CN110071978A - A kind of method and device of cluster management - Google Patents
A kind of method and device of cluster management Download PDFInfo
- Publication number
- CN110071978A CN110071978A CN201910351626.XA CN201910351626A CN110071978A CN 110071978 A CN110071978 A CN 110071978A CN 201910351626 A CN201910351626 A CN 201910351626A CN 110071978 A CN110071978 A CN 110071978A
- Authority
- CN
- China
- Prior art keywords
- node
- monitored
- key value
- cryptographic hash
- hash
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- 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
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the present application provides a kind of method and device of cluster management, is related to field of communication technology, when needing to restart in the presence of newly-increased node or disengaging node to solve cluster, the longer problem of service delay caused by restarting process.The scheme of the embodiment of the present application includes: to obtain surviving node list, and surviving node list includes the internet protocol address that each node of connection is established with host node, then calculates the cryptographic Hash of the IP address of each node in surviving node list；According to the cryptographic Hash of the IP address of each node; each node is mapped to a position on Hash ring respectively; then it obtains to the corresponding key value to be monitored of monitored data; determine the corresponding cryptographic Hash of key value respectively to be monitored; and then the position that cryptographic Hash maps to Hash ring is corresponded to according to respectively key value to be monitored, determine the monitoring range of each node.
Description
Technical field
This application involves fields of communication technology, more particularly to a kind of method and device of cluster management.
Background technique
All things on earth Internet age, the data formatization processing of flood tide are the basis of big data analysis and machine learning, Fluentd
Log collection frame is a kind of data gathering tool, has the function of that data are acquired, filter, handle, write out, can be in memory
Various complex process are carried out to data.Currently, the mass data under big data environment, occurs based on the more of consistency
Fluentd case technology includes multiple Fluentd nodes that is, in cluster, and a Fluentd node is host node, remaining
Fluentd node can be used as from node and access host node.
Host node is accessed when there is newly-increased node, or has that when being detached from host node from node, it is right that host node needs again
Each node in cluster carries out load balancing, it may be assumed that recalculates the cryptographic Hash of each node, and respectively corresponding to monitored data
To the cryptographic Hash of monitoring key (key) value, used parameter includes number of nodes when due to calculating cryptographic Hash, and number of nodes is sent out
Changing, so the cryptographic Hash of calculated each node and respectively the cryptographic Hash of key value to be monitored changes, and then cause
After re-starting load balancing, the data that each node need to be monitored can change, and can generate the works such as more Data Migration
Make, cause the cluster reboot time longer, generates service delay.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of method and device of cluster management, to realize that it is newly-increased that cluster exists
When node or disengaging node need to restart, reduce service delay caused by restarting process.Specific technical solution is as follows:
In a first aspect, the embodiment of the present application provides a kind of method of cluster management, the method is applied to the master in cluster
Node, which comprises
Obtain surviving node list, the surviving node list include established with the host node connection each node it is mutual
Networking protocol IP address；
Calculate the cryptographic Hash of the IP address of each node in the surviving node list；
According to the cryptographic Hash of the IP address of each node, each node is mapped to a position on Hash ring respectively；
It obtains to the corresponding key value to be monitored of monitored data, determines the corresponding cryptographic Hash of key value respectively to be monitored；
The position that cryptographic Hash maps to the Hash ring is corresponded to according to respectively key value to be monitored, determines the monitoring model of each node
It encloses.
In one possible implementation, respectively key value to be monitored corresponds to cryptographic Hash and maps to the Hash basis
The position of ring determines the monitoring range of each node, comprising:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped on the Hash ring respectively
One position；
It will be according to the inverse time since key value to be monitored is in the position on the Hash ring for each key value to be monitored
Needle sequential search to first node be determined as the node for monitoring the key value to be monitored.
In one possible implementation, the method also includes:
When detecting the access of newly-increased node, the surviving node list is added in the newly-increased node, after obtaining update
Surviving node list；And/or
When detecting disconnection with the disengaging node connecting between the host node, the disengaging node is deposited from described
It is deleted in movable joint point list, obtains updated surviving node list.
In one possible implementation, it is described obtain updated surviving node list after, the method is also
Include:
Calculate the cryptographic Hash of the IP address of each node in updated surviving node list；
According to the cryptographic Hash of the IP address of each node in updated surviving node list, each node is mapped into institute respectively
State a position on Hash ring；
The position that the Hash ring is mapped to according to the respectively corresponding cryptographic Hash of key value to be monitored, determines updated survival
The monitoring range of each node in node listing.
In one possible implementation, after the acquisition surviving node list, the method also includes:
The dummy node of each node setting preset quantity in the respectively described surviving node list, a node are corresponding
Each dummy node pass through respectively node IP address and dummy node label mark；
Calculate the cryptographic Hash of the mark of each dummy node；
According to the cryptographic Hash of the IP address of each dummy node, each dummy node is mapped to one on the Hash ring respectively
A position.
In one possible implementation, respectively key value to be monitored corresponds to cryptographic Hash and maps to the Hash basis
The position of ring determines the monitoring range of each node, comprising:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped on the Hash ring respectively
One position；
For each key value to be monitored, since key value to be monitored is in the position on the Hash ring, by suitable counterclockwise
Sequence searches node and dummy node；
If first node found counterclockwise is dummy node, it is determined that the key value to be monitored is by looking into
The corresponding node of the dummy node found is monitored；Alternatively,
If first node found counterclockwise is not dummy node, it is determined that the key value to be monitored by
The node found is monitored.
In one possible implementation, in the basis, respectively key value to be monitored corresponds to cryptographic Hash and maps to the Kazakhstan
After the position of uncommon ring determines the monitoring range of each node, the method also includes:
The key value to be monitored for needing to monitor to each node sending node respectively, so that each node is monitored as needed
Key value to be monitored carry out data processing.
Second aspect, the embodiment of the present application provide a kind of device of cluster management, and described device is applied to the master in cluster
Node, described device include:
Module is obtained, for obtaining surviving node list, the surviving node list includes establishing to connect with the host node
The internet protocol address of each node connect；
Computing module, the cryptographic Hash of the IP address for calculating each node in the surviving node list；
Mapping block, the cryptographic Hash of the IP address of each node for being calculated according to the computing module, respectively by each section
Point maps to a position on Hash ring；
The acquisition module is also used to obtain key value to be monitored, and determines the corresponding cryptographic Hash of key value respectively to be monitored；
Determining module determines each for corresponding to the position that cryptographic Hash maps to the Hash ring according to respectively key value to be monitored
The monitoring range of node.
In one possible implementation, the determining module, is specifically used for:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped on the Hash ring respectively
One position；
It will be according to the inverse time since key value to be monitored is in the position on the Hash ring for each key value to be monitored
Needle sequential search to first node be determined as the node for monitoring the key value to be monitored.
In one possible implementation, described device further include:
Update module, for the surviving node being added in the newly-increased node and is arranged when detecting the access of newly-increased node
Table obtains updated surviving node list；And/or when the abscission joint for detecting disconnection and being connect between the host node
When point, the disengaging node is deleted from the surviving node list, obtains updated surviving node list.
In one possible implementation, the computing module is also used to calculate in updated surviving node list
The cryptographic Hash of the IP address of each node；
The mapping block is also used to the cryptographic Hash according to the IP address of each node in updated surviving node list,
Each node is mapped to a position on the Hash ring respectively；
The determining module is also used to map to the position of the Hash ring according to the respectively corresponding cryptographic Hash of key value to be monitored
It sets, determines the monitoring range of each node in updated surviving node list.
In one possible implementation, described device further include: setup module；
The setup module, for being respectively that the virtual of preset quantity is arranged in each node in the surviving node list
Node, the corresponding each dummy node of a node pass through the IP address of node and the label mark of dummy node respectively；
The computing module is also used to calculate the cryptographic Hash of the mark of each dummy node；
The mapping block is also used to the cryptographic Hash of the IP address according to each dummy node, respectively reflects each dummy node
It is incident upon a position on the Hash ring.
In one possible implementation, the determining module, is specifically used for:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped on the Hash ring respectively
One position；
For each key value to be monitored, since key value to be monitored is in the position on the Hash ring, by suitable counterclockwise
Sequence searches node and dummy node；
If first node found counterclockwise is dummy node, it is determined that the key value to be monitored is by looking into
The corresponding node of the dummy node found is monitored；Alternatively,
If first node found counterclockwise is not dummy node, it is determined that the key value to be monitored by
The node found is monitored.
In one possible implementation, described device further include:
Sending module, the key value to be monitored for needing to monitor to each node sending node respectively, so that each node
The key value to be monitored monitored as needed carries out data processing.
The third aspect, the embodiment of the present application provide a kind of server, which is the host node in cluster, the server
It include: processor and machine readable storage medium, the machine readable storage medium, which is stored with, to be executed by the processor
Machine-executable instruction, the processor promoted by the machine-executable instruction: realizing cluster described in first aspect
The method of management.
Fourth aspect, the embodiment of the present application also provides a kind of computer readable storage medium, the computer-readable storages
Dielectric memory contains computer program, and cluster pipe described in first aspect is realized when the computer program is executed by processor
The method of reason.
5th aspect, the embodiment of the present application also provides a kind of computer program products comprising instruction, when it is being calculated
When being run on machine, so that the method that computer executes cluster management described in above-mentioned first aspect.
Therefore, using method provided by the embodiments of the present application, host node can obtain surviving node list, and calculate survival section
Then each node is mapped to one on Hash ring by the cryptographic Hash of the IP address of each node in point list respectively according to cryptographic Hash
A position, then key value to be monitored is obtained, determine the corresponding cryptographic Hash of key value respectively to be monitored, and then according to respectively key value to be monitored
Corresponding cryptographic Hash maps to the position of Hash ring, determines the monitoring range that each node is monitored.
Compared with prior art, host node determines the monitoring range of each node according to Hash ring in the embodiment of the present application.I.e.
Make there are the newly-increased of node or be detached from, when re-starting load balancing, due to each node monitoring range by node and
Position of the key value to be monitored on Hash ring determines that not changed node can still map to identical position on Hash ring
It sets.And respectively position that key value to be monitored maps to Hash ring will not change, so the monitoring of not changed node
Range will not generally change.Only the node adjacent with the node of disengaging may need to monitor and have disengaged from node and be responsible for monitoring
Key value to be monitored；Or a part key value to be monitored that the node adjacent with newly-increased node need to be monitored is changed to by increasing node newly
It monitors.So the monitoring range of the only node adjacent with newly-increased node or disengaging node may change.Compared to existing
The corresponding key value to be monitored of each node changes after load balancing again in technology, using the method for the embodiment of the present application
When cluster changes, the influence generated to node not changed in surviving node list is smaller, compared to existing skill
Art can reduce service delay.
Certainly, implement the application any product or method it is not absolutely required to and meanwhile reach all the above excellent
Point.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of illustrative diagram of cluster provided by the embodiments of the present application；
Fig. 2 is a kind of flow chart of the method for cluster management provided by the embodiments of the present application；
Fig. 3 is a kind of illustrative diagram of Hash ring provided by the embodiments of the present application；
Fig. 4 is the flow chart of the method for another cluster management provided by the embodiments of the present application；
Fig. 5 is the illustrative diagram of another Hash ring provided by the embodiments of the present application；
Fig. 6 is the illustrative diagram of another Hash ring provided by the embodiments of the present application；
Fig. 7 is the illustrative diagram of another Hash ring provided by the embodiments of the present application；
Fig. 8 is a kind of structural schematic diagram of the device of cluster management provided by the embodiments of the present application；
Fig. 9 is a kind of structural schematic diagram of server provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
For convenience of understanding, the application scenarios of the embodiment of the present application are illustrated first, using the side of the embodiment of the present application
Method, if host node is not present in cluster, elects host node after cluster starts or restarts.Alternatively, in cluster operational process
In, each heartbeat message that host node transmission can be periodically received from node in cluster, thus whether to judge host node
Survival, if not receiving the heartbeat message that host node is sent out of node at least one continuous period, then it is assumed that host node is not deposited
It is living, then it needs to re-elect host node.
It is understood that other determine that the method whether host node survives is also applied for the application implementation in the prior art
Example.
The election principle of host node are as follows: in each node of cluster, select the highest node of version as host node, if version
This highest node then selects the smallest node of group number as host node there are the version of multiple or each node is identical.
Wherein, each node in cluster is the server in cluster, and host node permission with higher can manage work
For from each node of node.Connection can be established with host node as each node from node, then host node can be safeguarded each
The information of node, and determine the monitoring range of each node.
For example, node A, node B, node C and node D access main section as shown in Figure 1, management node is as host node
Point is four of host node from node.Wherein, each node in Fig. 1 can be the node for being equipped with Fluentd tool.
It should be noted that " monitoring " can refer to the data for obtaining other equipment.In the embodiment of the present application, wait monitor
Data are the data for needing to be obtained by the node in cluster, and key value to be monitored waits for monitored data for identifying one group.For example, one
Platform server generate data be used as to monitored data, then the server generate to the corresponding key value to be monitored of monitored data
It can be the IP address of the server.
The monitoring range of node refers to that node is responsible for the range to monitored data monitored, and monitoring range can be by wait monitor
Key value indicates.For example, if the monitoring range of node A is key value 1 to be monitored and key value 2 to be monitored, then it represents that node A needs to supervise
Listen key value 1 to be monitored corresponding corresponding to monitored data to monitored data, and key value 2 to be monitored.
Each node in the embodiment of the present application in cluster is as data processing tools, for monitoring and handling number to be monitored
According to.Wherein, it can be configured according to business demand to monitored data, will be stored in advance to the corresponding key value to be monitored of monitored data
In database.Each node listens to after monitored data, can treat monitored data according to actual business scenario and be handled, right
The method handled to monitored data can refer to the relevant technologies, the embodiment of the present application to this with no restriction.
It as an example, can will be each if cluster is responsible for collecting the daily record data of each game server of a game
The IP address of game server is stored in data device as key value to be monitored.To which host node can be according to the embodiment of the present application
The method of offer obtains key value to be monitored from database, and determines the key value to be monitored that each node need to be monitored, and will be from number
It is distributed to each node according to the key value to be monitored obtained in library, and then each node is monitored according to the key value to be monitored that host node distributes
The daily record data that key value corresponding server to be monitored generates.
Such as, however, it is determined that the key value to be monitored that node C is received is the IP address and game server 2 of game server 1
IP address, then node C monitors game server 1 and trip according to the IP address of game server 1 and the IP address of game server 2
The daily record data that server 2 of playing generates.In other words, what node C need to be monitored is game server 1 and game services to monitored data
The daily record data that device 2 generates.
In order to simplify cluster management, scene as shown in connection with fig. 1, the embodiment of the present application provides a kind of side of cluster management
Method, this method are applied to the host node in cluster, as shown in Fig. 2, this method comprises:
S201, surviving node list is obtained.
Wherein, surviving node list includes the Internet protocol (Internet that each node of connection is established with host node
Protocol, IP) address.
For example, host node can determine to include node A, node B, node C and node D in surviving node list in conjunction with Fig. 1
IP address.
S202, calculate surviving node list in each node IP address cryptographic Hash.
Each node, is mapped to a position on Hash ring by S203, the cryptographic Hash according to the IP address of each node respectively.
Wherein, host node can construct a Hash ring, and as an example, which may include 231- 1 position,
After determining the cryptographic Hash of IP address of each node, each node can be mapped to one on Hash ring by host node according to cryptographic Hash
Position.
Illustratively, as shown in figure 3, Hash can be respectively mapped to node A, node B, node C and the node D in Fig. 1
Aforementioned four node is briefly referred to as node A, node B, node C, node D in Fig. 3 by a position in ring.
S204, it obtains to the corresponding key value to be monitored of monitored data, determines the corresponding cryptographic Hash of key value respectively to be monitored.
In one embodiment, each node waits for that monitored data exists in the form of key-value (key-value).
For example, there are audit log, Update log, system logs for daily record data, then if cluster needs to handle daily record data
It can be using the mark of all kinds of logs as key value, using the daily record data of all kinds of logs as value value.It is to be understood that database
In store the marks of all kinds of logs, the key value to be monitored that host node is obtained from database is the mark of all kinds of logs.
For another example if cluster needs to handle the daily record data of 100 servers, it can be by the IP address of every server
As key value, the daily record data that every server is generated is as value value.It is to be understood that storing each clothes in database
The IP address of business device, the key value to be monitored that host node is obtained from database are the IP address of each server.
Wherein, host node can read each key value for needing to monitor from database, and calculate the cryptographic Hash of each key value.
S205, the position that cryptographic Hash maps to Hash ring is corresponded to according to respectively key value to be monitored, determines the monitoring model of each node
It encloses.
After host node determines that key value respectively to be monitored corresponds to cryptographic Hash, it may be determined that position of each cryptographic Hash on Hash ring,
And then respectively key value to be monitored is mapped to a position on Hash ring respectively.Then for each key value to be monitored, to
It monitors position of the key value on Hash ring to start, find according to sequence counter-clockwise first node is determined as being used to supervise
Listen the node of the key value to be monitored.
For example, it is assumed that key value to be monitored is key1 to key9, as shown in figure 3, can be according to the cryptographic Hash of key1 to key9 point
Key1 to key9 is not mapped on Hash ring.
By taking key1 as an example, according to sequence counter-clockwise, first begun looking for from position of the key1 on Hash ring is saved
Point is node A, then can determine that the node for monitoring the corresponding data of key1 is node A.It, can from Fig. 3 according to this method
To find out, node A can monitor key1 and key2；Node B can monitor key3, key4 and key5；Node C can be monitored
Key6, key7 and key8；Node D can monitor key9.
It is understood that after host node determines the monitoring range of each node, it can be respectively into surviving node list
Each node sends its and needs the key value to be monitored monitored, in order to which to monitor the key value to be monitored got corresponding for each node
Value value.
Using method provided by the embodiments of the present application, host node can obtain surviving node list, and calculate surviving node column
Then each node is mapped to a position on Hash ring according to cryptographic Hash by the cryptographic Hash of the IP address of each node in table respectively
It sets, then obtains key value to be monitored, determine the corresponding cryptographic Hash of key value respectively to be monitored, and then corresponding according to respectively key value to be monitored
Cryptographic Hash map to the position of Hash ring, determine the monitoring range that each node is monitored.
Compared with prior art, host node determines the monitoring range of each node according to Hash ring in the embodiment of the present application, i.e.,
Make there are the newly-increased of node or be detached from, when re-starting load balancing, due to each node monitoring range by node and
Position of the key value to be monitored on Hash ring determines that not changed node can still map to identical position on Hash ring
It sets, and the position that respectively key value to be monitored maps to Hash ring will not change, so the monitoring of not changed node
Range will not generally change.Only the node adjacent with the node of disengaging may need to monitor and have disengaged from node and be responsible for monitoring
Key value to be monitored；Or a part key value to be monitored that the node adjacent with newly-increased node need to be monitored is changed to by increasing node newly
It monitors.So the monitoring range of the only node adjacent with newly-increased node or disengaging node may change.Compared to existing
The corresponding key value to be monitored of each node changes after load balancing again in technology, using the method for the embodiment of the present application
When cluster changes, the influence generated to node not changed in surviving node list is smaller, compared to existing skill
Art can reduce service delay.
In addition, in the prior art, host node need to safeguard that metadata (meta) information of entire cluster, meta information describe
The configuration information of the index information of each node and each node, persistence status information etc., the number of meta information in current cluster
Very big according to measuring, once cluster needs are restarted, each node needs again by the information reporting of itself to host node, in order to host node
Regenerate meta information, it is seen that cluster management is heavier.And the method for using the embodiment of the present application, it needs to hand between each node
Mutual information is less, even if cluster reboot, host node need to only obtain the IP address of each node, and the index without obtaining each node is believed
Breath, configuration information, that is, persistence information etc., i.e. the meta information of the entire cluster of Maintenance free simplify cluster management work, can
Realizing the cluster management work of lightweight, rapidly realizing load balancing and restarting work.
When node in the cluster changes, such as when the newly-increased node of appearance or appearance disengaging node, need to collection
The monitoring range of node in group is adjusted, and after updating below to surviving node list, re-starts load balancing
Method is described, this method as shown in figure 4, specifically includes the following steps:
S401, when detect newly-increased node access when, by newly-increased node be added surviving node list, obtain updated deposit
Movable joint point list.
Wherein, when there is newly-increased node in cluster, which can request access host node, host node establish with
After the connection of newly-increased node, surviving node list can be added in the IP address of newly-increased node.
S402, when detecting the disengaging node connecting between disconnection and host node, will be disengaged from node from surviving node
It is deleted in list, obtains updated surviving node list.
After each node accesses host node, each node periodically can send heartbeat message to host node, and host node can base
Disengaging node is determined whether there is in the heartbeat message.
In one embodiment, host node can determine that each node in surviving node list is every Fixed Time Interval
It is no to be detached from.For example, if the period that each node sends heartbeat message is 60 seconds, if it is determined that not receiving certain beyond 100 seconds
The heartbeat message of node, it is determined that the node has disconnected the connection with host node, i.e., the node is to be detached from node, then can take off this
IP address from node is deleted from surviving node list.
It should be noted that the node that S401 and S402 is access host node changes for example and there is newly-increased node or de-
It is executed in the case where from node, therefore S401 and S402 may not be existed simultaneously.For example, increasing node newly if it exists, but do not deposit
It is being detached from node, then is only carrying out S401, does not execute S402；It is detached from node if it exists, but there is no newly-increased node, then only carries out
S402 does not execute S401；If not only there is newly-increased node, but also exist and be detached from node, then S401 and S402 is both needed to execute, but this Shen
Please embodiment do not limit S401 and S402 execute sequence.
S403, the cryptographic Hash for calculating the IP address of each node in updated surviving node list.
S404, according to the cryptographic Hash of the IP address of each node in updated surviving node list, each node is reflected respectively
It is incident upon a position on Hash ring.
Illustratively, as shown in Fig. 3,5, if having increased node E in surviving node list newly, i.e., updated surviving node column
It include the IP address of node A, node B, node C, node D and node E in table.It is understood that node A, node B, node
C, the IP address of node D does not change, so corresponding cryptographic Hash does not also change, so mapping to the position on Hash ring
Setting will not change.It, can be according to the cryptographic Hash by node after host node calculates the cryptographic Hash of the IP address of newly-increased node E
E maps to the corresponding position of Hash ring.
S405, the position that Hash ring is mapped to according to the respectively corresponding cryptographic Hash of key value to be monitored, determine updated survival
The monitoring range of each node in node listing.
Wherein it is possible to understand, respectively the corresponding cryptographic Hash of key value to be monitored does not change, so on Hash ring
Position also do not change, host node can be for each key value to be monitored, from position of the key value to be monitored on Hash ring
Start, find according to sequence counter-clockwise first node is determined as to be used to monitor the node of the key value to be monitored.
For example, as shown in figure 5, key1 is still monitored by node A, and due to having increased node E newly, counterclockwise, from
First node that position of the key2 on Hash ring is begun looking for is node E, so can determine the section for monitoring key2
Point is node E.As seen from Figure 5, the monitoring range of remaining node in addition to node A does not change, and node B can be monitored
Key3, key4 and key5；Node C can monitor key6, key7 and key8；Node D can monitor key9.
By Fig. 3 and Fig. 5 comparison it is found that using the embodiment of the present application method, when occurring newly-increased node in the cluster, though
Right the embodiment of the present application also needs to re-start load balancing, since position of the node A to node D on Hash ring does not become
Change, and position of the key1 to key9 on Hash ring does not also change.So the monitoring of Fig. 5 interior joint B, node C, node D
Range does not change, and the key2 that only node A is responsible for monitoring originally becomes being monitored by newly-increased node E, so will not produce
Raw more Data Migration work, cluster reboot fast speed influence service delay smaller.
In a kind of possible embodiment, in order to enable respectively key value to be monitored more uniformly is distributed to each node, this
Apply dummy node can also being arranged for each node in embodiment, method particularly includes:
The dummy node of each node setting preset quantity respectively in surviving node list, then calculates each virtual section
Each dummy node is mapped to Hash ring respectively according to the cryptographic Hash of the IP address of each dummy node by the cryptographic Hash of the mark of point
On a position.
Wherein, the corresponding each dummy node of a node passes through the IP address of node and the label of dummy node respectively
Mark.
For example, if the IP address of node 1 is 10.1.1.1, corresponding two dummy nodes of node 1, respectively dummy node A
With dummy node B, then 10.1.1.1:A can be set by the mark of dummy node A, set the mark of dummy node B to
10.1.1.1:B.
After dummy node is set, the method that determines the monitoring range of each node in surviving node list are as follows:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on Hash ring respectively
Then position is looked into since key value to be monitored is in the position on Hash ring counterclockwise for each key value to be monitored
Look for node and dummy node.
If first node found counterclockwise is dummy node, it is determined that the key value to be monitored is by looking into
The corresponding node of the dummy node found is monitored；Alternatively,
If first node found counterclockwise is not dummy node, it is determined that the key value to be monitored by
The node found is monitored.
For example, if first node found is node 2, it is determined that be somebody's turn to do key value to be monitored and monitored by node 2.Alternatively,
If first node found is dummy node A, and dummy node A is the dummy node of node 1, it is determined that should be wait monitor
Key value is monitored by node 1.
It should be noted that the quantity of the corresponding dummy node of each node can be preset, the number of nodes in cluster
Fewer, the dummy node quantity for the setting of each node is more；Conversely, the number of nodes in cluster is more, for the setting of each node
Dummy node quantity is fewer.
It should be noted that dummy node is arranged when what value number of nodes be less than, and the quantity of dummy node is set
It can set based on experience value, the application is not construed as limiting this.It is non-limiting as example, node and virtual section on Hash ring
Point quantity can be for 32 or bigger.
The method after setting dummy node is illustrated below in conjunction with specific example.As shown in fig. 6, showing as one
, there are node A, node B in cluster, from fig. 6 it can be seen that node A needs to monitor 6 key values, and node B only needs
2 key values are monitored, i.e., when the node in cluster is less, the effect of load balancing is not good enough.
So can be respectively node A and node B setting dummy node, for example, node A corresponds to 2 dummy nodes, point
Not Wei dummy node A1, dummy node A2, the IP address for being identified as node A of dummy node A1: 1, the mark of dummy node A2
For the IP address of node A: 2.
Equally, node B also correspond to 2 dummy nodes, respectively dummy node B1, dummy node B2, dummy node B1's
It is identified as the IP address of node B: the IP address for being identified as node B of 1, dummy node B2: 2.
Host node can calculate separately the cryptographic Hash of the mark of above-mentioned each dummy node, then according to cryptographic Hash by each virtual section
Point maps on Hash ring, and the position after mapping is as shown in Figure 7.
It can be seen from figure 7 that key1 is still monitored by node A, first section found counterclockwise for key2, Key3
Point is dummy node A1, then key2, Key3 are monitored by node A.
It is dummy node B1 for key4, Key5 first node found counterclockwise, so key4, Key5 are by saving
Point B is monitored.And key6 is also monitored by node B.It is dummy node B2 for first node that key7 is found counterclockwise, so
Key7 is still monitored by node B.
After dummy node is arranged, node A monitors 4 key values, and node B monitors 4 key values, the key that each node is monitored
Value quantity is identical, and load balancing effect is more preferable.
Based on identical inventive concept, the embodiment of the present application also provides a kind of device of cluster management, which is applied to
Host node in cluster, as shown in figure 8, the device includes: to obtain module 801, computing module 802, mapping block 803 and determine
Module 804.
Module 801 is obtained, for obtaining surviving node list, surviving node list includes connection is established with host node each
The internet protocol address of node；
Computing module 802, the cryptographic Hash of the IP address for calculating each node in surviving node list；
Mapping block 803, the cryptographic Hash of the IP address of each node for being calculated according to computing module 802, respectively will be each
Node maps to a position on Hash ring；
Module 801 is obtained, is also used to obtain to the corresponding key value to be monitored of monitored data, determines key value pair respectively to be monitored
The cryptographic Hash answered；
Determining module 804 determines each for corresponding to the position that cryptographic Hash maps to Hash ring according to respectively key value to be monitored
The monitoring range of node.
In one possible implementation, determining module 804 are specifically used for:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on Hash ring respectively
Position；
It, will be according to suitable counterclockwise since key value to be monitored is in the position on Hash ring for each key value to be monitored
First node that sequence is found is determined as the node for monitoring key value to be monitored.
In one possible implementation, device further include: update module.
Update module, for surviving node list being added in newly-increased node, is obtained more when detecting the access of newly-increased node
Surviving node list after new；And/or when detecting the disengaging node connecting between disconnection and host node, it will be disengaged from saving
Point is deleted from surviving node list, obtains updated surviving node list.
In one possible implementation, computing module 802 are also used to calculate in updated surviving node list each
The cryptographic Hash of the IP address of node；
Mapping block 803 is also used to the cryptographic Hash according to the IP address of each node in updated surviving node list, point
Each node is not mapped to a position on Hash ring；
Determining module 804 is also used to map to the position of Hash ring according to the respectively corresponding cryptographic Hash of key value to be monitored, really
The monitoring range of each node in fixed updated surviving node list.
In one possible implementation, device further include: setup module.
Setup module, for be respectively in surviving node list each node setting preset quantity dummy node, one
The corresponding each dummy node of a node passes through the IP address of node and the label mark of dummy node respectively；
Computing module 802 is also used to calculate the cryptographic Hash of the mark of each dummy node；
Mapping block 803 is also used to the cryptographic Hash of the IP address according to each dummy node, respectively maps each dummy node
A position on to Hash ring.
In alternatively possible implementation, determining module 804 is specifically used for:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on Hash ring respectively
Position；
It is looked into counterclockwise since key value to be monitored is in the position on Hash ring for each key value to be monitored
Look for node and dummy node；
If first node found counterclockwise is dummy node, it is determined that key value to be monitored is by finding
The corresponding node of dummy node monitor；Alternatively,
If first node found counterclockwise is not dummy node, it is determined that key value to be monitored is by searching
The node arrived is monitored.
In one possible implementation, device further include: sending module.
Sending module, the key value to be monitored for needing to monitor to each node sending node respectively, so that each node
The key value to be monitored monitored as needed carries out data processing.
The embodiment of the present application also provides a kind of server, which can be the host node in cluster, such as Fig. 9 institute
Show, including processor 901, communication interface 902, memory 903 and communication bus 904, wherein processor 901, communication interface
902, memory 903 completes mutual communication by communication bus 904,
Memory 903, for storing computer program；
Processor 901 when for executing the program stored on memory 903, is realized in above method embodiment by leading
The step of node executes.
The communication bus that above-mentioned server is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface is for the communication between above-mentioned server and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal
Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components.
In another embodiment provided by the present application, a kind of computer readable storage medium is additionally provided, which can
It reads to be stored with computer program in storage medium, the computer program realizes any of the above-described cluster management when being executed by processor
Method the step of.
In another embodiment provided by the present application, a kind of computer program product comprising instruction is additionally provided, when it
When running on computers, so that the method that computer executes any cluster management in above-described embodiment.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or
It is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid State Disk (SSD)) etc..
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely the preferred embodiments of the application, are not intended to limit the protection scope of the application.It is all
Any modification, equivalent replacement, improvement and so within spirit herein and principle are all contained in the protection scope of the application
It is interior.
Claims (16)
1. a kind of method of cluster management, which is characterized in that the method is applied to the host node in cluster, the method packet
It includes:
Surviving node list is obtained, the surviving node list includes the internet that each node of connection is established with the host node
Protocol IP address；
Calculate the cryptographic Hash of the IP address of each node in the surviving node list；
According to the cryptographic Hash of the IP address of each node, each node is mapped to a position on Hash ring respectively；
It obtains to the corresponding key value to be monitored of monitored data, determines the corresponding cryptographic Hash of key value respectively to be monitored；
The position that cryptographic Hash maps to the Hash ring is corresponded to according to respectively key value to be monitored, determines the monitoring range of each node.
2. the method according to claim 1, wherein respectively key value to be monitored corresponds to cryptographic Hash mapping to the basis
To the position of the Hash ring, the monitoring range of each node is determined, comprising:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on the Hash ring respectively
Position；
It, will be according to suitable counterclockwise since key value to be monitored is in the position on the Hash ring for each key value to be monitored
First node that sequence is found is determined as the node for monitoring the key value to be monitored.
3. the method according to claim 1, wherein the method also includes:
When detecting the access of newly-increased node, the surviving node list is added in the newly-increased node, obtains updated deposit
Movable joint point list；And/or
When detecting disconnection with the disengaging node connecting between the host node, the disengaging node is saved from the survival
It is deleted in point list, obtains updated surviving node list.
4. according to the method described in claim 3, it is characterized in that, it is described obtain updated surviving node list after,
The method also includes:
Calculate the cryptographic Hash of the IP address of each node in updated surviving node list；
According to the cryptographic Hash of the IP address of each node in updated surviving node list, each node is mapped into the Kazakhstan respectively
A position on uncommon ring；
The position that the Hash ring is mapped to according to the respectively corresponding cryptographic Hash of key value to be monitored, determines updated surviving node
The monitoring range of each node in list.
5. the method according to claim 1, wherein after the acquisition surviving node list, the method
Further include:
The dummy node of each node setting preset quantity in the respectively described surviving node list, a node are corresponding every
A dummy node passes through the IP address of node and the label mark of dummy node respectively；
Calculate the cryptographic Hash of the mark of each dummy node；
According to the cryptographic Hash of the IP address of each dummy node, each dummy node is mapped to a position on the Hash ring respectively
It sets.
6. according to the method described in claim 5, it is characterized in that, the basis respectively key value to be monitored correspond to cryptographic Hash mapping
To the position of the Hash ring, the monitoring range of each node is determined, comprising:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on the Hash ring respectively
Position；
It is looked into counterclockwise since key value to be monitored is in the position on the Hash ring for each key value to be monitored
Look for node and dummy node；
If first node found counterclockwise is dummy node, it is determined that the key value to be monitored is by finding
The corresponding node of dummy node monitor；Alternatively,
If first node found counterclockwise is not dummy node, it is determined that the key value to be monitored is by searching
The node arrived is monitored.
7. method according to claim 1-5, which is characterized in that in the basis, respectively key value to be monitored is corresponding
After the position that cryptographic Hash maps to the Hash ring determines the monitoring range of each node, the method also includes:
Need the key value to be monitored monitored to each node sending node respectively so that each node monitor as needed to
It monitors key value and carries out data processing.
8. a kind of device of cluster management, which is characterized in that described device is applied to the host node in cluster, described device packet
It includes:
Module is obtained, for obtaining surviving node list, the surviving node list includes establishing connection with the host node
The internet protocol address of each node；
Computing module, the cryptographic Hash of the IP address for calculating each node in the surviving node list；
Mapping block, the cryptographic Hash of the IP address of each node for being calculated according to the computing module, respectively reflects each node
It is incident upon a position on Hash ring；
The acquisition module is also used to obtain to the corresponding key value to be monitored of monitored data, determines that respectively key value to be monitored is corresponding
Cryptographic Hash；
Determining module determines each node for corresponding to the position that cryptographic Hash maps to the Hash ring according to respectively key value to be monitored
Monitoring range.
9. device according to claim 8, which is characterized in that the determining module is specifically used for:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on the Hash ring respectively
Position；
It, will be according to suitable counterclockwise since key value to be monitored is in the position on the Hash ring for each key value to be monitored
First node that sequence is found is determined as the node for monitoring the key value to be monitored.
10. device according to claim 8, which is characterized in that described device further include:
Update module, for the surviving node list being added in the newly-increased node, is obtained when detecting the access of newly-increased node
To updated surviving node list；And/or when detecting disconnection with the disengaging node connecting between the host node,
The disengaging node is deleted from the surviving node list, obtains updated surviving node list.
11. device according to claim 10, which is characterized in that
The computing module is also used to calculate the cryptographic Hash of the IP address of each node in updated surviving node list；
The mapping block is also used to the cryptographic Hash according to the IP address of each node in updated surviving node list, respectively
Each node is mapped to a position on the Hash ring；
The determining module is also used to map to the position of the Hash ring according to the respectively corresponding cryptographic Hash of key value to be monitored, really
The monitoring range of each node in fixed updated surviving node list.
12. device according to claim 8, which is characterized in that described device further include: setup module；
The setup module, for be respectively in the surviving node list each node setting preset quantity virtual section
Point, the corresponding each dummy node of a node pass through the IP address of node and the label mark of dummy node respectively；
The computing module is also used to calculate the cryptographic Hash of the mark of each dummy node；
The mapping block is also used to the cryptographic Hash of the IP address according to each dummy node, respectively maps to each dummy node
A position on the Hash ring.
13. device according to claim 12, which is characterized in that the determining module is specifically used for:
According to the respectively corresponding cryptographic Hash of key value to be monitored, respectively key value to be monitored is mapped to one on the Hash ring respectively
Position；
It is looked into counterclockwise since key value to be monitored is in the position on the Hash ring for each key value to be monitored
Look for node and dummy node；
If first node found counterclockwise is dummy node, it is determined that the key value to be monitored is by finding
The corresponding node of dummy node monitor；Alternatively,
If first node found counterclockwise is not dummy node, it is determined that the key value to be monitored is by searching
The node arrived is monitored.
14. according to the described in any item devices of claim 8-13, which is characterized in that described device further include:
Sending module, for needing the key value to be monitored monitored to each node sending node respectively so that each node according to
The key value to be monitored for needing to monitor carries out data processing.
15. a kind of server, which is characterized in that including processor and machine readable storage medium, the machine readable storage is situated between
Matter is stored with the machine-executable instruction that can be executed by the processor, and the processor is promoted by the machine-executable instruction
Make: realizing method and step as claimed in claim 1 to 7.
16. a kind of machine readable storage medium, which is characterized in that be stored with machine-executable instruction, by processor call and
When execution, the machine-executable instruction promotes the processor: realizing method and step as claimed in claim 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910351626.XA CN110071978B (en) | 2019-04-28 | 2019-04-28 | Cluster management method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910351626.XA CN110071978B (en) | 2019-04-28 | 2019-04-28 | Cluster management method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110071978A true CN110071978A (en) | 2019-07-30 |
| CN110071978B CN110071978B (en) | 2022-04-22 |
Family
ID=67369357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910351626.XA Active CN110071978B (en) | 2019-04-28 | 2019-04-28 | Cluster management method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110071978B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110841282A (en) * | 2019-10-30 | 2020-02-28 | 腾讯科技（深圳）有限公司 | Data processing method and device, storage medium and electronic device |
| CN110971480A (en) * | 2019-10-18 | 2020-04-07 | 平安科技（深圳）有限公司 | Computer network condition monitoring method and device, computer equipment and storage medium |
| CN111478953A (en) * | 2020-03-27 | 2020-07-31 | 北京金山云网络技术有限公司 | Self-construction method, device, system, equipment and storage medium of server cluster |
| CN111781890A (en) * | 2020-07-14 | 2020-10-16 | 厦门海为科技有限公司 | Multi-equipment engineering communication method and system in configuration engineering |
| CN112231080A (en) * | 2020-09-27 | 2021-01-15 | 武汉物易云通网络科技有限公司 | Task scheduling method and device based on multiple hash rings with different precisions |
| CN113127409A (en) * | 2019-12-31 | 2021-07-16 | 深圳云天励飞技术有限公司 | Management method, device, equipment and medium of operation cluster for data real-time archiving |
| CN113821340A (en) * | 2021-08-27 | 2021-12-21 | 济南浪潮数据技术有限公司 | Dynamic balancing method, system, terminal and storage medium of distributed system |
| WO2022105298A1 (en) * | 2020-11-19 | 2022-05-27 | 深圳壹账通智能科技有限公司 | Node position determination method and apparatus, computer device and storage medium |
| CN115314558A (en) * | 2022-08-09 | 2022-11-08 | 中国电信股份有限公司 | Resource allocation method and device in computational power network, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105187547A (en) * | 2015-09-25 | 2015-12-23 | 浪潮(北京)电子信息产业有限公司 | Load balancing method and system |
| CN108551474A (en) * | 2018-03-26 | 2018-09-18 | 南京邮电大学 | A kind of load-balancing method of server cluster |
| CN108768985A (en) * | 2018-05-17 | 2018-11-06 | 成都致云科技有限公司 | A kind of accessed node access distribution method and device |
| CN109040212A (en) * | 2018-07-24 | 2018-12-18 | 苏州科达科技股份有限公司 | Equipment access server cluster method, system, equipment and storage medium |
-
2019
- 2019-04-28 CN CN201910351626.XA patent/CN110071978B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105187547A (en) * | 2015-09-25 | 2015-12-23 | 浪潮(北京)电子信息产业有限公司 | Load balancing method and system |
| CN108551474A (en) * | 2018-03-26 | 2018-09-18 | 南京邮电大学 | A kind of load-balancing method of server cluster |
| CN108768985A (en) * | 2018-05-17 | 2018-11-06 | 成都致云科技有限公司 | A kind of accessed node access distribution method and device |
| CN109040212A (en) * | 2018-07-24 | 2018-12-18 | 苏州科达科技股份有限公司 | Equipment access server cluster method, system, equipment and storage medium |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021072847A1 (en) * | 2019-10-18 | 2021-04-22 | 平安科技（深圳）有限公司 | Method and apparatus for monitoring condition of computer network, computer device, and storage medium |
| CN110971480A (en) * | 2019-10-18 | 2020-04-07 | 平安科技（深圳）有限公司 | Computer network condition monitoring method and device, computer equipment and storage medium |
| CN110971480B (en) * | 2019-10-18 | 2022-08-19 | 平安科技（深圳）有限公司 | Computer network condition monitoring method and device, computer equipment and storage medium |
| CN110841282A (en) * | 2019-10-30 | 2020-02-28 | 腾讯科技（深圳）有限公司 | Data processing method and device, storage medium and electronic device |
| CN113127409A (en) * | 2019-12-31 | 2021-07-16 | 深圳云天励飞技术有限公司 | Management method, device, equipment and medium of operation cluster for data real-time archiving |
| CN111478953A (en) * | 2020-03-27 | 2020-07-31 | 北京金山云网络技术有限公司 | Self-construction method, device, system, equipment and storage medium of server cluster |
| CN111478953B (en) * | 2020-03-27 | 2022-09-06 | 北京金山云网络技术有限公司 | Self-construction method, device, system, equipment and storage medium of server cluster |
| CN111781890A (en) * | 2020-07-14 | 2020-10-16 | 厦门海为科技有限公司 | Multi-equipment engineering communication method and system in configuration engineering |
| CN112231080A (en) * | 2020-09-27 | 2021-01-15 | 武汉物易云通网络科技有限公司 | Task scheduling method and device based on multiple hash rings with different precisions |
| CN112231080B (en) * | 2020-09-27 | 2024-01-26 | 武汉物易云通网络科技有限公司 | Task scheduling method and device based on multiple hash rings with different precision |
| WO2022105298A1 (en) * | 2020-11-19 | 2022-05-27 | 深圳壹账通智能科技有限公司 | Node position determination method and apparatus, computer device and storage medium |
| CN113821340A (en) * | 2021-08-27 | 2021-12-21 | 济南浪潮数据技术有限公司 | Dynamic balancing method, system, terminal and storage medium of distributed system |
| CN115314558A (en) * | 2022-08-09 | 2022-11-08 | 中国电信股份有限公司 | Resource allocation method and device in computational power network, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110071978B (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110071978A (en) | A kind of method and device of cluster management | |
| US10977277B2 (en) | Systems and methods for database zone sharding and API integration | |
| US10997211B2 (en) | Systems and methods for database zone sharding and API integration | |
| US11379461B2 (en) | Multi-master architectures for distributed databases | |
| US10795905B2 (en) | Data stream ingestion and persistence techniques | |
| US10691716B2 (en) | Dynamic partitioning techniques for data streams | |
| US9201742B2 (en) | Method and system of self-managing nodes of a distributed database cluster with a consensus algorithm | |
| US9794135B2 (en) | Managed service for acquisition, storage and consumption of large-scale data streams | |
| US9276959B2 (en) | Client-configurable security options for data streams | |
| US20150134626A1 (en) | Partition-based data stream processing framework | |
| US9367261B2 (en) | Computer system, data management method and data management program | |
| US8984328B2 (en) | Fault tolerance in a parallel database system | |
| GB2407887A (en) | Automatically modifying fail-over configuration of back-up devices | |
| US10048994B2 (en) | Identifying failed customer experience in distributed computer systems | |
| CN110048896A (en) | A kind of company-data acquisition methods, device and equipment | |
| US8934378B1 (en) | Resilient cache-based topology detection of a dynamic cluster | |
| US11792157B1 (en) | Detection of DNS beaconing through time-to-live and transmission analyses | |
| US10924452B1 (en) | Auditing IP address assignments | |
| CN107908713B (en) | Distributed dynamic rhododendron filtering system based on Redis cluster and filtering method thereof | |
| CN107180034A (en) | The group system of MySQL database | |
| US10715608B2 (en) | Automatic server cluster discovery | |
| JP5604989B2 (en) | SEARCH DEVICE, SEARCH METHOD, AND SEARCH PROGRAM | |
| US11902081B1 (en) | Managing collection agents via an agent controller | |
| US20240022628A1 (en) | Scalable processing of domain name system queries for a global server load balancing service | |
| US20220398128A1 (en) | Distributed task assignment in a cluster computing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |