CN101127728A - A load sharing router and device and method for load sharing - Google Patents
A load sharing router and device and method for load sharing Download PDFInfo
- Publication number
- CN101127728A CN101127728A CNA2007101755812A CN200710175581A CN101127728A CN 101127728 A CN101127728 A CN 101127728A CN A2007101755812 A CNA2007101755812 A CN A2007101755812A CN 200710175581 A CN200710175581 A CN 200710175581A CN 101127728 A CN101127728 A CN 101127728A
- Authority
- CN
- China
- Prior art keywords
- processing unit
- line processing
- physical interface
- router
- interface card
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 100
- 238000005538 encapsulation Methods 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000004148 unit process Methods 0.000 claims description 2
- 238000011144 upstream manufacturing Methods 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 4
- 239000012141 concentrate Substances 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 101100153168 Arabidopsis thaliana TIC21 gene Proteins 0.000 description 1
- 101100273813 Homo sapiens CDKN1A gene Proteins 0.000 description 1
- 108700038981 SUMO-1 Proteins 0.000 description 1
- 101100083337 Schizosaccharomyces pombe (strain 972 / ATCC 24843) pic1 gene Proteins 0.000 description 1
- 102100026940 Small ubiquitin-related modifier 1 Human genes 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 230000008521 reorganization Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The utility model relates to a load-sharing router in the technical field of communication, comprising two main control panels, a plurality of physical interface cards and a plurality of line processing units, wherein one main control panels primary, while the other main control panel is spare, which are used for monitoring each unit, managing equipment of the router, and the running routing protocol; the physical interface cards are completely connected with the line processing units. The utility model also provides the method and equipment for router load-sharing. The utility model is characterized in that the physical interface card in the router is completely connected with the line processing unit, thereby separating the physical interface card from the line processing unit, the line processing unit can be dispatched by the physical interface card according to the load information of each line processing unit, enabling load-sharing in each line processing unit.
Description
Technical field
The present invention relates to communication technical field, the equipment, the method that relate in particular to a kind of load balancing router and realize load balancing.
Background technology
Along with the raising of router performance, its framework is also changing.Centralized platform from early stage develops into present switch type platform, and disposal ability constantly promotes.Concentrating the forwarding router framework as shown in Figure 1, is to adopt CPU to be responsible for configuration management, route and forwarding, supports professional and abundant flexibly interface, is with good expansibility.And the switch-type router framework as shown in Figure 2, this router is present main flow, adopt distributed NP (Network processor, network processing unit) or ASIC (Application Specific Integrated Chip, application-specific IC) framework of Zhuan Faing, connect each interface with choke free high speed switching network, systematic function is improved significantly.
As shown in Figure 3, for concentrating the active and standby configuration diagram of relay type router,, generally adopt the dual master control type structure in order to improve reliability.Two master control borads generally are to use as primary, spare master control borad respectively.Main control board is responsible for route, forwarding and equipment control, and slave control board then is in Status of Backups.After main control board breaks down, then business is all switched to slave control board.This kind processing mode has improved the reliability of system, but the bottleneck of disposal ability still is CPU and bus.Adopt two master control borads to do load balancing in order further to promote performance, also to have.
But in realizing process of the present invention, the inventor finds that there is following shortcoming at least in described concentrated relay type router architectures:
1. no matter whether adopt active and standby part of master control borad, CPU and bus all still are the bottlenecks of system;
2. although two master control borads adopt the load balancing mode can promote performance to a certain extent, because the restriction of framework can't adopt more master control borad to share Business Processing, the lifting of performance is limited.
The Line Processing Unit of existing switch-type router and physical interface card architecture are as shown in Figure 4, each PIC (Physical Interface Card, physical interface card) only with a LPU (Line ProcessingUnit, Line Processing Unit) links to each other, these two parts lump together, be inserted on the groove position, by the switching network interconnection, carry out clog-free exchange between the LPU.The path of flow is PIC → LPU → switching network → LPU → PIC.
Under this framework, PIG finishes the opto-electronic conversion of user interface and decides frame and handle, and Frame is sent to LPU.NP on the LPU or ASIC carry out Business Processing, comprise data frame analyzing, classification, route querying and forwarding, exchange to the LPU of respective grooves position through switching network, carrying out downlink business by NP on it or ASIC handles, finish the encapsulation back according to interface type Frame is sent to PIC, carry out operations such as framing coding and electric light conversion by PIC and send on the subscriber's line.
Though described switch-type router framework has solved the shortcoming of concentrated forwarding router, has promoted systematic function, in realizing process of the present invention, the inventor finds that there is following shortcoming at least in above-mentioned switch-type router:
1. owing to LPU and PIC close coupling, the inefficacy of LPU can cause service disconnection, and LPU is more complicated than PIC, and failure rate is higher;
2. because PIC interface and type of service on each LPU are not quite similar, the load of LPU also is not quite similar, and causes the load weight of LPU to differ.Very big with regard to difference as 32E1 PIC and 4 * 2.5G POS PIC to the resource consumption of LPU.Often form local focus in a router, become the bottleneck of using and testing, then often load is lighter for the LPU outside the focus, and idle disposal ability can not be fully utilized.
3. the upgrading of any one LPU all can interrupting service;
4. centralized forwarding and distributed forwarding plane are isolated and come, be difficult to unified both frameworks, cause platform numerous, be unfavorable for platform normalization.
Summary of the invention
Equipment, method that the embodiment of the invention provides a kind of load balancing router and realizes load balancing have solved the not first-class problem of load weight that existing router LPU and PIC close coupling are brought.
The embodiment of the invention is achieved through the following technical solutions:
The embodiment of the invention provides a kind of router of realizing load balancing, comprising:
Two active and standby each other master control borads are used for each unit of router is monitored and equipment control, and the operation Routing Protocol;
Be connected entirely between a plurality of physical interface cards and a plurality of Line Processing Unit, described a plurality of physical interface cards and described a plurality of Line Processing Units.
The embodiment of the invention provides a kind of physical interface card, is arranged in the router, and described router is provided with a plurality of Line Processing Units, and this physical interface card comprises:
Memory cell is used to store the characteristic information of a plurality of Line Processing Units;
The uplink scheduling unit is used for according to the message scheduling data of the Line Processing Unit loading condition information obtained in real time and the described memory cell corresponding Line Processing Unit of reporting for work.
The embodiment of the invention provides a kind of router to realize the method for load balancing, comprising:
The physical interface card of router obtains the loading condition information of Line Processing Unit in real time;
Reach the corresponding Line Processing Unit of Line Processing Unit message scheduling of the specific transactions correspondence of storage in advance according to described loading condition information;
The Line Processing Unit that datagram is transmitted to described scheduling is handled.
The technical scheme that is provided by the invention described above embodiment as can be seen, the embodiment of the invention is by being connected the physical interface card in the router entirely with Line Processing Unit, realize separating of physical interface card and Line Processing Unit, make physical interface card to dispatch Line Processing Unit, realize the load balancing of each Line Processing Unit according to the loading condition information of each Line Processing Unit.
Description of drawings
Fig. 1 concentrates the forwarding router Organization Chart for prior art;
Fig. 2 is a prior art switch-type router Organization Chart;
Fig. 3 concentrates the active and standby configuration diagram of relay type router for prior art;
Fig. 4 is the Business Processing and the physical interface card architecture of prior art switch-type router;
Fig. 5 is the embodiment of the invention one described router architectures figure;
Fig. 6 is the embodiment of the invention two described router architectures figure;
Fig. 7 is the embodiment of the invention three described router load sharing method flow charts.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that is obtained under the creative work prerequisite.
The embodiment of the invention realizes separating of physical interface card and Line Processing Unit by full connection (being that each PIC all has link to be connected with each LPU) mode is set between PIC and the LPU, makes the flow of each PIC can exchange on any one LPU.Described full connection approach can realize by switching network, also can directly adopt MESH (netted connection) mode to connect between PIC and LPU for mini-plant.Master control borad by the monitoring of being responsible for whole system and management is given PIC with the loading condition information real-time informing on each LPU (perhaps transmitting by in-band information), and PIC can guarantee that the load of each LPU is roughly suitable according to the loading condition Information Selection LPU of each LPU.The particular service that is directed to specific LPU for needs is handled, and can dispose relevant entries on PIC, guarantees that this particular service direct traffic is to specific LPU.This PIC and LPU can be by master control borad unified monitoring and management.
The router that the embodiment of the invention one provides, to realize being connected to full example by switching network between PIC and the LPU, as shown in Figure 5, described router architectures comprises: two active and standby each other master control borads, m piece PIC, k piece LPU and some network boards (m, k are natural number).Described two active and standby each other master control borads are responsible for the monitoring and the equipment control of whole system, and the operation Routing Protocol etc.HUB on it is responsible for handling and distributing the loading condition of each LPU,, gives PIC with performance index, the present load advisory of each LPU that is.
Connect by switching network between described PIC and the LPU.The flow of each PIC can exchange on any one LPU.
As shown in Figure 5, PIC is provided with:
PHY/MAC/Framer is circuit reception and data framing and relevant treatment entity, for existing P IC goes up entity, does not elaborate herein;
Resolution unit is used for from described PHY/MAC/Framer receiving data stream, and carries out heading and resolve;
The traffic classification processing unit is used for the processing such as classify of the data flow after the described parsing;
Memory cell is used to store the characteristic information of each LPU, for example the LPU information of specific transactions correspondence;
Uplink scheduling unit and descending scheduling unit, described two unit can be arranged on the same physical entity; Described uplink scheduling unit, be used under the data flow situation after receiving described traffic classification processing unit processes the characteristic information data dispatching of the storage corresponding LPU that reports for work in advance in the loading condition information of each LPU that sends in real time according to master control borad and the memory cell; The loading condition information of described LPU comprises: the performance indication of LPU present load situation and LPU etc.; Described descending scheduling unit is used to downstream data flow scheduling outbound port;
The FIC interface is the switching network interface chip, is used for the conversion of data format between switching network and the PIC, for upstream data newspaper, to need to be responsible for the datagram transmitted to be converted to the form of switching network identification, sends to switching network in the mode of cell or message; For the downlink data newspaper, be responsible for cell or message are converted to the data format that PIC goes up transmission.This FIC is provided with: the switching network flow-control information obtains and the processing unit (not shown), is used for obtaining in real time the current flow-control information of each switching network, and according to described flow-control information scheduling cell or the data switching network of reporting for work.The flow-control information of described each switching network is meant the flow control information of each switching network, hereinafter to be referred as flow-control information.
Recomposition unit is used for the cell of data that receives from the FIC interface processing of recombinating; When transmitting message, this recomposition unit can be set.
Encapsulation unit is used for finishing according to physical interface type the encapsulation of link layer, sends the descending scheduling unit afterwards to.
Data channel between PIC and the switching network is divided into uplink and downlink two parts, up be FIC interface from PIC to switching network, descending then is FIC interface from the switching network to PIC.
The processing mode of up direction (is example with the flow process on the PIC1) is: the message that receives from PHY/MAC/Framer carries out heading through resolution unit and resolves, undertaken by the traffic classification processing unit processing such as traffic classification, send to the uplink scheduling unit afterwards, described uplink scheduling unit obtains the LPU information of each specific transactions correspondence from memory cell, and the LPU that links to each other with the switching network outbound port according to the real-time loading condition message scheduling of each LPU.The principle of described scheduling LPU can comprise: under the situation that satisfies single LPU disposal ability, guarantee that as far as possible a stream can not be assigned on a plurality of LPU, that is, make the amount of flowing to end be given a LPU and handle, and make the load basis equalization of each LPU.Single current for surpassing single LPU disposal ability can adopt thinner traffic classification specification or the mode of Hash, is divided into a plurality of son streams.The particular service that is directed to specific LPU for needs is handled, PIC is the relevant LPU of this specific transactions scheduling according to the information in the memory cell, guarantee that the particular service direct traffic is to specific LPU, after scheduling LPU finishes, switching network flow-control information in the described FIC interface obtains the current flow-control information of each switching network that obtains with the processing unit utilization, scheduling cell or the data switching network of reporting for work.
The processing mode of down direction (is example with the flow process on the PICm) is: the message that LPU handled exchanges on the corresponding PIC through switching network, FIC on the PIC finishes the conversion of message or cell format and the extraction of flow-control information, message or cell are sent into recomposition unit, be reassembled as complete message.If message is then ignored reorganization.(adopt Hash) is dispatched to the single current on a plurality of LPU for exceeding the LPU disposal ability, at the down direction laggard line ordering of recombinating.Encapsulation unit is finished the encapsulation of link layer according to physical interface type, and the message after the encapsulation is sent into the scheduling that the descending scheduling unit carries out outbound port, finally sends on the physical interface through PHY/MAC/Framer.
In order to guarantee switching performance, described switching network can be the exchange of many planes, and the parallel data flow of transmitting of a plurality of switching networks promptly is set, and avoids a congested situation of retransmission failure that causes of switching network to take place.
Described LPU mainly is made up of FIC, packet processing engine and queue management device etc., be responsible for to handle the data flow that sends through switching network from PIC, finish route querying and Business Processing and loading condition information is notified to described a plurality of physical interface card by packet processing engine.The indication of packet processing engine loading condition on each LPU and performance can be sent to HUB on the master control borad in real time by the specialized hardware line, and HUB sends to each PIC to relevant index signal in time-multiplexed mode, as the foundation of LPU scheduling.Loading condition on the LPU also can be broadcast on each PIC in real time by in-band information.Described queue management device is used for the datagram after the described packet processing engine processing is sent to corresponding physical interface card or other LPU.
When handling complicated business, can be provided with and finish the special LPU that particular service is handled, then on other a plurality of LPU, store the information of described special LPU, these a plurality of LPU are after finishing respective handling, according to described canned data, the data flow that need further finish special processing sends to corresponding special LPU.
Present embodiment makes described PIC be connected entirely with LPU by between a plurality of PIC and LPU switching network being set, and makes PIC can obtain the loading condition information of each LPU in real time, according to the loading condition Information Selection LPU of described LPU, has realized the load balancing of LPU.
The router architectures that the embodiment of the invention two provides is to connect entirely by the MESH mode between PIC and LPU, and as shown in Figure 6, for the small dimension configuration, switching network is existence in logic.Directly the FIC on the PIC is set to the MESH mode, directly links to each other with LPU, and other of PIC are provided with described in the embodiment one.LPU also can unify with master control borad, is the SPU (ServiceProcessing Unit, Service Processing Unit) among Fig. 6, and the function that main control module is finished described active and standby each other master control borad is set on two LPU therein.
Present embodiment is realized full connection the between the PIC and LPU in the router by the MESH mode, thereby the flow of each PIC can be exchanged on any one LPU, has realized the load balancing of LPU.
The embodiment of the invention three provides a kind of method that realizes that router load is shared, and as shown in Figure 7, comprises the steps:
Step 1:PIC receives message, to described message resolve, processing such as traffic classification;
Step 2: obtain the loading condition information of current each LPU,, be dispatched to corresponding LPU according to the described loading condition information and the LPU information of specific transactions correspondence of storage in advance;
Described PIC can obtain the loading condition information of each LPU in real time by master control borad, or obtains described information by in-band message.
For realizing the load balancing of LPU, the principle of described PIC scheduling LPU comprises:
Under the situation that satisfies single LPU disposal ability, guarantee that as far as possible a stream can not be assigned on a plurality of LPU, and make the load basis equalization of each LPU.Single current for surpassing single LPU disposal ability can adopt thinner traffic classification specification or Hash, is divided into a plurality of son streams.The particular service that is directed to specific LPU for needs is handled, and PIC for the relevant LPU of this specific transactions scheduling, guarantees that the particular service direct traffic is to specific LPU according to the information in the memory cell.
Step 3: the LPU that described message is transmitted to described scheduling;
If adopt switching network to be connected between described PIC and the LPU, then PIC obtains the flow-control information of switching network in real time, understands the work at present situation of each switching network, selects the less relatively switching network forwarding data flow of current bearing capacity;
Step 4: described LPU carries out after route querying and related service handle described message, it is mail to corresponding PIC or transfers other LPU to further handle;
The described situation that transfers other LPU to comprises: need be for further processing to current business, and this processing need be finished the special LPU realization of this processing procedure.Send to PIC after the finishing dealing with of all LPU.
Step 5: the described PIC that receives described message recombinates, is dispatched to corresponding outbound port after the processing such as encapsulation described message, sends on the physical interface through PHY/MAC/Framer.
The described router of present embodiment, its PIC can dispatch LPU according to the loading condition information of each LPU when selecting LPU, realize the load balancing of each LPU.
In sum, the embodiment of the invention is connected with LPU entirely by PIC, realize separating of physical interface card and Line Processing Unit, PIC dispatches LPU according to the loading condition information of each LPU, when realizing the load balancing of each LPU, system reliability is improved greatly, and the fault of LPU and upgrading can not have influence on business.
The above; only for the preferable embodiment of the present invention, but protection scope of the present invention is not limited thereto, and anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; the variation that can expect easily or replacement all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claim.
Claims (21)
1. a router of realizing load balancing is characterized in that, comprising:
Two active and standby each other master control borads are used for each unit of router is monitored and equipment control, and the operation Routing Protocol;
Be connected entirely between a plurality of physical interface cards and a plurality of Line Processing Unit, described a plurality of physical interface cards and described a plurality of Line Processing Units.
2. router as claimed in claim 1 is characterized in that, realizes being connected entirely by switching network between described a plurality of physical interface cards and the described a plurality of Line Processing Units.
3. router as claimed in claim 1 is characterized in that, direct netted connection the between described a plurality of physical interface cards and the described a plurality of Line Processing Units.
4. router as claimed in claim 3 is characterized in that, described master control borad and described Line Processing Unit merge, and on two Line Processing Units the function that main control module is finished described two active and standby each other master control borads are set respectively therein.
5. router as claimed in claim 1 is characterized in that, described Line Processing Unit is provided with:
Packet processing engine is used for route querying and Business Processing, and loading condition information is notified to described a plurality of physical interface card;
Queue management device is used to send the datagram after packet processing engine is handled.
6. router as claimed in claim 5 is characterized in that, when comprising the special Line Processing Unit of handling the particular service of predesignating in described a plurality of Line Processing Units, then also is provided with at described Line Processing Unit:
Special Line Processing Unit information memory cell is used to store described special Line Processing Unit relevant information.
7. router as claimed in claim 5 is characterized in that, described physical interface card obtains the real-time loading condition information of described Line Processing Unit by described master control borad or in-band information.
8. a physical interface card is arranged in the router, and described router is provided with a plurality of Line Processing Units, it is characterized in that, this physical interface card comprises:
Memory cell is used to store the characteristic information of a plurality of Line Processing Units;
The uplink scheduling unit is used for according to the message scheduling data of the Line Processing Unit loading condition information obtained in real time and the described memory cell corresponding Line Processing Unit of reporting for work.
9. physical interface card as claimed in claim 8 is characterized in that, described physical interface card further comprises:
The switching network interface chip, the conversion of the physical interface card datagram format that is used to come in and go out.
10. physical interface card as claimed in claim 9 is characterized in that, when realizing being connected entirely by switching network between described a plurality of physical interface cards and a plurality of Line Processing Units, also comprises on the described physical interface card:
The switching network flow-control information obtains and processing unit, is used for obtaining in real time the current flow-control information of each switching network, and according to described flow-control information scheduling cell or the data switching network of reporting for work.
11. physical interface card as claimed in claim 10 is characterized in that, described switching network flow-control information obtains with processing unit and is arranged on the switching network interface chip.
12. physical interface card as claimed in claim 8 is characterized in that, also comprises:
Be used for upstream is carried out the resolution unit that heading is resolved;
Be used for traffic classification processing unit that the data flow after the described parsing is classified and handled; And
Finish the encapsulation unit of link layer according to physical interface type;
Be used to the descending scheduling unit of described encapsulation back data stream scheduling outbound port.
13. physical interface card as claimed in claim 12 is characterized in that, also comprises:
Be used for recomposition unit that the downlink data cell is recombinated and handled.
14. a router is realized the method for load balancing, it is characterized in that, comprising:
The physical interface card of router obtains the loading condition information of Line Processing Unit in real time;
Reach the corresponding Line Processing Unit of Line Processing Unit message scheduling of the specific transactions correspondence of storage in advance according to described loading condition information;
The Line Processing Unit that datagram is transmitted to described scheduling is handled.
15. method as claimed in claim 14 is characterized in that, the method that described physical interface card obtains the loading condition information of Line Processing Unit in real time comprises:
Obtain or obtain by master control borad by in-band information.
16. method as claimed in claim 14 is characterized in that, the loading condition information of described Line Processing Unit comprises:
The performance indication of Line Processing Unit, present load situation.
17. method as claimed in claim 14 is characterized in that, when being connected by a plurality of switching networks between described physical interface card and the described Line Processing Unit, described method also comprises:
Physical interface card obtains the flow-control information of described each switching network in real time, and according to described flow-control information scheduling cell or the data switching network of reporting for work.
18., it is characterized in that the method for the corresponding Line Processing Unit of described scheduling comprises as claim 14 or 17 described methods:
Satisfying under the single Line Processing Unit disposal ability situation, on flow point to a Line Processing Unit;
Being directed to the particular service of specific circuit processing unit for needs, according to the described Line Processing Unit information of this specific transactions correspondence of storage in advance, is the relevant Line Processing Unit of this specific transactions scheduling.
19. method as claimed in claim 18 is characterized in that, according to described dispatching method, when certain data flow surpasses single Line Processing Unit disposal ability, described data flow is divided into a plurality of son streams, handles thereby be assigned on a plurality of Line Processing Units.
20. method as claimed in claim 14 is characterized in that, between described physical interface card and the described Line Processing Unit by switching network or the direct netted interactive information that is connected.
21. method as claimed in claim 14 is characterized in that, the processing of described Line Processing Unit comprises:
After current Line Processing Unit is finished respective handling,, then described data flow is sent to special circuit processing unit processes if need do further special processing to current data stream.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007101755812A CN100571219C (en) | 2007-09-30 | 2007-09-30 | A kind of load balancing router and the equipment, the method that realize load balancing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007101755812A CN100571219C (en) | 2007-09-30 | 2007-09-30 | A kind of load balancing router and the equipment, the method that realize load balancing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101127728A true CN101127728A (en) | 2008-02-20 |
| CN100571219C CN100571219C (en) | 2009-12-16 |
Family
ID=39095654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007101755812A Expired - Fee Related CN100571219C (en) | 2007-09-30 | 2007-09-30 | A kind of load balancing router and the equipment, the method that realize load balancing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100571219C (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101888304A (en) * | 2009-05-15 | 2010-11-17 | 华为技术有限公司 | Updating method, device and system for routing equipment |
| CN101252535B (en) * | 2008-03-28 | 2010-12-22 | 杭州华三通信技术有限公司 | Centralize type forwarding network appliance and method |
| CN102347904A (en) * | 2011-10-21 | 2012-02-08 | 杭州华三通信技术有限公司 | Router equipment, main card thereof and method for adapting main card to interface card |
| CN104811400A (en) * | 2014-01-26 | 2015-07-29 | 杭州迪普科技有限公司 | Distributed network apparatus |
-
2007
- 2007-09-30 CN CNB2007101755812A patent/CN100571219C/en not_active Expired - Fee Related
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252535B (en) * | 2008-03-28 | 2010-12-22 | 杭州华三通信技术有限公司 | Centralize type forwarding network appliance and method |
| CN101888304A (en) * | 2009-05-15 | 2010-11-17 | 华为技术有限公司 | Updating method, device and system for routing equipment |
| CN102347904A (en) * | 2011-10-21 | 2012-02-08 | 杭州华三通信技术有限公司 | Router equipment, main card thereof and method for adapting main card to interface card |
| CN104811400A (en) * | 2014-01-26 | 2015-07-29 | 杭州迪普科技有限公司 | Distributed network apparatus |
| CN104811400B (en) * | 2014-01-26 | 2018-04-06 | 杭州迪普科技股份有限公司 | A kind of distributed network equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100571219C (en) | 2009-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102971996B (en) | Switching node with the load balance of packet burst | |
| CN1277375C (en) | Switching method between permanent connection and exchage connection in optical network | |
| CN101534198B (en) | Communication system | |
| CN102111327B (en) | Method and system for cell dispatching | |
| CN102868645A (en) | Open flow switchboard system and message processing method of open flow switchboard system | |
| CN104836750A (en) | Data center network flow scheduling method based on round-robin | |
| CN102148677A (en) | Method for updating address resolution protocol table entries and core switch | |
| CN1937782A (en) | Frame device and its message transmitting method | |
| CN101610143B (en) | Protection method, system and device of link data | |
| CN100571219C (en) | A kind of load balancing router and the equipment, the method that realize load balancing | |
| US7327712B2 (en) | Selection system, its selection method for voice channels, and switchboard for use therein | |
| CN100536369C (en) | Service protection device in optical communication network and method thereof | |
| CN103326916A (en) | System and method for automatic partition of intelligent substation and optimization of VLAN | |
| CN103457851A (en) | PTN (packet transfer network) organization architecture and service bearing method thereof | |
| CN202310005U (en) | Multi-business communication device possessing voice program control exchange function | |
| CN103139005B (en) | The method that Network resource allocation reasonability is detected and device | |
| CN101621530A (en) | Method and device for dispatching load balancing network resource based on light path share | |
| CN101635683A (en) | Method and device for transmitting service based on link aggregation | |
| CN101145857B (en) | A service convergence system for saving core router port | |
| CN101043460B (en) | Apparatus and method for realizing single stream forwarding of multi-network processing unit | |
| CN206820765U (en) | A kind of terminal communication access net communication resource model framework | |
| CN103259830A (en) | Low-latency convergence TAP | |
| CN110113258A (en) | Method and system for automatically protecting data plane link by using control plane link | |
| CN102231710A (en) | Method for carrying out message interaction between single boards in network equipment and network equipment | |
| CN102045259B (en) | Packet switching equipment and method for managing customer service |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20091216 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |