CN108111337B - Method and equipment for arbitrating main nodes in distributed system - Google Patents
Method and equipment for arbitrating main nodes in distributed system Download PDFInfo
- Publication number
- CN108111337B CN108111337B CN201711275402.2A CN201711275402A CN108111337B CN 108111337 B CN108111337 B CN 108111337B CN 201711275402 A CN201711275402 A CN 201711275402A CN 108111337 B CN108111337 B CN 108111337B
- Authority
- CN
- China
- Prior art keywords
- group
- node
- nodes
- main
- groups
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/30—Decision processes by autonomous network management units using voting and bidding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0668—Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
-
- 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
- H04L67/104—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
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
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)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Computer And Data Communications (AREA)
- Multi Processors (AREA)
Abstract
The invention discloses a method and a device for arbitrating a main node by a distributed system, wherein the method comprises the following steps: arbitrating in nodes of each group divided in advance to obtain main nodes in the groups of a plurality of groups; and arbitrating in the group main nodes of the plurality of groups to obtain the system main node of the distributed system. The invention effectively improves the arbitration efficiency of the main node of the distributed system.
Description
Technical Field
The present invention relates to the field of network technologies, and in particular, to a method and an apparatus for arbitrating master nodes in a distributed system.
Background
With the development and popularization of the internet, cloud computing and big data technology, a distributed system is an important technical means for solving the problem of the rapid increase of application system data. The service system is deployed to a plurality of data centers, and a main node needs to be arbitrated in the distributed system to be used as a manager for unified coordination, so that the data consistency is ensured.
In a distributed system with N nodes, a master node is arbitrated through the prior art, and each node needs to initiate a master node arbitration request for N-1 times to other nodes to judge whether the arbitration is passed or not. The main node needs to send heartbeat information to N-1 nodes in an optional period; when the master node is abnormal, each node is required to initiate the master node arbitration request for N-1 times to other nodes.
With the increase of the number N of the nodes, the number of times of arbitration interaction is increased, and the number of heartbeat information sent by the main node is also increased, so that the distributed system has large arbitration range, low arbitration efficiency, large network pressure and large pressure for sending the heartbeat information by the main node in the period of time.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks, the present invention provides a method and a device for arbitrating a master node in a distributed system, so as to at least solve the problem of low arbitration efficiency of the master node in the distributed system in the prior art.
In order to solve the above technical problem, a method for arbitrating a master node in a distributed system according to the present invention includes:
arbitrating in nodes of each group divided in advance to obtain main nodes in the groups of a plurality of groups;
and arbitrating in the group main nodes of the plurality of groups to obtain the system main node of the distributed system.
In order to solve the above technical problem, an apparatus for arbitrating a master node in a distributed system according to the present invention includes a memory and a processor; the memory stores a computer program for a distributed system arbitrating master node, which is executed by the processor to implement the steps of the method as described above.
The invention has the following beneficial effects:
the distributed system is divided into groups, firstly, arbitration is carried out in each group to arbitrate the main nodes of each group, then, the main nodes of each group are arbitrated to arbitrate the main nodes of the whole distributed system, and the arbitration efficiency of the main nodes of the distributed system is effectively improved.
Drawings
FIG. 1 is a flow chart of a method for arbitrating master nodes in a distributed system according to an embodiment of the present invention;
FIG. 2 is a schematic node structure diagram of a distributed system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a packet in an embodiment of the invention;
FIG. 4 is a flow chart of arbitration in an embodiment of the present invention;
FIG. 5 is a flow chart of master node exception handling in an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an apparatus for arbitrating master nodes in a distributed system according to an embodiment of the present invention.
Detailed Description
In order to solve the problems in the prior art, the present invention provides a method and an apparatus for arbitrating master nodes in a distributed system, which are described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Example one
An embodiment of the present invention provides a method for arbitrating master nodes in a distributed system, as shown in fig. 1, where the method includes:
s101, arbitrating in nodes of each pre-divided group to obtain main nodes in the groups of a plurality of groups;
and S102, arbitrating in the master nodes in the groups to obtain the system master node of the distributed system.
In the embodiment of the invention, the master node in the group represents the master node in the group, and the system master node represents the master node of the distributed system.
The embodiment of the invention carries out grouping on the distributed system, firstly carries out arbitration in each group to arbitrate the main node of each group, and then carries out arbitration on the main node of each group to arbitrate the main node of the whole distributed system, thereby effectively improving the arbitration efficiency of the main nodes of the distributed system.
According to the embodiment of the invention, in the distributed system, when the master nodes in the group are abnormal, the arbitration is firstly carried out in the group where the master nodes are located, the master nodes in the group are arbitrated again, all the groups are not required to arbitrate the master nodes, and only the abnormal group is required to initiate an arbitration request, so that the arbitration range is effectively reduced, the arbitration efficiency is improved, and the network pressure is reduced; meanwhile, when the system main nodes are abnormal, the main nodes in each group are arbitrated without initiating arbitration requests to all the nodes, so that the arbitration range is effectively reduced, the arbitration efficiency is improved, and the network pressure is reduced.
For example, in a distributed system with N nodes, if the distributed system is evenly divided into G groups, and each group has N/G nodes, the arbitration frequency required to be initiated by a master node in the arbitration group is N/G-1, and the arbitration frequency required to be initiated by a system master node arbitrating the whole distributed system is G-1.
When the system main node is abnormal, the arbitration times needing to be initiated are (N/G-1) + (G-1).
When N > G, G >1, then N-1> (N/G-1) + (G-1). The arbitration range is effectively reduced in a grouping mode, and therefore the main node arbitration efficiency is improved.
On the basis of the above embodiment, a modification of the above embodiment is further proposed.
In this embodiment of the present invention, optionally, before performing arbitration in nodes of each group divided in advance to obtain a master node in a group of a plurality of groups, the method includes:
the distributed system is divided into a plurality of groups.
In the embodiment of the present invention, optionally, the distributed system is divided into a plurality of groups according to one or more of the following information:
node location information, network resource information, and computing power information.
In the embodiment of the present invention, optionally, after dividing the distributed system into a plurality of groups, the method includes:
and sending the grouping information of each group to each node in the distributed system so that each node is added into the corresponding group according to the grouping information.
For example, dividing N nodes of the distributed system into a plurality of groups, and sending grouping information to each node;
the grouping mode is as follows: according to the geographical position, network resources, computing capacity and other conditions of the nodes, the embodiment is only one grouping strategy, specifically, the nodes can be divided into one group according to the nodes with similar node distribution regions, or the nodes are divided according to the same operator used by the node network, so that the cooperative capacity between the group and the group can be effectively improved.
After each node receives the grouping information, inquiring the grouping information to which the node belongs; if the node inquires the grouping information, inquiring the main node of the group according to the grouping information; and if the group information of the node is not inquired, randomly selecting the main nodes of other groups as the main nodes, or waiting for grouping without any processing.
Specifically, as shown in fig. 2, a model grouping a distributed system having N nodes:
if N is 9, 9 nodes in the distributed system are respectively a node G1-1, a node G1-2, a node G1-3, a node G2-1, a node G2-2, a node G2-3, a node G3-1, a node G3-2 and a node G3-3;
the node G1-1, the node G1-2 and the node G1-3 are divided into a group to form a group G1;
the node G2-1, the node G2-2 and the node G2-3 are divided into a group to form a group G2;
the node G3-1, the node G3-2 and the node G3-3 are divided into a group to form a group G3.
The model is only an example, and the number of nodes in the group G1, the group G2 and the group G3 may be the same or different; grouping may also be performed based on the geographic location of the nodes, network resources, computing power, and the like.
The members of the model group are nodes, and the group can be grouped again, and the members of the model group are groups, such as: the groups G1, G2 and G3 are divided into one group, more levels of group division are generated, the groups can be divided in any mode as long as the groups are consistent with logic, the operation of a distributed system is not influenced, the arbitration process is not influenced, the groups can be divided into any number of layers, and the groups belong to the model.
In this embodiment of the present invention, optionally, the arbitrating in the nodes of each group divided in advance to obtain the intra-group master nodes of a plurality of groups includes:
for any node: after the node is added into a corresponding group, whether a main node in the group exists in the group is inquired;
if not, initiating a request of a main node in the group to arbitrate in the group to obtain the main node in the group of the group;
if yes, inquiring whether the main node in the group is in the tenure period, and if not, initiating a main node arbitration request in the group to arbitrate in the group to obtain the main node in the group.
In this embodiment of the present invention, optionally, the arbitrating among the group master nodes in the multiple groups to obtain the system master node of the distributed system includes:
for any intra-group master node: after the master nodes in the group are added into the distributed system, inquiring whether system master nodes exist in the distributed system or not;
if not, initiating a system arbitration main node request to arbitrate in main nodes in each group to obtain a system main node;
if yes, inquiring whether the system main node is in the tenure, and if not, initiating a system arbitration main node request to arbitrate in the main nodes in each group to obtain the system main node.
In this embodiment of the present invention, optionally, after performing arbitration among master nodes in a plurality of groups to obtain a system master node of the distributed system, the method includes:
and the system main node sends arbitration information to each group main node and starts the system main node of the distributed system to be in the hold period.
For example, if the group has no main node in the group, a main node arbitration request is initiated to other nodes in the group, and the main node in the group is arbitrated; if the group has the main nodes in the group, inquiring whether the main nodes in the group are in the tenure period through an arbitration module, and if so, not initiating an arbitration main node request; otherwise, initiating a request for arbitrating the master node.
The main node in the group sends the arbitration information to other nodes in the distributed system; the main nodes in the group inquire the main nodes of the system of the whole distributed system, if the main nodes exist, the main nodes of the system are obtained, and main node arbitration requests are not initiated to the main nodes in the groups in other groups; if not, the master node in each group initiates the arbitration master node request of the system, and becomes the system master node of the whole distributed system through G-1 times of arbitration (assuming that the distributed system has G groups in total).
Specifically, as shown in fig. 4, the arbitration master node flow chart:
step 1: dividing N nodes of a distributed system into a plurality of groups, and sending grouping information to each node;
step 2: after each node receives the grouping information, inquiring the grouping information to which the node belongs;
and step 3: whether the node is the grouping information of the node; if yes, executing step 4; if not, executing step 12;
and 4, step 4: if the node belongs to the grouping information of the node, whether the group has a main node in the group is inquired according to the grouping information; if not, executing the step 5; if yes, executing step 7;
and 5: if the group has no main node in the group, initiating a main node arbitration request in the group to other nodes in the group;
step 6: arbitrating the main nodes of the group by an arbitration module; executing the step 8;
and 7: if the group has the main nodes in the group, the request of the arbitration main node is not needed to be initiated;
and 8: inquiring whether the whole distributed system is an effective system main node or not, and if so, executing the step 9; if not, executing step 10;
and step 9: if the master node information of the system exists, the master node information of the system is acquired, and master node arbitration requests are not initiated to master nodes in other groups;
step 10: inquiring system main nodes of the whole distributed system, if not, initiating main node arbitration requests of the system by the main nodes in each group;
step 11: arbitrating a main node of the whole distributed system;
step 12: if the node does not belong to the grouping information of the node, randomly selecting the main nodes of other groups as the main nodes, or waiting for grouping without any processing.
In this embodiment of the present invention, optionally, after performing arbitration in nodes of each group divided in advance to obtain master nodes in a plurality of groups, the method includes:
for each group: sending first heartbeat information to a non-group main node of the group through the group main node of the group;
and when the non-group main node cannot receive the first heartbeat information, carrying out arbitration again in the group of nodes to obtain the group main node of the group.
In this embodiment of the present invention, optionally, after performing arbitration among master nodes in a plurality of groups to obtain a system master node of the distributed system, the method includes:
sending second heartbeat information to the main nodes in each group through the system main node;
and when the master nodes in each group cannot receive the second heartbeat information, carrying out arbitration again in the master nodes in each group to obtain the system master nodes of the distributed system.
For example, the system master node only needs to periodically send heartbeat information to the master nodes in each group in an optional period, and does not need to send the heartbeat information to each node in the distributed system; the intra-group master node of each group sends heartbeat information to the non-intra-group master nodes in the group without sending heartbeat information to the nodes of other groups.
If the non-group main node in the group does not receive the heartbeat information of the group main node and is overtime, the non-group main node initiates a main node arbitration request in the group, and re-arbitrates the group main node of the group.
If the main nodes in each group can not receive the heartbeat information of the system main nodes of the distributed system and time out, the main nodes in other groups initiate main node arbitration requests of the system (only the request is sent to the main nodes in each group), and the main nodes of the whole distributed system are arbitrated again.
Specifically, as shown in fig. 5, the master node exception flow chart:
step 1: when a certain node fails to receive heartbeat information and times out, the node finds that the main node is abnormal;
step 2: judging whether the main node is a system main node; if yes, executing the step 3, and if not, executing the step 5;
and step 3: if the abnormal main node is the system main node of the whole distributed system, initiating a main node arbitration request to the main nodes in each group;
and 4, step 4: each group of main nodes arbitrate out the system main nodes of the whole distributed system through an arbitration module;
and 5: if the abnormal master node is the master node in the group, initiating a master node arbitration request to other nodes in the group (if the master node in the group is not the system master node of the distributed system, the system master node of the distributed system does not need to be arbitrated);
step 6: each node in the group arbitrates out the main node in the group through an arbitration module;
and 7: 6, inquiring whether the whole distributed system has a system main node or not by the arbitrated group main nodes; if no system main node of the whole distributed system exists, entering the step 2, and if the system main node exists, executing the step 8;
and 8: if the system main node of the whole distributed system exists, the arbitration main node request does not need to be initiated.
In the embodiment of the invention, when the master node of the arbitration system needs to be arbitrated from the distributed system, the distributed system is firstly grouped, arbitration is carried out in each group, and the master node in each group is arbitrated; and secondly, arbitrating the main nodes in the groups of each group to arbitrate the system main nodes of the whole distributed system.
When the system main node of the whole distributed system is abnormal, firstly, a main node arbitration request needs to be initiated in the group where the main node in the group is located, and the main node arbitration request does not need to be initiated to all the nodes in the distributed system, and then, the main node arbitration request is conducted with the main nodes in the groups to arbitrate the main nodes of the system again, so that the arbitration range is effectively reduced, and the arbitration efficiency is improved.
Example two
The embodiment of the present invention provides a device for arbitrating master nodes in a distributed system, as shown in fig. 6, where the device includes a memory 20 and a processor 22; the memory 20 stores a computer program for arbitrating master nodes in a distributed system, and the processor 22 executes the computer program to implement the steps of the method according to any one of the embodiments.
In detail, the following steps are realized:
arbitrating in nodes of each group divided in advance to obtain main nodes in the groups of a plurality of groups;
and arbitrating in the group main nodes of the plurality of groups to obtain the system main node of the distributed system.
In this embodiment of the present invention, optionally, before performing arbitration in nodes of each group divided in advance to obtain a master node in a group of a plurality of groups, the method includes:
the distributed system is divided into a plurality of groups.
In the embodiment of the present invention, optionally, the distributed system is divided into a plurality of groups according to one or more of the following information:
node location information, network resource information, and computing power information.
In the embodiment of the present invention, optionally, after dividing the distributed system into a plurality of groups, the method includes:
and sending the grouping information of each group to each node in the distributed system so that each node is added into the corresponding group according to the grouping information.
In this embodiment of the present invention, optionally, the arbitrating in the nodes of each group divided in advance to obtain the intra-group master nodes of a plurality of groups includes:
for any node: after the node is added into a corresponding group, whether a main node in the group exists in the group is inquired;
if not, initiating a main node arbitration request in the group to arbitrate in the group to obtain the main node in the group;
if yes, inquiring whether the main node in the group is in the tenure period, and if not, initiating a main node arbitration request in the group to arbitrate in the group to obtain the main node in the group.
In this embodiment of the present invention, optionally, the arbitrating among the group master nodes in the multiple groups to obtain the system master node of the distributed system includes:
for any intra-group master node: after the master nodes in the group are added into the distributed system, inquiring whether system master nodes exist in the distributed system or not;
if not, initiating a main node arbitration request of the system to arbitrate in main nodes in each group to obtain a system main node;
if yes, inquiring whether the system main node is in the tenure, and if not, initiating a system arbitration main node request to arbitrate in the main nodes in each group to obtain the system main node.
In this embodiment of the present invention, optionally, after performing arbitration among master nodes in a plurality of groups to obtain a system master node of the distributed system, the method includes:
and the system main node sends arbitration information to each group main node and starts the system main node of the distributed system to be in the hold period.
In this embodiment of the present invention, optionally, after performing arbitration in nodes of each group divided in advance to obtain master nodes in a plurality of groups, the method includes:
for each group: sending first heartbeat information to a non-group main node of the group through the group main node of the group;
and when the non-group master node does not receive the first heartbeat information, carrying out arbitration again in the nodes of the group.
In this embodiment of the present invention, optionally, after performing arbitration among master nodes in a plurality of groups to obtain a system master node of the distributed system, the method includes:
sending second heartbeat information to the main nodes in each group through the system main node;
and when the master nodes in each group do not receive the second heartbeat information, carrying out arbitration again in the master nodes in each group.
Of course, when the embodiment of the present invention is specifically implemented, reference may also be made to embodiment one, so that a corresponding technical effect is achieved.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A method for a distributed system to arbitrate a master node, the method comprising:
arbitrating in nodes of each group divided in advance to obtain main nodes in the groups of a plurality of groups;
arbitrating in the group main nodes of a plurality of groups to obtain a system main node of the distributed system;
the arbitrating is performed in the nodes of each group divided in advance to obtain the group master nodes of a plurality of groups, and the method comprises the following steps:
for any node: after the node is added into a corresponding group, whether a main node in the group exists in the group is inquired;
if not, initiating a main node arbitration request in the group to arbitrate in the group to obtain the main node in the group;
if yes, inquiring whether the main node in the group is in the tenure period, if not, initiating a main node arbitration request in the group to arbitrate in the group to obtain the main node in the group;
the arbitrating among the master nodes in the groups of the multiple groups to obtain the system master node of the distributed system includes:
for any intra-group master node: after the master nodes in the group are added into the distributed system, inquiring whether system master nodes exist in the distributed system or not;
if not, initiating a main node arbitration request of the system to arbitrate in main nodes in each group to obtain a system main node;
if yes, inquiring whether the system main node is in the tenure, and if not, initiating a main node arbitration request of the system to arbitrate among the main nodes in each group to obtain the system main node.
2. The method of claim 1, wherein arbitrating among the nodes of each of the pre-partitioned groups before obtaining the master nodes within the groups of the plurality of groups comprises:
the distributed system is divided into a plurality of groups.
3. The method of claim 2, wherein the distributed systems are divided into groups based on one or more of:
node location information, network resource information, and computing power information.
4. The method of claim 2, wherein after the dividing the distributed system into a plurality of groups, comprising:
and sending the grouping information of each group to each node in the distributed system so that each node is added into the corresponding group according to the grouping information.
5. The method of any of claims 1-4, wherein arbitrating among master nodes in a plurality of groups to obtain a system master node for the distributed system comprises:
and the system main node sends arbitration information to each group main node and starts the system main node of the distributed system to be in the hold period.
6. The method according to any one of claims 1 to 4, wherein the arbitrating among the nodes of each group divided in advance, after obtaining the master nodes in the groups of the plurality of groups, comprises:
for each group: sending first heartbeat information to a non-group main node of the group through the group main node of the group;
and when the non-group master node does not receive the first heartbeat information, carrying out arbitration again in the nodes of the group.
7. The method of any of claims 1-4, wherein arbitrating among master nodes in a plurality of groups to obtain a system master node for the distributed system comprises:
sending second heartbeat information to the main nodes in each group through the system main node;
and when the master nodes in each group do not receive the second heartbeat information, carrying out arbitration again in the master nodes in each group.
8. An apparatus for a distributed system to arbitrate for master nodes, the apparatus comprising a memory and a processor; the memory stores a computer program for a distributed system arbitrating master node, which computer program is executed by the processor to carry out the steps of the method according to any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711275402.2A CN108111337B (en) | 2017-12-06 | 2017-12-06 | Method and equipment for arbitrating main nodes in distributed system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711275402.2A CN108111337B (en) | 2017-12-06 | 2017-12-06 | Method and equipment for arbitrating main nodes in distributed system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108111337A CN108111337A (en) | 2018-06-01 |
CN108111337B true CN108111337B (en) | 2021-04-06 |
Family
ID=62208142
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711275402.2A Active CN108111337B (en) | 2017-12-06 | 2017-12-06 | Method and equipment for arbitrating main nodes in distributed system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108111337B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109040184B (en) * | 2018-06-28 | 2021-09-07 | 武汉船舶通信研究所(中国船舶重工集团公司第七二二研究所) | Host node election method and server |
CN108984349B (en) * | 2018-08-17 | 2021-10-08 | 杭州朗和科技有限公司 | Method and device for electing master node, medium and computing equipment |
CN110166184B (en) * | 2019-04-03 | 2020-01-31 | 特斯联(北京)科技有限公司 | distributed communication confirmation request management method and system |
CN111835534B (en) * | 2019-04-15 | 2022-05-06 | 华为技术有限公司 | Method for cluster control, network device, master control node device and computer readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102355369A (en) * | 2011-09-27 | 2012-02-15 | 华为技术有限公司 | Virtual clustered system as well as processing method and processing device thereof |
CN104601364A (en) * | 2014-12-03 | 2015-05-06 | 华为技术有限公司 | Method and device for managing members in management cluster |
CN104917792A (en) * | 2014-03-12 | 2015-09-16 | 上海宝信软件股份有限公司 | Democratic and autonomous cluster management method and system |
US9146705B2 (en) * | 2012-04-09 | 2015-09-29 | Microsoft Technology, LLC | Split brain protection in computer clusters |
CN106559263A (en) * | 2016-11-17 | 2017-04-05 | 杭州沃趣科技股份有限公司 | A kind of improved distributed consensus algorithm |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107508694B (en) * | 2016-06-14 | 2021-11-16 | 中兴通讯股份有限公司 | Node management method and node equipment in cluster |
-
2017
- 2017-12-06 CN CN201711275402.2A patent/CN108111337B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102355369A (en) * | 2011-09-27 | 2012-02-15 | 华为技术有限公司 | Virtual clustered system as well as processing method and processing device thereof |
US9146705B2 (en) * | 2012-04-09 | 2015-09-29 | Microsoft Technology, LLC | Split brain protection in computer clusters |
CN104917792A (en) * | 2014-03-12 | 2015-09-16 | 上海宝信软件股份有限公司 | Democratic and autonomous cluster management method and system |
CN104601364A (en) * | 2014-12-03 | 2015-05-06 | 华为技术有限公司 | Method and device for managing members in management cluster |
CN106559263A (en) * | 2016-11-17 | 2017-04-05 | 杭州沃趣科技股份有限公司 | A kind of improved distributed consensus algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN108111337A (en) | 2018-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108111337B (en) | Method and equipment for arbitrating main nodes in distributed system | |
CN109213600B (en) | GPU resource scheduling method and device based on AI cloud | |
CN105718317A (en) | Task scheduling method and task scheduling device | |
CN101951411A (en) | Cloud scheduling system and method and multistage cloud scheduling system | |
CN109117252B (en) | Method and system for task processing based on container and container cluster management system | |
CN109416646B (en) | Optimization method for container allocation and processing equipment | |
CN114281521B (en) | Method, system, equipment and medium for optimizing deep learning heterogeneous resource communication efficiency | |
CN104239150B (en) | A kind of method and device of hardware resource adjustment | |
CN110187960A (en) | A kind of distributed resource scheduling method and device | |
CN106331192B (en) | Network protocol IP address allocation method and device | |
CN112286688B (en) | Memory management and use method, device, equipment and medium | |
CN104268007A (en) | Distributed event request scheduling method and system | |
CN105786447A (en) | Method and apparatus for processing data by server and server | |
CN104281636A (en) | Concurrent distributed processing method for mass report data | |
CN109240826B (en) | Method for allocating computing resources when nodes share computing equipment in multi-block chain network | |
Khetan et al. | A novel survey on load balancing in cloud computing | |
CN102932389B (en) | A kind of request processing method, device and server system | |
CN104158860A (en) | Job scheduling method and job scheduling system | |
CN109254844B (en) | Triangle calculation method of large-scale graph | |
CN106980463A (en) | The method for controlling quality of service and device of storage system | |
CN106447755A (en) | Animation rendering system | |
CN116226178A (en) | Data query method and device, storage medium and electronic device | |
TW202315360A (en) | Microservice allocation method, electronic equipment, and storage medium | |
JP2004219299A (en) | Parallel multiple target tracking system | |
CN107317880B (en) | Method and device for realizing load balance |
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 |