i.e. two copy redundancy backups, but be not excluded for there are three or other quantity possibility situation, different data block
Quantity then configured according to the hardware configuration of database all-in-one machine, the size of data block is then influenced in delay machine memory node
Validity when data block is backed up, the redundancy that processing module 130 can choose suitable backup node execution data block are standby
Part operation.
The embodiment of the present invention is by being configured at database all-in-one machine for data processing equipment 100 (for example, Agent software)
Each backup node in, (can also configured with software for being communicated with data processing equipment 100 in each memory node
Think Agent software), which may be implemented to the detailed record of data block information and the remote copy of data block
With the ability of incremental replication, for the database all-in-one machine of two copy Redundancy Designs, when a memory node breaks down, still
The effect of two copy redundancies of all data blocks so may be implemented.
Based on the data processing equipment 100 that the various embodiments described above of the present invention provide, the embodiment of the present invention also provides a kind of number
Data processing equipment 100 according to library all-in-one machine, configured with any of the above-described embodiment offer of the present invention in the database all-in-one machine.
With reference to shown in Fig. 3 and Fig. 4, it is similarly the structural schematic diagram of database all-in-one machine provided in an embodiment of the present invention.This
Inventive embodiments provide database all-in-one machine include：At least one backup node, and be respectively communicated with each backup node
Memory node, and the data processing equipment 100 that any of the above-described embodiment of the present invention provides is equipped in each backup node
(for example, Agent software), in each memory node configured with for being communicated with data processing equipment 100 software (
Can be Agent software), and the address and data block information of this memory node are stored in each memory node.In addition, this
It can be by network-in-dialing, in reality between backup node and memory node in inventive embodiments and between backup node
In, ping operation can be carried out by the address of the Agent software configured and storage on each node, to realize communication
Ability.Fig. 3 is different with the basic configuration of the one of database shown in Fig. 4, i.e., calculate node is different with the quantity of memory node, but all
Configured with backup node, and in Fig. 3 and Fig. 4 backup node configuration quantity it is also different.
It should be noted that the structure of database all-in-one machine provided in an embodiment of the present invention is not limited to Fig. 3 and shown in Fig. 4
Structure does not limit calculate node in database all-in-one machine, the quantity of memory node and backup node, as long as each backup saves
It is equipped with the data processing equipment 100 that any of the above-described embodiment of the present invention provides in point, and is configured with and is used in memory node
The software communicated with data processing equipment 100, and database can be realized when a memory node breaks down
Two copy redundancy backup abilities, all can serve as the database all-in-one machine in the embodiment of the present invention.
It is also configured with backup node in database all-in-one machine provided in an embodiment of the present invention, and matches in each backup node
It is equipped with the data processing equipment 100 that any of the above-described embodiment of the present invention provides, may be implemented and data provided by the above embodiment
The identical processing capacity of processing unit 100, and technical effect having the same, therefore details are not described herein.
Based on data processing equipment 100 and database all-in-one machine that the various embodiments described above of the present invention provide, the present invention is implemented
Example also provides a kind of data processing method of database all-in-one machine, and the data processing method of the database all-in-one machine is using this hair
The database all-in-one machine that bright any of the above-described embodiment provides carries out data processing.
As shown in figure 5, being a kind of flow chart of the data processing method of database all-in-one machine provided in an embodiment of the present invention.
Data processing method provided in this embodiment is executed by database all-in-one machine, which is any of the above-described reality of the present invention
The database all-in-one machine of example offer is applied, structure can refer to Fig. 3 and database all-in-one machine shown in Fig. 4, data processing method
It may include steps of：
S310, backup node is according to the address detected database all-in-one machine of each memory node stored in this backup node
In each memory node working condition.
The data processing method of database all-in-one machine provided in an embodiment of the present invention, for applied to two copy Redundancy Designs
Processing method in database all-in-one machine, the structure of database all-in-one machine in the embodiment of the present invention, internal backup node configuration
Data processing equipment (for example, Agent software) and memory node in the structure of software (for example, Agent software) that configures
It is had been described in the above-described embodiments with function, therefore details are not described herein.At data in the above embodiment of the present invention
The hardware configuration and software capability of device and database all-in-one machine are managed, is stored with each deposit in the backup node of the embodiment of the present invention
Address of node is stored up, the address and data block information of this memory node are stored in each memory node, which, which can be, deposits
The IP address of node is stored up, data block information is for example recorded in the block table (block table) of ASM or UAS, the data block information
Such as may include：Position of size, quantity and the data block of data block in its affiliated memory node.In addition, database
Backup node in all-in-one machine can be according to the working condition of each memory node of address real-time detection of its storage, the reality of detection
Now mode can be：What backup node configured on the Agent software (data processing equipment) and memory node by its configuration
Agent software, using these memory nodes of the IP address ping of each memory node, after some memory node failure, backup section
Agent software in point by the IP address of failed storage node can not ping lead to the failed storage node, then detect that this is deposited
Store up nodes break down.Any backup node knows the work shape of each memory node in database all-in-one machine according to testing result
State.
S320, backup node when detecting that the first memory node breaks down, according in addition to the first memory node its
The address of its memory node obtains the data block information of other memory nodes, and the data block in the second memory node is backuped to
In backup node, the second memory node is to be stored with the memory node of part or all data blocks in the first memory node.
In embodiments of the present invention, above-mentioned it is stated that be stored with each memory node address in backup node, and back up section
Point can lead to the memory node not broken down according to these addresses ping, i.e., other storage sections in addition to the first memory node
Point can ping it is logical, since the data block in memory node is designed as two copy redundancy backups, failed storage node is (i.e.
First memory node) in data block copy there remains a copy in other memory nodes, the Agent software in backup node
It can be can be obtained other according to the configuration file of Agent software in other memory nodes of the address scan of other memory nodes
Data block information in memory node, and the data block of only one data copy can be finally obtained, only one data copy
Data block be exactly data block in the first memory node, and the object backed up.That is, can according to scanning result
To know which other memory node is the data block in the first memory node also store in, it is stored with the first memory node identical
The node of data block is the second memory node.Therefore, the backup node of database all-in-one machine can be according to above- mentioned information, by
Data block identical with the first memory node backups in the backup node in two memory nodes.The reality backed up in present invention implementation
Existing mode can be remote synchronization data block or asynchronous replication of data block, only just trigger when some memory node breaks down
The operation of remote backup data block；In addition, the standard that some memory node of database one machine testing breaks down, that is, trigger standby
Part condition can be：Detect that some memory node cannot respond in x seconds (s), i.e. the IP address of the memory node can not
Ping is logical, and the length of the x can be set by administrator.
It should be noted that can be had by scanning the data block for obtaining only one data copy in the embodiment of the present invention by one
Or it is multiple, when to be multiple, it is likely distributed in multiple second memory nodes；In addition, the quantity of the second memory node can be
One or more, when the data block of the first memory node to break down is stored entirely in another memory node, second is deposited
Storing up node is this memory node, and in this scenario, backup node is by all data blocks of this second memory node
It backups in the backup node；When the data block of the first memory node to break down is stored in multiple memory nodes, these
The partial data block of the first memory node, example as shown in Figure 3, delay machine memory node 210a (are only stored in memory node
One memory node) in data block A be stored in memory node 210b, data block B is stored in memory node 210c, is deposited at this time
Storing up node 210b and memory node 210c is all the second memory node, and in this scenario, backup node is deposited each second respectively
Partial data block identical with the first memory node backups in the backup node in storage node.
Existing design is in the database all-in-one machine of two copy redundancies, if delay machine occurs for a memory node, and can not be extensive
It is multiple, then the data block in the memory node on normal storage node by only one copy, as shown in Figure 1, data block C is also
There are two copy, there is the list of data block at this time in data block A in delay machine memory node 1 and data block B only one copy
Point risk, if there is another memory node delay machine, data block A or data block B be will be lost.The prior art does not have also
It is provided with an effective method and there was only two copy redundancies to solve memory node, and in the case where breaking down a memory node,
There is the problem of single-point risk in data block.In contrast, the data processing side of database all-in-one machine provided in an embodiment of the present invention
Data processing in method, configured with the offer of any of the above-described embodiment in the backup node that each of database all-in-one machine additionally configures
Device is realized by the software (for example, Agent software) on the data processing equipment and each memory node in backup node
The intercommunication of backup node and each memory node can be by other memory nodes so as to when some memory node breaks down
In data block identical with delay machine memory node backup in backup node, that is, in the application scenarios for avoiding two copy redundancies,
The data block single-point risk problem that one memory node of delay machine occurs also ensures compared with the application scenarios of three copy redundancies
The effective use of memory space.
The data processing method of database all-in-one machine provided in an embodiment of the present invention, by backup node to database one
The detection of each memory node working condition in machine, backup node obtain according to each memory node address and remove failed storage node
Except other memory nodes data block information, and will be identical with the first memory node to break down in the second memory node
Data block backups in backup node, and in the database all-in-one machine so as to avoid two copy Redundancy Design of data block, some is deposited
Storage node delay machine and the problem of the data block single-point risk occurred, while ensure that effective benefit of memory space in memory node
With.The data processing method of database all-in-one machine provided in an embodiment of the present invention can guarantee memory space effective use
On the basis of, improve the reliability of data block in memory node.
Being had been described above in database all-in-one machine in above-described embodiment can save configured with a backup node or multiple backups
Point.
In a kind of possible implementation of the embodiment of the present invention, a backup section is only configured in database all-in-one machine
Point is stored with the address of this backup node in the application scenarios, in backup node；Correspondingly, the implementation of S320, can be with
Including：
Backup node is when detecting that the first memory node breaks down, according to the address scan stored in this backup node
Data block information in addition to the first memory node in other memory nodes, and according to the address of scanning result and backup node,
Data block in second memory node is backuped in the backup node.
In the embodiment of the present invention, due to only having a backup node, the ground of the backup node stored in database all-in-one machine
Location is the destination address backed up.
It is standby that at least two are configured in the alternatively possible implementation of the embodiment of the present invention, in database all-in-one machine
Part node is stored with address and the storage priority of each backup node in the application scenarios, in backup node；Correspondingly,
The implementation of S320 may include：
Backup node is when detecting that the first memory node breaks down, according to the address scan stored in this backup node
Data block information in addition to the first memory node and this backup node in other nodes, and according to scanning result and each backup
Data block in second memory node is backuped to storage highest priority according to storage priority and is currently by address of node
In empty backup node.The implementation example of the application scenarios is referred to implement example shown in Fig. 4, and details are not described herein.
Optionally, Fig. 6 is the process of the data processing method of another database all-in-one machine provided in an embodiment of the present invention
Figure.On the basis of embodiment shown in Fig. 5, method provided in an embodiment of the present invention can also include：
S330, the data block information in the second memory node of backup node real time scan, in determining the second memory node
When the data block backed up updates, updated data block is backuped to again in the backup node.
In embodiments of the present invention, database all-in-one machine can go out the update status of data block with real-time judge, if standby
Data block in part node has in the second memory node when updating, data block that can again after backup updating, to reach
Data block has the purpose of high availability.
Optionally, Fig. 7 is the process of the data processing method of another database all-in-one machine provided in an embodiment of the present invention
Figure.On the basis of the various embodiments described above, method provided in an embodiment of the present invention can also include：
S340, backup node are deleted in this backup node when detecting that the first memory node restores normal operating conditions
Data block.
Embodiment illustrated in fig. 7 is shown on the basis of process shown in Fig. 5.In embodiments of the present invention, standby
Although part node has the hardware configuration identical or close with memory node, and the redundant storage energy of data block may be implemented
Power, but since only there are in the case where a memory node delay machine, just trigger backup node to realize in database all-in-one machine
The redundant storage of data block, database all-in-one machine are detecting delay machine memory node (i.e. the first memory node) recovery normal work
Afterwards, the data block stored in the backup node can be deleted, actively so that other memory nodes of follow-up data library all-in-one machine are delayed
When machine, which can continue to execute the redundancy backup operation of data block.
Optionally, in embodiments of the present invention, the data block information stored in database all-in-one machine includes：Data block is in institute
Belong to the position in node and the size and number of the data block.In addition, in the embodiment of the present invention identical block quantity
Usually two, i.e. two copy redundancy backups, but be not excluded for there are three or other quantity possibility situation, the number of different data block
Amount is then configured according to the hardware configuration of database all-in-one machine, and the size of data block is then influenced to data in delay machine memory node
Validity when block is backed up, therefore can choose the redundancy backup operation that suitable backup node executes data block.
Fig. 8 is a kind of structural schematic diagram of computer equipment provided in an embodiment of the present invention.It is provided in an embodiment of the present invention
Computer equipment 40 may include：Memory 41 and processor 42.
Wherein, memory 41, for saving executable instruction；
Processor 42, for realizing any of the above-described embodiment of the present invention when executing the executable instruction that memory 41 saves
The database all-in-one machine of offer carries out data processing.
The data that the embodiment and the above embodiment of the present invention of computer equipment 40 provided in an embodiment of the present invention provide
The method that library all-in-one machine carries out data processing is essentially identical, and this will not be repeated here.
The embodiment of the present invention also provides a kind of computer readable storage medium, which has can
It executes instruction, which may be implemented the database one that any of the above-described embodiment of the present invention provides when being executed by processor
Body machine carries out data processing.The embodiment and the above-mentioned reality of the present invention of computer readable storage medium provided in an embodiment of the present invention
The method for applying the database all-in-one machine progress data processing of example offer is essentially identical, and this will not be repeated here.
Although disclosed herein embodiment it is as above, the content only for ease of understanding the present invention and use
Embodiment is not intended to limit the invention.Technical staff in any fields of the present invention is taken off not departing from the present invention
Under the premise of the spirit and scope of dew, any modification and variation, but the present invention can be carried out in the form and details of implementation
Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.
It will appreciated by the skilled person that whole or certain steps, system, dress in method disclosed hereinabove
Functional module/unit in setting may be implemented as software, firmware, hardware and its combination appropriate.In hardware embodiment,
Division between the functional module/unit referred in the above description not necessarily corresponds to the division of physical assemblies；For example, one
Physical assemblies can have multiple functions or a function or step and can be executed by several physical assemblies cooperations.Certain groups
Part or all components may be implemented as by processor, such as the software that digital signal processor or microprocessor execute, or by
It is embodied as hardware, or is implemented as integrated circuit, such as specific integrated circuit.Such software can be distributed in computer-readable
On medium, computer-readable medium may include computer storage medium (or non-transitory medium) and communication media (or temporarily
Property medium).As known to a person of ordinary skill in the art, term computer storage medium is included in for storing information (such as
Computer readable instructions, data structure, program module or other data) any method or technique in the volatibility implemented and non-
Volatibility, removable and nonremovable medium.Computer storage medium include but is not limited to RAM, ROM, EEPROM, flash memory or its
His memory technology, CD-ROM, digital versatile disc (DVD) or other optical disc storages, magnetic holder, tape, disk storage or other
Magnetic memory apparatus or any other medium that can be used for storing desired information and can be accessed by a computer.This
Outside, known to a person of ordinary skill in the art to be, communication media generally comprises computer readable instructions, data structure, program mould
Other data in the modulated data signal of block or such as carrier wave or other transmission mechanisms etc, and may include any information
Delivery media.
Claims (13)
1. a kind of data processing equipment, which is characterized in that be set in each backup node of database all-in-one machine, the data
The address and data block information of this memory node, the data processing equipment packet are stored in each memory node of library all-in-one machine
It includes：
Memory module, for storing data in the all-in-one machine of library each memory node address；
Detection module, each storage in database all-in-one machine described in the address detected for being stored according to the memory module
The working condition of node；
Processing module, for being deposited according to removing described first when the detection module detects that the first memory node breaks down
The address of other memory nodes obtains the data block information of other memory nodes except storage node, by the second memory node
Data block backups in backup node belonging to the processing module, and second memory node is to be stored with first storage
The memory node of part or all data blocks in node.
2. data processing equipment according to claim 1, which is characterized in that the database all-in-one machine includes a backup
Node；
The memory module is also used to store the address of the backup node；
The processing module backups to the data block in second memory node in the backup node, including：
When the detection module detects that first memory node breaks down, according to the address of memory module storage
The data block information in addition to first memory node in other memory nodes is scanned, and according to scanning result and the backup
Address of node backups to the data block in second memory node in the backup node；Alternatively,
The database all-in-one machine includes at least two backup nodes；
The memory module is also used to store address and the storage priority of each backup node；
The processing module backups to the data block in second memory node in the backup node, including：
When the detection module detects that first memory node breaks down, according to the address of memory module storage
The data block information in addition to first memory node and the affiliated backup node of the processing module in other nodes is scanned, and
It, will be in second memory node according to the storage priority according to the address of scanning result and each backup node
Data block backups to storage highest priority and in currently empty backup node.
3. data processing equipment according to claim 1 or 2, which is characterized in that
The processing module, the data block information being also used in the second memory node described in real time scan are determining described second
When the data block backed up in memory node updates, updated data block is backuped into the backup node again
In.
4. data processing equipment according to claim 1 or 2, which is characterized in that
The processing module is also used to detect that first memory node restores normal operating conditions in the detection module
When, delete the data block in the backup node.
5. data processing equipment according to claim 1 or 2, which is characterized in that
The data block information includes：The size and number of position and the data block of the data block in affiliated node.
6. a kind of database all-in-one machine, which is characterized in that including：At least one backup node, and saved with each backup
The memory node being respectively communicated with is put, configuration is just like data according to any one of claims 1 to 5 in each backup node
Processing unit is stored with the address and data block information of this memory node in each memory node.
7. a kind of data processing method of database all-in-one machine, which is characterized in that use database one as claimed in claim 6
Body machine executes the data processing method, the method includes：
Backup node is every in the database all-in-one machine according to the address detected of each memory node stored in this backup node
The working condition of a memory node；
The backup node is when detecting that the first memory node breaks down, according to other in addition to first memory node
The address of memory node obtains the data block information of other memory nodes, and the data block in the second memory node is backuped to
In the backup node, wherein second memory node is to be stored with part or total data in first memory node
The memory node of block.
8. the data processing method of database all-in-one machine according to claim 7, which is characterized in that the database one
Machine includes a backup node, and the address of this backup node is stored in the backup node；
The backup node backups to the data block in the second memory node in backup node, including：
The backup node is when detecting that first memory node breaks down, according to the address stored in this backup node
The data block information in addition to first memory node in other memory nodes is scanned, and according to scanning result and the backup
Address of node backups to the data block in second memory node in the backup node；Alternatively,
The database all-in-one machine includes at least two backup nodes, is stored with each backup node in the backup node
Address and storage priority；
The backup node backups to the data block in the second memory node in the backup node, including：
The backup node is when detecting that first memory node breaks down, according to the address stored in this backup node
Scan the data block information in addition to first memory node and this backup node in other nodes, and according to scanning result and
Data block in second memory node is backuped to according to the storage priority and is deposited by the address of each backup node
Store up highest priority and in currently empty backup node.
9. the data processing method of database all-in-one machine according to claim 7 or 8, which is characterized in that further include：
Data block information in second memory node described in the backup node real time scan is determining second memory node
In the data block that has been backed up when updating, updated data block is backuped to again in the backup node.
10. the data processing method of database all-in-one machine according to claim 7 or 8, which is characterized in that further include：
The backup node is deleted in this backup node when detecting that first memory node restores normal operating conditions
Data block.
11. the data processing method of database all-in-one machine according to claim 7 or 8, which is characterized in that the data block
Information includes：The size and number of position and the data block of the data block in affiliated node.
12. a kind of computer equipment, which is characterized in that including：Memory and processor；
The memory, for saving executable instruction；
The processor, for realizing such as claim 7~11 when executing the executable instruction that the memory saves
Any one of described in database all-in-one machine data processing method.
13. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has executable finger
It enables, the database all-in-one machine as described in any one of claim 7~11 is realized when the executable instruction is executed by processor
Data processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810543101.1A CN108874918B (en) | 2018-05-30 | 2018-05-30 | Data processing device, database all-in-one machine and data processing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810543101.1A CN108874918B (en) | 2018-05-30 | 2018-05-30 | Data processing device, database all-in-one machine and data processing method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108874918A true CN108874918A (en) | 2018-11-23 |
| CN108874918B CN108874918B (en) | 2021-11-26 |
Family
ID=64335893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810543101.1A Active CN108874918B (en) | 2018-05-30 | 2018-05-30 | Data processing device, database all-in-one machine and data processing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108874918B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113709197A (en) * | 2020-05-21 | 2021-11-26 | 顺丰科技有限公司 | Alliance block chain organization system and block chain system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1786920A (en) * | 2004-12-09 | 2006-06-14 | 国际商业机器公司 | Performing scheduled backups of a backup node associated with a plurality of agent nodes |
| CN101539873A (en) * | 2009-04-15 | 2009-09-23 | 成都市华为赛门铁克科技有限公司 | Data recovery method, data node and distributed file system |
| CN103064759A (en) * | 2012-12-18 | 2013-04-24 | 华为技术有限公司 | Data recovery method and device |
| CN104054076A (en) * | 2013-01-14 | 2014-09-17 | 华为技术有限公司 | Data storage method, database storage node failure processing method and apparatus |
| CN105354108A (en) * | 2014-08-22 | 2016-02-24 | 中兴通讯股份有限公司 | Data backup method and node |
| CN105406980A (en) * | 2015-10-19 | 2016-03-16 | 浪潮(北京)电子信息产业有限公司 | Multi-node backup method and multi-node backup device |
| US20160124817A1 (en) * | 2014-10-31 | 2016-05-05 | Red Hat, Inc. | Fault tolerant listener registration in the presence of node crashes in a data grid |
| CN105930498A (en) * | 2016-05-06 | 2016-09-07 | ***股份有限公司 | Distributed database management method and system |
| CN107015884A (en) * | 2016-01-28 | 2017-08-04 | 杭州海康威视数字技术股份有限公司 | A kind of date storage method and device |
| CN107329708A (en) * | 2017-07-04 | 2017-11-07 | 郑州云海信息技术有限公司 | A kind of distributed memory system realizes data cached method and system |
| CN107357689A (en) * | 2017-08-02 | 2017-11-17 | 郑州云海信息技术有限公司 | The fault handling method and distributed memory system of a kind of memory node |
| CN107484108A (en) * | 2017-08-25 | 2017-12-15 | 中国联合网络通信集团有限公司 | Method, sensing equipment and the radio sensing network of data backup |
-
2018
- 2018-05-30 CN CN201810543101.1A patent/CN108874918B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1786920A (en) * | 2004-12-09 | 2006-06-14 | 国际商业机器公司 | Performing scheduled backups of a backup node associated with a plurality of agent nodes |
| CN101539873A (en) * | 2009-04-15 | 2009-09-23 | 成都市华为赛门铁克科技有限公司 | Data recovery method, data node and distributed file system |
| CN103064759A (en) * | 2012-12-18 | 2013-04-24 | 华为技术有限公司 | Data recovery method and device |
| CN104054076A (en) * | 2013-01-14 | 2014-09-17 | 华为技术有限公司 | Data storage method, database storage node failure processing method and apparatus |
| CN105354108A (en) * | 2014-08-22 | 2016-02-24 | 中兴通讯股份有限公司 | Data backup method and node |
| US20160124817A1 (en) * | 2014-10-31 | 2016-05-05 | Red Hat, Inc. | Fault tolerant listener registration in the presence of node crashes in a data grid |
| CN105406980A (en) * | 2015-10-19 | 2016-03-16 | 浪潮(北京)电子信息产业有限公司 | Multi-node backup method and multi-node backup device |
| CN107015884A (en) * | 2016-01-28 | 2017-08-04 | 杭州海康威视数字技术股份有限公司 | A kind of date storage method and device |
| CN105930498A (en) * | 2016-05-06 | 2016-09-07 | ***股份有限公司 | Distributed database management method and system |
| CN107329708A (en) * | 2017-07-04 | 2017-11-07 | 郑州云海信息技术有限公司 | A kind of distributed memory system realizes data cached method and system |
| CN107357689A (en) * | 2017-08-02 | 2017-11-17 | 郑州云海信息技术有限公司 | The fault handling method and distributed memory system of a kind of memory node |
| CN107484108A (en) * | 2017-08-25 | 2017-12-15 | 中国联合网络通信集团有限公司 | Method, sensing equipment and the radio sensing network of data backup |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113709197A (en) * | 2020-05-21 | 2021-11-26 | 顺丰科技有限公司 | Alliance block chain organization system and block chain system |
| CN113709197B (en) * | 2020-05-21 | 2024-02-23 | 顺丰科技有限公司 | Alliance block chain organization system and block chain system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108874918B (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3518110B1 (en) | Designation of a standby node | |
| JP6362119B2 (en) | Arbitration processing method, quorum storage device, and system after cluster brain division | |
| CN106331098B (en) | Server cluster system | |
| CN105407117B (en) | The methods, devices and systems of distributed backup data | |
| US7702667B2 (en) | Methods and systems for validating accessibility and currency of replicated data | |
| US10305749B2 (en) | Low latency flow cleanup of openflow configuration changes | |
| US20150347246A1 (en) | Automatic-fault-handling cache system, fault-handling processing method for cache server, and cache manager | |
| CN106506490B (en) | A kind of distributed computing control method and distributed computing system | |
| CN110351313B (en) | Data caching method, device, equipment and storage medium | |
| JP2017531250A (en) | Granular / semi-synchronous architecture | |
| CN110377459A (en) | A kind of disaster tolerance system, disaster tolerance processing method, monitoring node and backup cluster | |
| CN111176888B (en) | Disaster recovery method, device and system for cloud storage | |
| CN107426021A (en) | Construction method, device and the redundant system of redundant system | |
| CN106959820A (en) | A kind of data extraction method and system | |
| CN108572976A (en) | Data reconstruction method, relevant device and system in a kind of distributed data base | |
| CN110659158A (en) | Influx DB data backup method based on dual-computer hot standby environment | |
| CN112839076B (en) | Data storage method, data reading method, gateway, electronic equipment and storage medium | |
| CN111342986B (en) | Distributed node management method and device, distributed system and storage medium | |
| CN108614750A (en) | The restoration methods and device of delay machine data | |
| CN108319522A (en) | A method of reinforcing distributed memory system reliability | |
| CN109347655B (en) | Network data based fault recovery system and method and storage medium | |
| JP6604336B2 (en) | Information processing apparatus, information processing method, and program | |
| CN105490847A (en) | Real-time detecting and processing method of node failure in private cloud storage system | |
| CN108874918A (en) | A kind of data processing equipment, database all-in-one machine and its data processing method | |
| CN108509296A (en) | A kind of method and system of processing equipment failure |
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 |