WO2018076636A1

WO2018076636A1 - Interlaken package cutting and scheduling method and apparatus, and computer storage medium

Info

Publication number: WO2018076636A1
Application number: PCT/CN2017/081746
Authority: WO
Inventors: 李龙龙; 林海都; 陈宗正; 魏方旭
Original assignee: 深圳市中兴微电子技术有限公司
Priority date: 2016-10-31
Filing date: 2017-04-24
Publication date: 2018-05-03
Also published as: CN108011842A

Abstract

Disclosed are an Interlaken package cutting and scheduling method and apparatus, and a computer storage medium. The method comprises: receiving a data package sent by at least one upstream port, and respectively performing package cutting processing on a data package corresponding to each upstream port, so as to acquire slice data corresponding to each upstream port; acquiring an interface corresponding to each upstream port from a pre-set Interlaken interface group, wherein the Interlaken interface group includes at least two Interlaken interfaces; scheduling the slice data corresponding to each upstream port to an Interlaken interface corresponding to each upstream port; and sending the slice data corresponding to each upstream port via the Interlaken interface corresponding to each upstream port.

Description

Interlaken packet cutting and scheduling method, device and computer storage medium

Cross-reference to related applications

The present application is filed on the basis of the Chinese Patent Application No. No. No. No. No. No. No. No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No No

Technical field

The present invention relates to the field of integrated circuits for Interlaken scheduling, and in particular, to an Interlaken packet and scheduling method, apparatus, and computer storage medium.

Background technique

With the introduction of 56 gigabits per second (Gbps) serializer/deserializer (SERDES, Serializer/Deserializer), big data, multi-port data transmission, and wide application of 28Gbps SERDES and flexible Interlaken interface Sex and ease of use have spawned the Interlaken interface being heavily used in the backplane. The Interlaken interface designed in the prior art is limited by the data bit width and can only transmit 200G to 300Gbits of data per second, so that it can not meet the 400Gbps interface transmission of 400Gbps or higher.

Summary of the invention

To solve the above technical problem, an embodiment of the present invention is to provide an Interlaken packet and scheduling method, apparatus, and computer storage medium, which are intended to multiplex and reuse an existing Interlaken interface into multiple Interlaken interfaces, and send at least one upstream port. The data packets are respectively scheduled to the Interlaken interface corresponding to each upstream port, thereby increasing the rate of data transmission.

The technical solution of the embodiment of the present invention is implemented as follows:

In a first aspect, an embodiment of the present invention provides an Interlaken packet cutting and scheduling method, where the method includes:

Receiving a data packet sent by at least one port of the upstream port, and performing packet cutting processing on each data packet corresponding to each upstream port to obtain slice data corresponding to each upstream port;

Acquiring an interface corresponding to each upstream port from a preset Interlaken interface group; where the Interlaken interface group includes at least two Interlaken interfaces;

Scheduling the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports;

The slice data corresponding to each of the upstream ports is sent by the Interlaken interface corresponding to each of the upstream ports.

In an embodiment, the data packet sent by the upstream port is received, and the data packet corresponding to each upstream port is separately packetized to obtain the slice data corresponding to each upstream port, which specifically includes:

Receiving, by the upstream, at least one port, the data packet sent by the upstream port, and acquiring the packet description information of the data packet corresponding to each upstream port, where the packet description information includes a packet header, a trailer, and a packet length information;

Obtaining a port identifier of the current to-be-scheduled port according to the preset polling schedule, and acquiring the to-be-scheduled data packet and the to-be-scheduled data corresponding to the port identifier of the to-be-scheduled port according to the port identifier of the current to-be-scheduled port Package description information of the package;

And performing packetizing processing on the to-be-scheduled data packet corresponding to the current to-be-scheduled port according to the preset packet-cutting information and the packet description information of the to-be-scheduled data packet, and acquiring the slice data corresponding to the current to-be-scheduled port; The packet cutting information includes a maximum burst length (Burstmax), a minimum burst length (Burstmin), a parameter value of a normal type or an enhanced scheduling mode;

Update the information of the polling schedule, and obtain the port identifier of the next port to be scheduled according to the updated polling schedule.

In an embodiment, the preset polling schedule is composed of a port identifier of the upstream port and a scheduling indicator value corresponding to the port identifier, and is used to obtain a port identifier of the current to-be-scheduled port.

In an embodiment, the obtaining, by the preset polling schedule, the port identifier of the port to be scheduled, specifically includes:

Obtaining, according to a preset first polling rule, a scheduling indication sequence consisting of scheduling indication values from a preset polling scheduling table; wherein each row scheduling indication sequence respectively corresponds to a row of port identification sequences;

Obtaining the port identifier of the current to-be-scheduled port from the obtained scheduling instruction sequence of the line according to the preset second polling rule.

In an embodiment, the packet to be scheduled corresponding to the current to-be-scheduled port is packet-cut according to the preset packet-cut information and the packet description information of the to-be-scheduled packet, and the current to-be-obtained is obtained. The slice data corresponding to the scheduling port includes:

When the parameter value of the normal scheduling mode in the packet-cutting information is a valid value, the parameter value of Burstmax in the packet-cutting information is uniformly cut by the unit length of the slice data, and When the length of the packet data remaining after the uniform cutting is smaller than the parameter value of the Burstmax, the remaining packet data is taken as one slice data;

When the parameter value of the enhanced scheduling mode in the packet-cutting information is a valid value, the parameter value of Burstmax in the packet-cutting information is uniformly cut by the unit length of the slice data, and When the length of the packet data remaining after the uniform cutting is greater than Burstmax and less than Burstmax+Burstmin, the remaining packet data is cut into two pieces of data; wherein the length of the first slice data corresponding to the remaining packet data is equal to Burstmax-Burstmin, the length of the second slice data corresponding to the remaining packet data is equal to the remaining packet data length minus the length of the first slice data.

In an embodiment, the scheduling of the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports includes:

Scheduling the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports according to the preset data scheduling mode information, where the data scheduling mode information is used to indicate that each of the upstream ports corresponds to The slice data is scheduled to the Interlaken interface corresponding to each of the upstream ports in a full packet mode or an interleaved mode.

In an embodiment, the scheduling, according to the preset data scheduling mode information, the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports, specifically:

When the data scheduling mode information indicates the whole packet mode, all the slice data corresponding to the entire packet data of each upstream port is spliced into one piece of data, and the spliced whole piece of data is scheduled to each of the pieces. The Interlaken interface corresponding to the upstream port;

When the data scheduling mode information indicates the interleaving mode, the slice data of each upstream port is uniformly scheduled to the Interlaken interface corresponding to each upstream port.

In a second aspect, an embodiment of the present invention provides an Interlaken packet cutting and scheduling apparatus, where the apparatus includes: a data packet cutting module, a data packet scheduling module, and an Interlaken interface module;

The packet-cutting module is configured to receive a data packet sent by at least one port upstream, and perform packet-cut processing on each data packet corresponding to each upstream port to obtain slice data corresponding to each upstream port;

The data packet scheduling module is configured to obtain an interface corresponding to each upstream port from a preset Interlaken interface group.

The packet scheduling module is further configured to schedule the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports;

The Interlaken interface module is configured to send the slice data corresponding to each of the upstream ports.

In an embodiment, the data packet cutting module includes: a data packet processing submodule, Interlaken packet control submodule and packet packet submodule;

The data packet processing submodule is configured to receive a data packet sent by at least one port upstream, and obtain packet description information of each data packet corresponding to each upstream port;

The Interlaken packet control sub-module is configured to obtain, according to a preset polling schedule, a port identifier of a port to be scheduled, and obtain a port identifier of the port to be scheduled according to the port identifier of the current to-be-scheduled port. Packet to be scheduled and packet description information of the to-be-scheduled packet;

The packet-cutting packet sub-module is configured to perform packet-cutting processing on the to-be-scheduled data packet corresponding to the current to-be-scheduled port according to the preset packet-cutting information and the packet description information of the to-be-scheduled packet, and obtain the The slice data corresponding to the current to-be-scheduled port; wherein the packet-cut information includes a maximum burst length (Burstmax), a minimum burst length (Burstmin), a parameter value of a normal type or an enhanced scheduling mode;

The Interlaken packet control submodule is further configured to update information of the polling schedule.

In an embodiment, the Interlaken packet control submodule is specifically configured as follows:

In an embodiment, the data packet packetizing submodule is specifically configured as follows:

When the parameter value of the enhanced scheduling mode in the packet cutting information is a valid value, The parameter value of Burstmax in the information is the unit length of the slice data, and the data packet to be scheduled is uniformly cut, and when the length of the remaining packet data after the uniform cutting is greater than Burstmax and less than Burstmax+Burstmin, the remaining The packet data is cut into two pieces of data; wherein the length of the first slice data corresponding to the remaining packet data is equal to Burstmax-Burstmin, and the length of the second slice data corresponding to the remaining packet data is equal to the remaining The packet data length is subtracted from the length of the first slice data.

In an embodiment, the data packet scheduling module is specifically configured as:

In an embodiment, the apparatus further includes: a data packet buffer module, a data packet information cache module, and an Interlaken scheduling information management module;

The data packet buffering module is configured to store a data packet sent by at least one port upstream;

The packet information cache module is configured to store package description information of a data packet corresponding to each upstream port;

The Interlaken scheduling information management module is configured to store preset packet cutting information and data scheduling mode information.

The embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the Interlaken packet cutting and scheduling method according to the embodiment of the invention.

The Interlaken packet-cutting and scheduling method, apparatus, and computer storage medium provided by the embodiments of the present invention use a plurality of small-small-area Interlaken interfaces to transmit data packets sent by at least one upstream port. This significantly increases the rate of data transfer; in addition, because each Interlaken interface is designed in a similar manner, the design cycle of the integrated circuit is greatly reduced.

DRAWINGS

FIG. 1 is a schematic diagram of a method for Interlaken packet cutting and scheduling according to an embodiment of the present invention;

2 is a schematic diagram of a method of packet cutting according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a method for obtaining a port identifier of a current port to be scheduled according to an embodiment of the present disclosure;

FIG. 4 is a schematic structural diagram of a polling schedule according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of another method for obtaining a port identifier of a current port to be scheduled according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a specific method for performing packet cutting processing on a data packet to be scheduled according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a packet cutting result according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of another packet cutting result according to an embodiment of the present invention; FIG.

FIG. 9 is a schematic structural diagram of an Interlaken packet cutting and scheduling apparatus according to an embodiment of the present invention;

10 is a schematic structural diagram of another Interlaken packet cutting and scheduling apparatus according to an embodiment of the present invention;

FIG. 11 is a schematic structural diagram of another Interlaken packet cutting and scheduling apparatus according to an embodiment of the present invention; schematic diagram;

FIG. 12 is a schematic diagram of a workflow of an Interlaken packet cutting and scheduling apparatus according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be clearly and completely described in the following with reference to the accompanying drawings.

Embodiment 1

As shown in FIG. 1 , the figure shows an Interlaken packet cutting and scheduling method according to an embodiment of the present invention. The method may include:

S110: Receive a data packet sent by at least one port in the upstream, and perform packet cutting processing on each data packet corresponding to each upstream port to obtain slice data corresponding to each upstream port.

S120. Obtain an interface corresponding to each upstream port from a preset Interlaken interface group, where the Interlaken interface group includes at least two Interlaken interfaces.

S130, scheduling the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports;

It should be noted that, when scheduling the slice data corresponding to the upstream port, the slice data of the upstream port may be scheduled to the appropriate Interlaken interface according to the ratio of the bandwidth of the upstream port to the bit width of the Interlaken sub-interface. Transfer to avoid congestion in the data transmission process. For example, the bandwidth of the upstream port currently being scheduled is 100 Gbps, and the bit width of an Interlaken interface in the Interlaken interface group is also 100 Gbps. Then, the slice data of the upstream port with the bandwidth of 100 Gbps can be scheduled to the bit width. Transfer over the 100Gbps Interlaken interface.

S140: Send, by using an Interlaken interface corresponding to each of the upstream ports, slice data corresponding to each of the upstream ports.

Illustratively, the receiving a data packet sent by at least one port upstream, and separately for each The data packet corresponding to the upstream port is subjected to packet-cut processing, and the slice data corresponding to each upstream port is obtained, as shown in FIG. 2, which may specifically include:

S210. Receive a data packet sent by at least one port in the upstream, and obtain packet description information of a data packet corresponding to each upstream port.

As an implementation manner, the packet description information of the data packet may include: header information, trailer information, packet length information, and the like.

S220. Obtain a port identifier of the current to-be-scheduled port according to the preset polling schedule, and obtain a to-be-scheduled data packet corresponding to the port identifier of the to-be-scheduled port according to the port identifier of the current to-be-scheduled port. Scheduling packet description information of the data packet;

S230. Perform packet cutting processing on the to-be-scheduled data packet corresponding to the current to-be-scheduled port according to the preset packet-cut information and the packet description information of the to-be-scheduled data packet, and obtain the slice data corresponding to the current to-be-scheduled port. ;

As an implementation manner, the preset packet cutting information may include: a maximum burst length (Burstmax), a minimum burst length (Burstmin), a parameter value of a normal type or an enhanced scheduling mode.

S240. Update the information of the polling schedule, and return to step S220.

As an implementation manner, in step S220, the preset polling schedule is composed of a port identifier of an upstream port and a scheduling indicator value corresponding to the port identifier, and is used to obtain a port identifier of a current port to be scheduled.

It should be noted that all port identifiers in the polling schedule correspond to all ports configured in the port table configured by the CPU.

Correspondingly, the port identifier of the current port to be scheduled is obtained according to the preset polling schedule, as shown in FIG. 3, which may specifically include:

S310. Acquire, according to a preset first polling rule, a scheduling indication sequence consisting of scheduling indication values from a preset polling scheduling table, where each row scheduling indication sequence respectively corresponds to one Row port identification sequence;

S320. Obtain, according to the preset second polling rule, the port identifier of the current to-be-scheduled port from the obtained scheduling instruction sequence of the row.

It should be noted that the preset first polling rule may be a top-down order or a bottom-up order, and the purpose is to obtain a row of scheduling indication sequence. Similarly, the preset second polling rules may be in a left-to-right order or a right-to-left order, and the purpose is to obtain a port identifier of a current port to be scheduled.

As shown in FIG. 4, the figure shows a structure of the polling schedule. As can be seen from the figure, the polling schedule is represented by the port table cfg_rd_port_j (j=1, 2, . . . , n And a scheduling indication table cfg_rd_order_j (j=1, 2, . . . , n) corresponding to the port table cfg_rd_port_j (j=1, 2, . . . , n), and cfg_rd_port_1 in the polling schedule The port identifier included in cfg_rd_port_n corresponds to all ports included in the port table configured by the CPU; cfg_rd_order_1 to cfg_rd_order_n correspond to whether the port packet corresponding to the port identifier in cfg_rd_port_1 to cfg_rd_port_n is currently scheduled. For example, the indication value in the corresponding cfg_rd_order_1 at the location of P ₁ ^{2 in} FIG. 4 is 1, indicating the port identifier in the corresponding cfg_rd_port_1 at the location.

The corresponding port packet is currently schedulable. Conversely, when the indication value in the corresponding cfg_rd_order_1 at the position of P ₁ ² is 0, the port identifier is indicated.

The corresponding port packet is currently not schedulable.

Therefore, based on the polling schedule shown in FIG. 4, the port identifier of the current port to be scheduled can be obtained by polling in two directions, as shown in FIG. 5, which may specifically include:

S510. According to a preset polling schedule, the cfg_rd_order_1 to cfg_rd_order_n are polled in order from top to bottom to obtain a row scheduling indication sequence cfg_rd_order_j; wherein j=1, 2, . . . , n;

S520. According to the obtained row scheduling indication sequence cfg_rd_order_j, the port identifier of the to-be-scheduled port is obtained by polling in a left-to-right order.

It should be noted that the direction of the polling may be arbitrary, and the purpose thereof is mainly to enable the data of all the ports to be uniformly scheduled and output. In addition, the scheduling indication value corresponding to each port in the scheduling indication table cfg_rd_order_j (j=1, 2, . . . , n) is updated in real time, for example, the current port of the corresponding port at the P ₁ ² location is not cached. Packet, at this time, the indicated value in the corresponding cfg_rd_order_1 at this location will be updated to 0.

Specifically, in step S230, the packet to be scheduled corresponding to the current to-be-scheduled port is packet-cut according to the preset packet-cut information and the packet description information of the to-be-scheduled packet, and the current packet is obtained. The slice data corresponding to the port to be scheduled, as shown in FIG. 6, may specifically include:

S610. Read parameter values of a common type and an enhanced scheduling mode in the packet cutting information.

S620, when the parameter value of the common type scheduling mode in the packet cutting information is a valid value, the parameter value of the Burstmax in the packet information is a unit length of the slice data, and the data packet to be scheduled is uniformly cut, and When the length of the packet data remaining after the uniform cutting is smaller than the parameter value of the Burstmax, the remaining packet data is taken as one slice data;

S630, when the parameter value of the enhanced scheduling mode in the packet-cutting information is a valid value, uniformly cutting the to-be-scheduled data packet by using a parameter value of Burstmax in the packet-cutting information as a unit length of the slice data, and When the length of the packet data remaining after the uniform cutting is greater than Burstmax and less than Burstmax+Burstmin, the remaining packet data is cut into two pieces of data; wherein, the remaining piece of data corresponds to the first piece of slice data. The length is equal to Burstmax-Burstmin, and the length of the second slice data corresponding to the remaining packet data is equal to the length of the remaining packet data minus the length of the first slice data.

It can be understood that the parameter value of the normal type or enhanced scheduling mode is used to indicate that the data packet to be scheduled is sliced according to the cutting method in which scheduling mode. For example, the length of the to-be-scheduled data packet that needs to be packet-cut processing is 520 bytes, Burstmax=256 bytes in the packet-cut information, and Burstmin=16 bytes, at this time, in the packet-cut information When the parameter value of the normal scheduling mode is a valid value (for example, if the parameter value is equal to 0), the packet cutting result of the data packet is as shown in FIG. 7, that is, the packet cutting result of the data packet is: the first slice data length is 256. Byte, The second slice data length is 256 bytes, and the third slice data length is 8 bytes; when the parameter value of the enhanced scheduling mode in the packet change information is a valid value (for example, the parameter value is equal to 1), The packet cutting result of the data packet is as shown in FIG. 8, that is, the packet cutting result of the data packet is: the first slice data length is 256 bytes, and the second slice data length is 240 bytes (ie, Burstmax-Burstmin). The third slice data length is 24 bytes (ie 520-256-240).

Illustratively, the slice data corresponding to each of the upstream ports is scheduled to the Interlaken interface corresponding to each of the upstream ports, and preferably, each of the upstream ports may be corresponding according to preset data scheduling mode information. The slice data is scheduled to the Interlaken interface corresponding to each of the upstream ports, where the data scheduling mode information is used to indicate whether the slice data corresponding to each upstream port is scheduled in the whole packet mode or the interleaving mode. Interlaken interface corresponding to each upstream port.

As an embodiment, when the data scheduling mode information indicates the whole packet mode, all the slice data corresponding to the entire packet data of each upstream port is spliced into one piece of data, and the spliced whole piece of data is spliced. Dispatching to the Interlaken interface corresponding to each of the upstream ports; when the data scheduling mode information indicates an interleaving mode, the slice data of each of the upstream ports is uniformly scheduled to each upstream port in an interleaved manner Corresponding Interlaken interface.

The embodiment of the present invention provides an Interlaken packet-cutting and scheduling method, which can separately receive the received data packets sent by at least one port of the upstream port to the Interlaken interface corresponding to each upstream port, and the method simultaneously utilizes multiple small bits. The wide-capacity Interlaken interface separately transmits the data packets sent by at least one upstream port, thereby significantly increasing the data transmission rate. In addition, since each Interlaken interface is designed in a similar manner, the design of the integrated circuit is greatly shortened. cycle.

Embodiment 2

Based on the foregoing technical concept, referring to FIG. 9, an Interlaken packet cutting and scheduling apparatus 10 according to an embodiment of the present invention is shown. The apparatus may include: a packet cutting module 110, a packet scheduling module 120 and an Interlaken interface module 130; wherein

The packet packet cutting module 110 is configured to receive a data packet sent by at least one port upstream, and perform packet cutting processing on each data packet corresponding to each upstream port to obtain slice data corresponding to each upstream port.

The packet scheduling module 120 is configured to obtain an interface corresponding to each upstream port from a preset Interlaken interface group.

The packet scheduling module 120 is further configured to schedule the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports;

The Interlaken interface module 130 is configured to send the slice data corresponding to each of the upstream ports.

In the above solution, the data packet cutting module 110, as shown in FIG. 10, may specifically include: a data packet processing sub-module 1101, an Interlaken packet control sub-module 1102, and a packet-cutting packet sub-module 1103;

The data packet processing sub-module 1101 is configured to receive data packets sent by at least one upstream port, and obtain packet description information of each data packet corresponding to each upstream port.

The Interlaken packet control sub-module 1102 is configured to obtain a port identifier of a port to be scheduled according to a preset polling schedule, and obtain a port identifier of the port to be scheduled according to the port identifier of the current to-be-scheduled port. Corresponding data packet to be scheduled and packet description information of the to-be-scheduled data packet;

The packet-cutting packet sub-module 1103 is configured to perform packet-cutting processing on the to-be-scheduled data packet corresponding to the current to-be-scheduled port according to the preset packet-cutting information and the packet description information of the to-be-scheduled data packet, and acquire The slice data corresponding to the current to-be-scheduled port; wherein the packet-cut information includes a maximum burst length (Burstmax), a minimum burst length (Burstmin), a parameter value of a normal type or an enhanced scheduling mode;

The Interlaken packet control sub-module 1102 is further configured to update the polling schedule information.

As an implementation manner, the Interlaken packet control submodule 1102 is specifically configured to:

As an implementation manner, the data packet cutout submodule 1103 is specifically configured to:

As an implementation manner, the data packet scheduling module 120 is specifically configured to:

In the above solution, as shown in FIG. 11, the apparatus 10 may further include: a data packet buffering module 140, a data packet information caching module 150, and an Interlaken scheduling information management module 160;

The data packet buffering module 140 is configured to store a data packet sent by at least one port upstream;

It should be noted that, in order to utilize the data packet cache most efficiently, the data packets sent by each upstream port are generally stored in the data packet buffer module in the form of a linked list by port identification.

The packet information cache module 150 is configured to store package description information of a data packet corresponding to each upstream port;

The Interlaken scheduling information management module 160 is configured to store preset packet cutting information and data scheduling mode information.

In an actual application, the packet packet cutting module 110, the packet scheduling module 120, the Interlaken interface module 130, the packet buffer module 140, the packet information buffer module 150, and the Interlaken scheduling information management module 160 may be packetized and scheduled by Interlaken. A central processing unit (CPU, Central Processing Unit), a digital signal processor (DSP), a micro control unit (MCU), a microprocessor unit (MPU, Microprocessor Unit) or programmable on the device 10 Gate array (FPGA, Field-Programmable Gate Array) and other implementations.

Embodiment 3

In order to facilitate the understanding of the foregoing solution, this embodiment describes a workflow of the foregoing device 10 in conjunction with FIG. 12, and the workflow may specifically include:

S710. The data packet processing submodule 1101 receives a data packet sent by at least one port upstream, and performs packet header processing and packet tail pairing processing and packet length calculation on the currently received data packet.

S711, the data packet processing sub-module 1101 writes the currently received data packet to the linked list according to the port identifier corresponding to the currently received data packet; wherein the linked list is stored in the data packet buffer module 140;

S712. When the tail data of the currently received data packet is written into the linked list, the data packet processing submodule 1101 writes the header, the end of the packet, and the packet length information of the currently received data packet according to the port identifier. Into the packet information cache module 150;

The S713, the Interlaken packet control sub-module 1102 obtains the port identifier of the current to-be-scheduled port according to the preset polling schedule, and obtains the current to-be-waited from the packet information cache module 150 according to the port identifier of the current to-be-scheduled port. The header, trailer, and packet length information corresponding to the port identifier of the dispatch port;

S714, the Interlaken packet control sub-module 1102 generates a set of read list port identifiers and read list enable signals aligned with the current data packet header data to be scheduled according to the obtained packet header, packet tail, and packet length information.

S715, the Interlaken packet control sub-module 1102 continuously reads the data of the current to-be-scheduled data packet from the linked list, and reads the data according to the generated read list port identifier and the read list enable signal. The data of the current to-be-scheduled data packet is sent to the packet-cutting packet sub-module 1103;

S715. When the Interlaken packet control sub-module 1102 completes the data reading of the current to-be-scheduled data packet, the Interlaken packet control sub-module 1102 obtains packet-cut information from the Interlaken scheduling information management module 160. The packet cutting information includes: Parameter values for Burstmax, Burstmin, and normal or enhanced scheduling modes;

S716, the Interlaken packet control sub-module 1102 generates an aligned packet control signal according to the obtained packet-cut information, and sends the packet-cut packet control module 1103;

S717, the packet packet-cutting sub-module 1103 performs packet-cutting processing on the current to-be-scheduled data packet according to the aligned packet-cut control signal, and acquires slice data corresponding to the current to-be-scheduled port;

It should be noted that the packet packetizing submodule 1103 is different for the packet processing method of the current to-be-scheduled data packet in the normal scheduling mode and the enhanced scheduling mode, and specifically, the packet cutting processing method has been implemented in the foregoing manner. The detailed description is given in the example, and to avoid repetition, it will not be repeated here.

S718. The data packet scheduling module 120 schedules the slice data corresponding to the current to-be-scheduled port to the Interlaken interface corresponding to the current to-be-scheduled port.

It should be noted that the data packets of the same port must be scheduled to the same Interlaken interface. In the specific implementation, the data of the current to-be-scheduled port can be scheduled to be appropriate according to the ratio of the bandwidth of the current to-be-scheduled port to the bit width of the Interlaken interface. Interlaken interface. In addition, as shown in the second embodiment, the data packet processing sub-module 1101, the Interlaken packet control sub-module 1102, and the packet-cutting packet sub-module 1103 are sub-modules of the data packet-cutting module 110.

It should be noted that the data packet scheduling module 120 may determine that the data scheduling mode information (including the parameter values of the whole packet mode and the interleaving mode) in the Interlaken scheduling information management module 160 is in the form of a whole packet mode. The slice data is scheduled to be dispatched, or the slice data is scheduled to be dispatched in the form of an interleaving pattern.

The embodiment of the invention further describes a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the Interlaken packet cutting and scheduling method described in the foregoing embodiments.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, Or a computer program product. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

The above is only the preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present invention are included in the scope of the present invention.

Industrial applicability

The technical solution of the embodiment of the present invention simultaneously utilizes multiple Interlaken interfaces with small bit width and small capacity to separately transmit data packets sent by at least one upstream port, thereby significantly increasing the rate of data transmission; The Interlaken interface is designed in a similar way, thus greatly reducing the design cycle of the integrated circuit.

Claims

An Interlaken packet cutting and scheduling method, the method comprising:

Receiving a data packet sent by at least one port of the upstream port, and performing packet cutting processing on each data packet corresponding to each upstream port to obtain slice data corresponding to each upstream port;

Acquiring an interface corresponding to each upstream port from a preset Interlaken interface group; where the Interlaken interface group includes at least two Interlaken interfaces;

Scheduling the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports;

The slice data corresponding to each of the upstream ports is sent by the Interlaken interface corresponding to each of the upstream ports.
The method of claim 1, wherein the receiving the data packet sent by the upstream port and performing the packet-cutting processing on the data packet corresponding to each upstream port to obtain the slice data corresponding to each upstream port, Specifically include:

Receiving, by the upstream, at least one port, the data packet sent by the upstream port, and acquiring the packet description information of the data packet corresponding to each upstream port, where the packet description information includes a packet header, a trailer, and a packet length information;

Obtaining a port identifier of the current to-be-scheduled port according to the preset polling schedule, and acquiring the to-be-scheduled data packet and the to-be-scheduled data corresponding to the port identifier of the to-be-scheduled port according to the port identifier of the current to-be-scheduled port Package description information of the package;

And performing packetizing processing on the to-be-scheduled data packet corresponding to the current to-be-scheduled port according to the preset packet-cutting information and the packet description information of the to-be-scheduled data packet, and acquiring the slice data corresponding to the current to-be-scheduled port; The packet cutting information includes a parameter value of a maximum burst length Burstmax, a minimum burst length Burstmin, a normal type or an enhanced scheduling mode;

Update the information of the polling schedule, and obtain the port identifier of the next port to be scheduled according to the updated polling schedule.
The method according to claim 2, wherein the preset polling schedule is composed of a port identifier of an upstream port and a scheduling indicator value corresponding to the port identifier, and is used to obtain a port identifier of a current port to be scheduled.
The method of claim 2, wherein the obtaining the port identifier of the current port to be scheduled according to the preset polling schedule includes:

Obtaining, according to a preset first polling rule, a scheduling indication sequence consisting of scheduling indication values from a preset polling scheduling table; wherein each row scheduling indication sequence respectively corresponds to a row of port identification sequences;

Obtaining the port identifier of the current to-be-scheduled port from the obtained scheduling instruction sequence of the line according to the preset second polling rule.
The method according to claim 2, wherein the packet processing of the to-be-scheduled data packet corresponding to the current to-be-scheduled port is performed according to the preset packet-cutting information and the packet description information of the to-be-scheduled data packet, Obtaining the slice data corresponding to the current to-be-scheduled port, specifically:

When the parameter value of the normal scheduling mode in the packet-cutting information is a valid value, the parameter value of Burstmax in the packet-cutting information is uniformly cut by the unit length of the slice data, and When the length of the packet data remaining after the uniform cutting is smaller than the parameter value of the Burstmax, the remaining packet data is taken as one slice data;

When the parameter value of the enhanced scheduling mode in the packet-cutting information is a valid value, the parameter value of Burstmax in the packet-cutting information is uniformly cut by the unit length of the slice data, and When the length of the packet data remaining after the uniform cutting is greater than Burstmax and less than Burstmax+Burstmin, the remaining packet data is cut into two pieces of data; wherein the length of the first slice data corresponding to the remaining packet data is equal to Burstmax-Burstmin, the length of the second slice data corresponding to the remaining packet data is equal to the remaining packet data length minus the length of the first slice data.
The method of claim 1, wherein said each upstream port corresponds to The slice data is scheduled to the Interlaken interface corresponding to each of the upstream ports, including:

Scheduling the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports according to the preset data scheduling mode information, where the data scheduling mode information is used to indicate that each of the upstream ports corresponds to The slice data is scheduled to the Interlaken interface corresponding to each of the upstream ports in a full packet mode or an interleaved mode.
The method of claim 6, wherein the scheduling of the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports according to the preset data scheduling mode information includes:

When the data scheduling mode information indicates the whole packet mode, all the slice data corresponding to the entire packet data of each upstream port is spliced into one piece of data, and the spliced whole piece of data is scheduled to each of the pieces. The Interlaken interface corresponding to the upstream port;

When the data scheduling mode information indicates the interleaving mode, the slice data of each upstream port is uniformly scheduled to the Interlaken interface corresponding to each upstream port.
An Interlaken packet cutting and scheduling device, the device comprising: a packet packet cutting module, a packet scheduling module and an Interlaken interface module; wherein

The packet-cutting module is configured to receive a data packet sent by at least one port upstream, and perform packet-cut processing on each data packet corresponding to each upstream port to obtain slice data corresponding to each upstream port;

The data packet scheduling module is configured to obtain an interface corresponding to each upstream port from a preset Interlaken interface group.

The packet scheduling module is further configured to schedule the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports;

The Interlaken interface module is configured to send the slice data corresponding to each of the upstream ports.
The apparatus according to claim 8, wherein the data packet cutting module comprises: a data packet processing submodule, an Interlaken packet control submodule, and a data packet cutout submodule; wherein

The data packet processing submodule is configured to receive a data packet sent by at least one port upstream, and obtain packet description information of each data packet corresponding to each upstream port;

The Interlaken packet control sub-module is configured to obtain, according to a preset polling schedule, a port identifier of a port to be scheduled, and obtain a port identifier of the port to be scheduled according to the port identifier of the current to-be-scheduled port. Packet to be scheduled and packet description information of the to-be-scheduled packet;

The packet-cutting packet sub-module is configured to perform packet-cutting processing on the to-be-scheduled data packet corresponding to the current to-be-scheduled port according to the preset packet-cutting information and the packet description information of the to-be-scheduled packet, and obtain the The slice data corresponding to the current to-be-scheduled port; wherein the packet-cut information includes a parameter value of a maximum burst length Burstmax, a minimum burst length Burstmin, a normal type or an enhanced scheduling mode;

The Interlaken packet control submodule is further configured to update information of the polling schedule.
The device according to claim 9, wherein the Interlaken packet control submodule is specifically configured to:

Obtaining, according to a preset first polling rule, a scheduling indication sequence consisting of scheduling indication values from a preset polling scheduling table; wherein each row scheduling indication sequence respectively corresponds to a row of port identification sequences;

Obtaining the port identifier of the current to-be-scheduled port from the obtained scheduling instruction sequence of the line according to the preset second polling rule.
The device according to claim 9, wherein the packet packet sub-module is specifically configured as:

When the parameter value of the normal scheduling mode in the packet cutting information is a valid value, the packet is cut out The parameter value of Burstmax in the information is a unit length of the slice data, and the data packet to be scheduled is uniformly cut, and when the length of the remaining packet data after the uniform cutting is smaller than the parameter value of the Burstmax, the remaining Packet data as a slice data;

When the parameter value of the enhanced scheduling mode in the packet-cutting information is a valid value, the parameter value of Burstmax in the packet-cutting information is uniformly cut by the unit length of the slice data, and When the length of the packet data remaining after the uniform cutting is greater than Burstmax and less than Burstmax+Burstmin, the remaining packet data is cut into two pieces of data; wherein the length of the first slice data corresponding to the remaining packet data is equal to Burstmax-Burstmin, the length of the second slice data corresponding to the remaining packet data is equal to the remaining packet data length minus the length of the first slice data.
The device according to claim 8, wherein the packet scheduling module is specifically configured to:

Scheduling the slice data corresponding to each of the upstream ports to the Interlaken interface corresponding to each of the upstream ports according to the preset data scheduling mode information, where the data scheduling mode information is used to indicate that each of the upstream ports corresponds to The slice data is scheduled to the Interlaken interface corresponding to each of the upstream ports in a full packet mode or an interleaved mode.
The device according to claim 12, wherein the packet scheduling module is specifically configured to:

When the data scheduling mode information indicates the whole packet mode, all the slice data corresponding to the entire packet data of each upstream port is spliced into one piece of data, and the spliced whole piece of data is scheduled to each of the pieces. The Interlaken interface corresponding to the upstream port;

When the data scheduling mode information indicates the interleaving mode, the slice data of each upstream port is uniformly scheduled to the Interlaken interface corresponding to each upstream port.
The device according to claim 8, wherein said device further comprises: data packet buffering a storage module, a packet information cache module, and an Interlaken scheduling information management module; wherein

The data packet buffering module is configured to store a data packet sent by at least one port upstream;

The packet information cache module is configured to store package description information of a data packet corresponding to each upstream port;

The Interlaken scheduling information management module is configured to store preset packet cutting information and data scheduling mode information.
A computer storage medium having stored therein computer executable instructions for performing the Interlaken packetizing and scheduling method of any one of claims 1 to 7.