CN1956410A - Method for implementing information interaction between single boards - Google Patents
Method for implementing information interaction between single boards Download PDFInfo
- Publication number
- CN1956410A CN1956410A CNA2005101143963A CN200510114396A CN1956410A CN 1956410 A CN1956410 A CN 1956410A CN A2005101143963 A CNA2005101143963 A CN A2005101143963A CN 200510114396 A CN200510114396 A CN 200510114396A CN 1956410 A CN1956410 A CN 1956410A
- Authority
- CN
- China
- Prior art keywords
- message
- formation
- buffer
- veneer
- message buffer
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
This invention relates to a method for realize information interaction among single boards including; setting interaction information among single boards carrying same route information in a same information buffer queue and single boards interact information by said queue, which can compress information volume among single boards as much as possible without influencing service to reduce transmission times and length so as to reduce the load of CPU and lower the probability of reset.
Description
Technical field
The present invention relates to the communications field, relate in particular to a kind of method that realizes information interaction between single boards.
Background technology
A plurality of veneers are inserted on the same backboard in the machine frame, and message is by FE (FastEthernet on the backboard between veneer; Fast Ethernet) bus transmits, and is equivalent to a small-sized Ethernet.Wherein, every veneer has own unique CPU numbering, is equivalent to the MAC Address in the Ethernet.
Carry out the process of information interaction between veneer, as shown in Figure 1:
When veneer is sent out message outward, need fill in message header, comprise transmit leg CPU numbering, recipient CPU numbering, type of message, message-length etc., can be to guarantee message by the correct purpose veneer that sends to.Message to Ethernet switching chip, afterwards arrives purpose veneer by the Ethernet switching chip exchange through the FE bus transfer.Described purpose veneer extracts and carries out respective handling for information about in the message header.
By above-mentioned processing procedure as seen, the transmitting-receiving of message between different boards can consume a part of system resource, particularly cpu resource, and a piece of news will trigger once and interrupt.
The operation of former veneer is professional few, and the message between different boards amount is not very big, and along with the development of chip technology, the CPU operational capability is more and more stronger, so message between different boards does not cause the concern that people are too many to the consumption of cpu resource.But along with increase new function point on some older veneers, amount of information mutual between veneer is also along with rapid increase.Along with the increase of size of message, system CPU occupancy rate will improve rapidly, because the ability of CPU handling interrupt is limited, when size of message increases to a certain degree, can cause CPU overload, influence the processing of other business, some situation even can cause the congested of CPU, the fatal problem of board resetting.Therefore, press for the size of message between effective densified veneer, reduce the cpu resource that takies when handling interaction message between veneer.
Summary of the invention
In view of above-mentioned existing in prior technology problem, the purpose of this invention is to provide a kind of method that realizes information interaction between single boards, by the present invention, can solve because message between different boards too much causes the problem of CPU overload, by the present invention, do not need to change the hardware of old veneer, but the processing procedure of message between different boards is done to a certain degree optimization, thereby size of message between compressive plate as much as possible under traffic affecting prerequisite not, reduce the number of times and the length of message between different boards transmitting-receiving, thereby reach the purpose that reduces CPU usage.
The objective of the invention is to be achieved through the following technical solutions:
A kind of method that realizes information interaction between single boards provided by the invention comprises:
A, will carry interaction message between the veneer of identical routing iinformation, be arranged in the same message buffer formation;
Carry out the mutual of information by described message buffer formation between B, veneer.
Wherein, before described steps A, comprise:
The message buffer is set, is used for the interaction message between the buffer memory veneer.
Wherein, described steps A specifically comprises:
A1, analyze the interaction message between veneer in the described message buffer, will have the message header of identical routing iinformation, and corresponding message body extracts;
A2, the described routing iinformation that extracts is combined into new message header;
A3, message buffer formation is set, and adds described newly-generated message header for described message buffer formation, and the corresponding message body that is extracted.
Wherein, described message buffer formation comprises: the maximum cushioning time parameter of message in maximum message body number parameter of holding in formation length available parameter, the formation and the formation.
Wherein, when new information arrived, described step B specifically comprised:
Whether B1, the new length to message of judgement surpass the total length of described message buffer formation, if surpass, then directly newly send to message described; Otherwise, execution in step B2;
B2, the new length available that whether surpasses the current message buffer of described message buffer formation to the length of message of judgement, if surpass, then the message in the described current message buffer is sent, newly put into described current message buffer with described then, change step B3 then over to message; Otherwise, direct execution in step B3;
B3, judge in the current message buffer thresholding that whether reaches setting with the described message body number that newly has an identical routing iinformation to message, if reach the thresholding of setting, then the message in the described current buffering area is all sent, and empty described current buffering area, execution in step B4 then; Otherwise, direct execution in step B4;
B4, newly put into described current message buffer to message with described.
Wherein, described step B also comprises:
B5, when maximum cushioning time of message in the formation arrives the setting-up time of timer, then the message in the current message buffer is sent.
Wherein, described step B also comprises:
B6, the described message that sends out arrive network exchanging chip through bus, after exchange, by bus described message are sent to the purpose veneer;
B7, described purpose veneer are handled the described message that receives.
Wherein, the value of the parameter in the described message buffer formation is identical or different.
Wherein, the value of the parameter in the different message buffer formation is identical or different in the same system.
As seen from the above technical solution provided by the invention, method of the present invention will be carried interaction message between the veneer of identical routing iinformation, be arranged in the same message buffer formation; Carry out the mutual of information by described message buffer formation between veneer.By the present invention, can be under traffic affecting prerequisite not, size of message between compressive plate as much as possible, reduce the number of times and the length of message between different boards transmission, thereby effectively offloading the CPU, the probability of reduction board resetting makes old veneer support new business under the situation of not changing hardware.
Description of drawings
The principle schematic of Fig. 1 when communicating between veneer;
Fig. 2 is a flow chart of the present invention.
Embodiment
The invention provides a kind of method that realizes information interaction between single boards, its core is: will carry interaction message between the veneer of identical routing iinformation, and be arranged in the same message buffer formation; Carry out the mutual of information by described message buffer formation between veneer.
The main thought of embodiment provided by the invention is, at first according to the message establishing message buffer formation in the message buffering district, fill out message header, when new message arrives, judge new length earlier to message, if surpass the total length of described message buffer formation, then directly newly send to message with described; If the length that newly arrives message surpasses the length available of the current message buffer of described message buffer formation, then the message in the described current message buffer is sent, newly put into described current message buffer with described then to message; If newly arrive the length available of the length of message, then directly newly put into described current message buffer to message with described less than the current message buffer of described message buffer formation; And then judge to have in the current queue newly whether have the message body number of identical routing iinformation above certain thresholding to message with described, if surpass, then need the message in the formation is all sent, empty formation then, will newly be put in the formation again to message; If the message body number does not surpass threshold value in the current queue, then will newly be put into the message queue tail of the queue to message.Message buffer formation has the timer protection in addition, behind timer expiry, the message in the message buffer formation need be sent, to satisfy the system real time demand.Specific implementation process comprises as shown in Figure 2:
Message between one batten is segmented, be divided into message header and message body, message header is used for writing down the routing iinformation that some are used for addressing, and as source CPU numbering, purpose CPU numbering etc., and message body is used to write down the particular content of this communication.
For example existing two veneers are designated as A veneer and B veneer respectively, supposes that A need send 100 message and arrive B, need apply for 100 message header structures and filled that according to former processing these 100 entrained routing iinformations of message header are the same.Given this, the present invention's routing iinformation that these are unified extracts and is combined into a new message header.
Still in conjunction with above-mentioned hypothesis, when message buffer formation is set, for described message buffer formation adds described newly-generated message header, this message header back is followed the message body of 100 message again, the benefit of doing like this is effectively to reduce message-length, and can produce 100 interruptions in the past, become 1 time now, thereby reduced significantly the processing time of CPU.This method is not only applicable to two message formats between veneer, and is suitable equally to the polylith veneer.Need and two veneers of B, C carry out interacting message such as, A veneer, then need create message buffer formation corresponding to B veneer and C veneer respectively at the A veneer, different message enters different formations, and is separate between each formation.
Message buffer formation through above-mentioned setting has three important parameters:
1. queue length: because message between different boards finally can be converted to ethernet frame and send, so queue length should be moderate;
2. the message body number of the maximum that can hold in the formation: for reaching the purpose of buffering, when setting thresholding, should consider that the message body number of the maximum that can hold in the formation can not be very little;
3. message maximum cushioning time in the formation: consider the real-time requirement, the time that message body is deposited in buffer queue can not be oversize, otherwise can have influence on the reliability of system.
More than three parameters can set different values according to concrete application scenario, the value in the same system between the different messages formation also can be different.
Whether step 105, the new length to message of judgement surpass the total length of described message buffer formation, if surpass, then execution in step 115, promptly directly newly send to message described; Otherwise, execution in step 106;
Execution in step 108, judge in the current message buffer thresholding that whether reaches setting with the described message body number that newly has an identical routing iinformation to message, if reach the thresholding of setting, then execution in step 109, the message that is about in the described current buffering area all sends, and emptying described current buffering area, execution in step 110 then; Otherwise direct execution in step 110 is about to describedly newly put into described current message buffer to message.
The specific embodiments that is provided by the invention described above is as can be seen: the message header that the present invention will be mail to a plurality of message of same veneer extracts, form a public message header, each message body is placed successively after the common message head then, thereby reduce the message between different boards amount, reduce the number of times of message between different boards transmitting-receiving number of times and CPU handling interrupt; Thereby effectively offloading the CPU, the probability of reduction board resetting makes old veneer support new business under the situation of not changing hardware.
The above; only for the preferable embodiment of the present invention, but protection scope of the present invention is not limited thereto, and anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; the variation that can expect easily or replacement all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claim.
Claims (9)
1, a kind of method that realizes information interaction between single boards is characterized in that, comprising:
A, will carry interaction message between the veneer of identical routing iinformation, be arranged in the same message buffer formation;
Carry out the mutual of information by described message buffer formation between B, veneer.
2, method according to claim 1 is characterized in that, comprises before described steps A:
The message buffer is set, is used for the interaction message between the buffer memory veneer.
3, method according to claim 2 is characterized in that, described steps A specifically comprises:
A1, analyze the interaction message between veneer in the described message buffer, will have the message header of identical routing iinformation, and corresponding message body extracts;
A2, the described routing iinformation that extracts is combined into new message header;
A3, message buffer formation is set, and adds described newly-generated message header for described message buffer formation, and the corresponding message body that is extracted.
4, according to any described method of claim 1 to 3, it is characterized in that described message buffer formation comprises: the maximum cushioning time parameter of message in maximum message body number parameter of holding in formation length available parameter, the formation and the formation.
5, method according to claim 4 is characterized in that, when new information arrived, described step B specifically comprised:
Whether B1, the new length to message of judgement surpass the total length of described message buffer formation, if surpass, then directly newly send to message described; Otherwise, execution in step B2;
B2, the new length available that whether surpasses the current message buffer of described message buffer formation to the length of message of judgement, if surpass, then the message in the described current message buffer is sent, newly put into described current message buffer with described then, change step B3 then over to message; Otherwise, direct execution in step B3;
B3, judge in the current message buffer thresholding that whether reaches setting with the described message body number that newly has an identical routing iinformation to message, if reach the thresholding of setting, then the message in the described current buffering area is all sent, and empty described current buffering area, execution in step B4 then; Otherwise, direct execution in step B4;
B4, newly put into described current message buffer to message with described.
6, method according to claim 5 is characterized in that, described step B also comprises:
B5, when maximum cushioning time of message in the formation arrives the setting-up time of timer, then the message in the current message buffer is sent.
7, method according to claim 6 is characterized in that, described step B also comprises:
B6, the described message that sends out arrive network exchanging chip through bus, after exchange, by bus described message are sent to the purpose veneer;
B7, described purpose veneer are handled the described message that receives.
8, method according to claim 4 is characterized in that, the value of the parameter in the described message buffer formation is identical or different.
9, method according to claim 4 is characterized in that, the value of the parameter in the same system in the different message buffer formation is identical or different.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2005101143963A CN1956410A (en) | 2005-10-24 | 2005-10-24 | Method for implementing information interaction between single boards |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2005101143963A CN1956410A (en) | 2005-10-24 | 2005-10-24 | Method for implementing information interaction between single boards |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1956410A true CN1956410A (en) | 2007-05-02 |
Family
ID=38063516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2005101143963A Pending CN1956410A (en) | 2005-10-24 | 2005-10-24 | Method for implementing information interaction between single boards |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1956410A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101505234B (en) * | 2009-03-17 | 2012-01-11 | 中兴通讯股份有限公司 | System and method for inter-board communication |
| CN109361620A (en) * | 2018-11-09 | 2019-02-19 | 杭州迪普科技股份有限公司 | A kind of method, apparatus, equipment and storage medium that data are sent |
-
2005
- 2005-10-24 CN CNA2005101143963A patent/CN1956410A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101505234B (en) * | 2009-03-17 | 2012-01-11 | 中兴通讯股份有限公司 | System and method for inter-board communication |
| CN109361620A (en) * | 2018-11-09 | 2019-02-19 | 杭州迪普科技股份有限公司 | A kind of method, apparatus, equipment and storage medium that data are sent |
| CN109361620B (en) * | 2018-11-09 | 2022-11-01 | 杭州迪普科技股份有限公司 | Data sending method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1975680A (en) | Method for realizing interprocess asynchronous communication based on Java | |
| CN107659515A (en) | Message processing method, device, message processing chip and server | |
| CN1825804A (en) | System and method for implementing communication between distributed system boards | |
| CN1658575A (en) | Method for improving service quality in SGSN network processor | |
| CN1725732A (en) | Message speed limit method | |
| CN1816042A (en) | Method for transmission of data between processors | |
| CN101035033A (en) | Message mirroring method and network device for supporting the remote message mirror | |
| CN1852246A (en) | Method for multi-cast broadcasting flow distribution node to receive multi-cast broadcasting flow | |
| CN1777148A (en) | Routing table next-hop IP address to MAC address analytic method | |
| CN101035130A (en) | Browser/server structure based information distribution method and system | |
| CN1248465C (en) | Management method of data fransmission/receiving butter region in network communication | |
| CN1152313C (en) | Section-by-section congestion control method based on random early detection | |
| CN1956410A (en) | Method for implementing information interaction between single boards | |
| CN101064668A (en) | Method for realizing IPV6 protocol stack in distributed routing subsystem | |
| CN1219370C (en) | Communication method for performing all-tier protocol stack processing by base station side | |
| CN1221099C (en) | Method for controlling service priority for tunneling data packet in general packet wireless service | |
| CN1476212A (en) | Method and device for realizing data package transmission on synchronous digital system | |
| CN1744561A (en) | Super-long message processing method during message conversion process | |
| CN1933450A (en) | Interplate communicating method and interface plate | |
| CN1705295A (en) | Packet transmission system having priority and method therefor | |
| CN101060518A (en) | A multi-path binding service information sending and receiving equipment | |
| CN1192577C (en) | Network frame quick distribution method with flow rate control in network equipment | |
| CN1411217A (en) | Method of raising IP message forwarding speed utilizing slow storage technology | |
| CN1315308C (en) | Method for transmitting realtime multimedia data on internet | |
| CN1300495A (en) | Apparatus, system and method relating to block data communication |
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 |