CN102025550A - System and method for managing data in distributed cluster - Google Patents
System and method for managing data in distributed cluster Download PDFInfo
- Publication number
- CN102025550A CN102025550A CN201010597613XA CN201010597613A CN102025550A CN 102025550 A CN102025550 A CN 102025550A CN 201010597613X A CN201010597613X A CN 201010597613XA CN 201010597613 A CN201010597613 A CN 201010597613A CN 102025550 A CN102025550 A CN 102025550A
- Authority
- CN
- China
- Prior art keywords
- node
- responsible
- data
- subscription
- data partition
- 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
Abstract
The invention discloses a system for managing data in a distributed cluster, which comprises a master node and responsible nodes, wherein the master node is used for partitioning stored data and selecting one slave node for each data partition as one responsible node; and each responsible node is used for managing the corresponding data partition under the charge. The invention also discloses a method for managing data in a distributed cluster. By using the system and the method, updates of different data partitions can be distributed on different slave nodes, thereby effectively sharing the load of the master node. Simultaneously, the responsible nodes can be assigned in accordance with practical situations of the slave nodes, thereby giving a full play to capabilities of the slave nodes.
Description
Technical field
The present invention relates to the computer cluster technology, be meant the system and method for data management in a kind of distributed type assemblies especially.
Background technology
Computer cluster is called for short cluster, is a kind of parallel or distributed processing system(DPS).Described cluster interconnects by one group of loose integrated computer, and highly closely needed evaluation work is finished in cooperation.Wherein, single computer is commonly called node.Can realize memory database system by Clustering, comprising host node and a plurality of from node.Host node is responsible for to each from the node synchrodata, and to managing from node.Each node has been stored identical data, and each node can finish identical work, because can a plurality of node parallel processings, therefore utilize Clustering can improve the treatment effeciency of data; On the other hand, the data of a plurality of nodes, the course of work is just the same, can tolerate that therefore faults such as deadlock appear in part of nodes, and then improve the availability and the stability of group system.
Node carries out parallel processing, has stored identical data, carries out collaborative work in cluster, and it is as a whole to make that cluster externally shows.The consistency that this shows data in the cluster seems extremely important, otherwise different node will show different behaviors, can influence cluster and carry out the data processing service.For distributed memory bank cluster, data are its cores, keep the consistency of cluster interior nodes data even more important.
Solving the problem of data consistency in the current cluster technology, mainly is to utilize host node to manage.When host node produces data variation, with the data that change be pushed in the cluster other from node, but there are two problems in this management method: 1) host node has been born too much load, is unfavorable for load balancing; 2) the passive acceptance of other nodes, participation is low, and simultaneously, host node is treated each node is all identical, can not be with reference to the actual conditions from node, for example: performance, running status etc. can not be given full play to the ability from node.These problems have become the bottleneck of Clustering development.
Summary of the invention
In view of this, main purpose of the present invention is to provide the system and method for data management in a kind of distributed type assemblies, can share the load of host node, in conjunction with giving full play to its ability from the actual conditions of node.
For achieving the above object, technical scheme of the present invention is achieved in that
The invention provides the system of data management in a kind of distributed type assemblies, described system comprises: host node and responsible node, wherein,
Described host node is used for the data of storage are carried out subregion, for each data partition select one from node as responsible node;
Described responsible node is used for the data partition that described responsible node is responsible for is managed.
Wherein, described responsible node manages the data partition of self being responsible for, and comprising:
When the information of the responsible data partition of described responsible node changes, by described responsible node the data that change are sent to other and finish write operation from node;
Make regular check on subscription queue, according to the data of effective subscribe request in the data partition of self being responsible for from the node transmission that sends subscribe request.
Wherein, described host node selects one specifically to be according to selecting responsible node from the running status of node with from node capacity from node as responsible node for each data partition.
Wherein, described system also comprises:
Initiate node is used for the broadcast transmission register requirement, receive registration response after, send register node information to host node, receive host node synchronous clustered node tabulation and data partition information;
Described host node, after also being used to receive register requirement, judge whether described initiate node is legal, if it is legal then return registration response, otherwise return failure response, after receiving register node information,, and in cluster, upgrade clustered node tabulation and data partition information synchronously with the information adding clustered node tabulation of initiate node.
Wherein, the node of described initiate node or write operation failure also is used for sending the subscription data request to host node;
Described host node also is used to receive the subscription data request, add in the subscription queue, and in cluster synchronous subscription queue.
Wherein, described responsible node also is used to make regular check on subscription queue, judges whether the subscription progress in the subscription data request is consistent with current data, if inconsistent then current data group bag structure notification message is sent to the node of subscription.
The present invention also provides the method for data management in a kind of distributed type assemblies, and described method comprises:
Host node carries out subregion to the data of storage, for each data partition select one from node as responsible node;
The data partition that responsible node is responsible for described responsible node manages.
Wherein, described responsible node manages the data partition of self being responsible for, and comprising:
When the information of the responsible data partition of described responsible node changes, by described responsible node the data that change are sent to other and finish write operation from node;
Make regular check on subscription queue, according to the data of effective subscribe request in the data partition of self being responsible for from the node transmission that sends subscribe request.
Wherein, described host node selects one specifically to be according to selecting responsible node from the running status of node with from node capacity from node as responsible node for each data partition.
Wherein, in the process of responsible node management, described method also comprises:
Initiate node broadcasts sends register requirement; Host node judges whether described initiate node is legal after receiving register requirement, if legal then return the registration response, otherwise return failure response, and the end process flow process; Initiate node sends register node information to host node after receiving the registration response; After host node receives register node information,, and in cluster, upgrade clustered node tabulation and data partition information synchronously with the information adding clustered node tabulation of initiate node.
The system and method for data management in the distributed type assemblies provided by the present invention, host node carries out subregion to the data of storage, for each data partition select one from node as responsible node; The data partition that responsible node is responsible for described responsible node manages.It is different from node to make that the renewal of different pieces of information subregion is distributed in, and can effectively share the load of host node.Simultaneously, according to carrying out the appointment of responsible node, can give full play to ability from node from the actual conditions of node.
Description of drawings
Fig. 1 is the system configuration schematic diagram of data management in a kind of distributed type assemblies of the present invention;
The message structure schematic diagram that Fig. 2 preserves for node in the system of data management in a kind of distributed type assemblies of the present invention;
Fig. 3 is the method flow schematic diagram of data management in a kind of distributed type assemblies of the present invention.
Embodiment
To be host node carry out subregion to the data of storage to basic thought of the present invention, for each data partition select one from node as responsible node; The data partition that responsible node is responsible for described responsible node manages.
The technical solution of the present invention is further elaborated below in conjunction with the drawings and specific embodiments.
Fig. 1 is the system configuration schematic diagram of data management in a kind of distributed type assemblies of the present invention, and as shown in Figure 1, described system comprises: host node 11 and responsible node 12, wherein,
Described host node 11 is used for the data of storage are carried out subregion, for each data partition select one from node as responsible node 12;
Concrete, it specifically is from number of nodes the data of storage to be carried out subregion according to what move in the current cluster that the data of 11 pairs of storages of described host node are carried out subregion.Because each data partition behind the subregion all will be responsible for from node by one, so the quantity of subregion should be smaller or equal to the quantity from node.Described host node 11 selects one specifically to be according to selecting responsible node 12 from the running status of node with from node capacity from node as responsible node 12 for each data partition.Wherein, describedly comprise from the running status of node with from node capacity: the transmission speed of the network that inserts from node, from the current running status of node self, and from the ability of node processing data.Described host node 11 obtains from the state of node and node capacity and realizes by the regular information synchronization of each node the cluster.Further, in the cluster running, if responsible node 12 faults, described host node 11 according to reselect from the state of node and node capacity one be responsible for other data partitions from node, take over the responsible node 12 of fault.If do not have to be responsible for from node, for example: other from node all had separately responsible data partition or be responsible for when the current state of node and node capacity are not enough to become responsible node 12, host node 11 carries out subregion and selects responsible node 12 data of storage again, promptly adjusts all data partitions.
Described responsible node 12 is used for other data partitions of being responsible for from responsible node described in the node 12 are managed.
Concrete, described responsible node 12 manages the data partition of self being responsible for and comprises: when the information of the data partition of being responsible for when described responsible node 12 changes, by described responsible node 12 data that change are sent to other and finish write operation from node; Make regular check on subscription queue, according to the data of effective subscribe request in the data partition of self being responsible for from the node transmission that sends subscribe request.
Further in cluster, all nodes have been preserved identical message structure, the message structure schematic diagram that Fig. 2 preserves for node in the system of data management in a kind of distributed type assemblies of the present invention, as shown in Figure 2, preserved in the node 20: clustered node tabulation 21, subscription queue 22, data partition information 23 and Cluster Database data 24, wherein, described clustered node tabulation 21 comprises: the node identification of each node, node capacity and node state in the cluster; Described subscription queue 22 comprises: the scope of node, subscription progress and the subscription of subscription task sign, subscription; Described data partition information 23 comprises: the information of the responsible node of each data partition; Described Cluster Database data 24 are data of the storage in the cluster.Further, can be divided into three data subregions in the Cluster Database data 24, manage by three responsible nodes 12 respectively.Described clustered node tabulation 21, subscription queue 22 and data partition information 23 are safeguarded by host node 11.
Further, also comprise in the described system: initiate node 13, be used for the broadcast transmission register requirement, receive registration response after, send the register node information to host node 11, receive host node 11 synchronous clustered nodes tabulation and data partition information;
Concrete, in the register requirement that initiate node 13 sends, the IP address of having carried initiate node 13.After receiving the registration response, owing to the IP address of having carried host node 11 in the registration response, therefore initiate node 13 sends register node information to host node 11 and can adopt the clean culture transmission.Comprise in the described register node information: the ability of described initiate node and node state, i.e. the software and hardware information of this node.
Described host node 11, after also being used to receive register requirement, judge whether described initiate node 13 is legal, if it is legal then return registration response, otherwise return failure response, after receiving register node information,, and in cluster, upgrade clustered node tabulation and data partition information synchronously with the information adding clustered node tabulation of initiate node 13.
Concrete, whether described host node: judging that the cluster internal segment is counted reaches the upper limit if judging whether described initiate node 13 is legal, comprising, and whether the IP address is in tolerance band, if do not reach the upper limit and IP address in the scope of permission, then initiate node 13 is legal; If reach the upper limit or IP address not in the scope of permission, then initiate node 13 is illegal.
Further, after initiate node 13 added cluster, initiate node 13 also was used for sending the subscription data request to host node 11;
Concrete, comprise in the described subscription data request: the scope of node, subscription progress and the subscription of subscription task sign, subscription.Wherein, described subscription progress is the timestamp of the data that existed of current node.The scope of described subscription, promptly the data content of Ding Yueing can be determined according to data partition.Need to prove, except initiate node 13 can send the subscription data request, receive the more new data that responsible node sends from node after, during the write operation failure, also can send the subscription data requests to host node 11.
Described host node 11 also is used to receive the subscription data request, add in the subscription queue, and in cluster synchronous subscription queue.
Concrete, after described host node 11 receives the subscription data requests, check the validity of subscribing to, check promptly whether the subscription data requested data format is correct, if correctly then add in the subscription queue, otherwise return the response of subscribing to failure.
Further, described responsible node 12 also is used to make regular check on subscription queue, judges whether the subscription progress in the subscription data request is consistent with current data, if it is unanimity then do not handle, if inconsistent then current data group bag structure notification message is sent to the node of subscription.
Concrete, because the timestamp of the data that the subscription progress is the node of subscription have been existed, therefore identical when the timestamp of the current data of described responsible node 12 and subscription progress, illustrate that the data in the node of the current data of responsible node 12 and subscription are identical, the node of subscription does not need to upgrade; When subscription progress and current data are inconsistent, the data difference of responsible node 12 is described, the node of subscription needs to upgrade.
Fig. 3 is the method flow schematic diagram of data management in a kind of distributed type assemblies of the present invention, as shown in Figure 3, said method comprising the steps of:
Concrete, it specifically is from number of nodes the data of storage to be carried out subregion according to what move in the current cluster that described data to storage are carried out subregion.Because each data partition behind the subregion all will be responsible for from node by one, so the quantity of subregion should be smaller or equal to the quantity from node.Describedly select one specifically to be according to selecting responsible node as responsible node for each data partition from the running status of node with from node capacity from node.Wherein, describedly comprise from the running status of node with from node capacity: the transmission speed of the network that inserts from node, from the current running status of node self, and from the ability of node processing data.Described host node obtains from the state of node and node capacity and realizes by the regular information synchronization of each node the cluster.Further, in the cluster running, if the responsible node fault, described host node according to reselect from the state of node and node capacity one be responsible for other data partitions from node, he takes over the responsible node of fault.If do not have to be responsible for from node, for example: other from node all had separately responsible data partition or be responsible for when the current state of node and node capacity are not enough to become responsible node, host node carries out subregion and selects responsible node the data of storage again, promptly adjusts all data partitions.
Concrete, described responsible node manages the data partition of self being responsible for and comprises: when the information of the responsible data partition of described responsible node changes, by described responsible node the data that change are sent to other and finish write operation from node; Make regular check on subscription queue, according to the data of effective subscribe request in the data partition of self being responsible for from the node transmission that sends subscribe request.
Further, after step 302, i.e. in the process of responsible node management, when cluster had initiate node, described method also comprised:
Step 303a, initiate node broadcasts sends register requirement;
Concrete, in the register requirement that initiate node sends, carried initiate IP addresses of nodes.
Step 303b, host node judge whether described initiate node is legal after receiving register requirement, if legal then return the registration response, otherwise return failure response, and the end process flow process;
Concrete, whether described host node: judging that the cluster internal segment is counted reaches the upper limit if judging whether described initiate node is legal, comprising, and whether the IP address is in tolerance band, if do not reach the upper limit and IP address in the scope of permission, then initiate node is legal; If reach the upper limit or IP address not in the scope of permission, then initiate node is illegal.
Step 303c, initiate node send register node information to host node after receiving the registration response;
Concrete, receive the registration response after because the IP address of having carried host node in the registration response, therefore initiate node sends register node information to host node and can adopt clean culture to send.Comprise in the described register node information: the ability of described initiate node and node state, i.e. the software and hardware information of this node.
After step 303d, host node receive register node information,, and in cluster, upgrade clustered node tabulation and data partition information synchronously with the information adding clustered node tabulation of initiate node.
Further, after the described step 303d, also comprise the data subscription procedure, specifically comprise:
Step 304a, initiate node sends the subscription data request to host node;
Concrete, comprise in the described subscription data request: the scope of node, subscription progress and the subscription of subscription task sign, subscription.Wherein, described subscription progress is the timestamp of the data that existed of current node.The scope of described subscription, promptly the data content of Ding Yueing can be determined according to data partition.Need to prove, except initiate node can send the subscription data request, receive the more new data that responsible node sends from node after, during the write operation failure, also can send the subscription data requests to host node 11.
Step 304b receives the subscription data request, add in the subscription queue, and in cluster subscription queue synchronously.
Concrete, after described host node receives the subscription data request, check the validity of subscribing to, check promptly whether the subscription data requested data format is correct, if correctly then add in the subscription queue, otherwise return the response of subscribing to failure.
Further, after the described step 304b, comprise that also responsible node upgrades the data of data partition according to subscription queue, specifically comprise: responsible node is made regular check on subscription queue, judge whether the subscription progress in the subscription data request is consistent with current data, if it is unanimity then do not handle, if inconsistent then current data group bag structure notification message is sent to the node of subscription.
Concrete, because the timestamp of the data that the subscription progress is the node of subscription have been existed, therefore identical when the timestamp of the current data of described responsible node and the progress of subscription illustrates that the data in the node of the current data of responsible node and subscription are identical, and the node of subscription does not need renewal; When subscription progress and current data are inconsistent, the data difference of responsible node is described, the node of subscription needs to upgrade.
The above is preferred embodiment of the present invention only, is not to be used to limit protection scope of the present invention, all any modifications of being done within the spirit and principles in the present invention, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the system of data management in the distributed type assemblies is characterized in that described system comprises: host node and responsible node, wherein,
Described host node is used for the data of storage are carried out subregion, for each data partition select one from node as responsible node;
Described responsible node is used for the data partition that described responsible node is responsible for is managed.
2. system according to claim 1 is characterized in that, described responsible node manages the data partition of self being responsible for, and comprising:
When the information of the responsible data partition of described responsible node changes, by described responsible node the data that change are sent to other and finish write operation from node;
Make regular check on subscription queue, according to the data of effective subscribe request in the data partition of self being responsible for from the node transmission that sends subscribe request.
3. system according to claim 1 and 2 is characterized in that, described host node selects one specifically to be according to selecting responsible node from the running status of node with from node capacity from node as responsible node for each data partition.
4. system according to claim 1 and 2 is characterized in that, described system also comprises:
Initiate node is used for the broadcast transmission register requirement, receive registration response after, send register node information to host node, receive host node synchronous clustered node tabulation and data partition information;
Described host node, after also being used to receive register requirement, judge whether described initiate node is legal, if it is legal then return registration response, otherwise return failure response, after receiving register node information,, and in cluster, upgrade clustered node tabulation and data partition information synchronously with the information adding clustered node tabulation of initiate node.
5. system according to claim 4 is characterized in that, the node of described initiate node or write operation failure also is used for sending the subscription data request to host node;
Described host node also is used to receive the subscription data request, add in the subscription queue, and in cluster synchronous subscription queue.
6. system according to claim 5, it is characterized in that described responsible node also is used to make regular check on subscription queue, judge whether the subscription progress in the subscription data request is consistent with current data, if inconsistent then current data group bag structure notification message is sent to the node of subscription.
7. the method for data management in the distributed type assemblies is characterized in that described method comprises:
Host node carries out subregion to the data of storage, for each data partition select one from node as responsible node;
The data partition that responsible node is responsible for described responsible node manages.
8. method according to claim 7 is characterized in that, described responsible node manages the data partition of self being responsible for, and comprising:
When the information of the responsible data partition of described responsible node changes, by described responsible node the data that change are sent to other and finish write operation from node;
Make regular check on subscription queue, according to the data of effective subscribe request in the data partition of self being responsible for from the node transmission that sends subscribe request.
9. according to claim 7 or 8 described methods, it is characterized in that described host node selects one specifically to be according to selecting responsible node from the running status of node with from node capacity from node as responsible node for each data partition.
10. according to claim 7 or 8 described methods, it is characterized in that in the process of responsible node management, described method also comprises:
Initiate node broadcasts sends register requirement; Host node judges whether described initiate node is legal after receiving register requirement, if legal then return the registration response, otherwise return failure response, and the end process flow process; Initiate node sends register node information to host node after receiving the registration response; After host node receives register node information,, and in cluster, upgrade clustered node tabulation and data partition information synchronously with the information adding clustered node tabulation of initiate node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010597613XA CN102025550A (en) | 2010-12-20 | 2010-12-20 | System and method for managing data in distributed cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010597613XA CN102025550A (en) | 2010-12-20 | 2010-12-20 | System and method for managing data in distributed cluster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102025550A true CN102025550A (en) | 2011-04-20 |
Family
ID=43866442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010597613XA Pending CN102025550A (en) | 2010-12-20 | 2010-12-20 | System and method for managing data in distributed cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102025550A (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051591A (en) * | 2011-10-11 | 2013-04-17 | 北京大学 | Method and system for synchronizing identification information of distributed and multi-level application systems |
| WO2013091212A1 (en) * | 2011-12-22 | 2013-06-27 | 华为技术有限公司 | Partition management method, device and system in distributed storage system |
| CN103891244A (en) * | 2012-09-04 | 2014-06-25 | 华为技术有限公司 | Method and device for storing and retrieving data |
| CN104320459A (en) * | 2014-10-24 | 2015-01-28 | 杭州华三通信技术有限公司 | Node management method and device |
| CN104539583A (en) * | 2014-12-05 | 2015-04-22 | 浙江浙大中控信息技术有限公司 | Real-time database subscription system and method |
| CN104813609A (en) * | 2012-09-07 | 2015-07-29 | 威智伦公司 | Physical security system having multiple server nodes |
| CN105306583A (en) * | 2015-11-11 | 2016-02-03 | 广州新科佳都科技有限公司 | Distributed permission management method and system based on atomic broadcast technology |
| CN105338028A (en) * | 2014-07-30 | 2016-02-17 | 浙江宇视科技有限公司 | Method and device for selecting master and slave nodes in distributed server cluster |
| CN105336138A (en) * | 2015-10-28 | 2016-02-17 | 深圳市科陆电子科技股份有限公司 | Method and system for wireless electricity meter to be automatically registered to concentrator |
| CN105357222A (en) * | 2015-11-27 | 2016-02-24 | 国网信息通信产业集团有限公司 | Distributed Session management middleware |
| CN105518659A (en) * | 2014-10-28 | 2016-04-20 | 华为技术有限公司 | Data partition allocation method and apparatus of distributed database |
| CN105512200A (en) * | 2015-11-26 | 2016-04-20 | 华为技术有限公司 | Distributed database processing method and device |
| CN105550309A (en) * | 2015-12-12 | 2016-05-04 | 天津南大通用数据技术股份有限公司 | MPP framework database cluster sequence system and sequence management method |
| CN105933391A (en) * | 2016-04-11 | 2016-09-07 | 青岛海信传媒网络技术有限公司 | Node capacity expansion method, device and system |
| CN106062717A (en) * | 2014-11-06 | 2016-10-26 | 华为技术有限公司 | Distributed storage replication system and method |
| CN103051591B (en) * | 2011-10-11 | 2016-11-30 | 北京大学 | A kind of distributed, synchronous method of multi-layer application system identification information and system |
| CN106227470A (en) * | 2016-08-05 | 2016-12-14 | 浪潮(北京)电子信息产业有限公司 | A kind of SRM method and device |
| CN106375102A (en) * | 2015-07-22 | 2017-02-01 | 华为技术有限公司 | Service registration method, application method and correlation apparatus |
| CN106888245A (en) * | 2016-06-07 | 2017-06-23 | 阿里巴巴集团控股有限公司 | A kind of data processing method, apparatus and system |
| CN107079045A (en) * | 2014-10-14 | 2017-08-18 | 微软技术许可有限责任公司 | Recognized using the node of cluster |
| CN107395587A (en) * | 2017-07-18 | 2017-11-24 | 北京初识科技有限公司 | A kind of data managing method and system based on multipoint cooperative mechanism |
| WO2017214801A1 (en) * | 2016-06-13 | 2017-12-21 | 深圳天珑无线科技有限公司 | Distributed network message processing method and node |
| WO2017214802A1 (en) * | 2016-06-13 | 2017-12-21 | 深圳天珑无线科技有限公司 | Distributed network message processing method and node |
| CN108604202A (en) * | 2016-05-12 | 2018-09-28 | 华为技术有限公司 | The working node of parallel processing system (PPS) is rebuild |
| CN108924206A (en) * | 2018-06-26 | 2018-11-30 | 郑州云海信息技术有限公司 | A kind of cluster event synchronizing method, device and the equipment of distributed system |
| CN109005193A (en) * | 2018-09-03 | 2018-12-14 | 湖北文理学院 | Alarming method for power, device and electric terminal |
| CN109274766A (en) * | 2018-10-30 | 2019-01-25 | 浙江理工大学 | It is a kind of for being knitted the data subscription method and device of interconnection plane |
| CN109639773A (en) * | 2018-11-26 | 2019-04-16 | 中国船舶重工集团公司第七六研究所 | A kind of the distributed data cluster control system and its method of dynamic construction |
| CN109962813A (en) * | 2019-03-22 | 2019-07-02 | 西安电子科技大学 | A kind of network structure generation method for network structure secret protection |
| CN110901691A (en) * | 2018-09-17 | 2020-03-24 | 株洲中车时代电气股份有限公司 | Ferroelectric data synchronization system and method and train network control system |
| CN112311641A (en) * | 2020-12-30 | 2021-02-02 | 深圳市法拉第电驱动有限公司 | CAN communication-based communication method and system for upper computer and lower computer |
| CN112954008A (en) * | 2021-01-26 | 2021-06-11 | 网宿科技股份有限公司 | Distributed task processing method and device, electronic equipment and storage medium |
| CN113132139A (en) * | 2019-12-31 | 2021-07-16 | 国民技术股份有限公司 | Block chain member management method and device, electronic equipment and computer readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252603A (en) * | 2008-04-11 | 2008-08-27 | 清华大学 | Cluster distributed type lock management method based on storage area network SAN |
| US20080313293A1 (en) * | 2001-09-06 | 2008-12-18 | Bea Systems, Inc. | System and method for exactly once message store communication |
| CN101562515A (en) * | 2008-04-15 | 2009-10-21 | 中兴通讯股份有限公司 | Key data synchronizing method for multi-processor |
-
2010
- 2010-12-20 CN CN201010597613XA patent/CN102025550A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080313293A1 (en) * | 2001-09-06 | 2008-12-18 | Bea Systems, Inc. | System and method for exactly once message store communication |
| CN101252603A (en) * | 2008-04-11 | 2008-08-27 | 清华大学 | Cluster distributed type lock management method based on storage area network SAN |
| CN101562515A (en) * | 2008-04-15 | 2009-10-21 | 中兴通讯股份有限公司 | Key data synchronizing method for multi-processor |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051591B (en) * | 2011-10-11 | 2016-11-30 | 北京大学 | A kind of distributed, synchronous method of multi-layer application system identification information and system |
| CN103051591A (en) * | 2011-10-11 | 2013-04-17 | 北京大学 | Method and system for synchronizing identification information of distributed and multi-level application systems |
| CN103299296B (en) * | 2011-12-22 | 2016-03-09 | 华为技术有限公司 | Partition management method, equipment and system in a kind of distributed memory system |
| WO2013091212A1 (en) * | 2011-12-22 | 2013-06-27 | 华为技术有限公司 | Partition management method, device and system in distributed storage system |
| CN103299296A (en) * | 2011-12-22 | 2013-09-11 | 华为技术有限公司 | Partition management method, device and system in distributed storage system |
| CN103891244A (en) * | 2012-09-04 | 2014-06-25 | 华为技术有限公司 | Method and device for storing and retrieving data |
| CN103891244B (en) * | 2012-09-04 | 2016-11-16 | 华为技术有限公司 | A kind of method and device carrying out data storage and search |
| CN104813609A (en) * | 2012-09-07 | 2015-07-29 | 威智伦公司 | Physical security system having multiple server nodes |
| US10454997B2 (en) | 2012-09-07 | 2019-10-22 | Avigilon Corporation | Distributed physical security system |
| CN105338028B (en) * | 2014-07-30 | 2018-12-07 | 浙江宇视科技有限公司 | Main and subordinate node electoral machinery and device in a kind of distributed server cluster |
| CN105338028A (en) * | 2014-07-30 | 2016-02-17 | 浙江宇视科技有限公司 | Method and device for selecting master and slave nodes in distributed server cluster |
| CN107079045A (en) * | 2014-10-14 | 2017-08-18 | 微软技术许可有限责任公司 | Recognized using the node of cluster |
| CN104320459A (en) * | 2014-10-24 | 2015-01-28 | 杭州华三通信技术有限公司 | Node management method and device |
| CN104320459B (en) * | 2014-10-24 | 2018-01-09 | 新华三技术有限公司 | A kind of node administration method and device |
| CN105518659A (en) * | 2014-10-28 | 2016-04-20 | 华为技术有限公司 | Data partition allocation method and apparatus of distributed database |
| WO2016065530A1 (en) * | 2014-10-28 | 2016-05-06 | 华为技术有限公司 | Data partition allocation method and apparatus of distributed database |
| CN105518659B (en) * | 2014-10-28 | 2019-07-26 | 华为技术有限公司 | The data partition allocation method and device of distributed data base |
| US10713134B2 (en) | 2014-11-06 | 2020-07-14 | Huawei Technologies Co., Ltd. | Distributed storage and replication system and method |
| CN106062717A (en) * | 2014-11-06 | 2016-10-26 | 华为技术有限公司 | Distributed storage replication system and method |
| CN104539583A (en) * | 2014-12-05 | 2015-04-22 | 浙江浙大中控信息技术有限公司 | Real-time database subscription system and method |
| CN104539583B (en) * | 2014-12-05 | 2018-01-30 | 浙江浙大中控信息技术有限公司 | A kind of real-time data base ordering system and method |
| CN106375102B (en) * | 2015-07-22 | 2019-08-27 | 华为技术有限公司 | A kind of service registration method, application method and relevant apparatus |
| CN106375102A (en) * | 2015-07-22 | 2017-02-01 | 华为技术有限公司 | Service registration method, application method and correlation apparatus |
| US10979317B2 (en) | 2015-07-22 | 2021-04-13 | Huawei Technologies Co., Ltd. | Service registration method and usage method, and related apparatus |
| CN105336138A (en) * | 2015-10-28 | 2016-02-17 | 深圳市科陆电子科技股份有限公司 | Method and system for wireless electricity meter to be automatically registered to concentrator |
| CN105306583A (en) * | 2015-11-11 | 2016-02-03 | 广州新科佳都科技有限公司 | Distributed permission management method and system based on atomic broadcast technology |
| CN105512200A (en) * | 2015-11-26 | 2016-04-20 | 华为技术有限公司 | Distributed database processing method and device |
| WO2017088358A1 (en) * | 2015-11-26 | 2017-06-01 | 华为技术有限公司 | Distributed database processing method and device |
| US10872101B2 (en) | 2015-11-26 | 2020-12-22 | Huawei Technologies Co., Ltd. | Distributed database processing method and device |
| CN105357222A (en) * | 2015-11-27 | 2016-02-24 | 国网信息通信产业集团有限公司 | Distributed Session management middleware |
| CN105550309A (en) * | 2015-12-12 | 2016-05-04 | 天津南大通用数据技术股份有限公司 | MPP framework database cluster sequence system and sequence management method |
| CN105933391A (en) * | 2016-04-11 | 2016-09-07 | 青岛海信传媒网络技术有限公司 | Node capacity expansion method, device and system |
| CN105933391B (en) * | 2016-04-11 | 2019-06-21 | 聚好看科技股份有限公司 | A kind of node expansion method, apparatus and system |
| CN108604202A (en) * | 2016-05-12 | 2018-09-28 | 华为技术有限公司 | The working node of parallel processing system (PPS) is rebuild |
| CN108604202B (en) * | 2016-05-12 | 2021-01-15 | 华为技术有限公司 | Working node reconstruction for parallel processing system |
| CN106888245A (en) * | 2016-06-07 | 2017-06-23 | 阿里巴巴集团控股有限公司 | A kind of data processing method, apparatus and system |
| WO2017214801A1 (en) * | 2016-06-13 | 2017-12-21 | 深圳天珑无线科技有限公司 | Distributed network message processing method and node |
| WO2017214802A1 (en) * | 2016-06-13 | 2017-12-21 | 深圳天珑无线科技有限公司 | Distributed network message processing method and node |
| CN106227470A (en) * | 2016-08-05 | 2016-12-14 | 浪潮(北京)电子信息产业有限公司 | A kind of SRM method and device |
| CN107395587B (en) * | 2017-07-18 | 2020-01-03 | 北京微星优财网络科技有限公司 | Data management method and system based on multipoint cooperation mechanism |
| CN107395587A (en) * | 2017-07-18 | 2017-11-24 | 北京初识科技有限公司 | A kind of data managing method and system based on multipoint cooperative mechanism |
| CN108924206A (en) * | 2018-06-26 | 2018-11-30 | 郑州云海信息技术有限公司 | A kind of cluster event synchronizing method, device and the equipment of distributed system |
| CN109005193A (en) * | 2018-09-03 | 2018-12-14 | 湖北文理学院 | Alarming method for power, device and electric terminal |
| CN110901691A (en) * | 2018-09-17 | 2020-03-24 | 株洲中车时代电气股份有限公司 | Ferroelectric data synchronization system and method and train network control system |
| CN109274766A (en) * | 2018-10-30 | 2019-01-25 | 浙江理工大学 | It is a kind of for being knitted the data subscription method and device of interconnection plane |
| CN109639773B (en) * | 2018-11-26 | 2021-04-13 | 中国船舶重工集团公司第七一六研究所 | Dynamically constructed distributed data cluster control system and method thereof |
| CN109639773A (en) * | 2018-11-26 | 2019-04-16 | 中国船舶重工集团公司第七六研究所 | A kind of the distributed data cluster control system and its method of dynamic construction |
| CN109962813A (en) * | 2019-03-22 | 2019-07-02 | 西安电子科技大学 | A kind of network structure generation method for network structure secret protection |
| CN113132139A (en) * | 2019-12-31 | 2021-07-16 | 国民技术股份有限公司 | Block chain member management method and device, electronic equipment and computer readable medium |
| CN112311641A (en) * | 2020-12-30 | 2021-02-02 | 深圳市法拉第电驱动有限公司 | CAN communication-based communication method and system for upper computer and lower computer |
| CN112954008A (en) * | 2021-01-26 | 2021-06-11 | 网宿科技股份有限公司 | Distributed task processing method and device, electronic equipment and storage medium |
| CN112954008B (en) * | 2021-01-26 | 2022-11-04 | 网宿科技股份有限公司 | Distributed task processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102025550A (en) | System and method for managing data in distributed cluster | |
| US9495392B2 (en) | System and method for parallel multiplexing between servers in a cluster | |
| CN107066319B (en) | Multi-dimensional scheduling system for heterogeneous resources | |
| US9201742B2 (en) | Method and system of self-managing nodes of a distributed database cluster with a consensus algorithm | |
| US20100306280A1 (en) | Swarm-Based Synchronization Over a Network of Object Stores | |
| CN109379448B (en) | File distributed deployment method and device, electronic equipment and storage medium | |
| CN111770149B (en) | Novel alliance chain system based on distributed storage | |
| CN102402441B (en) | System and method for configuring multiple computers | |
| CN101741907A (en) | Method and system for balancing server load and main server | |
| CN101751415A (en) | Metadata service system metadata synchronized method and writing server updating method | |
| EP3138003A1 (en) | System and method for supporting a bypass-domain model and a proxy model and updating service information for across-domain messaging in a transactional middleware machine environment | |
| CN102333029A (en) | Routing method in server cluster system | |
| CN110830574B (en) | Method for realizing intranet load balance based on docker container | |
| CN110569302A (en) | method and device for physical isolation of distributed cluster based on lucene | |
| WO2022134797A1 (en) | Data fragmentation storage method and apparatus, a computer device, and a storage medium | |
| CN112199427A (en) | Data processing method and system | |
| CN101344882B (en) | Data query method, insertion method and deletion method | |
| KR101956320B1 (en) | System and method for preventing single-point bottleneck in a transactional middleware machine environment | |
| CN106202082A (en) | The method and device of built-up foundation data buffer storage | |
| CN104202386A (en) | High-concurrency distributed file system and secondary load balancing method thereof | |
| JP5945543B2 (en) | System including middleware machine environment | |
| CN112351106B (en) | Service grid platform containing event grid and communication method thereof | |
| CN103401951A (en) | Peer-to-peer architecture based elastic cloud distribution method | |
| CN115866059B (en) | Block chain link point scheduling method and device | |
| CN111258840B (en) | Cluster node management method and device and cluster |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110420 |