CN101754057A - Data scheduling method used in EPON terminal system and based on absolute priority - Google Patents
Data scheduling method used in EPON terminal system and based on absolute priority Download PDFInfo
- Publication number
- CN101754057A CN101754057A CN200910155317A CN200910155317A CN101754057A CN 101754057 A CN101754057 A CN 101754057A CN 200910155317 A CN200910155317 A CN 200910155317A CN 200910155317 A CN200910155317 A CN 200910155317A CN 101754057 A CN101754057 A CN 101754057A
- Authority
- CN
- China
- Prior art keywords
- data
- bandwidth
- priority
- frame
- 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.)
- Withdrawn
Links
Images
Landscapes
- Small-Scale Networks (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a data scheduling method used in an EPON terminal system and based on absolute priority. The EPON terminal system is a point-to-multipoint network system, comprises three parts: an end OLT, a terminal ONU and a passive optical divider, and is characterized in that: a. FIFOs used for data caching are added in the terminal ONU, and the number of the FIFOs is determined by the current priority number for data discrimination; b. address spaces are allocated in an external memory according to the priority; c. the terminal ONU transmits data to the end OLT, a transmission time slot for report frames used for bandwidth application is reserved at the tail part of a transmission time slot, and the number of data remained in the current system and to be transmitted can be accurately calculated when every time slot transmission is ended; d. when a higher priority comes, the current transmitted data is confirmed to be consistent with the data applied to be transmitted; and e. when end OLT allocates bandwidth more than the applied bandwidth to the terminal ONU, absolute priority scheduling can be selected or round-robin scheduling is selected to equally allocate the excessive bandwidth. Through practical operation and testing, the invention has the advantages that the effect is good, the bandwidth utilization ratio is high and the data transmission requirement of the EPON system is satisfied.
Description
Technical field
The present invention relates to be applied to the data dispatching method of EPON terminal system (ONU), relate in particular to and utilizing external memory storage, comprise SDRAM, DDR-SDRAM and DDRII-SDRAM, to the data buffer memory, and employed first priority level scheduling method when distinguishing the different pieces of information grade of service.
Background technology
The EPON system is the network system of a kind of point to multiple spot, and it mainly comprises three parts: local side OLT, terminal (user side) ONU and passive optical splitter, as shown in Figure 1.At down direction, the Ethernet data bag that OLT sends is transferred to each ONU with a kind of broadcast mode through behind the passive optical splitter of 1xN, and ONU then extracts packet selectively; At up direction, because the directional characteristic of passive optical splitter, the packet that any one ONU sends can only arrive OLT, and can not arrive ONU, that is: the data of all ONU are sent to same OLT, have made up the network of the point-to-multipoint of EPON system thus.
When ONU need at first need to apply for sending the bandwidth that data are used when OLT sends data, OLT then gives current ONU distribute data sending time slots according to certain algorithm, and ONU can utilize this section sending time slots to send data to OLT afterwards.And between ONU bandwidth application and acquisition sending time slots, ONU can not send data to OLT, does not lose in order to ensure frame, the data that need utilize buffer memory to arrive; In order to distinguish the data, services of the inner different brackets of ONU, need adopt certain algorithm to dispatch simultaneously to the ONU internal data.
Utilizing external memory storage data cached at present, and when carrying out data dispatch algorithm based on absolute priority, at first according to the data quantity stored in the external memory storage to the OLT bandwidth application, obtain the data sending time slots of OLT distribution as ONU after, extract data from external memory storage, send to OLT then.This method can be brought some problems:
At first, after ONU obtains sending time slots from external memory storage sense data have certain time delay because memory is carried out read operation, just when OLT sends data, produce certain time delay, cause the waste of bandwidth; Simultaneously external memory storage self needs refresh operation and keeps data, and refresh operation needs the regular hour just can finish, during this period of time can't access external memory, and this has increased the weight of the waste of data bandwidth more;
Secondly, owing to the data uncertainty of the time of advent, when ONU obtains time slot when OLT sends data, the data that might have higher priority at this moment arrive ONU, in general absolute priority dispatching algorithm, ONU can dispatch the data of limit priority, it is inconsistent with the actual data that send to the data that the OLT application sends this moment to occur ONU, though this inconsistent confusion and the mistake that can not cause system, but cause certain difficulty can for the time slot allocation of OLT, also can bring for simultaneously the data statistics of OLT and mix, more serious then is the waste that causes bandwidth;
At last, during to OLT request for data bandwidth, OLT might distribute to ONU exceed the data bandwidth of its application, thereby has produced the remaining bandwidth problem at ONU.In general absolute priority dispatching algorithm, ONU can dispatch the data of limit priority, and this moment, lower-priority data can not get bandwidth for a long time, is easy to occur " dying of hunger " phenomenon.
Summary of the invention
The objective of the invention is to overcome the deficiency that prior art exists, and provide a kind of when utilizing external memory storage (comprising SDRAM, DDR-SDRAM and DDRII-SDRAM) as the buffer memory data, by increasing the use of FIFO, and adopt strategy flexibly and constitute be applied to the data dispatching method of EPON terminal system based on absolute priority.
The objective of the invention is to finish by following technical solution, described EPON terminal system is the network system of a kind of point to multiple spot, and it mainly comprises three parts: local side OLT, terminal ONU and passive optical splitter, and described data dispatching method:
In the described terminal ONU of a, increase the FIFO be useful on metadata cache, and the number of described FIFO depends on the priority progression of current differentiation data, promptly current data is divided into 8 priority, and then the FIFO number is 8; The width of FIFO is matched with the data bit width of external memory storage usually, and promptly external memory storage is 32 bit data bit wides, and then the data width of FIFO is 32; The degree of depth of FIFO is optional;
According to the priority assignment address space, promptly the external memory storage of Cai Yonging is the 8MB capacity in the b external memory storage, and needing to distinguish data simultaneously is 8 priority, and then each priority data is divided the address space of 1MB;
The described terminal ONU of c sends data to local side OLT, reserve the sending time slots of the Report frame of bandwidth application use at the afterbody of sending time slots, each time slot sends when finishing, can add up accurately that also to remain how many data etc. in the current system to be sent, and then the amount of bandwidth of accurately controlling ONU and being applied for, optimize the use of the network bandwidth;
When d arrived in higher priority, the data that the data of guaranteeing current transmission are and application sends were consistent: only when utilizing Report frame request for data bandwidth, be to handle in strict accordance with the algorithm of absolute priority promptly;
E when promptly remaining bandwidth being arranged, according to the needs of using, can select the absolute priority scheduling when local side OLT has distributed the bandwidth that exceeds its application to terminal ONU, or selects polling dispatching meeting mean allocation bandwidth.
In the described part (a), also comprise: 1 the priority number of the current differentiation data of the strict coupling of number needs of FIFO; Can the not match data width of external memory storage of the data width of 2 FIFO, promptly when the data width of external memory storage was 32, the data width of FIFO can be 8,16 or 32; When the data width of external memory storage was 8, the data width of FIFO still can be chosen as 32,16 or 8; The described FIFO of 3 sends after the frame that finishes, current priority can also continue transmit frame, require this moment FIFO sending continuously between two frames, can not there be extra time delay to produce, thus, the degree of depth of FIFO can be set to certain reasonable value, guarantees when the transmission of Frame, even access external memory can be brought certain time delay, but utilize FIFO can " cover " time delay of bringing thus.
In the described part (b), also comprise: 1, described external memory storage can random access, and the frame of each priority can be in address space storage arbitrarily, and each priority frame is according to certain algorithm stores; Its allocated bandwidth situation during according to the terminal ONU actual motion proposes to use the fixed address space allocation method, proposes to need to use the bigger external memory storage of memory capacity simultaneously.
In the described part (c), pointed request for data Bandwidth Calculation Formula is:
Frame bandwidth demand among main broadband demand=FIFO
The bandwidth demand of the bandwidth demand of frame+Report frame among the+SDRAM.
In the described part (d),, when then applying for, at first satisfy the Frame of limit priority at every turn, satisfy the Frame of time priority then owing to utilize the data bandwidth of Report frame application that a restriction threshold values is arranged at every turn.If this moment, the Frame of limit priority was 0, then at first satisfy the Frame of time priority, all the other situations are by that analogy.
Described part (e), local side OLT can be divided into 3 parts for the terminal ONU distributed time slot, and wherein part 1 is the bandwidth demand that ONU utilizes the application of Report frame; Part 2 then is the bandwidth that OLT might give the ONU overabsorption, promptly so-called remaining bandwidth; The 3rd part then is that ONU sends the needed time slot bandwidth of Report frame.Wherein the time slot bandwidth of part 2 might be 0; The time slot bandwidth of the 3rd part is certain fixed value.
Algorithm of the present invention has been applied in the chip development process of ONU, and through the actual motion test, effect is good, and the bandwidth availability ratio height has satisfied EPON system data transmission requirement.
Description of drawings
Fig. 1 is existing EPON terminal system structural representation.
Fig. 2 is an EPON terminal system structural representation of the present invention.
Fig. 3 is the formation schematic diagram in actual request for data of the present invention broadband.
Embodiment
The present invention will be described in detail below in conjunction with accompanying drawing: EPON terminal system of the present invention is the network system of a kind of point to multiple spot, it mainly comprises three parts: local side OLT, terminal ONU and passive optical splitter, described data dispatching method mainly comprises as the lower part:
A increases FIFO in ONU, be used for the buffer memory of data: the number of FIFO depends on the priority progression of current differentiation data, if current data is divided into 8 priority, then the FIFO number is 8; If only need to distinguish 4 priority, then the FIFO number is 4; The width of FIFO is matched with the data bit width of external memory storage in the ordinary course of things, if external memory storage is 32 bit data bit wides, then the data width of FIFO is 32; The degree of depth of FIFO is optional;
B externally in the memory according to the priority assignment address space, simplify dispatching algorithm: if the external memory storage that adopts is the 8MB capacity, needing to distinguish data simultaneously is 8 priority, then each priority data is divided the address space of 1MB;
E when ONU when OLT sends data, reserve the sending time slots of the Report frame of bandwidth application use at the afterbody of sending time slots, thereby when each time slot sends end, can add up accurately that also to remain how many data etc. in the current system to be sent, and then the amount of bandwidth of accurately controlling ONU and being applied for, optimize the use of the network bandwidth;
When d arrived as higher priority, the data that the data of guaranteeing current transmission are and application sends were consistent: only when utilizing Report frame request for data bandwidth, be to handle in strict accordance with the algorithm of absolute priority promptly.By this method, can farthest utilize bandwidth, guarantee that the bandwidth of applying for can not be wasted;
E works as OLT and has distributed the bandwidth that exceeds its application to ONU, when promptly remaining bandwidth being arranged, according to the needs of using, can select the absolute priority scheduling, also can select dispatching algorithms such as polling dispatching meeting mean allocation bandwidth, accomplish " flexibly " scheduling, at utmost satisfy the user demand characteristic.
In above-mentioned described part of the present invention (a), also comprise:
A) number of FIFO needs the priority number of the current differentiation data of strict coupling;
B) data width of the FIFO data width of external memory storage that can not match, for example when the data width of external memory storage was 32, the data width of FIFO can be 8,16 or 32; And when the data width of external memory storage was 8, the data width of FIFO still can be chosen as 32,16 or 8; But for the facilitating chip exploitation, the general selection of the data width of FIFO mated with the data bit width of external memory storage.
C) if according to bandwidth application principle, after FIFO sends the frame that finishes, current priority can also continue transmit frame, in order farthest to utilize bandwidth, requires this moment FIFO sending continuously between two frames, can not there be extra time delay to produce, thus, the degree of depth of FIFO can be set to certain reasonable value, guarantees when the transmission of Frame, even access external memory can be brought certain time delay, but utilize FIFO can " cover " time delay of bringing thus.
In above-mentioned described part of the present invention (b), also comprise:
A) because external memory storage can random access, therefore the frame of each priority can be stored at any address space, but for the facilitating chip development difficulty, optimizes chip logic, advise that each priority frame according to certain algorithm stores, accomplishes the maximization of space utilization efficient; When utilizing the external memory stores Frame, give the storage area in each priority assignment fixed address space, might bring the waste of memory space, for example priority is that 8 data can be stored in 0 ~ 1MB space of external memory storage, priority is that 7 data can be stored in 1 ~ 2MB space of exterior storage, when the data of priority 8 are filled up memory space, and the data of priority 7 are when being empty, though external memory storage still has living space, can not continue the data of memory priority level 8.Therefore the fixed address space allocation method is succinct when realizing, but can cause the space waste;
B) the present invention develops angle from actual chips, and the allocated bandwidth situation during according to the ONU actual motion proposes to use the fixed address space allocation method, and proposing simultaneously needs to use the bigger external memory storage of memory capacity, accomplishes not losing of frame;
Request for data Bandwidth Calculation Formula pointed in above-mentioned described part of the present invention (c) is:
Frame bandwidth demand among main broadband demand=FIFO
The bandwidth demand of the bandwidth demand of frame+Report frame among the+SDRAM.
In above-mentioned described part of the present invention (d), owing to utilize the data bandwidth of Report frame application that a restriction threshold values is arranged at every turn, when then applying for, at first satisfy the Frame of limit priority at every turn, satisfy the Frame of time priority then.If this moment, the Frame of limit priority was 0, then at first satisfy the Frame of time priority, all the other situations are by that analogy.For example when threshold values when being set at 100KB, and the Frame of limit priority has 120KB, the Frame of inferior priority has 80KB, this moment is when utilizing the Report frame, can only apply for the bandwidth of the limit priority frame of 100KB, inferior priority can't obtain the bandwidth application, therefore when obtaining the data sending time slots, also can't send the frame of time priority.Utilize this method, the absolute priority scheduling when having accomplished the bandwidth application;
In above-mentioned described part of the present invention (e), with reference to the accompanying drawings 3, OLT can be divided into 3 parts for the ONU distributed time slot, and wherein part 1 is the bandwidth demand that ONU utilizes the application of Report frame; Part 2 then is the bandwidth that OLT might give the ONU overabsorption, promptly so-called remaining bandwidth; The 3rd part then is that ONU sends the needed time slot bandwidth of Report frame.Wherein the time slot bandwidth of part 2 might be 0; The time slot bandwidth of the 3rd part is certain fixed value.
The present invention is after tested: when the frame of transmission 64 bytes and when distinguishing frame and being 8 service priority grades, up total bandwidth can reach 970Mbps, has only the frame of the 1st, the 2 two priority the frame losing phenomenon to occur, and the frame of all the other priority is not lost; When the frame of transmission 128,256,512 bytes and when distinguishing frame and being 8 service priority grades, up total bandwidth can reach 980Mbps and higher, has only the frame of the 1st priority the frame losing phenomenon to occur, and the frame of all the other priority is not lost;
Utilizing algorithm of the present invention to carry out in the chip design development process, two modules have been related generally to: SDRAM module and fifo module, as shown in Figure 2, SDRAM module wherein is responsible for the Frame that buffer memory receives from the user, FIFO then is can storage frame the time, just proposes the request of reading frame to the SDRAM module.
In the current design, the differentiation priority service grade of support comprises 8 grades, so the number of FIFO is 8; The degree of depth of FIFO is chosen as 4KB; The data width coupling of SDRAM and FIFO is 32b.
When realizing,, realize that this Frame is carried out service priority distinguishes (supporting 8 priority altogether), deposits in the different SDRAM address spaces according to priority then when when the user receives Frame; Need to utilize the frame number and the frame length of current each priority frame of register pair to count simultaneously.
When the empty water level of FIFO 1/2 the time, to SDRAM the request of reading respective frame priority is proposed, SDRAM then satisfies this request.
At each time slot end, as shown in Figure 3, need be according to the bandwidth demand of data bandwidth demand among data bandwidth demand of storing among the FIFO and the SDRAM and Report frame, three's addition obtains the data bandwidth of this actual application.
When this was realized, the application threshold values of Report frame was that register can be joined; Use polling method to handle to remaining bandwidth.
Claims (6)
1. data dispatching method that is applied to the EPON terminal system based on absolute priority, described EPON terminal system is the network system of a kind of point to multiple spot, it mainly comprises three parts: local side OLT, terminal ONU and passive optical splitter is characterized in that:
In a, the described terminal ONU, increase the FIFO be useful on metadata cache, and the number of described FIFO depends on the priority progression of current differentiation data, promptly current data is divided into 8 priority, and then the FIFO number is 8; The width of FIFO is matched with the data bit width of external memory storage usually, and promptly external memory storage is 32 bit data bit wides, and then the data width of FIFO is 32; The degree of depth of FIFO is optional;
According to the priority assignment address space, promptly the external memory storage of Cai Yonging is the 8MB capacity in b, the external memory storage, and needing to distinguish data simultaneously is 8 priority, and then each priority data is divided the address space of 1MB;
C, described terminal ONU send data to local side OLT, reserve the sending time slots of the Report frame of bandwidth application use at the afterbody of sending time slots, each time slot sends when finishing, can add up accurately that also to remain how many data etc. in the current system to be sent, and then the amount of bandwidth of accurately controlling ONU and being applied for, optimize the use of the network bandwidth;
D, when higher priority arrives, the data that the data of guaranteeing current transmission are and application sends are consistent: only when utilizing Report frame request for data bandwidth, be to handle in strict accordance with the algorithm of absolute priority promptly;
E, distributed the bandwidth that exceeds its application to terminal ONU when local side OLT, when promptly remaining bandwidth being arranged,, can select the absolute priority scheduling, or selected the polling dispatching can the mean allocation bandwidth according to the needs of using.
2. the data dispatching method that is applied to the EPON terminal system based on absolute priority according to claim 1 is characterized in that also comprising in the described part (a): 1) the priority number of the current differentiation data of the strict coupling of the number needs of FIFO; 2) data width of the FIFO data width of external memory storage that can not match, promptly when the data width of external memory storage was 32, the data width of FIFO can be 8,16 or 32; When the data width of external memory storage was 8, the data width of FIFO still can be chosen as 32,16 or 8; 3) described FIFO sends after the frame that finishes, current priority can also continue transmit frame, require this moment FIFO sending continuously between two frames, can not there be extra time delay to produce, thus, the degree of depth of FIFO can be set to certain reasonable value, guarantees when the transmission of Frame, even access external memory can be brought certain time delay, but utilize FIFO can " cover " time delay of bringing thus.
3. the data dispatching method that is applied to the EPON terminal system based on absolute priority according to claim 1, it is characterized in that in the described part (b), also comprise: described external memory storage can random access, the frame of each priority can be in address space storage arbitrarily, and each priority frame is according to certain algorithm stores; Its allocated bandwidth situation during according to the terminal ONU actual motion proposes to use the fixed address space allocation method, proposes to need to use the bigger external memory storage of memory capacity simultaneously.
4. the data dispatching method that is applied to the EPON terminal system based on absolute priority according to claim 1 is characterized in that in the described part (c), pointed request for data Bandwidth Calculation Formula is:
Frame bandwidth demand among main broadband demand=FIFO
The bandwidth demand of frame among the+SDRAM
The bandwidth demand of+Report frame.
5. the data dispatching method that is applied to the EPON terminal system based on absolute priority according to claim 1, it is characterized in that in the described part (d), owing to utilize the data bandwidth of Report frame application that a restriction threshold values is arranged at every turn, when then applying at every turn, at first satisfy the Frame of limit priority, satisfy the Frame of time priority then.If this moment, the Frame of limit priority was 0, then at first satisfy the Frame of time priority, all the other situations are by that analogy.
6. the data dispatching method that is applied to the EPON terminal system based on absolute priority according to claim 1, it is characterized in that described part (e), local side OLT can be divided into 3 parts for the terminal ONU distributed time slot, and wherein part 1 is the bandwidth demand that ONU utilizes the application of Report frame; Part 2 then is the bandwidth that OLT might give the ONU overabsorption, promptly so-called remaining bandwidth; The 3rd part then is that ONU sends the needed time slot bandwidth of Report frame.Wherein the time slot bandwidth of part 2 might be 0; The time slot bandwidth of the 3rd part is certain fixed value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200910155317A CN101754057A (en) | 2009-12-11 | 2009-12-11 | Data scheduling method used in EPON terminal system and based on absolute priority |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200910155317A CN101754057A (en) | 2009-12-11 | 2009-12-11 | Data scheduling method used in EPON terminal system and based on absolute priority |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101754057A true CN101754057A (en) | 2010-06-23 |
Family
ID=42480317
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN200910155317A Withdrawn CN101754057A (en) | 2009-12-11 | 2009-12-11 | Data scheduling method used in EPON terminal system and based on absolute priority |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101754057A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102012868A (en) * | 2010-12-02 | 2011-04-13 | 杭州开鼎科技有限公司 | Data caching architecture applied in local side of Ethernet passive optical network (EPON) system |
CN102404652A (en) * | 2010-09-10 | 2012-04-04 | 高通创锐讯通讯科技(上海)有限公司 | Double data rate (DDR) buffer Ethernet network package method for optical line terminal (OLT) or optical network unit (ONU) chip in Ethernet passive optical network (EPON) |
CN104636310A (en) * | 2014-12-19 | 2015-05-20 | 上海华为技术有限公司 | Data processing method, device and system |
CN104994030A (en) * | 2015-05-11 | 2015-10-21 | 华中科技大学 | EPON communication system dynamic bandwidth allocation method used in intelligent power distribution network |
CN108462649A (en) * | 2017-02-20 | 2018-08-28 | 深圳市中兴微电子技术有限公司 | The method and apparatus for reducing high-priority data propagation delay time under congestion state in ONU |
CN110830388A (en) * | 2018-08-09 | 2020-02-21 | 中兴通讯股份有限公司 | Data scheduling method, device, network equipment and computer storage medium |
CN112953848A (en) * | 2021-03-12 | 2021-06-11 | 西安电子科技大学 | Strict priority based traffic supervision method, system and equipment |
CN113938774A (en) * | 2021-10-13 | 2022-01-14 | 芯河半导体科技(无锡)有限公司 | Low-delay bandwidth allocation method |
-
2009
- 2009-12-11 CN CN200910155317A patent/CN101754057A/en not_active Withdrawn
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404652A (en) * | 2010-09-10 | 2012-04-04 | 高通创锐讯通讯科技(上海)有限公司 | Double data rate (DDR) buffer Ethernet network package method for optical line terminal (OLT) or optical network unit (ONU) chip in Ethernet passive optical network (EPON) |
CN102012868A (en) * | 2010-12-02 | 2011-04-13 | 杭州开鼎科技有限公司 | Data caching architecture applied in local side of Ethernet passive optical network (EPON) system |
CN102012868B (en) * | 2010-12-02 | 2012-11-07 | 杭州开鼎科技有限公司 | Data caching architecture applied in local side of Ethernet passive optical network (EPON) system |
CN104636310A (en) * | 2014-12-19 | 2015-05-20 | 上海华为技术有限公司 | Data processing method, device and system |
CN104994030A (en) * | 2015-05-11 | 2015-10-21 | 华中科技大学 | EPON communication system dynamic bandwidth allocation method used in intelligent power distribution network |
CN108462649A (en) * | 2017-02-20 | 2018-08-28 | 深圳市中兴微电子技术有限公司 | The method and apparatus for reducing high-priority data propagation delay time under congestion state in ONU |
CN108462649B (en) * | 2017-02-20 | 2020-07-07 | 深圳市中兴微电子技术有限公司 | Method and device for reducing high-priority data transmission delay in congestion state of ONU |
CN110830388A (en) * | 2018-08-09 | 2020-02-21 | 中兴通讯股份有限公司 | Data scheduling method, device, network equipment and computer storage medium |
CN112953848A (en) * | 2021-03-12 | 2021-06-11 | 西安电子科技大学 | Strict priority based traffic supervision method, system and equipment |
CN112953848B (en) * | 2021-03-12 | 2023-05-02 | 西安电子科技大学 | Traffic supervision method, system and equipment based on strict priority |
CN113938774A (en) * | 2021-10-13 | 2022-01-14 | 芯河半导体科技(无锡)有限公司 | Low-delay bandwidth allocation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101754057A (en) | Data scheduling method used in EPON terminal system and based on absolute priority | |
US8225026B2 (en) | Data packet access control apparatus and method thereof | |
CN102684976B (en) | Method, device and system for carrying out data reading and writing on basis of DDR SDRAN (Double Data Rate Synchronous Dynamic Random Access Memory) | |
CN101848135B (en) | Management method and management device for statistical data of chip | |
US9690507B2 (en) | System and method for enabling high read rates to data element lists | |
CN108984280B (en) | Method and device for managing off-chip memory and computer-readable storage medium | |
CN102037455A (en) | Credit management when resource granularity is larger than credit granularity | |
CN102083206B (en) | Method, device and system for allocating air interface resources | |
CN105656807A (en) | Network chip multi-channel data transmission method and transmission device | |
CN106371916B (en) | A kind of thread optimized method and device thereof of storage system IO | |
CN102841869A (en) | Multi-channel I2C controller based on FPGA | |
US7088730B2 (en) | Ethernet switching architecture and dynamic memory allocation method for the same | |
US10678718B2 (en) | Network device and method of operation | |
CN103023800A (en) | Method for scheduling traffic under multi-core network processor by traffic chart mapping scheduling strategy | |
CN110287127A (en) | A kind of Nonvolatile memory management method and system that more granularity multicores are expansible | |
CN100539538C (en) | Storage management system with chained list processor | |
CN206946471U (en) | A kind of shared read-write SDRAM of multichannel circuit arrangement | |
CN1298593A (en) | AMPIC DRAM system in a telecommunication switch | |
CN103117962B (en) | A kind of spaceborne Shared memory switch device | |
CN102025634A (en) | Management method and equipment of data packet cache | |
CN105335323A (en) | Buffering device and method of data burst | |
CN101309194A (en) | SPI4.2 bus bridging implementing method and SPI4.2 bus bridging device | |
CN101291275B (en) | SPI4.2 bus bridging implementing method and SPI4.2 bus bridging device | |
CN102932265B (en) | Data caching management device and method | |
CN101043437B (en) | Method and apparatus for transmitting quickly operation, management and maintenance cell |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C04 | Withdrawal of patent application after publication (patent law 2001) | ||
WW01 | Invention patent application withdrawn after publication |
Open date: 20100623 |