Ethernet frame transmission system based on fc switch with fusion port

Abstract

The application provides an Ethernet frame transmission system based on FC switches with fusion ports, comprising: at least one first FC switch, configured with an Ethernet MAC port and an FC_MAC port; at least one second FC switch, configured with an Ethernet MAC port and an FC_MAC port; wherein the first FC switch and the second FC switch are connected in cascade via the FC_MAC ports, and after power-on of the two, the respective cascade port numbers of the two FC switches connected in cascade and the domain addresses of the FC switches connected therewith are obtained; the Ethernet MAC ports of the first FC switch and the second FC switch are set as Ethernet fusion ports, and through complete information content stripping and recombination, the frame is reassembled, so that the bandwidth utilization is maximized and the FC transmission efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of FC Fibre Channel network technology, and in particular to protocol conversion technology therein, specifically proposing an Ethernet frame transmission system based on an FC switch with converged ports. Background Technology

[0002] FC (Fiber Channel) is a high-speed serial transmission bus proposed by the American National Standards Institute (ANSI). Due to its dual advantages of channel and network, it has the advantages of high bandwidth, high reliability, high stability, and resistance to electromagnetic interference. It can provide very stable and reliable fiber optic connections and is easy to build large-scale data transmission and communication networks.

[0003] Ethernet technology, as the link layer standard for local area networks (LANs), currently holds over 90% market share in LANs. With increasing network interconnectivity, cross-protocol transmission between Ethernet and FC (Fanguc-Ethernet) has significant practical implications. Given the ever-growing scale of networks and the increasing prevalence of cross-LAN communication, cross-LAN and cross-FC-Ethernet protocol communication is a pressing issue that urgently needs to be addressed.

[0004] Currently, the conversion between Ethernet and FC protocols is usually accomplished using a protocol conversion daughter card. This daughter card can only perform protocol conversion but cannot forward or route information, nor can it enable cross-LAN communication. To achieve cross-LAN communication and protocol conversion, most systems currently use Ethernet switches in conjunction with protocol conversion daughter cards, connecting multiple devices, resulting in complex wiring and low efficiency.

[0005] Based on the aforementioned situation, FC protocol to Ethernet protocol conversion schemes have emerged. Currently, most FC protocol to Ethernet protocol conversions are implemented using FCoE and IPFC methods. Both of these schemes use one protocol frame as the payload and encapsulate it with the header of another protocol frame, resulting in low bandwidth utilization.

[0006] For example, the existing Chinese patent application number 201611218332.2 uses IPFC (IP over FiberChannel) to implement FC encapsulation of Ethernet frames. That is, the Ethernet frame is directly encapsulated by FC, and the complete Ethernet frame is retained in the FC frame. The frame header of the Ethernet frame is not disassembled. Instead, the FC frame header is directly added. This solution can only be used for the transmission of Ethernet frames in FC networks, but it cannot be used by FC devices to directly parse the frame content.

[0007] A Chinese patent application with application number 201611218356.8 proposes to set up a FIFO data buffer inside the FC-EG gateway to cache Ethernet frames and IPFC sequences. The number of cached frames is not less than 8. The internal cached data is based on complete frames, and the frames are independent and cannot be spliced. The added FC frame header further occupies bandwidth, resulting in lower bandwidth utilization.

[0008] In existing patent applications 201611262119.1 and 201710827605.1, the transmission method of FCoE is used, which encapsulates the entire Ethernet frame as data content (payload) in the FC frame without any reassembly process. Summary of the Invention

[0009] In view of the technical problems and defects of the existing technology, the present invention aims to propose an Ethernet frame transmission system based on an FC switch with converged port. By completely stripping and reassembling the information content and reframing the protocol conversion, the bandwidth utilization can be maximized and the transmission efficiency of the FC network can be improved.

[0010] According to a first aspect of the present invention, an Ethernet frame transmission system based on an FC switch with converged ports is provided, comprising:

[0011] At least one first FC switch is configured with an Ethernet MAC port and an FC_MAC port;

[0012] At least one second FC switch is configured with an Ethernet MAC port and an FC_MAC port;

[0013] The first FC switch and the second FC switch are cascaded through the FC_MAC port. After the two FC switches are powered on, they obtain the cascade port number of each of the two cascaded FC switches and the domain address of the FC switch to which they are connected.

[0014] The first FC switch and the second FC switch are connected to the local area network via their respective Ethernet MAC ports;

[0015] The first FC switch and the second FC switch are each connected to one or more terminal devices through their respective FC_MAC ports;

[0016] The Ethernet MAC ports of the first FC switch and the second FC switch are configured as Ethernet converged ports, and the Ethernet converged ports are configured as follows:

[0017] On the receiving channel, Ethernet frames are received and the data content after stripping the IP header and UDP header is reassembled into complete UDP frame content. Then, the data content is grouped into FC frames and sent to the FC switching matrix of the current switch for routing. The data content is sent based on the routing result.

[0018] On the transmission channel, FC frames are received from the FC switching matrix. After parsing the intra-frame data of the FC frames, the UDP frame content is reassembled, and finally, Ethernet frames are sent through the Ethernet IP core.

[0019] As an optional implementation, after power-on, the first FC switch and the second FC switch obtain their respective cascading port numbers and the domain addresses of the FC switches they are connected to by broadcasting cascading protocol frames.

[0020] As an optional implementation, the Ethernet converged port includes:

[0021] Ethernet IP core;

[0022] The Ethernet frame receiving module is used to receive Ethernet frames forwarded by the Ethernet IP core and to identify and verify the frame type.

[0023] The frame content stripping and reassembly module includes multiple memories, which are used to select free memories for storage when a frame is received from the Ethernet frame receiving module; and to strip the IP header and UDP header from the received frame, then reassemble the stripped data content into a complete UDP frame content, and output the IP address corresponding to this frame.

[0024] The FC frame assembly module is configured to read the data content from the non-empty memory in the frame content stripping and reassembly module, assemble FC frames, and then send them to the FC switching matrix of the FC switch.

[0025] The ARP configuration table is set up to store the mapping between MAC addresses and IP addresses carried in ARP frames;

[0026] The IP_FCID bridging table is set to store FC frame header configurations;

[0027] The FC frame parsing module communicates with the FC switching matrix of the FC switch to receive FC frames sent by the FC switching matrix, parse them to obtain the data content within the frame, and remove the FC frame header.

[0028] The frame content reassembly module contains multiple memories, which are used to select free memories for storage based on the data content sent from the FC frame parsing module, reassemble the data content into complete IU content, and output the IP address corresponding to the FC frame.

[0029] The Ethernet frame sending module is used to read the data content in the non-empty memory of the frame content reassembly module, assemble it into Ethernet frames, and then send the Ethernet frames through the Ethernet IP core.

[0030] As an optional implementation, the FC frame grouping module searches for the corresponding FC frame header configuration in the IP_FCID bridging table according to the source IP and destination IP addresses corresponding to the read UDP frame, segments the data content of the output UDP frame according to the FC frame length limit, and assembles it into an FC frame according to the found configuration content before sending it to the FC switching matrix for routing; if the corresponding FC configuration is not found in the IP_FCID bridging table, the UDP frame is discarded.

[0031] As an optional implementation, in the group FC frame module, the configuration content in the IP_FCID bridging table is configured by the CPU:

[0032] If the UDP frame is sent to the Ethernet port or FC port of this FC switch, the DID domain address in the frame header is configured to 1, and the port address is configured to the corresponding routing port number.

[0033] If a UDP frame is sent to an Ethernet port or FC port connected to another FC switch, the DID domain address in the frame header is configured to 2, and the port address is configured to the corresponding routing port number of the other FC switch.

[0034] As an optional implementation, all frames entering the FC switching matrix are FC frames;

[0035] In the switching matrix, routing is performed based on the destination domain address and port address in the FC frame, and the routing table is configured by the CPU of the FC switch;

[0036] The Ethernet converged port is configured with a corresponding routing port number, which corresponds to the port address;

[0037] When the domain address is this FC switch, the FC frame is sent to the corresponding port of this FC switch according to the port address; if the domain address is another FC switch, this FC frame is sent to the FC cascade port connected to the FC switch corresponding to the destination domain address; after the destination FC switch receives the FC frame through the cascade port, it sends the FC frame to the corresponding port according to the port address.

[0038] If the destination port is an FC port, the FC frame will be sent directly to the terminal device connected to the port through this FC port.

[0039] If the destination port is an Ethernet port, the FC frame is sent to this Ethernet port, and then the Ethernet transmission process begins.

[0040] As an optional implementation, when an Ethernet port of an FC switch has data that needs to be routed to another Ethernet port of the same FC switch or a cascaded FC switch, or when a terminal device of an FC switch needs to send data to an Ethernet port of the same FC switch or a cascaded FC switch, the FC frame routed to the Ethernet port needs to go through the Ethernet transmission process.

[0041] As an optional implementation, the Ethernet transmission process includes the following steps:

[0042] FC frames routed from the FC switching matrix enter the FC frame parsing module. The FC frame parsing module strips the FC frame header and then inputs the frame data content (payload) into the frame content reassembly module. At the same time, it extracts the SID and DID from the FC frame header and looks up the corresponding IP address in the IP_FCID bridging table, and sends it to the frame content reassembly module.

[0043] The frame content reassembly module contains several memories with a capacity of N. It receives the frame data content (payload) sent by the FC frame parsing module, selects free memories for storage, reassembles the frame data content (payload) into complete IU content, and outputs the IP address corresponding to this IU content.

[0044] If the frame content reassembly module has a non-empty memory, the Ethernet frame sending module initiates a read request to read the frame data content (payload) from the non-empty memory and assemble it into an Ethernet frame. Specifically, based on the source IP and destination IP address corresponding to the read IU content, the corresponding MAC frame header configuration is searched in the ARP configuration table. Based on the query result and the Ethernet frame length limit, the IU content is segmented and assembled into an Ethernet frame.

[0045] If the corresponding MAC address is not found in the ARP configuration table, the Ethernet frame sending module will actively initiate an ARP request to query the entire network. If an ARP response is received within the timeout period, framing will continue. If the corresponding MAC address is not obtained within the timeout period, the IU content will be discarded.

[0046] As can be seen from the above technical solution of the present invention, compared with the prior art, the Ethernet frame transmission system of the FC switch with converged port proposed in the present invention can maximize bandwidth utilization and improve FC transmission efficiency by completely stripping and reassembling the information content and reframing the frame. The configured reassembly module completely strips the data content in the Ethernet frame or FC frame, reassembles it into a complete data content of a certain length, and then re-segments and reframes it, thereby greatly improving bandwidth utilization and data transmission efficiency.

[0047] It should be understood that all combinations of the foregoing concepts and the additional concepts described in more detail below may be considered part of the inventive subject matter of this disclosure, provided that such concepts do not contradict each other. Furthermore, all combinations of the claimed subject matter are considered part of the inventive subject matter of this disclosure.

[0048] The foregoing and other aspects, embodiments, and features of the teachings of the present invention will be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the invention, such as features and / or beneficial effects of exemplary embodiments, will become apparent from the following description or may be learned through practice of specific embodiments according to the teachings of the present invention. Attached Figure Description

[0049] The accompanying drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in the various figures may be denoted by the same reference numeral. For clarity, not every component is labeled in each figure. Embodiments of various aspects of the invention will now be described by way of example and with reference to the accompanying drawings.

[0050] Figure 1 This is a schematic diagram of an Ethernet frame transmission system with FC switches cascaded according to an embodiment of the present invention.

[0051] Figure 2 This is an Ethernet MAC configuration diagram of the Ethernet converged port according to an embodiment of the present invention.

[0052] Figure 3 This is a schematic diagram of the FCID structure according to an embodiment of the present invention.

[0053] Figure 4 This is a topology diagram of the first type of Ethernet frame transmission according to an embodiment of the present invention. In the diagram, the Ethernet frame enters from Ethernet port 0 of FC switch 1 and is sent to Ethernet port 1 of the cascaded FC switch 2.

[0054] Figure 5 yes Figure 4 The frame flow process of Ethernet frame transmission in the embodiment.

[0055] Figure 6 This is a topology diagram of the second type of Ethernet frame transmission according to an embodiment of the present invention. In the diagram, the Ethernet frame enters from the Ethernet port of FC switch 1 and is sent to the FC port 2 of the cascaded FC switch 2.

[0056] Figure 7 yes Figure 6 The frame flow process of Ethernet frame transmission in the embodiment.

[0057] Figure 8This is a topology diagram of the third type of Ethernet frame transmission according to an embodiment of the present invention. In the diagram, the Ethernet frame enters from the Ethernet port of FC switch 1 and is sent to the FC port 2 of the same FC switch.

[0058] Figure 9 yes Figure 8 The frame flow process of Ethernet frame transmission in the embodiment.

[0059] Figure 10 This is a topology diagram of the third type of Ethernet frame transmission according to an embodiment of the present invention. In the diagram, the Ethernet frame enters from the Ethernet port of FC switch 1 and is sent to the Ethernet port 2 of the same FC switch.

[0060] Figure 11 yes Figure 10 The frame flow process of Ethernet frame transmission in the embodiment. Detailed Implementation

[0061] To better understand the technical content of the present invention, specific embodiments are described below in conjunction with the accompanying drawings.

[0062] Various aspects of the invention are described in this disclosure with reference to the accompanying drawings, which illustrate numerous illustrative embodiments. The embodiments of this disclosure are not necessarily intended to encompass all aspects of the invention. It should be understood that the various concepts and embodiments described above, as well as those described in more detail below, can be implemented in any of many ways, because the concepts and embodiments disclosed herein are not limited to any particular implementation. Furthermore, some aspects of the invention disclosed may be used alone or in any suitable combination with other aspects of the invention disclosed.

[0063] Combination Figure 1-3 The illustrated embodiment of the Ethernet frame transmission system based on an FC switch with a converged port includes: at least one first FC switch configured with an Ethernet MAC port and an FC_MAC port; and at least one second FC switch configured with an Ethernet MAC port and an FC_MAC port, as shown below. Figure 1 As shown, the example is a cascaded switch 1 and switch 2.

[0064] The first FC switch and the second FC switch are cascaded via the FC_MAC port, as shown in the figure, through FC_MAC1_1 and FC_MAC2_1. After powering on, both switches obtain the cascade port number of each cascaded FC switch and the domain address of the FC switch to which they are connected.

[0065] The first FC switch and the second FC switch are connected to the local area network through their respective Ethernet MAC ports.

[0066] The first FC switch and the second FC switch are each connected to one or more terminal devices through their respective FC_MAC ports.

[0067] Combination Figure 1 , 2 As shown, the Ethernet MAC ports of the first FC switch and the second FC switch are configured as Ethernet converged ports, and the sending / receiving of Ethernet frames is realized through the Ethernet converged ports.

[0068] On the receiving channel, Ethernet frames are received and the data content after stripping the IP header and UDP header is reassembled into complete UDP frame content. Then, the data content is grouped into FC frames and sent to the FC switching matrix of the current switch for routing. The data content is sent based on the routing result.

[0069] On the transmission channel, FC frames are received from the FC switching matrix. After parsing the intra-frame data of the FC frames, the UDP frame content is reassembled, and finally, Ethernet frames are sent through the Ethernet IP core.

[0070] In an embodiment of the present invention, after power-on, the first FC switch and the second FC switch obtain their respective cascading port numbers and the domain addresses of the FC switches connected to them by broadcasting cascading protocol frames.

[0071] For example Figure 1 In the example shown, FC port 1_1 of FC switch 1 is cascaded with FC port 2_1 of FC switch 2.

[0072] After the switch is powered on, the CPU will broadcast a cascading protocol frame to all FC ports except the CPU port through the FC port connected to it. If the FC port receives the cascading protocol frame, it will forward it directly to the FC port connected to the CPU and then send it to the CPU. After receiving the cascading protocol frame, the CPU will reply and communicate relevant information, informing the switch of its domain address and obtaining key information such as the cascading port.

[0073] Through the cascading protocol, this switch also obtains the cascading port number of this switch, as well as the domain address of the connected switch.

[0074] Through cascading protocol communication, CPU1 corresponding to switch 1 learns that port 1_1 is a cascading port and the domain address domain2 of switch 2 connected to 1_1. Similarly, CPU2 corresponding to switch 2 learns that port 2_1 is a cascading port and the domain address domain1 of switch 1 connected to 2_1.

[0075] Combination Figure 2As shown, the principle of an Ethernet converged port according to an embodiment of the present invention is illustrated, which includes:

[0076] Ethernet IP core;

[0077] The Ethernet frame receiving module is used to receive Ethernet frames forwarded by the Ethernet IP core and to identify and verify the frame type.

[0078] The frame content stripping and reassembly module includes multiple memories, which are used to select free memories for storage when a frame is received from the Ethernet frame receiving module; and to strip the IP header and UDP header from the received frame, then reassemble the stripped data content into a complete UDP frame content, and output the IP address corresponding to this frame.

[0079] The FC frame assembly module is configured to read the data content from the non-empty memory in the frame content stripping and reassembly module, assemble FC frames, and then send them to the FC switching matrix of the FC switch.

[0080] The ARP configuration table is set up to store the mapping between MAC addresses and IP addresses carried in ARP frames;

[0081] The IP_FCID bridging table is set to store FC frame header configurations;

[0082] The FC frame parsing module communicates with the FC switching matrix of the FC switch to receive FC frames sent by the FC switching matrix, parse them to obtain the data content within the frame, and remove the FC frame header.

[0083] The frame content reassembly module contains multiple memory units with a capacity of N. It selects free memory units to store the data content sent from the FC frame parsing module, reassembles the data content into complete IU content, and outputs the IP address corresponding to the FC frame.

[0084] The Ethernet frame sending module is used to read the data content in the non-empty memory of the frame content reassembly module, assemble it into Ethernet frames, and then send the Ethernet frames through the Ethernet IP core.

[0085] Combination Figure 2 As shown in the example, the FC frame grouping module looks up the corresponding FC frame header configuration in the IP_FCID bridging table based on the source IP and destination IP addresses of the read UDP frame. It then segments the data content of the output UDP frame according to the FC frame length limit, assembles it into an FC frame based on the found configuration content, and sends it to the FC switching matrix for routing. If the corresponding FC configuration is not found in the IP_FCID bridging table, the UDP frame is discarded.

[0086] In the FC frame group module, the configuration content in the IP_FCID bridging table is distributed and configured by the CPU:

[0087] If the UDP frame is sent to the Ethernet port or FC port of this FC switch, the DID domain address in the frame header is configured to 1, and the port address is configured to the corresponding routing port number.

[0088] If a UDP frame is sent to an Ethernet port or FC port connected to another FC switch, the DID domain address in the frame header is configured to 2, and the port address is configured to the corresponding routing port number of the other FC switch.

[0089] Combination Figure 2 As shown in the example, the Ethernet frame sending module searches for the corresponding MAC frame header configuration in the ARP configuration table based on the source IP and destination IP address corresponding to the read IU content, and segments and assembles the IU content into Ethernet frames according to the query results and the Ethernet frame length limit.

[0090] If the corresponding MAC address is not found in the ARP configuration table, the Ethernet frame sending module will actively initiate an ARP request to query the entire network. If an ARP response is received within the timeout period, framing will continue. If the corresponding MAC address is not obtained within the timeout period, the IU content will be discarded.

[0091] It should be understood that, in the embodiments of the present invention, in conjunction with Figure 1 , 2 As shown, all frames entering the FC switching matrix are FC frames;

[0092] In the switching matrix, routing is performed based on the destination domain address and port address in the FC frame, and the routing table is configured by the CPU of the FC switch;

[0093] The Ethernet converged port is configured with a corresponding routing port number, which corresponds to the port address;

[0094] When the domain address is this FC switch, the FC frame is sent to the corresponding port of this FC switch according to the port address; if the domain address is another FC switch, this FC frame is sent to the FC cascade port connected to the FC switch corresponding to the destination domain address; after the destination FC switch receives the FC frame through the cascade port, it sends the FC frame to the corresponding port according to the port address.

[0095] If the destination port is an FC port, the FC frame will be sent directly to the terminal device connected to the port through this FC port.

[0096] If the destination port is an Ethernet port, the FC frame is sent to this Ethernet port, and then the Ethernet transmission process begins.

[0097] Combination Figure 1 , 2 When an Ethernet port of an FC switch has data that needs to be routed to another Ethernet port of the same FC switch or a cascaded FC switch, or when a terminal device of an FC switch needs to send data to an Ethernet port of the same FC switch or a cascaded FC switch, the FC frame routed to the Ethernet port needs to go through the Ethernet transmission process.

[0098] As an optional example, the Ethernet transmission process includes the following steps:

[0099] FC frames routed from the FC switching matrix enter the FC frame parsing module. The FC frame parsing module strips the FC frame header and then inputs the frame data content (payload) into the frame content reassembly module. At the same time, it extracts the SID and DID from the FC frame header and looks up the corresponding IP address in the IP_FCID bridging table, and sends it to the frame content reassembly module.

[0100] The frame content reassembly module contains several memories with a capacity of N. It receives the frame data content (payload) sent by the FC frame parsing module, selects free memories for storage, reassembles the frame data content (payload) into complete IU content, and outputs the IP address corresponding to this IU content.

[0101] If the frame content reassembly module has a non-empty memory, the Ethernet frame sending module initiates a read request to read the frame data content (payload) from the non-empty memory and assemble it into an Ethernet frame. Specifically, based on the source IP and destination IP address corresponding to the read IU content, the corresponding MAC frame header configuration is searched in the ARP configuration table. Based on the query result and the Ethernet frame length limit, the IU content is segmented and assembled into an Ethernet frame.

[0102] If the corresponding MAC address is not found in the ARP configuration table, the Ethernet frame sending module will proactively initiate an ARP request to query the entire network. If an ARP response is received within the timeout period, framing will continue. If the corresponding MAC address is not obtained within the timeout period, the IU content will be discarded.

[0103] {Example 1}

[0104] Combination Figure 1 , 2 ,as well as Figure 4-11The specific process shown will be illustrated using the cascading of two FC switches with converged ports as an example to illustrate the implementation of this solution. It should be understood that in practical use, multiple FC switches with converged ports can be connected via FC ports to achieve communication between multiple local area networks and FC networks.

[0105] like Figure 1 As shown, FC port 1_1 of FC switch 1 is cascaded with FC port 2_1 of FC switch 2.

[0106] The ports configured for FC switch 1 and FC switch 2 are as follows:

[0107] The orange port is an Ethernet converged port;

[0108] The green port is the FC port;

[0109] Two FC switches with converged ports are cascaded via the FC ports.

[0110] Ethernet port 1_0 of FC switch 1 is connected to Ethernet LAN 1, and Ethernet port 2_1 of FC switch 2 is connected to Ethernet LAN 2.

[0111] Different Ethernet ports on the same switch can be connected to different local area networks.

[0112] As explained above, after the FC switch is powered on, the CPU will broadcast a cascading protocol frame to all FC ports except the CPU port through the FC port connected to it. If the FC port receives the cascading protocol frame, it will forward it directly to the FC port connected to the CPU and then send it to the CPU. After receiving the cascading protocol frame, the CPU will reply and communicate relevant information, informing the switch of its domain address and obtaining key information such as the cascading port.

[0113] Through the cascading protocol, this switch also obtains the cascading port number of this switch and the domain address of the connected switch.

[0114] Through cascading protocol communication, CPU1 corresponding to switch 1 learns that port 1_1 is a cascading port and the domain address domain2 of switch 2 connected to 1_1; similarly, CPU2 corresponding to switch 2 learns that port 2_1 is a cascading port and the domain address domain1 of switch 1 connected to 2_1.

[0115] {Example 2}

[0116] Combination Figure 1 As shown, in this embodiment of the invention, the Ethernet MAC ports of the first FC switch and the second FC switch are configured as Ethernet converged ports.

[0117] like Figure 2 The example Ethernet converged port shown is configured to perform the following operations:

[0118] On the receiving channel, Ethernet frames are received and the data content after stripping the IP header and UDP header is reassembled into complete UDP frame content. Then, the data content is grouped into FC frames and sent to the FC switching matrix of the current switch for routing. The data content is sent based on the routing result.

[0119] On the transmission channel, FC frames are received from the FC switching matrix. After parsing the intra-frame data of the FC frames, the UDP frame content is reassembled, and finally, Ethernet frames are sent through the Ethernet IP core.

[0120] Specifically, the Ethernet converged port includes:

[0121] Ethernet IP core;

[0122] The Ethernet frame receiving module is used to receive Ethernet frames forwarded by the Ethernet IP core and to identify and verify the frame type.

[0123] The frame content stripping and reassembly module includes multiple memories, which are used to select free memories for storage when a frame is received from the Ethernet frame receiving module; and to strip the IP header and UDP header from the received frame, then reassemble the stripped data content into a complete UDP frame content, and output the IP address corresponding to this frame.

[0124] The FC frame assembly module is configured to read the data content from the non-empty memory in the frame content stripping and reassembly module, assemble FC frames, and then send them to the FC switching matrix of the FC switch.

[0125] The ARP configuration table is set up to store the mapping between MAC addresses and IP addresses carried in ARP frames;

[0126] The IP_FCID bridging table is set to store FC frame header configurations;

[0127] The FC frame parsing module communicates with the FC switching matrix of the FC switch to receive FC frames sent by the FC switching matrix, parse them to obtain the data content within the frame, and remove the FC frame header.

[0128] The frame content reassembly module contains multiple memory units with a capacity of N. It selects free memory units to store the data content sent from the FC frame parsing module, reassembles the data content into complete IU content, and outputs the IP address corresponding to the FC frame.

[0129] The Ethernet frame sending module is used to read the data content in the non-empty memory of the frame content reassembly module, assemble it into Ethernet frames, and then send the Ethernet frames through the Ethernet IP core.

[0130] Ethernet receive processing

[0131] Ethernet frames input from the Ethernet network are fed into the Ethernet frame receiving module via the Ethernet IP core. The Ethernet frame receiving module determines the frame type and performs verification.

[0132] If it is an ARP frame, the mapping between MAC address and IP address carried in the frame is stored in the ARP configuration table;

[0133] If it is a UDP frame, the Ethernet frame header and trailer are stripped before being sent to the frame content stripping and reassembly module.

[0134] The frame content stripping and reassembly module contains several memory units with a capacity of N. Taking a switch that supports 8K reassembly and can process 16 frames in parallel as an example, the frame content stripping and reassembly module contains 16 memory units of 8KB each.

[0135] In the frame content stripping and reassembly module, when a frame sent by the Ethernet frame receiving module is received, an idle memory is selected for storage, the IP header and UDP header in the data are stripped, and the data content (payload) is reassembled into a complete UDP frame content. At the same time, the IP address corresponding to this frame is output.

[0136] In an optional embodiment, if a UDP frame longer than 8K is received under the agreed 8K reassembly condition, it is discarded in this module, and the corresponding memory is released. When all 16 memory slots are fully used, newly arriving frames will be discarded.

[0137] Combination Figure 2 As shown, if there is a non-empty memory in the frame stripping and reassembly module, the FC module initiates a read request, reads the payload from the non-empty memory, and performs FC frame assembly.

[0138] In an optional embodiment, the group FC module looks up the corresponding FC frame header configuration in the IP_FCID module based on the source IP and destination address of the read UDP frame.

[0139] In the configuration of this invention, the configuration content in the IP_FCID module is sent down by the CPU. Figure 1Taking the system shown as an example, if this frame is sent to the Ethernet port or FC port of this switch 1, the DID domain address in the frame header is configured as 1, and the port address is configured as the corresponding routing port number; if this frame is sent to the Ethernet port or FC port connected to another switch 2, the DID domain address in the frame header is configured as 2, and the port address is configured as the corresponding routing port number of switch 2.

[0140] like Figure 3 The structure of FCID is illustrated exemplarily. The DID and SID (collectively referred to as FCID) in the FC frame header are composed of 24 bits. The lower 8 bits are the port address, used to identify the routing port number. The higher 8 bits are the domain address, used to identify the switch domain address. The middle 8 bits are the area address, which is not used in the scheme of this invention.

[0141] In an embodiment of the present invention, in the FC frame grouping module, the output data content is segmented according to the FC frame length limit, and then assembled into FC frames according to the corresponding configuration content before being sent to the FC switching matrix for routing. If the IP address does not find the corresponding FC configuration in IP_FCID, the frame is discarded.

[0142] Routing

[0143] All frames entering the switching matrix are FC frames. The switching matrix routes data based on the destination domain address and port address in the FC frame. The routing table is configured by the CPU. Ethernet ports are also configured with corresponding routing port numbers, corresponding to the port addresses.

[0144] When the domain address is the local switch, the frame is sent to the corresponding port on the local switch based on the port address. If the domain address is another switch, the frame is sent to the FC cascade port connected to the switch corresponding to the destination domain address. After receiving the FC frame through the cascade port, the destination switch sends the FC frame to the corresponding port based on the port address.

[0145] If the destination port is an FC port, the frame is sent directly to the FC terminal device connected to the port through this port. If the destination port is an Ethernet port, the FC frame is sent to this port, and then the Ethernet transmission process begins.

[0146] Ethernet transmission processing

[0147] When an Ethernet port has data that needs to be routed to another Ethernet port of the same switch or a cascaded switch, or when an FC terminal device needs to send data to the Ethernet port of the same switch or a cascaded switch, the FC frame routed to the Ethernet port needs to go through a transmission process.

[0148] Combination Figure 2 As shown, as an optional embodiment, the Ethernet transmission process is as follows:

[0149] FC frames routed from the switching matrix enter the FC frame parsing module. This module completely removes the FC frame header, inputs the frame data content (payload) into the frame content reassembly module, extracts the SID and DID from the FC frame header, looks up the corresponding IP address in the IP_FCID bridging table, and sends it to the frame content reassembly module.

[0150] The frame content reassembly module contains several memories with a capacity of N. Taking a switch that supports 8K reassembly and can process 16 frames in parallel as an example, the frame content reassembly module contains 16 memories of 8KB each.

[0151] In the frame content reassembly module, when the frame content (payload) sent by the FC frame parsing module arrives, an idle memory is selected for storage, the data content (payload) is reassembled into complete IU content, and the IP address corresponding to this frame is output.

[0152] As an optional example, if an FC IU with a frame length greater than 8K is received under the agreed 8K reassembly condition, it will be discarded in this module, and the corresponding memory will be released. When all 16 memory slots are fully used, newly arriving frames will be discarded.

[0153] In the FC frame protocol, the IU (Information Unit, referring to a collection of multiple FC frames on the same channel) is similar to a UDP frame in Ethernet. An Ethernet UDP frame can be divided into multiple Ethernet frames, and the frames are marked with fragment offsets. In an FC frame, an IU can be divided into many FC frames, and frames belonging to the same IU are marked in the frame header. In this scheme, the frames in an IU arrive in the order they arrive by default, so they are stored sequentially.

[0154] Combination Figure 2 If the frame reassembly module has a non-empty memory, the Ethernet frame sending module initiates a read request to read the payload from the non-empty memory and assemble it into an Ethernet frame. Based on the source and destination IP addresses of this frame, the module looks up the corresponding MAC header configuration in the ARP configuration table, and segments the payload content according to the query results and the Ethernet frame length limit to assemble the Ethernet frame.

[0155] If the MAC address corresponding to the IP address is not found in the ARP configuration table, this module will actively initiate an ARP request to query the entire network. If an ARP response is received within the timeout period, the frame will continue to be assembled. If the corresponding MAC address is not obtained within the timeout period, the frame will be discarded.

[0156] Combination Figure 4-5 Figures 6-7, 8-9, and 10-11 illustrate the Ethernet frame transmission topology logic and the corresponding frame flow process in the two FC switches under four different scenarios based on the aforementioned system implementation according to the present invention:

[0157] The transmission process starts from Ethernet port 0 of FC switch 1 and is sent to Ethernet port 1 of the cascaded FC switch 2.

[0158] The transmission process starts from the Ethernet port of FC switch 1 and is sent to the FC port 2 of the cascaded FC switch 2.

[0159] The transmission process starts from the Ethernet port of FC switch 1 and is sent to the FC port 2 of this FC switch;

[0160] The transmission process starts from the Ethernet port of FC switch 1 and is sent to the Ethernet port 2 of this FC switch.

[0161] While the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Those skilled in the art can make various modifications and refinements without departing from the spirit and scope of the invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. An Ethernet frame transmission system based on an FC switch with a converged port, characterized in that, include: At least one first FC switch is configured with an Ethernet MAC port and an FC_MAC port; At least one second FC switch is configured with an Ethernet MAC port and an FC_MAC port; The first FC switch and the second FC switch are cascaded through the FC_MAC port. After the two FC switches are powered on, they obtain the cascade port number of each of the two cascaded FC switches and the domain address of the FC switch to which they are connected. The first FC switch and the second FC switch are connected to the local area network via their respective Ethernet MAC ports; The first FC switch and the second FC switch are each connected to one or more terminal devices through their respective FC_MAC ports; The Ethernet MAC ports of the first FC switch and the second FC switch are configured as Ethernet converged ports, and the Ethernet converged ports are configured as follows: On the receiving channel, Ethernet frames are received and the data content after stripping the IP header and UDP header is reassembled into complete UDP frame content. Then, the UDP frame content is grouped into FC frames and sent to the FC switching matrix of the current switch for routing. The data content is sent based on the routing result. On the transmission channel, FC frames from the FC switching matrix are received, intra-frame data is parsed, reassembled into complete IU content, and then grouped into Ethernet frames. Finally, Ethernet frames are sent through the Ethernet IP core. The Ethernet converged port includes: Ethernet IP core; The Ethernet frame receiving module is used to receive Ethernet frames forwarded by the Ethernet IP core and to identify and verify the frame type. The frame content stripping and reassembly module includes multiple memories, which are used to select free memories for storage when a frame is received from the Ethernet frame receiving module; and to strip the IP header and UDP header from the received frame, then reassemble the stripped data content into a complete UDP frame content, and output the IP address corresponding to the frame. The FC frame assembly module is configured to read the UDP frame content from the non-empty memory in the frame content stripping and reassembly module, assemble FC frames, and then send them to the FC switching matrix of the FC switch. The ARP configuration table is set up to store the mapping between MAC addresses and IP addresses carried in ARP frames; The IP_FCID bridging table is set to store FC frame header configurations; The FC frame parsing module communicates with the FC switching matrix of the FC switch to receive FC frames sent by the FC switching matrix, parse them to obtain the data content within the frame, and remove the FC frame header. The frame content reconstruction module contains multiple memories, which are used to select free memories for storage based on the data content sent from the FC frame parsing module, reconstruct the data content parsed by the FC frame parsing module into complete IU content, and output the IP address corresponding to the FC frame. The Ethernet frame sending module is used to read the IU content in the non-empty memory of the frame content reassembly module, assemble Ethernet frames, and then send the Ethernet frames through the Ethernet IP core.

2. The Ethernet frame transmission system based on an FC switch with converged port according to claim 1, characterized in that, After powering on, the first FC switch and the second FC switch obtain their respective cascading port numbers and the domain addresses of the FC switches they are connected to by broadcasting cascading protocol frames.

3. The Ethernet frame transmission system based on an FC switch with converged port according to claim 1, characterized in that, The FC frame module looks up the corresponding FC frame header configuration in the IP_FCID bridging table according to the source IP and destination IP addresses of the read UDP frame, segments the data content of the output UDP frame according to the FC frame length limit, and assembles the FC frame according to the found configuration content before sending it to the FC switching matrix for routing. If the corresponding FC configuration is not found in the IP_FCID bridging table, the UDP frame is discarded.

4. The Ethernet frame transmission system based on an FC switch with converged port according to claim 1, characterized in that, In the group FC frame module, the configuration content in the IP_FCID bridging table is configured by the CPU: If the UDP frame is sent to the Ethernet port or FC port of this FC switch, the DID domain address in the frame header is configured to 1, and the port address is configured to the corresponding routing port number. If a UDP frame is sent to an Ethernet port or FC port connected to another FC switch, the DID domain address in the frame header is configured to 2, and the port address is configured to the corresponding routing port number of the other FC switch.

5. The Ethernet frame transmission system based on an FC switch with converged port according to claim 1, characterized in that, The Ethernet frame sending module searches for the corresponding MAC frame header configuration in the ARP configuration table based on the source IP and destination IP address corresponding to the read IU content, and segments and assembles the IU content into Ethernet frames according to the query results and the Ethernet frame length limit. If the corresponding MAC address is not found in the ARP configuration table, the Ethernet frame sending module will actively initiate an ARP request to query the entire network. If an ARP response is received within the timeout period, framing will continue. If the corresponding MAC address is not obtained within the timeout period, the IU content will be discarded.

6. The Ethernet frame transmission system based on an FC switch with converged port according to claim 1, characterized in that, All frames entering the FC switching matrix are FC frames; In the switching matrix, routing is performed based on the destination domain address and port address in the FC frame, and the routing table is configured by the CPU of the FC switch; The Ethernet converged port is configured with a corresponding routing port number, which corresponds to the port address; When the domain address is this FC switch, the FC frame is sent to the corresponding port of this FC switch according to the port address; if the domain address is another FC switch, this FC frame is sent to the FC cascade port connected to the FC switch corresponding to the destination domain address; after the destination FC switch receives the FC frame through the cascade port, it sends the FC frame to the corresponding port according to the port address. If the destination port is an FC port, the FC frame will be sent directly to the terminal device connected to the port through this FC port. If the destination port is an Ethernet port, the FC frame is sent to this Ethernet port, and then the Ethernet transmission process begins.

7. The Ethernet frame transmission system based on an FC switch with converged port according to claim 6, characterized in that, When an Ethernet port of an FC switch has data that needs to be routed to another Ethernet port of the same FC switch or a cascaded FC switch, or when a terminal device of an FC switch needs to send data to an Ethernet port of the same FC switch or a cascaded FC switch, the FC frame routed to the Ethernet port needs to go through the Ethernet transmission process.

8. The Ethernet frame transmission system based on an FC switch with converged port according to claim 6, characterized in that, The Ethernet transmission process includes the following steps: FC frames routed from the FC switching matrix enter the FC frame parsing module. The FC frame parsing module strips the FC frame header and then inputs the parsed data content into the frame content reassembly module. At the same time, it extracts the SID and DID from the FC frame header and looks up the corresponding IP address in the IP_FCID bridging table, and sends it to the frame content reassembly module. The frame content reassembly module contains several memories with a capacity of N. It receives the data content sent by the FC frame parsing module, selects free memories for storage, reassembles the data content into complete IU content, and outputs the IP address corresponding to this IU content. If the frame content reassembly module has a non-empty memory, the Ethernet frame sending module initiates a read request to read the IU content from the non-empty memory and assemble it into an Ethernet frame. Specifically, based on the source IP and destination IP address corresponding to the read IU content, the corresponding MAC frame header configuration is searched in the ARP configuration table. Based on the query result and the Ethernet frame length limit, the IU content is segmented and assembled into an Ethernet frame. If the corresponding MAC address is not found in the ARP configuration table, the Ethernet frame sending module will actively initiate an ARP request to query the entire network. If an ARP response is received within the timeout period, framing will continue. If the corresponding MAC address is not obtained within the timeout period, the IU content will be discarded.

Images