CN102594610A - Host election method after topology division as well as device and network equipment - Google Patents
Host election method after topology division as well as device and network equipment Download PDFInfo
- Publication number
- CN102594610A CN102594610A CN2012100749995A CN201210074999A CN102594610A CN 102594610 A CN102594610 A CN 102594610A CN 2012100749995 A CN2012100749995 A CN 2012100749995A CN 201210074999 A CN201210074999 A CN 201210074999A CN 102594610 A CN102594610 A CN 102594610A
- Authority
- CN
- China
- Prior art keywords
- main process
- process equipment
- subsystem
- equipment
- topology
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a host election method after topology division as well as a device and network equipment, which are used for sufficiently utilizing equipment resources after the topology division for improving the network performance, wherein the host election method after topology division comprises the following steps that: after a thermal stack system is divided into a plurality of sub systems through the topology division, host equipment of each sub system respectively determines the number of member equipment of the sub system, in addition, the determined number of the member equipment of the sub system is carried in a double-host detection message to be sent to host equipment of other sub systems, and the host equipment of the sub system with the greatest number of member equipment is elected to be the host equipment of the thermal stack system after the topology division.
Description
Technical field
The present invention relates to network communications technology field, relate in particular to main frame electoral machinery, device and the network equipment after a kind of topology divides.
Background technology
The folded technology of thermal reactor is combined into a logical device through using inner link interconnected multiple devices, and simultaneously between internal physical device, the mechanism through hot backup redundancy realizes high availability, solves the availability issue that exists in the folded system of existing cold dome.1), being implemented in the pile system running stack equipment can online adding and withdraw from pile system its major advantage has:, and guarantee that the pile system data forwarding do not interrupt; 2), when piling up main frame and break down (software fault or hardware fault cause software fault) will re-elect the new main frame that piles up automatically, and guarantee that trouble-free device data is transmitted in the pile system and do not interrupt.
At present, the folded technology of common thermal reactor has virtual switch unit (VSU, Virtual Switching Unit), and VSU is a kind of network system Intel Virtualization Technology, supports multiple devices are combined into single virtual unit.Equipment room piles up through virtual switch link (VSL, Virtual Switch Link) connection in the VSU system, sees that from function VSL can be regarded as one and piles up line.The message interaction agreement of moving on the VSL link is virtual switch link protocol (VSLP, Virtual Switch Link Protocol).
In the VSU system; The VSU territory that a plurality of equipment are formed has unique domain identifier (Domain ID); Have only the equipment of the same domain identifier of configuration could form the VSU system, when setting up the VSU system, multiple devices elect an overall main equipment through certain election contest agreement; An overall slave unit, all the other equipment all are overall candidate device.Main equipment is responsible for controlling whole VSU system, and operation chain of command agreement is also participated in data forwarding; Remaining equipment comprises that slave unit and candidate device only participate in data forwarding, does not move the chain of command agreement, and the chain of command data that all receive all will be transmitted to main equipment and handle.Slave unit also receives the state of main equipment simultaneously in real time synchronously, constitutes 1: 1 Hot Spare with overall main equipment.After master malfunction, slave unit will switch to master role, manage whole VSU system.Each member device in the VSU territory all has unique numbering (Switch ID), and this numbering is used to manage member device, and the interface on configuration member's equipment etc.The user need dispose this numbering when equipment is added the VSU system, and guarantees that this numbering is unique in same VSU system.If the VSU system finds the numbering conflict, then distribute voluntarily by main equipment.
Shown in Fig. 1 a and Fig. 1 b; Be respectively the Physical View and the logical view of VSU system; The single logic entity that VSU forms two in the legacy network or multiple devices, the VSU system that for example is arranged in Fig. 1 a convergence-level can regard an independent equipment as and core layer, Access Layer carry out alternately, shown in 1b; Access layer equipment connects through aggregated links and VSU system; Between Access Layer and convergence-level, avoided double-layer loop like this,, also simplified the three-layer network topology in addition because the VSU system has reduced the number of route entity.
After the VSU system buildup is accomplished; Through equipment Topology Management (DTM; Device Topology Manager) equipment in the list management system; Concerning the port of arbitrary equipment, be called the VSU port with the port of miscellaneous equipment in the VSU system sets up that topology is connected (VSL link), not with the miscellaneous equipment port set up topological be connected be called edge interface.During initialization, has only local node in the DTM table, after the VSL link connects (UP); To outwards send hello packet from the VSU port of all connections; Simultaneously, these VSU ports also can be monitored the hello packet of miscellaneous equipment, and each equipment is after receiving hello packet; Therefrom parse topological node information, search in the DTM table whether the respective neighbours node is arranged.If there is not corresponding node, then newly-built node; If have, then upgrade nodal information.First hop neighbor of the source node of hello packet (being directly-connected neighbor) is after receiving hello packet; Can check inlet (being the direct-connected mouth of the source node message outlet) information that whether comprises this node in the message; If do not comprise, first hop neighbor can add to direct-connected information in the message, and the VSU port from non-inlet forwards then; After other member devices are received hello packet like this, can also set up direct-connected information about source node.Hello packet is propagated with the form that floods in topology, ends in the terminal or source node of topology.Comprise member device information all in the whole VSU system (information such as member's number information, member's medium access control (MAC, Media Access Control) address, member's host name that comprise the VSU system) in the final DTM table.
In the VSU system, if link failure or Single Point of Faliure take place, cause the continuous hello packet of not receiving that the opposite end is sent 5 times of equipment, just think that this link is unavailable, thereby when topology is split into two or more little topologys, be called the topology division.As shown in Figure 2, the network topology structure sketch map when the VSU system splits into two VSU subsystems.After the topology division took place, all devices that each VSU subsystem comprises was called the member device of this VSU subsystem, is example with Fig. 2, and the member device of the VSU subsystem on the left side comprises the overall main equipment of the preceding VSU system of division and two candidate device on the left side; The member device of the VSU subsystem on the right comprises the overall slave unit of the preceding VSU system of division and two candidate device on the right.In this case, the overall slave unit in the VSU system originally will switch to the VSU subsystem main equipment on the right, for the ease of with original VSU system in main equipment distinguish; The main equipment of the VSU subsystem after the division is called main process equipment; Can be known that by Fig. 2 the main process equipment of the VSU subsystem on the right is the overall slave unit of original VSU system, the main process equipment of the VSU subsystem on the left side is the overall main equipment of original VSU system; Because the configuration of two master-slave equipments is identical; Make to occur two main frames in the network, two main frames possibly cause following problem: " at three layers, IP address conflict appears; At two layers, generating tree has identical bridge identifier symbol, possibly cause conflict." twin-engined existence works the mischief to network, must be detected, and take corresponding measure, so need two main frames to detect (DAD, Dual Active Detect).DAD detects dedicated link through between the member device of VSU system, setting up DAD; As shown in Figure 3; Be the schematic network structure that detects based on BFD DAD, whether be in the same VSU system through the equipment that detects both link ends, thereby judge whether the VSU system topology has taken place divided.
VSU supports two-way forwarding to detect (BFD; Bidirectional Forwarding Detection) the two main frame testing mechanisms of DAD; BFD DAD detects and realizes through the BFD agreement; For BFD DAD measuring ability is normally moved, except that under three layer interfaces, enabling BFD DAD measuring ability, also need on this interface, dispose DAD IP address.DAD IP address and different place, common IP address are that DAD IP address and member device bind, and all need configuration on the principal and subordinate's member device among the VSU, and must belong to different segment.It is following that BFD DAD detects principle:
(1) when the VSU system normally moves, have only the DAD IP address that disposes on the main equipment to come into force, do not come into force in the DAD IP address that disposes on the slave unit, and the BFD session is in (down) state of closing;
(2) after the division of VSU system, can form two VSU subsystems, all can come into force in the DAD IP address that disposes on the main equipment in the different VSU subsystems, and the BFD session is activated, and can detect two main frame conflicts this moment.
The VSU system is after topology splits into two main frames; Carry out between two main frames after the division according to priority or MAC conduct an election (priority value maximum be main frame, when the priority of member's equipment is the same, then conduct an election according to MAC Address; What MAC Address was minimum is main frame); Elect successful main frame then to carry out data forwarding, another main frame and member device thereof all get into recovery (recovery) state, and the VSL port is all closed (shutdown).
16 member devices of maximum support during VSU realizes at present; If in topological structure as shown in Figure 4, above-mentioned main frame electoral machinery will cause following problem: suppose that equipment 1 priority is the highest, election becomes overall main equipment; Equipment 2 priority the 2nd, election becomes overall slave unit.Link failure occurs between equipment 1 and the equipment 2, after the division of generation topology, occur two VSU subsystems respectively: VSU subsystem 1, member device are original equipment 1; VSU subsystem 2, member device is remaining equipment 2, equipment 3, equipment 4, equipment 5 and equipment 6.Conduct an election according to priority or MAC between VSU subsystem 1 and the VSU subsystem 2; Because equipment 2 priority, cause the 2 election failures of VSU subsystem less than equipment 1, thereby cause equipment 2-6 all to get into the recovery state, only remaining equipment 1 continues as main frame, carries out data forwarding.After the topology division, available devices (having only equipment 1) quantity sharply reduces like this, because network available devices negligible amounts has caused network performance decline, the equipment of One's name is legion is in down state on the other hand, causes the waste of device resource.
Summary of the invention
The embodiment of the invention provides main frame electoral machinery, device and the network equipment after a kind of topology division, in order to make full use of the device resource after topology divides, improves network performance.
The embodiment of the invention provides the main frame electoral machinery after a kind of topology division, comprising:
After the folded system topological of thermal reactor was split into a plurality of subsystems, the main process equipment of each subsystem was confirmed the member device number of this subsystem; And
With the member device number of this subsystem of determining, be carried at the main process equipment that sends to other subsystem in two main frame detection messages; And
The main process equipment of the subsystem that election member device number is maximum is the main process equipment of topology division after heat pile system.
The embodiment of the invention provides the main frame voting device after a kind of topology division, comprising:
Confirm the unit, be used for after the topology division takes place the folded system of thermal reactor, confirming the member device number of this device place subsystem;
Transmitting element is used for the member device number of determining, and is carried at the main process equipment that sends to other subsystem in two main frame detection messages;
The election unit is used to elect the main process equipment of the main process equipment of the maximum subsystem of member device number for topology division after heat pile system.
The embodiment of the invention provides a kind of network equipment, comprises the main frame voting device after above topology divides.
Main frame electoral machinery, device and the network equipment after the topology division that the embodiment of the invention provides; After the topology division took place in the thermal reactor system of folding, the main process equipment of each subsystem after the division was confirmed respectively self to belong to the member device number of subsystem, simultaneously through carrying the member device data of determining in mutual each other two main frame detection messages; Like this; Through consultation, the main process equipment of the election member subsystem that number is many at double is the system host equipment after dividing between each main process equipment, thereby can improve the quantity of the folded system of the thermal reactor available devices after the division; Reduced the waste of device resource; Simultaneously, because available devices quantity increases, make network performance more excellent.
Other features and advantages of the present invention will be set forth in specification subsequently, and, partly from specification, become obvious, perhaps understand through embodiment of the present invention.The object of the invention can be realized through the structure that in the specification of being write, claims and accompanying drawing, is particularly pointed out and obtained with other advantages.
Description of drawings
Fig. 1 a is in the prior art, the Physical View of VSU system;
Fig. 1 b is in the prior art, the logical view of VSU system;
Fig. 2 is in the prior art, and the network topology after the division of VSU system is sketch map as a result;
Fig. 3 is in the prior art, based on the schematic network structure of BFD DAD detection;
Fig. 4 is in the prior art, and the network topology after the division of a kind of in addition VSU system is sketch map as a result;
Fig. 5 is in the embodiment of the invention, the implementing procedure sketch map of main frame electoral machinery;
Fig. 6 is in the embodiment of the invention, the BFD message format sketch map after the expansion;
Fig. 7 is in the embodiment of the invention, confirms the implementing procedure sketch map of the member device number of each subsystem;
Fig. 8 is in the embodiment of the invention, and the VSU system takes place to carry out the schematic flow sheet that main frame is elected after the topology division;
Fig. 9 is in the embodiment of the invention, the structural representation of main frame voting device.
Embodiment
Because the main frame election mechanism after the generation topology division of the folded system of existing thermal reactor exists and reduces network available devices quantity; Cause the waste of available devices resource on the one hand; The problem that also can cause the network performance bottleneck on the other hand, therefore, in order to improve the quantity that division back available devices takes place the folded system of thermal reactor; Improve the performance of network, the embodiment of the invention provides the main frame electoral machinery after a kind of topology division.
Below in conjunction with Figure of description the preferred embodiments of the present invention are described; Be to be understood that; Preferred embodiment described herein only is used for explanation and explains the present invention; And be not used in qualification the present invention, and under the situation of not conflicting, embodiment and the characteristic among the embodiment among the present invention can make up each other.
Suppose that the topology division takes place in original thermal reactor system of folding, obtain a plurality of subsystems, during owing to the division of generation topology; Have only the main process equipment of each subsystem to be in active state; The main process equipment of each subsystem need carry out two main frames and detect, electing the main frame of division after heat pile system, for the quantity of the available devices that increases the folded system of thermal reactor after the division; In the embodiment of the invention; Carry member device number separately at the main process equipment of each subsystem in through mutual each other two main frame detection messages, like this, make each main process equipment when the main frame of election division after heat pile system; Can select the main frame of the main process equipment of the maximum subsystem of member's number of devices with reference to the member device number of system separately as division after heat pile system.Concrete, as shown in Figure 5, the implementing procedure sketch map for the main frame electoral machinery may further comprise the steps:
After S501, the folded system topological of thermal reactor were split into a plurality of subsystems, the main process equipment of each subsystem was confirmed the member device number of this subsystem;
Wherein, the folded system of the thermal reactor that relates among the embodiment one includes but not limited to the system into VSU.
The member device number of S502, this subsystem that will determine is carried at the main process equipment that sends to other subsystem in two main frame detection messages;
Wherein, Can adopt following dual mode to carry out DAD (two main frame detection) between each main process equipment: BFD (two-way forwarding detection) detection mode and LACP (link aggregate control protocol) detection mode; Wherein, When adopting BFD DAD, two main frame detection messages mutual between each main process equipment are the BFD message.Below be that the BFD message is that example describes with two main frame detection messages.
Can know equipment number of members each other in order to make each main process equipment; Need expand the BFD message in the embodiment of the invention, increase a field, be used to carry member device number in this subsystem; For the ease of describing; The field that increases is called Member ID, and concrete, the BFD message format after the expansion is as shown in Figure 6.Wherein:
The Vers:BFD protocol version comprises 0 and 1, is 1 at present;
Diag: provide the local reason that forwards other states for the last time from the UP state to, comprising: 0-does not have diagnostic message, and 1-controls overtime detection; The 2-echo function lost efficacy, 3-neighbor advertisement session Down, and 4-forwarding face resets; The 5-channel failure, the 6-interface channel lost efficacy, and 7-manages Down;
The local state of Sta:BFD, value is: 0 represents AdminDown, and 1 represents Down, and 2 represent Init, and 3 represent Up;
P: when parameter changes, transmit leg the BFD message is mid-should sign, recipient's this message that must make an immediate response;
F: must be in the back message using of response P flag set with the F flag set;
C: forwarding/control separation flags, in case set, the variation of control plane does not influence BFD and detects, as: control plane is OSPF, and when restarting/GR (smooth restarting), BFD can continue to detect Link State as OSPF (SPF of exploitation formula);
A: the authentication sign, on behalf of session, set need verify;
D: on behalf of the transmit leg expectation, query requests, set adopt query pattern that link is detected;
M: be used for using when point of application is to multiple spot in the future, must be provided with 0 at present;
Detect Mult: detect overtime multiple, be used for the detection side and calculate the detection time-out time;
Length: message length;
My Discriminator:BFD session connection local terminal identifier;
Your Discriminator:BFD session connection distal marker symbol;
Desired Min Tx Interval: the local minimum BFD message of supporting sends at interval;
Required Min RX Interval: the local minimum BFD message of supporting receives at interval;
Required Min Echo RX Interval: the local minimum Echo message of supporting receives (if the Echo function is not supported in this locality, then being provided with 0) at interval;
The intrasystem equipment number of members of Member ID sign book.
The main process equipment of S503, subsystem that election member device number is maximum be the main process equipment that topology divides the after heat pile system.
During practical implementation, in step S501, folded system divides when thermal reactor, obtain a plurality of subsystems after, the DTM of the main process equipment of each subsystem only comprises self node in showing, its numerical value is 1.At this moment; Each main process equipment will send probe messages to the intrasystem miscellaneous equipment of book; And receive the probe messages that miscellaneous equipment sends, concrete, each main process equipment will be from self all ports that are in connection (UP) state outwards send probe messages with the mode that floods; Concrete, this probe messages can be hello packet.Simultaneously, these ports also can be monitored the probe messages that Peer-Port sends, after ports having receives the probe messages of Peer-Port transmission; This main process equipment is the fetch equipment sign therefrom, and searches in the local DTM table whether have this device identification, if do not exist; To in the DTM table, set up new topological node; And,, only refresh topological node information and get final product if exist with member device number increase by 1.Probe messages is propagated with the form that floods in network topology, ends in the terminal or source node of topology.Like this, over time, when reaching topological stablizing, the member device number in the DTM table is the intrasystem member device number of book.
Based on this, as shown in Figure 7, among the step S501, can confirm the member device number of each subsystem according to following steps:
Member device number in the equipment Topology Management DTM table of the main process equipment initialization of S701, each subsystem self is 1;
S702, each main process equipment outwards send probe messages, and receive the probe messages that the intrasystem miscellaneous equipment of book sends;
S703, each main process equipment are resolved the probe messages that receives, and read the device identification of carrying in this probe messages;
S704, each main process equipment judge whether this device identification exists in the DTM table of self, if, execution in step S705, otherwise, execution in step S706;
S705, refresh the local topology nodal information, the member device number remains unchanged in the DTM table, and execution in step S707;
S706, set up new topological node, the member device number adds 1 in the DTM table;
It is stable that S707, each main process equipment judge whether network reaches topology, if, execution in step S708, otherwise execution in step S702;
During practical implementation; Each main process equipment is monitored probe messages repeatedly, and whether the device identification that comprises in definite probe messages have newly-increased device identification, if there is not the newly added equipment sign in the certain hour section; Explain that then network is in the topological convergence state, it is stable to reach topology.
S708, the member device number when each main process equipment is stablized topology, in the DTM table are the member device number of this subsystem.
Preferably; In two main frame detection messages, can also carry the precedence information and the mac address information of main process equipment, like this, in step S503; When if the number of members of each subsystem after the topology division is identical; Can elect the main frame of division after heat pile system in such a way:, select the main frame of the highest main process equipment of priority, if the priority of each main process equipment is identical as division after heat pile system according to the precedence information of the main process equipment that carries in two main frame detection messages; Then, select the main frame of the minimum main process equipment of MAC Address for division after heat pile system according to the mac address information of the main process equipment that carries in two main frame detection messages.
For a better understanding of the present invention, below be that the VSU system is an example with the folded system of thermal reactor, the implementation process of the embodiment of the invention is described.
As shown in Figure 8, in the embodiment of the invention, the VSU system takes place to carry out the schematic flow sheet that main frame is elected after the topology division, may further comprise the steps:
S801, VSU system are split into a plurality of VSU subsystems;
During practical implementation, when the topology division takes place in the VSU system, will activate the two main frames of BFD and detect.
The main process equipment of S802, each VSU subsystem is confirmed the equipment number of members of this subsystem respectively;
Concrete, each main process equipment can be confirmed the intrasystem equipment number of members of book according to step S601～step S608.
Exchange BFD message between S803, each main process equipment;
Wherein, in the BFD message, carry the intrasystem equipment number of members of book, the precedence information of self and the mac address information of self.
Whether the equipment number of members in S804, each subsystem of comparison is identical, if, execution in step S805, otherwise, execution in step S806;
Whether the priority of the main process equipment of S805, each subsystem of continuation comparison is identical, if, execution in step S807, otherwise execution in step S808;
The main process equipment of S806, subsystem that election equipment number of members is maximum is the main frame of division after heat pile system, and flow process finishes;
The size of the MAC Address of the main process equipment of S807, each subsystem of comparison, and the main process equipment of election MAC Address minimum is the main frame of division after heat pile system, flow process end;
S808, the main process equipment that election priority is the highest are the main frame of division after heat pile system.
Below to be split into two VSU subsystems with the VSU system be that example describes, in the present embodiment, suppose that the network topology structure figure of VSU system is as shown in Figure 4 before the division: equipment 1,2,3,4,5,6 is formed the VSU systems; Equipment 1 priority is the highest, and equipment 2 priority are inferior high, like this; When VSU system election main frame, equipment 1 election is overall main equipment, and equipment 2 elections are overall slave unit; VSL link occurs fault between equipment 1 and equipment 2 causes the VSU system to be split into VSU subsystem 1 and VSU subsystem 2, wherein; VSU subsystem 1 comprises equipment 1; Its main process equipment is an equipment 1, and VSU subsystem 2 comprises equipment 2,3,4,5,6, and its main process equipment is an equipment 2.Equipment 1 confirms that the member device number of VSU subsystem 1 is 1; Equipment 2 confirms that the member device number of VSU subsystem 2 is 5; And activate two main frames and detect, carrying out two main frames when detecting, mutual BFD message between equipment 1 and the equipment 2; And in the BFD message, carry the member device number that belongs to subsystem separately; Because the member device number of VSU subsystem 2 is more than the member device number of VSU subsystem 1, so the main process equipment of VSU subsystem 2 (equipment 2) will be elected the main process equipment into division after heat pile system, (equipment 2 and equipment 3,4,5,6 are proceeded data forwarding to the member device of VSU subsystem 2; And the member device of VSU subsystem 1 (equipment 1) returns to form entering, and closes other all of the port except that VSL link member port.
In the embodiment of the invention; Main frame voting machine when the topology division takes place the folded system of thermal reactor is made as: at first according to the member device number election main frame of each subsystem of division back, when the member device number is identical, conduct an election according to the priority of the main process equipment of each subsystem; When the priority of each main process equipment is identical; Then continue to conduct an election according to the MAC Address of each main process equipment, what MAC Address was minimum will be elected successful subsystem will substitute the folded system of original thermal reactor and carry out data forwarding by the main frame of election for division after heat pile system; Promptly each member device of this subsystem will be proceeded data forwarding; And the subsystem of election failure, its each member device returns to form entering, and closes all of the port except that VSL link member port.Thereby, guaranteed that the main process equipment of the subsystem that topological division back equipment number of members is maximum can have been increased the number of available devices by the main frame of election for division after heat pile system, reduce the waste of device resource, and improved network performance.
Based on same inventive concept; The main frame voting device and the network equipment after a kind of topology divides also are provided in the embodiment of the invention; Because the principle that this device and the network equipment are dealt with problems is similar with the main frame electoral machinery after topology divides; Therefore the enforcement of this device can repeat part and repeat no more referring to the enforcement of method.
As shown in Figure 9, the structural representation of the main frame voting device after the topology division that provides for the embodiment of the invention comprises:
Transmitting element 902 is used for the member device number of determining, and is carried at the main process equipment that sends to other subsystem in two main frame detection messages;
In the practical implementation, confirm that unit 901 can comprise:
The initialization subelement, the member device number that is used for the equipment Topology Management DTM table of this device of initialization is 1;
Receive subelement, be used to receive the probe messages that is in the intrasystem miscellaneous equipment transmission of book;
Read subelement, be used to resolve the probe messages that the reception subelement receives, read the device identification of carrying in this probe messages;
First confirms subelement, when being used for confirming reading device identification that subelement reads and not having the equipment Topology Management DTM table of this device, the member device number in the DTM table is added 1;
Second confirms subelement, is used for confirming when topology stablize, the member device number of said DTM table is the member device number of this subsystem.
During practical implementation, can also carry the precedence information and the mac address information of main process equipment in the main frame detection messages; Election unit 903 can also be used for when if the member device number of each subsystem is identical, and according to the precedence information of the main process equipment of each subsystem, the high main process equipment of election priority is as the main process equipment of topology division after heat pile system; And when if the priority of the main process equipment of each system is identical, according to the mac address information of the main process equipment of each subsystem, the little main process equipment of election MAC Address is as the main process equipment of topology division after heat pile system.
In the practical implementation, the main frame voting device after the topology division can also comprise:
The data forwarding unit is used for when the election of this device quilt is divided the main process equipment of after heat pile system for topology, and the member device that belongs to subsystem with self is proceeded data forwarding together; And
Recovery unit is used for when this device is not divided the main process equipment of after heat pile system by election for topology, gets into together with the member device that self belongs to subsystem to return to form.
Need to prove; Main frame voting device after the topology division that the embodiment of the invention provides can be arranged in the network equipment of forming the folded system of thermal reactor; Main frame voting device after the topology division is arranged on a kind of preferably implementation method of just dividing invention embodiment in the network equipment of forming the folded system of thermal reactor; During practical implementation, the main frame voting device after the topology division also can independently be provided with.
Main frame electoral machinery, device and the network equipment after the topology division that the embodiment of the invention provides; After the topology division took place in the thermal reactor system of folding, the main process equipment of each subsystem after the division was confirmed respectively self to belong to the member device number of subsystem, simultaneously through carrying the member device data of determining in mutual each other two main frame detection messages; Like this; Through consultation, the main process equipment of the election member subsystem that number is many at double is the system host equipment after dividing between each main process equipment, thereby can improve the quantity of the folded system of the thermal reactor available devices after the division; Reduced the waste of device resource; Simultaneously, because available devices quantity increases, make network performance more excellent.
Those skilled in the art should understand that embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of the embodiment of complete hardware embodiment, complete software implementation example or combination software and hardware aspect.And the present invention can be employed in the form that one or more computer-usable storage medium (including but not limited to magnetic disc store, CD-ROM, optical memory etc.) that wherein include computer usable program code go up the computer program of implementing.
The present invention is that reference is described according to the flow chart and/or the block diagram of method, equipment (system) and the computer program of the embodiment of the invention.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or the block diagram and/or square frame and flow chart and/or the block diagram and/or the combination of square frame.Can provide these computer program instructions to the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce a machine, make the instruction of carrying out through the processor of computer or other programmable data processing device produce to be used for the device of the function that is implemented in flow process of flow chart or a plurality of flow process and/or square frame of block diagram or a plurality of square frame appointments.
These computer program instructions also can be stored in ability vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work; Make the instruction that is stored in this computer-readable memory produce the manufacture that comprises command device, this command device is implemented in the function of appointment in flow process of flow chart or a plurality of flow process and/or square frame of block diagram or a plurality of square frame.
These computer program instructions also can be loaded on computer or other programmable data processing device; Make on computer or other programmable devices and to carry out the sequence of operations step producing computer implemented processing, thereby the instruction of on computer or other programmable devices, carrying out is provided for being implemented in the step of the function of appointment in flow process of flow chart or a plurality of flow process and/or square frame of block diagram or a plurality of square frame.
Although described the preferred embodiments of the present invention, in a single day those skilled in the art get the basic inventive concept could of cicada, then can make other change and modification to these embodiment.So accompanying claims is intended to be interpreted as all changes and the modification that comprises preferred embodiment and fall into the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, belong within the scope of claim of the present invention and equivalent technologies thereof if of the present invention these are revised with modification, then the present invention also is intended to comprise these changes and modification interior.
Claims (10)
1. the main frame electoral machinery after a topology divides is characterized in that, comprising:
After the folded system topological of thermal reactor was split into a plurality of subsystems, the main process equipment of each subsystem was confirmed the member device number of this subsystem respectively; And
With the member device number of this subsystem of determining, be carried at the main process equipment that sends to other subsystem in two main frame detection messages; And
The main process equipment of the subsystem that election member device number is maximum is the main process equipment of topology division after heat pile system.
2. method according to claim 1 is characterized in that the main process equipment of each subsystem is confirmed the member device number of this subsystem, specifically comprises:
Member device number in the equipment Topology Management DTM table of the main process equipment initialization of each subsystem self is 1; And
Each main process equipment receives the probe messages that the intrasystem miscellaneous equipment of book sends; And
The probe messages that parsing receives reads the device identification of carrying in the said probe messages; And
When confirming that said device identification does not exist in self the equipment Topology Management DTM table, the member device number in the DTM table is added 1; And
Member device number when confirming topological stablizing, in the said DTM table is the member device number of this subsystem.
3. the method for claim 1 is characterized in that, also carries the precedence information and the mac address information of main process equipment in the said pair of main frame detection messages; And
Said method also comprises:
When if the member device number of each subsystem is identical, according to the precedence information of the main process equipment of each subsystem, the high main process equipment of election priority is as the main process equipment of topology division after heat pile system; And
When if the priority of the main process equipment of each subsystem is identical, according to the mac address information of the main process equipment of each subsystem, the little main process equipment of election MAC Address is as the main process equipment of topology division after heat pile system.
4. like claim 1,2 or 3 described methods, it is characterized in that, also comprise:
The main process equipment and the member device thereof of topology division after heat pile system are proceeded data forwarding, and remaining main process equipment and member device thereof get into and return to form.
5. the method for claim 1 is characterized in that, the folded system of said thermal reactor comprises virtual switch unit VSU system, and said pair of main frame detection messages comprises that two-way forwarding detects the BFD message.
6. the main frame voting device after a topology divides is characterized in that, comprising:
Confirm the unit, be used for after the topology division takes place the folded system of thermal reactor, confirming the member device number of this device place subsystem;
Transmitting element is used for the member device number of determining, and is carried at the main process equipment that sends to other subsystem in two main frame detection messages;
The election unit is used to elect the main process equipment of the main process equipment of the maximum subsystem of member device number for topology division after heat pile system.
7. device as claimed in claim 6 is characterized in that, said definite unit comprises:
The initialization subelement, the member device number that is used for the equipment Topology Management DTM table of this device of initialization is 1;
Receive subelement, be used to receive the probe messages that the intrasystem miscellaneous equipment of book sends;
Read subelement, be used to resolve the probe messages that said reception subelement receives, read the device identification of carrying in the said probe messages;
First confirms subelement, is used for confirming saidly reading device identification that subelement reads when not having the equipment Topology Management DTM table of this device, and the member device number in the DTM table is added 1;
Second confirms subelement, is used for confirming when topology stablize, the member device number of said DTM table is the member device number of this subsystem.
8. device as claimed in claim 6 is characterized in that, also carries the precedence information and the mac address information of main process equipment in the said pair of main frame detection messages; And
Said election unit also is used for when if the member device number of each subsystem is identical, and according to the precedence information of the main process equipment of each subsystem, the high main process equipment of election priority is as the main process equipment of topology division after heat pile system; And when if the priority of the main process equipment of each system is identical, according to the medium access control mac address information of the main process equipment of each subsystem, the little main process equipment of election MAC Address is as the main process equipment of topology division after heat pile system.
9. like claim 6,7 or 8 described devices, it is characterized in that, also comprise:
The data forwarding unit is used for when the election of this device quilt is divided the main process equipment of after heat pile system for topology, and the member device that belongs to subsystem with self is proceeded data forwarding together; And
Recovery unit is used for when this device is not divided the main process equipment of after heat pile system by election for topology, gets into together with the member device that self belongs to subsystem to return to form.
10. a network equipment is characterized in that, comprises the described device of the arbitrary claim of claim 6～9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100749995A CN102594610A (en) | 2012-03-20 | 2012-03-20 | Host election method after topology division as well as device and network equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100749995A CN102594610A (en) | 2012-03-20 | 2012-03-20 | Host election method after topology division as well as device and network equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102594610A true CN102594610A (en) | 2012-07-18 |
Family
ID=46482830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012100749995A Pending CN102594610A (en) | 2012-03-20 | 2012-03-20 | Host election method after topology division as well as device and network equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102594610A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103036760A (en) * | 2012-12-18 | 2013-04-10 | 迈普通信技术股份有限公司 | Topology convergence method and member equipment of stacking system |
| CN104579809A (en) * | 2013-10-22 | 2015-04-29 | 华为技术有限公司 | Detection method and device for stacking splitting |
| CN106936646A (en) * | 2017-04-24 | 2017-07-07 | 新华三技术有限公司 | The determination method and device of main control board |
| CN107295056A (en) * | 2016-04-05 | 2017-10-24 | 瞻博网络公司 | Agreement is performed on some links of the aggregated links using aggregated links address |
| CN109395418A (en) * | 2018-11-13 | 2019-03-01 | 上海葡萄纬度科技有限公司 | Bus master-slave equipment determines method and system and its medium and bus apparatus |
| CN110086581A (en) * | 2019-05-30 | 2019-08-02 | 深圳市中航比特通讯技术有限公司 | The synchronous method and apparatus of a main prepare more data under a kind of network integration scene |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101610182A (en) * | 2009-06-26 | 2009-12-23 | 杭州华三通信技术有限公司 | Multi-primary apparatus conflict detection method and stack member apparatus in piling up |
| CN101714932A (en) * | 2009-12-03 | 2010-05-26 | 杭州华三通信技术有限公司 | MAD testing method and device for IRF stacker |
| CN102209008A (en) * | 2011-05-18 | 2011-10-05 | 杭州华三通信技术有限公司 | Multi-activation detection method and device used for intelligent elastic framework |
| CN102315975A (en) * | 2011-10-17 | 2012-01-11 | 杭州华三通信技术有限公司 | Fault processing method based on intelligent resilient framework (IRF) system and equipment thereof |
| CN102340434A (en) * | 2011-07-07 | 2012-02-01 | 杭州华三通信技术有限公司 | Multihoming access-based loop avoidance method and edge devices |
-
2012
- 2012-03-20 CN CN2012100749995A patent/CN102594610A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101610182A (en) * | 2009-06-26 | 2009-12-23 | 杭州华三通信技术有限公司 | Multi-primary apparatus conflict detection method and stack member apparatus in piling up |
| CN101714932A (en) * | 2009-12-03 | 2010-05-26 | 杭州华三通信技术有限公司 | MAD testing method and device for IRF stacker |
| CN102209008A (en) * | 2011-05-18 | 2011-10-05 | 杭州华三通信技术有限公司 | Multi-activation detection method and device used for intelligent elastic framework |
| CN102340434A (en) * | 2011-07-07 | 2012-02-01 | 杭州华三通信技术有限公司 | Multihoming access-based loop avoidance method and edge devices |
| CN102315975A (en) * | 2011-10-17 | 2012-01-11 | 杭州华三通信技术有限公司 | Fault processing method based on intelligent resilient framework (IRF) system and equipment thereof |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103036760A (en) * | 2012-12-18 | 2013-04-10 | 迈普通信技术股份有限公司 | Topology convergence method and member equipment of stacking system |
| CN103036760B (en) * | 2012-12-18 | 2016-01-06 | 迈普通信技术股份有限公司 | The topological convergence method of pile system and member device |
| CN104579809A (en) * | 2013-10-22 | 2015-04-29 | 华为技术有限公司 | Detection method and device for stacking splitting |
| CN104579809B (en) * | 2013-10-22 | 2018-05-04 | 华为技术有限公司 | The detection method and equipment of a kind of stacking splitting |
| CN107295056A (en) * | 2016-04-05 | 2017-10-24 | 瞻博网络公司 | Agreement is performed on some links of the aggregated links using aggregated links address |
| CN107295056B (en) * | 2016-04-05 | 2020-10-16 | 瞻博网络公司 | Method for executing a protocol on a component link of an aggregated link, data forwarding device, and non-transitory storage device |
| CN106936646A (en) * | 2017-04-24 | 2017-07-07 | 新华三技术有限公司 | The determination method and device of main control board |
| CN106936646B (en) * | 2017-04-24 | 2019-12-06 | 新华三技术有限公司 | method and device for determining main master control board |
| CN109395418A (en) * | 2018-11-13 | 2019-03-01 | 上海葡萄纬度科技有限公司 | Bus master-slave equipment determines method and system and its medium and bus apparatus |
| CN109395418B (en) * | 2018-11-13 | 2022-02-11 | 上海葡萄纬度科技有限公司 | Bus master-slave equipment determining method and system, medium thereof and bus equipment |
| CN110086581A (en) * | 2019-05-30 | 2019-08-02 | 深圳市中航比特通讯技术有限公司 | The synchronous method and apparatus of a main prepare more data under a kind of network integration scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105933391B (en) | A kind of node expansion method, apparatus and system | |
| CN102724069B (en) | Collision detection method, device and network device of dual-master device in thermal staking system | |
| CN102594610A (en) | Host election method after topology division as well as device and network equipment | |
| CN107846358B (en) | Data transmission method, device and network system | |
| JP6283361B2 (en) | Systems and methods for supporting degraded fat tree discovery and routing in a middleware machine environment | |
| WO2018171565A1 (en) | Disaster recovery deployment method, device and system | |
| CN102624635B (en) | Method and device for realizing graceful restart | |
| CN105808158B (en) | Method and apparatus for grouping multiple SAS expanders to form a single cohesive SAS expander | |
| WO2017193966A1 (en) | Link switching method for service in storage system, and storage device | |
| WO2012071920A1 (en) | Method, system, token conreoller and memory database for implementing distribute-type main memory database system | |
| CN104769886A (en) | Adding device-wide capabilities and parameters to split-architecture devices | |
| CN106330786A (en) | MAC address synchronization method, apparatus and system | |
| US9614749B2 (en) | Data processing system and method for changing a transmission table | |
| CN103002065A (en) | Method and device for sharing internet protocol (IP) address by host device and standby device | |
| CN101702678B (en) | Star-shaped stack system and method thereof | |
| CN106953767A (en) | A kind of network-building method of equipment room, apparatus and system | |
| CN102647304A (en) | Synchronizing method of address resolution protocols and device | |
| WO2016082078A1 (en) | Path management system, device and method | |
| CN104767665A (en) | Ring communication network master station redundancy method, device and system | |
| CN103036702A (en) | Network segment crossing N+1 backup method and network segment crossing N+1 backup device | |
| CN104410527A (en) | Topological detection method, exchanger and heat stacking system | |
| CN114285755A (en) | Cross-subnet interaction method and device, electronic equipment and storage medium | |
| CN107547374B (en) | Aggregation route processing method and device | |
| CN104579809B (en) | The detection method and equipment of a kind of stacking splitting | |
| CN114124803B (en) | Device management method and device, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120718 |