CN102209042B - Method and device for preventing first input first output (FIFO) queue from overflowing - Google Patents
Method and device for preventing first input first output (FIFO) queue from overflowing Download PDFInfo
- Publication number
- CN102209042B CN102209042B CN201110205098.0A CN201110205098A CN102209042B CN 102209042 B CN102209042 B CN 102209042B CN 201110205098 A CN201110205098 A CN 201110205098A CN 102209042 B CN102209042 B CN 102209042B
- Authority
- CN
- China
- Prior art keywords
- ring
- data
- write
- idle
- fifo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 13
- 239000003550 marker Substances 0.000 claims description 18
- 230000003139 buffering effect Effects 0.000 claims description 16
- 238000000151 deposition Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Landscapes
- Information Transfer Systems (AREA)
- Communication Control (AREA)
- Multi Processors (AREA)
Abstract
The invention provides a method for preventing a first input first output (FIFO) queue from overflowing. The method comprises the following steps of: A, establishing a first BD (buffer descriptor) ring and a second BD ring in a device memory; B, writing data in the FIFO in an idle BD in a first BD ring through a first write pointer by a hardware transceiver, and producing a receiving interruption by the hardware transceiver after the write-in; C, reading the data from the first BD ring by using a first read pointer after driving software detects the receiving interruption; writing the read data in the second BD ring by using a second write pointer by a driving software; reading the data from the second BD ring by using a second read pointer and processing the data by the driving software. By the scheme of the invention, the FIFO can be prevented from overflowing on the premise that the hardware transceiver is not modified; correspondingly, the driving receiving stability and reliability can be improved.
Description
Technical field
The present invention relates to data communication technology field, relate in particular to the reception mechanism of device driver software, particularly a kind of method and apparatus of avoiding First Input First Output to overflow.
Background technology
In the network equipment, device driver software receives data and generally adopts buffer descriptor (BD) ring mechanism at present, and BD ring is a data buffering between drive software and hardware transceiver.As shown in Figure 1, in device memory 103, distribute BD 104, each BD 104 is become with buffering pointer set by Status Flag, and Status Flag is indicated this BD to be idle or to have data pending, region of memory of buffering pointed, for depositing pending data.The end to end composition of a plurality of BD 104 BD ring.BD ring is a data buffering between drive software 101 and hardware transceiver 102.
In the time of device initialize, by drive software 101, BD ring is constructed, the information announcement of then BD being encircled is to hardware transceiver 102.Hardware transceiver 102 is received after data, first in First Input First Output (FIFO) 105, keep in the data that receive, in FIFO 105, temporary data reach after certain water level, again temporary data are transferred to the idle BD receiving BD ring from FIFO 105 upper, finally in the mode of interrupting, notify drive software 101 to process the data of receiving.
Although the FIFO 105 of BD ring and hardware transceiver 102 is the same has been all cushioning effect, BD encircles can deposit more data, can tolerate larger network burst flow.Because the time of drive software 101 deal with data is long and unfixing, so conventionally up a reception task can be waken in break in service process, delay processing.The lasting speed lower than hardware transceiver 102 data writings of speed when the task of reception deal with data, BD ring can be taken by data, hardware transceiver 102 cannot move away the data in FIFO 105, as long as now also have data to enter, FIFO 105 will overflow.
Visible, adopt above-mentioned mechanism to receive data, it is situation about easily occurring that FIFO overflows.Particularly for integrated system, to control drive software and forward all operations in a CPU (CPU) of drive software, the time that driving reception task is scheduled can not be guaranteed, and it is more general that FIFO overflows situation.
As shown in Figure 1, when FIFO 105 overflows, hardware transceiver 102 tends to stop receiving data, and produces an interrupt notification drive software 101.The way of drive software 101 is to empty the data that receive on BD ring, and then statistics once receives overflow error, finally restarts hardware transceiver 102 and continues to receive data.
Generally, the consequence that FIFO overflows is namely lost several messages, does not have too large problem.But, if FIFO overflows repeatedly, will produce a large amount of extra interruptions, further increase the expense of drive software system, reduce the handling property of drive software, form vicious circle.In addition, some hardware transceiver, after FIFO overflows for many times, can cause that internal state machine is disorderly, and the lighter does not again receive data, and severe one is write data on wrong memory address, causes system crash.And how to avoid hardware transceiver FIFO to overflow, be the key addressing the above problem.
Summary of the invention
The invention provides a kind of method and apparatus of avoiding First Input First Output to overflow, avoid occurring receiving FIFO and overflow under the prerequisite of not revising hardware transceiver, corresponding raising drives stability and the reliability receiving.
The method that a kind of FIFO of avoiding that the embodiment of the present invention proposes overflows, comprises the steps:
A, in device memory, create the first buffer descriptor BD ring and the 2nd BD ring;
B, hardware transceiver write the data in FIFO in the idle BD of the one BD ring by the first write pointer, and after completing, hardware transceiver produces receive interruption;
C, drive software detect after receive interruption, utilize the first read pointer reading out data from a BD ring; Drive software utilizes the second write pointer that read data are write in the 2nd BD ring; Drive software utilizes the second read pointer reading out data processing from the 2nd BD ring.
Preferably, the BD number in a described BD ring and the 2nd BD ring is m, m >=n, and n is that hardware transceiver produces a maximum message segment number that receive interruption is corresponding.
Preferably, for a BD ring and the 2nd BD ring, each BD continuous adjacent in internal memory in same BD ring, comprises a loopback flag bit in the mode field of BD.
Preferably, for a BD ring and the 2nd BD ring, each BD in same BD ring is discontinuous adjacent in internal memory, has a special field for depositing the internal memory initial address of next BD in BD, and this field of last BD is deposited the internal memory initial address of first BD.
Preferably, step B comprises:
Whether B1, hardware transceiver FIFO reach after high water level, judge in FIFO and have data to need to shift, if execution step B2; Otherwise go to step B6;
B2, judge whether the BD in a BD ring of the first write pointers point is idle, if so, performs step B3, otherwise returns to step B2;
B3, from the BD that W1 points to, take out buffer zone address, the mode by data by direct memory access DMA is written in buffering area;
B4, judge whether a BD ring completes the reception of a message, if so, continue execution step B5, otherwise return to step B3;
B5, the first write pointers point is set the idle marker of BD for there being data, then by the next BD of the first write pointers point the one BD ring;
B6, hardware transceiver judge whether to meet the condition that produces receive interruption, if produce receive interruption, completing steps B; Otherwise return to step B1.
Preferably, step C comprises:
C1, drive software check in interrupt handling routine whether the BD in the BD ring that the first read pointer points to has data, if execution step C2, otherwise go to step C6;
Whether the BD of the 2nd BD ring of C2, inspection the second write pointers point is idle, if so, performs step C3, otherwise goes to step C5;
The buffering pointer exchange of C3, BD that the buffering pointer of the second write pointers point BD and the first read pointer are pointed to;
C4, the second write pointers point is set the idle marker of BD for there being data, make the next BD of the second write pointers point the 2nd BD ring;
C5, the BD that the first read pointer points to is set idle marker for idle, make the first read pointer point to the next BD of a BD ring, then go to step C1;
C6, in reception task, check that whether the BD of the 2nd BD ring that the second read pointer points to has data, if there is no data, completes data receiver and processes; If there are data, forward step C7 to;
The buffer address of the BD that C7, the 2nd BD pointing to from the second read pointer encircle, take out data and process, execution step C8 after completing;
C8, the 2nd BD ring that the second read pointer points to is set the idle marker of BD for idle, make the second read pointer point to the next BD of the 2nd BD ring, then go to step C6.
The embodiment of the present invention also proposes a kind of equipment, comprises hardware transceiver module, and buffer descriptor BD ring module and drive software module create and have the first buffer descriptor BD ring and the 2nd BD ring in described BD ring module, wherein:
Described hardware transceiver module, for the data of fifo fifo unit being write by the first write pointer in the idle BD of a BD ring, generation receive interruption after completing;
Described drive software module, for after the receive interruption of described hardware transceiver module generation being detected, utilizes the first read pointer reading out data from a BD ring; Utilize the second write pointer that read data are write in the 2nd BD ring; And utilize the second read pointer reading out data processing from the 2nd BD ring.
Preferably, the BD number in a described BD ring and the 2nd BD ring is m, m >=n, and n is that hardware transceiver produces a maximum message segment number that receive interruption is corresponding.
Preferably, for a BD ring and the 2nd BD ring, each BD continuous adjacent in internal memory in same BD ring, comprises a loopback flag bit in the mode field of BD.
Preferably, for a BD ring and the 2nd BD ring, each BD in same BD ring is discontinuous adjacent in internal memory, has a special field for depositing the internal memory initial address of next BD in BD, and this field of last BD is deposited the internal memory initial address of first BD.
As can be seen from the above technical solutions, two BD rings are therefrom set in equipment, by transmit data between two BD rings, reach the effect that a BD encircles driven software fast processing, guarantee that hardware transceiver can find idle BD data writing from a BD ring, thereby avoided overflowing of hardware transceiver FIFO.
Accompanying drawing explanation
Fig. 1 is the principle schematic that available technology adopting BD articulating is received data;
Fig. 2 adopts BD articulating to receive the principle schematic of data in the embodiment of the present invention;
Fig. 3 is the process chart of embodiment of the present invention scheme hardware transceiver part;
Fig. 4 is the process chart of embodiment of the present invention scheme drive software part.
Embodiment
The present invention proposes avoids the basic thought of the method that First Input First Output overflows as follows: on the basis of original BD ring, increased a BD ring.The BD ring that hardware transceiver can be accessed is referred to as a BD ring, or fast B D ring.Another BD ring is referred to as the 2nd BD ring, or BD encircles at a slow speed.By transmit data between two BD rings, reach the effect that a BD encircles driven software fast processing, guarantee that hardware transceiver can find idle BD data writing from a BD ring, thereby avoided overflowing of hardware transceiver FIFO.
The present invention realizes easily, and successful does not rely on special hardware transceiver characteristic, is complete general drivers design.In design, utilized space to exchange the method for time for, successfully the contradiction between drive software buffering and hardware transceiver FIFO has been transferred between two drive software bufferings, although increase some memory costs, thoroughly solve hardware transceiver FIFO and overflow the problem of bringing.
For making feature and the technique effect of technical solution of the present invention clearer, below by specific embodiment, the present invention program is further elaborated.
Suppose that hardware transceiver receives that at most n message produces a receive interruption, device driver software need to distribute 2 * m BD from internal memory so, m >=n, and BD of every m BD composition encircles.The mode that forms BD ring is relevant to the agreement of BD ring with hardware transceiver, is divided into following two kinds:
Mode one: each BD of same BD ring must be continuous adjacent in internal memory, in the mode field of BD, there is a loopback flag bit, loopback flag bit is that this BD of 1 expression is last BD, and loopback flag bit is 0 and represents that this BD is not last BD.During drive software initialization, the internal memory initial address of first BD in BD ring is write in hardware transceiver register, hardware transceiver finds next BD by the internal memory of skew BD size, when finding that BD is last BD of BD ring, automatically jump back to first BD, complete the traversal of BD ring.
Mode two: each BD of same BD ring can not be continuous adjacent in internal memory, BD has a special field for depositing the internal memory initial address of next BD, this field of last BD is deposited the internal memory initial address of first BD, forms an end to end ring.During drive software initialization, the internal memory initial address of first BD is write in hardware transceiver register, hardware transceiver finds next BD by this field, completes the traversal of BD ring.
After two BD ring has created, be that each BD distributes a data buffer zone, the internal memory initial address of data buffer zone write to the buffering pointer field of BD, the idle marker arranging in the mode field of BD is the free time.Select one of them BD ring as fast B D ring, the internal memory initial address of its first BD is write in hardware transceiver register.As shown in Figure 2, thick arrow represents the flow direction of data to two BD rings after initialization completes, the BD of thin arrow points current operation.
In Fig. 2, the first write pointer (W1) is safeguarded by hardware transceiver, points to the BD of the current BD ring that can access of hardware transceiver.The first read pointer (R1), the second write pointer (W2) and the second read pointer (R2) safeguarded by drive software, points to respectively and in the BD that can carry out read operation in a BD ring, the 2nd BD ring, can carry out the BD that can carry out read operation in the BD of write operation and the 2nd BD ring.When initialization completes, W1 and R1 point to first BD of a BD ring, and W2 and R2 point to first BD of the 2nd BD ring.Certainly in the present invention, W1 and R1 are not limited to point to first BD of a BD ring, two pointers can point to any same BD of a BD ring, and the internal memory initial address of that BD in BD ring during now drive software initialization, W1 and R1 being pointed to is simultaneously write in hardware transceiver register.In like manner, W2 and R2 point to the same BD of the 2nd BD ring.
The embodiment of the present invention proposes a kind of equipment, comprises hardware transceiver module, and buffer descriptor BD ring module and drive software module, can avoid the situation that occurs that First Input First Output overflows.In described BD ring module, create and have the first buffer descriptor BD ring and the 2nd BD ring, wherein:
Described hardware transceiver module, for the data of fifo fifo unit being write by the first write pointer in the idle BD of a BD ring, generation receive interruption after completing;
Described drive software module, for after the receive interruption of described hardware transceiver module generation being detected, utilizes the first read pointer reading out data from a BD ring; Utilize the second write pointer that read data are write in the 2nd BD ring; And utilize the second read pointer reading out data processing from the 2nd BD ring.
Preferably, the BD number in a described BD ring and the 2nd BD ring is m, m >=n, and n is that hardware transceiver produces a maximum message segment number that receive interruption is corresponding.
Preferably, for a BD ring and the 2nd BD ring, each BD continuous adjacent in internal memory in same BD ring, comprises a loopback flag bit in the mode field of BD.
Preferably, for a BD ring and the 2nd BD ring, each BD in same BD ring is discontinuous adjacent in internal memory, has a special field for depositing the internal memory initial address of next BD in BD, and this field of last BD is deposited the internal memory initial address of first BD.
As shown in Figure 3 and Figure 4, wherein Fig. 3 shows the handling process of hardware transceiver part to the data receiver flow process of the two BD rings based on the said equipment that the embodiment of the present invention proposes, and Fig. 4 shows the handling process of drive software part.
The processing procedure of hardware transceiver part is that hardware transceiver writes the data in FIFO in the idle BD of the one BD ring by the first write pointer, and after completing, hardware transceiver produces receive interruption, specifically comprises the steps:
Step 301: hardware transceiver FIFO reaches after high water level, and judge in FIFO and whether have data to need to shift, if so, to go to step 306, otherwise execution step 302.
Step 302: whether the BD that judges W1 pointed is idle, if so, performs step 303, otherwise, step 302 returned to.
Described judgement is specially: the idle marker bit in the mode field of the BD that inspection W1 points to, and 1 represents that this BD is idle if, 0 represents that this BD is occupied if.
Step 303: take out buffer zone address the BD pointing to from W1, the mode by data by direct memory access (DMA) is written in buffering area.
Step 304: judged whether the reception of a message, if so, continued execution step 305, otherwise return to step 303.
Step 305: the idle marker bit of the BD of the current sensing of W1 is set to 0, then W1 is pointed to the next BD of a BD ring.
Step 306: hardware transceiver judges whether to meet the condition (time surpasses thresholding or message number surpasses thresholding) that produces receive interruption, if execution step 307.Otherwise return to step 301.
Step 307: hardware transceiver produces receive interruption.
So far, the processing procedure of hardware transceiver part completes, next carry out the processing of drive software part, as shown in Figure 4, the processing procedure of drive software part is that drive software detects after receive interruption, utilize the first read pointer reading out data from a BD ring, then utilize the second write pointer that read data are write in the 2nd BD ring, finally utilize the second read pointer that the data of the 2nd BD ring are read out.Specifically comprise the steps:
Step 401: drive software checks that in interrupt handling routine whether the BD in the BD ring that R1 points to has data, if so, performs step 402, otherwise goes to step 406.
Whether the BD that described middle inspection R1 points to has data is exactly in checking, to check the idle marker bit of the BD that R1 points to, and 1 represents there is no data if, and 0 indicates that data are pending if.
Step 402: whether the BD that checks the 2nd BD ring that W2 points to is idle, if so, performs step 403, otherwise goes to step 405.
The BD that described inspection W2 points to whether free time be the idle marker bit of the BD that checks that W2 points to equally, 0 indicates that data not yet process if, if this BD free time of 1 expression.
Step 403: W2 is pointed to the buffering pointer exchange of the buffering pointer of BD and the BD that R1 points to.
Step 404: the idle marker bit of the BD that W2 is pointed to sets to 0 (representing has data not yet to process in this BD), W2 points to the next BD of the 2nd BD ring.
Step 405: the idle marker bit of the BD that R1 is pointed to put for 1 (representing that this BD is idle), and R1 points to next BD, then goes to step 401.
Step 406: drive software checks the idle marker bit of the BD that R2 points in reception task, judges whether the BD that R2 points to has data, if idle marker bit is 1 expression, there is no data, exits task, completes data receiver and processes.0 indicates that data are pending if, forwards step 407 to.
Step 407: take out data the buffer address of the BD that drive software points to from R2 and process, after completing, execution step 408.
Step 408: the idle marker bit of the BD that R2 is pointed to put for 1 (representing that this BD is idle), and R2 points to next BD, then goes to step 406.
Through the above description of the embodiments, those skilled in the art can be well understood to the mode that the present invention can add essential hardware transceiver platform by drive software and realize, can certainly all by hardware transceiver, implement, but in a lot of situation, the former is better execution mode.Understanding based on such, what technical scheme of the present invention contributed to background technology can embody with the form of drive software product in whole or in part, this computer drives software product can be stored in storage medium, as ROM/RAM, magnetic disc, CD etc., comprise that some instructions are with so that a computer equipment (can be personal computer, server, or the network equipment etc.) carry out the method described in some part of each embodiment of the present invention or embodiment.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of making, be equal to replacement, improvement etc., within all should being included in the scope of protection of the invention.
Claims (10)
1. a method of avoiding First Input First Output FIFO to overflow, is characterized in that, comprises the steps:
A, in device memory, create the first buffer descriptor BD ring and the 2nd BD ring;
B, hardware transceiver write the data in FIFO in the idle BD of the one BD ring by the first write pointer, and after completing, hardware transceiver produces receive interruption;
C, drive software detect after receive interruption, utilize the first read pointer reading out data from a BD ring; Drive software utilizes the second write pointer that read data are write in the 2nd BD ring; Drive software utilizes the second read pointer reading out data processing from the 2nd BD ring.
2. method according to claim 1, is characterized in that, the BD number in a described BD ring and the 2nd BD ring is m, m >=n, and n is that hardware transceiver produces a maximum message segment number that receive interruption is corresponding.
3. method according to claim 1, is characterized in that, for a BD ring and the 2nd BD ring, each BD continuous adjacent in internal memory in same BD ring, comprises a loopback flag bit in the mode field of BD.
4. method according to claim 1, it is characterized in that, for a BD ring and the 2nd BD ring, each BD in same BD ring is discontinuous adjacent in internal memory, in BD, have a special field for depositing the internal memory initial address of next BD, this field of last BD is deposited the internal memory initial address of first BD.
5. according to the method described in claim 1-4 any one, it is characterized in that, step B comprises:
Whether B1, hardware transceiver FIFO reach after high water level, judge in FIFO and have data to need to shift, if execution step B2; Otherwise go to step B6;
B2, judge whether the BD in a BD ring of the first write pointers point is idle, if so, performs step B3, otherwise returns to step B2;
B3, from the BD of the first write pointers point, take out buffer zone address, the mode by data by direct memory access DMA is written in buffering area;
B4, judge whether a BD ring completes the reception of a message, if so, continue execution step B5, otherwise return to step B3;
B5, the first write pointers point is set the idle marker of BD for there being data, then by the next BD of the first write pointers point the one BD ring;
B6, hardware transceiver judge whether to meet the condition that produces receive interruption, if produce receive interruption, completing steps B; Otherwise return to step B1.
6. according to the method described in claim 1-4 any one, it is characterized in that, step C comprises:
C1, drive software check in interrupt handling routine whether the BD in the BD ring that the first read pointer points to has data, if execution step C2, otherwise go to step C6;
Whether the BD of the 2nd BD ring of C2, inspection the second write pointers point is idle, if so, performs step C3, otherwise goes to step C5;
The buffering pointer exchange of C3, BD that the buffering pointer of the second write pointers point BD and the first read pointer are pointed to;
C4, the second write pointers point is set the idle marker of BD for there being data, make the next BD of the second write pointers point the 2nd BD ring;
C5, the BD that the first read pointer points to is set idle marker for idle, make the first read pointer point to the next BD of a BD ring, then go to step C1;
C6, in reception task, check that whether the BD of the 2nd BD ring that the second read pointer points to has data, if there is no data, completes data receiver and processes; If there are data, forward step C7 to;
The buffer address of the BD that C7, the 2nd BD pointing to from the second read pointer encircle, take out data and process, execution step C8 after completing;
C8, the 2nd BD ring that the second read pointer points to is set the idle marker of BD for idle, make the second read pointer point to the next BD of the 2nd BD ring, then go to step C6.
7. an equipment, comprises hardware transceiver module, and buffer descriptor BD ring module and drive software module, is characterized in that, in described BD ring module, create and have the first buffer descriptor BD ring and the 2nd BD ring, wherein:
Described hardware transceiver module, for the data of fifo fifo unit being write by the first write pointer in the idle BD of a BD ring, generation receive interruption after completing;
Described drive software module, for after the receive interruption of described hardware transceiver module generation being detected, utilizes the first read pointer reading out data from a BD ring; Utilize the second write pointer that read data are write in the 2nd BD ring; And utilize the second read pointer reading out data processing from the 2nd BD ring.
8. equipment according to claim 7, is characterized in that, the BD number in a described BD ring and the 2nd BD ring is m, m >=n, and n is that hardware transceiver produces a maximum message segment number that receive interruption is corresponding.
9. equipment according to claim 7, is characterized in that, for a BD ring and the 2nd BD ring, each BD continuous adjacent in internal memory in same BD ring, comprises a loopback flag bit in the mode field of BD.
10. equipment according to claim 7, it is characterized in that, for a BD ring and the 2nd BD ring, each BD in same BD ring is discontinuous adjacent in internal memory, in BD, have a special field for depositing the internal memory initial address of next BD, this field of last BD is deposited the internal memory initial address of first BD.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110205098.0A CN102209042B (en) | 2011-07-21 | 2011-07-21 | Method and device for preventing first input first output (FIFO) queue from overflowing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110205098.0A CN102209042B (en) | 2011-07-21 | 2011-07-21 | Method and device for preventing first input first output (FIFO) queue from overflowing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102209042A CN102209042A (en) | 2011-10-05 |
| CN102209042B true CN102209042B (en) | 2014-04-16 |
Family
ID=44697711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110205098.0A Expired - Fee Related CN102209042B (en) | 2011-07-21 | 2011-07-21 | Method and device for preventing first input first output (FIFO) queue from overflowing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102209042B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105183373B (en) * | 2015-08-28 | 2018-11-09 | 迈普通信技术股份有限公司 | A kind of data processing method and the network equipment |
| CN108259381B (en) * | 2016-12-29 | 2022-06-07 | 航天信息股份有限公司 | Data frame processing method and device and vehicle-mounted unit |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365999A (en) * | 2005-02-03 | 2009-02-11 | 五级网络公司 | send complete event batch |
| CN101690047A (en) * | 2007-07-13 | 2010-03-31 | 国际商业机器公司 | Enhancement of quality of service in network endpoint systems |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DK1514191T3 (en) * | 2002-06-19 | 2009-12-07 | Ericsson Telefon Ab L M | Driver construction for a network device |
| US7457892B2 (en) * | 2006-06-05 | 2008-11-25 | Freescale Semiconductor, Inc. | Data communication flow control device and methods thereof |
| US20080086575A1 (en) * | 2006-10-06 | 2008-04-10 | Annie Foong | Network interface techniques |
-
2011
- 2011-07-21 CN CN201110205098.0A patent/CN102209042B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365999A (en) * | 2005-02-03 | 2009-02-11 | 五级网络公司 | send complete event batch |
| CN101690047A (en) * | 2007-07-13 | 2010-03-31 | 国际商业机器公司 | Enhancement of quality of service in network endpoint systems |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102209042A (en) | 2011-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103176746B (en) | Systems and methods for enhanced controller architecture in data storage systems | |
| CN112559476B (en) | Log storage method for improving performance of target system and related equipment thereof | |
| CN101707565B (en) | Method and device for sending and receiving zero-copy network message | |
| CN102855214B (en) | Realize the method for data consistency and a kind of multiple nucleus system | |
| CN111124267A (en) | Method, apparatus and computer program product for data writing | |
| US20230094634A1 (en) | Memory system and data processing system including the same | |
| US12222876B2 (en) | Method for generating information based on FIFO memory and apparatus, device and medium | |
| CN102622412A (en) | Method and device of concurrent writes for distributed file system | |
| CN103713882A (en) | Method and device for swapping data in memory | |
| CN109375868B (en) | Data storage method, scheduling device, system, equipment and storage medium | |
| CN102209042B (en) | Method and device for preventing first input first output (FIFO) queue from overflowing | |
| US7822040B2 (en) | Method for increasing network transmission efficiency by increasing a data updating rate of a memory | |
| CN108228490A (en) | A kind of driving method based on PCIe card high speed data transfer | |
| CN111651396B (en) | Optimized PCIE (peripheral component interface express) complete packet out-of-order management circuit implementation method | |
| CN102779098B (en) | The cooperating type adaptive prefetching methods, devices and systems of hybrid cache | |
| CN114902173A (en) | Software VSYNC filtering | |
| CN102063271B (en) | State machine based write back method for external disk Cache | |
| CN103559079A (en) | Shared memory based data access method and device | |
| CN116897581A (en) | Computing task scheduling device, computing device, computing task scheduling method and computing method | |
| CN102609240B (en) | The method of processor circuit and reading data | |
| CN101894084A (en) | Device for writing operation in CLB bus | |
| CN106326094B (en) | Check the method and system of pointer exception | |
| CN116225988A (en) | Data transmission method, data transmission device and electronic equipment | |
| CN110647493A (en) | Data transmission method, processor and PCIE system | |
| CN103198017B (en) | A kind of method of test data integrity protection and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140416 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |