CN103516621B - The method and apparatus of queue scheduling - Google Patents
The method and apparatus of queue scheduling Download PDFInfo
- Publication number
- CN103516621B CN103516621B CN201210222139.1A CN201210222139A CN103516621B CN 103516621 B CN103516621 B CN 103516621B CN 201210222139 A CN201210222139 A CN 201210222139A CN 103516621 B CN103516621 B CN 103516621B
- Authority
- CN
- China
- Prior art keywords
- port
- generic
- queue
- scheduling
- burst
- 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.)
- Active
Links
Abstract
The embodiment of the present invention provides a kind of method and apparatus of queue scheduling, multiple subqueues are split into non-generic port queue it is tied on non-generic port and is scheduled, and by increasing logic port level scheduler, non-generic port is scheduled with common ports share bandwidth, solve and treat process problem of the performance of scheduling queue more than queue in the case of system list queue processing ability.Meanwhile dispatched by twin-stage burst and package-restructuring ensure that the integrality of packet, and time interval resource is made full use of, improve the bag forward efficiency of system.
Description
Technical field
The present invention relates to queue scheduling in the method for traffic management in data communication technology, more particularly to a kind of traffic management
Method and apparatus.
Background technology
Queue scheduling, i.e. queue check (for example receiving mandate triggering etc.) by certain triggering, and arbitration queue goes out team
Condition, go out team according to certain rule-based scheduling queue, conventional dispatching algorithm has RR (Round Robin, poll) dispatching algorithm
With SP (Strict Priority, strict priority) dispatching algorithm.
With the development of chip related software, hardware technology, the requirement more and more higher to traffic management chip, to bag
Forward rate, queue scheduling complexity propose higher requirement.For example it is assumed that each physical port of traffic management chip goes out
Team ability be 40G/N, forward rate is 72MPPS/N (N is the quantity of exit port), if to handle size be 40G, forward rate be
72MPPS flow, it is not achievable according to existing dispatching method.That is, treat that the performance of scheduling queue exceedes system list
During queue processing ability, the method for queue scheduling can not realize the scheduling to the queue in the prior art.
The content of the invention
The embodiment of the present invention provides a kind of method and apparatus of queue scheduling, exceedes system list in the performance for treating scheduling queue
In the case of queue processing ability, remain able to realize the scheduling to the queue.
To achieve these goals, the embodiment of the present invention provides a kind of method of queue scheduling, including：
Enqueue is tied into common port and/or non-generic port to be scheduled；
Logic port level scheduler is set, according to the scheduling mode scheduling common port that is pre-configured with and/or non-general
Go side mouth, the multiple subqueues obtained after being split to enqueue corresponding to the non-generic port and/or the common port pair
The common port queue answered is authorized, wherein, the common port and non-generic ports share bandwidth；
The subqueue that will be authorized and/common port queue are put into register, and carry out first order burst scheduling；
After the subqueue carries out first order burst scheduling, the subqueue is respectively written into corresponding FIFO and first entered
First go out, and the packet header mark of each subqueue is recorded into FIFO order by the FIFO that sorts, according in the sequence FIFO
FIFO numberings FIFO corresponding to reads data until reading bag tail, again reads off the sequence FIFO；
The data carried out to the data in the FIFO and/or the common port queue after first order burst scheduling are entered
Row second level burst is dispatched.
It is described by enqueue be tied to common port and/or non-generic port be scheduled including：
Joined the team according to judging preset strategy and be classified as non-generic port queue or common port queue, will be described non-general
Logical port queue splits into multiple subqueues, is tied on non-generic port and is scheduled, and the common port queue is bound
Dispatched on to common port, wherein, the non-generic port and common port are logic port, each non-generic port pair
Answer multiple physical ports, each common corresponding physical port in port.
The setting logic port level scheduler includes：
Corresponding to physical port scheduler subordinate set logic port level scheduler, the logic port level scheduler with
Logic port is corresponding.
The scheduling mode scheduling common port and non-generic port that the basis is pre-configured with include：
The common port and non-generic port are adjusted using robin manner or strict priority scheduling mode
Degree.
The progress first order burst scheduling includes：According to the burst of fixed size and time slot to subqueue and/or general
Logical port queue is scheduled.
The progress first order burst scheduling includes：
Per x periodic scheduling once, per x/n periodic scheduling once, x is certainly for the non-generic port for the common port
So number, n are the number of register corresponding to the non-generic port.
The progress first order burst scheduling includes exporting the one or more of herein below：Physical port number, common end
Mouth/non-generic port designations, physical queue number, packet header and bag tail tag will, the register label of non-generic port polling.
The data carried out to the data in the FIFO and/or the common port queue after first order burst scheduling are entered
Burst scheduling in the row second level includes：
To each burst markings to indicate that the burst comes from common port or non-generic port.
The embodiment of the present invention also provides a kind of device of queue scheduling, including：
Join the team column processing unit, be scheduled for enqueue to be tied into common port and/or non-generic port；
Authorisation process unit, for setting logic port level scheduler, according to the scheduling mode scheduling being pre-configured with
Common port and non-generic port, are authorized to the multiple subqueue and/or common port queue, wherein, it is described common
Port and non-generic ports share bandwidth；
First order burst scheduling units, register is put into for the subqueue that will be authorized and/common port queue,
And carry out first order burst scheduling；
Package-restructuring unit, for after the subqueue carries out first order burst scheduling, the subqueue to be respectively written into
Corresponding FIFO FIFOs, and the packet header mark of each subqueue is recorded into FIFO order by the FIFO that sorts, according to institute
The FIFO numberings FIFO corresponding to stated in sequence FIFO reads data until reading bag tail, again reads off the sequence FIFO；
Second level burst scheduling units, for the data in the FIFO and/or the common port queue to be carried out with the
Data after one-level burst scheduling carry out second level burst scheduling.
The column processing unit of joining the team is additionally operable to：Judge to join the team according to preset strategy to be classified as non-generic port queue or general
Logical port queue, splits into multiple subqueues by the non-generic port queue, is tied on non-generic port and is scheduled, will
The common port queue, which is tied on common port, to be dispatched, wherein, the non-generic port and common port are logic
Port, each non-generic port correspond to multiple physical ports, each common corresponding physical port in port.
The authorisation process unit is additionally operable to：In scheduler subordinate corresponding to physical port, the scheduling of logic port level is set
Device, the logic port level scheduler are corresponding with logic port.
The first order burst scheduling units are additionally operable to：Polling dispatching is used to the common port and non-generic port
Mode or strict priority scheduling mode are scheduled.
The first order burst scheduling units are additionally operable to：According to the burst of fixed size and time slot to subqueue and/or
Common port queue is scheduled.
The first order burst scheduling units are additionally operable to：Per common port described in x periodic scheduling once, the week per x/n
Phase dispatches the non-generic port once, and x is natural number, and n is the number of register corresponding to the non-generic port.
The first order burst scheduling units are additionally operable to：Export the one or more of herein below：It is physical port number, general
Go side mouth/non-generic port designations, physical queue number, packet header and bag tail tag will, the register label of non-generic port polling.
The second level burst scheduling units are additionally operable to：To each burst markings to indicate the burst from common
Port or non-generic port.
In method and apparatus provided in an embodiment of the present invention, multiple subqueues are split into non-generic port queue and are tied to
It is scheduled on non-generic port, and by increasing logic port level scheduler, makes non-generic port and common ports share band
Width is scheduled, and is solved and is treated that processing of the performance more than queue in the case of system list queue processing ability of scheduling queue is asked
Topic.Meanwhile dispatched by twin-stage burst and package-restructuring ensure that the integrality of packet, and time interval resource is made full use of, improve
The bag forward efficiency of system.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the method for queue scheduling provided in an embodiment of the present invention；
Fig. 2 is the process schematic of column processing of being joined the team in method shown in Fig. 1；
The setting schematic diagram of scheduler when Fig. 3 is authorisation process in method shown in Fig. 1；
Fig. 4 is the process schematic that first order burst is dispatched in method shown in Fig. 1；
Fig. 5 is the process schematic that package-restructuring is handled in method shown in Fig. 1；
Fig. 6 is dequeue schematic diagram in method shown in Fig. 1；
Fig. 7 is the structural representation of the device of queue scheduling provided in an embodiment of the present invention.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with accompanying drawing to the present invention
Embodiment be described in detail.It should be noted that in the case where not conflicting, in the embodiment and embodiment in the application
Feature can mutually be combined.
Main idea is that：Particular queue of some queue performances beyond system list queue processing ability is bound
Onto non-generic port, finally it is mapped on common port, non-generic port is authorized and is uniformly processed, shares common port
Resource, improve system effectiveness.Further, using two-stage burst scheduling plus package-restructuring scheme, ensure that the message property completed is filled simultaneously
Divide and utilize time interval resource, dispatched according to configurable burst sizes, improve the dispatching of total port.Wherein, non-generic end
Mouth and common port are logic port, and each non-generic port corresponds to multiple physical ports, each common corresponding physics in port
Port.
The embodiment of the present invention provides a kind of method of queue scheduling, as shown in figure 1, including：
Step 101, queue type's judgement is carried out to the enqueue received and bag is handled.
Judge to join the team according to preset strategy to be classified as non-generic port queue or common port queue, the preset strategy is for example
For：The corresponding relation of type of service and port type is pre-set, judges it for non-generic end according to the type of service of enqueue
Mouth queue or common port queue.Non-generic port queue is split into multiple subqueues, it is enterprising to be tied to non-generic port
Row scheduling, common port queue is tied on common port and dispatched.In bag processing procedure is entered, one can also be used
2bit counter, for recording chained list situation that current non-generic port queue uses (i.e. relative to the of the polymerization queue
0th, 1,2,3 physical queue number), as shown in Fig. 2 when there is non-generic port queue to join the team, then current block should write
Physical queue number is equal to the chained list counter of polymerization queue number+current.Because the pattern of current queue can match somebody with somebody, Ren Heyi
Bar chained list is likely to be configured to non-generic port queue or common port queue, so current each queue should be reserved
The counter, for common port queue, this counter is only 0.
Step 102, authorisation process is carried out to non-generic port queue and/or common port queue.
As shown in figure 3, logic port level scheduler is provided below in physical port level scheduler in the authorization module of chip.Patrol
Collect port level scheduler and binding processing, and non-generic port and common port are uniformly carried out to all non-generic ports
QOS modes can configure (such as strict priority scheduling mode, robin manner), and non-generic port and common port are total to
Bandwidth is enjoyed, most the flow of non-generic port is mapped to the purpose on physical port at last so as to reach.Logic port level scheduler
Obtained multiple subqueues are split to non-generic port queue and/or common port queue authorizes, authorized queue
Carry out subsequent treatment.
Step 103, first order burst scheduling is carried out to non-generic port queue and/or common port queue.
Each subqueue of non-generic port and common port queue are put into each register, each subqueue and
Common port equalization is scheduled according to fixed burst sizes, and burst sizes be can configure, and the time slot of scheduling is fixed, and is reduced
Conflict, while go to deduct according to burst and authorize surplus, further reduce conflict.As shown in figure 4, common port is adjusted per x cycle
Degree once, non-generic port per x/n periodic scheduling once, wherein, x is natural number, and n is register corresponding to non-generic port
Number.Common port and non-port are polled scheduling according to fixed burst, and non-generic port is entered in reg0 to regn-1
Row polling dispatching, scheduling output include following one or more：Physical port number, common port/non-generic port designations, physics
The reg labels (reg0...regn-1) of queue number, packet header and bag tail tag will, non-generic port polling.
Step 104, package-restructuring processing is carried out to the first order burst scheduling results of non-generic port queue.
The message of non-generic port can have out of order situation when first order burst is dispatched, and can be mapped to final general
Go side mouth, there can be the out of order of non-generic port bag, package-restructuring is carried out to first order burst scheduling results in the embodiment of the present invention
Processing.Package-restructuring is completed by some row FIFO, wherein, sequence FIFO is used to enter first order burst sop (packet header mark)
Row sequence, other FIFO are used to deposit the burst information that first order burst scheduler schedules come, and read the data in FIFO
When need to read sequence FIFO first, if sequence FIFO non-NULLs, according to the FIFO numberings in sequence FIFO to corresponding FIFO
Data are read until reading bag tail, again read off sequence FIFO, if non-NULL, repeat top-operation.Such as shown in Fig. 5, Bao Chong
Group processing is carried out by n FIFO, and reg0 to the regn-1 in each FIFO0...FIFOn-1 and Fig. 4 is corresponded, and is had in addition
One sequence FIFO, for recording packet header mark into FIFO0-FIFOn-1 order, if sequence FIFO non-NULLs, read
FIFO numberings read data packet into the FIFO of reference numeral therein, until reading bag tail, sequence FIFO is again read off, if
Non-NULL, repeat top-operation.
Step 105, second level burst tune is carried out to data corresponding to non-generic port queue and/or common port queue
Degree.
Package-restructuring completes a long bag of complete packet scheduling and long time space be present, the burst that flow be present, this hair
In bright embodiment using in FIFO with come with walking by the way of, section and common port in the FIFO dispatched at first carry out first
Two level burst is dispatched, and the section marking of common port and non-generic port is made a distinction, and improves the performance of system.
Still by taking Fig. 5 as an example, in order to shorten the delay that package-restructuring is brought, as long as there is burst size datas to enter in FIFO0-FIFOn-1
Row burst is dispatched, and non-generic port burst size datas and common port burst data carry out burst scheduling again, as long as
It is to come from common port and non-generic port to each burst marks, that is, ensure that the order of bag, improves scheduling effect again
Rate.As shown in fig. 6, it is dequeue schematic diagram, non-generic port data carries out package-restructuring unit after first order burst scheduling, general
Logical port data enters common port burst buffer units, and then package-restructuring unit and common port burst buffer units are by number
Transmitted according to second level burst scheduling units, carry out second level burst scheduling.
By using method provided in an embodiment of the present invention, multiple subqueues are split into non-generic port queue and are tied to
It is scheduled on non-generic port, and by increasing logic port level scheduler, makes non-generic port and common ports share band
Width is scheduled, and is solved and is treated that processing of the performance more than queue in the case of system list queue processing ability of scheduling queue is asked
Topic.Meanwhile dispatched by twin-stage burst and package-restructuring ensure that the integrality of packet, and time interval resource is made full use of, improve
The bag forward efficiency of system.
Based on also providing a kind of dress of queue scheduling with above method embodiment identical technical concept, the embodiment of the present invention
Put, as shown in fig. 7, comprises：
Column processing unit of joining the team 10, it is scheduled for enqueue to be tied into common port and/or non-generic port；
Authorisation process unit 20, for setting logic port level scheduler, institute is dispatched according to the scheduling mode being pre-configured with
State common port and non-generic port, after being split to enqueue corresponding to the non-generic port obtained multiple subqueues and/
Or common port queue corresponding to the common port is authorized, wherein, the common port and non-generic ports share band
It is wide；
First order burst scheduling units 30, deposit is put into for the subqueue that will be authorized and/common port queue
Device, and carry out first order burst scheduling；
Package-restructuring unit 40, for after the subqueue carries out first order burst scheduling, the subqueue to be write respectively
FIFO FIFOs corresponding to entering, and the packet header mark of each subqueue is recorded into FIFO order by the FIFO that sorts, according to
FIFO numberings FIFO corresponding in the sequence FIFO reads data until reading bag tail, again reads off the sequence
FIFO；
Second level burst scheduling units 50, for being carried out to the data in the FIFO and/or the common port queue
Data after first order burst scheduling carry out second level burst scheduling.
Preferably, the column processing unit 10 of joining the team is additionally operable to：Judge to join the team according to preset strategy to be classified as non-generic port
Queue or common port queue, the non-generic port queue is split into multiple subqueues, is tied on non-generic port
It is scheduled, the common port queue is tied on common port and dispatched, wherein, the non-generic port and common
Port is logic port, and each non-generic port corresponds to multiple physical ports, each common corresponding physical port in port.
Preferably, the authorisation process unit 20 is additionally operable to：In scheduler subordinate corresponding to physical port, logical end is set
Mouth level scheduler, the logic port level scheduler are corresponding with logic port.
The first order burst scheduling units 30 are additionally operable to：The common port and non-generic port are adjusted using poll
Degree mode or strict priority scheduling mode are scheduled.
The first order burst scheduling units 30 are additionally operable to：According to the burst of fixed size and time slot to subqueue and/
Or common port queue is scheduled.
The first order burst scheduling units 30 are additionally operable to：Per common port described in x periodic scheduling once, it is individual per x/n
Once, x is natural number for non-generic port described in periodic scheduling, and n is the number of register corresponding to the non-generic port.
The first order burst scheduling units 30 are additionally operable to：Export the one or more of herein below：Physical port number,
Common port/non-generic port designations, physical queue number, packet header and bag tail tag will, the register label of non-generic port polling.
The second level burst scheduling units 50 are additionally operable to：To each burst markings to indicate the burst from general
Go side mouth or non-generic port.
By using device provided in an embodiment of the present invention, multiple subqueues are split into non-generic port queue and are tied to
It is scheduled on non-generic port, and by increasing logic port level scheduler, makes non-generic port and common ports share band
Width is scheduled, and is solved and is treated that processing of the performance more than queue in the case of system list queue processing ability of scheduling queue is asked
Topic.Meanwhile dispatched by twin-stage burst and package-restructuring ensure that the integrality of packet, and time interval resource is made full use of, improve
The bag forward efficiency of system.
One of ordinary skill in the art will appreciate that all or part of step in the above method can be instructed by program
Related hardware is completed, and described program can be stored in computer-readable recording medium, such as read-only storage, disk or CD
Deng.Alternatively, all or part of step of above-described embodiment can also be realized using one or more integrated circuits.Accordingly
Ground, each module/unit in above-described embodiment can be realized in the form of hardware, can also use the shape of software function module
Formula is realized.The present invention is not restricted to the combination of the hardware and software of any particular form.
Claims (16)
- A kind of 1. method of queue scheduling, it is characterised in that including：Enqueue is tied into common port and/or non-generic port to be scheduled；Logic port level scheduler is set, according to the scheduling mode scheduling common port being pre-configured with and/or non-generic end Mouthful, corresponding to the multiple subqueues obtained after being split to enqueue corresponding to the non-generic port and/or the common port Common port queue is authorized, wherein, the common port and non-generic ports share bandwidth；The subqueue that will be authorized and/common port queue are put into register, and carry out first order burst scheduling；After the subqueue carries out first order burst scheduling, the subqueue is respectively written into corresponding FIFO FIFOs, And the packet header mark of each subqueue is recorded into FIFO order by the FIFO that sorts, according to the FIFO volumes in the sequence FIFO Number FIFO corresponding to reads data until read bag tail, again reads off the sequence FIFO；Data in the FIFO and/or the common port queue are carried out with the data after first order burst scheduling and carries out the Two level burst is dispatched.
- 2. the method as described in claim 1, it is characterised in that described that enqueue is tied to common port and/or non-generic Port be scheduled including：Joined the team according to judging preset strategy and be classified as non-generic port queue or common port queue, by the non-generic end Mouth queue splits into multiple subqueues, is tied on non-generic port and is scheduled, and the common port queue is tied to general It is scheduled on the mouth of go side, wherein, the non-generic port and common port are logic port, and each non-generic port is corresponding more Individual physical port, each common corresponding physical port in port.
- 3. the method as described in claim 1, it is characterised in that the setting logic port level scheduler includes：In scheduler subordinate corresponding to physical port, logic port level scheduler, the logic port level scheduler and logic are set Port is corresponding.
- 4. method as claimed in claim 1 or 2, it is characterised in that described in the scheduling mode scheduling that the basis is pre-configured with Common port and non-generic port include：The common port and non-generic port are scheduled using robin manner or strict priority scheduling mode.
- 5. the method as described in claim 1, it is characterised in that the progress first order burst scheduling includes：According to fixed big The small and burst of time slot is scheduled to subqueue and/or common port queue.
- 6. the method as described in claim 1, it is characterised in that the progress first order burst scheduling includes：Per x periodic scheduling once, per x/n periodic scheduling once, x is nature for the non-generic port for the common port Number, n are the number of register corresponding to the non-generic port.
- 7. the method as described in claim 1, it is characterised in that it is following interior that the progress first order burst scheduling includes output That holds is one or more：Physical port number, common port/non-generic port designations, physical queue number, packet header and bag tail tag will, The register label of non-generic port polling.
- 8. the method as described in claim 1, it is characterised in that to the data in the FIFO and/or the common port team Row, which carry out the data after first order burst scheduling, which carries out second level burst scheduling, includes：To each burst markings to indicate that the burst comes from common port or non-generic port.
- A kind of 9. device of queue scheduling, it is characterised in that including：Join the team column processing unit, be scheduled for enqueue to be tied into common port and/or non-generic port；Authorisation process unit, it is described common according to the scheduling mode scheduling being pre-configured with for setting logic port level scheduler Port and non-generic port, obtained multiple subqueues and/or described after being split to enqueue corresponding to the non-generic port Common port queue is authorized corresponding to common port, wherein, the common port and non-generic ports share bandwidth；First order burst scheduling units, register is put into for the subqueue that will be authorized and/common port queue, is gone forward side by side Row first order burst is dispatched；Package-restructuring unit, for after the subqueue carries out first order burst scheduling, the subqueue to be respectively written into correspondingly FIFO FIFOs, and by the FIFO that sorts record each subqueue packet header mark into FIFO order, according to the row FIFO numberings FIFO corresponding in sequence FIFO reads data until reading bag tail, again reads off the sequence FIFO；Second level burst scheduling units, for carrying out the first order to the data in the FIFO and/or the common port queue Data after burst scheduling carry out second level burst scheduling.
- 10. device as claimed in claim 9, it is characterised in that the column processing unit of joining the team is additionally operable to：According to preset strategy Judgement, which is joined the team, is classified as non-generic port queue or common port queue, and the non-generic port queue is split into more height teams Row, are tied on non-generic port and are scheduled, and the common port queue is tied on common port and dispatched, its In, the non-generic port and common port are logic port, and each non-generic port corresponds to multiple physical ports, each common The corresponding physical port in port.
- 11. device as claimed in claim 9, it is characterised in that the authorisation process unit is additionally operable to：It is corresponding in physical port Scheduler subordinate logic port level scheduler is set, the logic port level scheduler is corresponding with logic port.
- 12. the device as described in claim 9 or 10, it is characterised in that the first order burst scheduling units are additionally operable to：It is right The common port and non-generic port are scheduled using robin manner or strict priority scheduling mode.
- 13. device as claimed in claim 9, it is characterised in that the first order burst scheduling units are additionally operable to：According to solid The burst for determining size and time slot is scheduled to subqueue and/or common port queue.
- 14. device as claimed in claim 9, it is characterised in that the first order burst scheduling units are additionally operable to：The week per x Once, per non-generic port described in x/n periodic scheduling once, x is natural number, and n is described non-for the phase scheduling common port The number of register corresponding to common port.
- 15. device as claimed in claim 9, it is characterised in that the first order burst scheduling units are additionally operable to：Output with Lower content it is one or more：Physical port number, common port/non-generic port designations, physical queue number, packet header and bag tail tag The register label of will, non-generic port polling.
- 16. device as claimed in claim 9, it is characterised in that the second level burst scheduling units are additionally operable to：To each Burst markings are to indicate that the burst comes from common port or non-generic port.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210222139.1A CN103516621B (en) | 2012-06-29 | 2012-06-29 | The method and apparatus of queue scheduling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210222139.1A CN103516621B (en) | 2012-06-29 | 2012-06-29 | The method and apparatus of queue scheduling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103516621A CN103516621A (en) | 2014-01-15 |
| CN103516621B true CN103516621B (en) | 2017-11-17 |
Family
ID=49898684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210222139.1A Active CN103516621B (en) | 2012-06-29 | 2012-06-29 | The method and apparatus of queue scheduling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103516621B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113328960B (en) * | 2020-02-28 | 2023-11-17 | 华为技术有限公司 | Queue cache management method, device, storage medium and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1411211A (en) * | 2002-04-17 | 2003-04-16 | 华为技术有限公司 | Ethernet exchange chip output queue management and dispatching method and device |
| CN1866927A (en) * | 2006-05-08 | 2006-11-22 | 国家数字交换系统工程技术研究中心 | Information switching realizing system and method and scheduling algorithm |
| CN101478483A (en) * | 2009-01-08 | 2009-07-08 | 中国人民解放军信息工程大学 | Method for implementing packet scheduling in switch equipment and switch equipment |
-
2012
- 2012-06-29 CN CN201210222139.1A patent/CN103516621B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1411211A (en) * | 2002-04-17 | 2003-04-16 | 华为技术有限公司 | Ethernet exchange chip output queue management and dispatching method and device |
| CN1866927A (en) * | 2006-05-08 | 2006-11-22 | 国家数字交换系统工程技术研究中心 | Information switching realizing system and method and scheduling algorithm |
| CN101478483A (en) * | 2009-01-08 | 2009-07-08 | 中国人民解放军信息工程大学 | Method for implementing packet scheduling in switch equipment and switch equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103516621A (en) | 2014-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105005546B (en) | A kind of asynchronous AXI bus structures of built-in intersection point queue | |
| TWI280011B (en) | Store and forward switch device, system and method | |
| CN102185750B (en) | Packaging body | |
| CN106713185A (en) | Load balancing method and apparatus of multi-core CPU | |
| CN102508808B (en) | System and method for realizing communication of master chip and extended chip | |
| US7796629B1 (en) | Packet switch with configurable bandwidth allocation precision | |
| CN102667742B (en) | For the wireless electric-controlled making sheet of software-defined radio platform | |
| CN102204183A (en) | Message order-preserving processing method, order-preserving coprocessor and network equipment | |
| CN109784930A (en) | A kind of processing method, device, electronic equipment and the medium of block chain transaction data | |
| CN110505653A (en) | A kind of method, equipment and the computer storage medium of service quality control | |
| WO1994008308A1 (en) | Method and apparatus for processing data within stations of a communication network | |
| CN104798010B (en) | At least part of serial storage protocol compliant frame conversion | |
| CZ110496A3 (en) | Apparatus for batched data processing | |
| US20100098104A1 (en) | Switching device | |
| CN109672628A (en) | A kind of V2X data package processing method, device, equipment and storage medium | |
| CN108279927A (en) | The multichannel command control method and system, controller of adjustable instruction priority | |
| CN105656807A (en) | Network chip multi-channel data transmission method and transmission device | |
| CN108834090A (en) | A kind of assistance information transmission method and device | |
| CN103049240A (en) | Peripheral component interconnect express (PCI-E) device and data receiving reordering method thereof | |
| CN108366430A (en) | The method and terminal device of scheduling request | |
| CN110290187A (en) | Transmission method and device, storage medium, the electronic device of data information | |
| CN103516621B (en) | The method and apparatus of queue scheduling | |
| JP3698079B2 (en) | DATA TRANSFER METHOD, DATA TRANSFER DEVICE, AND PROGRAM | |
| CN110113781A (en) | The reporting of Buffer Status Report, resource allocation methods, terminal and the network equipment | |
| CN110519178A (en) | Low time delay data processing method, apparatus and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20140115 Assignee: SANECHIPS TECHNOLOGY Co.,Ltd. Assignor: ZTE Corp. Contract record no.: 2015440020319 Denomination of invention: Queue scheduling method and device License type: Common License Record date: 20151123 |
|
| LICC | Enforcement, change and cancellation of record of contracts on the licence for exploitation of a patent or utility model | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221123 Address after: 518055 Zhongxing Industrial Park, Liuxian Avenue, Xili street, Nanshan District, Shenzhen City, Guangdong Province Patentee after: SANECHIPS TECHNOLOGY Co.,Ltd. Address before: 518057 Ministry of justice, Zhongxing building, South Science and technology road, Nanshan District hi tech Industrial Park, Shenzhen, Guangdong Patentee before: ZTE Corp. |
|
| TR01 | Transfer of patent right |