Data forwarding method for advanced telecom computing architecture chassis

Abstract

The application provides a data forwarding method for an advanced telecommunication computing architecture (ATCA) chassis. The method comprises: a first switching board card forwarding an original signaling message to each processing board card, and a second switching board card equally dividing the original data message into M first data messages and distributing one first data message to each processing board card; each processing board card divides the received first data message into M second data messages, each second data message corresponding to one processing board card; each processing board card forwards the second data message corresponding to other processing board cards to the processing board card corresponding to the second data message through the first switching board card; and each processing board card forwards each second data message corresponding to each processing board card to a target system based on the original signaling message. The data forwarding method for the ATCA chassis can improve the performance and stability of the slot processing board card and improve the data forwarding performance.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a data forwarding method for an advanced telecommunications computing architecture chassis. Background Technology

[0002] With the explosive growth of mobile internet data traffic, the hardware of business analysis systems is also expanding significantly. ATCA (Advanced Telecommunications Computing Architecture) chassis are typically fully loaded with 14 sets of cards (including 2 switching cards and 12 processing cards).

[0003] The existing data forwarding method for ATCA chassis involves individual input and output of each board (i.e., a single processing board). The configurations of each board are relatively independent, and a larger amount of data is processed by stacking them up. The configurations of each board are different due to the different data flow inputs and outputs, and each board needs to be managed separately. When there are many boards, managing the boards is complicated and prone to errors.

[0004] Furthermore, due to varying access traffic, some processing boards may overflow during peak periods, while others may only utilize 50% of their performance, leading to unstable ATCA data offloading performance and wasted processing capacity. Additionally, since the output service data needs to be routed to the same backend processor, the maximum throughput of the 10 Gigabit output port of the slot2 switch board is 24 * 10 Gbps, supporting a maximum of 24 processors. If each backend processor has a processing capacity of 6 Gbps, then the current maximum throughput forwarded by the ATCA chassis is 144 Gbps. When the throughput exceeds this value, additional hardware chassis and offloading boards are required.

[0005] In summary, the existing data forwarding methods for ATCA chassis have poor performance. Summary of the Invention

[0006] This invention provides a data forwarding method for advanced telecommunications computing architecture chassis, which addresses the shortcomings of poor data forwarding performance in existing technologies and achieves high-performance, balanced data forwarding.

[0007] This invention provides a data forwarding method for an advanced telecommunications computing architecture chassis, the advanced telecommunications computing architecture chassis including a first switching board, a second switching board, and M processing boards; wherein, 2≤M≤K-2; K represents the total number of slots in the advanced telecommunications computing architecture chassis;

[0008] The data forwarding method includes:

[0009] The first switching board forwards the original signaling message to each of the processing boards, and the second switching board divides the original data message into M first data messages evenly, and distributes one first data message to each of the processing boards.

[0010] Each processing board will receive the first data packet and divide it into M second data packets, with each second data packet corresponding to one processing board.

[0011] Each processing board forwards the second data packet corresponding to other processing boards to the processing board corresponding to the second data packet through the first switching board.

[0012] Each processing board forwards its corresponding second data packets to the target system based on the original signaling message.

[0013] According to a data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention, the first switching board forwards raw signaling messages to each of the processing boards, including:

[0014] The first switching board copies the original signaling message to obtain M copies of the original signaling message;

[0015] The first switching board forwards the original signaling message to each of the processing boards.

[0016] According to the present invention, a data forwarding method for an advanced telecommunications computing architecture chassis is provided, wherein each processing board divides the received first data packet into M second data packets, and each second data packet corresponds to one processing board, including:

[0017] Each processing board marks the data in the first data packet with its own mark based on the IMSI in the first data packet.

[0018] Based on the markings of the data in the first data packet, the first data packet is divided into M second data packets.

[0019] According to a data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention, each processing board forwards the second data packet corresponding to other processing boards to the processing board corresponding to the second data packet through the first switching board, including:

[0020] Each processing board sends the second data packet corresponding to other processing boards to the first switching board, so that the first switching board forwards the second data packet to the processing board corresponding to the second data packet based on the tag of each second data packet.

[0021] According to a data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention, the second data packet includes N sets of third data packets;

[0022] Where N is the number of output ports of each processing board.

[0023] According to a data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention, the processing board is marked as the virtual MAC address of the output port of the processing board.

[0024] According to a data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention, each processing board forwards each corresponding second data packet to a target system based on the original signaling packet, including:

[0025] Each processing board forwards the second data packet to the target system through its output port based on the original signaling message and the virtual MAC address of its output port.

[0026] According to the present invention, a data forwarding method for an advanced telecommunications computing architecture chassis is provided, wherein the first switching board is of model SW-10Q.

[0027] According to the present invention, a data forwarding method for an advanced telecommunications computing architecture chassis is provided, wherein the second switching board is of model SW-24X.

[0028] According to the present invention, a data forwarding method for an advanced telecommunications computing architecture chassis is provided, wherein the processing board is of model NP-12X.

[0029] The data forwarding method for advanced telecommunications computing architecture chassis provided by this invention evenly distributes raw data packets to each processing board through a second switching board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on processing boards in traditional ATCA chassis. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of service data tagged traffic through "post-association," improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0031] Figure 1 This is a flowchart illustrating the data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention.

[0032] Figure 2 This is one of the schematic diagrams of the board deployment of the ATCA chassis provided by the present invention;

[0033] Figure 3 This is the second schematic diagram of the board deployment of the ATCA chassis provided by the present invention;

[0034] Figure 4 This is one of the schematic diagrams illustrating the principle of the data forwarding method for an advanced telecommunications computing architecture chassis provided by the present invention;

[0035] Figure 5 This is the second schematic diagram of the data forwarding method for advanced telecommunications computing architecture chassis provided by the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0037] The following is combined Figures 1-5 This invention describes a data forwarding method for an advanced telecommunications computing architecture chassis.

[0038] Figure 1 This is a flowchart illustrating the data forwarding method for an advanced telecommunications computing architecture chassis provided in this application. Figure 1 As shown, the method includes steps 101, 102, 103 and 104.

[0039] The execution entity of the data forwarding method for advanced telecommunications computing architecture chassis provided in this embodiment of the invention can be an ATCA chassis.

[0040] The advanced telecommunications computing architecture chassis includes a first switching board, a second switching board, and M processing boards; where 2≤M≤K-2; and K represents the total number of slots in the advanced telecommunications computing architecture chassis.

[0041] Specifically, the ATCA chassis can deploy K boards. These K boards may include two switching boards (a first switching board and a second switching board, respectively) and multiple processing boards.

[0042] The ATCA chassis can be viewed as an overall ISP (Internet Service Provider) raw data processing subsystem.

[0043] Figure 2 This is one of the schematic diagrams of the board deployment of the ATCA chassis provided by the present invention. Figure 3 This is the second schematic diagram of the board deployment of the ATCA chassis provided by the present invention. Figure 2 The board deployment on the front panel of the ATCA chassis is shown. Figure 3 The diagram illustrates the board deployment on the rear panel of the ATCA chassis. For example, as shown... Figure 2 and Figure 3 As shown, slot 1 of the ATCA chassis is equipped with a 1*40G switching board, model SW-24X; slot 2 is equipped with a 1*100G switching board, model SW-10Q; and slots 3-14 are equipped with 12*40G processing boards, model NP-12X.

[0044] The ATCA chassis is a standard 40G or 100G ATCA chassis, with slot 1 for switching raw ISP service data and slot 2 for switching signaling data (balanced input). For each board, the number in the box indicates the input or output port number included on that board.

[0045] The following is based on Figure 2 and Figure 3 Using the ATCA chassis shown as an example, the implementation process of the data forwarding method is described.

[0046] Step 101: The first switching board forwards the original signaling message to each processing board, and the second switching board divides the original data message into M first data messages evenly, and distributes one first data message to each processing board.

[0047] Specifically, the first switching board SW-24X can receive the input raw signaling messages through the front board port XE1, and forward the raw signaling messages to the 12 processing boards NP-12X through the chassis fabric1 bus backplane.

[0048] The second switching board SW-10Q can receive the input raw data packets through the front board port CE1-10, and forward the raw signaling packets evenly to the 12 processing boards NP-12X through the chassis fabric2 bus backplane. That is, the second switching board SW-10Q evenly divides the raw data packets into M first data packets and distributes one first data packet to each processing board NP-12X.

[0049] Optionally, after the second switching board SW-10Q receives system service data (i.e., raw data packets) from the front board 10Q-F and the rear board 10Q-R, it can distribute the data evenly to the 12 processing boards NP-12X using the IP hash algorithm, with each board handling 1 / 12 of the traffic.

[0050] Step 102: Each processing board will divide the received first data packet into M second data packets, and each second data packet corresponds to one processing board.

[0051] Specifically, after each processing board NP-12X receives the original signaling message and the first data message, it can divide the first data message into M second data messages based on a preset division standard.

[0052] Optionally, the preset classification criteria may include at least one of the following: the data type, business type, and source application (APP, Application) in the first data message.

[0053] Optionally, each processing board can achieve a one-to-one correspondence between each second data packet and each processing board by tagging the first data packet.

[0054] Step 103: Each processing board forwards the second data packet corresponding to other processing boards to the processing board corresponding to the second data packet through the first switching board.

[0055] Specifically, for each processing board NP-12X, the second data packet corresponding to itself in the first data packet is retained, and the second data packets corresponding to other processing boards are forwarded to the first switching board SW-24X.

[0056] Based on the correspondence between the second data packet and the processing board, the first switching board SW-24X forwards each second data packet to the processing board NP-12X corresponding to the second data packet.

[0057] Step 104: Each processing board forwards the corresponding second data packets to the target system based on the original signaling messages.

[0058] Specifically, each processing board NP-12X, through the back IO board, retains and receives the second data packet forwarded by the first switching board SW-24X, and outputs it to the background processor in the target system.

[0059] Optionally, the target system can be an analytical storage backend system used to analyze and store system business data in the background.

[0060] Optionally, after receiving the associated tagged balance data (i.e., the second data message), the target system can analyze, process, and store the data, and display and query it to customers through the system's web interface.

[0061] It should be noted that, without increasing the investment in 100G-NP processing boards (e.g., NP-12X), the raw traffic capacity is 500Gbps: the processing capacity of each backend processor is 6Gbps, corresponding to 6*12=72 (sets) of protocol analysis and processing units. In this embodiment of the invention, the maximum forwarding output traffic of the ATCA chassis is 432Gbps; compared with the traditional ATCA chassis's processing capacity of 144Gbps, the processing capacity of the load cards is greatly improved.

[0062] This invention innovatively proposes a high-efficiency data forwarding solution for a 12-node board, improving hardware board utilization and processing capacity; it standardizes the configuration management of processing boards, upgrading from board configuration to slot location configuration; it has high fault tolerance, allowing for direct hot-swappable replacement of boards in case of failure, simply by loading the slot configuration; and it is suitable for dual-star ATCA high-efficiency load balancing systems.

[0063] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0064] Based on any of the above embodiments, the first switching board forwards the original signaling messages to each processing board, including: the first switching board copies the original signaling messages to obtain M copies of the original signaling messages.

[0065] Specifically, after the first switching board SW-24X receives the original signaling message from the front board, it can obtain 12 copies of the original signaling message through full copying (or full copying in the sub-computer room).

[0066] The first switching board forwards the original signaling messages to each processing board.

[0067] Specifically, the first switching board SW-24X can evenly distribute the 12 copies of the original signaling messages to the processing board NP-12X, with each processing board receiving 1 / 1 copy of the original signaling message.

[0068] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0069] Based on any of the above embodiments, each processing board will divide the received first data packet into M second data packets, and each second data packet corresponds to a processing board. This includes: each processing board marking the data in the first data packet with its own processing board's mark based on the IMSI in the first data packet.

[0070] Specifically, after each processing board NP-12X receives the original signaling message and the first data message, it performs data association tagging.

[0071] Optionally, each NP-12X processing board can take the modulus based on the number of processors in the target system to mark the first data packet, that is, mark it with the mark of each processing board.

[0072] It is understandable that there is a correspondence between the modulus results and the NP-12X processing boards.

[0073] Optionally, each NP-12X processing board can associate and tag the data packet with the IMSI (International Mobile Subscriber Identity) in the first data packet and the virtual MAC address of the output port (i.e., the 1*6 XE ports on the back board) of each NP-12X processing board. The processed data is then divided into 12*N parts.

[0074] Figure 4 This is one of the schematic diagrams illustrating the principle of the data forwarding method for an advanced telecommunications computing architecture chassis provided by this invention. In the ATCA dual-star architecture, such as... Figure 4 As shown, after the processing board NP-12X receives the original signaling message and the first data message (which can be regarded as the "white ball" in the figure) from the switching boards SW-10Q and SW-24X, it marks them into 12-color "colored balls" according to the seq-number and IMSI association of the modulus result.

[0075] It should be noted that the colors of the "colored balls" are determined by... Figure 4 The filled pattern in the circle (representing "ball") is represented by a pattern.

[0076] Based on the markings of the data in the first data packet, the first data packet is divided into M second data packets.

[0077] Specifically, data with the same marker in the first data packet are divided into the same second data packet, thus obtaining M second data packets.

[0078] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0079] Based on any of the above embodiments, each processing board forwards the second data packet corresponding to other processing boards to the processing board corresponding to the second data packet through the first switching board, including: each processing board sends the second data packet corresponding to other processing boards to the first switching board, so that the first switching board forwards the second data packet to the processing board corresponding to the second data packet based on the tag of each second data packet.

[0080] Specifically, the first switching board can perform cross-matrix forwarding of the tagged data (i.e., the second data packet) based on the virtual MAC address.

[0081] Optionally, the NX-12 processing board can be configured with output ports, allowing configuration of fixed virtual MAC address output rules for the 12*6 XE ports on the back of the NX-12 processing board, with mutually exclusive MAC address segments.

[0082] Specifically, it includes:

[0083] a. Configure forwarding rules for the NX-12 processing board;

[0084] b. The NX-12 processing board divides the second data packet into 12*N groups of marking data. The virtual MAC-1 group corresponding to this board is output from the back IO.

[0085] c. Other tagged virtual MAC groups -2 to 12 are forwarded to SW-X24.

[0086] Optionally, the first switching board SW-X24 can be configured for switching output flow control, configuring the data output forwarding rules after internal tagging of the first switching board SW-X24, and the virtual MAC address range of the 40GE port of the internal 12-node corresponding to the processing board NX-12 is mutually exclusive.

[0087] Specifically, it includes:

[0088] Ⅰ. The first switching board SW-X24 receives 12 sets of virtual MAC data (i.e., the second data packets corresponding to other processing boards) from the processing board NX-12 in slot 3-14;

[0089] II. Configure the virtual MAC addresses of the internal 40GE bus ports of the 12 processing boards NX-12 corresponding to the first switching board SW-X24;

[0090] III. Configure 12 virtual MAC forwarding rules on the first switching board SW-X24, and forward the 12 virtual MAC data to the corresponding processing board NX-12 according to the group.

[0091] Figure 5 This is the second schematic diagram illustrating the principle of the data forwarding method for an advanced telecommunications computing architecture chassis provided by this invention. In the ATCA dual-star architecture, Figure 5 As shown, the processing board NX-12 (12NPs) marks the system data (12 colored balls), keeps its own defined colored ball, and forwards the remaining 11 colored balls to the switching board SW-24X.

[0092] After receiving the "colored ball" forwarded from the 12*NP-12X processing card, the SW-24X switching card forwards it to the 12 NP-12X processing boards according to the 12 color definitions.

[0093] For example: Define the NP-12X card in slot-13 as "13 Dark Red". After leaving its own dark red ball, it forwards the marking data of the remaining 11 colored balls ("11 Red", "9 Orange", "7 Yellow", "5 Light Green", "3 Green", "4 Light Blue", "6 Light Purple", "8 Purple", "10 Pink", "12 Blue", "14 Dark Blue") to the SW-24X switching card in slot2. After receiving the data, the SW-24X switching card distributes it to the NP-12X processing card in slot3-14 according to the color of the marked business data.

[0094] After receiving 11 sets of color card data forwarded to it by the switching board, the NP-12X processing board adds one set of data for its own color, for a total of 12 sets of color card data (as follows: the NP-12X board in slot 13 keeps its own "13 Dark Red" data, and then receives 11 sets of "13 Dark Red" data from the switching SW-24X, for a total of 12 sets of data). The NP-12X processing board then uses its own PORT1-6 ports (specifically NP-12X-NR1-6) to forward the balanced "color ball" data to the target system (in this embodiment, 10GE data from port 6 meets the requirements based on the processing capacity of the service board), thus achieving balanced processing traffic of the same source and destination and load balancing subsystem.

[0095] It should be noted that the colors of the "colored balls" are determined by... Figure 5 The filled pattern in the circle (representing "ball") is represented by a pattern.

[0096] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0097] Based on any of the above embodiments, the second data packet includes N sets of third data packets; where N is the number of output ports of each processing board.

[0098] Specifically, optionally, each processing board NP-12X can associate and tag the data packet with the IMSI (International Mobile Subscriber Identity) in the first data packet and the virtual MAC address of the output port (i.e., the 1*6 XE ports on the back board) of each processing board NP-12X. The processed data is then divided into 12*N parts.

[0099] After processing, each second data packet includes N sets of third data packets.

[0100] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0101] Based on any of the above embodiments, the processing board is marked as the virtual MAC address of the output port of the processing board.

[0102] Specifically, each NP-12X processing board can be tagged according to the IMSI in the first data packet, and after taking the modulus based on the number of backend processors, the virtual MAC address of the output port of the NP-12X processing board can be tagged.

[0103] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0104] Based on any of the above embodiments, each processing board forwards each second data packet corresponding to each processing board to the target system based on the original signaling message, including: each processing board forwards the second data packet to the target system through the output port based on the original signaling message and the virtual MAC address of the output port of each processing board.

[0105] Specifically, each processing board NP-12X outputs port data. After receiving the tagging data (specifically the second data packet corresponding to the processing board NP-12X) from its own 1*6 XE ports forwarded by itself and the first switching board SW-X24, it outputs the data to the target system from its own 1*6 XE ports.

[0106] For each processing board NP-12X, it receives 11 sets of tagging data forwarded from the first switching board SW-X24; the card outputs the data from the NR1-6 ports (i.e., 1*6 XE ports) of the back IO board according to the virtual MAC forwarding rules of the tagging data.

[0107] This invention, through a second switching board, evenly distributes the raw data packets to each processing board. Each processing board then evenly distributes the first data packet, achieving balanced distribution of raw data packets from each processing board to each backend processor. This solves the problem of uneven traffic load on traditional ATCA chassis processing boards. By fully scheduling the I / O card port resources of the processing boards and matrix-distributing traffic output, it achieves balanced output of "post-association" of service data tagging traffic, improving the performance and stability of slot processing boards and enhancing data forwarding performance. Furthermore, it eliminates the need for subsequent use of box-type splitter boards, thus saving the cost of adding such equipment later.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data forwarding method for an advanced telecommunications computing architecture chassis, characterized in that, The advanced telecommunications computing architecture chassis includes a first switching board, a second switching board, and M processing boards; wherein, 2≤M≤K-2; and K represents the total number of slots in the advanced telecommunications computing architecture chassis. The data forwarding method includes: The first switching board forwards the original signaling message to each of the processing boards, and the second switching board divides the original data message into M first data messages evenly, and distributes one first data message to each of the processing boards. Each processing board will receive the first data packet and divide it into M second data packets, with each second data packet corresponding to one processing board. Each processing board forwards the second data packet corresponding to other processing boards to the processing board corresponding to the second data packet through the first switching board. Each processing board forwards the second data packets corresponding to each processing board to the target system based on the original signaling message; Each processing board will receive the first data packet and divide it into M second data packets. Each second data packet corresponds to one processing board, including: Each processing board marks the data in the first data packet with its own mark based on the IMSI in the first data packet. Based on the markings of the data in the first data packet, the first data packet is divided into M second data packets.

2. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, The first switching board forwards the original signaling messages to each of the processing boards, including: The first switching board copies the original signaling message to obtain M copies of the original signaling message; The first switching board forwards the original signaling message to each of the processing boards.

3. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, Each processing board forwards the second data packet corresponding to other processing boards to the processing board corresponding to the second data packet through the first switching board, including: Each processing board sends the second data packet corresponding to other processing boards to the first switching board, so that the first switching board forwards the second data packet to the processing board corresponding to the second data packet based on the tag of each second data packet.

4. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, The second data packet includes N sets of third data packets; Where N is the number of output ports of each processing board.

5. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, The label on the processing board is the virtual MAC address of the output port of the processing board.

6. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, Each processing board forwards its corresponding second data packets to the target system based on the original signaling message, including: Each processing board forwards the second data packet to the target system through its output port based on the original signaling message and the virtual MAC address of its output port.

7. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, The first switching board is model SW-10Q.

8. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, The second switching board is model SW-24X.

9. The data forwarding method for an advanced telecommunications computing architecture chassis according to claim 1, characterized in that, The processing board is model NP-12X.

Images