CN109450817A - The mixed scheduling method that time trigger Ethernet multi-service message is sent - Google Patents
The mixed scheduling method that time trigger Ethernet multi-service message is sent Download PDFInfo
- Publication number
- CN109450817A CN109450817A CN201811492235.1A CN201811492235A CN109450817A CN 109450817 A CN109450817 A CN 109450817A CN 201811492235 A CN201811492235 A CN 201811492235A CN 109450817 A CN109450817 A CN 109450817A
- Authority
- CN
- China
- Prior art keywords
- data
- message
- transmitter
- sent
- transmission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/625—Queue scheduling characterised by scheduling criteria for service slots or service orders
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/625—Queue scheduling characterised by scheduling criteria for service slots or service orders
- H04L47/6275—Queue scheduling characterised by scheduling criteria for service slots or service orders based on priority
Abstract
The invention belongs to network communication technologies.For the transmission requirement of multiple business message in AS6802 standard, a kind of mixed scheduling method that time trigger Ethernet multiple business message is sent is formulated, and it is applicable in the transmission scheduling message interaction mechanism of the method, meet the transmission characteristic of doing one's best of the time trigger characteristic of TT message, the event trigger characteristic of PCF message, the rate limit characteristic of RC message and BE message, it solves the problems, such as to be difficult to take into account multiple business message transmission characteristic in time trigger Ethernet, supports the end system of multiple business stream to provide technical support for design and implementation.
Description
Technical field
The invention belongs to network communication technologies, are related to a kind of mixed scheduling side that a variety of message of time trigger Ethernet are sent
Method and related data structures.
Background technique
In the Ethernet for meeting IEEE802.3 standard, the network equipment transmits principle using event triggering Ethernet, arbitrarily
The network equipment can put access network at any time, using first reaching the principle first serviced.By shared between the network equipment
Medium communication necessarily causes some message to generate the delay of uncertain shake and accumulation in transmission process.
The AFDX network for meeting ARINC664Part7 standard is based on Ethernet, increases virtual link in data link layer
(VL), the mechanism such as bandwidth allocation gap (BAG), shake management, effectively avoid the conflict in message transmitting procedure, have message
Real-time and certainty, to meet the reliability and deterministic demand of avionics system information transmission.
Meet the TTE network of AS6802 standard, compatible Ethernet and AFDX network, coordinates using between a network equipment
Based on the Network Synchronization time support the TT message of time trigger mechanism, event to trigger machine to reduce propagation delay time and shake
The RC message (i.e. AFDX message) and BE message (ether network information) of system, to meet in single network different in real time and safe
The application of grade needs.
AS6802 standard supports three kinds of service messages such as TT, RC and BE in network level, is not gathered an end
In system, more without proposing the transmission scheduling mechanism between three kinds of message.
The present invention devises a kind of transmission scheduling message interaction machine for meeting the message transmission characteristic such as PCF, TT, RC and BE
System, has formulated the non-preemptive time trigger and priority mixed scheduling method of one kind of multiple service messages, and realization meets TT and disappears
Time trigger characteristic, the event trigger characteristic of PCF message, the rate limit characteristic of RC message and the doing one's best for BE message of breath
The transmission of transmission characteristic is dispatched, and solves the problems, such as to be difficult to take into account multiple business message transmission characteristic in time trigger Ethernet,
The end system of multiple business stream is supported to provide technical support for design and implementation.
Summary of the invention
Goal of the invention:
The present invention devises a kind of transmission scheduling message interaction machine for meeting the message transmission characteristic such as PCF, TT, RC and BE
System, has formulated the non-preemptive time trigger and priority mixed scheduling method of one kind of multiple service messages, has solved time touching
It is difficult to the problem of taking into account multiple business message transmission characteristic in hair Ethernet, the end system of multiple business stream is supported for design and implementation
System provides technical support.
Technical solution:
The mixed scheduling method that time trigger Ethernet multi-service message is sent, which is characterized in that specifically include following step
It is rapid:
Step 1: host is applied and end system synchronizing function is as data source, generates the primary data for needing to send；Host
Pass through TT transmitter, RC transmitter and BE transmitter respectively according to type using the data of generation, is packaged into the TT of time trigger
Message, the RC message of event trigger mechanism and BE message；The data that end system synchronizing function generates are packaged by PCF transmitter
The PCF message of event triggering, tetra- kinds of transmitters of TT, PCF, RC and BE provide following scheduling information:
(1) tetra- kinds of transmitters of safeguard corresponding transmission buffer area respectively；
(2) .TT transmitter safeguards a transmissions planning chart, comprising one or more sending time points and corresponding buffering area,
Planning chart is according to chronological order tissue；
(3) .PCF transmitter safeguards a transmission request signal and fixed buffer area；
(4) .RC transmitter safeguards a transmission dispatch list, the state comprising all VL；
(5) whether .BE transmitter safeguards a transmit queue, be ready to comprising BE data, the address of BE data and length；
Step 2: scheduler and all transmitter concurrent workings, it is currently transmitted plan that first item in TT planning chart, which is arranged,
Jump to step 3；
Step 3: if end system is in synchronous regime, reading the plan of transmission, can be sent before planned time point
Data frame length is denoted as permission length, changes with the variation of local clock, and otherwise setting allows length to be fixed as largest frames
It is long, 1518 bytes.
If allowing length less than 64 bytes, step 4 is jumped to；Otherwise step 6 is jumped to；
Step 4: scheduler forbidden data is sent until planned time point, is judged whether the planning data is ready to, is then
Step 5 is jumped to after transmission；Otherwise step 5 is jumped directly to.
Step 5: setting the next item down, the next item down of table tail item is header entry, to send plan, jumps to step 3；
Step 6: according to the priority of PCF, RC, BE from high to low, it is fair to judge whether its data frame length is less than or equal to
Perhaps the data frame of length, all VL of RC business judges simultaneously, is to send a frame, jumps to step 3 after the completion, otherwise directly jumps
Go to step 3.
In the step 1, the state of VL include RC data whether be ready to, data address, data length.
The utility model has the advantages that
The three kinds of service messages and its transmission characteristic proposed based on AS6802 standard, have formulated a kind of time trigger Ethernet
The dispatching method that middle multiple business message is sent, meet the time trigger characteristic of TT message, the rate limit characteristic of RC message and
The transmission characteristic of doing one's best of BE message supports the end system of multiple business stream to provide technical support for design and implementation.
This method uses non-preemptive scheduling, avoids because occurring a large amount of endless full wafers on network caused by seizing scheduling
It is disconnected, it saves and sends the bandwidth that imperfect segment occupies.
In order to guarantee that the time trigger characteristic of TT frame, this method are that the transmission of TT frame makes a reservation for its sending time point, institute in advance
There is the message that can occupy this time point transmission not to be allowed to, ensure that the accurate timing of TT frame is sent, as shown in Figure 2.Work as TT
When being dispatched to i-th, if there is TT frame is sent, then the non-TT frame that is sent according to priority in region 2；If there is no TT frame
It is sent, then the non-TT frame being sent according to priority in region 1 and 2.
It is more than the data frame for allowing length when a VL is ready for sending, another VL is ready for sending low when carrying out RC scheduling
In the data frame for allowing length, this method carries out transmission control to the VL of all RC business simultaneously, it is ensured that after the former will not block
Person improves network bandwidth service efficiency.
Detailed description of the invention
Fig. 1 is dispatching method flow chart.
Fig. 2 is the relationship that TT sending time point and non-TT frame are sent
Specific embodiment
Implementation steps of the invention are described further with reference to the accompanying drawing, as shown in Figure 1, technical solution of the present invention
Specifically implementation steps in detail include:
Step 1: host is applied and end system synchronizing function is as data source, generates the primary data for needing to send.Host
Pass through TT transmitter, RC transmitter and BE transmitter respectively according to type using the data of generation, is packaged into the TT of time trigger
Message, the RC message of event trigger mechanism and BE message.The data that end system synchronizing function generates are packaged by PCF transmitter
The PCF message of event triggering.All transmitters and scheduler concurrent working, transmitter provide following information:
(1) .TT transmitter, PCF transmitter, RC transmitter and BE transmitter safeguard corresponding transmission buffer area respectively,
It only includes a unit that middle PCF, which sends buffer area,；
(2) .TT transmitter safeguards transmissions a planning chart ttSchTbl, each in table is that { ttPit, ttStatus } is formed
Binary group, in which:
A) ttPit indicates that the sending time point of static configuration, the list item of ttSchTbl are arranged according to the sequencing of ttPit
Column；
B) ttStatus indicates that the status information of sending time point ttPit corresponding data, value are sent between 0 and TT maximum
Buffer area number is indicated when between the number ttMaxBufNo of buffer area, maps directly to the position of data to be sent in the buffer
It sets；Otherwise indicate that data are unripe；
(3) .PCF transmitter safeguards a transmission request signal pcfReq；
(4) .RC transmitter safeguards that a RC sends dispatch list rcSchTbl, and each single item indicates the hair of a RC data in table
The status information for sending virtual link rcVL is indicated by the triple of { rcBuf, rcBufLen, rcReq } composition:
A) rcBuf indicates the storage address of rcVL data frame to be sent；
B) rcBufLen indicates the frame length of rcVL data frame to be sent；
C) rcReq indicates whether the rcVL has data to be sent；
D) wherein data to be sent refer to the data of the regular function of flow by RC transmitter；
(5) .BE transmitter safeguards a BE data transmit queue, and each single item is buffered by the transmission of a BE data in queue
Regional address beBuf and length beBufLen composition, whether queue is empty to be indicated by beReq:
Step 2: scheduler and all transmitter concurrent workings, it is current planning item that first item in TT planning chart, which is arranged,
TtSchItem jumps to step 3；
Step 3: if end system, which is in, stablizes synchronous regime Sync, reading ttSchItem, record sending time point
TtPit jumps to step 4；Otherwise it is the value not less than maximum frame length that setting, which allows to send frame length value txLenAllowed, is jumped
To step 8；
Step 4: reading local clock localClock, calculate its time difference timeDiff for arriving ttPit, it is contemplated that
LocalClock is using cluster period ClusterCycleDuration as the period, therefore timeDiff calculation method is as follows:
If localClock is less than ttPit, timeDiff=ttPit-localClock；
Otherwise timeDiff=ClusterCycleDuration+ttPit-localClock；
Then branch to step 5；
Step 5: calculating allows to send frame length value txLenAllowed:
TxLenAllowed=(timeDiff-tshift)*netspeed-ifsLen；
Wherein netspeed indicates network rate；IfsLen indicates the length of leading character, starting delimiter and frame period, Gu
It is set to 20 bytes；tshiftIndicate switching time, not less than such data from allow to be sent to data reach physical layer time difference.
Due to the addressing of PCF, RC, BE data frame, the difference of read access time, tshiftMay be different, therefore the permission frame of three kinds of data frames
Long value is respectively txLenAllowedPCF、txLenAllowedRCAnd txLenAllowedBE；
If three kinds of txLenAllowed are below 64, waiting is equal to ttPit until localClock, jumps to step
6；Otherwise step 8 is jumped to；
Step 6: the data mode ttStatus of ttSchItem is read, if ttStatus designation date is ready for,
Buffer area is sent from TT according to the position of ttStatus instruction and reads and send TT data, is waited after being sent completely, is jumped to step
Rapid 7；Otherwise step 7 is jumped directly to；
Step 7: if ttSchItem be TT planning chart last, be arranged first item be ttSchItem；Otherwise it sets
Setting its next item down is ttSchItem.Then branch to step 3；
Step 8: the transmission request of the message such as response PCF, RC, BE:
PcfGnt=pcfReq AND (64≤txLenAllowedPCF)
(Π indicates to carry out logical AND operation item by item)
RcvlGnt=meets { rcReqi AND rcBufLeni≤txLenAllowedRC) minimum i value
BeGnt=NOT (pcfGnt AND rcGnt) AND beReq AND (beBufLen≤
txLenAllowedBE)
Then branch to step 9；
Step 9: the transmission of the message such as processing PCF, RC, BE:
(1) if pcfGnt is equal to 1, the PCF data frame in pcfBuf is sent, enters step 3 after the completion；
(2) if rcGnt is equal to 1, rcvlGnt { rcbuf, rcBufLen } specified RC data frame is sent,
3 are entered step after the completion；
(3) if beGnt is equal to 1, { bebuf, beBufLen } specified BE data is sent, are entered step after the completion
3。
The technical principle and advantage of technical solution of the present invention include:
The advantages of non-preemptive scheduling:
Using preemption scheduling, high-priority data frame can be generated and seize physical link, lead to lower-priority data frame
It sends and does not complete, occur a large amount of segments on network, while lower-priority data frame needs to send again, reduces bandwidth usage
Rate, thus this method use non-preemptive scheduling, eliminate it is above must not factor.
The resource reservation of TT data:
Due to the requirement that the time trigger characteristic and non-preemption of TT data are dispatched, if non-TT data frame cannot be in TT
Sending time point is sent completely before reaching it is necessary to forbid its transmission.Therefore this method defines txLenAllowed parameter to control
Make the transmission of non-TT data frame.According to above-mentioned steps, txLenAllowed curve is as shown in Figure 2.
When localClock is in the point i and ttPit that sets aside some timeiBetween when, txLenAllowed is less than 64, the control of step 8
Logic processed ensure that non-TT data frame is all forbidden sending, and guarantee that the TT data frame reached on time can be sent on time；When
When localClock=ttPiti, if the transmission data at the time point are ready for, it is switched to after being sent completely next
The sending point TT ttPitj；Otherwise switch immediately.Non- TT data frame is controlled by ttPitj.
TT data occupy fractional bandwidth in time trigger Ethernet, and the bandwidth of all data does not exceed interface bandwidth, because
There is transmission of the enough time for non-TT data frame between this two neighboring TT sending time point.
The priority scheduling of non-TT data is realized in step 8.
Claims (2)
1. the mixed scheduling method that time trigger Ethernet multi-service message is sent, which is characterized in that specifically includes the following steps:
Step 1: host is applied and end system synchronizing function is as data source, generates the primary data for needing to send；Host application
The data of generation pass through TT transmitter, RC transmitter and BE transmitter according to type respectively, be packaged into time trigger TT message,
The RC message and BE message of event trigger mechanism；The data that end system synchronizing function generates are packaged into event by PCF transmitter
The PCF message of triggering, tetra- kinds of transmitters of TT, PCF, RC and BE provide following scheduling information:
(1) tetra- kinds of transmitters of safeguard corresponding transmission buffer area respectively；
(2) .TT transmitter safeguards a transmission planning chart, includes one or more sending time points and corresponding buffering area, plan
Table is according to chronological order tissue；
(3) .PCF transmitter safeguards a transmission request signal and fixed buffer area；
(4) .RC transmitter safeguards a transmission dispatch list, the state comprising all VL；
(5) whether .BE transmitter safeguards a transmit queue, be ready to comprising BE data, the address of BE data and length；
Step 2: scheduler and all transmitter concurrent workings, it is currently transmitted plan that first item in TT planning chart, which is arranged, is jumped
To step 3；
Step 3: if end system is in synchronous regime, reading the plan of transmission, the data that can be sent before planned time point
Frame length is denoted as permission length, changes with the variation of local clock, and otherwise setting allows length to be fixed as maximum frame length,
1518 bytes.
If allowing length less than 64 bytes, step 4 is jumped to；Otherwise step 6 is jumped to；
Step 4: scheduler forbidden data is sent until planned time point, is judged whether the planning data is ready to, is, sends
After jump to step 5；Otherwise step 5 is jumped directly to.
Step 5: setting the next item down, the next item down of table tail item is header entry, to send plan, jumps to step 3；
Step 6: according to the priority of PCF, RC, BE from high to low, judging whether its data frame length is less than or equal to allows to grow
Degree, the data frame of all VL of RC business judges simultaneously, is to send a frame, jumps to step 3 after the completion, otherwise jump directly to
Step 3.
2. the mixed scheduling method that time trigger Ethernet multi-service message according to claim 1 is sent, which is characterized in that institute
State in step 1, the state of VL include RC data whether be ready to, data address, data length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811492235.1A CN109450817B (en) | 2018-12-07 | 2018-12-07 | Mixed scheduling method for time-triggered Ethernet multi-service message transmission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811492235.1A CN109450817B (en) | 2018-12-07 | 2018-12-07 | Mixed scheduling method for time-triggered Ethernet multi-service message transmission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109450817A true CN109450817A (en) | 2019-03-08 |
| CN109450817B CN109450817B (en) | 2023-04-07 |
Family
ID=65556911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811492235.1A Active CN109450817B (en) | 2018-12-07 | 2018-12-07 | Mixed scheduling method for time-triggered Ethernet multi-service message transmission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109450817B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111092712A (en) * | 2019-11-28 | 2020-05-01 | 中国航空工业集团公司西安航空计算技术研究所 | Preemptive scheduling method for time-triggered Ethernet |
| CN114448546A (en) * | 2021-12-29 | 2022-05-06 | 中国航空工业集团公司西安航空计算技术研究所 | Scheduling method of time-triggered network message based on timer |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060242252A1 (en) * | 2005-04-22 | 2006-10-26 | Shengbing Jiang | Extensible scheduling of messages on time-triggered busses |
| US20160294720A1 (en) * | 2015-04-01 | 2016-10-06 | Honeywell International Inc. | Systematic hybrid network scheduling for multiple traffic classes with host timing and phase constraints |
| CN108449285A (en) * | 2018-03-01 | 2018-08-24 | 中国航空无线电电子研究所 | Fraction dispatching method applied to shared Ethernet |
| CN108462650A (en) * | 2016-12-12 | 2018-08-28 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of output unit based on TTE interchangers |
-
2018
- 2018-12-07 CN CN201811492235.1A patent/CN109450817B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060242252A1 (en) * | 2005-04-22 | 2006-10-26 | Shengbing Jiang | Extensible scheduling of messages on time-triggered busses |
| US20160294720A1 (en) * | 2015-04-01 | 2016-10-06 | Honeywell International Inc. | Systematic hybrid network scheduling for multiple traffic classes with host timing and phase constraints |
| CN108462650A (en) * | 2016-12-12 | 2018-08-28 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of output unit based on TTE interchangers |
| CN108449285A (en) * | 2018-03-01 | 2018-08-24 | 中国航空无线电电子研究所 | Fraction dispatching method applied to shared Ethernet |
Non-Patent Citations (1)
| Title |
|---|
| EKARIN SUETHANUWONG等: "Message Fragmentation of Event-Triggered Traffic in TTEthernet Systems Using the Timely Block Method", 《2016 INTERNATIONAL CONFERENCE ON COMPUTATIONAL TECHNIQUES IN INFORMATION AND COMMUNICATION TECHNOLOGIES》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111092712A (en) * | 2019-11-28 | 2020-05-01 | 中国航空工业集团公司西安航空计算技术研究所 | Preemptive scheduling method for time-triggered Ethernet |
| CN111092712B (en) * | 2019-11-28 | 2022-04-05 | 中国航空工业集团公司西安航空计算技术研究所 | Preemptive scheduling method for time-triggered Ethernet |
| CN114448546A (en) * | 2021-12-29 | 2022-05-06 | 中国航空工业集团公司西安航空计算技术研究所 | Scheduling method of time-triggered network message based on timer |
| CN114448546B (en) * | 2021-12-29 | 2024-01-23 | 中国航空工业集团公司西安航空计算技术研究所 | Scheduling method of time-triggered network message based on timer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109450817B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6381647B1 (en) | Method and system for scheduling network communication | |
| CN110035022B (en) | AFDX (avionics full Duplex switched Ethernet) switching method and switch based on time-triggered architecture | |
| US6266702B1 (en) | Method and apparatus to insert and extract data from a plurality of slots of data frames by using access table to identify network nodes and their slots for insertion and extraction data | |
| CN1668020B (en) | Method, apparatus and system for guaranteed packet delivery times in asynchronous networks | |
| EP2466824B1 (en) | Service scheduling method and device | |
| CN106773928B (en) | A kind of gigabit TTE end system controller based on FPGA | |
| US6317415B1 (en) | Method and system for communicating information in a network | |
| EP4319055A1 (en) | Message transmission method and apparatus | |
| CN1989738A (en) | Propagation of minimum guaranteed scheduling rates | |
| US20090086737A1 (en) | System-on-chip communication manager | |
| CN109587077B (en) | Hybrid scheduling method for TTE network and TTE network terminal | |
| US20070257786A1 (en) | Sequencing multi-source messages for delivery as partial sets to multiple destinations | |
| CN103873550A (en) | Method for data transmission among ecus and/or measuring devices | |
| CN101795266A (en) | Avionics any source multicast (ASM) protocol controller | |
| US20190166058A1 (en) | Packet processing method and router | |
| CN109450817A (en) | The mixed scheduling method that time trigger Ethernet multi-service message is sent | |
| CN115022182B (en) | Real-time flow scheduling optimization method for train communication network based on QSILP algorithm | |
| CN113411242B (en) | Asynchronous multi-priority scheduling processing method under time trigger mechanism | |
| CN111404837B (en) | Data transmission control method, network equipment and system | |
| CN109525315B (en) | Optical fiber channel network end system based on time triggering | |
| CN110809012B (en) | Train network communication data scheduling control method | |
| Pleinevaux | An improved hard real-time scheduling for the IEEE 802.5 | |
| US20230412522A1 (en) | Control apparatus, resource allocation method and program | |
| CN115065646A (en) | Message timing sending method and device based on software and hardware cooperation | |
| JPH0771102B2 (en) | Method and apparatus for transmitting signaling information in LAN system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |