CN112751788B - Double-plane switching method supporting multi-type frame mixed transmission - Google Patents
Double-plane switching method supporting multi-type frame mixed transmission Download PDFInfo
- Publication number
- CN112751788B CN112751788B CN202011603675.7A CN202011603675A CN112751788B CN 112751788 B CN112751788 B CN 112751788B CN 202011603675 A CN202011603675 A CN 202011603675A CN 112751788 B CN112751788 B CN 112751788B
- Authority
- CN
- China
- Prior art keywords
- priority
- frame
- low
- port
- network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000005540 biological transmission Effects 0.000 title claims abstract description 14
- 239000000872 buffer Substances 0.000 claims abstract description 64
- 238000007781 pre-processing Methods 0.000 claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 230000003068 static effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/15—Interconnection of switching modules
- H04L49/1515—Non-blocking multistage, e.g. Clos
- H04L49/1523—Parallel switch fabric planes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2425—Traffic characterised by specific attributes, e.g. priority or QoS for supporting services specification, e.g. SLA
- H04L47/2433—Allocation of priorities to traffic types
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a biplane switching method supporting multi-type frame mixed transmission, which specifically comprises the following steps: step 1: setting a high-priority forwarding table and a low-priority forwarding table; step 2: performing MAC receiving operation on each port of the IP core; step 3: filtering the network frame obtained in the step 2 and dividing the network frame into a high priority and a low priority; step 4: respectively preprocessing a high-priority network frame and a low-priority network frame; step 5: respectively carrying out high-priority and low-priority exchange processing on data frames in the high-priority and low-priority pretreatment buffer areas of each port of the IP core; step 6: output buffer processing; step 7: and (3) performing MAC sending operation on each port of the IP core, and returning to the step (2). The method of the invention adopts two exchange planes, can work in parallel and the data are not affected each other in the exchange process, so that the efficiency of processing the data by the system is greatly improved. In addition, the output module preferentially processes the high-priority traffic, and ensures the stable transmission of the high-priority traffic.
Description
Technical Field
The invention belongs to the field of computer networks, and particularly relates to a biplane switching method supporting multi-type frame mixed transmission.
Background
After the concept of ethernet was proposed by Bao Bomei kakov in 1973, ethernet has been developed over several decades to become the most widely used communication standard in the world. The ethernet solves the information sharing in the network, establishes a channel for the mutual transmission of information in the local area network, but the traditional ethernet does not solve the real-time performance and reliability of information transmission, and especially cannot guarantee the bandwidth of the flow with high priority or higher stability requirements when the network flows with different priority and stability requirements (such as control information and audio and video information) are faced, which limits the application range and further development of the ethernet to a great extent.
The switch is used as an important ring in the network, the switch structure of the common Ethernet switch is a single switch plane, all frames are processed in a running water mode according to the sequence, frames with different priorities are processed uniformly, and frames with high priorities cannot be processed preferentially, so that the real-time performance and reliability of the frames with high priorities cannot be guaranteed.
Disclosure of Invention
In order to solve the above-mentioned problems existing in the general ethernet, the present invention is directed to a dual plane switching method supporting multi-type frame hybrid transmission.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a biplane switching method supporting multi-type frame mixed transmission specifically comprises the following steps:
step 1: setting a high-priority forwarding table and a low-priority forwarding table, wherein the specific operation is as follows:
step 11, setting a high-priority forwarding table and a low-priority forwarding table respectively in a static configuration mode, wherein configuration items comprise table item enabling, a destination MAC address, a switching destination port and a priority; all ports of the IP core share a high-priority forwarding table and a low-priority forwarding table.
Step 12, generating a plurality of forwarding table entries according to the user requirements, wherein each forwarding table entry comprises table entry enabling, a destination MAC address, a switching destination port and a priority, and writing the generated forwarding table entries into a high-priority forwarding table and a low-priority forwarding table correspondingly;
step 2: performing MAC receiving operation on each port of the IP core;
step 3: filtering the network frame obtained in the step 2 and dividing the network frame into a high priority and a low priority;
step 4: preprocessing the high-priority network frame and the low-priority network frame respectively, wherein the preprocessing operation is as follows:
setting a high-priority preprocessing buffer area and a low-priority preprocessing buffer area for each port of the IP core;
searching a corresponding high or low priority forwarding table according to the priority of the network frame obtained in the step 3, searching a corresponding exchange destination port and table entry enabling corresponding to the network frame according to the destination MAC address of the network frame, adding exchange destination port information and frame length to the frame head of the network frame if enabling exists, and writing the network frame into a corresponding high or low priority preprocessing buffer area according to the priority; if not, discarding the network frame;
step 5: the data frames in the high-priority preprocessing buffer area and the low-priority preprocessing buffer area of each port of the IP core are respectively subjected to high-priority and low-priority switching processing, and the specific operation is as follows:
polling a high-priority preprocessing buffer area of each port of the IP core, if a data frame exists, reading a frame of data frame, transmitting the data frame to an output port of a port for displaying the exchange destination port information according to the exchange destination port information of a frame header, and then executing the step 6; the reading rate is N times of the writing rate in the step 4, and N is the number of ports of the switching system; if no data frame exists, directly executing the step 6;
the same polling processing as described above for the high-priority preprocessing buffer is performed for the low-priority preprocessing buffer of each port of the IP core.
Step 6: the output buffer processing specifically comprises the following steps:
setting a high-priority output buffer and a low-priority output buffer for each port of the IP core;
writing the data frames of the output ports of each port obtained in the step 5 into a high-priority output buffer and a low-priority output buffer of each port respectively according to the priority of the data frames, and reading the buffers according to the priority;
step 7: a MAC (Media Access Control) send operation is performed on each port of the IP core. The specific operation is as follows:
converting the data frame transmitted in the step 6 into a network byte order, adding a preamble before the frame, adding a CRC field at the end of the frame, and then transmitting the frame to the network of each port of the IP core; and then returns to step 2.
Further, the specific operation of the step 2 is as follows:
for each port of the IP core, when the MAC module corresponding to the port receives the data frame in the network, the preamble of the network frame is removed, CRC check is carried out, and then the network frame is analyzed to obtain the destination MAC address, the frame type and the frame length of the network frame.
Further, the specific operation of the step 3 is as follows:
filtering the unnecessary network frames in the network frames processed in the step 2 according to the filtering requirement of the user on the frame types, and dividing the filtered network frames into high and low priorities according to the priority requirement of the user on the frame types.
Further, the writing operation in the step 6 specifically includes the following steps:
A. if the MAC module is in an idle state and the high-priority output buffer is not empty, starting to read the data frame of the high-priority output buffer, acquiring the effective actual length according to the length information carried by the data frame header, removing the frame length information carried by the frame header and the exchange destination port information when the data frame is output to the MAC module, and executing the step 7;
B. if the MAC module is in an idle state, the high-priority output buffer is empty, and the low-priority buffer is not empty, reading a data frame of the low-priority output buffer, acquiring the effective actual length according to frame length information carried by a data frame header, removing the frame length information carried by the frame header and exchange port information when the data frame is output to the MAC module, and executing the step 7;
C. if the MAC module is not in an idle state, neither the high priority output buffer nor the low priority output buffer is read.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, two exchange planes are adopted, based on the characteristic of FPGA parallel processing, the two exchange planes can work in parallel, and the two plane data are not influenced mutually in the exchange process, so that the exchange capacity of the system is effectively improved, the blockage in the exchange of the system is reduced, and the data processing efficiency of the system is greatly improved.
2. The output module preferentially processes the high-priority traffic, so that the high-priority traffic is not influenced by the low-priority traffic, and the bandwidth of the high-priority traffic is ensured. The switching mechanism is utilized in a system with higher reliability, and can ensure that the real-time high-priority traffic is not influenced by other non-real-time low-priority traffic, and ensure the stable transmission of the high-priority traffic.
Drawings
FIG. 1 is a standard network frame format;
fig. 2 is a configuration format of a high priority forwarding table and a low priority forwarding table;
FIG. 3 is a swap pre-processing buffer frame format;
fig. 4 is a schematic view of the structure of the device of the present invention.
The invention is further explained below with reference to the drawing and the specific embodiments.
Detailed Description
The invention provides a biplane switching method supporting multi-type frame mixed transmission, which specifically comprises the following steps:
step 1: setting a high-priority forwarding table and a low-priority forwarding table. The specific operation is as follows:
step 11, setting a high-priority forwarding table and a low-priority forwarding table respectively by adopting a static configuration mode, wherein as shown in fig. 2, a configuration item comprises an item enabling, a destination MAC address, a switching destination port and a priority; all ports of the IP core share a high-priority forwarding table and a low-priority forwarding table.
Step 12, generating a plurality of forwarding table entries according to the user requirements, wherein each forwarding table entry comprises table entry enabling, a destination MAC address, a switching destination port and a priority, and writing the generated forwarding table entries into a high-priority forwarding table and a low-priority forwarding table correspondingly;
step 2: a MAC (Media Access Control) receive operation is performed on each port of the IP core. The specific operation is as follows:
for each port of the IP core, when the MAC module corresponding to the port receives a data frame (hereinafter referred to as a network frame) in the network, the preamble of the network frame is removed, CRC check is performed, and then the network frame is analyzed to obtain a destination MAC address, a frame type and a frame length of the network frame; the network frame format is shown in fig. 1.
Step 3: and judging and filtering frame types. The specific operation is as follows:
filtering the unnecessary network frames in the network frames processed in the step 2 according to the filtering requirement of the user on the frame types, and dividing the filtered network frames into a high priority and a low priority according to the priority requirement of the user on the frame types;
step 4: and respectively preprocessing the high-priority network frame and the low-priority network frame. The pretreatment operation is as follows:
setting a high-priority preprocessing buffer area and a low-priority preprocessing buffer area for each port of the IP core;
searching a corresponding high or low priority forwarding table according to the priority of the network frame obtained in the step 3, searching a corresponding exchange destination port and table entry enabling corresponding to the network frame according to the destination MAC address of the network frame, adding exchange destination port information and frame length to the frame head of the network frame if enabling exists, and writing the network frame into a corresponding high or low priority preprocessing buffer area according to the priority; if not, the network frame is discarded.
Step 5: and respectively carrying out high-priority and low-priority exchange processing on the data frames in the high-priority and low-priority pretreatment buffer areas of each port of the IP core. The specific operation is as follows:
polling a high-priority preprocessing buffer area of each port of the IP core, if a data frame exists, reading a frame of data frame, transmitting the data frame to an output port of a port for displaying the exchange destination port information according to the exchange destination port information of a frame header, and then executing the step 6; the reading rate is N times of the writing rate in the step 4, and N is the number of ports of the switching system; if no data frame exists, directly executing the step 6;
the same polling processing as described above for the high-priority preprocessing buffer is performed for the low-priority preprocessing buffer of each port of the IP core.
Step 6: and outputting a caching process. The specific operation is as follows:
setting a high-priority output buffer and a low-priority output buffer for each port of the IP core;
writing the data frames of the output ports of each port obtained in the step 5 into a high-priority output buffer and a low-priority output buffer of each port respectively according to the priority of the data frames, and reading the buffers according to the priority; the specific operation of the actions is as follows:
A. if the MAC module is in an idle state and the high-priority output buffer is not empty, starting to read the data frame of the high-priority output buffer, acquiring the effective actual length according to the length information carried by the data frame header, removing the frame length information carried by the frame header and the exchange destination port information when the data frame is output to the MAC module, and executing the step 7;
B. if the MAC module is in an idle state, the high-priority output buffer is empty, and the low-priority buffer is not empty, reading a data frame of the low-priority output buffer, acquiring the effective actual length according to the frame length information carried by the data frame header, removing the frame length information carried by the frame header and the exchange port information when the data frame is output to the MAC module, and executing the step 7.
C. If the MAC module is not in an idle state, neither the high priority output buffer nor the low priority output buffer is read.
In actual operation, the high priority interrupt low priority operation is not supported, and only after the transmission of the low priority data frame is finished, the judgment of whether to send the high priority network frame is performed.
Step 7: a MAC (Media Access Control) send operation is performed on each port of the IP core. The specific operation is as follows:
converting the data frame transmitted in the step 6 into a network byte order, adding a preamble before the frame, adding a CRC field at the end of the frame, and then transmitting the frame to the network of each port of the IP core; and then returns to step 2.
In specific implementation, the method is realized based on the FPGA.
Claims (1)
1. A biplane switching method supporting multi-type frame mixed transmission is characterized by comprising the following steps:
step 1: setting a high-priority forwarding table and a low-priority forwarding table, wherein the specific operation is as follows:
step 11, setting a high-priority forwarding table and a low-priority forwarding table respectively in a static configuration mode, wherein configuration items comprise table item enabling, a destination MAC address, a switching destination port and a priority; all ports of the IP core share a high-priority forwarding table and a low-priority forwarding table;
step 12, generating a plurality of forwarding table entries according to the user requirements, wherein each forwarding table entry comprises table entry enabling, a destination MAC address, a switching destination port and a priority, and writing the generated forwarding table entries into a high-priority forwarding table and a low-priority forwarding table correspondingly;
step 2: performing MAC receiving operation on each port of the IP core; the specific operation is as follows:
for each port of the IP core, when the MAC module corresponding to the port receives a data frame in the network, the preamble of the network frame is removed, CRC check is carried out, and then the network frame is analyzed to obtain the destination MAC address, the frame type and the frame length of the network frame;
step 3: filtering the network frame obtained in the step 2 and dividing the network frame into a high priority and a low priority; the specific operation is as follows:
filtering the unnecessary network frames in the network frames processed in the step 2 according to the filtering requirement of the user on the frame types, and dividing the filtered network frames into a high priority and a low priority according to the priority requirement of the user on the frame types;
step 4: preprocessing the high-priority network frame and the low-priority network frame respectively, wherein the preprocessing operation is as follows:
setting a high-priority preprocessing buffer area and a low-priority preprocessing buffer area for each port of the IP core;
searching a corresponding high or low priority forwarding table according to the priority of the network frame obtained in the step 3, searching a corresponding exchange destination port and table entry enabling corresponding to the network frame according to the destination MAC address of the network frame, adding exchange destination port information and frame length to the frame head of the network frame if enabling exists, and writing the network frame into a corresponding high or low priority preprocessing buffer area according to the priority; if not, discarding the network frame;
step 5: the data frames in the high-priority preprocessing buffer area and the low-priority preprocessing buffer area of each port of the IP core are respectively subjected to high-priority and low-priority switching processing, and the specific operation is as follows:
polling a high-priority preprocessing buffer area of each port of the IP core, if a data frame exists, reading a frame of data frame, transmitting the data frame to an output port of a port for displaying the exchange destination port information according to the exchange destination port information of a frame header, and then executing the step 6; the reading rate is N times of the writing rate in the step 4, and N is the number of ports of the switching system; if no data frame exists, directly executing the step 6;
for the low-priority preprocessing buffer area of each port of the IP core, carrying out the same polling processing as the high-priority preprocessing buffer area;
step 6: the output buffer processing specifically comprises the following steps:
setting a high-priority output buffer and a low-priority output buffer for each port of the IP core;
writing the data frames of the output ports of each port obtained in the step 5 into a high-priority output buffer and a low-priority output buffer of each port respectively according to the priority of the data frames, and reading the buffers according to the priority; the writing operation specifically comprises the following steps:
A. if the MAC module is in an idle state and the high-priority output buffer is not empty, starting to read a data frame of the high-priority output buffer, acquiring an effective actual length according to length information carried by a data frame header, removing frame length information carried by the frame header and exchange destination port information when the data is output to the MAC module, and executing step 7;
B. if the MAC module is in an idle state, the high-priority output buffer is empty, and the low-priority buffer is not empty, reading a data frame of the low-priority output buffer, acquiring the effective actual length according to frame length information carried by a data frame header, removing the frame length information carried by the frame header and exchange port information when the data frame is output to the MAC module, and executing the step 7;
C. if the MAC module is not in an idle state, the data frames in the high-priority output buffer and the low-priority output buffer are not read;
in actual operation, the operation of interrupting low priority by high priority is not supported, and only after the transmission of the low priority data frame is finished, the judgment of whether to send the high priority network frame is performed;
step 7: MAC (Media Access Control) sending operation is performed on each port of the IP core, and the specific operation is as follows:
converting the data frame transmitted in the step 6 into a network byte order, adding a preamble before the frame, adding a CRC field at the end of the frame, and then transmitting the frame to the network of each port of the IP core; and then returns to step 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011603675.7A CN112751788B (en) | 2020-12-30 | 2020-12-30 | Double-plane switching method supporting multi-type frame mixed transmission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011603675.7A CN112751788B (en) | 2020-12-30 | 2020-12-30 | Double-plane switching method supporting multi-type frame mixed transmission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112751788A CN112751788A (en) | 2021-05-04 |
| CN112751788B true CN112751788B (en) | 2023-11-14 |
Family
ID=75647681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011603675.7A Active CN112751788B (en) | 2020-12-30 | 2020-12-30 | Double-plane switching method supporting multi-type frame mixed transmission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112751788B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114826303B (en) * | 2021-12-21 | 2024-04-12 | 航天科工通信技术研究院有限责任公司 | Data demodulation system based on high priority frame |
| CN114401238B (en) * | 2021-12-27 | 2024-02-06 | 西安电子科技大学 | Switch management control method, system, computer equipment and data processing terminal |
| CN114448574A (en) * | 2022-03-03 | 2022-05-06 | 湖南军安信达科技有限公司 | MAC frame data transmission processing equipment and data transmission processing method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7502366B1 (en) * | 2000-05-23 | 2009-03-10 | Advanced Micro Devices, Inc. | Arrangement in a network switch for prioritizing data frames based on user-defined frame attributes |
| CN103916252A (en) * | 2014-04-18 | 2014-07-09 | 岳阳巅峰电子科技有限责任公司 | High-bandwidth Ethernet IP core based on FPGA |
| CN104717159A (en) * | 2013-12-14 | 2015-06-17 | 中国航空工业集团公司第六三一研究所 | Scheduling method based on store-and-forward switching structure |
| CN105634986A (en) * | 2014-11-30 | 2016-06-01 | 中国科学院沈阳自动化研究所 | Switch implementation method and system |
| CN111917666A (en) * | 2020-07-27 | 2020-11-10 | 西安电子科技大学 | Data frame preemptive cache management method based on service level protocol |
-
2020
- 2020-12-30 CN CN202011603675.7A patent/CN112751788B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7502366B1 (en) * | 2000-05-23 | 2009-03-10 | Advanced Micro Devices, Inc. | Arrangement in a network switch for prioritizing data frames based on user-defined frame attributes |
| CN104717159A (en) * | 2013-12-14 | 2015-06-17 | 中国航空工业集团公司第六三一研究所 | Scheduling method based on store-and-forward switching structure |
| CN103916252A (en) * | 2014-04-18 | 2014-07-09 | 岳阳巅峰电子科技有限责任公司 | High-bandwidth Ethernet IP core based on FPGA |
| CN105634986A (en) * | 2014-11-30 | 2016-06-01 | 中国科学院沈阳自动化研究所 | Switch implementation method and system |
| CN111917666A (en) * | 2020-07-27 | 2020-11-10 | 西安电子科技大学 | Data frame preemptive cache management method based on service level protocol |
Non-Patent Citations (3)
| Title |
|---|
| FC交换机中优先级技术的研究和实现;李大鹏等;《测控技术》;20151218(第12期);全文 * |
| H. Shah ; Cinea Corp. ; E. Rosen ; Juniper Networks ; F. Le Faucheur ; G. Heron ; Cisco Systems ; .IP-Only LAN Service (IPLS).IETF rfc7436.2015,全文. * |
| 一种带优先级队列的千兆以太网MAC设计;董继承等;《电子设计工程》;20110420(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112751788A (en) | 2021-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112751788B (en) | Double-plane switching method supporting multi-type frame mixed transmission | |
| US6731652B2 (en) | Dynamic packet processor architecture | |
| CN109194679B (en) | Multi-protocol interface data acquisition device and acquisition method based on SpaceFibre interface | |
| CN100553199C (en) | Method of realizing group broadcasting, system and equipment based on the PCIE switching network | |
| CN108809864B (en) | Multi-line card high-density TAP switch based on FPGA | |
| CN101707544A (en) | E1 channel multidirectional network bridge transmission device and method | |
| EP3188419B1 (en) | Packet storing and forwarding method and circuit, and device | |
| JP2000269997A (en) | Lan repeating exchange device | |
| CN114827292B (en) | Industrial heterogeneous protocol high-speed conversion optimization processing method and system | |
| US5832236A (en) | High speed frame translation for computer networks | |
| CN114422617B (en) | Message processing method, system and computer readable storage medium | |
| CN113300800B (en) | Multi-mode deterministic data processing device and method | |
| CN106254018B (en) | High speed signal receives the integrated system and data processing method with demultiplexing | |
| CN107196879B (en) | UDP message processing method and device and network forwarding device | |
| WO2017088489A1 (en) | Data message transmission method and system, and communication system | |
| CN116346720A (en) | Information transmission device and method | |
| CN109450823B (en) | Network large-capacity switching device based on aggregation type cross node | |
| CN101296189A (en) | Distributed stream processing network appliance and packet transmission method thereof | |
| CN109274605B (en) | Synchronous transmission method suitable for packet switching network | |
| CN114500581B (en) | Method for realizing equal-delay distributed cache Ethernet MAC architecture | |
| CN116489113B (en) | Port expanding method and system of switch chip and switch | |
| WO2022121454A1 (en) | Traffic table sending method and related apparatus | |
| CN114513381B (en) | AF_XDP-based real-time Ethernet field bus data packet processing method | |
| CN113422741B (en) | Time-triggered Ethernet switch structure | |
| CN112073291B (en) | Jitter-free link layer message insertion device and method |
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 |