CN108900331A - A kind of distributed type assemblies management method and distributed type assemblies - Google Patents
A kind of distributed type assemblies management method and distributed type assemblies Download PDFInfo
- Publication number
- CN108900331A CN108900331A CN201810668217.8A CN201810668217A CN108900331A CN 108900331 A CN108900331 A CN 108900331A CN 201810668217 A CN201810668217 A CN 201810668217A CN 108900331 A CN108900331 A CN 108900331A
- Authority
- CN
- China
- Prior art keywords
- node
- cluster
- business
- nodes
- host 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0663—Performing the actions predefined by failover planning, e.g. switching to standby network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of distributed type assemblies management methods, and applied to the host node of cluster, this method includes：It receives the business record that each node is sent in cluster and is stored；When cluster meets recovery condition, the data that the business record according to itself storage carries out cluster are restored；Recovery condition includes having nodes break down in cluster starting or cluster.The present invention by saving the business records of whole nodes in real time in host node, so that the data that direct basis host node itself stores when needing cluster recovery, improve the speed of company-data recovery.The present invention also provides a kind of distributed type assemblies based on the above method.
Description
Technical field
The present invention relates to distributed type assemblies technical fields, more particularly to a kind of distributed type assemblies management method and one kind
Distributed type assemblies.
Background technique
The common Managed Solution in NAS network attached storage cluster, mainly by being run on all clustered nodes
One management software, then the management software is managed by the interaction of the message between different nodes.The cluster is being transported
During row, traditional operation reserve is that all nodes are common to be elected in cluster starting or nodes break down
Carry out a host node, then the recovery process of host node guidance cluster, the distribution etc. including resource.
When there is nodes break down, host node, which can control whole nodes in addition to itself, to be freezed, later host node according to
It is secondary that data are obtained out of each node database, functional rehabilitation and industry are carried out to the node in addition to malfunctioning node again later
The business of malfunctioning node (is drifted to the operation of other nodes) by business drift, thus restore the normal operation of cluster, cluster starting
When be also similarly, since host node needs to obtain the database data of each node when node failure and cluster occur and starting,
Therefore lead to that cluster starts or to restore normal process slower.
Therefore, how a kind of fireballing distributed type assemblies management method of cluster recovery is provided and distributed type assemblies are abilities
The current problem to be solved of field technique personnel.
Summary of the invention
The object of the present invention is to provide a kind of distributed type assemblies management method and distributed type assemblies, by real in host node
The business record of Shi Baocun whole node, so that the data that direct basis host node itself stores when needing cluster recovery are i.e.
Can, improve the speed of company-data recovery.
In order to solve the above technical problems, being applied to the cluster the present invention provides a kind of distributed type assemblies management method
Host node, the method includes：
It receives the business record that each node is sent in the cluster and is stored；
When the cluster meets recovery condition, the data that the business record according to itself storage carries out cluster are restored；Institute
Stating recovery condition includes having nodes break down in the cluster starting or the cluster.
Preferably, when having nodes break down in the cluster, the business record according to itself storage is collected
Group data restore process be specially：
After freezing whole nodes in addition to itself, recovery operation is carried out to non-malfunctioning node；
According to the business record of itself storage, described malfunctioning node, the business of the malfunctioning node is drifted into not event
It is run on barrier node.
Preferably, remaining node in the cluster in addition to host node is divided into multiple points according to default rule of classification
Group, each grouping is interior to elect base's host node to be managed a group interior nodes.
Preferably, when having nodes break down in the cluster, the business record according to itself storage is collected
Group data restore process be specially：
Whole nodes where freezing the malfunctioning node in grouping；
According to the business record of itself storage, described malfunctioning node, the business of the malfunctioning node is drifted to described
Operation in remaining grouping other than malfunctioning node.
Preferably, further include：
Several base's host nodes are selected according to default redundancy rule；
The business record that itself is saved is backed up in several selected base's host nodes.
Preferably, when having nodes break down in the cluster, the business record according to itself storage is collected
Group data restore process be specially：
Whole nodes where freezing the malfunctioning node in grouping；
Select the object grouping of carry out business drift；
If backup has the business record in base's host node of the object grouping, the base of the object grouping is notified
Layer host node, the business record of malfunctioning node stored for base's host node of object grouping according to itself, described, by institute
The business for stating malfunctioning node drifts to operation in the node being grouped where itself；
If the business record has been not backed up in base's host node of the object grouping, according to itself storage, institute
The business of the malfunctioning node is drifted in the node of the object grouping and is run by the business record for stating malfunctioning node.
Preferably, the host node is the cluster interior starting time earliest node.
In order to solve the above technical problems, the present invention also provides a kind of distributed type assemblies, including multiple nodes, one of them
As host node；
The host node, for receiving the business record of each node transmission in the cluster and being stored；Described
When cluster meets recovery condition, the data that the business record according to itself storage carries out cluster are restored；The recovery condition includes
There is nodes break down in the cluster starting or the cluster；
Remaining node in addition to host node is sent to the host node for executing group service, and by business record.
Preferably, remaining node in the cluster in addition to host node is divided into multiple points according to default rule of classification
Group, each grouping is interior to elect base's host node；Base's host node is for being managed a group interior nodes.
Preferably, the business record in the host node backs up to several bases master selected according to default redundancy rule
In node.
The present invention provides a kind of distributed type assemblies management method and distributed type assemblies, each node carries out business movement
Afterwards, business record can be sent to host node to store, so that the newest industry of the whole for being stored with entire cluster in host node
Business record, when cluster starts or when having nodes break down to need to carry out data recovery, due to host node stored whole
Business record, so when host node no longer need to obtain data one by one in the database of each node, but direct basis
The data itself saved can carry out the whole of cluster and restore, and the process of company-data recovery be simplified, to substantially increase
The speed that company-data restores.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to institute in the prior art and embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of flow chart of the process of distributed type assemblies management method provided by the invention；
Fig. 2 is a kind of structural schematic diagram of distributed type assemblies provided by the invention.
Specific embodiment
Core of the invention is to provide a kind of distributed type assemblies management method and distributed type assemblies, passes through real in host node
The business record of Shi Baocun whole node, so that the data that direct basis host node itself stores when needing cluster recovery are i.e.
Can, improve the speed of company-data recovery.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It is shown in Figure 1 applied to the host node of cluster the present invention provides a kind of distributed type assemblies management method, Fig. 1
For a kind of flow chart of the process of distributed type assemblies management method provided by the invention；This method includes：
Step s1：It receives the business record that each node is sent in cluster and is stored；
Cluster interior nodes can generate the business record of record traffic executive condition, in business during execution task
It has no progeny, is able to carry out business recovery according to these business records.In the prior art, the position that these business records save is orientation
In the database of node for executing the business, and the position that the business record of each node saves is redirected to by the present invention
In the database of host node, so that after each node generates business record, spontaneous can be sent to these business records
It is saved in host node.
Step s2：When cluster meets recovery condition, the data that the business record according to itself storage carries out cluster are restored；
Recovery condition includes having nodes break down in cluster starting or cluster.
In cluster starting, need to initialize clustered node, the data such as resource allocation, parameter setting restore behaviour
Make, restores each node in cluster to corresponding functions can be realized.When there is nodes break down, due to distributed type assemblies
In may influence each other between each node, complete a certain business jointly, therefore, can shadow when having nodes break down
Ringing other nodes also can not work normally, therefore, in order to realize that the business by malfunctioning node drifts to the operation of other normal nodes
Purpose, need first to other normal nodes carry out data recovery, so that other nodes is worked normally.
In a particular embodiment, when having nodes break down in cluster, the business record according to itself storage is collected
Group data restore process be specially：
After freezing whole nodes in addition to itself, recovery operation is carried out to non-malfunctioning node；
According to itself storage, malfunctioning node business record, the business of malfunctioning node is drifted on non-malfunctioning node
Operation.
It is understood that other nodes generally also will receive influence when due to there is nodes break down, therefore, in order to
Lower wrong execution business of nonserviceabling is avoided, the operation of normal node is influenced, it usually needs host node will be removed in entire cluster
Remaining outer node all freezes, and suspends business, and later, business record of the host node according to each node of storage will not
The data of the node of failure are restored, and non-malfunctioning node is enable to work normally, and construct on these non-malfunctioning nodes
The working environment of the business of malfunctioning node, business record of the last host node according to malfunctioning node, by malfunctioning node are carried out
Business is drifted on non-malfunctioning node and is run, and business is enable to operate normally.
In an advantageous embodiment, remaining node in cluster in addition to host node is divided into according to default rule of classification
Multiple groupings, each grouping is interior to elect base's host node to be managed a group interior nodes.
It is understood that host node in addition to having the function of that data are restored, also needs to carry out pipe to whole nodes sometimes
Reason, and the present embodiment is by being grouped node, not every group node elects base's host node, so that node administration can
It is shared respectively by each base's host node, reduces the load pressure of the host node of cluster entirety.
Wherein, when grouping, the number of every group node can be set, and be successively grouped according to the sequence of node IP, finally not
The node of the foot number forms one group, such as every group 3；Alternatively, can also be grouped according to nodal function；Of every group node
Number can be the same or different, and the present invention does not limit specific grouping strategy.
Further, when having nodes break down in cluster, the business record according to itself storage carries out the number of cluster
It is specially according to the process of recovery：
Whole nodes where freezing malfunctioning node in grouping；
According to itself storage, malfunctioning node business record, the business of malfunctioning node is drifted to other than malfunctioning node
Remaining grouping in operation.
It is understood that when node is grouped, it can be by the setting of grouping strategy, so that each grouping is as far as possible
With more comprehensive function, in this way when cluster executes business, can be executed as unit of each grouping, different grouping
Between there is isolation as far as possible, so that when there is node failure, can only freeze grouping where malfunctioning node, or
Only freeze part relevant to Packet Service where malfunctioning node to be grouped, it is this without freezing whole nodes in cluster
In the case of, since part grouping is not freezed, business record that host node can be stored with direct basis itself, malfunctioning node,
The business of malfunctioning node is drifted in the grouping that do not freeze, thus the case where service disconnection caused by avoiding node from all freezing
Occur, improves the reliability of business execution.
In another preferred embodiment, it is based on above-mentioned grouping, this method further includes：
Several base's host nodes are selected according to default redundancy rule；
The business record that itself is saved is backed up in several selected base's host nodes.
It is understood that in order to improve the reliability of business, when avoiding host node failure, the case where node can not restore
Occur, can choose part base host node as redundancy, the business record that host node saves is stored to selected base
As backup in host node, the reliability of cluster is improved.
Wherein, in a preferred embodiment, whole base's host nodes may be selected and save business record as backup node
Backup, certainly, the selection number present invention of base's host node is not construed as limiting.
It is further known that based on the above embodiment, business when having nodes break down in cluster, according to itself storage
Record carry out cluster data restore process be specially：
Whole nodes where freezing malfunctioning node in grouping；
Select the object grouping of carry out business drift；
If backup has business record in base's host node of object grouping, the base's host node for notifying object to be grouped is supplied
Business record that base's host node of object grouping is stored according to itself, malfunctioning node, the business of malfunctioning node is drifted to
Operation in the node being grouped where itself；
It is storage, malfunctioning node according to itself if being not backed up business record in base's host node of object grouping
The business of malfunctioning node is drifted in the node of object grouping and is run by business record.
It is understood that when host node carries out data recovery and business drift, if the business of direct basis host node
If record carries out data recovery, the related data for saving host node is needed to be sent in base's host node of respective packets,
Then corresponding node is sent to by base's host node again, so that the time that data are restored is longer；And in the present embodiment, by
There is whole business records in backup in some or all of base's host node, therefore, if host node selects these bases at this time
Grouping where host node carries out data recovery or business drift, then does not need host node and transmit data, but directly benefit
With the business record kept in base's host node, the speed that data are restored and business is drifted about is improved, it is more efficient.
Wherein, host node can directly set to obtain in the present invention, can also be obtained by election, in a kind of specific embodiment
In, the election regulation of host node can be：
Itself starting time can be sent to every other node after each node starting；
After each node receives the starting time of other nodes transmission, it is compared with the starting time of oneself,
Start the triumph of morning time, if oneself is won, continues itself starting time being sent to other nodes, if oneself loses
It loses, then sets other side to the host node of oneself；After the starting time for receiving the transmission of other nodes again later, then it will receive
The starting time be compared with the starting time for the host node oneself being arranged, and set triumph side to the host node of oneself；
And so on, until whole nodes settings host node converge to it is same after until.Host node under this mode
For the node that the starting time in cluster is earliest.
Certainly, in other embodiments, the starting time can not also be compared between node, other parameters can be compared
Compared with to determine triumph side；Or above-mentioned more convergent mode can not also be used to determine host node, how the present invention is to electing master
Node is not construed as limiting.
In addition, the way to elect of base's host node can also use above-mentioned more convergent mode by being manually set,
Each node in each grouping sends itself parameter to other nodes respectively and is compared, winner's conduct after the completion of restraining
Base's host node, or other ways to elect can also be used, this is not limited by the present invention.
The present invention provides a kind of distributed type assemblies management method, after each node carries out business movement, business can be remembered
Record is sent to host node and is stored, so that the newest business record of the whole for being stored with entire cluster in host node, works as cluster
When starting or thering is nodes break down to need to carry out data recovery, due to the stored whole business record of host node, therefore
Host node no longer needs to obtain data one by one in the database of each node at this time, but the data that direct basis itself saves
It can carry out the whole of cluster to restore, simplify the process of company-data recovery, to substantially increase company-data recovery
Speed.
Shown in Figure 2 the present invention also provides a kind of distributed type assemblies, Fig. 2 is a kind of distribution provided by the invention
The structural schematic diagram of cluster.The cluster includes multiple nodes 3, one of to be used as host node 1；
Host node 1, for receiving the business record of each transmission of node 3 in cluster and being stored；Meet in cluster extensive
When multiple condition, the data that the business record according to itself storage carries out cluster are restored；Recovery condition includes cluster starting or cluster
Inside there is node 3 to break down；
Remaining node 3 in addition to host node 1 is sent to host node 1 for executing group service, and by business record.
Preferably, remaining node 3 in cluster in addition to host node 1 is divided into multiple groupings according to default rule of classification,
Base's host node 2 is elected in each grouping；Base's host node 2 is for being managed group interior nodes 3.
Preferably, the business record in host node 1 backs up to the main section of several bases selected according to default redundancy rule
In point 2.
The present invention provides a kind of distributed type assemblies, after each node carries out business movement, business record can be sent to
Host node is stored so that the newest business record of the whole for being stored with entire cluster in host node, when cluster starting or
When thering is nodes break down to need to carry out data recovery, due to the stored whole business record of host node, so when main section
It puts and obtains data in the database for no longer needing each node one by one, but the data that direct basis itself saves can carry out
The whole of cluster restores, and simplifies the process of company-data recovery, to substantially increase the speed of company-data recovery.
Above several specific embodiments are only the preferred embodiment of the present invention, and above several specific embodiments can be with
Any combination, the embodiment obtained after combination is also within protection scope of the present invention.It should be pointed out that for the art
For those of ordinary skill, relevant speciality technical staff deduced out in the case where not departing from spirit of that invention and concept thereof other change
Into and variation, should all be included in the protection scope of the present invention.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of distributed type assemblies management method, which is characterized in that applied to the host node of the cluster, the method includes：
It receives the business record that each node is sent in the cluster and is stored；
When the cluster meets recovery condition, the data that the business record according to itself storage carries out cluster are restored；It is described extensive
Multiple condition includes having nodes break down in the cluster starting or the cluster.
2. the method according to claim 1, wherein when having nodes break down in the cluster, it is described according to
It is specially according to the process that the data that the business record of itself storage carries out cluster are restored：
After freezing whole nodes in addition to itself, recovery operation is carried out to non-malfunctioning node；
According to the business record of itself storage, described malfunctioning node, the business of the malfunctioning node is drifted into non-failure section
It is run on point.
3. the method according to claim 1, wherein in the cluster remaining node in addition to host node according to
Default rule of classification is divided into multiple groupings, elects base's host node to carry out pipe to group interior nodes in each grouping
Reason.
4. according to the method described in claim 3, it is characterized in that, when having nodes break down in the cluster, it is described according to
It is specially according to the process that the data that the business record of itself storage carries out cluster are restored：
Whole nodes where freezing the malfunctioning node in grouping；
According to the business record of itself storage, described malfunctioning node, the business of the malfunctioning node is drifted into the failure
Operation in remaining grouping other than node.
5. according to the method described in claim 3, it is characterized in that, further including：
Several base's host nodes are selected according to default redundancy rule；
The business record that itself is saved is backed up in several selected base's host nodes.
6. according to the method described in claim 5, it is characterized in that, when having nodes break down in the cluster, it is described according to
It is specially according to the process that the data that the business record of itself storage carries out cluster are restored：
Whole nodes where freezing the malfunctioning node in grouping；
Select the object grouping of carry out business drift；
If backup has the business record in base's host node of the object grouping, the base master of the object grouping is notified
Node, the business record of malfunctioning node store for base's host node of object grouping according to itself, described will the event
The business of barrier node drifts to operation in the node being grouped where itself；
If being not backed up the business record in base's host node of the object grouping, according to itself storage, described event
The business of the malfunctioning node is drifted in the node of the object grouping and is run by the business record for hindering node.
7. method according to claim 1-6, which is characterized in that when the host node is starting in the cluster
Between earliest node.
8. a kind of distributed type assemblies, which is characterized in that including multiple nodes, one of them is as host node；
The host node, for receiving the business record of each node transmission in the cluster and being stored；In the cluster
When meeting recovery condition, the data that the business record according to itself storage carries out cluster are restored；The recovery condition includes described
There is nodes break down in cluster starting or the cluster；
Remaining node in addition to host node is sent to the host node for executing group service, and by business record.
9. distributed type assemblies according to claim 8, which is characterized in that remaining section in the cluster in addition to host node
Point is divided into multiple groupings according to default rule of classification, elects base's host node in each grouping；The base master
Node is for being managed a group interior nodes.
10. distributed type assemblies according to claim 9, which is characterized in that the business record in the host node backs up to
In several base's host nodes according to the selection of default redundancy rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810668217.8A CN108900331A (en) | 2018-06-26 | 2018-06-26 | A kind of distributed type assemblies management method and distributed type assemblies |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810668217.8A CN108900331A (en) | 2018-06-26 | 2018-06-26 | A kind of distributed type assemblies management method and distributed type assemblies |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108900331A true CN108900331A (en) | 2018-11-27 |
Family
ID=64346055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810668217.8A Pending CN108900331A (en) | 2018-06-26 | 2018-06-26 | A kind of distributed type assemblies management method and distributed type assemblies |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108900331A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111355600A (en) * | 2018-12-21 | 2020-06-30 | 杭州海康威视数字技术股份有限公司 | Method and device for determining main node |
| CN112751926A (en) * | 2020-12-29 | 2021-05-04 | 北京浪潮数据技术有限公司 | Method, system and related device for managing working nodes in cluster |
| CN114518963A (en) * | 2022-04-21 | 2022-05-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Edge information cooperative processing method and system for airborne end system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103095598A (en) * | 2012-12-17 | 2013-05-08 | 华中科技大学 | Monitoring data aggregate method under large-scale cluster environment |
| CN103139302A (en) * | 2013-02-07 | 2013-06-05 | 浙江大学 | Real-time copy scheduling method considering load balancing |
| CN104268274A (en) * | 2014-10-14 | 2015-01-07 | 华为技术有限公司 | Database journal recording method, device and system |
| CN106301938A (en) * | 2016-08-25 | 2017-01-04 | 成都索贝数码科技股份有限公司 | A kind of high availability and the data base cluster system of strong consistency and node administration method thereof |
| CN107678883A (en) * | 2017-09-22 | 2018-02-09 | 郑州云海信息技术有限公司 | A kind of cluster recovery method and apparatus based on storage system |
-
2018
- 2018-06-26 CN CN201810668217.8A patent/CN108900331A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103095598A (en) * | 2012-12-17 | 2013-05-08 | 华中科技大学 | Monitoring data aggregate method under large-scale cluster environment |
| CN103139302A (en) * | 2013-02-07 | 2013-06-05 | 浙江大学 | Real-time copy scheduling method considering load balancing |
| CN104268274A (en) * | 2014-10-14 | 2015-01-07 | 华为技术有限公司 | Database journal recording method, device and system |
| CN106301938A (en) * | 2016-08-25 | 2017-01-04 | 成都索贝数码科技股份有限公司 | A kind of high availability and the data base cluster system of strong consistency and node administration method thereof |
| CN107678883A (en) * | 2017-09-22 | 2018-02-09 | 郑州云海信息技术有限公司 | A kind of cluster recovery method and apparatus based on storage system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111355600A (en) * | 2018-12-21 | 2020-06-30 | 杭州海康威视数字技术股份有限公司 | Method and device for determining main node |
| CN111355600B (en) * | 2018-12-21 | 2023-05-02 | 杭州海康威视数字技术股份有限公司 | Main node determining method and device |
| CN112751926A (en) * | 2020-12-29 | 2021-05-04 | 北京浪潮数据技术有限公司 | Method, system and related device for managing working nodes in cluster |
| CN112751926B (en) * | 2020-12-29 | 2023-05-26 | 北京浪潮数据技术有限公司 | Management method, system and related device for working nodes in cluster |
| CN114518963A (en) * | 2022-04-21 | 2022-05-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Edge information cooperative processing method and system for airborne end system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3768775B2 (en) | Backup apparatus and backup method | |
| CN109729129A (en) | Configuration modification method, storage cluster and the computer system of storage cluster | |
| US5299207A (en) | Centralized supervisory system for transmission network elements and method of supervising transmission network elements | |
| EP2492813A2 (en) | Method And Systems For Validating Accessibility And Currency Of Replicated Data | |
| CN109474465A (en) | A kind of method and system of the high availability that can dynamically circulate based on server cluster | |
| CN108900331A (en) | A kind of distributed type assemblies management method and distributed type assemblies | |
| TWI701916B (en) | Method and device for self-recovering management ability in distributed system | |
| CN105095008B (en) | A kind of distributed task scheduling fault redundance method suitable for group system | |
| CN108173971A (en) | A kind of MooseFS high availability methods and system based on active-standby switch | |
| CN102394914A (en) | Cluster brain-split processing method and device | |
| CN103888277A (en) | Gateway disaster recovery backup method, apparatus and system | |
| CN109446178A (en) | A kind of Hadoop object storage high availability method, system, device and readable storage medium storing program for executing | |
| CN110333986B (en) | Method for guaranteeing availability of redis cluster | |
| CN109669820A (en) | Task monitoring and managing method and device based on Kettle | |
| CN107153660A (en) | The fault detect processing method and its system of distributed data base system | |
| CN105227385A (en) | A kind of method and system of troubleshooting | |
| CN105915426A (en) | Failure recovery method and device of ring network | |
| CN114338670B (en) | Edge cloud platform and network-connected traffic three-level cloud control platform with same | |
| CN117061512A (en) | Distributed information management method and system based on big data | |
| JPH0314161A (en) | Processor monitoring processing system | |
| CN104794026B (en) | A kind of failover method of cluster instance multi-data source binding | |
| US20160164719A1 (en) | Fault tolerance method for distributed stream processing system | |
| WO2002001347A2 (en) | Method and system for automatic re-assignment of software components of a failed host | |
| CN109508261A (en) | A kind of electric network data node standby method and standby system based on big data | |
| CN108833189A (en) | A kind of memory node management system and method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |