CN107800737A - The determination method, apparatus and server cluster of host node in a kind of server cluster - Google Patents
The determination method, apparatus and server cluster of host node in a kind of server cluster Download PDFInfo
- Publication number
- CN107800737A CN107800737A CN201610801522.0A CN201610801522A CN107800737A CN 107800737 A CN107800737 A CN 107800737A CN 201610801522 A CN201610801522 A CN 201610801522A CN 107800737 A CN107800737 A CN 107800737A
- Authority
- CN
- China
- Prior art keywords
- server
- node
- host node
- cluster
- server cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- 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
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
- H04L67/1051—Group master selection mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1073—Registration or de-registration
-
- 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
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
- H04L67/1048—Departure or maintenance mechanisms
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Hardware Redundancy (AREA)
Abstract
Embodiments of the invention provide the determination method, apparatus and server cluster of host node in a kind of server cluster.Wherein method includes:Receive the registration request that multiple servers are successively sent;According to the registration request, for each node ID of server-assignment one;According to the node ID, it is determined that a server being registered in multiple servers in server cluster is host node.The solution of the present invention, which avoids individual server, to be there is Single Point of Faliure and causes operation system to be withdrawn, can not externally provide online service, and avoids multiple servers while the problem of work causes processing to same part data and then causes damage or the result mistake of data.
Description
Technical field
The present invention relates to technical field of the computer network, a kind of determination side of host node in server cluster is particularly related to
Method, device and server cluster.
Background technology
With the rapid development (such as big data, cloud computing, communication network) of various technologies, many key areas are to service
The requirement more and more higher of availability.High Availabitity online service is externally provided using server cluster effectively to be reduced because of software and hardware
Operation system externally withdraws the time caused by failure.
For some business, for can only be handled in same part data same time by individual server, Ruo Duotai
Server is handled it simultaneously, may result in damage or the result mistake of data.
In order to ensure the security and correctness of data while High Availabitity online service is externally provided, in legacy system
There are some general processing methods.Such as field of storage is shared in tradition, in order to avoid multiple nodes are simultaneously to shared storage
Operation, technology is typically retained using SCSI3 (one kind of data transmission technology) Fencing isolation etc. is carried out to shared storage
Method.In other field or the existing environment of field of storage, Fencing hardware condition may not be had, or make
Greatest differences be present with environment.
Many key areas are using general server hardware, multiple one server set of server construction at present
Group.The cluster includes a host node and multiple slave nodes, causes in order to avoid multiple servers work simultaneously to same number
According to processing so that cause damage or the result mistake of data, therefore at any one time in cluster only have host node start clothes
Business, externally provide online service.In order to ensure the cluster can normal work, it is necessary to solve two problems:
1) how host node is chosen in server cluster;
2) in server host node failure, how slave node automatically switches to new host node.
The content of the invention
The invention provides a kind of determination method, apparatus of host node in server cluster and server cluster.Avoid
There is Single Point of Faliure and causes operation system to be withdrawn, can not externally provide online service in individual server, and avoids multiple services
The problem of device work simultaneously causes the processing to same part data and then causes damage or the result mistake of data.
In order to solve the above technical problems, embodiments of the invention provide following scheme:
A kind of determination method of host node in server cluster, including:
Receive the registration request that multiple servers are successively sent;
According to the registration request, for each node ID of server-assignment one;
According to the node ID, it is determined that based on a server being registered in multiple servers in server cluster
Node.
Wherein, according to the registration request, include for the step of each one node ID of server-assignment:
According to the registration request, respectively each server generates a transient node;
A node ID, the node as server corresponding with the transient node are distributed for transient node each described
Sequence number.
Wherein, according to the registration request, include for the step of each one node ID of server-assignment:
According to the sequencing of the registration request of the server received, for each server according to from small to large or
The node ID of order-assigned one of person from big to small.
Wherein, according to the node ID, it is determined that a service being registered in multiple servers in server cluster
The step of device is host node includes:
According to the node ID, it is determined that the node ID minimum being registered in multiple servers in server cluster
Server or the server of node ID maximum are as host node.
Wherein, the determination method of host node also includes in above-mentioned server cluster:
When the minimum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if
As the server fail of host node, then in remaining server from multiple servers in addition to failed server, really
The minimum server of node ID is determined as host node;Or
When the maximum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if
As the server fail of host node, then in remaining server from multiple servers in addition to failed server, really
The maximum server of node ID is determined as host node.
Wherein, as also including after the server fail of host node:Delete and saved temporarily corresponding to the failed server
Point.
Embodiments of the invention also provide a kind of determining device of host node in server cluster, including:
Receiving module, the registration request successively sent for receiving multiple servers;
Distribute module, for being each node ID of server-assignment one according to the registration request;
Determining module, for according to the node ID, it is determined that being registered in multiple servers in server cluster
One server is host node.
Wherein, the distribute module is specifically used for:According to the registration request, respectively each server generation one is interim
Node;A node ID, the node sequence as server corresponding with the transient node are distributed for transient node each described
Number.
Wherein, the distribute module is specifically used for:
According to the sequencing of the registration request of the server received, for each server according to from small to large or
The node ID of order-assigned one of person from big to small.
Wherein, the determining module is specifically used for:According to the node ID, it is determined that being registered to more in server cluster
The server of node ID minimum in individual server or the server of node ID maximum are as host node.
Wherein, the determining module is additionally operable to:
When the minimum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if
As the server fail of host node, then in remaining server from multiple servers in addition to failed server, really
The minimum server of node ID is determined as host node;Or
When the maximum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if
As the server fail of host node, then in remaining server from multiple servers in addition to failed server, really
The maximum server of node ID is determined as host node.
Wherein, the determining device of host node also includes in server cluster:
Removing module, face for after the server fail as host node, deleting corresponding to the failed server
Shi Jiedian.
Embodiments of the invention also provide a kind of server cluster, including multiple servers, and master in server cluster
The determining device of node.
The such scheme of the present invention comprises at least following beneficial effect:
The such scheme of the present invention, the registration request successively sent by receiving multiple servers;Please according to the registration
Ask, for each node ID of server-assignment one;According to the node ID, it is determined that being registered to more in server cluster
A server in individual server is host node.Individual server is avoided Single Point of Faliure occur and cause operation system to be stopped
Clothes, online service can not be externally provided, and avoid multiple servers while work causing the processing to same part data and then leading
The problem of causing damage or the result mistake of data.
Brief description of the drawings
Fig. 1 is the determination method flow diagram of host node in server cluster of the invention;
Fig. 2 is server cluster original state schematic diagram;
Fig. 3 is the server cluster state after server service2 breaks down;
Fig. 4 is the server cluster state after server service2 fault restorations;
Fig. 5 is the schematic diagram of the determining device of host node in server cluster of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
For in the prior art, multiple servers, which work, to be caused the processing to same part data and then causes data simultaneously
Damage or the problem of result mistake, embodiments of the invention inquire about cluster to realize to server cluster by Node registry
Management, by Node registry inquire about cluster be server-assignment sequence number.It is host node to choose the minimum server of sequence number, in office
Only have host node externally to perform online service in one moment cluster, avoid providing user the repetition of online service and then cause
As a result mistake.
As shown in figure 1, embodiments of the invention provide a kind of determination method of host node in server cluster, including:
Step 11, the registration request that multiple servers are successively sent is received;
Step 12, according to the registration request, for each node ID of server-assignment one;
Step 13, according to the node ID, it is determined that a clothes being registered in multiple servers in server cluster
Business device is host node.
The embodiment of the present invention, the registration request successively sent by receiving multiple servers;Please according to the registration
Ask, for each node ID of server-assignment one;According to the node ID, it is determined that being registered to more in server cluster
A server in individual server is host node.Individual server is avoided Single Point of Faliure occur and cause operation system to be stopped
Clothes, online service can not be externally provided, and avoid multiple servers while work causing the processing to same part data and then leading
The problem of causing damage or the result mistake of data.
In the above-described embodiments, step 12 can include:
Step 121, a transient node is generated according to the registration request, respectively each server;
Step 122, a node ID is distributed for each described transient node, as service corresponding with the transient node
The node ID of device.
Step 12 can also include:According to the sequencing of the registration request of the server received, for each clothes
Device be engaged according to the node ID of order-assigned one from small to large or from big to small.
Specifically, such as according to the server received registration request sequencing, respectively each server generation
One transient node, be each described transient node according to the node ID of order-assigned one from small to large or from big to small,
Node ID as server corresponding with the transient node.
Wherein, above-mentioned steps 13 can include:According to the node ID, it is determined that being registered to multiple in server cluster
The server of node ID minimum in server or the server of node ID maximum are as host node.
Further, the determination method of host node also includes in above-mentioned server cluster:
Step 14, the minimum server of multiple server interior joint sequence numbers in server cluster is registered to is as main section
During point, if the server fail as host node, remaining service from multiple servers in addition to failed server
In device, determine the minimum server of node ID as host node;Or
Step 15, the maximum server of multiple server interior joint sequence numbers in server cluster is registered to is as main section
During point, if the server fail as host node, remaining service from multiple servers in addition to failed server
In device, determine the maximum server of node ID as host node.
Wherein, as also including after the server fail of host node:
Step 16, transient node corresponding to the failed server is deleted.
Certainly, in above-described embodiment, include and choose the minimum server of node ID as host node or choose section
The maximum server of point sequence number is not limited to choose the minimum or maximum server of node ID as master as host node
Node, an one of server can also be chosen as host node by Else Rule.
As shown in figs 2-4, in order to which the problem of the selection and switching of host node, the present invention uses in settlement server cluster
Node registry inquires about cluster to realize that the specific implementation example of the management to server cluster is as follows:
On startup, each server can arrive under Node registry inquiry cluster/service catalogues server cluster
Row registration, log-on message is Hostname- node ID, such as:Service1-0000000014, and then in/service mesh
Transient node/service/service1-0000000014 is formed under record.Wherein, Node registry inquiry cluster can be automatically clothes
Business device Allotment Serial Number, sequence number is monotonic increase, naturally it is also possible to is successively decreased.
When server breaks down, it can disconnect inquires about linking for cluster with Node registry, and it is originally in Node registry
The transient node generated on inquiry cluster can inquire about cluster by Node registry and delete.
As shown in Figure 2, it is assumed that when server cluster starts, server service2 (its Hostname is service2) is most
It is first the serial number 0000000013 of its distribution to Node registry inquiry cluster registration, Node registry inquiry cluster, it is in node
Trade mark enquiries cluster /service catalogues under formed transient node/service/service2-0000000013;
Thereafter, server service1 (its Hostname is service1) registers to Node registry inquiry cluster, node
The external Allotment Serial Number monotonic increase of trade mark enquiries cluster, naturally it is also possible to successively decrease;For the serial number of its distribution
0000000014, its Node registry inquiry cluster /service catalogues under formed transient node/service/service1-
0000000014;
Thereafter, for server service3 to Node registry inquiry cluster registration, Node registry inquiry cluster is its distribution
Serial number 0000000015, its Node registry inquiry cluster /service catalogues under formed transient node/service/
service3-0000000015;The state of final server cluster is as shown in Figure 2;
Now because server service2 sequence number is minimum (0000000013), therefore it turns into host node, starts
Line service externally provides service.Now server service1 and service3 is in idle condition, does not perform online service.
As shown in Figure 3, it is assumed that after server cluster work a period of time, there is mechanical disorder in server service2, this
When it is disconnected and linked with Node registry inquiry cluster, its transient node originally generated on Node registry inquiry cluster/
Service/service2-0000000013 is deleted by Node registry inquiry cluster, now server cluster state such as Fig. 3 institutes
Show.
After server cluster start completion, each server can continue to monitor Node registry inquiry cluster catalogue/
Service change, if it find that the sequence number of oneself be it is minimum just automatically become host node and then start online service, such as
Fruit finds that the sequence number of oneself automatically becomes slave node without being minimum, is then in idle condition.
In figure 3, server service1 and server service3 persistently monitor Node registry inquiry cluster catalogue/
Service change, server service1 has found that the current sequence number of oneself is minimum, therefore server service1 upgrades
For host node, start online service, server service3 has found that the sequence number of oneself is not still minimum, therefore it is continued as
Slave node, in idle condition, do not start online service.
As shown in figure 4, after server service2 fault recovery, it revert to server cluster again, again to
Node registry inquiry cluster registration, Node registry inquiry cluster ensures external Allotment Serial Number monotonic increase, for the sequence number of its distribution
For 0000000016, its Node registry inquiry cluster /service catalogues under form transient node/service/
service2-0000000016.Each server persistently monitors Node registry inquiry cluster catalogue/service change, service
Sequence number current device service1 is still minimum, remains as host node, and server service3 and service2 sequence number are not most
It is small, for slave node, in idle condition, do not start online service.
In the above embodiment of the present invention, each server can continue to monitor Node registry inquiry cluster catalogue/
Service change, if it find that the sequence number of oneself be it is minimum just automatically become host node and then start online service, such as
Fruit finds that the sequence number of oneself automatically becomes slave node without being minimum, is then in idle condition.In the event of server host node
During barrier, the minimum slave node of sequence number automatically switches to new host node and externally performs online service.Server is avoided single-point occur
Failure and cause externally provide online service in time.
Start online service by choosing host node in server cluster with upper type;A period of time in office can be ensured simultaneously
Carve only host node in cluster and externally perform online service;Avoid providing user the repetition of online service and then cause result
Mistake.Simultaneously by the way that with upper type, in server host node failure, the minimum slave node of sequence number automatically switches to new main section
Point starts online service, avoids server from Single Point of Faliure occur and causes externally provide online service in time.
As shown in figure 5, embodiments of the invention also provide a kind of determining device 50 of host node in server cluster, bag
Include:
Receiving module 51, the registration request successively sent for receiving multiple servers;
Distribute module 52, for being each node ID of server-assignment one according to the registration request;
Determining module 53, for according to the node ID, it is determined that being registered in multiple servers in server cluster
A server be host node.
Wherein, the distribute module 52 is specifically used for:According to the registration request, respectively each server generation one is faced
Shi Jiedian;A node ID, the node as server corresponding with the transient node are distributed for transient node each described
Sequence number.
Wherein, the distribute module 52 is specifically used for:According to the sequencing of the registration request of the server received, it is
Each server is according to the node ID of order-assigned one from small to large or from big to small.
Wherein, the determining module 53 is specifically used for:According to the node ID, it is determined that being registered in server cluster
The server of node ID minimum in multiple servers or the server of node ID maximum are as host node.
Wherein, the determining module is additionally operable to:Multiple server interior joint sequence numbers in server cluster is registered to are most
When small server is as host node, if the server fail as host node, except failure takes from multiple servers
In remaining server outside business device, determine the minimum server of node ID as host node;Or it is being registered to server
When the server of multiple server interior joint sequence numbers maximum in cluster is as host node, if the server as host node occurs
Failure, then in remaining server from multiple servers in addition to failed server, determine the maximum server of node ID
As host node.
Wherein, the determining device of host node also includes in server cluster:Removing module, in the clothes as host node
After business device breaks down, transient node corresponding to the failed server is deleted.
Such as Fig. 2,3,4, embodiments of the invention also provide a kind of server cluster, including multiple servers, and service
The determining device of host node in device cluster.Wherein, the determining device such as can be the Node registry inquiry cluster in Fig. 2,3,4.
It should be noted that the device is device corresponding with above method embodiment, own in above method embodiment
Implementation can also reach identical technique effect suitable for the embodiment of the device.
In the above embodiment of the present invention, each server can continue to monitor Node registry inquiry cluster catalogue/
Service change, if it find that the sequence number of oneself be it is minimum just automatically become host node and then start online service, such as
Fruit finds that the sequence number of oneself automatically becomes slave node without being minimum, is then in idle condition.In the event of server host node
During barrier, the minimum slave node of sequence number automatically switches to new host node and externally performs online service.Server is avoided single-point occur
Failure and cause externally provide online service in time.
Start online service by choosing host node in server cluster with upper type, while a period of time in office can be ensured
Carve only host node in cluster and externally perform online service;Avoid providing user the repetition of online service and then cause result
Mistake.Simultaneously by the way that with upper type, in server host node failure, the minimum slave node of sequence number automatically switches to new main section
Point starts online service, avoids server from Single Point of Faliure occur and causes externally provide online service in time.
Described above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, on the premise of principle of the present invention is not departed from, some improvements and modifications can also be made, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (13)
1. a kind of determination method of host node in server cluster, it is characterised in that including:
Receive the registration request that multiple servers are successively sent;
According to the registration request, for each node ID of server-assignment one;
According to the node ID, it is determined that being saved based on a server being registered in multiple servers in server cluster
Point.
2. the determination method of host node in server cluster according to claim 1, it is characterised in that according to the registration
Request, include for the step of each one node ID of server-assignment:
According to the registration request, respectively each server generates a transient node;
A node ID, the node sequence as server corresponding with the transient node are distributed for transient node each described
Number.
3. the determination method of host node in server cluster according to claim 2, it is characterised in that according to the registration
Request, include for the step of each one node ID of server-assignment:
According to the sequencing of the registration request of the server received, for each server according to from small to large or from
The small node ID of order-assigned one is arrived greatly.
4. the determination method of host node in server cluster according to claim 3, it is characterised in that according to the node
Sequence number a, it is determined that server being registered in multiple servers in server cluster includes the step of being host node:
According to the node ID, it is determined that the service that the node ID being registered in multiple servers in server cluster is minimum
Device or the server of node ID maximum are as host node.
5. the determination method of host node in server cluster according to claim 4, it is characterised in that also include:
When the minimum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if conduct
The server fail of host node, then in remaining server from multiple servers in addition to failed server, it is determined that section
The minimum server of point sequence number is as host node;Or
When the maximum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if conduct
The server fail of host node, then in remaining server from multiple servers in addition to failed server, it is determined that section
The maximum server of point sequence number is as host node.
6. the determination method of host node in server cluster according to claim 5, it is characterised in that as host node
Also include after server fail:Delete transient node corresponding to the failed server.
A kind of 7. determining device of host node in server cluster, it is characterised in that including:
Receiving module, the registration request successively sent for receiving multiple servers;
Distribute module, for being each node ID of server-assignment one according to the registration request;
Determining module, for according to the node ID, it is determined that being registered to one in multiple servers in server cluster
Server is host node.
8. the determining device of host node in server cluster according to claim 7, it is characterised in that the distribute module
It is specifically used for:According to the registration request, respectively each server generates a transient node;For transient node each described
A node ID is distributed, the node ID as server corresponding with the transient node.
9. the determining device of host node in server cluster according to claim 8, it is characterised in that the distribute module
It is specifically used for:
According to the sequencing of the registration request of the server received, for each server according to from small to large or from
The small node ID of order-assigned one is arrived greatly.
10. the determining device of host node in server cluster according to claim 9, it is characterised in that the determination mould
Block is specifically used for:According to the node ID, it is determined that the node ID being registered in multiple servers in server cluster is most
Small server or the server of node ID maximum are as host node.
11. the determining device of host node in server cluster according to claim 10, it is characterised in that the determination mould
Block is additionally operable to:
When the minimum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if conduct
The server fail of host node, then in remaining server from multiple servers in addition to failed server, it is determined that section
The minimum server of point sequence number is as host node;Or
When the maximum server of multiple server interior joint sequence numbers in being registered to server cluster is as host node, if conduct
The server fail of host node, then in remaining server from multiple servers in addition to failed server, it is determined that section
The maximum server of point sequence number is as host node.
12. the determining device of host node in server cluster according to claim 11, it is characterised in that also include:
Removing module, saved temporarily corresponding to the failed server for after the server fail as host node, deleting
Point.
13. a kind of server cluster, including multiple servers, it is characterised in that also include such as any one of claim 10-12 institutes
The determining device of host node in the server cluster stated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610801522.0A CN107800737A (en) | 2016-09-05 | 2016-09-05 | The determination method, apparatus and server cluster of host node in a kind of server cluster |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610801522.0A CN107800737A (en) | 2016-09-05 | 2016-09-05 | The determination method, apparatus and server cluster of host node in a kind of server cluster |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107800737A true CN107800737A (en) | 2018-03-13 |
Family
ID=61529793
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610801522.0A Pending CN107800737A (en) | 2016-09-05 | 2016-09-05 | The determination method, apparatus and server cluster of host node in a kind of server cluster |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107800737A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109189854A (en) * | 2018-08-14 | 2019-01-11 | 新华三技术有限公司成都分公司 | The method and node device of sustained traffic are provided |
CN111538763A (en) * | 2020-04-24 | 2020-08-14 | 咪咕文化科技有限公司 | Method for determining main node in cluster, electronic equipment and storage medium |
CN111769981A (en) * | 2020-06-19 | 2020-10-13 | 苏州浪潮智能科技有限公司 | Decentralized architecture main node election method, data file transmission method and system |
CN112395140A (en) * | 2020-11-17 | 2021-02-23 | 平安科技(深圳)有限公司 | Decentralized task scheduling method, device, equipment and medium |
WO2023146855A1 (en) * | 2022-01-26 | 2023-08-03 | Capital One Services, Llc | Systems and methods for leader node election in cluster server configurations |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101217402A (en) * | 2008-01-15 | 2008-07-09 | 杭州华三通信技术有限公司 | A method to enhance the reliability of the cluster and a high reliability communication node |
US20090113018A1 (en) * | 2007-10-31 | 2009-04-30 | Allan Thomson | Mobility service clustering using network service segments |
CN103731341A (en) * | 2013-12-30 | 2014-04-16 | 广州华多网络科技有限公司 | Method and system for processing instant messaging services |
CN105447097A (en) * | 2015-11-10 | 2016-03-30 | 北京北信源软件股份有限公司 | Data acquisition method and system |
-
2016
- 2016-09-05 CN CN201610801522.0A patent/CN107800737A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090113018A1 (en) * | 2007-10-31 | 2009-04-30 | Allan Thomson | Mobility service clustering using network service segments |
CN101217402A (en) * | 2008-01-15 | 2008-07-09 | 杭州华三通信技术有限公司 | A method to enhance the reliability of the cluster and a high reliability communication node |
CN103731341A (en) * | 2013-12-30 | 2014-04-16 | 广州华多网络科技有限公司 | Method and system for processing instant messaging services |
CN105447097A (en) * | 2015-11-10 | 2016-03-30 | 北京北信源软件股份有限公司 | Data acquisition method and system |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109189854A (en) * | 2018-08-14 | 2019-01-11 | 新华三技术有限公司成都分公司 | The method and node device of sustained traffic are provided |
CN109189854B (en) * | 2018-08-14 | 2021-06-08 | 新华三技术有限公司成都分公司 | Method and node equipment for providing continuous service |
CN111538763A (en) * | 2020-04-24 | 2020-08-14 | 咪咕文化科技有限公司 | Method for determining main node in cluster, electronic equipment and storage medium |
CN111538763B (en) * | 2020-04-24 | 2023-08-15 | 咪咕文化科技有限公司 | Method for determining master node in cluster, electronic equipment and storage medium |
CN111769981A (en) * | 2020-06-19 | 2020-10-13 | 苏州浪潮智能科技有限公司 | Decentralized architecture main node election method, data file transmission method and system |
CN112395140A (en) * | 2020-11-17 | 2021-02-23 | 平安科技(深圳)有限公司 | Decentralized task scheduling method, device, equipment and medium |
CN112395140B (en) * | 2020-11-17 | 2023-01-17 | 平安科技(深圳)有限公司 | A decentralized task scheduling method apparatus, device and medium |
WO2023146855A1 (en) * | 2022-01-26 | 2023-08-03 | Capital One Services, Llc | Systems and methods for leader node election in cluster server configurations |
US11907137B2 (en) | 2022-01-26 | 2024-02-20 | Capital One Services, Llc | Systems and methods for leader node election in cluster server configurations |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107800737A (en) | The determination method, apparatus and server cluster of host node in a kind of server cluster | |
CN102769667B (en) | Method, equipment and system for generating ID | |
CN102710554B (en) | The service state detection method of distributed information system and distributed information system | |
CN104199957A (en) | Redis universal agent implementation method | |
CN109660466A (en) | A kind of more live load balance realizing methods towards cloud data center tenant | |
CN105024855A (en) | Distributed cluster management system and method | |
US20100299447A1 (en) | Data Replication | |
CN104993998A (en) | Enterprise-level safety instant messaging system supporting cloud deploying and method | |
CN107645413B (en) | Intelligent telephone exchange network core side access side full-automatic configuration platform and method | |
CN110083651B (en) | Data loading method and device | |
CN104092746B (en) | A kind of O&M auditing system and the network load balancing method in its system | |
CN107528891B (en) | Websocket-based automatic clustering method and system | |
CN105677380B (en) | Method and device for board-by-board upgrading of double master control isolations | |
CN104090992A (en) | Method for high-availability configuration between conversion nodes in cluster storage system | |
CN102917084A (en) | Automatic allocation method of IP address of node inside fat tree structure networking data center | |
CN107682411A (en) | A kind of extensive SDN controllers cluster and network system | |
CN113824723A (en) | End-to-end system solution applied to audio and video data transmission | |
CN101227333B (en) | Disaster tolerance network managing system and login method of network managing subscriber end | |
CN108063787A (en) | The method that dual-active framework is realized based on distributed consensus state machine | |
CN106937351B (en) | Session realization method and core network element | |
CN111651320A (en) | High-concurrency connection method and system | |
CN101778131A (en) | Data synchronization system | |
CN107911496A (en) | A kind of VPN service terminal acts on behalf of the method and device of DNS | |
CN107835222A (en) | Combustion gas data transmission method and Internet of things system based on compound Internet of Things | |
CN105790985B (en) | Data switching method, first device, second device and 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180313 |
|
RJ01 | Rejection of invention patent application after publication |