CN104301246A - Large-flow load balanced forwarding method and device based on SDN - Google Patents
Large-flow load balanced forwarding method and device based on SDN Download PDFInfo
- Publication number
- CN104301246A CN104301246A CN201410581056.0A CN201410581056A CN104301246A CN 104301246 A CN104301246 A CN 104301246A CN 201410581056 A CN201410581056 A CN 201410581056A CN 104301246 A CN104301246 A CN 104301246A
- Authority
- CN
- China
- Prior art keywords
- stream packet
- large stream
- path
- tor switch
- master controller
- 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
Abstract
The invention provides a large-flow load balanced forwarding method and device based on an SDN. The method comprises the steps that a TOR exchanger receives large-flow messages; the large-flow messages are stored in a large-flow hash flow table of the TOR exchanger, and meanwhile the large-flow messages are forwarded to a center controller; the center controller calculates the forwarding route of the corresponding large-flow messages according to the information carried by the large-flow messages and sends the forwarding route of the large-flow messages to the TOR exchanger, and meanwhile the forwarding route of the large-flow messages is stored in the large-flow hash flow table of the TOR exchanger. According to the large-flow load balanced forwarding method and device based on the SDN, large-flow forwarding information is increased in the large-flow hash flow table, the precious entries of an ACL are effectively saved, the size of the exchange chip is decreased, and the cost of an exchange chip is effectively lowered while the large-flow messages are forwarded in a balanced mode.
Description
Technical field
The present invention relates to network communication field, particularly relate to the balanced retransmission method of a kind of large current load based on SDN and device.
Background technology
In modern data center, a small amount of large stream occupies most network bandwidths, is the important technology of raising and optimized network utilance to the detection of flowing greatly and load balancing, how to balance these large streams again and becomes more and more crucial.
In the balanced retransmission method of traditional large current load, first large stream packet is detected by server end, and the Controller that the center that is advertised to by the described large stream packet detected controls, Controller configures ACL entry on physics TOR switch, and in ACL, specify ECMP path implement load balancing.
The instruction list of ACL to be Access Control List (ACL) (abbreviation of Access Control List) be router and exchange interface, is used for the packet of control port turnover.Contain matching relationship, condition and query statement in this table, table is a frame structure just, its objective is to control certain access.
So, in large stream packet repeating process, need the consumption of a large amount of acl entry, and be often adopt TCAM to realize ACL on TOR switch, TCAM is a kind of three-state content addressing memory (abbreviation of ternary content addressable memory), is mainly used in the list items such as fast finding ACL, route; TCAM this for switch resource valuable, do not calculate if the forwarding strategy that essential factor is large stream consumes TCAM, cause exchange chip to need to design larger TCAM for this reason, improve the cost of exchange chip.
Summary of the invention
An object of the present invention is to provide the balanced retransmission method of a kind of large current load based on SDN and device.
One of for achieving the above object, the balanced retransmission method of the large current load based on SDN of an embodiment of the present invention, described method comprises: TOR switch receives large stream packet;
Described large stream packet is kept in the large stream hash stream table of TOR switch, meanwhile, described large stream packet is forwarded to master controller Controller;
Described master controller Controller calculates its corresponding large stream packet forward-path according to the information that described large stream packet carries, and described large stream packet forward-path is sent to TOR switch, meanwhile, described large stream packet forward-path is stored in the lump in the large stream hash stream table of TOR switch.
It is as a further improvement on the present invention, described that " TOR switch receives large stream packet; " after,
Described method also comprises:
Inquire about the large stream hash stream table of described TOR switch, whether there is the large stream packet forward-path mated with described large stream packet;
If so, according to described large stream packet forward-path, described large stream packet is forwarded to corresponding convergence switch;
If not, described large stream packet is forwarded to master controller Controller.
As a further improvement on the present invention, describedly " meanwhile, described large stream packet is forwarded to master controller Controller; " specifically comprise:
Described large stream packet is informed to CPU, and described CPU passes through its northbound interface, by described large stream packet configuration distributing to master controller Controller.
As a further improvement on the present invention, described " described large stream packet forward-path is sent to TOR switch by described master controller Controller " specifically comprises:
Described large stream packet forward-path is informed to CPU by described master controller Controller, and described large stream packet forward-path is sent to TOR switch by south orientation outlet configuration by described CPU.
As a further improvement on the present invention, described method also comprises:
Another large stream hash stream table is set in described master controller Controller.
One of for achieving the above object, the balanced retransmission unit of the large current load based on SDN of an embodiment of the present invention, described device comprises:
TOR switch, with described TOR switch by the interconnective master controller Controller of network and convergence switch;
Described TOR switch comprises:
Configuration module, for receiving large stream packet;
Memory module, for being kept at by described large stream packet in the large stream hash stream table of TOR switch, meanwhile, is forwarded to master controller Controller by described large stream packet;
Described master controller Controller comprises:
Control module, for receiving the large stream packet that configuration module forwards, calculating its corresponding large stream packet forward-path according to the information that described large stream packet carries, and described large stream packet forward-path is sent to configuration module;
Wherein, described configuration module also for: receive the large stream packet forward-path that control module forwards, and by described memory module, described large stream packet forward-path to be stored in the large stream hash stream table of TOR switch in the lump.
As a further improvement on the present invention, a judge module is also comprised in described configuration module;
Described judge module is used for: after configuration module receives large stream packet, inquires about the large stream hash stream table of described TOR switch, whether there is the large stream packet forward-path mated with described large stream packet;
If so, according to described large stream packet forward-path, described large stream packet is forwarded to corresponding convergence switch;
If not, described large stream packet is forwarded to master controller Controller.
As a further improvement on the present invention, institute's configuration module also for:
Described large stream packet is informed to CPU, and described CPU passes through its northbound interface, by described large stream packet configuration distributing to master controller Controller.
As a further improvement on the present invention, described control module also for:
Described large stream packet forward-path is informed to CPU, and described large stream packet forward-path is sent to TOR switch by south orientation outlet configuration by described CPU.
As a further improvement on the present invention, another large stream hash stream table is set in described master controller Controller.
Compared with prior art, the invention has the beneficial effects as follows: the balanced retransmission method of the large current load based on SDN of the present invention and device by increasing large flow forwarding information in large stream hash stream table, the valuable entry of effective saving ACL, while making the equilibrium of large stream packet forward, effectively reduce size and the cost of exchange chip.
Accompanying drawing explanation
Fig. 1 is the flow chart based on the balanced retransmission method of the large current load of SDN in an embodiment of the present invention;
Fig. 2 is the module map based on the balanced retransmission unit of the large current load of SDN in an embodiment of the present invention;
Fig. 3 is large stream packet repeating process process schematic diagram in an embodiment of the present invention.
Embodiment
Describe the present invention below with reference to embodiment shown in the drawings.But these execution modes do not limit the present invention, the structure that those of ordinary skill in the art makes according to these execution modes, method or conversion functionally are all included in protection scope of the present invention.
SDN is software defined network (abbreviation of Software Defined Network), it is a kind of new network innovation of Emulex network framework, its core technology OpenFlow by network equipment chain of command and data surface being separated, thus achieves the flexible control of network traffics.
Described OpenFlow is a kind of new network exchange model technology.
As shown in Figure 1, in one embodiment of the present invention, the balanced retransmission method of the described large current load based on SDN comprises:
TOR switch receives large stream packet.
Stream, its English full name " Flow ", according to attribute definition Flow such as message characteristic and interfaces, the mode of a traditional definition Flow has: Mac address, source; Object Mac address; VLAN; MPLS label; Five-tuple (source IP+ object IP+ tetra-layers of head protocol number+four layers of head source port+ tetra-layers of head destination interface).
Accordingly, " stream " is divided into " flowing greatly ", " rill " two kinds according to its proportion occupying link bandwidth or the size that occupies bandwidth.The English full name of described " rill " is " Mice flow ", and it is less that it occupies bandwidth, responsive to network delay, is all control message substantially, such as: the control message of TCP, described " rill " directly affects the transmission performance of TCP.Described large stream, its English full name is " Elephant flow ", and the bandwidth occupying link is comparatively large, and be the TCP message that some are active for a long time, it does not require network delay, only has requirement to bandwidth.
Described TOR switch, towards the access switch (abbreviation of Top of rack) of main frame in data center, is the top being positioned at racks of data centers from level.
Shown in composition graphs 3, server end sends large stream packet, such as: TCP talks with; Further, TOR switch receives the large stream packet coming from server end and send.
Described Server, has dividing of soft or hard.From the angle of hardware, Server is the server physically existed; And say from the angle of software, Server refers to the computer software possessing server side functionality, and the server software run.Whole network is jointly built by countless nodes and interface channel to form.And from the aspect of " firmly ", be built by countless hardware servers and other digitlization terminal of computing device (such as PC, mobile phone etc.) and Intermediate connection device (such as netting twine, router etc.).From the aspect of " soft ", by countless running server software and client software (in other words terminal software) and they be interconnected to exchange and be built into.
Further, described large stream packet is kept in the large stream hash stream table of TOR switch, meanwhile, described large stream packet is forwarded to master controller Controller.
In present embodiment, described large stream packet is informed to CPU, described CPU passes through its northbound interface, by described large stream packet configuration distributing to master controller Controller.Accordingly, described CPU can adopt OpenFlow technology by described large stream packet configuration distributing to master controller Controller.
Further, described master controller Controller calculates its corresponding large stream packet forward-path according to the information that described large stream packet carries.
In present embodiment, because master controller Controller can know the strategy of whole network, such as: the forward-path etc. of the forwarding port information that whole network topology state, large stream packet are corresponding and correspondence.After described master controller Controller receives described large stream packet, namely start to calculate it, to obtain the large stream packet forward-path of corresponding described large stream packet.
Described large stream packet forward-path is: in described large stream packet repeating process, the forward-path of one deck convergence switch under TOR switch correspondence.
Data center in present embodiment adopts the framework of Spine-leaf, and Spine layer and Leaf interlayer are connected by ECMP load-balancing technique.Described TOR switch is in Leaf layer, and described convergence switch is in Spine layer.So, the large stream packet correspondence that described forward-path comprises via TOR switch is forwarded to the information such as the port numbers of convergence switch.
Further, described large stream packet forward-path is sent to TOR switch after calculating its corresponding large stream packet forward-path according to the information that described large stream packet carries by described master controller Controller.
In present embodiment, described large stream packet forward-path is informed to CPU by described master controller Controller, and described large stream packet forward-path is sent to TOR switch by south orientation outlet configuration by described CPU.Accordingly, described CPU can adopt OpenFlow technology that described large stream packet forward-path configuration is sent to TOR switch.
Further, the large stream packet forward-path received is stored in the large stream hash stream table of TOR switch by described TOR switch in the lump, transfers in order to large stream packet next time.
Concrete, described TOR switch receives large stream packet, inquires about the large stream hash stream table of described TOR switch, whether there is the large stream packet forward-path mated with described large stream packet; If so, according to described large stream packet forward-path, described large stream packet is forwarded to corresponding convergence switch; If not, described large stream packet is forwarded to master controller Controller.
In present embodiment, after the subsequently received large stream packet of described TOR switch, directly can inquire about the large stream hash stream table of described TOR switch, and forward according to its large stream packet forward-path corresponding with described large stream packet stored, if do not inquire the large stream packet forward-path corresponding with described large stream packet, so continue to repeat above-mentioned steps, described large stream packet is forwarded to master controller Controller and calculates corresponding large stream packet forward-path, afterwards described large stream packet forward-path is delivered to the large stream hash stream table of described TOR switch, continue again afterwards to transmit, so, thorough disengaging ACL, TCAM resource need not be consumed, and it is simple to operation, size and the cost of exchange chip can be reduced from design.
Further, in other execution modes of the present invention, one can also be increased simultaneously flow greatly hash stream table, for storage networking strategy in master controller Controller.When network strategy changes, TOR exchange opportunity notifies master controller Controller by CPU, makes it upgrade large stream hash stream table simultaneously, with when network strategy changes, carry out synchronized update, prevent error from taking system bandwidth, ensure the forwarding speed of large stream packet.
Such as: when a large stream packet is aging, that is, after described large stream packet transmission closes to an end, described large stream packet gradually becomes little stream packet.Described TOR exchange opportunity notifies CPU simultaneously, and inform master controller Controller by the northbound interface of described CPU, after described master controller Controller receives this information, namely corresponding large stream packet forward-path can be deleted in large stream hash stream table within it, and discharge bandwidth, inform TOR switch by the southbound interface of CPU simultaneously.
Shown in composition graphs 2, in the first execution mode of the present invention, the balanced retransmission unit of the described large current load based on SDN comprises: TOR switch, with described TOR switch by the interconnective master controller Controller of network and convergence switch;
Described TOR switch comprises: configuration module 100, memory module 200; Described master controller Controller comprises: control module 300, wherein, also arranges a judge module 101 in configuration module 100.
In present embodiment, configuration module 100 is for receiving large stream packet.
Stream, its English full name " Flow ", according to attribute definition Flow such as message characteristic and interfaces, the mode of a traditional definition Flow has: Mac address, source; Object Mac address; VLAN; MPLS label; Five-tuple (source IP+ object IP+ tetra-layers of head protocol number+four layers of head source port+ tetra-layers of head destination interface).
Accordingly, " stream " is divided into " flowing greatly ", " rill " two kinds according to its proportion occupying link bandwidth or the size that occupies bandwidth.The English full name of described " rill " is " Mice flow ", and it is less that it occupies bandwidth, responsive to network delay, is all control message substantially, such as: the control message of TCP, described " rill " directly affects the transmission performance of TCP.Described large stream, its English full name is " Elephant flow ", and the bandwidth occupying link is comparatively large, and be the TCP message that some are active for a long time, it does not require network delay, only has requirement to bandwidth.
Described TOR switch, towards the access switch (abbreviation of Top of rack) of main frame in data center, is the top being positioned at racks of data centers from level.
Shown in composition graphs 3, server end sends large stream packet, such as: TCP talks with; Further, TOR switch receives the large stream packet coming from server end and send.
Described Server, has dividing of soft or hard.From the angle of hardware, Server is the server physically existed; And say from the angle of software, Server refers to the computer software possessing server side functionality, and the server software run.Whole network is jointly built by countless nodes and interface channel to form.And from the aspect of " firmly ", be built by countless hardware servers and other digitlization terminal of computing device (such as PC, mobile phone etc.) and Intermediate connection device (such as netting twine, router etc.).From the aspect of " soft ", by countless running server software and client software (in other words terminal software) and they be interconnected to exchange and be built into.
Memory module 200 is for being kept at described large stream packet in the large stream hash stream table of TOR switch, and meanwhile, described large stream packet is forwarded to master controller Controller by configuration module 100.
In present embodiment, configuration module 100 is for informing to CPU by described large stream packet, and described CPU passes through its northbound interface, by described large stream packet configuration distributing to master controller Controller.Accordingly, described CPU can adopt OpenFlow technology by described large stream packet configuration distributing to master controller Controller.
Further, the large stream packet that control module 300 forwards for receiving configuration module 100, calculates its corresponding large stream packet forward-path according to the information that described large stream packet carries.
In present embodiment, because master controller Controller can know the strategy of whole network, such as: the forward-path etc. of the forwarding port information that whole network topology state, large stream packet are corresponding and correspondence.After control module 300 receives described large stream packet, namely start to calculate it, to obtain the large stream packet forward-path of corresponding described large stream packet.
Described large stream packet forward-path is: in described large stream packet repeating process, the forward-path of one deck convergence switch under TOR switch correspondence.
Data center in present embodiment adopts the framework of Spine-leaf, and Spine layer and Leaf interlayer are connected by ECMP load-balancing technique.Described TOR switch is in Leaf layer, and described convergence switch is in Spine layer.So, the large stream packet correspondence that described forward-path comprises via TOR switch is forwarded to the information such as the port numbers of convergence switch.
Further, described large stream packet forward-path is sent to TOR switch after calculating its corresponding large stream packet forward-path according to the information that described large stream packet carries by control module 300.
In present embodiment, described large stream packet forward-path is informed to CPU by control module 300, and described large stream packet forward-path is sent to TOR switch by south orientation outlet configuration by described CPU.Accordingly, described CPU can adopt OpenFlow technology that described large stream packet forward-path configuration is sent to TOR switch.
Described large stream packet forward-path also for receiving the large stream packet forward-path that control module forwards, and is stored in the large stream hash stream table of TOR switch by configuration module 100 in the lump, transfers in order to large stream packet next time.
Concrete, configuration module 100 receives large stream packet, and inquires about the large stream hash stream table of described TOR switch by judge module 101, whether there is the large stream packet forward-path mated with described large stream packet; If so, according to described large stream packet forward-path, described large stream packet is forwarded to corresponding convergence switch; If not, described large stream packet is forwarded to master controller Controller.
In present embodiment, after the subsequently received large stream packet of configuration module 100, judge module 101 directly can inquire about the large stream hash stream table of described TOR switch, forward according to the large stream packet forward-path corresponding with described large stream packet that it stores, if do not inquire the large stream packet forward-path corresponding with described large stream packet, so continue to repeat above-mentioned steps, described large stream packet is forwarded to control module 300 and calculates corresponding large stream packet forward-path, described large stream packet forward-path is delivered to configuration module 100 by control module 300 afterwards, continue again be stored to the large stream hash stream table of described TOR switch again by memory module 200 after to transmit, so, thorough disengaging ACL, TCAM resource need not be consumed, and it is simple to operation, size and the cost of exchange chip can be reduced from design.
Further, in other execution modes of the present invention, one can also be increased simultaneously flow greatly hash stream table, for storage networking strategy in master controller Controller.When network strategy changes, TOR exchange opportunity notifies master controller Controller by CPU, makes it upgrade large stream hash stream table simultaneously, with when network strategy changes, carry out synchronized update, prevent error from taking system bandwidth, ensure the forwarding speed of large stream packet.
Such as: when a large stream packet is aging, that is, after described large stream packet transmission closes to an end, described large stream packet gradually becomes little stream packet.Described TOR exchange opportunity notifies CPU simultaneously, and inform master controller Controller by the northbound interface of described CPU, after described master controller Controller receives this information, namely corresponding large stream packet forward-path can be deleted in large stream hash stream table within it, and discharge bandwidth, inform TOR switch by the southbound interface of CPU simultaneously.
Compared with prior art, the invention has the beneficial effects as follows: the balanced retransmission method of the large current load based on SDN of the present invention and device by increasing large flow forwarding information in large stream hash stream table, the valuable entry of effective saving ACL, while making the equilibrium of large stream packet forward, effectively reduce size and the cost of exchange chip.
For convenience of description, various module is divided into describe respectively with function when describing above device.Certainly, the function of each module can be realized in same or multiple software and/or hardware when implementing the application.
As seen through the above description of the embodiments, those skilled in the art can be well understood to the mode that the application can add required general hardware platform by software and realizes.Based on such understanding, the technical scheme of the application can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product can be kept to be preserved in medium, as ROM/RAM, magnetic disc, CD etc., comprising some instructions in order to make a computer equipment (can be personal computer, Information Push Server, or the network equipment etc.) perform the method described in some part of each execution mode of the application or execution mode.
Device embodiments described above is only schematic, the wherein said module illustrated as separating component can or may not be physically separates, parts as module display can be or may not be physical module, namely can be positioned at a place, or also can be distributed on multiple mixed-media network modules mixed-media.Some or all of module wherein can be selected according to the actual needs to realize the object of present embodiment scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
The application can be used in numerous general or special purpose computing system environment or configuration.Such as: personal computer, Information Push Server computer, handheld device or portable set, laptop device, many storage module system, system, set top box, programmable consumer-elcetronics devices, network PC, minicom, mainframe computer, the distributed computing environment (DCE) comprising above any system or equipment etc. based on micro-memory module.
The application can describe in the general context of computer executable instructions, such as program module.Usually, program module comprises the routine, program, object, assembly, data structure etc. that perform particular task or realize particular abstract data type.Also can put into practice the application in a distributed computing environment, in these distributed computing environment (DCE), be executed the task by the remote processing devices be connected by communication network.In a distributed computing environment, program module can be arranged in the local and remote computer preservation medium comprising preservation equipment.
Be to be understood that, although this specification is described according to execution mode, but not each execution mode only comprises an independently technical scheme, this narrating mode of specification is only for clarity sake, those skilled in the art should by specification integrally, technical scheme in each execution mode also through appropriately combined, can form other execution modes that it will be appreciated by those skilled in the art that.
A series of detailed description listed is above only illustrating for feasibility execution mode of the present invention; they are also not used to limit the scope of the invention, all do not depart from the skill of the present invention equivalent implementations done of spirit or change all should be included within protection scope of the present invention.
Claims (10)
1., based on the balanced retransmission method of large current load of SDN, it is characterized in that, described method comprises:
TOR switch receives large stream packet;
Described large stream packet is kept in the large stream hash stream table of TOR switch, meanwhile, described large stream packet is forwarded to master controller Controller;
Described master controller Controller calculates its corresponding large stream packet forward-path according to the information that described large stream packet carries, and described large stream packet forward-path is sent to TOR switch, meanwhile, described large stream packet forward-path is stored in the lump in the large stream hash stream table of TOR switch.
2. the balanced retransmission method of the large current load based on SDN according to claim 1, it is characterized in that, described " TOR switch receives large stream packet; " after,
Described method also comprises:
Inquire about the large stream hash stream table of described TOR switch, whether there is the large stream packet forward-path mated with described large stream packet;
If so, according to described large stream packet forward-path, described large stream packet is forwarded to corresponding convergence switch;
If not, described large stream packet is forwarded to master controller Controller.
3. the balanced retransmission method of the large current load based on SDN according to claim 1, is characterized in that, describedly " meanwhile, described large stream packet is forwarded to master controller Controller; " specifically comprise:
Described large stream packet is informed to CPU, and described CPU passes through its northbound interface, by described large stream packet configuration distributing to master controller Controller.
4. the balanced retransmission method of the large current load based on SDN according to claim 1, is characterized in that,
Described " described large stream packet forward-path is sent to TOR switch by described master controller Controller " specifically comprises:
Described large stream packet forward-path is informed to CPU by described master controller Controller, and described large stream packet forward-path is sent to TOR switch by south orientation outlet configuration by described CPU.
5. the balanced retransmission method of the large current load based on SDN according to claim 1, is characterized in that,
Described method also comprises:
Another large stream hash stream table is set in described master controller Controller.
6., based on the balanced retransmission unit of large current load of SDN, it is characterized in that, described device comprises:
TOR switch, with described TOR switch by the interconnective master controller Controller of network and convergence switch;
Described TOR switch comprises:
Configuration module, for receiving large stream packet, is forwarded to master controller Controller by described large stream packet;
Memory module, for being kept in the large stream hash stream table of TOR switch by described large stream packet;
Described master controller Controller comprises:
Control module, for receiving the large stream packet that configuration module forwards, calculating its corresponding large stream packet forward-path according to the information that described large stream packet carries, and described large stream packet forward-path is sent to configuration module;
Wherein, described configuration module also for: receive the large stream packet forward-path that control module forwards, and by described memory module, described large stream packet forward-path to be stored in the large stream hash stream table of TOR switch in the lump.
7. the balanced retransmission unit of the large current load based on SDN according to claim 6, is characterized in that, also comprise a judge module in described configuration module;
Described judge module is used for:
After configuration module receives large stream packet, inquire about the large stream hash stream table of described TOR switch, whether there is the large stream packet forward-path mated with described large stream packet;
If so, according to described large stream packet forward-path, described large stream packet is forwarded to corresponding convergence switch;
If not, described large stream packet is forwarded to master controller Controller.
8. the balanced retransmission unit of the large current load based on SDN according to claim 6, is characterized in that,
Described configuration module also for: described large stream packet is informed to CPU, described CPU by its northbound interface, by described large stream packet configuration distributing to master controller Controller.
9. the balanced retransmission unit of the large current load based on SDN according to claim 6, is characterized in that,
Described control module also for: described large stream packet forward-path is informed to CPU, described CPU by described large stream packet forward-path by south orientation outlet configuration be sent to TOR switch.
10. the balanced retransmission unit of the large current load based on SDN according to claim 6, is characterized in that,
Another large stream hash stream table is set in described master controller Controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410581056.0A CN104301246A (en) | 2014-10-27 | 2014-10-27 | Large-flow load balanced forwarding method and device based on SDN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410581056.0A CN104301246A (en) | 2014-10-27 | 2014-10-27 | Large-flow load balanced forwarding method and device based on SDN |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104301246A true CN104301246A (en) | 2015-01-21 |
Family
ID=52320818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410581056.0A Pending CN104301246A (en) | 2014-10-27 | 2014-10-27 | Large-flow load balanced forwarding method and device based on SDN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104301246A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105376178A (en) * | 2015-12-07 | 2016-03-02 | 北京邮电大学 | Data transmission method and device |
| CN105763606A (en) * | 2016-02-04 | 2016-07-13 | 杭州华三通信技术有限公司 | Service chain agent aggregation method and system |
| CN107342906A (en) * | 2016-04-29 | 2017-11-10 | 华为技术有限公司 | A kind of detection method, equipment and the system of elephant stream |
| CN107579923A (en) * | 2017-09-18 | 2018-01-12 | 迈普通信技术股份有限公司 | The balancing link load method and SDN controllers of a kind of SDN |
| CN107579928A (en) * | 2017-10-16 | 2018-01-12 | 成都西加云杉科技有限公司 | Flow forwarding method and system |
| CN108282481A (en) * | 2018-01-30 | 2018-07-13 | 电子科技大学 | A kind of data center network flow-measuring method based on SDN |
| CN111163015A (en) * | 2019-12-24 | 2020-05-15 | 北京百卓网络技术有限公司 | Message sending method and device and convergence and diversion equipment |
| CN111600806A (en) * | 2016-10-27 | 2020-08-28 | 贵州白山云科技股份有限公司 | Load balancing method and device, front-end scheduling server, storage medium and equipment |
| CN113595928A (en) * | 2021-08-04 | 2021-11-02 | 优刻得科技股份有限公司 | Load balancing method, apparatus and medium |
| CN114785707A (en) * | 2022-05-16 | 2022-07-22 | 电子科技大学 | Hierarchical massive stream cooperative monitoring method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685006A (en) * | 2012-05-03 | 2012-09-19 | 中兴通讯股份有限公司 | Method and device for forwarding data messages |
| CN102857416A (en) * | 2012-09-18 | 2013-01-02 | 中兴通讯股份有限公司 | Method for implementing virtual network and virtual network |
| CN102984064A (en) * | 2012-12-28 | 2013-03-20 | 盛科网络（苏州）有限公司 | Method and system for distinguishing and transmitting elephant flow |
| CN103401721A (en) * | 2013-08-22 | 2013-11-20 | 盛科网络（苏州）有限公司 | Network virtualization based TOR (top of rack) switch configuration method and device |
| CN103856417A (en) * | 2012-11-30 | 2014-06-11 | 中兴通讯股份有限公司 | Software-defined network message forwarding method and system |
| US20140237118A1 (en) * | 2013-02-19 | 2014-08-21 | Broadcom Corporation | Application Aware Elephant Flow Management |
| CN104022953A (en) * | 2013-02-28 | 2014-09-03 | 杭州华三通信技术有限公司 | Message forwarding method and device based on Open Flow |
-
2014
- 2014-10-27 CN CN201410581056.0A patent/CN104301246A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685006A (en) * | 2012-05-03 | 2012-09-19 | 中兴通讯股份有限公司 | Method and device for forwarding data messages |
| CN102857416A (en) * | 2012-09-18 | 2013-01-02 | 中兴通讯股份有限公司 | Method for implementing virtual network and virtual network |
| CN103856417A (en) * | 2012-11-30 | 2014-06-11 | 中兴通讯股份有限公司 | Software-defined network message forwarding method and system |
| CN102984064A (en) * | 2012-12-28 | 2013-03-20 | 盛科网络（苏州）有限公司 | Method and system for distinguishing and transmitting elephant flow |
| US20140237118A1 (en) * | 2013-02-19 | 2014-08-21 | Broadcom Corporation | Application Aware Elephant Flow Management |
| CN104022953A (en) * | 2013-02-28 | 2014-09-03 | 杭州华三通信技术有限公司 | Message forwarding method and device based on Open Flow |
| CN103401721A (en) * | 2013-08-22 | 2013-11-20 | 盛科网络（苏州）有限公司 | Network virtualization based TOR (top of rack) switch configuration method and device |
Non-Patent Citations (1)
| Title |
|---|
| 啸傲江湖: ""DevoFlow对Openflow的优化"", 《HTTP://C114.NET/BLOG-18988-178.HTML》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105376178B (en) * | 2015-12-07 | 2019-03-15 | 北京邮电大学 | A kind of method and apparatus of data transmission |
| CN105376178A (en) * | 2015-12-07 | 2016-03-02 | 北京邮电大学 | Data transmission method and device |
| CN105763606A (en) * | 2016-02-04 | 2016-07-13 | 杭州华三通信技术有限公司 | Service chain agent aggregation method and system |
| CN105763606B (en) * | 2016-02-04 | 2019-04-09 | 新华三技术有限公司 | A kind of method and system of service chaining agent polymerization |
| CN107342906A (en) * | 2016-04-29 | 2017-11-10 | 华为技术有限公司 | A kind of detection method, equipment and the system of elephant stream |
| CN111600806A (en) * | 2016-10-27 | 2020-08-28 | 贵州白山云科技股份有限公司 | Load balancing method and device, front-end scheduling server, storage medium and equipment |
| CN107579923A (en) * | 2017-09-18 | 2018-01-12 | 迈普通信技术股份有限公司 | The balancing link load method and SDN controllers of a kind of SDN |
| CN107579923B (en) * | 2017-09-18 | 2019-12-10 | 迈普通信技术股份有限公司 | Link load balancing method of SDN and SDN controller |
| CN107579928B (en) * | 2017-10-16 | 2019-12-17 | 成都西加云杉科技有限公司 | flow forwarding method and system |
| CN107579928A (en) * | 2017-10-16 | 2018-01-12 | 成都西加云杉科技有限公司 | Flow forwarding method and system |
| CN108282481A (en) * | 2018-01-30 | 2018-07-13 | 电子科技大学 | A kind of data center network flow-measuring method based on SDN |
| CN108282481B (en) * | 2018-01-30 | 2020-07-17 | 电子科技大学 | SDN-based data center network flow measurement method |
| CN111163015A (en) * | 2019-12-24 | 2020-05-15 | 北京百卓网络技术有限公司 | Message sending method and device and convergence and diversion equipment |
| CN113595928A (en) * | 2021-08-04 | 2021-11-02 | 优刻得科技股份有限公司 | Load balancing method, apparatus and medium |
| CN114785707A (en) * | 2022-05-16 | 2022-07-22 | 电子科技大学 | Hierarchical massive stream cooperative monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104301246A (en) | Large-flow load balanced forwarding method and device based on SDN | |
| US9736278B1 (en) | Method and apparatus for connecting a gateway router to a set of scalable virtual IP network appliances in overlay networks | |
| EP3355553B1 (en) | Reliable load-balancer using segment routing and real-time application monitoring | |
| US9021116B2 (en) | System and method to create virtual links for end-to-end virtualization | |
| US9680746B2 (en) | Source routing with fabric switches in an ethernet fabric network | |
| US8891375B2 (en) | System and method for virtual Ethernet interface binding | |
| US9088584B2 (en) | System and method for non-disruptive management of servers in a network environment | |
| US8730793B2 (en) | Method and apparatus providing network redundancy and high availability to remote network nodes | |
| US8913613B2 (en) | Method and system for classification and management of inter-blade network traffic in a blade server | |
| US9444743B2 (en) | Network system, switch and connected terminal detection method | |
| US9614759B2 (en) | Systems and methods for providing anycast MAC addressing in an information handling system | |
| US20070002826A1 (en) | System implementing shared interface for network link aggregation and system management | |
| US10484233B2 (en) | Implementing provider edge with hybrid packet processing appliance | |
| US20130003549A1 (en) | Resilient Hashing for Load Balancing of Traffic Flows | |
| US9008080B1 (en) | Systems and methods for controlling switches to monitor network traffic | |
| JP2013545359A (en) | Method, master switch, switching network, program, apparatus and system for switching in a switching network | |
| US10193811B1 (en) | Flow distribution using telemetry and machine learning techniques | |
| US10411742B2 (en) | Link aggregation configuration for a node in a software-defined network | |
| CN102843299A (en) | Method and system for realizing Openflow multi-stage flow tables on basis of ternary content addressable memory (TCAM) | |
| CN102025643A (en) | Flow table search method and device | |
| US20130088969A1 (en) | Network traffic distribution | |
| WO2017189042A1 (en) | Expedited fabric paths in switch fabrics | |
| CN107959625A (en) | Virtual router with dynamic stream relieving capacity | |
| US20120314715A1 (en) | Method and system for implementing a multi-chassis link aggregation group in a network | |
| CN102904825B (en) | A kind of message transmitting method based on Hash and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150121 |
|
| WD01 | Invention patent application deemed withdrawn after publication |