CN105827678A - High-availability framework based communication method and node - Google Patents
High-availability framework based communication method and node Download PDFInfo
- Publication number
- CN105827678A CN105827678A CN201510006672.8A CN201510006672A CN105827678A CN 105827678 A CN105827678 A CN 105827678A CN 201510006672 A CN201510006672 A CN 201510006672A CN 105827678 A CN105827678 A CN 105827678A
- Authority
- CN
- China
- Prior art keywords
- node
- cluster
- sub
- main access
- operation request
- 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
Landscapes
- Multi Processors (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a high-availability framework based communication method and a node. The communication method is characterized in that a main access node only needs to perform network communication with one service node and can forward a data operation required to be carried out to other service nodes in the cluster through the service node based on a high-availability cluster database environment, thereby achieving a purpose that data of each service node is operated synchronously. The communication method provided by the embodiment of the invention further has the characteristics of few level and simple path on the basis of not requiring the main access node to carry out the same operation on the multiple nodes, reducing repetitive operations, and not requiring the main access node to establish network connection with the multiple nodes and send the same operation content which reduces the resource utilization rate of a communication network. The efficiency of data operations is improved. A problem of complex management is avoided.
Description
Technical field
The present invention relates to communication, distributed type assemblies field, particularly relate to a kind of based on the communication means under High Availabitity framework and node.
Background technology
Present distributed type assemblies data base commonly used multinode data base concurrency mode of operation, such as DB2DPF framework etc., is distributed to different nodes to improve the degree of parallelism of read-write operation by mass data by certain algorithm.While considering to improve executed in parallel efficiency, in order to ensure the high availability of data, also require that between different nodes and the data of other node can be backed up accordingly, so that in the case of some node occurs extremely, other node can substitute this node and proceed work, so that the external service of total system can be carried out as usual, this namely the high availability of so-called distributed type assemblies data base.
In the distributed type assemblies database environment of High Availabitity, owing to the data of same content all exist backup at multiple nodes, when needs carry out data manipulation, data on each node will be carried out consistency operation, to ensure the data consistent of each node, namely on the premise of cloth parallel work-flow advantage of not losing points, ensure high availability and the data consistency of data base simultaneously.
At present, in order to ensure data consistency, based on the communication means under High Availabitity framework mainly, main access node first passes through network and is connected to all nodes with this data backup, the most respectively each node is carried out identical data manipulation, the purpose consistent to reach each node data, network architecture diagram now is as shown in Figure 1.
But this communication mode at least there is problems in that
1, multiple spot is standby mutually exists repetitive operation
When the identical data of the main access node multiple nodes in distributed type assemblies data base carries out same operation, identical data will be there is and calculate the situation that repeatedly (number of repetition is depending on number of nodes) is carried out, this can be greatly improved system resources consumption amount, thus seriously reduces the execution efficiency of data manipulation.
2, tradition one-to-many communication network resource utilization rate is low
Main access node is set up network generally by distributed type assemblies data base's external network to the multiple node of distributed type assemblies data store internal and is connected and send identical operation content.Identical data content is repeatedly carried out network transmission, and this can become several times to increase network data conveying capacity, considerably increases network data and transmits pressure, thus seriously reduces distributed type assemblies data base's external network service efficiency.
3, there is joint behavior Bucket Principle
When main access node carries out operating result confirmation to each node, need to wait that the operation on multiple node all confirms complete, just can determine that whether this operation completes.Owing to the process performance of each node is not quite similar, the most main access node has to wait that the nodal operation that in multiple node, performance is worst is complete, just can confirm that and has this time operated.During this, other performance preferably node is in stagnation waiting state, and distributed type assemblies data base's entirety service efficiency is low.
Based in the another kind of communication means under High Availabitity framework, it is provided that most preferably balance replication overhead and the method and system of consistency level that a kind of distributed data replicates.Progressively data are distributed to follow-up node by hierarchical fashion, so that it is determined that optimum link.Network architecture diagram now as in figure 2 it is shown, in system 10, including multiple private servers 12 arranged according to predetermined hierarchy, multiple leaf node D-server 20, multiple intermediate node D servers 16, a root node D-server 14.System 10 also includes multiple and special domain or weave connection and is referred to as the resource discovery server of O-server 22, distributed O-server is across wide area network 18 and D server communication, additionally, other O-server can also be by one or more LANs 24 and D server communication.
This under level distribution realizes by the way of communication, although communication performance is optimized relative to the first implementation, but there are still the problems such as level is too much, path is irregular, level is crossed the efficiency of data manipulation at most and is yet suffered from bottleneck, and path is irregular, can cause complex management.
Summary of the invention
The embodiment of the present invention provides a kind of based on the communication means under High Availabitity framework and node, for improving the efficiency of data manipulation, and reduces the complexity of management.
A kind of based on the communication means under High Availabitity framework, described method includes:
Agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database is set up network with main access node and is connected；
Set up, with main access node, the agent node that network is connected, determine sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to；
The agent node that network is connected is set up with main access node, agent node in each sub-cluster related to data manipulation respectively is set up cluster interior nodes and is connected, and send the second data operation request, wherein, agent node in the sub-cluster that each data manipulation relates to is according to the second data operation request received, node relevant to data manipulation in indicating this cluster performs data manipulation, and at the end of determining the data manipulation of this sub-cluster interior nodes, the data manipulation collecting this sub-cluster interior nodes performs result；
The agent node that network is connected is set up with main access node, the sub-cluster related to for each data manipulation, receive the data manipulation reported after the agent node in this sub-cluster collects and perform result, and perform the data manipulation that each agent node is reported to be sent to main access node after result collects；
Wherein, described sub-cluster is according to the first rule set in advance, divides the node in described high-available distributed Cluster Database and obtains, and divides in the sub-cluster obtained, and at least one sub-cluster interior joint quantity is no less than two；Agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster.
A kind of node, described node includes:
Network connecting module, is connected for setting up network with main access node；
Determine module, for determining the sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to, wherein, described sub-cluster is according to the first rule set in advance, node in described high-available distributed Cluster Database divided and obtains, and dividing in the sub-cluster obtained, at least one sub-cluster interior joint quantity is no less than two；
Cluster link block, it is connected for setting up cluster interior nodes with the agent node determined in each sub-cluster that the data manipulation that module is determined relates to respectively, and transmission determines the second data operation request that module is determined, wherein, agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster；
Receiver module, for the sub-cluster related to for each data manipulation, receives the data manipulation reported after the agent node in this sub-cluster collects and performs result, and receive the second data operation request；
Perform module, for the second data operation request received according to receiver module, node relevant to data manipulation in indicating this cluster performs data manipulation, and at the end of determining the data manipulation of this sub-cluster interior nodes, the data manipulation collecting this sub-cluster interior nodes performs result, reports and sets up, with main access node, the agent node that network is connected；
Sending module, is sent to main access node after the data manipulation receiving receiver module execution result being collected.
A kind of node, described node includes:
First link block, is connected for setting up network with main access node, and receives the first data operation request that main access node sends；
Processing module, for the first data operation request of receiving according to the first link block, determines sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to；
Second link block, it is connected for setting up network with the agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database, and sub-cluster information and the second data operation request information processing module determined is sent to and this agent node, wherein, described sub-cluster is according to the first rule set in advance, node in described high-available distributed Cluster Database divided and obtains, and dividing in the sub-cluster obtained, at least one sub-cluster interior joint quantity is no less than two；Agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster.
The scheme provided according to embodiments of the present invention, company-data lab environment based on High Availabitity, main access node needs only to carry out network service with a wherein service node, just other service node data manipulation to be performed can being forwarded in cluster by this service node up, to reach the purpose of each service node data syn-chronization operation.Same operation is being carried out to multiple nodes without main access node, reduce repetitive operation, set up network without main access node to multiple nodes connect and send identical operation content, on the basis of reducing communication network resource utilization rate, there is also level few, the simple feature in path, improve the efficiency of data manipulation, it is to avoid the problem of complex management.
Accompanying drawing explanation
A kind of network architecture diagram that Fig. 1 provides for prior art；
A kind of network architecture diagram that Fig. 2 provides for prior art；
The flow chart of steps of the communication means that Fig. 3 provides for the embodiment of the present invention one；
The network architecture schematic diagram that Fig. 4 provides for the embodiment of the present invention one；
The flow chart of steps of the communication means that Fig. 5 provides for the embodiment of the present invention two；
The node structure schematic diagram that Fig. 6 provides for the embodiment of the present invention three；
The node structure schematic diagram that Fig. 7 provides for the embodiment of the present invention four.
Detailed description of the invention
The present invention program provides a kind of based on the packet chain type forwarding communication plan under High Availabitity framework.Program company-data based on High Availabitity lab environment.First by whole node grouping inside Cluster Database, main access node need only to cluster in arbitrarily in group certain service node (referred to as agent node) carry out network service, the agent node just data manipulation to be performed can being in parallel distributed in other group by this node is in order to complete concurrent reading and concurrent writing.Proprietary high-speed internal communication network between each group node in depending on cluster, main access node only by just understanding the operation implementation status of each group interior nodes in real time with initial agent node communication.
Below in conjunction with Figure of description, the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred embodiment described herein is merely to illustrate and explains the present invention, is not intended to limit the present invention.And in the case of not conflicting, the embodiment in the application and the feature in embodiment can be mutually combined.
Embodiment one,
The embodiment of the present invention one provides a kind of based on the communication means under High Availabitity framework, and the flow chart of steps of this communication means can be as it is shown on figure 3, include:
Step 101, agent node are set up network with main access node and are connected.
In this step, the agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database is set up network with main access node and is connected.
Concrete, agent node directly can be set up network with main access node and be connected, it is also possible to sets up network by pretreatment node with main access node and is connected.
If the network connection establishment failure of agent node and main access node, then can be to main access node reverts back error message to circulate a notice of unusual condition, and process ends.
Wherein, described sub-cluster is according to the first rule set in advance, divides the node in described high-available distributed Cluster Database and obtains, and divides in the sub-cluster obtained, and at least one sub-cluster interior joint quantity is no less than two；Agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster.
Described first preset rules can be, but not limited to as random division, or for divide according to the context of at least one specific field of data in node.
Described second preset rules can be, but not limited to as randomly choosing, or is the resource service condition according to node, selects resource in a sub-cluster to use minimum node.
Concrete, in the resource service condition according to node, when selecting agent node, can be, but not limited to be accomplished by:
In each node deployment monitoring agent module, it is responsible for monitoring the resource service condition of this node, such as cpu busy percentage, IO utilization rate, network usage etc., timing simultaneously preserves to this locality from other node isochronous resources service conditions, such that it is able to realize the resource service condition according to node, select agent node.
Preferably, the node in a sub-cluster can pre-set priority, and synchronizing sequence can be carried out according to node priority.The resource service condition that oneself is all preserved by each node synchronizes to the upper priority node of oneself, and covers old time stamp data with up-to-date time stamp data.
Step 102, agent node determine the sub-cluster and the second data operation request that data manipulation relates to.
In this step, set up, with main access node, the agent node that network is connected, determine sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to.
It is connected if agent node directly sets up network with main access node, the most in this step, agent node receives the first data operation request that main access node sends, and determines, according to this first data operation request, the sub-cluster information and the second data operation request information that data manipulation relates to.
Being connected if agent node sets up network by pretreatment node with main access node, pretreatment node may be used for receiving the primary data operation requests that main access node sends, it is possible to primary data operation requests carries out follow-up agency's distribution, is equivalent to Access Layer.In this step, agent node can receive the sub-cluster information that relates to of data manipulation and the second data operation request information of the main access node request that pretreatment node sends, sub-cluster information and the second data operation request information that the data manipulation of main access node request relates to are the first data operation request that pretreatment node receives that main access node sends, and determine according to this first data operation request.
Step 103, agent node are set up cluster interior nodes and are connected.
In this step, setting up the agent node that network is connected with main access node, the agent node in each sub-cluster related to data manipulation respectively is set up cluster interior nodes and is connected, and sends the second data operation request.
Certainly, if the sub-cluster that data manipulation relates to includes the sub-cluster setting up the agent node place that network is connected with main access node, then can be understood as setting up the agent node that network is connected with main access node to establish cluster interior nodes with self and be connected, and to self sending the second data operation request.
Concrete, in this step, the agent node that network is connected is set up with main access node, when agent node in the sub-cluster related to data manipulation sets up cluster interior nodes connection failure, indicate this sub-cluster according to Second Rule set in advance, redefine agent node, and the agent node redefined out with this is set up cluster interior nodes and is connected.
Agent node in the sub-cluster that each data manipulation relates to is according to the second data operation request received, node relevant to data manipulation in indicating this cluster performs data manipulation, and at the end of determining the data manipulation of this sub-cluster interior nodes, the data manipulation collecting this sub-cluster interior nodes performs result.
Data manipulation is performed result and is sent to main access node by step 104, agent node.
In this step, the agent node that network is connected is set up with main access node, the sub-cluster related to for each data manipulation, receive the data manipulation reported after the agent node in this sub-cluster collects and perform result, and perform the data manipulation that each agent node is reported to be sent to main access node after result collects.
After step 103, it is also possible to include step 103 execution of ', step 103 ' be not limited to as shown in Figure 3 before step 104.
Step 103 ', agent node to main access node send data operation request confirm reception information.
Set up, with main access node, the agent node that network is connected, send data operation request to main access node and confirm reception information, indicate main access node to send new data operation request.
It should be noted that this step the process of each sub-cluster execution data manipulation can be carried out with step 103 simultaneously.
The schematic network structure that this communication means relates to can be as shown in Figure 4.It is divided into three sub-cluster with Cluster Database, it is respectively sub-cluster 1, sub-cluster 2 and sub-cluster 3, main access node (Client) is set up as a example by network is connected by pretreatment node with the agent node (Node1-1) in the sub-cluster 1 randomly choosed, assuming that the data manipulation that main access node is asked relates to sub-cluster 2 and sub-cluster 3, Node1-1 can set up cluster interior nodes with the agent node Node2-1 in sub-cluster 2, the agent node Node3-1 in sub-cluster 3 respectively and be connected.And agent node may indicate that the interior node relevant to data manipulation of this cluster performs data manipulation, as shown in Figure 4, the node that Node1-1, Node2-1 are relevant to data manipulation all may indicate that this cluster with Node3-1 in performs data manipulation.
The scheme provided the embodiment of the present invention one below by a concrete example illustrates.
Embodiment two,
The embodiment of the present invention two provides a kind of based on the communication means under High Availabitity framework, directly sets up as a example by network is connected with Client by agent node and illustrates, and the flow chart of steps of this communication means can be as it is shown in figure 5, include:
Step 201, Client set up network with agent node Node1-1 and are connected.
In this step, Client sends network connecting request to Cluster Database, sets up network with the agent node Node1-1 in the sub-cluster 1 randomly choosed and is connected.
Step 202, Client send initial data operation requests.
In this step, Client can send initial data operation requests (the first data operation request) to Node1-1, Node1-1 determines, according to this request, the sub-cluster that data manipulation relates to, it is possible to determine the data operation request (the second data operation request) needing to forward to other sub-cluster accordingly.
Step 203, Node1-1 set up cluster interior nodes and connect.
Assume that the sub-cluster that Node1-1 determines that data manipulation relates to is sub-cluster 2 and sub-cluster 3, the most in this step, Node1-1 can be with the agent node Node2-1 in sub-cluster 2, and the agent node Node3-1 in sub-cluster 3 sets up cluster interior nodes and connects at a high speed.
It is the most successful that step 204, Node1-1 determine that cluster interior nodes connects.
In this step, Node1-1 can be according to setting up whether successful connection judges whether to need to select new agent node in other sub-cluster.This step is operation in cluster, transparent to Client.
If Node1-1 determines cluster interior nodes successful connection, then can send the second data operation request to the agent node of successful connection.Otherwise, may indicate that the sub-cluster at the agent node place of connection failure reselects agent node, until determining cluster interior nodes successful connection.
Step 205, Node1-1 send data operation request to Client and confirm reception information.
Node1-1 is determining cluster interior nodes successful connection, and after the agent node of successful connection sends the second data operation request, can send data operation request to Client and confirm reception information.Client upon receiving this information, can send new data operation request to Cluster Database.
Before Client sends new data operation request, new network can be set up with the agent node (being probably the agent node outside Node1-1) in the sub-cluster again randomly choosed out and be connected.
Step 206, each sub-cluster perform data manipulation.
In this step, data manipulation performs in being dispersed to each sub-cluster respectively.Data manipulation can be performed result and be aggregated into the agent node of this sub-cluster by each node.
Step 207, Node1-1 reported information are to Client.
In this step, Node1-1 can receive the data manipulation of this cluster interior nodes reported after each agent node collects and perform result, and returns the data manipulation execution result collecting each sub-cluster interior nodes obtained to Client.
The scheme that the embodiment of the present invention one and embodiment two provide is on the premise of in cluster, each nodal parallel performs, it is proposed that a kind of concordance guaranteeing data manipulation based on the packet chain type forwarding communication means under High Availabitity framework.By arranging sub-cluster and agent node in the cluster, i.e. first selected agent node by rule set in advance, communication in sub-cluster and the transmission of the task between sub-cluster, solve the problem of inefficiency present in current communication methods, so that the performance of each node consistency data manipulation of cluster is to optimum.
With the embodiment of the present invention one, two based on same inventive concept, it is provided that following node.
Embodiment three,
The embodiment of the present invention three provides a kind of node, the structural representation of this node can as shown in Figure 6, including:
Network connecting module 11 is connected for setting up network with main access node；
Determine sub-cluster information and the second data operation request information that the data manipulation that module 12 is asked relates to for determining main access node, wherein, described sub-cluster is according to the first rule set in advance, node in described high-available distributed Cluster Database divided and obtains, and dividing in the sub-cluster obtained, at least one sub-cluster interior joint quantity is no less than two；
Cluster link block 13 is connected for setting up cluster interior nodes with the agent node determined in each sub-cluster that the data manipulation that module is determined relates to respectively, and transmission determines the second data operation request that module is determined, wherein, agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster；
Receiver module 14, for the sub-cluster related to for each data manipulation, receives the data manipulation reported after the agent node in this sub-cluster collects and performs result, and receive the second data operation request；
Perform module 15 for the second data operation request received according to receiver module, node relevant to data manipulation in indicating this cluster performs data manipulation, and at the end of determining the data manipulation of this sub-cluster interior nodes, the data manipulation collecting this sub-cluster interior nodes performs result, reports and sets up, with main access node, the agent node that network is connected；
Sending module 16 is sent to main access node after the data manipulation receiving receiver module execution result being collected.
Described determine that module 12, specifically for receiving the first data operation request that main access node sends, determines, according to this first data operation request, the sub-cluster information and the second data operation request information that data manipulation relates to.
Described network connecting module 11 is connected specifically for setting up network by pretreatment node with main access node；
The described sub-cluster information that relates to of data manipulation determining main access node request that module 12 sends specifically for receiving pretreatment node and the second data operation request information, sub-cluster information and the second data operation request information that the data manipulation of main access node request relates to are the first data operation request that pretreatment node receives that main access node sends, and determine according to this first data operation request.
Described sending module 16 is additionally operable to send data operation request to main access node and confirms reception information, indicates main access node to send new data operation request.
When described cluster link block 13 sets up cluster interior nodes connection failure specifically for the agent node in the sub-cluster related to data manipulation, indicate this sub-cluster according to Second Rule set in advance, redefine agent node, and the agent node redefined out with this is set up cluster interior nodes and is connected.
Embodiment four,
The embodiment of the present invention four provides a kind of node, the structural representation of this node can as it is shown in fig. 7, comprises:
First link block 21 is connected for setting up network with main access node, and receives the first data operation request that main access node sends；
Processing module 22 for the first data operation request received according to the first link block, determines sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to；
Second link block 23 is connected for setting up network with the agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database, and sub-cluster information and the second data operation request information processing module determined is sent to and this agent node, wherein, described sub-cluster is according to the first rule set in advance, node in described high-available distributed Cluster Database divided and obtains, and dividing in the sub-cluster obtained, at least one sub-cluster interior joint quantity is no less than two；Agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster.
Various embodiments of the present invention provide scheme relative to prior art, main advantage at least include following some:
1, avoid Data duplication to calculate, save resource
In the present invention program, Client end is without carrying out double counting work, after only needing agent node (or pretreatment node) that data are carried out one-time calculation, operation requests after being calculated by agent node again is sent to other agent node, it is ensured that the efficient utilization of Client end resource.
2, cluster outside network resource utilization rate is high
In the present invention program, Client only needs to send once-through operation to cluster environment to be asked.And non-conventional mode needs operation requests sends n time (n node), it is greatly saved cluster outside network resource utilization rate thus increases the Client handling capacity to collection pocket transmission operation requests further.
3, the problem that there is not joint behavior Bucket Principle
The present invention program is to be carried out by the way of other agent node Node2-1, Node3-1 carry out operation requests forwarding by agent node Node1-1, the data manipulation of each node is separate, the agent node made new advances can be elected to continue executing with task in the case of occurring extremely, reward data will not be sent to Client again.Constitute the cluster environment that each nodal operation progress is separate.Therefore, even if the performance difference of different node, owing to the operation process progress of each node is separate, the node that performance is good also will not be tied down by the node of poor performance.Thus ensure that each joint behavior plays to greatest extent.
4 it addition, the most there is not level too much in the scheme that the present invention provides, and the efficiency of data manipulation yet suffers from bottleneck, and, the problem of the complex management that path complexity causes.
Those skilled in the art are it should be appreciated that embodiments herein can be provided as method, system or computer program.Therefore, the form of the embodiment in terms of the application can use complete hardware embodiment, complete software implementation or combine software and hardware.And, the application can use the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code.
The application is with reference to describing according to method, equipment (system) and the flow chart of computer program and/or the block diagram of the embodiment of the present application.It should be understood that can be by the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device so that the instruction performed by the processor of computer or other programmable data processing device is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing device work in a specific way, the instruction making to be stored in this computer-readable memory produces the manufacture including command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make to perform sequence of operations step on computer or other programmable devices to produce computer implemented process, thus the instruction performed on computer or other programmable devices provides the step of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame for realization.
Although having been described for the preferred embodiment of the application, but those skilled in the art once know basic creative concept, then these embodiments can be made other change and amendment.So, claims are intended to be construed to include preferred embodiment and fall into all changes and the amendment of the application scope.
Obviously, those skilled in the art can carry out various change and modification without deviating from spirit and scope to the application.So, if these amendments of the application and modification belong within the scope of the application claim and equivalent technologies thereof, then the application is also intended to comprise these change and modification.
Claims (13)
1. one kind based on the communication means under High Availabitity framework, it is characterised in that described method includes:
Agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database is set up network with main access node and is connected；
Set up, with main access node, the agent node that network is connected, determine sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to；
The agent node that network is connected is set up with main access node, agent node in each sub-cluster related to data manipulation respectively is set up cluster interior nodes and is connected, and send the second data operation request, wherein, agent node in the sub-cluster that each data manipulation relates to is according to the second data operation request received, node relevant to data manipulation in indicating this cluster performs data manipulation, and at the end of determining the data manipulation of this sub-cluster interior nodes, the data manipulation collecting this sub-cluster interior nodes performs result；
The agent node that network is connected is set up with main access node, the sub-cluster related to for each data manipulation, receive the data manipulation reported after the agent node in this sub-cluster collects and perform result, and perform the data manipulation that each agent node is reported to be sent to main access node after result collects；
Wherein, described sub-cluster is according to the first rule set in advance, divides the node in described high-available distributed Cluster Database and obtains, and divides in the sub-cluster obtained, and at least one sub-cluster interior joint quantity is no less than two；Agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster.
2. the method for claim 1, it is characterised in that set up the agent node that network is connected with main access node, determines sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to, specifically includes:
Set up, with main access node, the agent node that network is connected, receive the first data operation request that main access node sends, determine, according to this first data operation request, the sub-cluster information and the second data operation request information that data manipulation relates to.
3. the method for claim 1, it is characterised in that the agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database is set up network with main access node and is connected, and specifically includes:
Agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database, sets up network by pretreatment node with main access node and is connected；
Set up, with main access node, the agent node that network is connected, determine sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to, specifically include:
The agent node that network is connected is set up with main access node, receive the sub-cluster information that relates to of data manipulation and the second data operation request information of the main access node request that pretreatment node sends, sub-cluster information and the second data operation request information that the data manipulation of main access node request relates to are the first data operation request that pretreatment node receives that main access node sends, and determine according to this first data operation request.
4. the method for claim 1, it is characterized in that, set up the agent node that network is connected with main access node, the agent node in each sub-cluster related to data manipulation respectively is set up cluster interior nodes and is connected, and after sending the second data operation request, described method also includes:
Set up, with main access node, the agent node that network is connected, send data operation request to main access node and confirm reception information, indicate main access node to send new data operation request.
5. the method for claim 1, it is characterised in that set up the agent node that network is connected with main access node, the agent node in each sub-cluster related to data manipulation respectively is set up cluster interior nodes and is connected, and specifically includes:
The agent node that network is connected is set up with main access node, when agent node in the sub-cluster related to data manipulation sets up cluster interior nodes connection failure, indicate this sub-cluster according to Second Rule set in advance, redefine agent node, and the agent node redefined out with this is set up cluster interior nodes and is connected.
6. the method as described in Claims 1 to 5 is arbitrary, it is characterised in that described first preset rules is random division, or for divide according to the context of at least one specific field of data in node.
7. the method as described in Claims 1 to 5 is arbitrary, it is characterised in that described second preset rules is for randomly choosing, or is the resource service condition according to node, selects resource in a sub-cluster to use minimum node.
8. a node, it is characterised in that described node includes:
Network connecting module, is connected for setting up network with main access node；
Determine module, for determining the sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to, wherein, described sub-cluster is according to the first rule set in advance, node in described high-available distributed Cluster Database divided and obtains, and dividing in the sub-cluster obtained, at least one sub-cluster interior joint quantity is no less than two；
Cluster link block, it is connected for setting up cluster interior nodes with the agent node determined in each sub-cluster that the data manipulation that module is determined relates to respectively, and transmission determines the second data operation request that module is determined, wherein, agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster；
Receiver module, for the sub-cluster related to for each data manipulation, receives the data manipulation reported after the agent node in this sub-cluster collects and performs result, and receive the second data operation request；
Perform module, for the second data operation request received according to receiver module, node relevant to data manipulation in indicating this cluster performs data manipulation, and at the end of determining the data manipulation of this sub-cluster interior nodes, the data manipulation collecting this sub-cluster interior nodes performs result, reports and sets up, with main access node, the agent node that network is connected；
Sending module, is sent to main access node after the data manipulation receiving receiver module execution result being collected.
9. node as claimed in claim 8, it is characterized in that, described determine module, specifically for receiving the first data operation request that main access node sends, determine, according to this first data operation request, the sub-cluster information and the second data operation request information that data manipulation relates to.
10. node as claimed in claim 8, it is characterised in that
Described network connecting module, is connected specifically for setting up network by pretreatment node with main access node；
Described determine module, specifically for receiving sub-cluster information and the second data operation request information that the data manipulation of the main access node request that pretreatment node sends relates to, sub-cluster information and the second data operation request information that the data manipulation of main access node request relates to are the first data operation request that pretreatment node receives that main access node sends, and determine according to this first data operation request.
11. node as claimed in claim 8, it is characterised in that described sending module, it is additionally operable to send data operation request to main access node and confirms reception information, indicate main access node to send new data operation request.
12. nodes as claimed in claim 8, it is characterized in that, described cluster link block, when setting up cluster interior nodes connection failure specifically for the agent node in the sub-cluster related to data manipulation, indicate this sub-cluster according to Second Rule set in advance, redefine agent node, and the agent node redefined out with this is set up cluster interior nodes and is connected.
13. 1 kinds of nodes, it is characterised in that described node includes:
First link block, is connected for setting up network with main access node, and receives the first data operation request that main access node sends；
Processing module, for the first data operation request of receiving according to the first link block, determines sub-cluster information and the second data operation request information that the data manipulation that main access node is asked relates to；
Second link block, it is connected for setting up network with the agent node in the sub-cluster randomly choosed in high-available distributed Cluster Database, and sub-cluster information and the second data operation request information processing module determined is sent to and this agent node, wherein, described sub-cluster is according to the first rule set in advance, node in described high-available distributed Cluster Database divided and obtains, and dividing in the sub-cluster obtained, at least one sub-cluster interior joint quantity is no less than two；Agent node in one sub-cluster is according to Second Rule set in advance, the node selected from the node of this sub-cluster.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510006672.8A CN105827678B (en) | 2015-01-07 | 2015-01-07 | Communication means and node under a kind of framework based on High Availabitity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510006672.8A CN105827678B (en) | 2015-01-07 | 2015-01-07 | Communication means and node under a kind of framework based on High Availabitity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105827678A true CN105827678A (en) | 2016-08-03 |
| CN105827678B CN105827678B (en) | 2019-03-05 |
Family
ID=56514740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510006672.8A Active CN105827678B (en) | 2015-01-07 | 2015-01-07 | Communication means and node under a kind of framework based on High Availabitity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105827678B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107295080A (en) * | 2017-06-19 | 2017-10-24 | 北京百度网讯科技有限公司 | Date storage method and server applied to distributed server cluster |
| CN109189575A (en) * | 2018-08-20 | 2019-01-11 | 北京奇虎科技有限公司 | A kind of Explore of Unified Management Ideas and device of more OpenStack clusters |
| CN109714183A (en) * | 2017-10-26 | 2019-05-03 | 阿里巴巴集团控股有限公司 | Data processing method and device in a kind of cluster |
| WO2020052322A1 (en) * | 2018-09-12 | 2020-03-19 | 华为技术有限公司 | Data processing method, device and computing node |
| CN112398905A (en) * | 2020-09-28 | 2021-02-23 | 联想(北京)有限公司 | Node and information synchronization method |
| CN112395334A (en) * | 2020-11-30 | 2021-02-23 | 浪潮云信息技术股份公司 | Method for dividing centerless distributed database cluster into a plurality of logic sub-clusters |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667034A (en) * | 2009-09-21 | 2010-03-10 | 北京航空航天大学 | Scalable monitoring system supporting hybrid clusters |
| CN102355413A (en) * | 2011-08-26 | 2012-02-15 | 北京邮电大学 | Method and system for unifying message space on large scale in real time |
| CN102739799A (en) * | 2012-07-04 | 2012-10-17 | 合一网络技术(北京)有限公司 | Distributed communication method in distributed application |
| CN103617231A (en) * | 2013-11-26 | 2014-03-05 | 国家电网公司 | Large data management system |
| CN103647797A (en) * | 2013-11-15 | 2014-03-19 | 北京邮电大学 | Distributed file system and data access method thereof |
| CN103647820A (en) * | 2013-12-09 | 2014-03-19 | 华为数字技术（苏州）有限公司 | Arbitration method and arbitration apparatus for distributed cluster systems |
| CN103905544A (en) * | 2014-03-25 | 2014-07-02 | 华为技术有限公司 | Cluster storage system and distribution method of nodes in cluster storage system |
| US20140301388A1 (en) * | 2013-04-06 | 2014-10-09 | Citrix Systems, Inc. | Systems and methods to cache packet steering decisions for a cluster of load balancers |
-
2015
- 2015-01-07 CN CN201510006672.8A patent/CN105827678B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667034A (en) * | 2009-09-21 | 2010-03-10 | 北京航空航天大学 | Scalable monitoring system supporting hybrid clusters |
| CN102355413A (en) * | 2011-08-26 | 2012-02-15 | 北京邮电大学 | Method and system for unifying message space on large scale in real time |
| CN102739799A (en) * | 2012-07-04 | 2012-10-17 | 合一网络技术(北京)有限公司 | Distributed communication method in distributed application |
| US20140301388A1 (en) * | 2013-04-06 | 2014-10-09 | Citrix Systems, Inc. | Systems and methods to cache packet steering decisions for a cluster of load balancers |
| CN103647797A (en) * | 2013-11-15 | 2014-03-19 | 北京邮电大学 | Distributed file system and data access method thereof |
| CN103617231A (en) * | 2013-11-26 | 2014-03-05 | 国家电网公司 | Large data management system |
| CN103647820A (en) * | 2013-12-09 | 2014-03-19 | 华为数字技术（苏州）有限公司 | Arbitration method and arbitration apparatus for distributed cluster systems |
| CN103905544A (en) * | 2014-03-25 | 2014-07-02 | 华为技术有限公司 | Cluster storage system and distribution method of nodes in cluster storage system |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10764369B2 (en) | 2017-06-19 | 2020-09-01 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Data storage method and server applicable to distributed server cluster |
| CN107295080A (en) * | 2017-06-19 | 2017-10-24 | 北京百度网讯科技有限公司 | Date storage method and server applied to distributed server cluster |
| CN109714183A (en) * | 2017-10-26 | 2019-05-03 | 阿里巴巴集团控股有限公司 | Data processing method and device in a kind of cluster |
| CN109189575A (en) * | 2018-08-20 | 2019-01-11 | 北京奇虎科技有限公司 | A kind of Explore of Unified Management Ideas and device of more OpenStack clusters |
| JP2021536642A (en) * | 2018-09-12 | 2021-12-27 | 華為技術有限公司Huawei Technologies Co., Ltd. | Data processing methods and devices, and computing nodes |
| CN110896404A (en) * | 2018-09-12 | 2020-03-20 | 华为技术有限公司 | Data processing method and device and computing node |
| CN110896404B (en) * | 2018-09-12 | 2021-09-14 | 华为技术有限公司 | Data processing method and device and computing node |
| WO2020052322A1 (en) * | 2018-09-12 | 2020-03-19 | 华为技术有限公司 | Data processing method, device and computing node |
| JP7192103B2 (en) | 2018-09-12 | 2022-12-19 | 華為技術有限公司 | DATA PROCESSING METHOD AND APPARATUS, AND COMPUTING NODE |
| US11558253B2 (en) | 2018-09-12 | 2023-01-17 | Huawei Technologies Co., Ltd. | Data processing method and apparatus, and computing node for updating container images |
| CN112398905A (en) * | 2020-09-28 | 2021-02-23 | 联想(北京)有限公司 | Node and information synchronization method |
| CN112398905B (en) * | 2020-09-28 | 2022-05-31 | 联想(北京)有限公司 | Node and information synchronization method |
| CN112395334A (en) * | 2020-11-30 | 2021-02-23 | 浪潮云信息技术股份公司 | Method for dividing centerless distributed database cluster into a plurality of logic sub-clusters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105827678B (en) | 2019-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105827678A (en) | High-availability framework based communication method and node | |
| US10015042B2 (en) | System and method for data replication using a single master failover protocol | |
| CN105335251B (en) | A kind of fault recovery method and system | |
| CN107453929B (en) | Cluster system self-construction method and device and cluster system | |
| JP3798661B2 (en) | Method for processing a merge request received by a member of a group in a clustered computer system | |
| CN103763155A (en) | Multi-service heartbeat monitoring method for distributed type cloud storage system | |
| CN105939389A (en) | Load balancing method and device | |
| CN105426427A (en) | MPP database cluster replica realization method based on RAID 0 storage | |
| CN109245926A (en) | Intelligent network adapter, intelligent network adapter system and control method | |
| CN108512753B (en) | Method and device for transmitting messages in cluster file system | |
| CN110377664A (en) | Method of data synchronization, device, server and storage medium | |
| CN114900449A (en) | Resource information management method, system and device | |
| CN116095145B (en) | Data control method and system of VPC cluster | |
| CN114168252A (en) | Information processing system and method, network scheme recommendation component and method | |
| CN111432438A (en) | Base station processing task real-time migration method | |
| CN104468674B (en) | Data migration method and device | |
| CN114338670B (en) | Edge cloud platform and network-connected traffic three-level cloud control platform with same | |
| CN112395313A (en) | Global sequence generation method and device, electronic equipment and computer storage medium | |
| CN113630317B (en) | Data transmission method and device, nonvolatile storage medium and electronic device | |
| CN108881452A (en) | A kind of method, apparatus and storage medium that data are synchronous | |
| US20240176762A1 (en) | Geographically dispersed hybrid cloud cluster | |
| EP3709173B1 (en) | Distributed information memory system, method, and program | |
| CN109947593B (en) | Data disaster tolerance method, system, strategy arbitration device and storage medium | |
| KR100492167B1 (en) | Shared-nothing database cluster server system and On-line scaling method | |
| CN108123822B (en) | Link processing method and link processing equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |