CN108011694B - A kind of efficient data exchange method based on FC - Google Patents
A kind of efficient data exchange method based on FC Download PDFInfo
- Publication number
- CN108011694B CN108011694B CN201711225376.2A CN201711225376A CN108011694B CN 108011694 B CN108011694 B CN 108011694B CN 201711225376 A CN201711225376 A CN 201711225376A CN 108011694 B CN108011694 B CN 108011694B
- Authority
- CN
- China
- Prior art keywords
- state machine
- port
- data
- layers
- frame
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0006—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/25—Arrangements specific to fibre transmission
- H04B10/2589—Bidirectional transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0009—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the channel coding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0056—Systems characterized by the type of code used
- H04L1/0061—Error detection codes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/12—Applying verification of the received information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/565—Conversion or adaptation of application format or content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/568—Storing data temporarily at an intermediate stage, e.g. caching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/22—Parsing or analysis of headers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L7/00—Arrangements for synchronising receiver with transmitter
- H04L7/0008—Synchronisation information channels, e.g. clock distribution lines
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Communication Control (AREA)
Abstract
The invention discloses a kind of, and the efficient data based on FC exchanges method, including:Utilize the conversion module of FC-0 layers in FPGA design FC agreement of high-speed serial datas to low-speed parallel data, high-speed serial digital signal can be converted into the parallel data of relative low speeds by the module, while debounce, locking and the recovery of reference clock are completed by the state machine of design;Using FC-1 layers in FPGA design FC agreement of 8b/10b encoding and decoding, the alignment of transmission word boundary and the detection of transmission word legitimacy, primitive detection, the control of receiver state machine, FC port state machine and transmitter status machine, to guarantee jumping for FC port status;Using FC-2 layers in FPGA design FC agreement of Frame Protocol parsing module, which can complete the parsing, registration and unregistration, buffer area of Frame Protocol to the flow control of buffer area, to guarantee the legitimacy of frame transmission.
Description
Technical field
Present invention relates particularly to a kind of, and the efficient data based on FC exchanges method, belongs to electronic engineering and computer science neck
Domain.
Background technique
With the development of information technology, big data processing has become the key technology of support upper layer decision.Especially exist
Intelligence manufacture field, " made in China 2025 " and " internet+advanced of German Industrial 4.0, American industry internet and China
The intelligence manufacture to be realized is not without a large amount of data are included in manufacturing industry ", acquisition including workshop level bottom isomeric data,
It handles and transmits, the data transmission between factory level ERP, MES and the data transmission between factory etc..How big data is realized
Efficient process is come to support upper layer decision be to realize that intelligence manufacture needs one of the critical issue that solves.There is a large amount of for plant site
Heterogeneous resource, the sensing of the lathe of production line, different model including different manufacturers and different agreement executes equipment how
Efficiently realizing the data exchange between these heterogeneous resources again is one of the key technology for realizing big data efficient process.
With the development of information technology, there are many Data Transport Protocol standards, including common Industrial Ethernet,
Modbus and Zigbee etc., but in terms of the efficiency of data processing, FC (Fiber Channel, optical-fibre channel) agreement tool
Standby great advantage.FC has many advantages, such as high bandwidth, low latency, long distance transmission, topological flexible, a variety of upper-layer protocols of support,
It is the communication protocol for being adaptation high-performance data transmission requirement and designing.
FC is applied at present in the advanced fighter of the states such as America and Europe, is aviation electronic bus agreement of new generation, is capable of providing
The support of unified avionics network of new generation building under avionics system.American National Standard Committee also specially sets up
Research optical-fibre channel is used for the sub-committee (ANSI FC-AE) of avionics system, the sub-committee and Boeing, Lip river
The cooperations such as gram West Germany-Martin Corporation have formulated one group dedicated for the FC protocol subset of avionics system, i.e. optical-fibre channel is navigated
Empty electronic environment (FC-AE).Optical-fibre channel substitutes current aviation electronics major network MIL-STD-1553, it has also become aviation electronics system
The inexorable trend of system development, optical-fibre channel will also become the first choice of the unified avionics network of building a new generation.FPGA conduct
Programmable hardware logic devices have the parallel processing and hardware-accelerated characteristic of height, are conducive to the realization of FC agreement.
So advanced efficient FC agreement is applied to civil field, realize that the efficient data of manufacture bottom heterogeneous resource are handed over
It changes, is capable of the realization early of the great strategy of power-assisted China intelligence manufacture.
Summary of the invention
The technical problem to be solved in the present invention is:A kind of efficient data exchange method based on FC is provided, including:It utilizes
For FC-0 layers of high-speed serial data to the conversion module of low-speed parallel data, which can be by high speed in FPGA design FC agreement
Serial digital signal is converted into the parallel data of relative low speeds, at the same by the state machine of design complete reference clock debounce,
Locking and recovery;Utilize FC-1 layers in FPGA design FC agreement of 8b/10b encoding and decoding, the alignment of transmission word boundary and transmission word
Legitimacy detection, primitive detection, the control of receiver state machine, FC port state machine and transmitter status machine, to guarantee the end FC
Mouth state jumps;Using FC-2 layers in FPGA design FC agreement of Frame Protocol parsing module, which can complete Frame Protocol
Parsing, registration and unregistration, the flow control of buffer area to buffer area, with guarantee frame transmission legitimacy.
The present invention solves its technical problem and adopts the following technical solutions to achieve:A kind of efficient data exchange based on FC
Method includes the following steps:
Step 1:Design conversion module of FC-0 layers in FC agreement of the high-speed serial data to low-speed parallel data, the mould
High-speed serial digital signal can be converted into the parallel data of relative low speeds by block, while complete reference by the state machine of design
Debounce, locking and the recovery of clock.It is implemented as follows:
1. designing module work under the rate of 8.5Gbps, the phaselocked loop of QPLL is selected, keeps FC-0 serioparallel exchange module each
CHANNEL (channel) shares same reference clock;
2. utilizing the debounce state machine of FPGA design reference clock, and goes here and there and turn using the clock output after debounce as FC-0
Change the mold the reference clock of block.Debounce state machine controls debounce chip by IIC agreement.According to designing in 1.
8.5Gbps operating rate, the reference clock after the debounce designed herein are 212.5MHZ.K28.5 is designed as control word simultaneously
Section, clock correction sequence are 10111100 " of ".
Step 2:Design FC-1 layers in FC agreement of 8b/10b encoding and decoding, transmission word boundary is aligned and transmission word is legal
Property detection, primitive detection, receiver state machine, FC port state machine and transmitter status machine control, to guarantee the port FC shape
State jumps.It is implemented as follows:
1. the encoding and decoding for being arranged FC-1 layers are the inside bit wide (outside of 32bit of the code encoding/decoding mode of 8B/10B, 40bit
Bit wide), the reference clock of 212.5MHZ, K28.5 as comma, and in a program examine comma whether be in the low of 40bit
8bit。
2. being designed using VHDL language, multiple subroutine modules simultaneously and concurrently complete the detection of transmission word legitimacy, primitive is examined
Survey, receiver state machine, FC port state machine and transmitter status machine.State machine is broadly divided into receiver state machine, transmitter
State machine, port state machine.Data are completed after serioparallel exchange and encoding and decoding by FC-0 serioparallel exchange module with 32bit (one
Word) it is sent to receiver state machine, receiver operation clock is 212.5MHZ.FC port state machine is completed the activation of link and is led to
Cross a series of handshake mechanism completion status conversions.After device power or entrance reset state, the port FC can be held by a series of
Mobile phone system enters activated state by non-initialization state, to start normal data communication.Gear send data when, data with
32bit (word) is sent to transmitter status machine, and transmitter work clock is 233.33MHZ.
Step 3:Design FC-2 layers of Frame Protocol parsing module in FC agreement, the module can complete Frame Protocol parsing,
Registration and unregistration, the flow control of buffer area to buffer area, to guarantee the legitimacy of frame transmission.It is implemented as follows:
1. the port FC is after FC-1 layers of completion link activation, data are uploaded to FC-2 layers.FC-2 layers first carry out frame
Parsing, frame includes SOF delimiter, frame head, payload, cyclic redundancy check field CRC, EOF delimiter.Process registers (PRLI) shape
The port of communicating pair can be passed through mapping association composition mapping pair by state machine;Process nullifies (PRLO) state machine and is used to release this
Kind mapping relations.The present invention is nullified using implicit, is nullified by continuously transmitting three or more NOS or OLS signals.
2. FC communication port both sides decide through consultation a credit value in advance, synchronized for the communication to both sides.Work as sender
After sending a frame data, count value adds 1, and count value subtracts 1 after receiving effective reply of other side.When count value is equal to credit value,
Sender, which suspends, to be sent, and is then sent state machine and is continued to monitor count value, and data are again started up when it is less than credit value and are sent.
A kind of efficient data exchange method based on FC that the present invention designs is suitable for Xilinx company Virtex-7FPGA
Chip, model XC7VX690T-2FFG1761C;Clock jitter removing chip is the SI5324 of SiLABS company.
The advantages of the present invention over the prior art are that:
(1) the FC-0 serioparallel exchange module of designed, designed can replace the gigabit used in such method design at present to pass
The method of defeated IP kernel, can be more flexible, economical design high-speed serial data to low-speed parallel data conversion.
(2) data correctness when clock jitter removing scheme used can guarantee high speed data transfer, the transmission for data
The reference clock of different frequency is used with reception, and the stability of data transmit-receive can guarantee as buffering using BRAM.
(3) guarantee that the rate-matched of communicating pair, the method are simple and easy using credit value and transmission frame count value.
Detailed description of the invention
Fig. 1 is overall construction drawing of the invention;
Fig. 2 is FC-0 layers of serioparallel exchange module reference clock connection figure of the present invention;
Fig. 3 is FC-1 layer state machine part-structure design drawing of the present invention;
Fig. 4 is FC-2 layers of registration part flow chart of the present invention;
Fig. 5 is FC-2 layers of part-structure design drawing of the present invention.
Specific embodiment
Further detailed description is done to the present invention with reference to the accompanying drawing.
The present invention relates to a kind of, and the efficient data based on FC exchanges method, and the fpga chip used is Xilinx company
XC7VX690T-2FFG1761C, clock jitter removing chip are the SI5324 of SiLABS company.It is as follows that content is embodied:
FC-0 layers:The conversion of fiber-optic signal and electric signal is completed using SFP module.FC-0 is the bottom of FC, i.e. physics
Link layer, including transmission medium, transmitter, receiver and interface, it is general support with cable or optical cable connection, it is specified that transmission
Rate is the multiple proportion of 1.0625Gbps.FC-0 serioparallel exchange state machine is designed based on FPGA and using VHDL language, with reality
Conversion of the existing high-speed serial signals to low-speed parallel data.
The relevant configuration of the FC-0 serioparallel exchange module of design is as follows:The rate of 8.5Gbps, the CHANNEL being connected with SFP
Positioned at BANK113.It is 8.5Gbps for rate, selects the phaselocked loop of QPLL, make each CHANNEL with same reference clock.FC-0
The design of serioparallel exchange module is verified using loopback test, including proximal end PCS, proximal end PMA, distal end PCS, distal end PMA.Selection
REFCLK0 is reference clock, and by SI5324 chip to reference clock debounce.Wherein when the reference of FC-0 serioparallel exchange module
Clock cut-in method is as shown in Fig. 2, system clock divide and be connected on debounce chip SI5324 by DCM IP kernel by FPGA, use
IIC protocol configuration SI5324 chip completes debounce, then clock is connected back at FC-0 serioparallel exchange module.Iic bus includes
Two signal line of SDA, SCL, SCL control clock, and SDA transmits data, and all data are with the transmission of 8bit byte.Utilize IIC agreement
It is fashionable to specified register write, device address to be configured is first write, then write the address of register corresponding position to be configured to, then write number
According to.IIC agreement of the invention selects a general line system chip U52 to configure by PCA9548IIC eight, and PCA9548 chip address is "
1110100 ", it include 8 channels IIC, configuration U52 chip will then use CH7, first to PCA9548 chip and Si5324 chip
Reset operation is carried out, two chips are that high level is to work normally.Pass through IIC protocol format later for IIC_SDA/SCL_
MAIN is connected with Si5324_SDA/SCL, and Slave Address is " 1110100 ", Control Register be "
10000000 " selection CH7 is indicated.Last IIC communication standard protocol is written to Si5324 chip register to be configured.This
When device address be " 1101000 ", the i.e. address of Si5324 chip.The N1_HS of Si5324 is 6, NC1_LS 6, and N2_HS is
9, N2_LS 316, N31 79.The reference clock REFCLK0 that can be detected FC-0 serioparallel exchange module after configuration is
212.5MHZ.Proximal end winding may be implemented at this time.Balanced mode selects LMP low-power consumption mode, to be suitable for line rate<
The short-range applications of 11.2Gb/s, channel differential loss<The case where 12dB.After selecting this mode, proximal end winding can be multiple in selection
Normal use in the case where channel.Interrupt voltage selects FLOAT, and CDR is locked at this time, and remote loop may be implemented.Due to FC
Agreement only uses K28.5 as control byte, so selecting comma for K28.5, clock correction sequence is 10111100 " of ", this
When transmission word can be with snap border.Loop back mode can be set as normal mode after loopback test.
FC_1 layers:FC-0 serioparallel exchange module is configured according to FC agreement, FC-0 serioparallel exchange module is made to complete 8b/
10b encoding and decoding, transmission word boundary alignment.It is set as the code encoding/decoding mode of 8B/10B, (32bit's is outer for the inside bit wide of 40bit
Position is wide), the reference clock of 212.5MHZ, K28.5 as comma, and in a program examine comma whether be in the low of 40bit
8bit completes encoding and decoding, word alignment with this.
Multiple subroutine modules simultaneously and concurrently, which are designed, using VHDL language completes the detection of transmission word legitimacy, primitive inspection
Survey, receiver state machine, FC port state machine and transmitter status machine.As shown in figure 3, state machine is broadly divided into receiver state
Machine, transmitter status machine, port state machine.Data by FC-0 serioparallel exchange module complete after serioparallel exchange and encoding and decoding with
The rxdata of 32bit is sent to receiver state machine, and transmission clock clk2 is 212.5MHZ.Receiver state machine includes primitive
Table is primitive, general data or illegal data with detection data.State machine includes 3 states:(1) synch lost state.
(2) word synchronous regime is obtained.(3) reset state.Wherein obtain word synchronous regime includes 4 sub- states again, is respectively:(1) do not have
There is illegal transmissions word to be detected.(2) the 1st illegal transmissions words are detected.(3) the 2nd illegal transmissions words are detected.
(4) the 3rd illegal transmissions words are detected.Only when state machine is in synchronous regime, transmission word, word clock could be believed
Number, validity information pass to upper layer.Data are carried out after legitimacy detection in receiver state machine with 32bit's (word)
Rx_out is uploaded to port state machine rx_in.The activation that port state machine completes link completes shape by a series of handshake mechanisms
State conversion.When device power or enter reset state after, the port FC can by a series of handshake mechanisms by non-initialization state into
Enter activated state, to start normal data communication.In the normal course of work, if dropout has occurred, request is super
When, when the abnormal conditions such as link failure or step-out, there is corresponding mechanism in the port FC to carry out recovery link, the behaviour such as investigation failure
Make.When port state machine is activated state, rx_out is to upper-layer protocol for bottom data upload, the upper-layer protocol data to be sent
Tx_in is sent by transmitter status machine.When port state machine is not in activated state, then sent by transmitter status machine a series of
Primitive agreement.Transmitter status machine state mainly includes three states:Invalid state, operating conditions, fault case.When state machine is in work
Attempt to send by the bit data stream of coding the port shape to corresponding FC chain road transmitter status machine in operating conditions when posing
The data tx_out that state machine is sent is sent to txdata_in.Data reach FC-0 by transmitter status machine with txdata_out
Layer serioparallel exchange module.System clock clk1 is 233.33MHZ.
FC-2 layers:The parsing of multiple subroutine modules completion Frame Protocols simultaneously and concurrently is designed using VHDL language and is set
Meter, registration and unregistration, the flow control of buffer area to buffer area.FC-2 layers mainly define link traffic and signaling protocol two
The behavior and parameter of aspect.Defined in link traffic the main ports behaviors such as Fabric Login, port registration, process registers and
Parameter meaning defines the composed structure of frame, the definition of frame head parameter, frame transmission process, N-port and the end F in signaling protocol
The behavior of mouth, the method etc. of flow control.The data of FC-2 are as unit of frame.The invention mainly relates to device data frame and extensions
Link data frame.Device data is used to transmit data between port;Extension link data is used to extend link service command, including
Port and switching fabric registration and unregistration stop to exchange, request transmission state etc..As shown in Figure 4 and Figure 5, port is at FC-1 layers
After completing link activation, data are uploaded to FC-2 layers.FC-2 first parses frame, frame include SOF delimiter, frame head,
Payload, cyclic redundancy check field CRC, EOF delimiter.The frame head of extension link service data frame includes that a large amount of needs are negotiated
Port information, needs communication network to distribute port address, and payload is filled by fixed communication parameter;The frame head of data frame uses fixation
Parameter, payload are filled by user.Registration switching fabric registration is completed after parsing to frame, determines network operating parameters.With Fig. 4
For, port sends Fabric Login extension link service request (FLOGI), when port is in switching fabric but other side port
When not supporting N-port to distribute, other side can reply the reject frame of a F_RJT.Port will do it second of framework after receiving F_RJT
Until other side replys ACC.N-port distribution is supported when port is in switching fabric and other side port, can reply an ACC confirmation
Frame, and distribute ID.When port is in point-to-point topology, other side port can reply an ACC acknowledgement frame and be shown to be a N-terminal
Mouthful.Port can and each want that the N-port communicated is registered after completing exchange registration, and if it is N-port, two-port can compare end
Mouth title, a WWN big side will initiate PLOGI frame, and another party waits and replys ACC.If other side is the port F, N-port passes through
Fabric Login knows that other those N-ports are available, sends PLOGI to destination port, and after receiving ACC, port registration terminates.Knot
Process registers can also be carried out after the completion of structure registration and port registration, after can directly mapping an information unit to N-port
Scsi target.Process registers (PRLI) order allows the subsequent one or more in the port A to map mapping association corresponding with the port B
Composition mapping pair;Process nullifies (PRLO) order and is used to release this operative relationship.Need to pass through cancellation after the completion of port communication
Release topological relation.The present invention is nullified using implicit, is nullified by continuously transmitting three or more NOS or OLS signals.To guarantee
Port will not receive the information more than its ability to accept, and communication system will use flow control.The present invention using buffer area to delay
Rush the flow control in area.Design has frame transmitting counter BB_credit_cnt in transmitter.It, which is counted, when initial resets, and works as hair
After the side of sending sends a frame data, counter can add 1, can subtract 1 after receiving the R_RDY of other side.Communicating pair is discussed slow in registration
Area reliability BB_credit is rushed, stops sending when counter reaches BB_credit.And first write-in is slow as long as having frame by other side
It deposits, sends R_RDY after reading a burst of and reply, can receive next frame.
In conclusion a kind of efficient data exchange method based on FC that the present invention designs, including:Utilize FPGA design
FC-0 layers of high-speed serial data to low-speed parallel data conversion module, design FC-1 layers of encoding and decoding and port state machine control
System designs FC-2 layers of Frame Protocol parsing module to complete the parsing, registration and unregistration, buffer area of Frame Protocol to the stream of buffer area
Amount control, to guarantee the legitimacy of frame transmission, the efficient exchange of realization data that can be more flexible, economic.
The content that description in the present invention is not described in detail belongs to the prior art well known to professional and technical personnel in the field.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (2)
1. a kind of efficient data based on FC exchanges method, which is characterized in that include the following steps:
Step 1:Design conversion module of FC-0 layers in FC agreement of the high-speed serial data to low-speed parallel data, the module energy
Enough parallel datas that high-speed serial digital signal is converted into relative low speeds, while reference clock is completed by the state machine of design
Debounce, locking and recovery, be implemented as follows:
1. designing module work under the rate of 8.5Gbps, the phaselocked loop of QPLL is selected, each channel of FC-0 serioparallel exchange module is made
Share same reference clock;
2. utilizing the debounce state machine of FPGA design reference clock, and using the clock output after debounce as FC-0 serioparallel exchange mould
The reference clock of block, debounce state machine control debounce chip by IIC agreement, according to 1. middle design in 8.5Gbps
Operating rate, the reference clock after the debounce designed herein is 212.5MHZ, while designing K28.5 as control byte, clock
Correction sequence is 10111100 " of ";
Step 2:Design FC-1 layers in FC agreement of 8b/10b encoding and decoding, the alignment of transmission word boundary and transmission word legitimacy inspection
It surveys, primitive detection, the control of receiver state machine, FC port state machine and transmitter status machine, to guarantee FC port status
It jumps, is implemented as follows:
1. the encoding and decoding for being arranged FC-1 layers be the code encoding/decoding mode of 8B/10B, 40bit inside bit wide 32bit external bit wide,
As comma, and in a program, whether inspection comma is in the low 8bit of 40bit to reference clock, the K28.5 of 212.5MHZ;
2. using VHDL language design multiple subroutine modules simultaneously and concurrently complete the detection of transmission word legitimacies, primitive detection,
Receiver state machine, FC port state machine and transmitter status machine, state machine are broadly divided into receiver state machine, transmitter status
Machine, port state machine, data after FC-0 serioparallel exchange module completion serioparallel exchange and encoding and decoding with mono- word of 32bit by being transmitted
To receiver state machine, receiver operation clock is 212.5MHZ, and FC port state machine completes the activation of link and passes through a system
The conversion of column handshake mechanism completion status, after device power or entrance reset state, the port FC can pass through a series of handshake mechanisms
Activated state is entered by non-initialization state, to start normal data communication, when sending out data, data are with 32bit mono-
Word is sent to transmitter status machine, and transmitter work clock is 233.33MHZ;
Step 3:FC-2 layers in FC agreement of Frame Protocol parsing module is designed, which can complete the parsing of Frame Protocol, registration
It is implemented as follows with cancellation, the flow control of buffer area to buffer area with guaranteeing the legitimacy of frame transmission:
1. the port FC is after FC-1 layers of completion link activation, data are uploaded to FC-2 layers, and FC-2 layers first parse frame,
Frame includes SOF delimiter, frame head, payload, cyclic redundancy check field CRC, EOF delimiter, process registers (PRLI) state machine
The port of communicating pair can be passed through mapping association composition mapping pair;Process nullifies (PRLO) state machine and is used to release this reflect
Relationship is penetrated, is nullified using implicit, is nullified by continuously transmitting three or more NOS or OLS signals;
2. FC communication port both sides decide through consultation a credit value in advance, synchronized for the communication to both sides, when sender sends
After one frame data, count value adds 1, and count value subtracts 1 after receiving effective reply of other side, when count value is equal to credit value, sends
Side's pause is sent, and is then sent state machine and is continued to monitor count value, and data are again started up when it is less than credit value and are sent.
2. a kind of efficient data based on FC as described in claim 1 exchanges method, it is characterised in that:The method is applicable in
In Xilinx company Virtex-7FPGA chip, model XC7VX690T-2FFG1761C;Clock jitter removing chip is SiLABS public
The SI5324 of department.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711225376.2A CN108011694B (en) | 2017-11-29 | 2017-11-29 | A kind of efficient data exchange method based on FC |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711225376.2A CN108011694B (en) | 2017-11-29 | 2017-11-29 | A kind of efficient data exchange method based on FC |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108011694A CN108011694A (en) | 2018-05-08 |
CN108011694B true CN108011694B (en) | 2018-11-20 |
Family
ID=62054743
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711225376.2A Active CN108011694B (en) | 2017-11-29 | 2017-11-29 | A kind of efficient data exchange method based on FC |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108011694B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108829620B (en) * | 2018-05-28 | 2019-05-17 | 北京航空航天大学 | A kind of exception small data acquisition method |
CN108809845B (en) * | 2018-05-28 | 2019-06-25 | 北京航空航天大学 | A kind of data transmission stream amount control method based on FC |
CN109995423A (en) * | 2019-03-12 | 2019-07-09 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of FC-AE-ASM parallel redundant system and its data processing method |
CN110347630B (en) * | 2019-05-29 | 2021-05-11 | 深圳市紫光同创电子有限公司 | Receiving circuit, reconfigurable method of receiving circuit and state machine system |
CN112148652B (en) * | 2020-09-15 | 2023-10-13 | 北京神州飞航科技有限责任公司 | FC protocol layering architecture implementation method |
CN113110882B (en) * | 2021-04-15 | 2023-02-28 | 山东英信计算机技术有限公司 | Method, device and system for managing FC port operation in FC drive |
CN113490080A (en) * | 2021-06-28 | 2021-10-08 | 天津津航计算技术研究所 | Multi-port FC switching host and switching method |
CN113438568B (en) * | 2021-06-28 | 2023-01-24 | 天津津航计算技术研究所 | FC exchange host device and exchange method |
CN113810109B (en) * | 2021-10-29 | 2022-09-27 | 西安微电子技术研究所 | Multi-protocol multi-service optical fiber channel controller and working method thereof |
CN115276795B (en) * | 2022-09-27 | 2022-11-29 | 中国人民解放军国防科技大学 | Multi-specification OTN signal monitoring processing card and signal monitoring method |
CN116015543A (en) * | 2022-12-08 | 2023-04-25 | 天津津航计算技术研究所 | Bus type FC network data quick recovery method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1731730A (en) * | 2005-08-15 | 2006-02-08 | 华中科技大学 | Kern memory exchange platform system for mass memory system |
CN104618207A (en) * | 2015-01-08 | 2015-05-13 | 中国科学院空间应用工程与技术中心 | Heterogeneous FC-AE-1553 network system and exchange method |
CN107196864A (en) * | 2014-08-12 | 2017-09-22 | 烽火通信科技股份有限公司 | A kind of multichannel FC business long distance transmitters based on FPGA |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8180856B2 (en) * | 2006-09-14 | 2012-05-15 | Ixia | Testing a network |
CN102098103B (en) * | 2010-12-02 | 2013-04-24 | 西北工业大学 | Direct interface method of fiber channel (FC) bus and high-speed intelligent unified bus |
-
2017
- 2017-11-29 CN CN201711225376.2A patent/CN108011694B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1731730A (en) * | 2005-08-15 | 2006-02-08 | 华中科技大学 | Kern memory exchange platform system for mass memory system |
CN107196864A (en) * | 2014-08-12 | 2017-09-22 | 烽火通信科技股份有限公司 | A kind of multichannel FC business long distance transmitters based on FPGA |
CN104618207A (en) * | 2015-01-08 | 2015-05-13 | 中国科学院空间应用工程与技术中心 | Heterogeneous FC-AE-1553 network system and exchange method |
Also Published As
Publication number | Publication date |
---|---|
CN108011694A (en) | 2018-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108011694B (en) | A kind of efficient data exchange method based on FC | |
CN106612141B (en) | A kind of fiber channel protocol common simulation test card and its data interactive method | |
CN103905281B (en) | FC-AE-1553 bus node card capable of interchangeably achieving functions of network controller and network terminal | |
CN202035013U (en) | Multiple E1-Ethernet protocol converter based on GFP | |
CN102761396B (en) | High-speed serial interface based on FPGA (Field Programmable Gate Array) | |
CN109194679B (en) | Multi-protocol interface data acquisition device and acquisition method based on SpaceFibre interface | |
WO2016119525A1 (en) | Elastic data interaction integrated bus system | |
CN105743566B (en) | A kind of double-PON port ONU optical link pretection switch devices and guard method | |
CN107831702B (en) | A kind of synchronous serial signal acquisition and control device based on gigabit Ethernet | |
CN102185833B (en) | Fiber channel (FC) input/output (I/O) parallel processing method based on field programmable gate array (FPGA) | |
Tao et al. | A field programmable gate array implemented fibre channel switch for big data communication towards smart manufacturing | |
CN109120624A (en) | A kind of more plane loose coupling high band wide data exchange systems | |
CN205320075U (en) | Multi -service digit optical transmitter and receiver based on optic fibre ethernet | |
CN104780333A (en) | High-bandwidth video source interface adaptation device based on FPGA (Field Programmable Gate Array) | |
CN104009867A (en) | Optical fiber Ethernet intelligent branching unit switching method based on FPGA | |
CN106817249A (en) | The simulation communication demo systems of FC AE 1553 and data transmission method for uplink | |
CN112865880B (en) | System and method for one-way data transmission through optical port | |
CN102263594B (en) | Method for realizing information interaction by RS232 and RS485 communication modes in optical network unit | |
WO2014205936A1 (en) | Sampling and control method based on point-to-point message synchronization | |
US9455867B2 (en) | Automatic configuration of a repeater | |
CN106168933B (en) | A method of virtual dual-port shared drive is realized based on high-speed serial communication | |
CN107094150A (en) | A kind of NCSI protocol realizations structure and method | |
EP1388952B1 (en) | Transceiver having shadow memory facilitating on-transceiver collection and communication of local parameters | |
CN105306421A (en) | PCI-E interface based signal processing method and PCI-E interface based signal processing device | |
CN101355589B (en) | Ethernet equipment, Ethernet communication system and method for configuring Ethernet equipment |
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 |