CN102215123B - Multi-ring-network-topology-structure-based large-scale trunking system - Google Patents
Multi-ring-network-topology-structure-based large-scale trunking system Download PDFInfo
- Publication number
- CN102215123B CN102215123B CN 201110150538 CN201110150538A CN102215123B CN 102215123 B CN102215123 B CN 102215123B CN 201110150538 CN201110150538 CN 201110150538 CN 201110150538 A CN201110150538 A CN 201110150538A CN 102215123 B CN102215123 B CN 102215123B
- Authority
- CN
- China
- Prior art keywords
- node
- ring
- network
- listing
- computing
- 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
- 239000002243 precursor Substances 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims description 12
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Abstract
The invention discloses a multi-ring-network-topology-structure-based large-scale trunking system. In the multi-ring-network-topology-structure-based large-scale trunking system, computing nodes are divided into a plurality of groups according to online time periods of the nodes, each group has a unique ring identifier, and the computing nodes in each group have a unique node identifier respectively; the computing nodes in each group are connected into a ring topology structure in a way of performing Hash operations on network addresses of the computing nodes in the group, taking key values obtained by the Hash operation as in-group node identifiers and clockwise arranging each computing node from lower node identifiers to greater node identifiers; an entire-ring node list of each ring is saved on a management node; and local-ring node lists are stored on each node in the ring, information about the nodes directly and indirectly adjacent to each node is saved, and each node periodically transmits own state messages to direct precursor nodes and direct successor nodes thereof. The system has higher stability, scalability and manageability.
Description
Technical field
The present invention relates to large-scale cluster system, relate in particular to a kind of large-scale cluster system based on the multi-ring networks topological structure, belong to the interleaving techniques application of information system and computer network.
Background technology
Large-scale cluster system is by being evenly distributed in calculation task on the resource pool that is made of the large-scale calculations node, makes the various application systems can be according to the transparent as required computing capability of obtaining high performance-price ratio, storage resources and information service.The large-scale data processing work such as information retrieval, data mining, business information processing and science calculating can have been carried on the large-scale cluster system platform.
Present group system is all emphasized good manageability, generally tends to adopt Centralized Topology, thereby ensures service quality.Namely use one or several main control server to strengthen quantity set group server and consist of, main control server is responsible for the state of each node of monitoring, carries out failure detection and realizes load balancing etc.
Major defect based on the control and management mechanism of Centralized Topology is exactly that system exists bottleneck problem and Single Point of Faliure, so single-point needs high availability, recovers daily record or dual-host backup etc. such as record, and advantage is that controllability is strong, easy to maintenance flexibly.
As seen, if in large-scale cluster system, adopt the strategy of concentrated controling management, computing node as performer needs initiatively regularly to send information to report the work at present state to management node, prevent the delay that node failure brings, this obviously is infeasible, because the huge computing node of quantity sends cycle information to management node and will bring a large amount of extra network service burdens, and the resources that consume in a large number easily management nodes, cause the effect that is similar to distributed denial of service attack.If adopt distributed controlling and managing mechanism, the heartbeat message quantity of receiving to reduce management node then needs a kind of network topology structure that is fit to efficiently large-scale cluster system to come the normal operation of support system.
Summary of the invention
Technical problem to be solved by this invention is to overcome existing large-scale cluster system because the quantity of node is huge, the defective that Systems balanth, scalability and manageability are difficult to ensure, a kind of large-scale cluster system based on the multi-ring networks topological structure is provided, can realizes the huge computing node of quantity is efficiently managed.
The present invention solves the problems of the technologies described above by the following technical solutions:
A kind of large-scale cluster system based on the multi-ring networks topological structure, described large-scale cluster system comprises management node
And computing node, described computing node is divided into a plurality of groups according to the online time period of node, and each group has a unique ring sign, and the computing node in each group has a unique node identifier; The computing node of each group is connected to a ring topology by the following method: the hash computing is carried out in the computing node network address in this group, the key value that obtains with the hash computing is as group interior nodes identifier, and by node identifier order from small to large each computing node is lined up along clockwise direction, thereby consist of ring topology; Preserve the loopful node listing of each ring on the management node.
Further, all store a local ring node listing on each node in the described ring, preserved with this node directly and the information of the node of indirect neighbor, comprising: the state that encircles identifier, forerunner and relative network distance, forerunner and the descendant node of node identification, forerunner and descendant node and this node of descendant node under the node; Each node regularly sends oneself state message to its direct precursor node and immediate successor node.
Node adds in accordance with the following methods:
When step 1, node adding network, at first send the message that a request adds network to management node, after management node receives that the node request adds message, calculate or verify the sign of node, and return to digital certificate of this node and receiveing the response, comprised the information of direct precursor node and immediate successor node in the ring in receiveing the response;
After step 2, node are received and are receiveed the response, contact with direct precursor node and immediate successor node in receiveing the response, and come the local ring node listing of this node of initialization by the local ring node listing of the direct precursor node in receiveing the response and immediate successor node;
Step 3, the direct precursor node in receiveing the response and immediate successor node are after the node updates solicited message that obtains this node, also upgrade local ring node listing separately, the direct precursor node is notified the local ring node listing of its direct precursor node updates oneself, and the immediate successor node is notified the local ring node listing of its immediate successor node updates oneself.
Node withdraws from accordance with the following methods:
The situation that node initiatively withdraws from:
Withdraw from node and at first send information to management node, require to nullify its log-on message; Then notify his forerunner's node and descendant node, withdraw from this network; When forerunner's node and descendant node know notified after, upgrade respectively in the local ring node listing separately and withdraw from the relevant data of node with this, management node also upgrades the loopful node listing;
The passive situation about withdrawing from of node:
When improper passive the exitting network of node arranged, its direct precursor node and descendant node do not receive the state information that this node should regularly be sent, and then direct precursor node and descendant node are reported improper passive exitting network of this node to management node; Management node is received backward this node photos and sending messages of report, if can not get at the appointed time this node feedack, confirms that then this node exits network, and responds confirmation to direct precursor node and the descendant node of this node; The direct precursor node of this node and descendant node upgrade local ring node listing separately, and management node upgrades the loopful node listing, and network topology is rebuild.
The present invention has following beneficial effect:
(1) system has realized load balancing, and computing node reduces to the amount of information of the online situation of report that management node sends,
Alleviated the load of management node;
(2) system has stronger scalability, namely both can support the small scale network system, also can support large-scale cluster system;
(3) the multi-ring networks topological structure of the present invention's proposition both had been applicable to sparse node failure, also was applicable to continuous nodes and lost efficacy.
Description of drawings
Fig. 1 is the structural representation of a ring topology of large-scale cluster system of the present invention.
Embodiment
Below in conjunction with accompanying drawing technical scheme of the present invention is elaborated:
Large-scale cluster system of the present invention comprises management node and computing node, described large-scale cluster system comprises management node and computing node, described computing node is divided into a plurality of groups according to the online time period of node, each group has a unique ring sign, and the computing node in each group has a unique node identifier; The computing node of each group is connected to a ring topology by the following method: the hash computing is carried out in the computing node network address in this group, the key value that obtains with the hash computing is as group interior nodes identifier, and by node identifier order from small to large each computing node is lined up along clockwise direction, thereby consist of ring topology; Preserve the loopful node listing of each ring on the management node.
System at first creates a unique ring sign for each ring
, the ring sign has indicated the type of ring, and determines it is which ring; In each ring, create unique node identifier in the ring for each node again
Therefore in fact each node identifier is comprised of two parts:
The hash computing is carried out in the network address that ring interior nodes identifier adopts hashing algorithm will be included into the node of specific ring, and the key value that computing obtains based on hash is lined up node in the direction of the clock from small to large, thus consisting of an identifier space is 0 ~
The ring topology of (m is the figure place of node label), namely maximum open ended node numbers are in the ring
Individual.In the interval of regulation, be the node of k for ring interior nodes identifier, clockwise line node is called the descendant node of node k in the ring; Counterclockwise line node is called forerunner's node of k.Obviously for the node in the ring, need to understand as far as possible in real time with it mutually the direct precursor of supervision and the situation of descendant node.
Yet, if node is only understood its current direct precursor and immediate successor node situation, if then when the current direct precursor of node or immediate successor node failure, the direct precursor that node is can not be rapidly new with it or immediate successor node are set up the mutually relation of supervision, particularly in the initial ring continuously during node failure in blocks, this situation will be difficult to solve more.For this reason, the present invention solves this problem at each ring interior nodes deploy local ring node listing.In the large-scale cluster system of the present invention, on management node, preserve the loopful node listing of each ring, all store a local ring node listing on each node in the ring, preserved with this node directly and the information of the node of indirect neighbor, comprising: the state that encircles identifier, forerunner and relative network distance, forerunner and the descendant node of node identification, forerunner and descendant node and this node of descendant node under the node; Nodes is
Ring in, every local link point range table space complexity is
Each list item definition of local ring node listing is as shown in table 1:
Table 1
| Local ring node listing list item | Definition |
| NodeID | Node identifier |
| RingID | Ring identifier under the node |
| Distance | Relative network distance with present node |
| Place | Node relative position (forerunner/follow-up) |
| Status | Node state (available/unavailable/not online) |
List item Distance in the table 1 refers to the relative network distance with present node, direct precursor, descendant node are respectively " 1 " and " 1 " with the relative network distance of this node, and the indirect forerunner of the first cis-position is respectively " 2 " and " 2 " with the relative network distance of descendant node (being the direct precursor node of direct precursor node or the immediate successor node of immediate successor node) and this node.
If the node label figure place gets 4, then the ring in comprised 16 nodes, so the local link point lists on the node 4 list items.System presents state shown in Figure 1 after operation after a while.Node 4 is as example in the ring, and its direct precursor node points to node 2, and descendant node points to node 6; In addition, the direct precursor node of node 2 and the immediate successor node of node 6 have also been comprised in the local ring node listing of node 4, purpose is to guarantee when the direct precursor of node 4 or descendant node inefficacy, can make things convenient for it rapidly and node 1 or node 10 contact, and upgrade rapidly the local ring node listing.
When a node joins corresponding ring, then need to guide by management node, and the local ring node listing that is about to adjacent node is upgraded.Node adds to be needed through three processes: node adds admission process, local ring node listing initialization procedure, upgrades other node local ring node listing process.Node 3 in Fig. 1 is as example, and concrete steps are as follows:
Step is when 1. node 3 adds network, at first send the message that a request adds network to management node, after management node receives that the node request adds message, calculate or verify the sign of node, and return to digital certificate of node and receiveing the response, comprised the information of direct precursor node (node 2) and immediate successor node (node 4) in the ring in receiveing the response;
Step 3. node 2,4 is also upgraded local ring node listing separately after the node updates solicited message that obtains node 3, and the local ring node listing of notifying respectively node 1 and node 6 to upgrade separately;
Step 4. node 3 regularly sends mutually state information with node 2,4 respectively, to allow the other side know own presence.
And when node exits network, being divided into two kinds of situations: the 1st kind of situation is that the normal active of this node exits network; Another kind of situation is improper passive the exitting network of node.If when node initiatively withdraws from the place ring, at first send information to management node, require to nullify its log-on message, then notify his forerunner's node and descendant node, withdraw from this network.When forerunner's node and descendant node know notified after, can upgrade respectively in the local ring node listing separately with the relevant data of this node, management node also can upgrade the loopful node listing.And when node because some are special, during passive withdrawing from, then need its front descendant node initiatively to upgrade the local ring node listing of self such as network disconnection or mechanical disorder, to keep the stable of ring, concrete steps are as follows:
Step is established node 3 improper passive exitting network 1. as shown in Figure 1, and its direct precursor node (node 2) and descendant node (node 4) will not receive the information that node 3 should regularly be sent;
Step 3. management node is received backward node 3 photos and sending messages of report, if can not get at the appointed time node 3 feedacks, confirms that then node 3 has exitted network, then responds confirmation to node 2 and node 4;
Step is node 2 and node 4 renewals local ring node listing separately 4., and management node upgrades the loopful node listing, and network topology is rebuild.
When the continuous nodes inefficacy occurs when, the system management node will receive incomplete failure node report (namely reporting from 1 part of inefficacy of forerunner or descendant node), this moment, server normally sent the node of reporting with inquiry, if it lost efficacy, and the single report that receives before processing again.As shown in Figure 1, suppose that node 0,1,2 lost efficacy simultaneously, this moment, management node can receive node 15 about the report about the inefficacy of node 2 of the inefficacy report of node 0 and node 4.Because management node does not receive the descendant node 1 of node 0 about the inefficacy report of node 0, server meeting inquiry node 1 learns that node 1 had lost efficacy, and then the report of processing node 15 transmissions, determines that node 0 lost efficacy.Can confirm also that in like manner node 2 also lost efficacy.
Claims (2)
1. large-scale cluster system based on the multi-ring networks topological structure, described large-scale cluster system comprises management node and computing node, it is characterized in that, described computing node is divided into a plurality of groups according to the online time period of node, each group has a unique ring sign, and the computing node in each group has a unique node identifier; The computing node of each group is connected to a ring topology by the following method: the hash computing is carried out in the computing node network address in this group, the key value that obtains with the hash computing is as group interior nodes identifier, and by node identifier order from small to large each computing node is lined up along clockwise direction, thereby consist of ring topology; Preserve the loopful node listing of each ring on the management node; All store a local ring node listing on each node in the described ring, preserved with this node directly and the information of the node of indirect neighbor, comprising: the state that encircles identifier, forerunner and relative network distance, forerunner and the descendant node of node identification, forerunner and descendant node and this node of descendant node under the node; Each node regularly sends oneself state message to its direct precursor node and immediate successor node; Node adds in accordance with the following methods:
When step 1, node adding network, at first send the message that a request adds network to management node, after management node receives that the node request adds message, calculate or verify the sign of node, it is the described group interior nodes identifier that obtains with the hash computing, and return to digital certificate of this node and receiveing the response, comprised the information of direct precursor node and immediate successor node in the ring in receiveing the response;
After step 2, node are received and are receiveed the response, contact with direct precursor node and immediate successor node in receiveing the response, and come the local ring node listing of this node of initialization by the local ring node listing of the direct precursor node in receiveing the response and immediate successor node;
Step 3, the direct precursor node in receiveing the response and immediate successor node are after the node updates solicited message that obtains this node, also upgrade local ring node listing separately, the direct precursor node is notified the local ring node listing of its direct precursor node updates oneself, and the immediate successor node is notified the local ring node listing of its immediate successor node updates oneself.
2. as claimed in claim 1 based on the large-scale cluster system of multi-ring networks topological structure, it is characterized in that node withdraws from accordance with the following methods:
The situation that node initiatively withdraws from:
Withdraw from node and at first send information to management node, require to nullify its log-on message; Then notify his forerunner's node and descendant node, withdraw from this network; When forerunner's node and descendant node know notified after, upgrade respectively in the local ring node listing separately and withdraw from the relevant data of node with this, management node also upgrades the loopful node listing;
The passive situation about withdrawing from of node:
When improper passive the exitting network of node arranged, its direct precursor node and descendant node do not receive the state information that this node should regularly be sent, and then direct precursor node and descendant node are reported improper passive exitting network of this node to management node; Management node is received backward this node photos and sending messages of report, if can not get at the appointed time this node feedack, confirms that then this node exits network, and responds confirmation to direct precursor node and the descendant node of this node; The direct precursor node of this node and descendant node upgrade local ring node listing separately, and management node upgrades the loopful node listing, and network topology is rebuild.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110150538 CN102215123B (en) | 2011-06-07 | 2011-06-07 | Multi-ring-network-topology-structure-based large-scale trunking system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110150538 CN102215123B (en) | 2011-06-07 | 2011-06-07 | Multi-ring-network-topology-structure-based large-scale trunking system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102215123A CN102215123A (en) | 2011-10-12 |
| CN102215123B true CN102215123B (en) | 2013-10-30 |
Family
ID=44746262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110150538 Active CN102215123B (en) | 2011-06-07 | 2011-06-07 | Multi-ring-network-topology-structure-based large-scale trunking system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102215123B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020290B (en) * | 2012-05-07 | 2015-09-16 | 山东电力集团公司青岛供电公司 | Electric network information method of calibration and system |
| CN102904752B (en) * | 2012-09-25 | 2016-06-29 | 新浪网技术(中国)有限公司 | A kind of node electoral machinery, node device and system |
| CN104182277A (en) * | 2013-05-21 | 2014-12-03 | 北大方正集团有限公司 | Distributed system and distributed method based on multitask system |
| CN104811325B (en) * | 2014-01-24 | 2018-12-25 | 华为技术有限公司 | A kind of clustered node controller monitoring method, relevant apparatus and controller |
| US9313663B2 (en) * | 2014-08-21 | 2016-04-12 | Futurewei Technologies, Inc. | Automatic division of internet protocol radio access networks to interior gateway protocol areas |
| CN105450492A (en) * | 2014-08-22 | 2016-03-30 | ***股份有限公司 | Adaptive ring network structure and method for establishing same |
| CN104301434B (en) * | 2014-10-31 | 2018-06-15 | 浪潮(北京)电子信息产业有限公司 | A kind of high-speed communication framework and method based on cluster |
| CN104506357B (en) * | 2014-12-22 | 2018-05-11 | 国云科技股份有限公司 | A kind of high-availability cluster node administration method |
| CN106936900B (en) * | 2017-02-27 | 2019-11-12 | 杭州数梦工场科技有限公司 | Clustered node statistical method and device |
| CN107995309A (en) * | 2017-12-18 | 2018-05-04 | 苏州蜗牛数字科技股份有限公司 | A kind of coordination approach and system of distributed data node |
| CN108347350B (en) * | 2018-01-25 | 2022-04-15 | ***股份有限公司 | Communication method and device |
| WO2020136874A1 (en) * | 2018-12-28 | 2020-07-02 | 三菱電機株式会社 | Monitoring device, network system, topology management device and monitoring program |
| CN110417586B (en) * | 2019-07-18 | 2022-04-08 | 新华三大数据技术有限公司 | Service monitoring method, service node, server and computer readable storage medium |
| CN110535706B (en) * | 2019-09-02 | 2022-03-01 | 成都吉胜科技有限责任公司 | Automatic cooperative scheduling method based on local area network |
| CN114641020B (en) * | 2020-12-15 | 2023-08-01 | 中国联合网络通信集团有限公司 | Early warning method, device and equipment applied to wireless access network IP network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100384179C (en) * | 2004-04-30 | 2008-04-23 | 华为技术有限公司 | A method of ring selection in resilient packet ring (RPR) network |
| CN101110752B (en) * | 2006-07-18 | 2011-07-20 | 华为技术有限公司 | Method and device for sensing neighbor connectivity on elastic packet ring |
| CN100450063C (en) * | 2007-02-02 | 2009-01-07 | 中国矿业大学 | Multi-ring interconnect transmission method of resilient packet ring based on loop identifier router |
-
2011
- 2011-06-07 CN CN 201110150538 patent/CN102215123B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN102215123A (en) | 2011-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102215123B (en) | Multi-ring-network-topology-structure-based large-scale trunking system | |
| CN102291416B (en) | A kind of method and system of client and server bi-directional synchronization | |
| CN101626563B (en) | Data storage system in communication network and information processing method | |
| CN101924650B (en) | Method for implementing services and intelligent server autonomy of failure information system | |
| CN102209041B (en) | Scheduling method, device and system | |
| CN106817408B (en) | Distributed server cluster scheduling method and device | |
| CN110611603B (en) | Cluster network card monitoring method and device | |
| CN104506357A (en) | High-usability cluster node management method | |
| CN104320495A (en) | Massive data storage method and system of power utilization information collecting system | |
| CN103036719A (en) | Cross-regional service disaster method and device based on main cluster servers | |
| CN111858033A (en) | Load balancing method based on cluster and multiple processes | |
| KR20100060304A (en) | Distributed content delivery system based on network awareness and method thereof | |
| CN104380289A (en) | Service-aware distributed hash table routing | |
| CN117061512A (en) | Distributed information management method and system based on big data | |
| CN110213359B (en) | Internet of vehicles networking data pushing system and method based on D2D | |
| CN103401951B (en) | Based on the elastic cloud distribution method of peer-to-peer architecture | |
| CN103944784A (en) | Large-scale-cloud-data-center-oriented server cooperative monitoring method | |
| CN104394209A (en) | Real-time database data transmission method applied to distributive energy management | |
| CN102118274A (en) | State monitoring method, device and system | |
| CN105025071A (en) | Oil-gas pipeline cloud processing system and implementation method | |
| CN102480524B (en) | Web page crawler cooperating method | |
| CN104052723A (en) | Information processing method and server | |
| CN114172792B (en) | Method and device for realizing sequence number generation method for ensuring high availability of service | |
| CN106210624A (en) | A kind of method of electrically-based industry multi-stage cascade Streaming Media intelligent scheduling | |
| CN103246497B (en) | A kind of real time data method for parallel processing based on Data Placement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: NANJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS Free format text: FORMER OWNER: NANJING POST + TELECOMMUNICATION UNIV. Effective date: 20150820 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20150820 Address after: 210003 Nanjing City, Jiangsu Province, the new model road No. 66 Patentee after: Nanjing University of Posts and Telecommunications Asset Management Co.,Ltd. Address before: 210003 Nanjing City, Jiangsu Province, the new model road No. 66 Patentee before: NANJING University OF POSTS AND TELECOMMUNICATIONS |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20151109 Address after: 224005, Jiangsu, Yancheng City New South District, Xindu street, wisdom Valley Science and technology innovation building, South 15 Patentee after: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Address before: 210003 Nanjing City, Jiangsu Province, the new model road No. 66 Patentee before: Nanjing University of Posts and Telecommunications Asset Management Co.,Ltd. |
|
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20111012 Assignee: Yanmi Technology (Yancheng) Co.,Ltd. Assignor: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Contract record no.: X2023980047098 Denomination of invention: Large scale cluster system based on multi ring network topology Granted publication date: 20131030 License type: Common License Record date: 20231115 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20111012 Assignee: Jiangsu Yanan Information Technology Co.,Ltd. Assignor: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Contract record no.: X2023980049133 Denomination of invention: Large scale cluster system based on multi ring network topology Granted publication date: 20131030 License type: Common License Record date: 20231203 Application publication date: 20111012 Assignee: Yancheng Nongfu Technology Co.,Ltd. Assignor: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Contract record no.: X2023980049126 Denomination of invention: Large scale cluster system based on multi ring network topology Granted publication date: 20131030 License type: Common License Record date: 20231203 |
|
| EE01 | Entry into force of recordation of patent licensing contract |