CN111314404B - FlexE-based data processing method, device, equipment and storage medium - Google Patents

Abstract

The embodiment of the application discloses a data processing method, a data processing device, data processing equipment and a storage medium based on FlexE. The method comprises the following steps: the data processing device determines the time slot number of each group of service data in n clock cycles from the current clock cycle; wherein n is a positive integer greater than or equal to 1; the data processing device determines the identifier of the assigned group of service data to be scheduled in M clock cycles from the current clock cycle according to the time slot number of each group of service data; wherein M is a positive integer greater than or equal to 1; the data processing device reads the appointed group service data according to the identification of the appointed service data; and the data processing device schedules the specified service data to a Flexe calendar.

Description

A FlexE-based data processing method and device, device and storage medium

technical field

The embodiments of the present application relate to the field of data communication, and relate to, but are not limited to, a method and apparatus, device, and storage medium for data processing based on FlexE (Flex Ethernet, flexible Ethernet technology).

Background technique

With the rapid development of Internet technology, especially the arrival of the 5G era with "user experience as the center", diversified scenarios have put forward differentiated requirements for devices such as ultra-large bandwidth and flexible scheduling. How to realize the differentiation of different services on the same device and how to provide a smooth upgradeable and cost-competitive bandwidth enhancement solution has become one of the key requirements of 5G.

FlexE is an interface technology that implements service isolation and network slicing on the bearer network. It has developed rapidly in the past two years and has been widely accepted by major standards organizations. Looking back at the development of Ethernet, the first generation of Ethernet Native Ethernet (local Ethernet) was born in 1980 and is widely used in the interconnection of campuses, enterprises and data centers. The second-generation Ethernet CarrierEthernet (Carrier Ethernet) has been developed since 2000 and has been used until now. It is mainly for operator networks and is widely used in carrier-class metropolitan area networks, 3G/4G mobile bearer networks, and dedicated line access. With the advent of the 5G era, new services such as cloud services, AR/VR, and Internet of Vehicles have emerged, and Ethernet technology has been further developed into the third-generation Ethernet, which is called FlexEthernet (FlexE for short).

In order to be suitable for more application scenarios, the traditional shared cache method can no longer meet the needs of the new FlexE technology, so it is necessary to design a new FlexE-based elastic pipeline to meet the needs of the FlexE technology.

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present application provide a FlexE-based data processing method, apparatus, device, and storage medium to solve at least one problem existing in the prior art.

An embodiment of the present application provides a FlexE-based data processing method, the method comprising:

The data processing device determines the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

The data processing device determines, according to the time slot number of each group of service data, the identifier of the specified group of service data to be scheduled under M clock cycles from the current clock cycle; wherein, M is a positive integer greater than or equal to 1;

The data processing device reads the specified group of service data according to the identifier of the specified service data;

The data processing device schedules the specified business data to the FlexE calendar.

Embodiments of the present application further provide a FlexE-based data processing device, the device comprising:

a first determining unit, configured to determine the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

The second determining unit is configured to, according to the time slot number of each group of service data, determine the identifier of the specified group of service data to be scheduled in M clock cycles from the current clock cycle; wherein, M is a positive integer greater than or equal to 1;

a reading unit, configured to read the specified group of service data according to the identifier of the specified service data;

A scheduling unit, configured to schedule the specified service data to the FlexE calendar.

An embodiment of the present application further provides a FlexE-based data processing device, the device includes: a memory and a processor, where the memory stores a computer program that can be run on the processor, and the processor implements the computer program when executing the computer program The above data processing method.

Embodiments of the present application further provide a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and the computer-executable instructions are configured to execute the above data processing method.

The technical solutions of the embodiments of the present application provide an elastic pipeline based on FlexE, which can flexibly handle the scheduling of customer service data, and implement a shared cache solution suitable for FlexE. Avoid the doubled increase in the demand for cache resources due to the increase in the number of services, and make rational use of cache resources to achieve cost-competitive bandwidth improvement.

Description of drawings

FIG. 1 is a schematic diagram of the principle of encapsulation and mapping of customer service data performed by FlexE according to an embodiment of the application;

2A is a schematic structural principle diagram of a FlexE-based data processing apparatus according to an embodiment of the present application;

2B is a schematic flowchart of a FlexE-based data processing method according to an embodiment of the present application;

3A is a schematic diagram of the structural principle of an elastic conduit according to an embodiment of the application;

3B is a schematic structural principle diagram of a time slot prediction module of an elastic pipeline according to an embodiment of the present application;

FIG. 4 is a schematic diagram of the composition and structure of a FlexE-based data processing apparatus according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a hardware entity of a FlexE-based data processing device according to an embodiment of the present application.

Detailed ways

FlexE is a new client interface, which is a medium between MAC (Media Access Control, media access control) and PCS (Physical coding sublayer, physical coding sublayer), realizes business and physical interface bandwidth. decoupling. The FlexE standard originated from the interface physical layer standard. It has the characteristics of flexible and adjustable bandwidth, data isolation, and perfect fit for 5G services. It is recognized by mainstream operators and suppliers around the world.

FlexE technology adds FlexE Shim layer (FlexE mezzanine) to the middle layer between the MAC layer and PHY (Port Physical Layer, physical port layer) layer of Ethernet through lightweight enhancement of Ethernet. The Flex Shim layer is distributed based on time division multiplexing. A mechanism to schedule and distribute the data of multiple Client (customer service) interfaces to multiple different sub-channels in a time-slot manner. Taking a 100G (100Gbps) pipeline as an example, the FlexE shim can be divided into 20 sub-channels of 5G rate, and each client-side interface can be designated to use one or more sub-channels to achieve service isolation.

FlexE can realize the bundling function of large ports, effectively solving the problems faced by previous network bandwidth upgrades. For example, the 50G bandwidth of the access layer can meet the business development needs in the early stage of 5G. With the further development of 5G, the access layer needs to be upgraded to 100G. Through the FlexE binding function, only one 50G port needs to be expanded to convert the access layer to 100G. Upgrading to 100G does not require a lot of business adjustment and cutover work, and can also protect the initial investment.

FlexE slicing divides a physical Ethernet port into multiple Ethernet flexible hard pipes based on time slot scheduling, so that the network has the characteristics of exclusive time slot and good isolation similar to TDM (Time Division Multiplex). It also has the dual characteristics of Ethernet statistical multiplexing and high network efficiency. It realizes statistical multiplexing of services within the same fragment, and services between fragments do not affect each other. Compared with the fragment isolation achieved by VPN (Virtual Private Network), it is more isolated. Well, more options for 5G network sharding.

FlexE technology completes the encapsulation and mapping processing of customer business data by using FlexE Calendar (FlexE Calendar). As shown in Figure 1, each customer business FIFO (First Input First Output, first-in first-out) queue 1 to N needs to slice 66b in parallel The data block is mapped to the calendar module 11. The granularity supported by each FlexE Calendar slot (time slot) is 5Gbps, the number of supported customer services is N, the number bit width is M×66b, and M is one clock cycle. The calendar module 11 schedules number of time slots. The 66b slice data block here refers to the slice data block obtained by encoding using the 66b encoding technology, which is transmitted by 66 bits of data bits.

In the above case, in order to apply to all application scenarios, each client service (Client) needs to support the bandwidth required by the maximum client. The cache resources of the FlexE Client encapsulation and mapping processing part are calculated by multiplying the number of clients by the maximum bandwidth supported by a single client. Proportionally, for scenarios where the number of clients is large and the bandwidth support of a single client is inconsistent, it is still necessary to ensure that the maximum bandwidth required by a single client prevails. In this way, the increase in the number of Clients will lead to the double commission of the cache resources, and the cache resources become the limit of the increase in the number of Clients, and a cost-competitive bandwidth improvement solution cannot be realized. Since FlexE Calendar needs to schedule M time slots in each cycle, it can correspond to M clients at most, while the traditional shared cache method can only process one Client per cycle, and cannot meet the special requirements of FlexE. Based on the above problems, the embodiments of the present application provide a FlexE-based data processing method and device, to implement a flexible Client elastic pipe sharing method based on a time slot prediction mechanism.

Describe below in conjunction with embodiment:

This embodiment of the present application provides a FlexE-based data processing method. As shown in FIG. 2A , the Client elastic pipeline 200 in this embodiment of the present application includes a FlexE calendar module 23 and a data processing apparatus 22 in this embodiment. The Client elastic pipe 200 is located between the MAC layer 21 and the physical layer 24 , wherein the data processing device 22 is located between the MAC layer 21 and the Hitachi module 23 . The data processing device 22 is used to determine the specified group of service data in each group of service data processed by the MAC layer 21, and to schedule the specified group of service data to the calendar time slot of the calendar module 23 of FlexE, and the calendar module 23 of FlexE will then assign the service data to the time slot of the calendar module 23 of FlexE. Data is mapped to the physical layer 24 .

As shown in FIG. 2B , the method described in this embodiment includes:

Step S101, the data processing device determines the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Here, one Client corresponds to a set of service data, and the number of time slots corresponding to each set of service data in each clock cycle is fixed, that is, in each clock cycle, the data to be processed by each Client service is determined by the data of the service itself. quantity to decide. In order to predict which set of service data to schedule in the next clock cycle, the data processing device must first determine the number of time slots corresponding to each set of service data in n clock cycles from the current clock cycle. The current clock cycle here is a clock cycle in which the current data processing device is preparing to perform data scheduling, and n clock cycles from the current clock cycle refer to n clock cycles counted backward from the current clock cycle, that is, the data to be processed in the future n clock cycles. For example, when n is equal to 3, the number of time slots corresponding to each group of service data in the current clock cycle, the next clock cycle, and the next clock cycle is determined.

Step S102, the data processing device determines, according to the time slot number of each group of service data, the identification of the specified group of service data to be scheduled under M clock cycles from the current clock cycle; wherein, M is a positive integer greater than or equal to 1;

According to the determined number of time slots of each group of service data, which group of service data will be scheduled in the next several clock cycles can be predicted. For example, when n is 1, the data processing device determines the number of time slots for each group of service data in the current clock cycle. If one group of service data has the largest number of time slots in the current clock cycle, the next clock cycle can schedule this time slot first. Group business data. That is, the identification of this group of business data is determined as the identification of the specified group of business data. The identifier here refers to a sign used to identify a specified group of service data, such as a service number. For example, if there are 8 groups of service data in total, it is determined that the 3rd group is the specified group of service data, then the service number of the 3rd group of service data is the identifier of the specified group of service data.

Step S103, the data processing device reads the specified group service data according to the identifier of the specified service data;

After the data processing apparatus determines the identifier of the service data of the designated group, it can read the service data of the designated group according to the identifier of the service data of the designated group.

Step S104, the data processing apparatus schedules the specified service data to the FlexE calendar.

The data processing apparatus schedules the read service data of the specified group to the FlexE calendar in the predicted clock cycle, so that the FlexE calendar maps the service data to the calendar time slot, and then maps the service data to the physical layer through the calendar time slot.

In this way, the data processing apparatus based on the prediction mechanism can determine which group of service data needs to be scheduled to the calendar time slot of the calendar module in each clock cycle, so as to utilize resources reasonably.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S201, the data processing device determines the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S202, the data processing device determines that the identification of a group of business data that meets the preset condition is the specified designation according to the number of time slots of each group of business data described in n clock cycles from the current clock cycle, and the current effective number of registers. The identity of the group business data.

The above-mentioned step S202 provides an implementation of the step S102: a caching mechanism is provided here, each group of service data provided by the MAC layer is stored in the cache module respectively, and then the specified group of service data in the cache module is stored according to the prediction result. Scheduled into a register bank for scheduling by the FlexE calendar.

The data processing device can predict whether the number of registers can store the business data of the next several clock cycles in time according to the number of time slots of each group of business data in the n clock cycles from the current clock cycle and the current number of valid registers. To meet the scheduling requirements of the FlexE calendar, the identifier of a group of service data that cannot be stored in time is determined as the identifier of the specified group of service data, and scheduling is performed in time in the next clock cycle. Here, an effective register is a register that stores service data that can be scheduled by the FlexE calendar. Only when each register group has a sufficient number of valid registers can the scheduling of the FlexE calendar be guaranteed to flow continuously.

Step S203, the data processing device reads the specified group service data according to the identifier of the specified service data;

Step S204, the data processing apparatus schedules the specified service data to the FlexE calendar.

The data processing apparatus in this embodiment provides registers, and each group of service data in each clock cycle is first buffered into the registers, and according to the number of valid registers corresponding to each group of service data and the number of time slots to be scheduled from the register group, It can be predicted that if scheduling is not performed, which group of business data may be conditioned first, resulting in packet breakage. Thereby, it is determined which group of service data is scheduled to be prioritized, so as to ensure that the valid registers of each group of service data can be replenished in time. Here, the number of time slots to be scheduled from the register set may be the next clock cycle, or may be the number of time slots to be scheduled from the register set in the next several clock cycles.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S301, the data processing device obtains the service data of the current clock cycle from the MAC layer, and saves the data in the corresponding cache module in groups;

Step S302, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S303: The data processing apparatus determines the number of registers currently valid in the register group of each group of service data.

The foregoing steps S301 to S303 provide an implementation manner of the caching mechanism mentioned in the previous embodiment, that is, providing a register set. The data processing device stores the data obtained from the MAC layer in the corresponding cache module, and then determines which group of service data stored in the cache module is scheduled to the corresponding register group according to the prediction mechanism. In this way, when the register group is about to be emptied, the service data in it can be dispatched to the register group in time, so that the register group can be used cyclically, and the effective number of registers can be replenished in time to ensure continuous flow.

Step S304, the data processing device determines the time slot number of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S305, the data processing device determines that the identification of a group of business data that satisfies the preset condition is the specified designation according to the number of time slots of each group of business data described in n clock cycles from the current clock cycle, and the current effective number of registers. The identity of the group business data.

Step S306, the data processing device reads the specified group service data according to the identifier of the specified service data;

Step S307: The data processing apparatus schedules the specified service data to the FlexE calendar.

The above steps S304 to S307 are the same as the steps S201 to S204, and are not repeated here. In this embodiment, it is determined that the structure of the data processing device includes a cache module and a register group. The data processing device obtains each group of service data corresponding to each Client service from the MAC layer, and stores them in the corresponding cache module in turn, and determines by prediction. The specified group of service data is dispatched to the corresponding register group. Through the buffer mechanism in this embodiment, which group of service data should be scheduled can be determined according to the number of valid registers and the number of time slots of each group of service data, so that the register group can be reasonably utilized.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S401, the data processing device obtains the service data of the current clock cycle from the MAC layer, and saves the data in the corresponding cache module in groups;

Step S402, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S403: The data processing apparatus determines the number of currently valid registers in the register group of each group of service data.

Step S404, the data processing device determines the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S405, the data processing device sequentially determines whether the number of time slots of each group of service data in the current clock cycle is greater than or equal to the number of registers;

Step S406, when the data processing device determines that the number of time slots of at least one group of service data is greater than or equal to the number of registers, the identification of any group of service data whose number of time slots is greater than or equal to the number of registers is determined as the designated group. Identification of business data;

The above steps S405 and S406 provide an implementation manner of step S305. Actually, only the number of time slots of each group of service data in the current clock cycle is used here. When the number of time slots of a group of service data is greater than or equal to the number of valid registers, the packet interruption will occur in the next clock cycle. Therefore, it is necessary to schedule this group of service data in the next clock cycle to ensure this group of services. Data will not be broken.

Step S407, the data processing device reads the specified group service data according to the identifier of the specified service data;

Step S408: The data processing apparatus schedules the specified service data to the FlexE calendar.

In this embodiment, a group of service data to be scheduled is determined according to the number of time slots of each group of service data in the current clock cycle. If the number of time slots of each group of service data is less than the number of registers, any group of service data can also be scheduled, and through the cyclic scheduling of each clock cycle, it is ensured that the valid registers in the register group are replenished in time without interruption of flow. .

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S501, the data processing device obtains the service data of the current clock cycle from the MAC layer, and is grouped and stored in the corresponding cache module;

Step S502, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S503: The data processing apparatus determines the number of currently valid registers in the register group of each group of service data.

Step S504, the data processing device determines the time slot number of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S505, determine the sum of the time slots of each group of service data in the first k clock cycles from the current clock cycle, which is the first accumulated sum; wherein, the k is a positive integer greater than 1 and less than or equal to n;

Step S506, when the data processing device determines that the first accumulated sum of at least one group of business data is greater than the number of registers, the first accumulated sum is greater than or equal to the identification of any group of business data of the number of registers is determined as the specified number. The identification of the group business data;

The above steps S505 and S506 provide another implementation manner of step S305. Determine the first k clock cycles from the current clock cycle, the number of time slots of each group of service data, and perform summation to obtain the first accumulated sum respectively. When the first accumulated sum of a group of business data is greater than or equal to the number of registers, it means that if this group of business data is not scheduled within k clock cycles, the corresponding register group will be emptied and packets will be broken. , this group of business data can be scheduled preferentially. When the first accumulated sum of multiple sets of service data is greater than or equal to the number of registers, any set of service data can be scheduled preferentially, and in the next clock cycle, the first accumulated sum of the multiple sets of service data whose first accumulated sum is greater than or equal to the number of registers can be scheduled. other groups, so that these groups of business data can be scheduled as soon as possible.

Step S507, the data processing device reads the specified group service data according to the identifier of the specified service data;

Step S508: The data processing apparatus schedules the specified service data to the FlexE calendar.

In this embodiment, the number of time slots of each group of service data in the first k clock cycles and the number of currently valid registers are determined to predict a group of service data whose register group may be emptied first if no scheduling is performed, so that Schedule in a timely manner.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S601, the data processing device obtains the service data of the current clock cycle from the MAC layer, and saves it in the corresponding cache module in groups;

Step S602, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S603, the data processing device determines the currently valid number of registers in the register group of each group of service data;

Step S604: The data processing apparatus determines the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1.

Step S605, determine the sum of the time slots of each group of service data in the first k clock cycles from the current clock cycle, which is the first accumulated sum; wherein, the k is a positive integer greater than 1 and less than or equal to n;

Step S606, when the data processing device determines that the first accumulated sum of at least two groups of service data is greater than or equal to the number of registers, respectively determines the sum of the number of time slots of the n clock cycles of each group of service data, which is: the second cumulative sum;

Step S607, the data processing device determines the difference between the second accumulated sum of each group of service data minus the number of the registers to be the first difference;

Step 608: When the data processing apparatus determines that there is at least one group of service data with the smallest first difference, determine the identifier of any group of service data with the smallest first difference as the identifier of the specified group of service data.

The above steps S605 to S608 provide another implementation manner of step S506. Since in the previous embodiment, the first accumulated sum of at least two sets of service data may be greater than or equal to the number of valid registers, here, instead of randomly selecting a set of service data for scheduling, another implementation method is adopted: determine each set of service data. The cumulative sum of the total number of time slots of the service data in n clock cycles is the second cumulative sum, and the number of valid registers is further subtracted to obtain the first difference, so as to determine the minimum first difference corresponding to at least one. A set of business data. And select a group from the service data with the smallest first difference for scheduling.

Here, the group of business data with the smallest first difference corresponds to the group with the smallest number of remaining registers in the nth clock cycle, that is, the group of business data with the greatest risk of being air-conditioned after the nth clock cycle. Therefore, priority is given here. Such a set of business data is scheduled.

In fact, when there are at least two sets of service data in the first k clock cycles of the first accumulated sum greater than or equal to the number of valid registers, k can also be incremented until only the first accumulated sum of one set of service data is greater than or equal to the number of valid registers. When k is incremented until k is equal to n, and the first accumulated sum of at least two groups of service data is greater than or equal to the number of valid registers, then any group with the smallest first difference is selected for scheduling. In this way, a set of service data that is most likely to be emptied the fastest in the next clock cycle is scheduled to be scheduled in the register set, that is, the best selection possible.

Step S609, the data processing device reads the specified group service data according to the identifier of the specified service data;

Step S610: The data processing apparatus schedules the specified service data to the FlexE calendar.

In this embodiment, after confirming the relationship between the first k clock cycles and the currently valid number of registers in turn, the first accumulated sum of at least two sets of service data is still greater than the number of registers; at this time, a new judgment condition is added, that is, It is determined that a group of service data with the smallest first difference is scheduled in the next clock cycle, so as to ensure that a group of service data whose register group is most likely to be emptied the fastest is scheduled to be scheduled.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S701, the data processing device obtains the service data of the current clock cycle from the MAC layer, and saves the data in the corresponding cache module in groups;

Step S702, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S703: The data processing apparatus determines the number of currently valid registers in the register group of each group of service data.

Step S704, the data processing device determines the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S705, the data processing device respectively determines the sum of the number of time slots of n clock cycles from the current clock cycle of each group of service data, which is the third accumulated sum;

Step S706, when the data processing device determines that the third accumulated sum of each group of service data is less than the number of registers, determines the difference between the number of registers of each group of service data minus the number of time slots of the current clock cycle, as second difference;

Step S707, when the data processing device determines that the second difference of at least one group of business data is less than or equal to the number of groups of business data, then the second difference is less than or equal to the number of groups of business data for any group of business data. The identifier of the data is determined as the identifier of the specified service data;

The above steps S705 to S707 provide another implementation manner of step S305. When the third accumulated sum of each group of service data is less than the number of registers, it means that all register groups will not be emptied in the nth clock cycle if scheduling is not performed. At this time, another rule can be used to find out a group of business data to be scheduled preferentially. Subtract the number of time slots of the current clock cycle from the number of valid registers corresponding to each group of service data to obtain the second difference; when there is at least one group of the second difference less than or equal to the number of groups of service data, it is determined to schedule the A set of business data. In this way, a set of service data that schedules the register group that is most likely to be emptied the fastest in the future is selected.

Step S708, the data processing device reads the specified group service data according to the identifier of the specified service data;

Step S709: The data processing apparatus schedules the specified service data to the FlexE calendar.

In this embodiment, when the third accumulated sum of each group of service data is less than the number of registers, within n clock cycles, if no scheduling is performed, no register group will be emptied, and scheduling may not be performed. However, in order to avoid air conditioning after n clock cycles, another judgment condition is added here, that is, to find a set of business data whose second difference is less than or equal to the total number of business groups, to determine that the next clock cycle can be scheduled in A set of business data for the register group that is most likely to be emptied the fastest in the future.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S801, the data processing device obtains the service data of the current clock cycle from the MAC layer, and saves the data in the corresponding cache module in groups;

Step S802, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S803: The data processing apparatus determines the number of registers currently valid in the register group of each group of service data.

Step S804, the data processing device determines the time slot number of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S805, the data processing device respectively determines the sum of the number of time slots of n clock cycles from the current clock cycle of each group of service data, which is the third accumulated sum;

Step S806, when the data processing device determines that the third accumulated sum of each group of service data is less than the number of registers, it determines the difference between the number of registers of each group of service data minus the number of time slots of the current clock cycle, which is: second difference;

Step S807, when the data processing apparatus determines that the second difference of at least two groups of service data is less than the number of groups, determine that the second difference is less than the first k of each group of service data of the number of groups. The sum of the number of time slots in the clock cycle is the fourth cumulative sum; wherein, the k is a positive integer greater than 1 and less than n;

Step S808, determining that the second difference is less than the difference between the number of registers of each group of service data and the fourth accumulated sum less than the number of groups to be the third difference;

In step S809, the data processing apparatus determines that the third difference value of at least one group of service data is the smallest, and then the identifier of any group of service data that the third difference value is the smallest is determined as the identifier of the specified group of service data;

The above steps S807 to S808 provide an implementation manner of step S707. When the third cumulative sum of each set of service data is less than the number of registers, and when the second difference of at least two sets of service data is less than or equal to the number of sets of service data, it is determined to schedule one set of service data. The determining method is as follows: determining the fourth accumulated sum of the at least two groups of service data, and subtracting the fourth accumulated sum from the valid register numbers of the at least two groups of service data respectively to obtain a third difference. The identifier of the group of service data with the smallest third difference is determined as the identifier of the specified group of service data, that is, the group of service data with the smallest third difference is determined to be scheduled. When there are at least two groups of service data with the smallest third difference, the value of k may also be incremented, and the third difference may be recalculated until k+1 is equal to n.

Step S810, the data processing device reads the specified group of service data according to the identifier of the specified service data;

Step S811, the data processing apparatus schedules the specified service data to the FlexE calendar.

When the second difference of at least two sets of service data is smaller than the total number of sets of service data in the previous embodiment, in this embodiment, another judgment condition is added, and the set of service data with the smallest third difference is A set of business data identified as the most suitable for scheduling as soon as possible.

The embodiment of the present application provides another FlexE-based data processing method, the method includes:

Step S901, the data processing device obtains the service data of the current clock cycle from the MAC layer, and saves it in the corresponding cache module in groups;

Step S902, after the data processing device reads the specified group of service data from the cache module, schedules it to the corresponding register group;

Step S903: The data processing apparatus determines the number of currently valid registers in the register group of each group of service data.

Step S904, the data processing device determines the time slot number of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

Step S905, the data processing device respectively determines the sum of the number of time slots of n clock cycles from the current clock cycle of each group of service data, which is the third accumulated sum;

Step S906, when the data processing device determines that the third accumulated sum of each group of service data is less than the number of registers, determine the difference between the number of registers of each group of service data minus the number of time slots of the current clock cycle, to be: second difference;

Step S907, when the data processing apparatus determines that there are at least two groups of service data whose second difference is less than the number of groups, determine that the second difference is less than the first k of each group of service data of the number of groups. The sum of the number of time slots in the clock cycle is the fourth cumulative sum; wherein, the k is a positive integer greater than 1 and less than n;

Step S908, determining that the second difference is less than the difference between the number of registers of each group of service data minus the fourth accumulated sum, which is the third difference;

Step S909, when the data processing device determines that there are at least two groups of service data with the smallest third difference, determine the sum of the number of time slots of n clock cycles of each group of service data with the smallest third difference, is the fifth cumulative sum;

Step S910, determining that the difference between the number of registers of each group of service data with the smallest third difference minus the fifth accumulated sum is the fourth difference;

Step S911, the data processing device determines that the fourth difference of at least one group of service data is the smallest, then the identifier of any group of service data with the smallest fourth difference is the identifier of the specified group of service data;

The above steps S909 to S911 provide an implementation of step S809. Here, when the third difference of at least two groups of service data is the smallest, the sum of the number of time slots of n clock cycles of the at least two groups of service data can be continued to obtain the fifth accumulated sum, and the effective The fourth difference is obtained from the difference between the number of registers and the fifth accumulated sum. When it is determined that only one group of service data has the smallest fourth difference, the identifier of this group of service data is determined to be the identifier of the specified group of service data. Since the data processing device has only determined the number of time slots of each group of service data in the n clock cycles from the current clock cycle, even if the fourth difference of at least two groups of service data is the smallest, it cannot pass this time slot. The calculation method in the embodiment continues to calculate the optimal set of service data. Therefore, if there are at least two groups of service data with the smallest fourth difference, the identifier of any group of service data may be selected as the identifier of the specified group of service data, thereby scheduling any group of service data.

Of course, a rule can also be given here to select a set of business data. For example, it is determined that among the at least two groups of service data with the smallest fourth difference, the identifier of the group of service data with the smallest number is the identifier of the specified group of service data.

Step S912, the data processing device reads the specified group of service data according to the identifier of the specified service data;

Step S913: The data processing apparatus schedules the specified service data to the FlexE calendar.

When the third difference of at least two sets of service data in the previous embodiment is the smallest, in this embodiment, another judgment condition is added, and the set of service data with the smallest fourth difference is determined as the most suitable A set of business data scheduled as soon as possible.

A schematic structural diagram of the FlexE-based Client elastic pipeline 300 in the embodiment of the present application is shown in FIG. 3 , the Client in this embodiment is a client service, and each Client corresponds to a set of service data. The elastic pipeline 300 in this embodiment includes a calendar module 31. The calendar module 31 allocates each Client service to the Calendar in the form of 66b sliced data blocks according to the configured time slot, and mainly completes the mapping of the Client service to the Calendar time slot and The mapping of Calendar time slots to PHY completes the decoupling between Client services and PHY. The total bandwidth processing capability of the calendar module 31 is W, then the corresponding number of time slots S=W/5, the number of time slots scheduled in each cycle For M, corresponding to 1 to M clients, Calendar is scheduled cyclically with S/M clock cycles as a round.

The elastic pipeline 300 in the embodiment of the present application further includes a shared MAC module 32, a distribution module 33, a shared RAM module 34, a time slot prediction module 35, and the like.

The total bandwidth supported by the shared MAC module 32 is Y, the data processing bit width is M×66b, and the bandwidth processing capability of the M×66b bit width is greater than or equal to Y; the serial processing of Client services is realized by time division multiplexing, including data buffering , packet parsing, IPG (Interpacket, interframe spacing) processing, CRC (Cyclic Redundancy Check, Cyclic Redundancy Check) calculation, etc. The bandwidth-based precise scheduling of multi-Client services is realized through time slot scheduling, and M×66b data in one clock cycle comes from the same Client. The shared MAC module 32 responds to the single FlexEClient flow control and overall flow control sent by the shared RAM module 34 based on the Client.

The distribution module 33 distributes the M×66b Client slice data to X (X=Y/5/M) shared RAM modules 34 for cache processing according to the valid tag and Client ID (Client ID) sent by the shared MAC module 32 .

Shared RAM module 34, there are X modules in total, and the shared cache of M client data is realized by means of VOQ (Virtual Output Queue, virtual output queue). Each client maintains a queue depth, and the queue depth of a single client reaches the client queue flow control. When the threshold is reached, flow control is performed on the corresponding Client; when the overall buffer depth reaches the overall flow control threshold, all M clients are flow controlled. The flow control threshold of a single Client queue is determined according to the bandwidth of a single Client service, and the overall flow control threshold is determined according to the bandwidth of all services. The read operation of the shared RAM module 34 and the corresponding Client scheduling queue selection depend on the output selection of the time slot prediction module 35 .

The time slot prediction module 35 calculates the number of time slots am (m=1, 2, . For the Client situation corresponding to the M timeslots scheduled by the periodic Calendar, calculate the number of timeslots bm corresponding to the M Clients respectively (m=1, 2, ..., M); the M timeslots scheduled according to the third clock cycle Calendar correspond to In the case of clients, calculate the number of time slots cm (m=1, 2, ..., M) corresponding to M clients respectively; the number of 2 M×66b register groups reserved for each client is xm (m=1, 2 , ..., M); according to am, bm, cm and xm, predict which Client of the shared RAM module 34 should be scheduled in the next clock cycle.

Prediction based on am, bm, cm, and xm is just one implementation of RAM slot prediction scheduling, which can be extended to the next n (n>2) clock cycles.

FIG. 3B is a schematic structural diagram of the time slot prediction module 35 , including a register group control module 41 , a time slot calculation module 42 , a prediction scheduling module 43 and the like.

The register group control module 41 is composed of 2 M*66b register groups (RBG, Register Block Group), and is used to cache the scheduling output of the shared RAM module 34 temporarily; at the same time, calculate the number of currently valid 66b data blocks corresponding to each Client xm (m=1, 2, . 31 for processing; the bit width of the data interface between the register group control module 41 and the calendar module 31 is M*66b, and a bitmap can be used here to distinguish whether the data is valid.

The time slot calculation module 42, according to the time slot information sent by the calendar module 31, calculates the current time, the next clock cycle and the client situation corresponding to the M time slots scheduled by the calendar module 31 of the third clock cycle, and calculates the M clients respectively. The corresponding time slot numbers am, bm, cm (m=1, 2, . . . , M).

The prediction scheduling module 43, for any Client m, starts the prediction mechanism only when the 2×M×66b register group is valid and the queue length of the corresponding Client m in the shared Client RAM meets a certain threshold in order to prevent flow interruption. . According to the values of am, bm, cm, and xm, each clock cycle selects the scheduled Client queue in the shared Client RAM according to the priority judgment conditions 1 to 10 (1 has the highest priority and 10 has the lowest priority).

The judgment conditions for the time slot prediction in the above scheme are as follows:

Condition 1: If only Client m satisfies xm<am+bm, the Client m queue is scheduled in the next clock cycle.

Condition 2: If there are multiple Clients that satisfy xm<am+bm, and only Client m satisfies the minimum value of am+bm+cm-xm, the Client m queue is scheduled in the next clock cycle.

Condition 3: If there are multiple Clients that satisfy xm<am+bm, and there are multiple clients that satisfy the smallest value of am+bm+cm-xm, the queue with the smallest Client ID will be scheduled in the next clock cycle.

Condition 4: If only Client m satisfies xm<am+bm+cm, the queue of Client m is scheduled in the next clock cycle.

Condition 5: If there are multiple Clients satisfying xm<am+bm+cm, the queue with the smallest Client ID will be scheduled in the next clock cycle.

Condition 6: If all Clients xm>=am+bm+cm, and only one of them satisfies xm-am<=8, the queue is scheduled in the next clock cycle.

Condition 7: If all Clients xm>=am+bm+cm, and multiple Clients satisfy xm-am<=8, only 1 Client among the Clients satisfying xm-am<=8 satisfy the minimum value of xm-am-bm , the queue is scheduled in the next clock cycle.

Condition 8: If all Clients xm>=am+bm+cm, and multiple Clients satisfy xm-am<=8, and among the Clients satisfying xm-am<=8, multiple Clients satisfy the minimum value of xm-am-bm , there is only one Client that satisfies xm-am<=8 and the minimum value of xm-am-bm satisfies the minimum value of xm-am-bm-cm, and the queue is scheduled in the next clock cycle.

Condition 9: If all Clients xm>=am+bm+cm, and multiple Clients satisfy xm-am<=8, and among the Clients satisfying xm-am<=8, multiple Clients satisfy the minimum value of xm-am-bm , there are multiple Clients that satisfy xm-am<=8 and the minimum value of xm-am-bm satisfies the minimum value of xm-am-bm-cm, and the queue with the smallest Client ID is scheduled in the next clock cycle.

Condition 10: If the above conditions are not met, no scheduling will be performed.

The principle of scheduling in the above scheme is to ensure that the 2×M×66b register group can be replenished in time to ensure that no current interruption occurs. The above solution can solve the problem of multiplying the cache resources caused by the increase in the number of clients. The FlexE client resource is about 1/m of the same situation, reducing power consumption and providing a solution for the substantial increase in the number of clients supported by FlexE.

The embodiment of the present application provides a data processing method, the method includes:

Step S31, the shared MAC module sends the Client service slice data with the valid mark and the Client ID to the distribution module;

Step S32, the distribution module distributes the Client service slice data to the shared RAM module for cache processing according to the valid mark and Client ID sent by the shared MAC module;

Step S33, the shared RAM module caches the Client service slice data distributed by the distribution module, and reads the Client service slice data scheduled by the time slot prediction module according to the RAM read control message provided by the time slot prediction module and sends it to the time slot prediction module. module;

Step S34, the time slot prediction module calculates the time slot number corresponding to each Client business in the current clock cycle, the second clock cycle and the third clock cycle according to the time slot scheduling situation of the current calendar module, and calculates and determines the current clock cycle time slot. the number of available register banks in the prediction module;

Step S35, according to the number of timeslots corresponding to each Client service in the above-mentioned three clock cycles, and the number of the current register group, successively judge whether the preset conditions are met, and obtain a judgment result;

Step S36, according to the judgment result, predict which Client service slice data of the shared RAM module should be scheduled in the next clock cycle.

The following is an example to illustrate.

The embodiment of the present application provides a flexible and elastic pipeline implementation method for FlexE that supports 120 FlexE Clients, and the FlexE Calendar schedules 8 time slots per clock cycle. FlexE supports a total client service bandwidth of 600G, a total of 120 timeslots, and a maximum supported bandwidth of a single client of 5mG (m=1 to 120).

The shared MAC module 32 supports a total bandwidth of 600G and a data processing bit width of 8×66b. Serial processing of Client services is realized by time division multiplexing, including data buffering, packet parsing, IPG (frame spacing) processing and CRC. calculation etc. The bandwidth-based precise scheduling of 120 Client services is achieved through time slot scheduling, and the 8×66b data in one clock cycle comes from the same Client. The shared RAM module 34 shares the Client RAM flow control and overall flow control based on the Client response.

The distribution module 33 distributes the 8×66b Client slice data to 15 shared RAMs for cache processing according to the valid tag and Client ID sent by the shared MAC module.

The shared RAM module 34 realizes the shared cache of 8 Client data by means of VOQ. Each Client maintains a queue depth. When the queue depth of a single Client reaches the client queue flow control threshold, flow control is performed on the corresponding Client; when the overall cache depth reaches The overall flow control threshold is used to control the flow of all 8 clients. The read operation of the shared Client RAM and the corresponding Client scheduling queue selection depend on the output selection of the time slot prediction module 35 .

The time slot prediction module 35 calculates the number of time slots a1 to a8 corresponding to the 8 clients respectively according to the client situation corresponding to the 8 time slots scheduled by Calendar at the current moment; In this case, calculate the number of time slots b1 to b8 corresponding to the 8 Clients respectively; according to the Client situation corresponding to the 8 time slots scheduled by Calendar in the third clock cycle, calculate the number of time slots c1 to c8 corresponding to the 8 Clients respectively; The client reserves two 8×66b register groups for buffering the scheduling output of the shared client RAM. The current valid registers are x1 to x8.

Since 8 time slots are scheduled in one cycle, a total of 120 time slots require 15 clock cycles to schedule a round, and the corresponding time slots of 8 Clients are distributed in 15 clock cycles Sm (m=1~15) as follows, with 8 1 , 4 2s, 2 4s, and 2 3s as an example to illustrate:

According to the judgment conditions 1 to 10, the number of valid 66b register groups xn (n=1 to 8) per cycle Tm (m=1 to 15), T1 is the original state, and the available 66b register groups are 2×8 = 16, scheduled once per cycle:

T1: 16 16 16 16 16 16 16 16

If condition 10 is met, the shared Client RAM queue is not scheduled

T2: 15 15 15 15 15 15 15 15

If condition 10 is met, the shared Client RAM queue is not scheduled

T3: 14 14 14 14 14 14 14 14

If condition 10 is met, the shared Client RAM queue is not scheduled

T4: 13 13 13 13 13 13 13 13

If condition 10 is met, the shared Client RAM queue is not scheduled

T5: 12 12 12 12 12 12 12 12

If condition 10 is met, the shared Client RAM queue is not scheduled

T6: 11 11 11 11 11 11 11 11

If condition 10 is met, the shared Client RAM queue is not scheduled

T7: 10 10 10 10 10 10 10 10

If condition 10 is met, the shared Client RAM queue is not scheduled

T8: 9 9 9 9 9 9 9 9

Satisfy condition 9, schedule Client5 queue

T9: 8 8 8 8 16 8 8 8

Satisfy condition 9, schedule Client6 queue

T10: 8 8 8 8 14 14 6 6

Satisfy condition 5, schedule Client7 queue

T11: 8 8 8 8 12 12 12 4

Satisfy condition 1, schedule Client8 queue

T12: 8 8 8 8 10 10 10 10

Satisfy condition 9, schedule Client7 queue

T13: 6 8 8 8 10 10 15 7

Satisfy condition 4, schedule Client8 queue

T14: 4 8 8 8 10 10 12 12

Satisfy condition 9, schedule Client1 queue

T15: 12 8 8 8 10 10 8 8

Satisfy condition 9, schedule Client7 queue

T16: 12 8 8 8 10 10 12 4

Satisfy condition 7, schedule Client8 queue

T17: 11 7 7 7 9 9 11 11

......

Embodiments of the present application further provide a FlexE-based data processing apparatus 400, the apparatus comprising:

The first determining unit 401 is configured to determine the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein, n is a positive integer greater than or equal to 1;

The second determination unit 402 is configured to determine, according to the time slot number of each group of service data, the identifier of the specified group of service data to be scheduled in M clock cycles from the current clock cycle; wherein, M is a positive integer greater than or equal to 1;

The reading unit 403 is configured to read the specified group service data according to the identifier of the specified service data;

The scheduling unit 404 is configured to schedule the specified service data to the FlexE calendar.

In other embodiments, the second determining unit is further configured to:

The data processing device determines, according to the number of time slots of each group of business data in n clock cycles from the current clock cycle, and the number of currently valid registers, the identification of a group of business data that satisfies the preset condition is the designated group of business data. 's identification.

In other embodiments, the apparatus further includes:

an acquisition unit, configured to acquire the service data of the current clock cycle from the MAC layer, and store it in a corresponding cache module in groups;

The scheduling unit is further configured to, after reading the specified group of service data from the cache module, schedule it to the corresponding register group;

The third determining unit is configured to determine the number of currently valid registers in the register group of each group of service data.

In other embodiments, the second determining unit includes:

a first determining module, configured to sequentially determine whether the number of time slots of each group of service data in the current clock cycle is greater than or equal to the number of registers;

The second determination module is configured to, when the first determination module determines that the number of time slots of at least one group of service data is greater than or equal to the number of registers, the number of time slots is greater than or equal to the number of registers of any group of service data. The identifier is determined to be the identifier of the specified group of service data.

In other embodiments, the second determining unit includes:

The first summation module, configured to determine the sum of the number of time slots of each group of service data in the first k clock cycles from the current clock cycle, is the first accumulated sum; wherein, the k is greater than 1 and less than or equal to n. positive integer;

a third determination module, configured to, when the third determination module determines that the first accumulated sum of at least one group of service data is greater than or equal to the number of registers, determine any group of services whose first accumulated sum is greater than or equal to the number of registers The identifier of the data is determined as the identifier of the specified group of service data.

In other embodiments, the third determining module includes:

A first summation submodule, configured to respectively determine the n clock cycles of each set of service data when the third determination module determines that the first accumulated sum of at least two sets of service data is greater than or equal to the number of registers The sum of the number of time slots is the second accumulated sum;

a first difference submodule, configured to determine the difference between the second accumulated sum of each group of service data minus the number of the registers, which is the first difference;

The first determining submodule is configured to, when there is at least one group of service data with the smallest first difference, determine the identifier of any group of service data with the smallest first difference as the identifier of the specified group of service data.

In other embodiments, the second determining unit includes:

The second summation module is configured to respectively determine the sum of the number of time slots of each group of service data in n clock cycles from the current clock cycle, which is the third accumulated sum;

a first difference module, configured to determine the difference between the number of registers of each group of service data minus the number of time slots of the current clock cycle when the third accumulated sum of each group of service data is less than the number of registers, is the second difference;

The fourth determination module is configured to, when the second difference of at least one group of business data is less than or equal to the number of groups of business data, then determine any group of services whose second difference is less than or equal to the number of groups of business data The identifier of the data is determined as the identifier of the specified service data.

In other embodiments, the fourth determining module includes:

The second summation submodule is configured to, when the second difference of at least two groups of service data is smaller than the number of groups, determine the top k of each group of service data whose second difference is smaller than the number of groups The sum of the number of time slots of the clock cycles is the fourth accumulated sum; wherein, the k is a positive integer greater than 1 and less than n;

a second difference submodule, configured to determine the difference between the number of registers of each group of service data whose second difference is less than the number of groups minus the fourth accumulated sum to be the third difference;

The second determination submodule is configured to determine that there is at least one group of service data with the smallest third difference, and then determine the identifier of any group of service data with the smallest third difference as the identifier of the specified group of service data .

In other embodiments, the second determination submodule includes:

A third summation submodule, configured to determine the sum of the number of time slots in n clock cycles of each group of service data with the smallest third difference when the third difference of at least two groups of service data is the smallest , is the fifth cumulative sum;

A third difference submodule, configured to determine the difference between the number of registers of each group of service data with the smallest third difference minus the fifth accumulated sum, as the fourth difference;

The third determining submodule is configured to determine that there is at least one group of service data with the smallest fourth difference, and then use any group of service data with the smallest fourth difference as the designated group of service data.

The descriptions of the above apparatus embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

It should be noted that, in the embodiments of the present application, if the above data processing method is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products in essence or in the parts that make contributions to the prior art. The computer software products are stored in a storage medium and include several instructions for A FlexE-based data processing device (which may be a personal computer, a mobile terminal, a server, or a network device, etc.) is caused to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a removable hard disk, a read only memory (Read Only Memory, ROM), a magnetic disk or an optical disk and other mediums that can store program codes. As such, the embodiments of the present application are not limited to any specific combination of hardware and software.

Correspondingly, an embodiment of the present application provides a FlexE-based data processing device, including a memory and a processor, where the memory stores a computer program that can be run on the processor, and the processor implements the above implementation when executing the program The steps in the data processing method provided by the example.

Correspondingly, the embodiments of the present application provide a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps in the data processing methods provided by the above embodiments.

It should be pointed out here that the descriptions of the above storage medium and device embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to the method embodiments. For technical details not disclosed in the embodiments of the storage medium and device of the present application, please refer to the description of the method embodiments of the present application to understand.

It should be noted that FIG. 5 is a schematic diagram of a hardware entity of a FlexE-based data processing device in an embodiment of the application. As shown in FIG. 5 , the hardware entity of the FlexE-based data processing device 500 includes: a processor 501, a communication interface 502 and memory 503, where

The processor 501 generally controls the overall operation of the FlexE-based data processing device 500 .

The communication interface 502 enables the FlexE-based data processing device 500 to communicate with other terminals or servers through a network.

The memory 503 is configured to store instructions and applications executable by the processor 501, and can also cache data to be processed or processed by the processor 501 and each module in the FlexE-based data processing device 500 (for example, image data, audio data, Voice communication data and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM).

It is to be understood that reference throughout the specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic associated with the embodiment is included in at least one embodiment of the present application. Thus, appearances of "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation. The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms. of.

The unit described above as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit; it may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may all be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integration The unit can be implemented either in the form of hardware or in the form of hardware plus software functional units.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by program instructions related to hardware, the aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, the execution includes: The steps of the above method embodiments; and the aforementioned storage medium includes: a removable storage device, a read only memory (Read Only Memory, ROM), a magnetic disk or an optical disk and other media that can store program codes.

Alternatively, if the above-mentioned integrated units of the present application are implemented in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products in essence or in the parts that make contributions to the prior art. The computer software products are stored in a storage medium and include several instructions for A FlexE-based data processing device (which may be a personal computer, a mobile terminal, a server, or a network device, etc.) is caused to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.

The above is only the embodiment of the present application, but the protection scope of the present application is not limited to this. Covered within the scope of protection of this application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims (12)

1. A Flexe-based data processing method, characterized in that the method comprises:

the data processing device determines the time slot number of each group of service data in n clock cycles from the current clock cycle; wherein n is a positive integer greater than or equal to 1;

the data processing device determines the identifier of the assigned group of service data to be scheduled in M clock cycles from the current clock cycle according to the time slot number of each group of service data; wherein M is a positive integer greater than or equal to 1;

the data processing device reads the appointed group service data according to the identification of the appointed group service data;

and the data processing device schedules the specified group service data to a Flexe calendar.

2. The data processing method of claim 1, wherein the determining, by the data processing apparatus, the identifier of the service data of the designated group to be scheduled from a current clock cycle to a next clock cycle according to the number of time slots of each group of service data comprises:

and the data processing device determines the identifier of a group of service data meeting the preset condition as the identifier of the specified group of service data according to the time slot number of each group of service data in n clock cycles from the current clock cycle and the current effective register number.

3. The data processing method of claim 2, wherein the method further comprises:

the data processing device acquires the service data of the current clock period from the MAC layer and stores the service data in a corresponding cache module in a grouping manner;

after the data processing device reads the specified group service data from the cache module, the data processing device is dispatched to the corresponding register group;

the data processing device determines the number of currently valid registers in the register group of each set of service data.

4. The data processing method according to claim 3, wherein the data processing apparatus determines, according to the number of time slots of each group of service data in n clock cycles from the current clock cycle and the number of currently valid registers, that the identifier of a group of service data meeting a preset condition is the identifier of the specified group of service data, and includes:

the data processing device determines whether the number of time slots of each group of service data in the current clock period is greater than or equal to the number of the registers in sequence;

and when the data processing device determines that the time slot number of at least one group of service data is greater than or equal to the register number, determining the identifier of any group of service data with the time slot number greater than or equal to the register number as the identifier of the specified group of service data.

5. The data processing method according to claim 3, wherein the data processing apparatus determines, according to the number of time slots of each group of service data in n clock cycles from the current clock cycle and the number of currently valid registers, that the identifier of a group of service data meeting a preset condition is the identifier of the specified group of service data, and includes:

determining the sum of the time slot numbers of the first k clock cycles of each group of service data from the current clock cycle as a first accumulated sum; wherein k is a positive integer greater than 1 and less than or equal to n;

when the data processing device determines that at least one group of service data has the first accumulation sum which is greater than or equal to the number of the registers, determining the identifier of any group of service data of which the first accumulation sum is greater than or equal to the number of the registers as the identifier of the specified group of service data.

6. The data processing method according to claim 5, wherein when the data processing apparatus determines that there is a first accumulated sum of at least one set of service data greater than or equal to the number of registers, determining an identifier of any set of service data having the first accumulated sum greater than or equal to the number of registers as the identifier of the specified set of service data comprises:

when the data processing device determines that the first accumulated sum of at least two groups of service data is greater than or equal to the number of the registers, respectively determining the sum of the time slot numbers of the n clock cycles of each group of service data as a second accumulated sum;

when the data processing device determines that the difference between the second accumulated sum of each group of service data and the number of the registers is subtracted, the difference is a first difference value;

when the data processing device determines that a first difference value of at least one group of service data is minimum, determining the identifier of any group of service data with the minimum first difference value as the identifier of the specified group of service data.

7. The data processing method according to claim 3, wherein the data processing apparatus determines, according to the number of time slots of each group of service data in n clock cycles from the current clock cycle and the number of currently valid registers, that the identifier of a group of service data meeting a preset condition is the identifier of the specified group of service data, and includes:

the data processing device respectively determines the sum of the time slot numbers of each group of service data in n clock cycles from the current clock cycle as a third accumulated sum;

when the data processing device determines that the third accumulated sum of each group of service data is smaller than the number of the registers, determining that the difference between the number of the registers of each group of service data and the number of the time slots of the current clock cycle is a second difference value;

when the data processing device determines that the second difference of at least one group of service data is less than or equal to the group number of the service data, determining the identifier of any group of service data of which the second difference is less than or equal to the group number of the service data as the identifier of the specified group of service data.

8. The data processing method according to claim 7, wherein when the data processing apparatus determines that the second difference value of at least one group of service data is less than or equal to the number of groups of service data, determining the identifier of any group of service data with the second difference value less than or equal to the number of groups of service data as the identifier of the specified group of service data comprises:

when the data processing device determines that the second difference value of at least two groups of service data is smaller than the group number, determining that the sum of the time slot numbers of the first k clock cycles of each group of service data of which the second difference value is smaller than the group number is a fourth accumulated sum; wherein k is a positive integer greater than 1 and less than n;

determining the difference between the number of registers of each group of service data of which the second difference is smaller than the group number and the fourth accumulated sum, as a third difference;

and if the data processing device determines that the third difference value of at least one group of service data is minimum, determining the identifier of any group of service data with the minimum third difference value as the identifier of the specified group of service data.

9. The data processing method according to claim 8, wherein the data processing apparatus determines that the third difference value of at least one group of service data is minimum, and then determines an identifier of any group of service data with the minimum third difference value as the identifier of the specified group of service data, including:

when the data processing device determines that the third difference value of at least two groups of service data is minimum, determining the sum of the time slot numbers of n clock cycles of each group of service data with the minimum third difference value as a fifth accumulated sum;

determining the difference between the number of registers of each group of service data with the minimum third difference value and the fifth accumulated sum, and taking the difference as a fourth difference value;

and if the data processing device determines that the fourth difference of at least one group of service data is minimum, any group of service data with the minimum fourth difference is the designated group of service data.

10. A Flexe-based data processing apparatus, characterized in that the apparatus comprises:

the first determining unit is configured to determine the number of time slots of each group of service data in n clock cycles from the current clock cycle; wherein n is a positive integer greater than or equal to 1;

a second determining unit, configured to determine, according to the number of time slots of each group of service data, an identifier of a specified group of service data to be scheduled in M clock cycles from a current clock cycle; wherein M is a positive integer greater than or equal to 1;

the reading unit is configured to read the specified group service data according to the identifier of the specified group service data;

and the scheduling unit is configured to schedule the specified group service data to a Flexe calendar.

11. A FlexE-based data processing device, characterized in that the device comprises: memory storing a computer program operable on a processor, the processor implementing a data processing method as provided in any of the preceding claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium having computer-executable instructions stored therein, the computer-executable instructions being configured to perform the data processing method provided by any one of claims 1 to 9.

Images