CN108199976B - Switching equipment, switching system and data sending method of RapidIO network - Google Patents
Switching equipment, switching system and data sending method of RapidIO network Download PDFInfo
- Publication number
- CN108199976B CN108199976B CN201711469173.8A CN201711469173A CN108199976B CN 108199976 B CN108199976 B CN 108199976B CN 201711469173 A CN201711469173 A CN 201711469173A CN 108199976 B CN108199976 B CN 108199976B
- Authority
- CN
- China
- Prior art keywords
- layer module
- physical layer
- physical
- data
- virtual
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/10—Packet switching elements characterised by the switching fabric construction
Abstract
The invention provides a switching device, a switching system and a data sending method of a RapidIO network; the virtual physical layer module is respectively connected with a plurality of physical ports; a plurality of physical ports are connected with the same external switching equipment; the switching matrix receives the data stream and sends the data stream to the virtual physical layer module; when the virtual physical layer module receives the data stream, selecting a physical port according to the residual cache capacity of the plurality of physical ports, and distributing the data frame in the data stream to the selected physical port; and the physical port receives the data frame distributed by the virtual physical layer module and sends the data frame. The invention can bind a plurality of physical ports for use by setting the virtual physical layer module, dynamically distributes data frames among the physical ports according to the residual cache capacity, and realizes the load balance of redundant links among the switching devices, thereby reducing the probability of communication bandwidth blockage of the RapidIO network and improving the stability and reliability of the network.
Description
Technical Field
The invention relates to the technical field of RapidIO, in particular to a switching device, a switching system and a data sending method of a RapidIO network.
Background
RapidIO as an embedded system interconnection technology has the advantages of high bandwidth, low time delay, high efficiency, high reliability and the like, and can provide a good solution for the internal interconnection of a high-performance embedded system. The RapidIO physical layer realizes a perfect flow control mechanism, so that the physical layer of the whole RapidIO network can ensure that RapidIO data frames cannot be discarded randomly, and can ensure that the sequence of each data frame in the same data stream after being forwarded by the RapidIO network is not changed, thereby embodying the characteristic of high reliability of the RapidIO network. With the scale of the RapidIO network becoming larger and larger, the bandwidth requirement becomes higher and higher, and bandwidth blocking points are easy to generate during networking. In the prior art, in order to solve the problem of bandwidth bottleneck, there are two following ways:
first, the protocols of the RapidIO2.2 version provide that the port width of RapidIO can support 1x, 2x, 4x, 8x and up to 16x working modes, the port rate can support 1.25G, 2.5G, 5G and up to 6.25G working modes, and the bandwidth of the port can be increased by increasing the port width and the port rate of RapidIO; the method can relieve the influence of network bandwidth bottleneck to a certain extent, but the method has the following defects: the RapidIO port width cannot be increased infinitely, when the port width specified by the RapidIO protocol is greater than 1, link alignment and binding operations need to be implemented on the underlying data path, and as the port width is gradually increased, skew (skew) between links of the same port becomes difficult to eliminate. In addition, the RapidIO port rate cannot be increased without limit, and a higher port rate means that the design of physical media connection (PMA) of a physical layer is more complicated, and the influence of dispersion, crosstalk, attenuation and the like needs to be considered when hardware is designed.
Secondly, by adjusting the networking topology structure and the routing table items, the high-bandwidth service is split to other network paths, and the problem of network bottleneck can be solved; for example, an independent control plane is designed on the whole network, so that the bandwidth bottleneck point of the network can be redistributed and utilized; this approach has the following disadvantages: the change cost of the network topology is too high, once a network is built, the network topology is basically fixed, and once the network topology is changed, all nodes involved on the whole network need to be changed, which is hardly realized in some application scenarios. In this way, the network bandwidth allocation is rigid, and very complex control plane participation is required to realize flexible adaptation. The RapidIO protocol specifies that data streams with the same source ID, destination ID and priority cannot be out of order in the transmission process, which means that all RapidIO data frames in the same data stream need to be forwarded according to the same network path. If it is necessary to split a high-bandwidth service to other network paths, which means that the split is a rigid split, the bandwidth required by the service is assumed to be dynamically changed, for example, the bandwidth of the service becomes low for a certain period of time, and the spare bandwidth is only wasted.
In summary, no effective solution is provided for the problem that the existing RapidIO network has a high probability of communication bandwidth blocking, which results in poor network stability and reliability.
Disclosure of Invention
In view of this, the present invention aims to provide a switching device, a switching system and a data sending method for a RapidIO network, so as to reduce the probability of communication bandwidth blocking of the RapidIO network and improve the stability and reliability of the network.
In a first aspect, an embodiment of the present invention provides a switching device of a RapidIO network, where the switching device is provided with a switching matrix, a virtual physical layer module, and multiple physical ports; the switching matrix is connected with the virtual physical layer module; the virtual physical layer module is respectively connected with a plurality of physical ports; a plurality of physical ports are connected with the same external switching equipment; the switching matrix is used for receiving the data stream and sending the data stream to the virtual physical layer module; the virtual physical layer module is used for selecting a physical port according to the residual cache capacity of the plurality of physical ports when receiving the data stream, and distributing the data frame in the data stream to the selected physical port; the physical port is used for receiving the data frame distributed by the virtual physical layer module and sending the data frame.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the virtual physical layer module includes a sequence identifier; the sequence identifier is used for recording the distribution sequence number of the data frame when each data frame is distributed to the corresponding physical port, and carrying the distribution sequence number when the data frame is sent to the selected physical port.
With reference to the first possible implementation manner of the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where the physical port includes a cache module, a physical layer module, and a high-speed transceiver, which are connected in sequence; the cache module is connected with the virtual physical layer module; a routing table is stored in the physical layer module; the high-speed transceiver is connected to an external switching device.
With reference to the second possible implementation manner of the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the physical layer module is configured to add an allocation sequence number to a Cmd field in a start of frame control symbol of a data frame.
With reference to the third possible implementation manner of the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the physical layer module is further configured to, when receiving a data stream sent by the same external switching device through multiple physical ports, extract an allocation sequence number of each data frame in the data stream from the Cmd field, and send the data frame and a corresponding allocation sequence number to the virtual physical layer module; the virtual physical layer module is also used for arranging the data frames according to the distribution sequence numbers and sending the data frames after being arranged to the switching matrix.
In a second aspect, an embodiment of the present invention provides a switching system of a RapidIO network, where the system includes at least two switching devices; the plurality of physical ports on the first switching device are respectively connected with the plurality of physical ports on the second switching device in a one-to-one correspondence manner.
With reference to the second aspect, an embodiment of the present invention provides a first possible implementation manner of the second aspect, where the physical port on the first switching device is connected to a corresponding physical port on the second switching device through an optical fiber, a coaxial cable, a twisted pair, or a backplane PCB.
With reference to the second aspect, an embodiment of the present invention provides a second possible implementation manner of the second aspect, where the system includes multiple switching devices and multiple endpoint devices.
In a third aspect, an embodiment of the present invention provides a data sending method for a RapidIO network, where the method is applied to the above switching device; the method comprises the following steps: the switching matrix receives the data stream and sends the data stream to the virtual physical layer module; when receiving a data stream, the virtual physical layer module selects a physical port according to the residual cache capacity of the plurality of physical ports, and distributes a data frame in the data stream to the selected physical port; and the physical port receives the data frame distributed by the virtual physical layer module and sends the data frame.
With reference to the third aspect, an embodiment of the present invention provides a first possible implementation manner of the third aspect, where the virtual physical layer module includes a sequence identifier; the method further comprises the following steps: when each data frame is allocated to a corresponding physical port, the sequence identifier records the allocation sequence number of the data frame, and when the data frame is sent to the selected physical port, the allocation sequence number is carried.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides switching equipment, a switching system and a data sending method of a RapidIO network, wherein a virtual physical layer module is respectively connected with a plurality of physical ports; a plurality of physical ports are connected with the same external switching equipment; when the virtual physical layer module receives a data stream sent by the switching matrix, selecting a physical port according to the residual cache capacity of the plurality of physical ports, and distributing a data frame in the data stream to the selected physical port; the physical port receives the data frame distributed by the virtual physical layer module and sends the data frame; in this way, the virtual physical layer module is arranged to bind the plurality of physical ports for use, and data frames are dynamically allocated among the plurality of physical ports according to the residual cache capacity, so that load balance of redundant links among the switching devices is realized, the probability of communication bandwidth blockage of the RapidIO network is reduced, and the stability and reliability of the network are improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic partial structure diagram of a RapidIO network according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a first switching device of a RapidIO network according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a switching device of a second RapidIO network according to an embodiment of the present invention;
fig. 4 is a schematic diagram of data transmission and reception by using a switch device of a RapidIO network according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a switching system of a first RapidIO network according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a switching system of a second RapidIO network according to an embodiment of the present invention;
fig. 7 is a flowchart of a data sending method of a RapidIO network according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic diagram of a partial structure of a RapidIO network is shown; with the larger and larger RapidIO network scale, the networking structure of the RapidIO network is more and more complex, so that bandwidth blocking points are easy to appear in the networking structure; in the networking structure shown in fig. 1, SW (Switch) 5 is responsible for data transmission between EP (Endpoint device) 1, EP2, EP3, EP4 and external devices; SW6 is responsible for data transmission of EP5, EP6, EP7, EP8 with external devices; therefore, SW5 and SW6 easily become bandwidth blocking points and become bandwidth bottlenecks of the RapidIO network.
In consideration of the problem that the network stability and reliability are poor due to high probability of communication bandwidth blockage in the conventional RapidIO network, the embodiment of the invention provides a switching device, a switching system and a data sending method of the RapidIO network; the technology can be applied to a RapidIO network, and network nodes which are easy to generate bandwidth blocking are arranged between the network nodes so as to solve the bandwidth bottleneck in the network; the technology can also be applied to other interconnected networks and scenes with the requirement of solving the bandwidth bottleneck. The present invention can be implemented by using relevant software or hardware, and is described by using the embodiment below.
The first embodiment is as follows:
referring to fig. 2, a schematic structural diagram of a switching device of a first RapidIO network is shown; the switching device is provided with a switching matrix 10, a virtual physical layer module 11 and a plurality of physical ports; the switching matrix 10 is connected with a virtual physical layer module 11; the virtual physical layer module 11 is connected with a plurality of physical ports respectively; a plurality of physical ports are connected with the same external switching equipment;
in fig. 2, the virtual physical layer module 11 is illustrated as being connected to two physical ports, namely a physical port 12 and a physical port 13; in this embodiment, the specific number of physical ports connected to one virtual physical layer module is not limited, but usually, a plurality of physical ports connected to the same virtual physical layer module are connected to the same external switch device.
The switching matrix 10 is configured to receive a data stream and send the data stream to the virtual physical layer module 11; the virtual physical layer module 11 is configured to, when receiving a data stream, select a physical port according to remaining buffer capacity of the plurality of physical ports, and allocate a data frame in the data stream to the selected physical port; the physical port is used for receiving the data frame distributed by the virtual physical layer module and sending the data frame.
For example, a data stream sent by the switch matrix to the virtual physical layer module includes a plurality of data frames, and in general, the data frames in the same data stream have the same source ID (Identification), destination ID and priority; taking an example that one data stream includes 10 data frames, the virtual physical layer module monitors the remaining buffer capacity of the physical port 12 and the physical port 13, where the remaining buffer capacity may be the number of remaining data blocks (blocks) in the buffer; if the remaining cache capacity of the physical port 12 is large and the remaining cache capacity of the physical port 13 is small, it indicates that the physical port 12 is idle and the physical port 13 is busy; at this time, the virtual physical layer module may only select the physical port 12, and all 10 data frames are allocated to the physical port 12; the virtual physical layer module may further select a physical port 12 and a physical port 13, and allocate 10 data frames to the physical port 12 and the physical port 13 respectively according to the specific remaining buffer capacities of the two physical ports, for example, the physical port 12 allocates 7 data frames, and the physical port 13 allocates 3 data frames.
Because a plurality of physical ports connected with one virtual physical layer module are connected with the same external switching equipment, one data stream is sent through a plurality of physical ports, or a physical port with more residual cache capacity is selected to send the data stream, so that the phenomenon that the data volume of a certain physical port is too large and the network bandwidth is blocked can be avoided.
The embodiment of the invention provides switching equipment of a RapidIO network, wherein a virtual physical layer module is respectively connected with a plurality of physical ports; a plurality of physical ports are connected with the same external switching equipment; when the virtual physical layer module receives a data stream sent by the switching matrix, selecting a physical port according to the residual cache capacity of the plurality of physical ports, and distributing a data frame in the data stream to the selected physical port; the physical port receives the data frame distributed by the virtual physical layer module and sends the data frame; in this way, the virtual physical layer module is arranged to bind the plurality of physical ports for use, and data frames are dynamically allocated among the plurality of physical ports according to the residual cache capacity, so that load balance of redundant links among the switching devices is realized, the probability of communication bandwidth blockage of the RapidIO network is reduced, and the stability and reliability of the network are improved.
Example two:
referring to fig. 3, a schematic structural diagram of a switching device of a second RapidIO network is shown; the switching device is implemented on the basis of the switching device provided in the first embodiment; the switching device is provided with a switching matrix 10, a virtual physical layer module 11 and a plurality of physical ports; the switching matrix 10 is connected with a virtual physical layer module 11; the virtual physical layer module 11 is connected with a plurality of physical ports respectively; a plurality of physical ports are connected with the same external switching equipment;
further, the virtual physical layer module includes an order identifier 110; the sequence identifier 110 is configured to record an allocation sequence number of each data frame when each data frame is allocated to a corresponding physical port, and carry the allocation sequence number when the data frame is sent to a selected physical port.
The sequence identifier is set to record and allocate sequence numbers to a plurality of data frames in the data stream, so that when an external switch receives the data frames through one or more physical ports, the data frames can be reordered according to the allocated sequence numbers to form a correct data frame sequence, and the data frames are ensured to meet the requirement of order preservation of the same data stream in a RapidIO protocol in the transmission process.
Further, the physical port comprises a cache module, a physical layer module and a high-speed transceiver which are connected in sequence; the cache module is connected with the virtual physical layer module; a routing table is stored in the physical layer module; the high-speed transceiver is connected to an external switching device.
In practical implementation, the routing table may be implemented by a hardware structure, such as a RAM (Random Access Memory), a hash table, a CAM (Content Addressable Memory) table, and the like.
In fig. 3, the physical port 12 includes a cache module 121, a physical layer module 122, and a high-speed transceiver 123; the physical port 13 includes a cache module 131, a physical layer module 132, and a high-speed transceiver 133;
in the RapidIO network, RapidIO data frames and control symbols are serial bit streams on a physical transmission medium, and serial-parallel conversion and delimitation of the data frames and the control symbols can be realized after passing through a high-speed transceiver; the speed and lane number (lane) of the high speed transceiver determine the port width and port rate of the port entity. If the number of lanes of a high-speed transceiver is greater than 1, inter-lane alignment needs to be performed within the high-speed transceiver, but inter-lane alignment between the two high-speed transceivers in port 1 and port 2 is not required.
The physical layer module completes the analysis and CRC check of the RapidIO data frame header in the receiving direction, and completes the routing table lookup in the routing table according to the destination address (D _ ID) in the frame header. In the sending direction, the physical layer module completes the encapsulation of the frame header and the CRC generation. In addition, the Physical Layer module needs to implement parsing, generation and related processing of all control symbols (control symbols) defined in the RapidIO protocol, including implementation of link-level flow control defined in detail in the RapidIO protocol LP-Serial Physical Layer Specification.
The buffer module provides temporary storage places for data frames in the receiving and transmitting directions, and the buffer units are controlled independently in the receiving and transmitting directions. The interior of the cache module is organized according to data blocks (blocks), and the size of each block is carefully designed, so that at most one RapidIO data frame can be completely stored. In the sending direction, a data frame to be sent is temporarily stored in a buffer unit in the sending direction, a queue is established according to the priority of the frame to be sent, which frame should be read out from the buffer unit and sent is determined according to the scheduling result of the priority queue. In RapidIO networks, Strict Priority (SP) methods are typically employed for scheduling. In the receiving direction, the buffer unit does not set up a priority scheduling queue any more, but delivers the received data frame to the virtual physical layer according to the first-in first-out working mode.
In fig. 3, 2 port entities (physical port 12 and physical port 13) are hooked under the virtual physical layer module, and the virtual physical layer module and its hooked port entity may be referred to as a logical port; when the two physical ports work in a mode bound by the virtual physical layer module, the virtual physical layer module allocates data frames to be transmitted to the two port entities in a transmission direction, and the specific allocation method is to transmit the data frames to the port with the most residual blocks by monitoring the number of the transmission cache residual blocks of the physical port 12 and the physical port 13. In the receiving direction, the virtual physical layer module needs to implement reordering of the data frames sent on the physical ports 12 and 13, and the receiving sequence of the ordered data frames is completely consistent with the sending sequence of the virtual physical layer module of the sending party.
Further, the physical layer module is configured to add an allocation sequence number to the Cmd field in the start of frame control symbol of the data frame. The physical layer module is also used for extracting the allocation sequence number of each data frame in the data stream from the Cmd field and sending the data frame and the corresponding allocation sequence number to the virtual physical layer module when receiving the data stream sent by the same external switching device through a plurality of physical ports; the virtual physical layer module is also used for arranging the data frames according to the distribution sequence numbers and sending the data frames after being arranged to the switching matrix.
TABLE 1
In order to implement the foregoing ordering scheme, this embodiment is extended to some extent based on the original RapidIO protocol, where table 1 shows a short control symbol defined by the RapidIO protocol, and according to the protocol definition of the RapidIO2.2 version, when a value of type1 is 0x0, the control symbol is a start-of-packet (start-of-packet) control symbol, and a CRC-5 field is followed by the start of a RapidIO data frame. In the RapidIO protocol, two formats of a short control symbol and a long control symbol are defined, the two control symbols are only distinguished in specific formats, and the definitions of fields in the control symbols are completely consistent, so that only the short control symbol is taken as an example for explanation in the embodiment. The protocol is defined in the start of frame control symbol, Cmd field is always 0, and other values are reserved by the protocol. In this embodiment, reserved values of the Cmd field are used, and a method for using the Cmd field in the start frame control symbol to carry an allocation sequence number of a data frame is proposed, so as to implement reordering of data frames between the physical port 12 and the physical port 13 in the receiving direction in the above logical port.
Specifically, in the transmitting direction, the virtual physical layer module maintains a transmitting frame sequence counter (equivalent to the sequence identifier), the bit width is 3 bits, and the starting value is 0. In the physical layer frame format specification of the RapidIO protocol, an ACK _ ID field is defined to indicate a transmission frame sequence number in a physical port for implementing frame retransmission and order-preserving transmission in link-level flow control, and in order to distinguish from the ACK _ ID field, the embodiment names a frame sequence counter maintained by a virtual physical layer module as FRAM _ ID, and the FRAM _ ID is used to indicate a transmission frame sequence number in a logical port. When the virtual phy module sends a data frame to the phy port 12 or the phy port 13, FRAM _ ID is incremented by 1, and the current value of the counter is entered into the phy module in the port along with the data frame, and the value of the FRAM _ ID counter is assigned to the Cmd field when the phy module generates the start of frame control. In the receiving direction, the physical layer module in the port extracts the value of the Cmd field in the frame start control symbol, and the value is used as the FRAM _ ID and is sent to the virtual physical layer module along with the received data frames, and the virtual physical layer module reorders the data frames according to the sequence of the FRAM _ ID.
Referring to fig. 4, a schematic diagram of data transmission and reception by using a switching device of a RapidIO network is shown; the virtual physical layer module 30 and the virtual physical layer module 31 are respectively arranged in the two pieces of switching equipment; the virtual physical layer module 30 sends seven data frames in a data stream through the physical port a and the physical port B connected thereto; wherein the data frame generates a corresponding FRAM _ ID value by a frame sequence counter before being assigned to a physical port; in a data frame sent by a physical port A, FRAM _ ID values are 1, 3, 4 and 6 respectively; in a data frame sent by a physical port B, FRAM _ ID values are respectively 2, 5 and 7; the data frames marked by the ACK-ID values in the data frames are the sequence inside each physical port; when the virtual physical layer module 31 receives seven data frames respectively transmitted by the physical port a and the physical port B, the data frames are reordered according to the FRAM _ ID value.
Example three:
corresponding to the switching device of the RapidIO network provided in the foregoing embodiment, refer to a schematic structural diagram of a switching system of a first RapidIO network shown in fig. 5; the system comprises at least two switching devices; the plurality of physical ports on the first switching device are respectively connected with the plurality of physical ports on the second switching device in a one-to-one correspondence manner.
As shown in fig. 5, a physical port 501 in the first switching device 50 is connected with a physical port 511 in the second switching device 51; the physical port 502 in the first switching device 50 is connected with the physical port 512 in the second switching device 51; it is to be understood that, the specific number of physical ports connected between the first switch device and the second switch device in a one-to-one correspondence is not limited herein.
Further, the physical port of the first switch device is connected to a corresponding physical port of the second switch device through an optical fiber, a coaxial cable, a twisted pair cable, or a Printed Circuit Board (PCB). The virtual physical layer on the first switching equipment and the second switching equipment connects a plurality of pairs of ports to form a plurality of links, and the plurality of links are bound together to be used as a logical link.
Referring to fig. 6, a schematic structural diagram of a switching system of a second RapidIO network is shown; the system includes a plurality of switching devices and a plurality of endpoint devices. As in fig. 6, the system includes six switching devices and eight endpoint devices; two physical ports in the SW5 are respectively connected with two physical ports in the SW6 in a one-to-one correspondence manner. In practical applications, the port widths or port rates of the two physical ports in SW5 may be the same or different.
The switching system of the RapidIO network provided by the embodiment of the invention has the same technical characteristics as the switching equipment of the RapidIO network provided by the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
Example four:
corresponding to the switching device and the switching system of the RapidIO network provided in the foregoing embodiments, refer to a flowchart of a data sending method of the RapidIO network shown in fig. 7; the method is applied to the switching equipment; the method comprises the following steps:
step S702, the switching matrix receives the data stream and sends the data stream to the virtual physical layer module;
step S704, when the virtual physical layer module receives the data stream, selecting a physical port according to the remaining buffer capacity of the plurality of physical ports, and distributing the data frame in the data stream to the selected physical port;
step S706, the physical port receives the data frame allocated by the virtual physical layer module, and sends the data frame.
Further, the virtual physical layer module comprises a sequence identifier; the method further comprises the following steps: when each data frame is allocated to a corresponding physical port, the sequence identifier records the allocation sequence number of the data frame, and when the data frame is sent to the selected physical port, the allocation sequence number is carried.
The data sending method of the RapidIO network provided by the embodiment of the invention has the same technical characteristics as the switching equipment and the switching system of the RapidIO network provided by the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
The embodiment of the invention provides switching equipment, a switching system and a data sending method of a RapidIO network, wherein a virtual physical layer module is designed between a physical layer and a transmission layer of a RapidIO protocol, a plurality of physical layer entities (equivalent to physical ports) are hung under the same virtual physical layer module, and based on the virtual physical layer module, a method for realizing dynamic load sharing among the physical ports of the RapidIO network is also provided.
The embodiment of the invention provides switching equipment, a switching system and a data sending method of a RapidIO network, which are characterized in that on the basis of not changing a RapidIO network architecture, N physical ports (usually, N <8) are bound into a logic port between two switching equipment, and meanwhile, a Cmd field of a frame start control symbol in a RapidIO protocol is expanded and defined on a binding link, so that the sequential transmission of data frames between the logic ports is realized.
The embodiment of the invention provides switching equipment, a switching system and a data sending method of a RapidIO network, which realize the following technical effects: (1) the load balance among the redundant links is dynamically realized; the data frame is dynamically allocated in a logical port according to the bandwidth utilization condition of each physical port and a certain allocation algorithm. (2) The binding of the physical ports is not limited by hardware design, and each physical port can work under different port widths and port speeds in one logic port. (3) The control plane of the network is not required to be changed while the network congestion is solved by increasing the bandwidth. (4) The definition of the extensions to the protocol only takes place between two bound logical ports, without any impact on the rest of the network. (5) On a plurality of data links in a logic port, a fine-grained load sharing implementation method taking a data frame as a unit is realized, rigid division of a network path according to data flow is avoided, and bandwidth resources are utilized more efficiently.
The switching device, the switching system, and the computer program product of the data transmission method of the RapidIO network according to the embodiments of the present invention include a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementations may refer to the method embodiments and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A switching device of a RapidIO network is characterized in that a switching matrix, a virtual physical layer module and a plurality of physical ports are arranged on the switching device;
the switching matrix is connected with the virtual physical layer module; the virtual physical layer module is respectively connected with the plurality of physical ports; a plurality of physical ports are connected with the same external switching equipment;
the switching matrix is used for receiving a data stream and sending the data stream to the virtual physical layer module;
the virtual physical layer module is used for selecting the physical ports according to the residual cache capacities of the physical ports when the data stream is received, and distributing data frames in the data stream to the selected physical ports;
the virtual physical layer module comprises a sequence identifier; the sequence identifier is used for recording the distribution sequence number of the data frame when each data frame is distributed to the corresponding physical port, and carrying the distribution sequence number when the data frame is sent to the selected physical port;
and the physical port is used for receiving the data frame distributed by the virtual physical layer module and sending the data frame.
2. The switching device according to claim 1, wherein the physical port comprises a cache module, a physical layer module and a high-speed transceiver connected in sequence;
the cache module is connected with the virtual physical layer module; a routing table is stored in the physical layer module; the high-speed transceiver is connected with the external switching device.
3. The switching device of claim 2, wherein the physical layer module is configured to add the allocation sequence number to a Cmd field in a start of frame control symbol of the data frame.
4. The switch device of claim 3, wherein the physical layer module is further configured to, when a data stream sent by the same external switch device is received through a plurality of physical ports, extract an allocation sequence number of each data frame in the data stream from the Cmd field, and send the data frame and the corresponding allocation sequence number to the virtual physical layer module;
the virtual physical layer module is further configured to arrange the data frames according to the allocation sequence numbers, and send the data frames after being arranged to the switching matrix.
5. A switching system for a RapidIO network, characterized in that the system comprises at least two switching devices according to any one of claims 1 to 4;
the plurality of physical ports on the first switching device are respectively connected with the plurality of physical ports on the second switching device in a one-to-one correspondence manner.
6. The system of claim 5, wherein the physical ports on the first switching device are connected to the corresponding physical ports on the second switching device via fiber optic, coaxial cable, twisted pair, or backplane PCB traces.
7. The system of claim 5, wherein the system comprises a plurality of the switching devices and a plurality of endpoint devices.
8. A data transmission method of RapidIO network, characterized in that the method is applied to the switching device of any one of claims 1-4; the method comprises the following steps:
the method comprises the steps that a data stream is received by a switching matrix and sent to a virtual physical layer module;
when the virtual physical layer module receives the data stream, selecting a physical port according to the residual cache capacity of a plurality of physical ports, and distributing data frames in the data stream to the selected physical port;
the virtual physical layer module comprises a sequence identifier; when each data frame is allocated to the corresponding physical port, the sequence identifier records an allocation sequence number of the data frame, and when the data frame is sent to the selected physical port, the data frame carries the allocation sequence number;
and the physical port receives the data frame distributed by the virtual physical layer module and sends the data frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711469173.8A CN108199976B (en) | 2017-12-28 | 2017-12-28 | Switching equipment, switching system and data sending method of RapidIO network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711469173.8A CN108199976B (en) | 2017-12-28 | 2017-12-28 | Switching equipment, switching system and data sending method of RapidIO network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108199976A CN108199976A (en) | 2018-06-22 |
| CN108199976B true CN108199976B (en) | 2021-05-04 |
Family
ID=62585702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711469173.8A Active CN108199976B (en) | 2017-12-28 | 2017-12-28 | Switching equipment, switching system and data sending method of RapidIO network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108199976B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109286471B (en) * | 2018-09-30 | 2021-01-22 | 中国人民解放军战略支援部队信息工程大学 | CRC (Cyclic redundancy check) method and device for SRIO (serial peripheral input/output) controller |
| CN111107017A (en) * | 2019-12-06 | 2020-05-05 | 苏州浪潮智能科技有限公司 | Method, equipment and storage medium for processing switch message congestion |
| CN114095580A (en) * | 2021-11-16 | 2022-02-25 | 天津市滨海新区信息技术创新中心 | RapidIO low-delay and high-transmission-efficiency architecture implementation method and electronic equipment |
| CN114124858B (en) * | 2022-01-29 | 2022-05-17 | 飞腾信息技术有限公司 | Control method and control device |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1097535A (en) * | 1993-01-29 | 1995-01-18 | L.M.埃利克逊电话股份有限公司 | Controlled access atm switch |
| US6347089B1 (en) * | 1997-07-02 | 2002-02-12 | Advanced Communication Devices Corp. | Simplified ethernet frame switching system architecture without local buffer requirement |
| US6963535B2 (en) * | 2000-12-28 | 2005-11-08 | Intel Corporation | MAC bus interface |
| CN1717669A (en) * | 2002-11-26 | 2006-01-04 | 思科技术公司 | Apparatus and method for distributing buffer status information in a switching fabric |
| CN1783828A (en) * | 2004-12-02 | 2006-06-07 | 华为技术有限公司 | Space division exchanging device and information element exchanging method |
| CN101106523A (en) * | 2007-08-03 | 2008-01-16 | 重庆邮电大学 | A buffering structure for sectioned share optical loop switching network |
| CN101404645A (en) * | 2008-04-29 | 2009-04-08 | 华为技术有限公司 | Multiport Ethernet interface, its implementing method and physical layer interface |
| CN104601494A (en) * | 2015-01-08 | 2015-05-06 | 中国科学院空间应用工程与技术中心 | FC-AE exchanger and exchanging method |
| CN105812225A (en) * | 2016-05-04 | 2016-07-27 | 烽火通信科技股份有限公司 | Virtual Ethernet communication component irrelevant to interface and method thereof for realizing communication |
| CN105847033A (en) * | 2016-02-26 | 2016-08-10 | 重庆世纪之光科技实业有限公司 | Scheduling method, device and system |
| CN105897621A (en) * | 2016-07-01 | 2016-08-24 | 中国航空无线电电子研究所 | Gigabit AFDX (Avionics Full Duplex Switched Ethernet) switcher based on CIOQ (Combined Input and Output Queuing) structure and switching method thereof |
| CN105959241A (en) * | 2016-04-27 | 2016-09-21 | 西安空间无线电技术研究所 | Unified scheduling method for space-borne photovoltaic hybrid exchange system |
| CN107343231A (en) * | 2017-09-04 | 2017-11-10 | 南京曦光信息科技有限公司 | Asymmetric caching and forwarding module and the Packet Switch Node and network that are made from it |
-
2017
- 2017-12-28 CN CN201711469173.8A patent/CN108199976B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1097535A (en) * | 1993-01-29 | 1995-01-18 | L.M.埃利克逊电话股份有限公司 | Controlled access atm switch |
| US6347089B1 (en) * | 1997-07-02 | 2002-02-12 | Advanced Communication Devices Corp. | Simplified ethernet frame switching system architecture without local buffer requirement |
| US6963535B2 (en) * | 2000-12-28 | 2005-11-08 | Intel Corporation | MAC bus interface |
| CN1717669A (en) * | 2002-11-26 | 2006-01-04 | 思科技术公司 | Apparatus and method for distributing buffer status information in a switching fabric |
| CN1783828A (en) * | 2004-12-02 | 2006-06-07 | 华为技术有限公司 | Space division exchanging device and information element exchanging method |
| CN101106523A (en) * | 2007-08-03 | 2008-01-16 | 重庆邮电大学 | A buffering structure for sectioned share optical loop switching network |
| CN101404645A (en) * | 2008-04-29 | 2009-04-08 | 华为技术有限公司 | Multiport Ethernet interface, its implementing method and physical layer interface |
| CN104601494A (en) * | 2015-01-08 | 2015-05-06 | 中国科学院空间应用工程与技术中心 | FC-AE exchanger and exchanging method |
| CN105847033A (en) * | 2016-02-26 | 2016-08-10 | 重庆世纪之光科技实业有限公司 | Scheduling method, device and system |
| CN105959241A (en) * | 2016-04-27 | 2016-09-21 | 西安空间无线电技术研究所 | Unified scheduling method for space-borne photovoltaic hybrid exchange system |
| CN105812225A (en) * | 2016-05-04 | 2016-07-27 | 烽火通信科技股份有限公司 | Virtual Ethernet communication component irrelevant to interface and method thereof for realizing communication |
| CN105897621A (en) * | 2016-07-01 | 2016-08-24 | 中国航空无线电电子研究所 | Gigabit AFDX (Avionics Full Duplex Switched Ethernet) switcher based on CIOQ (Combined Input and Output Queuing) structure and switching method thereof |
| CN107343231A (en) * | 2017-09-04 | 2017-11-10 | 南京曦光信息科技有限公司 | Asymmetric caching and forwarding module and the Packet Switch Node and network that are made from it |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108199976A (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108199976B (en) | Switching equipment, switching system and data sending method of RapidIO network | |
| US11601359B2 (en) | Resilient network communication using selective multipath packet flow spraying | |
| JP6158860B2 (en) | Innovative Adaptive Routing in Dragonfly Processor Interconnect Network | |
| JP5977383B2 (en) | Table-driven routing in a Dragonfly processor interconnect network | |
| US9007902B1 (en) | Method and apparatus for preventing head of line blocking in an Ethernet system | |
| US8310934B2 (en) | Method and device for controlling information channel flow | |
| US20030026267A1 (en) | Virtual channels in a network switch | |
| US20030026205A1 (en) | Packet input thresholding for resource distribution in a network switch | |
| EP3675439B1 (en) | Data transmission | |
| JP2009534005A (en) | Bidirectional link aggregation | |
| US20100095025A1 (en) | Virtual channel remapping | |
| US20100002714A1 (en) | PCI express network | |
| CN107770085B (en) | Network load balancing method, equipment and system | |
| US20110261823A1 (en) | Method and system for multiplexing data streaming in audio/video networks | |
| US20230344920A1 (en) | Reliable communications using a point to point protocol | |
| US20200120017A1 (en) | Data distribution method, data aggregation method, and related apparatuses | |
| CN110312283B (en) | Information processing method and device | |
| CN112005528B (en) | Data exchange method, data exchange node and data center network | |
| CN105812063B (en) | Network on mating plate system based on statistic multiplexing and communication means | |
| TW200947957A (en) | Non-block network system and packet arbitration method thereof | |
| US20040081096A1 (en) | Method and device for extending usable lengths of fibre channel links | |
| CN114900469B (en) | Method, system, equipment and medium for controlling data flow of multi host network card | |
| US20070086479A1 (en) | Techniques to buffer traffic in a communications system | |
| JP2015536621A (en) | Passive connectivity optical module | |
| WO2019165855A1 (en) | Message transmission method and device |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200528 Address after: 300450 Binhai New Area, Binhai - Zhongguancun Science Park Rongsheng Plaza, No. 4 Building 702-7, Tianjin Applicant after: TIANJIN XINHAICHUANG TECHNOLOGY Co.,Ltd. Address before: 300450 Binhai New Area, Binhai - Zhongguancun Science Park Rongsheng Plaza, No. 4 Building 702-7, Tianjin Applicant before: TIANJIN XINHAICHUANG TECHNOLOGY Co.,Ltd. Applicant before: INFORMATION TECHNOLOGY INNOVATION CENTER OF TIANJIN BINHAI NEW AREA |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |