CN103441918A - Self-organizing cluster server system and self-organizing method thereof - Google Patents
Self-organizing cluster server system and self-organizing method thereof Download PDFInfo
- Publication number
- CN103441918A CN103441918A CN2013103850234A CN201310385023A CN103441918A CN 103441918 A CN103441918 A CN 103441918A CN 2013103850234 A CN2013103850234 A CN 2013103850234A CN 201310385023 A CN201310385023 A CN 201310385023A CN 103441918 A CN103441918 A CN 103441918A
- Authority
- CN
- China
- Prior art keywords
- cluster
- sub
- node
- server
- self
- 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
Images
Landscapes
- Hardware Redundancy (AREA)
Abstract
The invention provides a self-organizing cluster server system and a self-organizing method thereof. The self-organizing cluster server system mainly relates to the organizing method of a sub-cluster server system, the method of connection between nodes in sub-clusters and the sub-clusters, and the dividing principle of the sub-clusters. The self-organizing method of the cluster server system comprises the steps of joining of the nodes, quitting of the nodes, dividing of the sub-clusters and combination of the sub-clusters. According to the self-organizing cluster server system and the self-organizing method thereof, server groups are organized to be the cluster system by means of self-organizing and the cluster system is divided into a plurality of ordered sub-clusters, an upper level of sub-clusters serve as a main server of a lower level of sub-clusters, the lower level of sub-clusters are defined as a server in the upper level of sub-clusters, therefore, main servers with strong computing capability are obtained, the number of servers is reduced logically, and complicated load allocation and management work is divided.
Description
Technical field
What the present invention relates to is a kind of cluster server, the present invention also relates to a kind of self-organizing method of cluster server.
Background technology
Along with the development of IT technology, computer becomes the important component part of the aspects such as people's daily life, work, study, amusement gradually.Yet, high-intensity science computation requirement is challenged the computing capability of supercomputer gradually, traffic carrying capacity on Internet and even enterprise network, Campus Networks development has all exceeded in the past the most optimistic estimation greatly, the user constantly pursues more happy user and experiences, yet the single server of upgrading, the return obtained is not proportional to the cost of paying, and the lifting cost performance of random device performance declines to a great extent.Therefore, hardware system and the software platform of server are had higher requirement, as extensibility, all-weather availability, manageability and higher cost performance.
For tackling the high application (as weather forecast, nuclear test simulation etc.) of some bulk density demands in reality, need server to have extremely powerful operational capability, yet according to existing technical merit, even single supercomputer also has been difficult to.For tackling this class challenge, need to by tens even the operational capability of hundreds of station server integrate, form server cluster.Use the server cluster technology except obtaining powerful operational capability, can also improve the transaction ability.Along with popularizing of network, for tackling with demands such as the daily request of the user of trillion countings and large data processing, increasing people starts to select relatively inexpensive server via Ethernet is linked to the composition server cluster, with this, reaches the demand that obtains superior performance than low-cost of using.
Two kinds of establishment server cluster methods commonly used are generally arranged: a kind of is to be a backup server of master server configuration, and when master server breaks down, backup server is taken over the function of master server; A kind of is the work of multiple servers shared master server, and each server provides fault tolerant service mutually, and when wherein a station server breaks down, system is isolated this server, and completes new load distribution by the load metastasis.These two kinds of methods have the deficiency of self, and the undue performance that relies on main service of a kind of front method, can make whole group system produce performance bottleneck; A kind of rear method is along with the continuous increase of interstitial content, and the task management expense of cluster can significantly increase, and therefore adopts the cluster scale of this method to be subject to certain restrictions.
Summary of the invention
The object of the present invention is to provide and a kind ofly can improve aggregated server system autgmentability, adaptability, the self-organizing aggregated server system that is easy to administer and maintain.The present invention also aims to provide a kind of self-organizing method of self-organizing aggregated server system.
Self-organizing aggregated server system of the present invention consists of a plurality of sub-cluster that comprise some nodes, and new server adds according to self-position, performance, the autonomous chooser cluster of purposes; When sub-cluster comprises server and reaches some, part server is removed to this sub-cluster and set up new sub-cluster, new sub-cluster is connected by a share service device with atomic cluster; The order that the grade of sub-cluster forms according to sub-cluster is definite, and the initial sub-cluster formed is the 1st grade of sub-cluster, and the new sub-cluster formed by the 1st grade of sub-cluster division is called the 2nd grade of sub-cluster, by that analogy; When exiting group system due to server node and make in a certain sub-cluster that number of nodes is very few, this sub-cluster is preferentially selected to merge coupled next stage sub-cluster, as does not have subordinate's sub-cluster to merge in the upper level sub-cluster;
Each server node of described sub-cluster interconnects, and provides the redundancy backup service for other server nodes; When the server node abnormal is arranged, first shift the service of operation on it to the adjacent service device, then its safety from sub-cluster is removed; When connecting the server abnormal of upper and lower two-stage sub-cluster, its node in the upper level sub-cluster is processed, and in the upper level sub-cluster, selected new connected node to replace the server of abnormal.
The self-organizing method of self-organizing aggregated server system of the present invention comprises the steps:
(1) when having the new node request to add aggregated server system, according to performance, the purposes characteristics of new node, for new node selects suitable sub-cluster as adding target, after destination subset group calculates new Task Assigned Policy, receive new node, and be its allocating task and resource;
(2) while having the node request to exit in aggregated server system, at first group system checks the residing position of this node and state, to the connected node between ordinary node and sub-cluster, adopt the heavy allocation strategy of different tasks, finishing the work, resource transfers, and after reaching new load balancing, then application is exited to node safety deleting from group system;
(3) in sub-cluster, there is new node to add fashionable, for preventing that in sub-cluster, task distributes the expense of required calculating excessive, need to check in sub-cluster, whether the server node number is greater than threshold values N(N for the numerical value definite according to the practical efficiency of aggregated server system, when group group system server node number is greater than N, the amount of calculation of distributing for system task sharply increases), if the sub-cluster node is too much, strategy is divided it according to the rules, keeps the sub-cluster scale in rational scope;
(4), while having node to exit, check in sub-cluster, whether the server node number is less than threshold values N in sub-cluster
0(N
0for preset value, in the sub-cluster group system, the server node number is less than N
0the time, excessive with adjacent subset group computing capability gap, be unfavorable for that whole group system realizes load balancing), sub-cluster and adjacent subset group that scale is less merge, to reduce the administration overhead of group system.
Self-organizing aggregated server system of the present invention is mainly by aspects such as the connected mode between teaming method, sub-cluster interior nodes and the sub-cluster of sub-cluster server system, sub-cluster division principles.The sub-cluster division principle is: in the self-organizing building process of aggregated server system, in order to reduce, the group system task is distributed, load balancing etc. the computing cost of task, usually by computing capability, stronger node is assigned in the sub-cluster that rank is higher, with the computing capability of average each node.Sub-cluster institutional frameworks at different levels are transparent each other, and for interconnective two adjacent subset groups, the next stage sub-cluster provides service as the part of connected node for the upper level sub-cluster.
The self-organizing method of aggregated server system of the present invention comprises the exiting of the adding of node, node, the division of sub-cluster and the flow processs such as merging of sub-cluster.The aggregated server system of setting up by the method is distributes calculation resources reasonably, dynamic adjusting system load, and effectively control the expense of non-calculation task.
Adopt self-organizing aggregated server system of the present invention and self-organizing method thereof, by Ad hoc mode, the server group is set up and become group system, and it is divided into to some orderly sub-cluster, higher level's sub-cluster is equivalent to the master server of subordinate's sub-cluster, subordinate's sub-cluster is defined as the server in higher level's sub-cluster, not only can obtain the master server that has powerful calculating ability like this, can also logically reduce the quantity of server, complicated load distribution and management work are divided and rule.Therefore, method provided by the invention can effectively overcome the shortcoming of current cluster server construction method commonly used.
The accompanying drawing explanation
Fig. 1 is the structure chart that the embodiment of the present invention is applied to the self-organizing aggregated server system;
The clustered node that Fig. 2 is the embodiment of the present invention adds flow chart;
The clustered node that Fig. 3 is the embodiment of the present invention exits flow chart;
The sub-cluster that Fig. 4 is the embodiment of the present invention is divided flow chart;
The sub-cluster that Fig. 5 is the embodiment of the present invention merges flow chart.
Embodiment
Below in conjunction with the accompanying drawing in the present invention, the technical scheme in the present invention is clearly and completely described.Obviously, described embodiment is only a part of embodiment of the present invention, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills are under the prerequisite of not making creative work, and the every other embodiment obtained, belong to the scope of protection of the invention.
Fig. 1 is the structure chart that the embodiment of the present invention is applied to the self-organizing aggregated server system.In the present embodiment, aggregated server system has 10,20,21 and 30 4 sub-cluster altogether.Sub-cluster 10 is the 1st grade of sub-cluster, comprises altogether 6 nodes, and 4 single server nodes and 2 the 2nd grade sub-cluster node (20 and 21) are wherein arranged; Sub-cluster 20 is the 2nd grade of sub-cluster, comprises altogether 5 nodes, and 4 single server nodes and 1 3rd level sub-cluster node (30) are wherein arranged; Sub-cluster 21 is the 2nd grade of sub-cluster node, comprises altogether 5 single server nodes; Sub-cluster 30 is the 3rd level sub-cluster, comprises altogether four sub-clustered nodes.In figure, solid line means that in sub-cluster, each node is in logic according to the circular pattern link, and dotted line means that the node in same sub-cluster is interconnected, and externally is rendered as Unified Global.
Node 101 belongs to the 1st grade of sub-cluster 10 and the 2nd grade of sub-cluster 20 simultaneously, as the hinged node of 10 and 20 two sub-cluster.In sub-cluster 10, node 101 is equivalent to ordinary node and exists, but this node does not represent 101 individualities, but represents sub-cluster 20, and this node has whole resources and the computing capability of sub-cluster 20.In sub-cluster 20, node N101, except as ordinary node, also is responsible for the work from higher level's sub-cluster 10 reception tasks and instruction.What need particularly point out is, load for each service in a balanced sub-cluster, the bottleneck that elimination is caused by master server performance deficiency, the distribution that might not continue to execute the task after 101 reception tasks, but according to sub-cluster current loading condition, task is transferred to suitable node and is distributed relevant calculating.
Self-organizing flow process below in conjunction with Fig. 2-5 pair aggregated server system is done brief description.
The clustered node that Fig. 2 is the embodiment of the present invention adds flow chart.
The node application adds aggregated server system at first will join request by sending node in network of living in, waits for the response of respective subset group in aggregated server system.If joining request of node do not answered, prove in network environment of living in and there is no the aggregated server system operation, the node that request adds can newly create aggregated server system; The response of receiving 1 sub-cluster when node directly adds this sub-cluster; If obtain the response of a plurality of sub-cluster, node needs the information of each sub-cluster is analyzed, and according to the situation of oneself, selects suitable sub-cluster to add.After node adds sub-cluster, the place sub-cluster will be analyzed the state of oneself, if the scale of this sub-cluster excessive (in sub-cluster, interstitial content is greater than threshold values N), this sub-cluster need to be repartitioned, by a part of node division, be new sub-cluster, excessive to reduce the shared ratio of the required computing cost of cluster management.The sub-cluster integral body newly marked off, as a node of atomic cluster, is the next stage sub-cluster of atomic cluster.
The clustered node that Fig. 3 is the embodiment of the present invention exits flow chart.
State and self present position that at first aggregated server system will judge aggregated server system exited in the node application.If this node is node unique in aggregated server system, this node can directly exit aggregated server system after the preservation work that completes resource and task.As also had other server node in cluster server, and this node is not the connected node between sub-cluster, after this node shifts had resource and Mission Success, can directly exit aggregated server system.If this node is the connected node of adjacent two sub-cluster, by owned resource and task transfers to backed off after random in the sub-cluster of higher level.Simultaneously, wherein the sub-cluster of higher level is selected new connected node and is added in more low-level sub-cluster from affiliated node.When having node to exit, respective subset group is analyzed oneself state, if the scale of this sub-cluster is too small, (in sub-cluster, interstitial content is less than threshold values N
0), this sub-cluster need to be carried out union operation with adjacent sub-cluster.
The sub-cluster that Fig. 4 is the embodiment of the present invention is divided flow chart.
When sub-cluster is carried out from new division, at first, need to be analyzed performance, function, resource and the task of each server node in sub-cluster, to obtain the lower splitting scheme of expense; Then, carry out the distribution of task, the transmission of resource, data according to the splitting scheme of analyzing gained; Finally, complete the division of sub-cluster, obtain sub-cluster and a more low-level sub-cluster of a same levels.For keeping the relative equilibrium of each node computing capability in sub-cluster, when carrying out the sub-cluster division, when the division expense is suitable, node that usually can technical capability is higher is retained in the sub-cluster that rank is higher.
The sub-cluster that Fig. 5 is the embodiment of the present invention merges flow chart.
When sub-cluster need to be carried out union operation, need first the information of aggregated server system to be analyzed.As there is higher level's sub-cluster in this sub-cluster, directly merge in higher level's sub-cluster; As there is not higher level's sub-cluster in this sub-cluster, the subordinate's sub-cluster be connected with this sub-cluster is analyzed, choose suitable subordinate's sub-cluster and self merging.If this sub-cluster does not exist higher level's sub-cluster not have subordinate's sub-cluster yet, prove that in this cluster service system, nodes is very few, union operation stops.
In sum, the present invention is set up aggregated server system by Ad hoc mode, can reach the purpose of dynamic assignment computational resource, balanced service load.In different sub-cluster, can effectively reduce task, load assignment overhead proportion by the node division by aggregated server system, significantly improve the effective rate of utilization of group system.
Certainly; the present invention also can have other various embodiments; in the situation that do not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art are when making according to the present invention various corresponding changes and distortion, but these corresponding changes and distortion all should belong to the protection range of the appended claim of the present invention.
Claims (2)
1. a self-organizing aggregated server system, it is characterized in that: the self-organizing aggregated server system consists of a plurality of sub-cluster that comprise some nodes, and new server adds according to self-position, performance, the autonomous chooser cluster of purposes; When sub-cluster comprises server and reaches some, part server is removed to this sub-cluster and set up new sub-cluster, new sub-cluster is connected by a share service device with atomic cluster; The order that the grade of sub-cluster forms according to sub-cluster is definite, and the initial sub-cluster formed is the 1st grade of sub-cluster, and the new sub-cluster formed by the 1st grade of sub-cluster division is called the 2nd grade of sub-cluster, by that analogy; When exiting group system due to server node and make in a certain sub-cluster that number of nodes is very few, this sub-cluster is preferentially selected to merge coupled next stage sub-cluster, as does not have subordinate's sub-cluster to merge in the upper level sub-cluster;
Each server node of described sub-cluster interconnects, and provides the redundancy backup service for other server nodes; When the server node abnormal is arranged, first shift the service of operation on it to the adjacent service device, then its safety from sub-cluster is removed; When connecting the server abnormal of upper and lower two-stage sub-cluster, its node in the upper level sub-cluster is processed, and in the upper level sub-cluster, selected new connected node to replace the server of abnormal.
2. the self-organizing method of a self-organizing aggregated server system, is characterized in that comprising the steps:
(1) when having the new node request to add aggregated server system, according to performance, the purposes characteristics of new node, for new node selects suitable sub-cluster as adding target, after destination subset group calculates new Task Assigned Policy, receive new node, and be its allocating task and resource;
(2) while having the node request to exit in aggregated server system, at first group system checks the residing position of this node and state, to the connected node between ordinary node and sub-cluster, adopt the heavy allocation strategy of different tasks, finishing the work, resource transfers, and after reaching new load balancing, then application is exited to node safety deleting from group system;
(3) in sub-cluster, have new node to add fashionable, look into server node number in sub-cluster and whether be greater than threshold values N, if the sub-cluster node is too much, strategy is divided it according to the rules, keeps the sub-cluster scale in rational scope;
(4), while having node to exit, check in sub-cluster, whether the server node number is less than threshold values N in sub-cluster
0, sub-cluster and adjacent subset group that scale is less merge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103850234A CN103441918A (en) | 2013-08-29 | 2013-08-29 | Self-organizing cluster server system and self-organizing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103850234A CN103441918A (en) | 2013-08-29 | 2013-08-29 | Self-organizing cluster server system and self-organizing method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103441918A true CN103441918A (en) | 2013-12-11 |
Family
ID=49695584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013103850234A Pending CN103441918A (en) | 2013-08-29 | 2013-08-29 | Self-organizing cluster server system and self-organizing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103441918A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103905544A (en) * | 2014-03-25 | 2014-07-02 | 华为技术有限公司 | Cluster storage system and distribution method of nodes in cluster storage system |
| 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 |
| CN104951475A (en) * | 2014-03-31 | 2015-09-30 | 中国电信股份有限公司 | Distributed file system and implementation method |
| CN105721545A (en) * | 2016-01-20 | 2016-06-29 | 浪潮(北京)电子信息产业有限公司 | Multi-level cluster management realization method |
| CN106131141A (en) * | 2016-06-27 | 2016-11-16 | 徐州医科大学 | A kind of distributed type assemblies load balancing parallel dispatch system and method |
| CN106302726A (en) * | 2016-08-15 | 2017-01-04 | 浪潮(北京)电子信息产业有限公司 | The monitoring method of the management node of a kind of distributed type assemblies data and module |
| CN106936614A (en) * | 2015-12-31 | 2017-07-07 | 华为技术有限公司 | The self-organizing method of group system, equipment and system |
| CN108092829A (en) * | 2018-01-31 | 2018-05-29 | 深信服科技股份有限公司 | Processing method, SDN controllers and the storage medium of cluster division |
| CN110537169A (en) * | 2017-04-28 | 2019-12-03 | 微软技术许可有限责任公司 | Cluster resource management in distributed computing system |
| CN113596746A (en) * | 2021-07-22 | 2021-11-02 | 北京金山云网络技术有限公司 | Cluster message processing method and device, electronic equipment and medium |
| CN114553864A (en) * | 2020-11-19 | 2022-05-27 | 富士通株式会社 | Network node clustering method, system and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1691619A (en) * | 2004-04-27 | 2005-11-02 | 国家数字交换系统工程技术研究中心 | Method for implementing self-organizing network |
| US20070112963A1 (en) * | 2005-11-17 | 2007-05-17 | International Business Machines Corporation | Sending routing data based on times that servers joined a cluster |
| CN101035021A (en) * | 2007-02-08 | 2007-09-12 | 北京航空航天大学 | Stable energy-saving group maintenance method |
| CN101060479A (en) * | 2007-05-28 | 2007-10-24 | 广州杰赛科技股份有限公司 | Wireless self-organized network distribution authentication multi-layer tree route method |
| US20090172139A1 (en) * | 2007-12-26 | 2009-07-02 | Kai Chiu Wong | Balanced consistent hashing for distributed resource management |
| CN101819540A (en) * | 2009-02-27 | 2010-09-01 | 国际商业机器公司 | Method and system for scheduling task in cluster |
| CN101969681A (en) * | 2010-11-08 | 2011-02-09 | 中国人民解放军空军工程大学 | Realization method of router of large-scale mobile self-organizing network |
| CN102158540A (en) * | 2011-02-18 | 2011-08-17 | 广州从兴电子开发有限公司 | System and method for realizing distributed database |
-
2013
- 2013-08-29 CN CN2013103850234A patent/CN103441918A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1691619A (en) * | 2004-04-27 | 2005-11-02 | 国家数字交换系统工程技术研究中心 | Method for implementing self-organizing network |
| US20070112963A1 (en) * | 2005-11-17 | 2007-05-17 | International Business Machines Corporation | Sending routing data based on times that servers joined a cluster |
| CN101035021A (en) * | 2007-02-08 | 2007-09-12 | 北京航空航天大学 | Stable energy-saving group maintenance method |
| CN101060479A (en) * | 2007-05-28 | 2007-10-24 | 广州杰赛科技股份有限公司 | Wireless self-organized network distribution authentication multi-layer tree route method |
| US20090172139A1 (en) * | 2007-12-26 | 2009-07-02 | Kai Chiu Wong | Balanced consistent hashing for distributed resource management |
| CN101819540A (en) * | 2009-02-27 | 2010-09-01 | 国际商业机器公司 | Method and system for scheduling task in cluster |
| CN101969681A (en) * | 2010-11-08 | 2011-02-09 | 中国人民解放军空军工程大学 | Realization method of router of large-scale mobile self-organizing network |
| CN102158540A (en) * | 2011-02-18 | 2011-08-17 | 广州从兴电子开发有限公司 | System and method for realizing distributed database |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN104917792B (en) * | 2014-03-12 | 2018-10-30 | 上海宝信软件股份有限公司 | The cluster management method and system of democratic autonomy |
| CN103905544A (en) * | 2014-03-25 | 2014-07-02 | 华为技术有限公司 | Cluster storage system and distribution method of nodes in cluster storage system |
| CN104951475A (en) * | 2014-03-31 | 2015-09-30 | 中国电信股份有限公司 | Distributed file system and implementation method |
| CN104951475B (en) * | 2014-03-31 | 2018-10-23 | 中国电信股份有限公司 | Distributed file system and implementation method |
| CN106936614B (en) * | 2015-12-31 | 2020-02-14 | 华为技术有限公司 | Self-organizing method, device and system of cluster system |
| CN106936614A (en) * | 2015-12-31 | 2017-07-07 | 华为技术有限公司 | The self-organizing method of group system, equipment and system |
| US10904093B2 (en) | 2015-12-31 | 2021-01-26 | Huawei Technologies Co., Ltd. | Cluster system self-organizing method, device, and cluster system |
| CN105721545A (en) * | 2016-01-20 | 2016-06-29 | 浪潮(北京)电子信息产业有限公司 | Multi-level cluster management realization method |
| CN105721545B (en) * | 2016-01-20 | 2019-01-22 | 浪潮(北京)电子信息产业有限公司 | A kind of multi-level cluster management implementation method |
| CN106131141A (en) * | 2016-06-27 | 2016-11-16 | 徐州医科大学 | A kind of distributed type assemblies load balancing parallel dispatch system and method |
| CN106302726A (en) * | 2016-08-15 | 2017-01-04 | 浪潮(北京)电子信息产业有限公司 | The monitoring method of the management node of a kind of distributed type assemblies data and module |
| CN106302726B (en) * | 2016-08-15 | 2019-05-28 | 浪潮(北京)电子信息产业有限公司 | A kind of monitoring method and module of the management node of distributed type assemblies data |
| CN110537169A (en) * | 2017-04-28 | 2019-12-03 | 微软技术许可有限责任公司 | Cluster resource management in distributed computing system |
| US11700300B2 (en) | 2017-04-28 | 2023-07-11 | Microsoft Technology Licensing, Llc | Cluster resource management in distributed computing systems |
| CN110537169B (en) * | 2017-04-28 | 2023-10-24 | 微软技术许可有限责任公司 | Cluster resource management in a distributed computing system |
| CN108092829A (en) * | 2018-01-31 | 2018-05-29 | 深信服科技股份有限公司 | Processing method, SDN controllers and the storage medium of cluster division |
| CN114553864A (en) * | 2020-11-19 | 2022-05-27 | 富士通株式会社 | Network node clustering method, system and computer readable storage medium |
| CN113596746A (en) * | 2021-07-22 | 2021-11-02 | 北京金山云网络技术有限公司 | Cluster message processing method and device, electronic equipment and medium |
| CN113596746B (en) * | 2021-07-22 | 2022-11-04 | 北京金山云网络技术有限公司 | Cluster message processing method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103441918A (en) | Self-organizing cluster server system and self-organizing method thereof | |
| CN102611735B (en) | A kind of load-balancing method of application service and system | |
| CN110134495B (en) | Container cross-host online migration method, storage medium and terminal equipment | |
| CN103227838B (en) | A kind of multi-load equilibrium treatment apparatus and method | |
| Sonbol et al. | EdgeKV: Decentralized, scalable, and consistent storage for the edge | |
| CN106843745A (en) | Capacity expansion method and device | |
| CN108519917A (en) | A kind of resource pool distribution method and device | |
| CN112256438B (en) | Load balancing control method and device, storage medium and electronic equipment | |
| CN102594861A (en) | Cloud storage system with balanced multi-server load | |
| CN102110021B (en) | Automatic optimization method for cloud computing | |
| CN101778002B (en) | Large-scale cluster system and building method thereof | |
| CN104038540A (en) | Method and system for automatically selecting application proxy server | |
| CN102394903B (en) | A kind of active reconstruction calculating system constructing system | |
| CN103997523A (en) | Smart city service system based on cloud services and implementation method thereof | |
| CN111858033A (en) | Load balancing method based on cluster and multiple processes | |
| Anandhi et al. | A challenge in improving the consistency of transactions in cloud databases-scalability | |
| CN106059940B (en) | A kind of flow control methods and device | |
| CN102339233A (en) | Cloud computing centralized management platform | |
| CN103997515B (en) | Center system of selection and its application are calculated in a kind of distributed cloud | |
| CN109873772A (en) | Stream scheduling method, device, computer equipment and storage medium based on stable matching | |
| CN112202679A (en) | Hardware equipment quantification method and system for hierarchical network topology automatic routing distribution | |
| CN102801750B (en) | Method for constructing cloud computing target system | |
| CN104270299A (en) | Method and system for virtual network mapping | |
| Wang et al. | An efficient hybrid P2P MMOG cloud architecture for dynamic load management | |
| CN105677440A (en) | Virtual machine automatic migrate system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131211 |
|
| WD01 | Invention patent application deemed withdrawn after publication |