CN104579975B - A kind of dispatching method of software defined network controller cluster - Google Patents
A kind of dispatching method of software defined network controller cluster Download PDFInfo
- Publication number
- CN104579975B CN104579975B CN201510073823.1A CN201510073823A CN104579975B CN 104579975 B CN104579975 B CN 104579975B CN 201510073823 A CN201510073823 A CN 201510073823A CN 104579975 B CN104579975 B CN 104579975B
- Authority
- CN
- China
- Prior art keywords
- controller node
- controller
- interchanger
- data
- hash tables
- 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
Landscapes
- Computer And Data Communications (AREA)
Abstract
The present invention relates to a kind of dispatching method of software defined network controller cluster, employ the scheme of controller cluster, load pressure can be shared to each controller node, avoid and all load pressures are concentrated to the problem of causing process performance relatively low to single controller node.Each controller node corresponding configuration portion Hash tables in cluster, each controller node only allows to change in the Hash tables that it possesses is responsible for the mark and its load factor of the interchanger of adapter by it, when each controller node have modified the data in the Hash tables that it possesses, the data syn-chronization that need to be changed accordingly updates the data in the Hash tables each possessed into other controller nodes, by other controller nodes;The present invention can determine that corresponding controller node takes over to interchanger according to the data in Hash tables, without introducing third party manager, whole cluster will not be caused to be limited to the performance of third party manager.
Description
Technical field
The present invention relates to network technique field, and in particular to a kind of dispatching method of software defined network controller cluster.
Background technology
At present, the scheduling scheme of software defined network (Software Defined Network, SDN) controller substantially wraps
Two kinds are included, a kind of is the scheduling scheme based on two-node cluster hot backup, and its framework by master controller node as shown in figure 1, usually be responsible for connecing
All interchangers are managed, when machine occurs delaying in master controller node, all interchangers are taken over by preparation controller node;Its shortcoming
It is that load pressure is all concentrated on single controller node, process performance is relatively low.
Another kind is the scheduling scheme that device cluster is controlled by third party manager, and its framework is as shown in Fig. 2 in institute
There is one third party manager of addition outside controller node, be responsible for dispatching all controller nodes in cluster;It is all
Controller node be all by the third party manager distribute interchanger taking over tasks;If controller node is delayed
Machine, third party manager will reschedule interchanger taking over tasks;Its shortcoming is if the machine of delaying, meeting shadow occurs in third party manager
The operation of overall network system is rung, simultaneously as the number of nodes upper limit of controller cluster is adjusted by the program of third party manager
Spend performance impact so that the performance of third party manager can be integrally formed the bottleneck of cluster.
The content of the invention
Scheduling scheme process performance of the invention for software defined network controller in the prior art is relatively low or is limited to
The technical problems such as the performance of third party manager, propose a kind of tune of the software defined network controller cluster with higher performance
Degree method.
A kind of dispatching method of software defined network controller cluster proposed by the present invention, the software defined network control
Device cluster includes some controller nodes;Each controller node accordingly possesses a Hash tables, the packet of every part of Hash table
Include:The identifying of each controller node, each controller node are responsible for the identifying of the interchanger of adapter, each controller node
Load factor;Wherein, each controller node only allows to change in the Hash tables that it possesses is responsible for the interchanger of adapter by it
Mark and its load factor;When each controller node have modified the data in the Hash tables that it possesses, it need to be changed
Data syn-chronization accordingly updates the data in the Hash tables each possessed into other controller nodes, by other controller nodes;
The dispatching method includes controller node electoral machinery, and the controller node electoral machinery includes:
This controller node obtains the mark for the interchanger for needing to elect adapter;
Data in the Hash tables possessed according to this controller node, judge whether to hand over corresponding to the mark that adapter is got
Change planes.
Preferably, the data in the Hash tables possessed according to this controller node, judge whether that adapter gets
Include corresponding to mark the step of interchanger:
Data in the Hash tables possessed according to this controller node, whether judge interchanger corresponding to the mark that gets
Taken over by other controller nodes;
If so, then this controller node is abandoned taking over;If it is not, the interchanger quantity then taken over according to this controller node is sentenced
It is disconnected whether to take over.
Preferably, the step of interchanger quantity taken over according to this controller node judges whether adapter includes:
Data in the Hash tables possessed according to this controller node, judge the interchanger quantity of this controller node adapter
It is whether minimum;If so, then according to whether having the interchanger quantity that other controller nodes are taken over and the adapter of this controller node
Interchanger quantity is equal to be judged whether to take over.
Preferably, it is described according to whether interchanger quantity and this controller node for having other controller nodes to take over are taken over
Interchanger quantity it is equal judge whether adapter the step of include:
Data in the Hash tables possessed according to this controller node, determine whether the friendship of other controller nodes adapter
Quantity of changing planes is equal with the interchanger quantity that this controller node is taken over;
If it is not, then this controller node takes over;If so, then judged whether according to the identification number of this controller node
Adapter.
Preferably, the identification number according to this controller node judges whether that the step of adapter includes:
Data in the Hash tables possessed according to this controller node, judge the identification number of this controller node all
It is whether minimum in the identification number of adapter interchanger quantity controller node equal thereto;
If so, then the adapter of this controller node takes over.
Preferably, this controller node also includes after being taken over to interchanger corresponding to the mark that gets:
This controller node is changed in the Hash tables that it possesses is responsible for the mark of the interchanger of adapter and its load by it
The factor, and the data syn-chronization changed is into other controller nodes;By other controller nodes, accordingly renewal each possesses
Hash tables in data.
Preferably, this controller node especially by the data syn-chronization that TCP is changed into other controller nodes.
Preferably, this controller node sends the packet for asking to take over to interchanger by openflow agreements, with reality
Now to the adapter of interchanger corresponding to the mark that gets.
Preferably, the dispatching method also includes synchrodata restorative procedure, and the synchrodata restorative procedure includes:
Inquire about and whether there is abnormal data in the Hash tables that this controller node possesses, if so, then to this controller node
Data in the Hash tables possessed are repaired, while corresponding data in the Hash tables possessed other controller nodes
Synchronize reparation.
Preferably, the dispatching method also includes load-balancing method, and the load-balancing method includes:
Data in the Hash tables possessed according to this controller node judge whether this controller node is idle in load
State, if so, the then interchanger of the busy controller node of active takeover load.
Beneficial effect:The dispatching method of software defined network controller cluster proposed by the present invention, it is using control
The scheme of device cluster, load pressure can be shared to the scheduling for each controller node, avoiding prior art two-node cluster hot backup
All load pressures are concentrated to the problem of causing process performance relatively low to single controller node in scheme;
Meanwhile each controller node corresponding configuration portion Hash tables in cluster of the invention, and limit each control
Device node only allows to change in the Hash tables that it possesses is responsible for the mark and its load factor of the interchanger of adapter by it, each
When controller node have modified the data in the Hash tables that it possesses, the data syn-chronization that need to be changed to other controller nodes
In, accordingly update the data in the Hash tables each possessed by other controller nodes;Therefore, the present invention can be according to Hash tables
In data determine that corresponding controller node takes over to interchanger, without introducing third party manager, so not
Whole cluster can be caused to be limited to the performance of third party manager.
Based on the Hash tables, the present invention can realize the redundancy and load balancing between each controller node, significantly
Improve the performance and efficiency of whole cluster.
Brief description of the drawings
Fig. 1 is the configuration diagram of two-node cluster hot backup in the prior art.
Fig. 2 is the configuration diagram for being controlled device cluster by third party manager in the prior art.
Fig. 3 is a kind of framework signal of the dispatching method embodiment of software defined network controller cluster proposed by the present invention
Figure.
Fig. 4 be a kind of software defined network controller cluster proposed by the present invention dispatching method embodiment in controller section
The overall flow figure of point electoral machinery.
Embodiment
For the ease of it will be appreciated by those skilled in the art that being carried out below in conjunction with accompanying drawing and embodiment to the present invention further
Description.
The dispatching method embodiment of a kind of software defined network controller cluster proposed by the present invention, referring to Fig. 3, described
Software defined network controller cluster includes some controller nodes (controller node is at least more than 2);Each controller
Node accordingly possesses a Hash tables, and the data of every part of Hash table include:The identifying of each controller node, each controller section
Point is responsible for the identifying of interchanger of adapter, the load factor of each controller node;Wherein, each controller node only allows to repair
Change in the Hash tables that it possesses and the mark and its load factor of the interchanger of adapter are responsible for by it;Each controller node modification
During data in its Hash table possessed, the data syn-chronization that need to be changed is into other controller nodes, by other controls
Device node accordingly updates the data in the Hash tables each possessed.
The form of Hash tables in the present embodiment is as shown in table 1:
Table 1
The identification number of controller node | The mark of current adapter interchanger | Load factor |
NodeId 1 | swId1 | 1 |
NodeId 2 | SwId4、swId5、swId6 | 3 |
NodeId 3 | swId7、swId8 | 2 |
NodeId 4 | Empty | 0 |
... | ... | ... |
In table 1, NodeId 1 to NodeId 4 is the identification number of each controller node, and swId1 is identification number
The mark for the interchanger currently taken over for NodeId 1 controller node;Simultaneously it can be seen that in table 1, identification number is
The load factor (namely weight, be represented by weight) of NodeId 1 controller node is 1.
In the present embodiment, the form of the preferred adoption rate of load factor, in order to load balancing computing.For example, from table 1
As can be seen that current only 1 interchanger (swId1) of adapter of controller node that identification number is NodeId 1, its load factor
For 1;Controller node 3 interchangers (SwId4, swId5, swId6) of current adapter that identification number is NodeId 2, it is loaded
The factor is 3;Current 2 interchangers (swId7, swId8) of adapter of controller node that identification number is NodeId 3, its load because
Son is 2;The load factor of this three is 1:3:2.Meanwhile in order that the performance of whole cluster is preferable, the value of load factor is preferred
Control is within 1 to 10.
Other symbols being related in table 1 can carry out mutually should be understood that according to above-mentioned explanation.
Hash tables in the present embodiment can realize controller node election, synchrodata reparation and load in the cluster
The schemes such as equilibrium.The present embodiment introduces the scheme of controller node election.
Specifically, the dispatching method of software defined network controller cluster includes controller node election side in the present embodiment
Method, the controller node electoral machinery integrally include step S100 and step S200:
S100, this controller node obtain the mark for the interchanger for needing to elect adapter;
Data in S200, the Hash tables possessed according to this controller node, judge whether the mark pair that adapter is got
The interchanger answered.
In the present embodiment, the controller node electoral machinery is mainly used in two kinds of situations:First, when there is new exchange
When machine is connected to this cluster, each controller node in this cluster can receive response, receive each controller section of response
Point can all run the controller node selection algorithm;Second, when have controller node delay machine when, its take over interchanger need
Taken over by election by other normal controller nodes, other normal controller nodes are selected based on the controller node
Algorithm determines whether to take over.
Controller node electoral machinery in the present embodiment is based primarily upon the number in the Hash tables of each controller node configuration
According to realizing, each controller node can realize the synchronized update of Hash table data by TCP, meanwhile, each controller
Node can send the packet of request adapter to interchanger by openflow agreements, corresponding to the mark got to realize
Interchanger adapter.
In order to which the purpose of the present embodiment is better achieved, further optimization is done to the controller node electoral machinery below
And it is discussed in detail.
In the present embodiment, step S200 specifically includes step S210 and step S220:
Data in S210, the Hash tables possessed according to this controller node, exchange corresponding to the mark for judging to get
Whether machine has been taken over by other controller nodes;
S220, if so, then this controller node is abandoned taking over;If it is not, the interchanger then taken over according to this controller node
Quantity judges whether to take over.
The Hash tables are by taking table 1 as an example, if the mark that step S100 is got is appointing in swId1 to swId8 in table 1
One, then illustrate that interchanger corresponding to the mark is taken over by controller node.For example, it is assumed that the mark got here is
" swId8 ", the identification number of this controller node is that " NodeId 2 ", by tabling look-up, this controller node knowable to 1 connects
Pipe is identified as the interchanger of " swId8 ", and the interchanger for being identified as " swId8 " is just identified serial number " NodeId 3 " controller
Taken over, therefore this controller node is abandoned taking over;If the mark that step S100 is got is " swId9 ", can by tabling look-up
Know, the interchanger for being identified as " swId9 " is not taken over by any controller node, and therefore, this controller node can be according to itself
The interchanger quantity currently taken over judges whether to take over.
It was found from shown in table 1, the interchanger number for the controller node adapter that identification number is NodeId 1 to NodeId 4
Amount is respectively 1,3,2 and 0.
In the present embodiment, in order to prevent interchanger from losing, the feelings only taken over by other controller nodes in interchanger
Under condition, this controller node can just abandon the adapter to the interchanger, otherwise can perform electoral machinery always, until the interchanger
Taken over;But in the case where judging that interchanger is not taken over by other controller nodes, this controller node may not necessarily directly connect
Pipe.Preferably, this controller node can combine self-condition, judge whether itself is currently to best suit the controller taken over
Node, accordingly to determine whether to take over.Therefore, the present embodiment is further optimized on the basis of step S220.
Specifically, the interchanger quantity taken in step S220 according to this controller node judges whether that the step of adapter has
Body includes step S230:
Data in S230, the Hash tables possessed according to this controller node, judge the exchange of this controller node adapter
Whether machine quantity is minimum;If so, then according to whether having the interchanger quantity that other controller nodes are taken over and this controller node
The interchanger quantity of adapter is equal to be judged whether to take over.
Meanwhile step S230 can also further optimize, specifically, according to whether there is other controller nodes in step S230
The interchanger quantity of adapter is equal with the interchanger quantity that this controller node is taken over to be judged whether to include step the step of adapter
S240 and step S250:
Data in S240, the Hash tables possessed according to this controller node, determine whether that other controller nodes connect
The interchanger quantity of pipe is equal with the interchanger quantity that this controller node is taken over;
S250, if it is not, then this controller node takes over;If so, then sentenced according to the identification number of this controller node
It is disconnected whether to take over.
Above-mentioned steps S230 to step S250 main function are to avoid adapter order occur between each controller node
Chaotic (for example, there are multiple controller nodes while take over or do not take over the situation of some interchanger), and what is set out connects
Pipe rule, to improve the standardized management to controller node.
In the present embodiment, in step S250 according to the identification number of this controller node judge whether adapter the step of it is specific
Including step S260 and step S270:
Data in S260, the Hash tables possessed according to this controller node, judge the identification number of this controller node
It is whether minimum in the identification number of all adapter interchanger quantity controller node equal thereto;
S270, if so, then this controller node adapter take over.
Step S260 to step S270 is primarily to do further standardized management to controller node, i.e., first using mark
Know the less controller node of sequence number, reuse the larger controller node of identification number, facilitate user to controller node
Using and management.Certainly, obviously can also be other modes in the present embodiment, for example, first using the larger control of identification number
Device node, reuse the less controller node of identification number.
In the present embodiment, this controller node also includes step after being taken over to interchanger corresponding to the mark that gets
S300:
S300, this controller node change in the Hash tables that it possesses by its be responsible for adapter interchanger mark and its
Load factor, and the data syn-chronization changed is into other controller nodes;By other controller nodes, accordingly renewal is respective
Data in the Hash tables possessed.
Overall flow after above step S100 to step S300 is integrated refers to Fig. 4.
In the preferred scheme of the present embodiment, in addition to the controller node electoral machinery, what the present embodiment proposed
A kind of dispatching method of software defined network controller cluster also includes synchrodata restorative procedure, the synchrodata reparation side
Method includes:
Inquire about and whether there is abnormal data in the Hash tables that this controller node possesses, if so, then to this controller node
Data in the Hash tables possessed are repaired, while corresponding data in the Hash tables possessed other controller nodes
Synchronize reparation.
In the present embodiment, each controller node can be currently connected to this cluster by openflow agreement queries
In all interchangers mark.By traveling through local (this controller node) Hash tables, one interchanger of inquiry is by how many
Controller node is taken over, and if the adapter of only controller node, illustrate to be in normal condition to interchanger;If not yet
There is controller node to take over the interchanger, this controller node will take over the interchanger by openflow agreements in time, and lead to
Know and give other controller nodes.If two or more controller nodes have taken over the interchanger, illustrate wherein one
The data of individual or multiple controller nodes exist abnormal;If this controller node is included in, this controller node needs
Query Information is sent by openflow agreements, repair or update the data of Hash tables on this controller node in time, simultaneously
Corresponding data synchronize reparation or renewal in the Hash tables that other controller nodes are possessed.
In the further preferred scheme of the present embodiment, except the controller node electoral machinery, synchrodata reparation
Outside method, a kind of dispatching method for software defined network controller cluster that the present embodiment proposes also includes synchrodata reparation
Method also includes load-balancing method, and the load-balancing method includes:
Data in the Hash tables possessed according to this controller node judge whether this controller node is idle in load
State, if so, the interchanger that then needs of the busy controller node of active takeover load are abandoned, until this controller node reaches
To load saturation state.
In the present embodiment, each controller node can regularly whether itself be in load idle condition, if in load
Idle condition, then continue calculating and also need to take over how many individual interchangers to can be only achieved load saturation state, then go to calculate it again
Whether he is in load busy state by controller node, if other controller nodes are in, load is busy, and it needs to abandon one
Individual or multiple switch makes itself to be within load saturation state, and (load idle condition) this controller node can actively connect
(this controller node first takes over the interchanger to the interchanger that the busy controller node needs of pipe load are abandoned, and reinforms former control
Device node processed abandons the adapter to the interchanger), until load saturation state.Here adapter work can not update this control
Data in the Hash tables that device node possesses, the work updated the data can be completed in synchrodata restorative procedure.
In summary, the dispatching method for a kind of software defined network controller cluster that the present embodiment proposes, due to using
Be controller cluster scheme, load pressure can be shared to each controller node, avoid prior art dual-locomotive heat
All load pressures are concentrated to the problem of causing process performance relatively low to single controller node in standby scheduling scheme.This implementation
Each controller node corresponding configuration portion Hash tables in the cluster of example, and limit each controller node and only allow to change it
The mark and its load factor of the interchanger of adapter are responsible for by it in the Hash tables possessed, each controller node have modified it
During data in the Hash tables possessed, the data syn-chronization that need to be changed is into other controller nodes, by other controller sections
Point accordingly updates the data in the Hash tables each possessed;Therefore, the present embodiment can determine phase according to the data in Hash tables
The controller node answered takes over to interchanger, without introducing third party manager, so whole cluster will not be caused
The performance of third party manager is limited to, thus greatly improves the efficiency and performance of overall cluster.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of dispatching method of software defined network controller cluster, the software defined network controller cluster includes some
Controller node;Characterized in that, each controller node accordingly possesses a Hash tables, the data of every part of Hash table include:
The identifying of each controller node, each controller node be responsible for the identifying of the interchanger of adapter, each controller node it is negative
Carry the factor;Wherein, each controller node only allows to change in the Hash tables that it possesses is responsible for the mark of the interchanger of adapter by it
Knowledge and its load factor;When each controller node have modified the data in the Hash tables that it possesses, the number that need to be changed
According to being synchronized in other controller nodes, the data in the Hash tables each possessed are accordingly updated by other controller nodes;
The dispatching method includes controller node electoral machinery, and the controller node electoral machinery includes:
This controller node obtains the mark for the interchanger for needing to elect adapter;
Data in the Hash tables possessed according to this controller node, judge whether to exchange corresponding to the mark that adapter is got
Machine.
2. the dispatching method of software defined network controller cluster according to claim 1, it is characterised in that the basis
Data in the Hash tables that this controller node possesses, judge whether to wrap the step of taking over interchanger corresponding to the mark got
Include:
Data in the Hash tables possessed according to this controller node, judge interchanger corresponding to the mark that gets whether by
Other controller nodes are taken over;
If so, then this controller node is abandoned taking over;If it is not, the interchanger quantity judgement then taken over according to this controller node is
No adapter.
3. the dispatching method of software defined network controller cluster according to claim 2, it is characterised in that the basis
The step of interchanger quantity of this controller node adapter judges whether adapter includes:
Data in the Hash tables possessed according to this controller node, judge this controller node adapter interchanger quantity whether
It is minimum;If so, then according to whether the interchanger quantity for having other controller nodes to take over exchanges with what this controller node was taken over
Machine quantity is equal to be judged whether to take over.
4. the dispatching method of software defined network controller cluster according to claim 3, it is characterised in that the basis
Whether have other controller nodes take over interchanger quantity it is equal with the interchanger quantity that this controller node is taken over judge be
The step of no adapter, includes:
Data in the Hash tables possessed according to this controller node, determine whether the interchanger of other controller nodes adapter
Quantity is equal with the interchanger quantity that this controller node is taken over;
If it is not, then this controller node takes over;If so, then judge whether to connect according to the identification number of this controller node
Pipe.
5. the dispatching method of software defined network controller cluster according to claim 4, it is characterised in that the basis
The identification number of this controller node judges whether that the step of adapter includes:
Data in the Hash tables possessed according to this controller node, judge the identification number of this controller node in all adapters
It is whether minimum in the identification number of interchanger quantity controller node equal thereto;
If so, then the adapter of this controller node takes over.
6. the dispatching method of software defined network controller cluster according to any one of claims 1 to 5, it is characterised in that
This controller node also includes after being taken over to interchanger corresponding to the mark that gets:
This controller node is changed in the Hash tables that it possesses is responsible for the mark and its load factor of the interchanger of adapter by it,
And the data syn-chronization changed is into other controller nodes;The Hash each possessed is accordingly updated by other controller nodes
Data in table.
7. the dispatching method of software defined network controller cluster according to claim 6, it is characterised in that this controller
Node is especially by the data syn-chronization that TCP is changed into other controller nodes.
8. the dispatching method of software defined network controller cluster according to claim 7, it is characterised in that this controller
Node sends the packet of request adapter to interchanger by openflow agreements, to realize to friendship corresponding to the mark that gets
The adapter changed planes.
9. the dispatching method of software defined network controller cluster according to claim 8, it is characterised in that the scheduling
Method also includes synchrodata restorative procedure, and the synchrodata restorative procedure includes:
Inquire about and whether there is abnormal data in the Hash tables that this controller node possesses, if so, then being gathered around to this controller node
Data in some Hash tables are repaired, while corresponding data are carried out in the Hash tables possessed other controller nodes
It is synchronous to repair.
10. the dispatching method of software defined network controller cluster according to claim 9, it is characterised in that the tune
Degree method also includes load-balancing method, and the load-balancing method includes:
Data in the Hash tables possessed according to this controller node judge whether this controller node is in load idle condition,
If so, the interchanger that then needs of the busy controller node of active takeover load are abandoned, until this controller node reaches negative
Carry saturation state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510073823.1A CN104579975B (en) | 2015-02-10 | 2015-02-10 | A kind of dispatching method of software defined network controller cluster |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510073823.1A CN104579975B (en) | 2015-02-10 | 2015-02-10 | A kind of dispatching method of software defined network controller cluster |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104579975A CN104579975A (en) | 2015-04-29 |
CN104579975B true CN104579975B (en) | 2018-01-05 |
Family
ID=53095200
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510073823.1A Active CN104579975B (en) | 2015-02-10 | 2015-02-10 | A kind of dispatching method of software defined network controller cluster |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104579975B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109697070B (en) * | 2017-10-23 | 2022-02-18 | 中移(苏州)软件技术有限公司 | Ambari-based cluster management method, device and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011065268A1 (en) * | 2009-11-26 | 2011-06-03 | 日本電気株式会社 | Load distribution system, load distribution method, and program |
CN102594697A (en) * | 2012-02-21 | 2012-07-18 | 华为技术有限公司 | Load balancing method and device |
CN102970379A (en) * | 2012-12-19 | 2013-03-13 | 中国电子科技集团公司第十五研究所 | Method for realizing load balance among multiple servers |
CN103618621A (en) * | 2013-11-21 | 2014-03-05 | 华为技术有限公司 | Method, device and system for automatic configuration of SDN |
CN103929333A (en) * | 2014-05-08 | 2014-07-16 | 陈桂芳 | Implementation method for SDN controller pool |
CN104104572A (en) * | 2014-07-15 | 2014-10-15 | 杭州华三通信技术有限公司 | Automatic deploying method and device for switch in SDN network |
CN104301243A (en) * | 2014-09-22 | 2015-01-21 | 华为技术有限公司 | Load control method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5910811B2 (en) * | 2011-07-27 | 2016-04-27 | 日本電気株式会社 | Switch device control system, configuration control device and configuration control method thereof |
-
2015
- 2015-02-10 CN CN201510073823.1A patent/CN104579975B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011065268A1 (en) * | 2009-11-26 | 2011-06-03 | 日本電気株式会社 | Load distribution system, load distribution method, and program |
CN102594697A (en) * | 2012-02-21 | 2012-07-18 | 华为技术有限公司 | Load balancing method and device |
CN102970379A (en) * | 2012-12-19 | 2013-03-13 | 中国电子科技集团公司第十五研究所 | Method for realizing load balance among multiple servers |
CN103618621A (en) * | 2013-11-21 | 2014-03-05 | 华为技术有限公司 | Method, device and system for automatic configuration of SDN |
CN103929333A (en) * | 2014-05-08 | 2014-07-16 | 陈桂芳 | Implementation method for SDN controller pool |
CN104104572A (en) * | 2014-07-15 | 2014-10-15 | 杭州华三通信技术有限公司 | Automatic deploying method and device for switch in SDN network |
CN104301243A (en) * | 2014-09-22 | 2015-01-21 | 华为技术有限公司 | Load control method and device |
Also Published As
Publication number | Publication date |
---|---|
CN104579975A (en) | 2015-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106375231B (en) | A kind of flow switching method, equipment and system | |
CN104579801B (en) | A kind of dispatching method of software defined network controller cluster | |
CN104468236B (en) | SDN controllers cluster, SDN switch and its connection control method | |
CA2203534C (en) | Dynamically controlled routing using dynamic management of intra-link traffic to virtual destination nodes | |
CN103188110B (en) | Based on the heat backup method that the cloud platform of zookeeper is served | |
US7739404B2 (en) | Scalable methods for distributing routing information to border gateway protocol (BGP) devices | |
CN108965014B (en) | QoS-aware service chain backup method and system | |
CN106844399A (en) | Distributed data base system and its adaptive approach | |
CN107579923A (en) | The balancing link load method and SDN controllers of a kind of SDN | |
CN102098740B (en) | Link aggregation routing method and device | |
CN102664784B (en) | A kind of mapping method of virtual network of node link pressure weight adaptive equalization | |
CN102098224B (en) | Method and device for sharing data stream loads | |
CN104243527A (en) | Data synchronization method and device and distributed system | |
CN105429811B (en) | network management system and method | |
US9820020B2 (en) | Grooming method and device for packet optical transport network | |
EP2425610A1 (en) | Pre-computing alternate forwarding state in a routed ethernet mesh network | |
JP2011160363A (en) | Computer system, controller, switch, and communication method | |
US20040240398A1 (en) | Processing method enabling each unit in stacking network device to run rapid spanning tree protocol | |
CN104579975B (en) | A kind of dispatching method of software defined network controller cluster | |
CN106210123A (en) | The software defined network controller system of one multinode | |
CN104639615A (en) | Data processing method and data processing device in controller cluster | |
CN105721328A (en) | VRRP load balancing method, VRRP load balancing device and router | |
US20140022945A1 (en) | Method for obtaining information about the operating states of nodes of a communications network in view of optimized-energy-cost routing, and corresponding device | |
WO2014029287A1 (en) | Method and device for sharing tunnel load | |
CN105959410B (en) | The load-balancing method and SiteServer LBS of server 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 | ||
CB02 | Change of applicant information |
Address after: 510000 building G1, No. 17, software Road, Guangzhou, Guangdong, Tianhe District Applicant after: Guangzhou hi tech software Limited by Share Ltd Address before: 510000 building G1, No. 17, software Road, Guangzhou, Guangdong, Tianhe District Applicant before: Guangzhou Pingao Software Development Co., Ltd. |
|
COR | Change of bibliographic data | ||
GR01 | Patent grant | ||
GR01 | Patent grant |