CN101707555B - Data interactive method and device in stack system - Google Patents
Data interactive method and device in stack system Download PDFInfo
- Publication number
- CN101707555B CN101707555B CN 200910223865 CN200910223865A CN101707555B CN 101707555 B CN101707555 B CN 101707555B CN 200910223865 CN200910223865 CN 200910223865 CN 200910223865 A CN200910223865 A CN 200910223865A CN 101707555 B CN101707555 B CN 101707555B
- Authority
- CN
- China
- Prior art keywords
- opposite end
- master control
- member device
- end member
- control borad
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Power Sources (AREA)
Abstract
The invention discloses a data interactive method in a stack system. The method comprises the following steps: a stack member equipment acquires the state of a main control board of the opposite end member equipment; whether the main control board of the opposite end member equipment can be used or not is judged according to the state of the main control board; when the judging result is 'yes', the stack member equipment and the opposite end member equipment interact data flow and control flow; and when the judging result is 'no', the stack member equipment and the opposite end member equipment interact data flow. The invention guarantees continuous transmission of data and improves the reliability and availability of the member equipment.
Description
Technical field
The present invention relates to communication technical field, particularly relate to data interactive method and device in a kind of pile system.
Background technology
Along with the rapid increase of network size, the technology of piling up is arisen at the historic moment.Wherein, the technology of piling up is that two or many network equipments are coupled together by stack port, forms pile system.From in logic, the network equipment that forms that is stacked is equivalent to same equipment, and the user management pile system is just as equipment of management, and promptly the user is by managing this pile system, thereby realizes all devices in piling up is managed.Wherein, the technology of piling up can provide high availability, enhanced scalability and streamlining management, has obtained using widely in data center, enterprise key net.
In the prior art, the technology of piling up that is applied in data center mainly comprises IRF (IntelligentResilient Framework, intelligent resilient infrastructure) technology and VSS (Virtual Switching System, virtual exchange system) technology etc.Wherein, the VSS technology is the technology of piling up that is applied to frame type equipment; And the IRF technology is promptly supported piling up of box-shaped device, also supports piling up of frame type equipment.
As shown in Figure 1,,, can significantly improve the exchange capacity of complete machine, improve the reliability of system then, shorten the recovery time of fault by the pile system after using this to pile up for a kind of schematic diagram that piles up of supporting two frame type equipments (machine frame).Further, in the pile system of two frame type equipments of above-mentioned support, each frame type equipment supports a master control borad at least (in the IRF technology, support each frame type equipment that two master control borads are arranged at most, in the VSS technology, only support each frame type equipment that a master control borad is arranged), promptly this pile system (being made up of two frame type equipments) has two master control borads at least.
In summary it can be seen that above-mentioned two kinds of technology all are that two or many frame type equipments are piled up, thereby are virtualized into a logical device.Wherein, this frame type equipment is the member device in the pile system, and in pile system, forwarding of data is independently to be realized by the power board of each member device; And master control borad (or forwarding engine) is responsible for whole piling up managed and control.
Existing piling up in the technology, for the situation of having only a master control borad in the frame type equipment, when this main control board occurs fault, then the flow of this frame type equipment of approach will interrupt, and causes this frame type equipment unavailable.As shown in Figure 2, for the situation of supporting two master control borads in the frame type equipment, for equipment 1 (main frame), when the master control borad in the equipment 1 all damages (being that master control borad master and slave1 all damage), then the flow of approach equipment 1 will interrupt, and causes equipment 1 to use.Same, when the master control borad of equipment 2 all damaged, then the flow of approach equipment 2 also can interrupt, and caused equipment 2 to use.
But, under application scenarioss such as data center, enterprise key net, more and more higher requirement has been proposed for availability, the uninterrupted forwarding of pile system; Prior art will cause professional interruption of transmitting when equipment 1 and/or equipment 2 can not use, can not satisfy the business need of uninterrupted forwarding.
Summary of the invention
The invention provides data interactive method and device in a kind of pile system, to guarantee professional uninterrupted forwarding.
In order to achieve the above object, the present invention proposes the data interactive method in a kind of pile system, be applied to comprise in the pile system of at least two member devices, at least comprise master control borad, interface board and power board in the described member device, described interface board is connected with the master control borad of self by described power board, described power board and described master control borad can both be handled data stream, described power board is independent of described master control borad work, wherein, described at least two member devices are respectively stack member apparatus and opposite end member device, said method comprising the steps of:
Described stack member apparatus obtains the master control board state of described opposite end member device;
Described stack member apparatus judges according to described master control board state whether the master control borad of described opposite end member device can use;
When judged result when being, described stack member apparatus and described opposite end member device interaction data stream and control flows; When judged result for not the time, described stack member apparatus flows with described opposite end member device interaction data.
Described stack member apparatus and described opposite end member device interaction data stream specifically comprise:
Described opposite end member device sends data flow by self power board to described stack member apparatus, or receives data flow from described stack member apparatus by self power board;
Stack member apparatus and the described opposite end mutual control flows of member device specifically comprise:
Described opposite end member device sends control flows by self master control borad to described stack member apparatus, or receives control flows from described stack member apparatus by self master control borad.
The out of use reason of master control borad comprises one or more in following:
Main control board occurs fault; Master control borad and slave board are switched; Master control borad is restarted; Slave board is restarted;
Described stack member apparatus is judged according to described master control board state whether the master control borad of described opposite end member device can use and is comprised:
Described stack member apparatus judges according to described master control board state whether the master control borad of described opposite end member device breaks down; Be specially:
Described stack member apparatus is safeguarded the master control borad tabulation of described opposite end member device;
Described stack member apparatus upgrades the master control borad tabulation of described opposite end member device according to the master control board state of described opposite end member device;
Described stack member apparatus judges according to the master control borad tabulation of the opposite end member device after upgrading whether all master control borads of described opposite end member device all break down.
When the master control borad of described opposite end member device can not use, described method also comprised: described opposite end member device switches to data flow path with described control flows;
When the master control borad that described stack member apparatus is judged described opposite end member device can not use, the master control borad of described stack member apparatus is handled the control flows in the member device data flow path of described opposite end, and described opposite end member device is managed and controls.
Judged result is not for the time, and described stack member apparatus is that NAMB piles up pattern, and described stack member apparatus also comprises after flowing with described opposite end member device interaction data:
Under NAMB piled up pattern, when described stack member apparatus gets access to when having master control borad to recover in the member device of described opposite end, described stack member apparatus was converted to and piles up pattern, and described stack member apparatus flows and control flows with described opposite end member device interaction data;
Under NAMB piles up pattern, when the state that gets access to all stacking member ports in the member device of described opposite end when described stack member apparatus is fault, described stack member apparatus is converted to single cpu mode, and described stack member apparatus and described opposite end member device do not carry out alternately.
Data interaction device in a kind of pile system, be applied to comprise in the pile system of at least two member devices, at least comprise master control borad, interface board and power board in the described member device, described interface board is connected with the master control borad of self by described power board, described power board and described master control borad can both be handled data stream, described power board is independent of described master control borad work, wherein, described at least two member devices are respectively stack member apparatus and opposite end member device, and described device comprises:
Acquisition module is used to obtain the master control board state of described opposite end member device;
Judge module electrically connects with described acquisition module, is used for judging according to the master control board state that described acquisition module obtains whether the master control borad of described opposite end member device can use;
Processing module electrically connects with described judge module, be used for when the judged result of described judge module when being, flow and control flows with described opposite end member device interaction data; When the judged result of described judge module for not the time, flow with described opposite end member device interaction data.
Described processing module specifically is used for, receive the data flow that described opposite end member device sends to described stack member apparatus by self power board, or, send data flow to described opposite end member device, receive described data flow by described opposite end member device by self power board;
Receive the control flows that described opposite end member device sends to described stack member apparatus by self master control borad, or, send control flows to described opposite end member device, receive described control flows by described opposite end member device by self control board.
The out of use reason of master control borad comprises one or more in following:
Main control board occurs fault; Master control borad and slave board are switched; Master control borad is restarted; Slave board is restarted;
Described judge module specifically is used for, and judges according to described master control board state whether the master control borad of described opposite end member device breaks down; Be specially:
Safeguard the master control borad tabulation of described opposite end member device; Upgrade the master control borad tabulation of described opposite end member device according to the master control board state of described opposite end member device; And judge according to the master control borad tabulation of the opposite end member device after upgrading whether all master control borads of described opposite end member device all break down.
Described processing module also is used for, when the master control borad of judging described opposite end member device can not use, by the master control borad that uses self control flows in the member device data flow path of described opposite end is handled, and described opposite end member device is managed and controls; Wherein, the control flows in the described data flow path is that described opposite end member device switches to described data flow path.
The judged result of judge module is not for the time, and described stack member apparatus is that NAMB piles up pattern, and described processing module also is used for:
Under NAMB piles up pattern, when described stack member apparatus gets access to when having master control borad to recover in the member device of described opposite end, described stack member apparatus is converted to piles up pattern, and with described opposite end member device interaction data stream and control flows;
Under NAMB piles up pattern, when the state that gets access to all stacking member ports in the member device of described opposite end when described stack member apparatus is fault, described stack member apparatus is converted to single cpu mode, and does not carry out alternately with described opposite end member device.
Compared with prior art, the present invention has the following advantages: have on the member device of power board, when all master control borads on member's equipment all can not use, can also carry out data interaction by using power board and other member device on the member device, guarantee the interrupted transmission of data, improved the reliabilty and availability of member device.
Description of drawings
Fig. 1 is for supporting the schematic diagram that piles up of two frame type equipments in the prior art;
Flow when Fig. 2 all damages for stack equipment master control borad in the prior art is transmitted schematic diagram;
Fig. 3 is the data interactive method flow chart in a kind of pile system of the present invention's proposition;
Fig. 4 is the networking model figure among the present invention;
Fig. 5 is the data interactive method flow chart in a kind of pile system that proposes under the application scenarios of the present invention;
Fig. 6 is the data pattern transfer process schematic diagram of the stack member apparatus of proposition under a kind of application scenarios of the present invention;
Fig. 7 is the data interaction device structure chart in a kind of pile system of the present invention's proposition.
Embodiment
Whether core concept of the present invention is in pile system, can use by the master control borad of judging the opposite end member device, when all master control borads of opposite end member device all can not use, determines a stack member apparatus and opposite end member device interaction data stream; When the opposite end member device has master control borad not have fault, determine stack member apparatus and opposite end member device interaction data stream and control flows, thereby guaranteed that data flow can not go out active.
Further, in the present invention, when the master control borad of opposite end member device can not use, this opposite end member device can use the control flows of the data flow path transmission self of self, the master control borad of stack member apparatus can be handled the control flows in this opposite end member device data flow path, and this opposite end member device is managed and controls; Be among the present invention by control flows is transmitted in data flow path, can guarantee to have in the pile system master control borad that all member devices in the pile system are managed and control, can not cause losing of data.
Data interactive method in a kind of pile system that the present invention proposes, be applied to comprise in the pile system of at least two member devices, at least comprise master control borad, interface board and power board in the described member device, described interface board is connected with the master control borad of self by described power board, described power board and described master control borad can both be handled data stream, described power board is independent of described master control borad work, wherein, described at least two member devices are respectively stack member apparatus and opposite end member device, as shown in Figure 3, said method comprising the steps of:
Step S301, described stack member apparatus obtains the master control board state of described opposite end member device.
Step S302, described stack member apparatus judges according to described master control board state whether the master control borad of described opposite end member device can use.
Step S303, when judged result when being, described stack member apparatus and described opposite end member device interaction data stream and control flows.
Step S304, when judged result for not the time, described stack member apparatus flows with described opposite end member device interaction data.
Data interactive method in the pile system that a kind of application scenarios of the present invention proposes down, this data interactive method is applied in to use and piles up in the networking of technology, and wherein, this technology of piling up comprises IRF technology and VSS technology etc., for convenience of description, be that example describes with the IRF technology among the present invention.In IRF piled up, all single device all were called member device, and by using stacking opening to interconnect, each stacking opening can be polymerized by one or more physical ports between the member device, and each physical port is called a stacking member port.Concrete, IRF wants operate as normal, needs earlier member device to be carried out physical connection, the physical port that is used to pile up connection on the equipment is a stacking member port, wherein, the stacking member port after the binding can be received and dispatched and pile up relevant negotiation packet, or is used for transmitting between member device service message etc.
As shown in Figure 4, be the networking model figure among the present invention; Wherein, member device 1 is two identical frame type equipments with member device 2, and at this pile system, including only this member device 1 and member device 2, and member's equipment 1 is that example describes for the main equipment of this pile system.Wherein, in member device, all include master control borad, power board and interface board.By using this master control borad, can each veneer (for example, this power board and interface board etc.) in self pairing member device be managed and control, for the master control borad of main equipment, can also whole pile system be managed and control; As seen, control flows needs to send through this master control borad, for example, this control flows can be IPC (IP Conferencing, conferencing over ip), VP (Virtual Path, virtual path), equipment control shake hands passage, pile up Topology Management agreement (this piles up, and the Topology Management agreement comprises that link is regularly surveyed, Topology Discovery agreement etc.) etc.By using this power board, can independently (for example control data stream, data stream such as is transmitted at operation), certainly, according to the actual needs, can also control this power board by master control borad, then data stream be controlled, independently data stream is controlled to be example with power board in the embodiment of the invention and describe; As seen, data flow needs to send through this power board.By using this interface board, can transmit above-mentioned control flows and data flow, and carry out the transmission of control flows and data flow with other member devices.As shown in Figure 4, solid line partly is the transmission course of data flow; Dotted portion is the transmission course of control flows.
In summary it can be seen, pass through to use power board among the present invention, data flow is independent of master control borad to be transmitted, make data flow not need through master control borad, when master control borad can not use, also can continue data stream is transmitted, thereby the disruption of data flow when having avoided master control borad not use has significantly improved the handling property of this pile system.Wherein, the out of use reason of this master control borad comprises main control board occurs fault; Master control borad and slave board are switched, slave board is restarted, master control borad is restarted etc.; Wherein, this master control borad and slave board are respectively two master control borads in the frame type equipment, for example, in the time of should being the main equipment of this pile system with member device under the scene 1, then the master control borad of this member device 1 is the master control borad of whole pile system, and the master control borad of this member device 2 is the slave board of whole pile system; By the use master control borad whole pile system is managed and controls, and slave board is in stand-by state, can only member device 2 be managed and control; Should be with under the scene, describe for example with the out of use former because main control board occurs fault of master control borad (main control board occurs fault, or two master control borads all break down).
Concrete, the data interactive method in the above-mentioned pile system may further comprise the steps as shown in Figure 5:
Step S501, stack member apparatus safeguard stacking member port state table and the tabulation of opposite end member device master control borad.Wherein, all need to safeguard the tabulation of stacking member port state table and opposite end member device master control borad in all stack member apparatus in pile system (being above-mentioned member device 1 and member device 2), in pile system, for each stack member apparatus, except self other all member devices are the opposite end member device, for example, should be with under the scene, member device 1 is a stack member apparatus, and member device 2 is the opposite end member device.Concrete, the content of carrying in this stacking member port state table comprises stacking opening, stacking member port index and state; The signal situation of a kind of stacking member port state table as shown in table 1:
Table 1
As can be seen from Table 1, a stacking opening Stack1 is arranged in this stack member apparatus, and this Stack1 is polymerized by two physical ports, these two physical ports are respectively stacking member port Port1 and stacking member port Port2, wherein, the state of Port1 is UP, and the state of Port2 is DOWN.Need to prove that the stacking member port state is that the reason of DOWN includes but not limited to reasons such as the link of stacking member port is pulled out, stacking member port breaks down.
The content of carrying in the member device master control borad tabulation of this opposite end comprises stacking opening, stack member apparatus master control board slot number and state, and wherein, this stack member apparatus master control board slot number is the master control board slot number of opposite end member device; The signal situation of a kind of opposite end member device master control borad tabulation as shown in table 2:
Table 2
| Stacking opening | Stack member apparatus master control board slot number | State |
| Stack1 | Slot0 | UP |
| Slot1 | DOWN |
As can be seen from Table 2, for the stacking opening Stack1 in this stack member apparatus, be connected respectively with master control borad Slot1 with the master control borad Slot0 of opposite end member device, wherein slot0 is on the throne, slot1 since extract or failure and other reasons not on the throne, promptly this Stack1 can not carry out with master control borad slot1 alternately.
Step S502, stack member apparatus obtain the master control board state of opposite end member device, and upgrade opposite end member device master control borad tabulation.Among the present invention, this stack member apparatus can obtain the master control board state of opposite end member device according to preset period, this preset period is what choose arbitrarily according to the actual needs, for example, this preset period is set to 10s, then the every master control board state that obtains an opposite end member device through 10s of this stack member apparatus.Further, this stack member apparatus mode of obtaining the master control board state of opposite end member device specifically comprises: the opposite end member device initiatively sends to this stack member apparatus with the master control board state of self; Stack member apparatus initiatively obtains the master control board state of opposite end member device.Wherein, equipment carries out both sides' reciprocal process by piling up topological agreement after startup, and promptly both sides send packet mutually to inform existing of the other side self master control borad; When a master control borad DOWN was arranged in the member device of opposite end, another master control borad in (1) this opposite end member device can this DOWN information of perception, and this master control borad that does not break down can send the information of master control borad DOWN to this stack member apparatus; (2) master control borad occurs after the DOWN, can not continue to send packet to stack member apparatus by piling up topological agreement, when stack member apparatus (for example, 1 minute) in the default time does not all receive packet from certain master control borad, then think this master control borad DOWN.
Step S503, when all master control borads of opposite end member device all broke down, stack member apparatus entered NAMB (Non-Availability Master Board, non-effective main board) and piles up pattern.Among the present invention, stack member apparatus is tabulated by the real-time opposite end member device master control borad that obtains, thereby know the master control board state of opposite end member device, when stack member apparatus knows that the state of stack member apparatus master control board slot correspondence is DOWN, when then all master control borads of opposite end member device all broke down, stack member apparatus entered NAMB and piles up pattern.Need to prove, be not limited among the present invention know that by obtaining opposite end member device master control borad tabulation in real time whether entering NAMB piles up pattern, for example, by being set for each master control borad of stacking opening correspondence, sign (represents master control borad UP among the present invention to identify 0, to identify 1 expression master control borad DOWN is that example describes), during initial the connection, the sign of each master control borad is 0, when the master control board state that gets access to the opposite end member device when stack member apparatus among the above-mentioned steps S302 is DOWN, corresponding identification is changed to 1, stack member apparatus knows that the sign of the master control borad of all opposite end member devices is at 1 o'clock, enters into NAMB and piles up pattern.Whether enter the mode that NAMB piles up pattern, the present invention no longer encyclopaedizes for knowing of other.
Among the present invention, when initial condition, because the master control borad of opposite end member device does not all break down, this stack member apparatus is in and piles up under the mode state, piling up under the mode state, this stack member apparatus and opposite end member device are formed pile system, stack member apparatus and opposite end member device can carry out data flow mutual and control flows alternately.Further, pile up pattern following time when stack member apparatus is in NAMB, illustrate that fault has all appearred in the master control borad of opposite end member device, at this moment, the opposite end member device can not continue to have transmitted control flows, and promptly no longer to carry out normal control flows mutual with the opposite end member device for this stack member apparatus; But, because the power board in the member device of opposite end can also normally use, so the opposite end member device can continue transmitting data stream, promptly under NAMB piles up pattern, the opposite end member device can carry out the reciprocal process of data flow by using this power board and stack member apparatus, thereby under the situation of main control board occurs fault, realize the transmission of data flow, significantly improved the efficiency of transmission of data in the pile system.
Step S504, NAMB pile up under the pattern, and when the master control borad of opposite end member device recovered, this stack member apparatus entered into and piles up pattern; When the equal fault of all stacking member ports of opposite end member device, this stack member apparatus enters into single cpu mode.
Among the present invention, when the opposite end member device recovers a master control borad or two master control borads, the opposite end member device can continue to transmit control flows, be that stack member apparatus and opposite end member device are formed pile system, mutual and the control flows of the line data of going forward side by side stream alternately, stack member apparatus returns to and piles up mode state.Further, under NAMB piles up pattern, this stack member apparatus obtains the stacking member port state of opposite end member device, when the state of all stacking member ports in the member device of opposite end is DOWN, then the thorough fault of opposite end member device (for example, power board also breaks down) enters single cpu mode this moment, stack member apparatus and opposite end member device no longer carry out any reciprocal process, promptly do not carry out data flow reciprocal process and control flows reciprocal process.
Need to prove, this stack member apparatus can obtain the stacking member port state of opposite end member device according to preset period, this preset period is what choose arbitrarily according to the actual needs, for example, this preset period is set to 10s, then the every stacking member port state that obtains an opposite end member device through 10s of this stack member apparatus does not repeat them here.Further, the mode that this stack member apparatus obtains the stacking member port state of opposite end member device includes but not limited to: stack member apparatus obtains the stacking member port state table of opposite end member device, and from this stacking member port state table, know the state of each stacking member port in the member device of opposite end, when the state of all stacking member ports is DOWN, then enter single cpu mode.
Among the present invention, after stack member apparatus enters into single cpu mode, have only opposite end member device complete machine to restart that (master control borad and power board are repaired, the opposite end member device does not have fault) when also joining pile system again, this stack member apparatus could to carry out data flow mutual and control flows is mutual with the opposite end member device, and this stack member apparatus will return to and pile up pattern.
As shown in Figure 6, be the data pattern transfer process of stack member apparatus, during initial condition, the master control borad of opposite end member device does not break down, data pattern is for piling up pattern, and it is mutual and control flows is mutual that stack member apparatus and opposite end member device carry out data flow; When all master control borads of opposite end member device all broke down (DOWN), the data pattern of stack member apparatus was converted to NAMB and piles up pattern, and it is mutual that stack member apparatus and opposite end member device carry out data flow; Under NAMB piled up pattern, when the opposite end member device had master control borad to recover, the data pattern of stack member apparatus is converted to piled up pattern, stack member apparatus and opposite end member device carry out data flow alternately and control flows mutual; Under NAMB piled up pattern, when all stacking member ports of opposite end member device all broke down (DOWN), the data pattern of stack member apparatus was converted to single cpu mode, and stack member apparatus and opposite end member device do not carry out any mutual; Under the single cpu mode, the opposite end member device adds (join) again in pile system, and the data pattern of stack member apparatus is converted to piles up pattern.
In summary it can be seen, above-mentioned handling process is that all master control borads all break down with the out of use reason of master control borad is that example describes, same, when the out of use former because master control borad of master control borad and slave board are switched, perhaps master control borad is restarted, when perhaps slave board was restarted, above-mentioned handling process was suitable equally, does not repeat them here.
Need to prove, based on above-mentioned handling process, data interactive method in the pile system provided by the invention also comprises: when the master control borad of opposite end member device can not use, this opposite end member device can switch to data flow path with control flows, this reason that can switch is that control flows has identical transmission channel with data flow, it is the transmission channel (data flow path) between power board and the interface board, at this moment, originally the control flows of transmitting between master control borad, power board and interface board can be transmitted in data flow path, does not repeat them here.
First kind of situation, when stack member apparatus gets access to the master control borad (master control borad of pile system) of opposite end member device in the time of can not using, the master control borad of this stack member apparatus (the former slave board that piles up system) will be switched and be new master control borad, and the control flows in the member device data flow path of the original opposite end of continued access that can be level and smooth, promptly the control flows in the member device data flow path of original opposite end is handled, then the veneer of (comprising the opposite end member device) of other member devices in the pile system (for example, power board and interface board etc.) is managed and controls; At this moment, the out of use reason of the master control borad of opposite end member device is that master control borad and slave board are switched, and perhaps master control borad is restarted.Wherein, this masterslave switchover and existing masterslave switchover process are similar, give unnecessary details no longer in detail in the embodiment of the invention.
Second kind of situation, when stack member apparatus gets access to the master control borad (slave board of pile system) of opposite end member device in the time of can not using, the master control borad of this stack member apparatus (master control borad of pile system) still can manage and control the veneer of all member devices in the pile system (comprising the opposite end member device), at this moment, the master control borad of this stack member apparatus is the interior control flows of continued access opposite end member device data flow path directly, does not repeat them here; Wherein, the out of use reason of the master control borad of opposite end member device can be that slave board is restarted.
Need to prove, in said process, if former master control board starting becomes slave board, perhaps slave board is restarted and is finished, perhaps master control borad restart finish after, control flows will return to the control flows passage and transmit, make control flows passage and data flow path still separately use, do not repeat them here.
The invention allows for the data interaction device in a kind of pile system, be applied to comprise in the pile system of at least two member devices, at least comprise master control borad, interface board and power board in the described member device, described interface board is connected with the master control borad of self by described power board, described power board and described master control borad can both be handled data stream, described power board is independent of described master control borad work, wherein, described at least two member devices are respectively stack member apparatus and opposite end member device, as shown in Figure 7, described device comprises:
Concrete, judge module 72 specifically is used for, and judges according to described master control board state whether the master control borad of described opposite end member device breaks down; Be specially: safeguard the master control borad tabulation of described opposite end member device; Upgrade the master control borad tabulation of described opposite end member device according to the master control board state of described opposite end member device; And judge according to the master control borad tabulation of the opposite end member device after upgrading whether all master control borads of described opposite end member device all break down.
Wherein, described processing module 73 specifically is used for, and receives the data flow that described opposite end member device sends to described stack member apparatus by self power board, or, send data flow to described opposite end member device, receive described data flow by self power board by described opposite end member device; Receive the control flows that described opposite end member device sends to described stack member apparatus by self master control borad, or, send control flows to described opposite end member device, receive described control flows by described opposite end member device by self control board.
Further, 73 of described processing moulds also are used for, when the master control borad of judging described opposite end member device can not use, by the master control borad that uses self control flows in the member device data flow path of described opposite end is handled, and described opposite end member device is managed and controls; Wherein, the control flows in the described data flow path is that described opposite end member device switches to described data flow path.
In addition, when the judged result of judge module 72 for not the time, described stack member apparatus is that NAMB piles up pattern, described processing module 73 also is used for: under NAMB piles up pattern, when described stack member apparatus gets access to when having master control borad to recover in the member device of described opposite end, described stack member apparatus is converted to piles up pattern, and with described opposite end member device interaction data stream and control flows; Under NAMB piles up pattern, when the state that gets access to all stacking member ports in the member device of described opposite end when described stack member apparatus is fault, described stack member apparatus is converted to single cpu mode, and does not carry out alternately with described opposite end member device.
In summary it can be seen that when initial condition, the master control borad of opposite end member device does not break down, data pattern is for piling up pattern, and it is mutual and control flows is mutual that stack member apparatus and opposite end member device carry out data flow; When all master control borads of opposite end member device all broke down (DOWN), the data pattern of stack member apparatus was converted to NAMB and piles up pattern, and it is mutual that stack member apparatus and opposite end member device carry out data flow; Under NAMB piled up pattern, when the opposite end member device had master control borad to recover, the data pattern of stack member apparatus is converted to piled up pattern, stack member apparatus and opposite end member device carry out data flow alternately and control flows mutual; Under NAMB piled up pattern, when all stacking member ports of opposite end member device all broke down (DOWN), the data pattern of stack member apparatus was converted to single cpu mode, and stack member apparatus and opposite end member device do not carry out any mutual; Under the single cpu mode, the opposite end member device adds (join) again in pile system, and the data pattern of stack member apparatus is converted to piles up pattern.
Need to prove, in the present invention, all include master control borad, power board and interface board in the member device.By using this master control borad, can each veneer in self pairing member device be managed and control, for the master control borad of main equipment, can also manage and control whole pile system; As seen, control flows needs to send through this master control borad, for example, this control flows can for IPC, VP, equipment control shake hands passage, pile up Topology Management agreement (this piles up, and the Topology Management agreement comprises that link is regularly surveyed, Topology Discovery agreement etc.) etc.By using this power board, can independently (for example control data stream, data stream such as is transmitted at operation), certainly, according to the actual needs, can also control this power board by master control borad, then data stream be controlled, independently data stream is controlled to be example with power board in the embodiment of the invention and describe; As seen, data flow needs to send through this power board.By using this interface board, can transmit above-mentioned control flows and data flow, and carry out the transmission of control flows and data flow with other member devices.
In summary it can be seen, pass through to use power board among the present invention, data flow is independent of master control borad to be transmitted, make data flow not need through master control borad, when master control borad can not use, also can continue data stream is transmitted, thereby the disruption of data flow when having avoided master control borad not use has significantly improved the handling property of this pile system.Wherein, the out of use reason of this master control borad comprises main control board occurs fault; Master control borad and slave board are switched, slave board is restarted, master control borad is restarted etc.
In addition, when stack member apparatus gets access to the master control borad (master control borad of pile system) of opposite end member device in the time of can not using, the master control borad of this stack member apparatus (the former slave board that piles up system) will be switched and be new master control borad, and the control flows in the member device data flow path of the original opposite end of continued access that can be level and smooth, the veneer to other member devices in the pile system (comprising the opposite end member device) manages and controls then; At this moment, the out of use reason of the master control borad of opposite end member device is that master control borad and slave board are switched, and perhaps master control borad is restarted.When stack member apparatus gets access to the master control borad (slave board of pile system) of opposite end member device in the time of can not using, the master control borad of this stack member apparatus (master control borad of pile system) still can manage and control the veneer of all member devices in the pile system (comprising the opposite end member device), at this moment, the master control borad of this stack member apparatus is the interior control flows of continued access opposite end member device data flow path directly, wherein, the out of use reason of the master control borad of opposite end member device can be that slave board is restarted.If former master control board starting becomes slave board, perhaps slave board is restarted and is finished, perhaps master control borad restart finish after, control flows will return to the control flows passage and transmit, and makes control flows passage and data flow path still separately use.
Wherein, each module of apparatus of the present invention can be integrated in one, and also can separate deployment.Above-mentioned module can be merged into a module, also can further split into a plurality of submodules.
Through the above description of the embodiments, those skilled in the art can be well understood to the present invention and can realize by hardware, also can realize by the mode that software adds necessary general hardware platform.Based on such understanding, technical scheme of the present invention can embody with the form of software product, it (can be CD-ROM that this software product can be stored in a non-volatile memory medium, USB flash disk, portable hard drive etc.) in, comprise some instructions with so that computer equipment (can be personal computer, server, the perhaps network equipment etc.) carry out the described method of each embodiment of the present invention.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, module in the accompanying drawing or flow process might not be that enforcement the present invention is necessary.
It will be appreciated by those skilled in the art that the module in the device among the embodiment can be distributed in the device of embodiment according to the embodiment description, also can carry out respective change and be arranged in the one or more devices that are different from present embodiment.The module of the foregoing description can be merged into a module, also can further split into a plurality of submodules.
The invention described above sequence number is not represented the quality of embodiment just to description.
More than disclosed only be several specific embodiment of the present invention, still, the present invention is not limited thereto, any those skilled in the art can think variation all should fall into protection scope of the present invention.
Claims (10)
1. the data interactive method in the pile system, it is characterized in that, be applied to comprise in the pile system of at least two member devices, at least comprise master control borad, interface board and power board in the described member device, described interface board is connected with the master control borad of self by described power board, described power board and described master control borad can both be handled data stream, described power board is independent of described master control borad work, wherein, described at least two member devices are respectively stack member apparatus and opposite end member device, said method comprising the steps of:
Described stack member apparatus obtains the master control board state of described opposite end member device;
Described stack member apparatus judges according to described master control board state whether the master control borad of described opposite end member device can use;
When judged result when being, described stack member apparatus and described opposite end member device interaction data stream and control flows; When judged result for not the time, described stack member apparatus flows with described opposite end member device interaction data.
2. the method for claim 1 is characterized in that, described stack member apparatus and described opposite end member device interaction data stream specifically comprise:
Described opposite end member device sends data flow by self power board to described stack member apparatus, or receives data flow from described stack member apparatus by self power board;
Stack member apparatus and the described opposite end mutual control flows of member device specifically comprise:
Described opposite end member device sends control flows by self master control borad to described stack member apparatus, or receives control flows from described stack member apparatus by self master control borad.
3. method as claimed in claim 1 or 2 is characterized in that, the out of use reason of master control borad comprises one or more in following:
Main control board occurs fault; Master control borad and slave board are switched; Master control borad is restarted; Slave board is restarted;
Described stack member apparatus is judged according to described master control board state whether the master control borad of described opposite end member device can use and is comprised:
Described stack member apparatus judges according to described master control board state whether the master control borad of described opposite end member device breaks down; Be specially:
Described stack member apparatus is safeguarded the master control borad tabulation of described opposite end member device;
Described stack member apparatus upgrades the master control borad tabulation of described opposite end member device according to the master control board state of described opposite end member device;
Described stack member apparatus judges according to the master control borad tabulation of the opposite end member device after upgrading whether all master control borads of described opposite end member device all break down.
4. method as claimed in claim 1 or 2 is characterized in that,
When the master control borad of described opposite end member device can not use, described method also comprised: described opposite end member device switches to data flow path with described control flows;
When the master control borad that described stack member apparatus is judged described opposite end member device can not use, the master control borad of described stack member apparatus is handled the control flows in the member device data flow path of described opposite end, and described opposite end member device is managed and controls.
5. the method for claim 1 is characterized in that, judged result is not for the time, and described stack member apparatus is that non-effective main board NAMB piles up pattern, and described stack member apparatus also comprises after flowing with described opposite end member device interaction data:
Under NAMB piled up pattern, when described stack member apparatus gets access to when having master control borad to recover in the member device of described opposite end, described stack member apparatus was converted to and piles up pattern, and described stack member apparatus flows and control flows with described opposite end member device interaction data;
Under NAMB piles up pattern, when the state that gets access to all stacking member ports in the member device of described opposite end when described stack member apparatus is fault, described stack member apparatus is converted to single cpu mode, and described stack member apparatus and described opposite end member device do not carry out alternately.
6. the data interaction device in the pile system, it is characterized in that, be applied to comprise in the pile system of at least two member devices, at least comprise master control borad, interface board and power board in the described member device, described interface board is connected with the master control borad of self by described power board, described power board and described master control borad can both be handled data stream, described power board is independent of described master control borad work, wherein, described at least two member devices are respectively stack member apparatus and opposite end member device, and described device comprises:
Acquisition module is used to obtain the master control board state of described opposite end member device;
Judge module electrically connects with described acquisition module, is used for judging according to the master control board state that described acquisition module obtains whether the master control borad of described opposite end member device can use;
Processing module electrically connects with described judge module, be used for when the judged result of described judge module when being, flow and control flows with described opposite end member device interaction data; When the judged result of described judge module for not the time, flow with described opposite end member device interaction data.
7. device as claimed in claim 6 is characterized in that,
Described processing module specifically is used for, receive the data flow that described opposite end member device sends to described stack member apparatus by self power board, or, send data flow to described opposite end member device, receive described data flow by described opposite end member device by self power board;
Receive the control flows that described opposite end member device sends to described stack member apparatus by self master control borad, or, send control flows to described opposite end member device, receive described control flows by described opposite end member device by self control board.
8. as claim 6 or 7 described devices, it is characterized in that the out of use reason of master control borad comprises one or more in following:
Main control board occurs fault; Master control borad and slave board are switched; Master control borad is restarted; Slave board is restarted;
Described judge module specifically is used for, and judges according to described master control board state whether the master control borad of described opposite end member device breaks down; Be specially:
Safeguard the master control borad tabulation of described opposite end member device; Upgrade the master control borad tabulation of described opposite end member device according to the master control board state of described opposite end member device; And judge according to the master control borad tabulation of the opposite end member device after upgrading whether all master control borads of described opposite end member device all break down.
9. as claim 6 or 7 described devices, it is characterized in that,
Described processing module also is used for, when the master control borad of judging described opposite end member device can not use, by the master control borad that uses self control flows in the member device data flow path of described opposite end is handled, and described opposite end member device is managed and controls; Wherein, the control flows in the described data flow path is that described opposite end member device switches to described data flow path.
10. device as claimed in claim 6 is characterized in that, the judged result of judge module is not for the time, and described stack member apparatus is that non-effective main board NAMB piles up pattern, and described processing module also is used for:
Under NAMB piles up pattern, when described stack member apparatus gets access to when having master control borad to recover in the member device of described opposite end, described stack member apparatus is converted to piles up pattern, and with described opposite end member device interaction data stream and control flows;
Under NAMB piles up pattern, when the state that gets access to all stacking member ports in the member device of described opposite end when described stack member apparatus is fault, described stack member apparatus is converted to single cpu mode, and does not carry out alternately with described opposite end member device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910223865 CN101707555B (en) | 2009-11-25 | 2009-11-25 | Data interactive method and device in stack system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910223865 CN101707555B (en) | 2009-11-25 | 2009-11-25 | Data interactive method and device in stack system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101707555A CN101707555A (en) | 2010-05-12 |
| CN101707555B true CN101707555B (en) | 2011-12-07 |
Family
ID=42377750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910223865 Active CN101707555B (en) | 2009-11-25 | 2009-11-25 | Data interactive method and device in stack system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101707555B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704345B (en) * | 2016-08-09 | 2021-03-16 | 迈普通信技术股份有限公司 | Management method and device for stacking equipment in automatic test |
| CN106911597B (en) * | 2017-02-14 | 2020-02-21 | 新华三技术有限公司 | Cross-board forwarding method and device |
| CN112073236B (en) * | 2020-09-01 | 2023-09-08 | 深信服科技股份有限公司 | Fault processing method of stacking system, frame type switch, stacking system and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1665198A (en) * | 2004-03-06 | 2005-09-07 | 鸿富锦精密工业（深圳）有限公司 | Management method of stacked switch |
| CN101110782A (en) * | 2007-08-28 | 2008-01-23 | 中兴通讯股份有限公司 | System management piling method used for Ethernet switchboard |
| US7593320B1 (en) * | 2004-04-30 | 2009-09-22 | Marvell International, Ltd. | Failover scheme for stackable network switches |
-
2009
- 2009-11-25 CN CN 200910223865 patent/CN101707555B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1665198A (en) * | 2004-03-06 | 2005-09-07 | 鸿富锦精密工业（深圳）有限公司 | Management method of stacked switch |
| US7593320B1 (en) * | 2004-04-30 | 2009-09-22 | Marvell International, Ltd. | Failover scheme for stackable network switches |
| CN101110782A (en) * | 2007-08-28 | 2008-01-23 | 中兴通讯股份有限公司 | System management piling method used for Ethernet switchboard |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101707555A (en) | 2010-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102347867B (en) | Processing method and equipment for stacking splitting detection | |
| CN101917337B (en) | Device and method for interconnecting router cluster middle plates | |
| CN102299846B (en) | Method for transmitting BFD (Bidirectional Forwarding Detection) message and equipment | |
| CN101674198B (en) | Method and device for realizing stacking | |
| CN101968744B (en) | Intelligent resilient framework (IRF) system-based method and system for upgrading box type equipment | |
| CN102185718A (en) | System upgrading method and device | |
| CN102255751A (en) | Stacking conflict resolution method and equipment | |
| CN101494602A (en) | Energy-saving method and apparatus for communication equipment | |
| CN103401786A (en) | Method, device and system for establishing network topology, controlling path and transmitting message | |
| CN102510408A (en) | Method for realizing TCP (transmission control protocol) application main and standby changeover | |
| CN101986626A (en) | Method and device for protecting equipment | |
| CN101808010B (en) | Equipment management method and equipment management device and main control board | |
| CN101877631A (en) | Server and business switching method thereof | |
| CN106330786A (en) | MAC address synchronization method, apparatus and system | |
| CN101707555B (en) | Data interactive method and device in stack system | |
| CN101588305A (en) | message handling method carried with multilayer labels and an exchanger | |
| CN101841735A (en) | Frame-type switch, stack system and fault treatment method after stack | |
| CN102307141A (en) | Message forwarding method and device | |
| CN109450707A (en) | A kind of data transmission method, device, gateway and readable storage medium storing program for executing | |
| CN104518995A (en) | Switch virtualization system based on distributed architecture | |
| CN103200092B (en) | A kind of routing daemon management method and equipment based on virtual network device | |
| CN102857436B (en) | Flow transmission method and flow transmission equipment based on IRF (intelligent resilient framework) network | |
| CN103004157B (en) | Interface register method and device for network device to join cluster system | |
| CN102281158A (en) | Line fault processing method and device | |
| CN103401708A (en) | Port configuration method and device |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 310052 Binjiang District Changhe Road, Zhejiang, China, No. 466, No. Patentee after: Xinhua three Technology Co., Ltd. Address before: 310053 Hangzhou hi tech Industrial Development Zone, Zhejiang province science and Technology Industrial Park, No. 310 and No. six road, HUAWEI, Hangzhou production base Patentee before: Huasan Communication Technology Co., Ltd. |