WO2016202158A1

WO2016202158A1 - Message transmission method and device, and computer-readable storage medium

Info

Publication number: WO2016202158A1
Application number: PCT/CN2016/083569
Authority: WO
Inventors: 王斌
Original assignee: 深圳市中兴微电子技术有限公司
Priority date: 2015-06-15
Filing date: 2016-05-26
Publication date: 2016-12-22
Also published as: CN106330741A; CN106330741B

Abstract

Disclosed is a message transmission method, comprising: when a message is output from a message queue, acquiring a linked list corresponding to the message queue which is created when the message is input into the message queue, the linked list comprising one or more blocks, each of the blocks comprising one or more slices, and the slices being in one-to-one correspondence to the addresses of message slices in the message queue; sequentially acquiring the slices from the ith block according to the address of the ith block pointed by a linked list pointer, where i is a positive integer; and outputting the message slices from the message queue according to the addresses of the message slices corresponding to various slices, and pointing the linked list pointer to the address of the (i+1)th block. Also disclosed at the same time are a message transmission device and a computer-readable storage medium.

Description

Message transmission method, device and computer readable storage medium

Technical field

The present invention relates to a packet forwarding device management technology, and in particular, to a message transmission method and apparatus, and a computer readable storage medium.

Background technique

With the rapid development of the Internet, network bandwidth has increased rapidly, and the interface speed and number of queues of packet forwarding devices, especially high-end routers, have also increased rapidly. In order to adapt to the speed of the interface and the increase of the number of queues, the network processor chip of the general router will have a dedicated traffic management system to complete the management of the high-speed data stream, and then the message buffer is processed and output.

Most of the prior art uses a memory chip external to the chip to store data, and is managed by a linked list structure inside the chip. Each node of the linked list corresponds to the storage space of each packet slice, and the first and last nodes of the linked list are recorded in advance, except for the head and tail. The inherent read latency of the intermediate nodes and hardware outside the node, from the current linked list node as the address to read the next node, to the actual reading of the data content stored in the address, requires several clock cycles, this time the linked list is not Effective use. Therefore, in the case of employing a single linked list structure, the prior art cannot solve the problem of uniform dequeue.

Summary of the invention

In order to solve the existing technical problems, the embodiment of the present invention mainly provides a message transmission method and device, and a computer readable storage medium, which can solve the problem of uniform dequeue in the case of adopting a single linked list structure.

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 a packet transmission method, where the method includes:

When the message queue outputs a message, a linked list corresponding to the message queue established when the message is input into the message queue is obtained, and the linked list includes one or more chunks, and each chunk includes one or a plurality of slices, the slices being in one-to-one correspondence with addresses of the message slices in the message queue;

Obtaining a slice sequentially from the i-th chunk according to an address of the i-th chunk pointed by the linked list pointer, wherein the i is a positive integer;

And outputting the message slice from the message queue according to an address of a message slice corresponding to each slice, and pointing the linked list pointer to an address of the i+1th block.

With reference to the first aspect, in a first implementation manner, the obtaining, according to the address of the i-th chunk pointed by the linked list pointer, sequentially acquiring the slice from the i-th chunk includes:

Obtaining a base address, the base address being an offset address of each chunk;

And each of the i-th chunks is sequentially used according to the base address, wherein an offset address of the j-th slice in the i-th chunk is equal to a base address plus the j and a specified value Product, the j is a positive integer.

In combination with the first achievable manner, in the second achievable manner, the number of slices per block is the same in the same linked list.

In combination with the implementation of any one of the first aspect, the first type, and the second implementation manner, in the third implementation manner, before the packet queue outputting the packet, the packet is input into the packet. At the time of the queue, the method further includes:

Establishing one of the linked lists corresponding to the message queue;

The number of slices in each chunk of the linked list and the number of slices occupied in the last chunk are saved.

In conjunction with the third implementation manner, in the fourth implementation manner, the establishing, by the linked list, the linked list includes:

If the message queue does not store a message, generate one of the linked list, the linked list includes a chunk; and save the address of the first node of the first cache area allocated to the packet queue as Addressing the address of the first chunk of the linked list and the address of the last chunk; and sequentially storing the address of the packet slice stored in the packet queue with the slice of the linked list;

If the message queue stores a message, it is determined whether there is a slice in the linked list that has no corresponding information;

If there is a slice with no corresponding information in the linked list, the address of the packet slice stored in the message queue is sequentially corresponding to the slice without the corresponding information;

If there is no slice in the linked list without corresponding information, it is determined whether the linked list includes only one chunk;

If the linked list includes only one chunk, a new last chunk is generated, and the address of the head node of the second free cache allocated to the message queue is saved as the address and location of the second chunk. Addressing the address of the new last chunk; the address of the packet slice stored in the packet queue is sequentially corresponding to the slice of the linked list;

If the linked list includes multiple chunks, generate a new last chunk, and save the first node address of the third free cache allocated to the message queue as the address of the new last chunk; The addresses of the message slices stored in the message queue are sequentially corresponding to the slices of the linked list.

With reference to the first aspect, in a fifth implementation manner, when a plurality of message queues output a message, the method further includes:

Obtaining a linked list that is in one-to-one correspondence with the plurality of message queues;

And outputting the packets from the plurality of message queues in sequence according to the output order of the plurality of message queues.

A second aspect of the present invention provides a message transmission apparatus, where the apparatus includes:

Obtaining a linked list unit, configured to output a message in the message queue, obtain a linked list corresponding to the message queue established when the message is input into the message queue, and the linked list includes one or more chunks, each The chunk includes one or more slices, and the slice has a one-to-one correspondence with an address of a message slice in the message queue;

Obtaining an address unit, configured to sequentially acquire a slice from the i-th chunk according to an address of the i-th chunk pointed to by the linked list pointer, where i is a positive integer;

Obtaining a message unit, configured to output the message slice from the message queue according to an address of a message slice corresponding to each slice, and point the linked list pointer to an address of the i+1th block.

With reference to the second aspect, in a first implementation manner, the acquiring a slice unit is configured to:

Determining, according to the base address, each slice in the i-th chunk, wherein an offset address of the j-th slice in the i-th chunk is equal to a base address plus the j and a specified value Product, the j is a positive integer.

In combination with any of the second aspect, the first and the second implementable manner, the apparatus further includes:

Establishing a unit, configured to establish one of the linked lists corresponding to the message queue;

And a saving unit configured to save the number of slices in each chunk of the linked list and the number of slices occupied in the last chunk.

In combination with the third achievable manner, in a fourth implementable manner, the establishing unit is configured to:

If the message queue does not store a message, generate a linked list, the linked list includes a chunk; and save an address of a first node of the first cache area allocated to the packet queue as the linked list The address of the first chunk and the address of the last chunk; the address of the packet slice stored in the message queue is sequentially corresponding to the slice of the linked list;

If there is a slice in the linked list without corresponding information, the report to the message queue is stored The address of the slice corresponds to the slice without the corresponding information;

With reference to the second aspect, in the fifth implementation manner, when multiple message queues output a message,

The acquiring a linked list unit is configured to obtain a linked list that is in one-to-one correspondence with the plurality of message queues;

The acquiring the message unit is configured to output the message from the plurality of message queues in sequence according to the output order of the plurality of message queues.

The embodiment of the present invention further provides a computer readable storage medium, the storage medium comprising a set of instructions, when executed, causing at least one processor to perform operations including:

The message transmission method and device, and the computer readable storage medium provided by the embodiment of the present invention, when the message queue outputs a message, first acquires the report established when the message is input into the message queue. a linked list corresponding to the text queue, the linked list includes one or more chunks, each chunk includes one or more slices, and the slice corresponds to the address of the packet slice in the message queue; The address of the i-th chunk pointed to by the pointer, and the respective slices of the chunk are sequentially obtained from the i-th chunk; and the packet slice is output from the packet queue according to the address of the packet slice corresponding to each slice. And point the linked list pointer to the address of the i+1th chunk. In this way, after the use of the slice in the current chunk is completed, the linked list pointer has already pointed to the address of the next chunk, and the slice in the next chunk can be used immediately without wasting several clock cycles to wait for the pointer to point to the next group. The address of the block; therefore, the time wasted by the output of the message queue is reduced, and the continuity of the slice in each block is ensured, thereby solving the problem of the uniform output queue.

DRAWINGS

FIG. 1 is a flowchart of a method for transmitting a message according to an embodiment of the present invention;

2 is a schematic diagram of a linked list according to an embodiment of the present invention;

FIG. 3 is a flowchart of another method for transmitting a message according to an embodiment of the present invention;

FIG. 4 is a flowchart of still another method for transmitting a message according to an embodiment of the present invention;

FIG. 5 is a flowchart of still another method for transmitting a message according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a process execution process according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a message transmission apparatus according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of still another message transmission apparatus according to an embodiment of the present invention.

detailed description

Embodiment 1

The embodiment of the invention provides a packet transmission method. As shown in FIG. 1 , the method may include:

Step 101: When the message queue outputs a message, obtain a linked list corresponding to the message queue established when the message is input into the message queue, where the linked list includes one or more chunks, and each chunk includes one or A plurality of slices corresponding to the address of the message slice in the message queue.

Here, the linked list stores the order and location of the messages of the input message queue, and each block corresponds to a segment of the message. For example, the message is input into the message queue, and the message queue has a linked list corresponding to the linked list. As shown in FIG. 2, it is assumed that the message is divided into 16 message slices, and the linked list includes three chunks, each chunk consisting of six slices, wherein the slice of the slash represents a slice of the message. Corresponding to the address, the unslashed slice indicates that there is no address corresponding to the packet slice. The six slices of the block 1 correspond to the addresses of the first six message slices in turn, the slices of the block 2 correspond to the addresses of the seventh to twelfth message slices, and the slices of the block 3 correspond to the thirteenth to the The address of 16 message slices. Here, the chunks described in this embodiment are the same as the nodes of the linked list in the prior art.

Step 102: Acquire each slice of the chunk from the i-th chunk according to the address of the i-th chunk pointed to by the linked list pointer.

Here, i is a positive integer.

Specifically, the base address is obtained, where the base address is an offset address of each chunk; each slice in the i-th chunk is sequentially used according to the base address, wherein the j-th slice in the i-th chunk The offset address is equal to the base address plus the product of j and the specified value, which is a positive integer. Here, the linked list can include three pointers, a head pointer, a tail pointer, and a linked list pointer. The first pointer points to the address of the first chunk, the tail pointer points to the address of the last chunk, and the linked list pointer points to the next chunk used.

Preferably, in the same linked list, the number of slices per block is the same. Preferably, the specified value of the embodiment of the present invention is 1, and the base address is 0. For example, the offset address of the sixth slice of chunk 2 in FIG. 2 is 0+6*1, which is 6.

Step 103: Output a message slice in the message queue according to the address of the packet slice corresponding to each slice, and point the linked list pointer to the address of the i+1th block.

As shown in FIG. 2, the head pointer in the linked list points to the address of chunk 1, and the tail pointer points to the address of chunk 3. When the packet slice corresponding to chunk 1 is being output, the linked list pointer points to chunk 2; when the packet slice corresponding to chunk 2 is being output, the linked list pointer points to chunk 3.

Compared with the prior art, the embodiment of the present invention can obtain the slice of the current chunk, and the linked list pointer points to the address of the next chunk. Therefore, after the slice is used in the current chunk, the linked list pointer has already pointed to the next group. The address of the block, the slice in the next block can be used immediately, without wasting a few clock cycles to wait for the pointer to point to the address of the next block, thus reducing the wasted time of the message queue output, ensuring the use The continuity of the slices in each chunk solves the problem of uniform output queues.

Further, as shown in FIG. 3, the method further includes:

Step 100a: Establish a linked list corresponding to the message queue.

Specifically, if the packet queue does not store the packet, a linked list is created, and the linked list includes a chunk, and the address of the first node of the first cache area allocated to the packet queue is saved as the address of the first chunk of the linked list. And the address of the last chunk, the address of the packet slice stored in the packet queue is corresponding to the slice of the linked list; if the packet queue stores the packet, it is determined whether there is no corresponding information in the linked list. If there is a slice with no corresponding information in the linked list, the address of the packet slice stored in the message queue corresponds to the slice without the corresponding information; if there is no slice without the corresponding information in the linked list, it is determined whether the linked list is Include only one chunk; if the linked list includes only one chunk, generate a new last chunk, and save the first node address of the second free cache allocated to the message queue as the second The address of the chunk and the address of the new last chunk, and the address of the packet slice stored in the packet queue is sequentially corresponding to the slice of the linked list; if the linked list includes multiple chunks, Generating a new last chunk, storing the first node address of the third free buffer allocated to the message queue as the address of the new last chunk, and storing the packet to the packet queue The addresses of the slices correspond in turn to the slices of the linked list. Here, the first cache area, the second cache area, and the third cache area are not particularly different, except that the three cache areas are not necessarily the same cache area.

Step 100b: Save the number of slices in each chunk of the linked list and the number of slices that have been occupied in the last chunk.

Correspondingly, when the message output queue, the address of the first chunk of the linked list, the address of the second chunk, the address of the last chunk, the number of slices in each chunk, and the last chunk are obtained. The number of occupied slices and the queue tag. At the beginning of the queue output, the head pointer of the linked list points to the address of the first chunk, the tail pointer points to the address of the last chunk, and the linked list pointer points to the second chunk, for the first The first slice of the chunk acquires the base address, calculates the offset address of the first slice, obtains the first slice of the first chunk, and determines the address of the corresponding packet slice according to the first slice. Enter the packet slice, and so on until the last slice of the first chunk is obtained. At the same time, the linked list pointer points to the address of the next chunk of the used chunk, and repeats the process of inputting the input packet. Until the chunk corresponding to the message slice in the last chunk is obtained, and the corresponding message is stopped.

Further, when a plurality of message queues output a message, the method further includes: obtaining a linked list that is in one-to-one correspondence with the plurality of message queues; and sequentially selecting the plurality of message queues according to the output order of the plurality of message queues Output message. In this way, the method provided by the embodiment of the present invention can obtain the linked list of each packet queue at the same time, and then output the packets in sequence according to the sequence of the message queue. Therefore, after the packet queue is outputted, the next report does not need to be acquired. In the linked list of the text queue, the next message queue can directly output the message slice, thereby saving the time for obtaining the linked list and ensuring the continuity of the output of the plurality of message queues, thereby achieving the requirement of uniform output.

Embodiment 2

The embodiment of the invention provides a message transmission method, which is applied to a message input message queue. The offset address of the i-th slice of the chunk of the embodiment of the present invention is equal to the base address 0 plus the sequence number of the slice multiplied by the specified value 1, and count-i is used to record the chunk when the packet is input into the message queue. The number of slices that have been occupied, that is, the number of the current slice. As shown in FIG. 4, the method may include:

Step 201: Obtain a queue identifier.

Here, the queue tag indicates whether a message queue corresponding to the linked list stores a message. Here, this In the embodiment of the present invention, the queue identifier is an empty flag. When the null flag is 1, it indicates that no packet is stored in the packet queue or the packet has been output. If the null flag is 0, the packet is stored in the queue message.

Step 202: Determine whether the empty flag is 1, if yes, execute step 203; if no, execute step 204.

Step 203: If the null flag is 1, generate a linked list, where the linked list includes a chunk, and save the address of the first node of the first cache area allocated to the message queue as the address and the last of the first chunk of the linked list. The address of the chunk, set count-i to 0, and set the queue empty flag to non-empty.

Here, the linked list may include a plurality of chunks, each of which includes the same number of blocks, and each node of the linked list corresponds to a storage space of the slice of the stored message. The address of the first chunk of the linked list corresponds to the address of the first node of the message queue, and the address of the last chunk of the linked list corresponds to the address of the last node of the message queue.

Step 204: If the null flag is 0, it is determined whether count-i is equal to 0. If yes, step 205 is performed; if not, step 208 is performed.

When count-i is equal to 0, it indicates that there is no slice with no corresponding information in the linked list. When count-i is not equal to 0, it means that the slice in one or several chunks in the linked list has no corresponding information.

Step 205: If count-i is equal to 0, it is determined whether the address of the first chunk of the linked list is equal to the address of the last chunk, and if yes, step 206 is performed; if not, step 207 is performed.

Here, when the address of the first chunk of the linked list is equal to the address of the last chunk, it indicates that the linked list includes only one chunk. When the address of the first chunk of the linked list is not equal to the address of the last chunk, the linked list includes At least two chunks.

Step 206: If the address of the first chunk of the linked list is equal to the address of the last chunk, generate a new last chunk, and save the first node address of the second free cache allocated to the packet queue as the second Step 208 is performed by the address of the chunk and the address of the new last chunk.

Step 207: If the address of the first chunk of the linked list is not equal to the address of the last chunk, generate one The new last chunk saves the first node address of the third free cache assigned to the message queue as the address of the new last chunk.

Step 208: Count-i is the offset address of each chunk, and sequentially compares the slice of the current chunk with the address of the packet slice of the input message queue.

Step 209: Determine whether there is a next message slice input message queue, if yes, execute step 204; if not, execute step 210.

Step 210: If no message slice is input into the message queue, the queue tag and the count-i of the last chunk are saved.

Here, no message slice input message queue indicates that the message input is completed.

It is worth noting that each time count-i is equal to the number of slices per block, and the slice needs to continue to be used, indicating that the slice of the current block is already occupied, and the slice of the next slice needs to be occupied. Count-i will be set to 0 and counted from the beginning.

Embodiment 3

The embodiment of the present invention provides a message transmission method, which is used to implement a message queue output message of a plurality of stored messages after the message is input into the message queue of the second embodiment, and is assumed to be in the embodiment of the present invention. After receiving three message queues (message queue 1, message queue 2, and message queue 3) to request output of the message, as shown in FIG. 5, the method includes:

Step 301: The message transmission device allocates a process for each of the three message queues, and the process is used to execute the message queue output message.

Step 302: The three processes enter the preparation phase, and the packet transmission device acquires the linked list corresponding to the queue 1 of the message, the queue-mark and the count-i of the last chunk, the address of the first chunk, the address of the second chunk, and The address of the last chunk is obtained, and the packet slice corresponding to the slice in the linked list is obtained.

Here, the linked list corresponding to the respective message queue, the queue-mark and the count-i of the last chunk, the address of the first chunk, the address of the second chunk, and the address of the last chunk are all in the message input report. The text queue is stored well.

Step 303: The process of the message queue 1 enters the execution phase, and the processes of the message queue 2 and the message queue 3 enter a waiting phase, and the message transmission device obtains the linked list, the queue mark, and the last block corresponding to the queue 1 of the message. Count-i, the address of the first chunk, the address of the second chunk, and the address of the last chunk, and obtain the packet slice corresponding to the slice in the linked list.

Specifically, the linked list pointer points to the address of the first chunk, and sequentially uses all the slices of the first chunk of the linked list in the process, and the linked list pointer points to the address of the second chunk; the second group is used in sequence. All slices of the block, at the same time, the linked list pointer points to the address of the third chunk; all slices of the third chunk are used, and so on, until the slice of the last chunk.

Here, the use of the slice of any one of the chunks may specifically include: assuming that count-i is used to record the number of slices corresponding to the packet slice in the chunk when the packet is input into the packet queue, for the purpose of understanding, the corresponding setting count -o,count-o is used to record the number of used slices in the chunk when the message is output. After the linked list pointer points to the address of the chunk, the offset address of the next slice is calculated according to the base address and the count-o, the specified value, and the offset address is equal to count-o multiplied by 1, according to the offset address, The next slice is obtained, so that the address of the packet slice corresponding to the slice is obtained, and the message slice is output. For the last chunk, when the count-o of the last chunk is equal to the count-i of the last chunk saved in advance, the packet slice taken in the message queue is the last packet slice, and the packet queue output is After the message is completed, here, count-o refers to the number of slices corresponding to the packet slice in the block when the message is output, that is, the number of the slice currently being used.

It should be noted that the algorithm for the offset address provided by the embodiment of the present invention is not limited thereto, and the offset address of each slice may also be the offset address of the previous slice plus a specified value. Here, in this embodiment, determining that the message queue output is completed may further include: the queue identifier is empty; or the count-o of each chunk in the linked list is 0.

Step 304: The process of the message queue 2 enters the execution phase, and the message queue 3 enters the waiting phase. The message transmission device obtains the linked list corresponding to the queue 2 of the message queue, the queue mark, and the count-i and the first group of the last block. The address of the block, the address of the second chunk, and the address of the last chunk, get the linked list The slice corresponding to the middle slice.

Step 305: The process of the message queue 3 enters an execution phase, and the message transmission device obtains the link table corresponding to the message queue 3, the queue mark, the count-i of the last chunk, the address of the first chunk, and the second group. The address of the block and the address of the last chunk are obtained, and the packet slice corresponding to the slice in the linked list is obtained.

The specific execution sequence of the process provided by the embodiment of the present invention is shown in FIG. 6. It should be noted that the methods used in the output of the message are the same in steps 303 to 305. Therefore, the embodiment is only described in detail in step 303, and is not repeated in

steps

304 and 305. In general, the message is output. After the queue is completed, the corresponding process is released, but when the following situations occur, the corresponding process will be queued behind all previous queues, waiting for the next call: the queue is not empty, that is, the queue depth is not 0; or the queue The port is not in the flow control state; or the process is not full.

Embodiment 4

The embodiment of the present invention provides a message transmission device 40. As shown in FIG. 7, the device 40 may include:

The obtaining linked list unit 401 is configured to: when the message queue outputs the message, obtain a linked list corresponding to the message queue established when the message is input into the message queue, where the linked list includes one or more chunks. Each chunk includes one or more slices that correspond one-to-one with the address of the message slice in the message queue.

The obtaining address unit 402 is configured to sequentially acquire a slice from the i-th chunk according to an address of the i-th chunk pointed to by the linked list pointer, where i is a positive integer.

The obtaining message unit 403 is configured to output the message slice from the message queue according to the address of the message slice corresponding to each slice, and point the linked list pointer to the address of the i+1th block.

Compared with the prior art, the embodiment of the present invention can obtain the slice of the current chunk, and the linked list pointer points to the address of the next chunk. Therefore, after the slice is used in the current chunk, the linked list pointer has already pointed to the next group. The address of the block, the slice in the next block can be used immediately, without wasting several clock cycles waiting for the pointer to point to the address of the next block, thus, The time wasted by the message queue output is reduced, and the continuity of the slices in each block is ensured, thereby solving the problem of uniform output queue.

Further, the acquiring slice unit 403 is specifically configured to:

Preferably, in the same linked list, the number of slices per block is the same.

Further, as shown in FIG. 8, the device 40 further includes:

The establishing unit 404 is configured to establish one of the linked lists corresponding to the message queue.

a saving unit 405, configured to save the number of slices in each chunk of the linked list, the number of occupied slices in the last chunk, and the queue tag, where the queue tag indicates the message queue Whether to store the message.

Further, the establishing unit 404 is specifically configured to:

If the linked list includes only one chunk, a new last chunk is generated and will be assigned to the The first node address of the second free buffer of the message queue is saved as the address of the second chunk and the address of the new last chunk; the address of the packet slice to be stored in the message queue Corresponding to the slice of the linked list in turn;

Further, when multiple message queues output messages,

The obtaining linked list unit 401 is further configured to acquire a linked list that is in one-to-one correspondence with the plurality of message queues;

The acquiring message unit 403 is further configured to sequentially output the message from the plurality of message queues according to the output order of the plurality of message queues.

In an actual application, the acquiring linked list unit 401, the obtaining address unit 402, the obtaining message unit 403, the establishing unit 404, and the saving unit 405 may each be a central processing unit (CPU) and a microprocessor located in the terminal. (Micro Processor Unit, MPU), Digital Signal Processor (DSP), or Field Programmable Gate Array (FPGA).

Based on the scenario provided by the foregoing multiple embodiments, the embodiment of the present invention can further provide a computer readable storage medium, where the storage medium includes a set of instructions, when executed, causing at least one processor to execute the following operating:

Outputting the message from the message queue according to an address of a packet slice corresponding to each slice Slice and point the linked list pointer to the address of the i+1th chunk.

The above is only the preferred embodiment of the present invention and is not intended to limit the scope of the present invention.

Claims

A message transmission method, the method comprising:

When the message queue outputs a message, a linked list corresponding to the message queue established when the message is input into the message queue is obtained, and the linked list includes one or more chunks, and each chunk includes one or a plurality of slices, the slices being in one-to-one correspondence with addresses of the message slices in the message queue;

Obtaining a slice sequentially from the i-th chunk according to an address of the i-th chunk pointed by the linked list pointer, wherein the i is a positive integer;

And outputting the message slice from the message queue according to an address of a message slice corresponding to each slice, and pointing the linked list pointer to an address of the i+1th block.
The method according to claim 1, wherein the sequentially acquiring the slices from the i-th chunk according to the address of the i-th chunk pointed to by the linked list pointer comprises:

Obtaining a base address, the base address being an offset address of each chunk;

And each of the i-th chunks is sequentially used according to the base address, wherein an offset address of the j-th slice in the i-th chunk is equal to a base address plus the j and a specified value Product, the j is a positive integer.
The method of claim 2, wherein the number of slices per block is the same in the same linked list.
The method according to any one of claims 1 to 3, wherein, when the message is input into the message queue before the message queue outputs the message, the method further includes:

Establishing one of the linked lists corresponding to the message queue;

The number of slices in each chunk of the linked list and the number of slices occupied in the last chunk are saved.
The method according to claim 4, wherein said establishing said one linked list corresponding to said message queue comprises:

If the message queue does not store a message, generate a linked list, the linked list includes a chunk; and save an address of a first node of the first cache area allocated to the packet queue as the linked list The address of the first chunk and the address of the last chunk; the address of the packet slice stored in the message queue is sequentially corresponding to the slice of the linked list;

If the message queue stores a message, it is determined whether there is a slice in the linked list that has no corresponding information;

If there is a slice with no corresponding information in the linked list, the address of the packet slice stored in the message queue is sequentially corresponding to the slice without the corresponding information;

If there is no slice in the linked list without corresponding information, it is determined whether the linked list includes only one chunk;

If the linked list includes only one chunk, a new last chunk is generated, and the address of the head node of the second free cache allocated to the message queue is saved as the address and location of the second chunk. Addressing the address of the new last chunk; the address of the packet slice stored in the packet queue is sequentially corresponding to the slice of the linked list;

If the linked list includes multiple chunks, generate a new last chunk, and save the first node address of the third free cache allocated to the message queue as the address of the new last chunk; The addresses of the message slices stored in the message queue are sequentially corresponding to the slices of the linked list.
The method of claim 1, wherein when the plurality of message queues output the message, the method further comprises:

Obtaining a linked list that is in one-to-one correspondence with the plurality of message queues;

And outputting the packets from the plurality of message queues in sequence according to the output order of the plurality of message queues.
A message transmission device, the device comprising:

Acquiring a linked list unit, configured to output a message in the message queue, obtain a linked list corresponding to the message queue established when the message is input into the message queue, and the linked list includes one or more Blocks, each chunk comprising one or more slices, the slices being in one-to-one correspondence with addresses of message slices in the message queue;

Obtaining an address unit, configured to sequentially acquire a slice from the i-th chunk according to an address of the i-th chunk pointed to by the linked list pointer, where i is a positive integer;

Obtaining a message unit, configured to output the message slice from the message queue according to an address of a message slice corresponding to each slice, and point the linked list pointer to an address of the i+1th block.
The apparatus according to claim 7, wherein the acquisition slice unit is configured to:

Obtaining a base address, the base address being an offset address of each chunk;

Determining, according to the base address, each slice in the i-th chunk, wherein an offset address of the j-th slice in the i-th chunk is equal to a base address plus the j and a specified value Product, the j is a positive integer.
The apparatus according to claim 8, wherein the number of slices per block is the same in the same linked list.
The device according to any one of claims 7 to 9, wherein the device further comprises:

Establishing a unit, configured to establish one of the linked lists corresponding to the message queue;

And a saving unit configured to save the number of slices in each chunk of the linked list and the number of slices occupied in the last chunk.
The apparatus according to claim 10, wherein said establishing unit is configured to

If the message queue does not store a message, generate a linked list, the linked list includes a chunk; and save an address of a first node of the first cache area allocated to the packet queue as the linked list The address of the first chunk and the address of the last chunk; the address of the packet slice stored in the message queue is sequentially corresponding to the slice of the linked list;

If the message queue stores a message, it is determined whether there is a slice in the linked list that has no corresponding information;

If there is a slice in the linked list without corresponding information, the report to the message queue is stored The address of the slice corresponds to the slice without the corresponding information;

If there is no slice in the linked list without corresponding information, it is determined whether the linked list includes only one chunk;

If the linked list includes only one chunk, a new last chunk is generated, and the address of the head node of the second free cache allocated to the message queue is saved as the address and location of the second chunk. Addressing the address of the new last chunk; the address of the packet slice stored in the packet queue is sequentially corresponding to the slice of the linked list;

If the linked list includes multiple chunks, generate a new last chunk, and save the first node address of the third free cache allocated to the message queue as the address of the new last chunk; The addresses of the message slices stored in the message queue are sequentially corresponding to the slices of the linked list.
The device according to claim 7, wherein, when a plurality of message queues output a message, the acquiring linked list unit is configured to acquire a linked list that is in one-to-one correspondence with the plurality of message queues;

The acquiring the message unit is configured to output the message from the plurality of message queues in sequence according to the output order of the plurality of message queues.
A computer readable storage medium comprising a set of instructions that, when executed, cause at least one processor to perform operations comprising:

When the message queue outputs a message, a linked list corresponding to the message queue established when the message is input into the message queue is obtained, and the linked list includes one or more chunks, and each chunk includes one or a plurality of slices, the slices being in one-to-one correspondence with addresses of the message slices in the message queue;

Obtaining a slice sequentially from the i-th chunk according to an address of the i-th chunk pointed by the linked list pointer, wherein the i is a positive integer;

And outputting the message slice from the message queue according to an address of a message slice corresponding to each slice, and pointing the linked list pointer to an address of the i+1th block.