CN102231697A - Bandwidth dispatching method of message queues as well as message reporting method and device - Google Patents
Bandwidth dispatching method of message queues as well as message reporting method and device Download PDFInfo
- Publication number
- CN102231697A CN102231697A CN2011101636754A CN201110163675A CN102231697A CN 102231697 A CN102231697 A CN 102231697A CN 2011101636754 A CN2011101636754 A CN 2011101636754A CN 201110163675 A CN201110163675 A CN 201110163675A CN 102231697 A CN102231697 A CN 102231697A
- Authority
- CN
- China
- Prior art keywords
- bandwidth
- formation
- guarantee
- message
- queue
- 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.)
- Pending
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a bandwidth dispatching method of message queues as well as a message reporting method and device, wherein the bandwidth dispatching method of the message queues comprises the following steps: respectively setting the minimum bandwidth guarantee value and the maximum bandwidth guarantee value for each queue needing guaranteed bandwidth; respectively setting a weight ratio for each queue; distributing the bandwidth which is at least equal to the bandwidth of the minimum bandwidth guarantee value of the queue to each queue needing guaranteed bandwidth; when the spare queue exists, distributing the bandwidth which is distributed to the spare queue to the non-spare queue according to the weight ratio; and if the spare queue is the queue needing guaranteed bandwidth, maintaining the bandwidth which is at least equal to the minimum bandwidth guarantee value of the queue for the queue, wherein the bandwidth needed to be distributed to the queue needing the guaranteed bandwidth is not beyond the maximum bandwidth guarantee value of the queue. According to the invention, the queues needing the guaranteed bandwidth can be ensured to occupy the reserved bandwidth and the utilization rate of bandwidth resources is improved.
Description
Technical field
The present invention relates to network field, relate in particular to a kind of bandwidth scheduling method, message reporting method and device thereof of message queue.
Background technology
Development along with communication network, communication protocol or standard are constantly weeded out the old and bring forth the new, and it is also more and more higher to performance demands, for example the telecommunications Ethernet requires to be lower than 50ms to the looped network switching time, and the participation that all needs CPU device on the communication equipment such as numerous standards such as G8031/G8032 or privately owned looped network agreement and other important agreement; In existing network, the form of network attack is also more diversified, and in numerous network attacks, CPU to communication equipment attacks more and more serious especially, too much attack message sends to CPU, cause cpu load overweight, can't handle normal protocol massages, thereby cause huge infringement network.Therefore,, guaranteeing service quality, strengthen the CPU anti-attack ability and select suitable QoS(Quality of Service, service quality the message of submitting CPU Differentiated Services how) strategy is particularly important.
The main at present a kind of method that adopts is simply to connect the speed limit of doing on the cpu port based on formation that goes out.The QoS scheduling strategy generally adopts the SP(absolute priority) or SP+WRR(weighting circulation) scheduling method, needs guaranteeing the SP scheduling method is used in the formation of the high priority of bandwidth, SP or WRR scheduling method are carried out in low formation to common priority.
The said method defective clearly owing to guarantee at needs all to have done speed limit in the formation of bandwidth, the size of speed limit is exactly the bandwidth value of reserving for this formation, so the bandwidth that each queuing data stream takies can not surpass the restriction of RSVP.Because needing the scheduling method of the formation of assurance bandwidth is the SP pattern, so even under congested situation, also can make the formation that needs to guarantee bandwidth preferentially obtain scheduling; But, because speed limit has all been carried out in each formation, so even even need have one or more formations that the free time is arranged in the formation of assurance bandwidth, this part idle bandwidth can not be distributed to other formation use, thereby the waste of bandwidth resources caused.
Summary of the invention
The technical problem to be solved in the present invention is how to guarantee that needs guarantee the bandwidth that the formation of bandwidth can occupy reservation all the time, also can improve the utilization rate of bandwidth resources.
In order to address the above problem, the invention provides a kind of bandwidth scheduling method of message queue, comprising:
For each need guarantee the formation of bandwidth minimum bandwidth guarantee value and maximum bandwidth guarantee value are set respectively; For individual queue is provided with weight proportion respectively;
For need guaranteeing the queue assignment of bandwidth, each equals the bandwidth of its minimum bandwidth guarantee value at least;
When having idle queues, the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Wherein, distribute to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
Further, need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set for each and for each need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the port that connects cpu port and goes out speed limit.
The present invention also provides a kind of bandwidth scheduling device of message queue, comprising:
Module is set, and the formation that is used to each to need to guarantee bandwidth is provided with minimum bandwidth guarantee value and maximum bandwidth guarantee value respectively; For individual queue is provided with weight proportion respectively;
First bandwidth allocation module is used to each to need to guarantee that the queue assignment of bandwidth equals the bandwidth of its minimum bandwidth guarantee value at least;
Second bandwidth allocation module is used for when having idle queues, and the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Described first, second bandwidth allocation module is distributed to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
Further, describedly be provided with that module need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set for each and for each need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the port that connects cpu port and goes out speed limit.
The present invention also provides a kind of message reporting method, comprising:
With on send to CPU message distribute into different formations according to the internal priority of this message;
For each need guarantee the formation of bandwidth minimum bandwidth guarantee value and maximum bandwidth guarantee value are set respectively; For individual queue is provided with weight proportion respectively;
For need guaranteeing the queue assignment of bandwidth, each equals the bandwidth of its minimum bandwidth guarantee value at least;
Adopt weighting round-robin scheduling pattern, the message in the individual queue is adopted as on the bandwidth resources of this queue assignment and gives CPU;
When having idle queues, the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Wherein, distribute to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
Further, described method also comprises:
The port that connects cpu port is set speed limit;
For each need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set and go out speed limit for each port that need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to described connection cpu port.
Further, described will on send to CPU message distribute according to the internal priority of this message and also comprise step in the step of into different formations:
Revise the internal priority of this message according to the reason of message.
The present invention also provides a kind of message reporting device, comprising:
Queue management module, be used for on send to CPU message distribute into different formations according to the internal priority of this message;
Module is set, and the formation that is used to each to need to guarantee bandwidth is provided with minimum bandwidth guarantee value and maximum bandwidth guarantee value respectively; For individual queue is provided with weight proportion respectively;
First bandwidth allocation module is used to each to need to guarantee that the queue assignment of bandwidth equals the bandwidth of its minimum bandwidth guarantee value at least;
Sending module is used to adopt weighting round-robin scheduling pattern, the message in the individual queue is adopted as on the bandwidth resources of this queue assignment and gives CPU;
Second bandwidth allocation module is used for when having idle queues, and the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Described first, second bandwidth allocation module is distributed to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
Further, the described module that is provided with also is used to be provided with the port that connects cpu port and goes out speed limit; For each need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set and go out speed limit for each port that need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to described connection cpu port.
Further, described queue management module also is used for revising according to the reason of message the internal priority of this message.
Technical scheme of the present invention both can be reserved minimum bandwidth for each guarantee formation of bandwidth, and when can make the formation bandwidth of assurance idle, this part bandwidth is allocated to other formations and used, thereby avoids the waste of bandwidth; Simultaneously can make the CPU total bandwidth be no more than CPU peak load bandwidth, effectively ensure CPU service quality.
Description of drawings
Fig. 1 is the schematic flow sheet of bandwidth scheduling method of the message queue of embodiment one;
Fig. 2 is the schematic flow sheet of the message reporting method of embodiment three;
Fig. 3 is one of schematic flow sheet of example among the embodiment three;
Fig. 4 be example among the embodiment three schematic flow sheet two.
Embodiment
Below in conjunction with drawings and Examples technical scheme of the present invention is described in detail.
Need to prove that if do not conflict, each feature among the embodiment of the invention and the embodiment can mutually combine, all within protection scope of the present invention.In addition, can in computer system, carry out in the step shown in the flow chart of accompanying drawing such as a set of computer-executable instructions, and, though there is shown logical order in flow process, but in some cases, can carry out step shown or that describe with the order that is different from herein.
Embodiment one, and a kind of bandwidth scheduling method of message queue as shown in Figure 1, comprising:
For each need guarantee the formation of bandwidth minimum bandwidth guarantee value and maximum bandwidth guarantee value are set respectively; For individual queue is provided with weight proportion respectively;
For need guaranteeing the queue assignment of bandwidth, each equals the bandwidth of its minimum bandwidth guarantee value at least;
When having idle queues, the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Wherein, distribute to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
In the present embodiment, when the minimum bandwidth guarantee value is set with the maximum bandwidth guarantee value can but be not limited to satisfy following condition: for each needs guarantees minimum bandwidth guarantee value sum that the formation of bandwidth is set and guarantees that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the port that is connected cpu port and goes out speed limit for each needs.
In the present embodiment, described minimum bandwidth guarantee value is the minimum operable bandwidth of formation under congestion situation, the scheduling method that so will not need to guarantee the formation of bandwidth is configured to the SP pattern, also can under congested situation, provide and submit the bandwidth resource of message to CPU, can assurance need guarantee the bandwidth that the formation of bandwidth can occupy reservation all the time, thereby when forwarding the forwarding data to from the free time, can switch fast.Described maximum bandwidth guarantee value has limited the bandwidth utilized of formation maximum, thereby makes when selecting for use SP queue scheduling pattern and high-priority queue congested, is unlikely to distribute very little bandwidth to give Low Priority Queuing, and causes Low Priority Queuing " to be died of hunger "; The maximum bandwidth guarantee value is set, and combination is disposed, and scheduling method is the WRR pattern between the formation that needs the assurance bandwidth, making needs to guarantee that the formation bandwidth of bandwidth is in the time of the free time, this part bandwidth dispatches for each formation that need guarantee bandwidth by the WRR weight proportion of setting, share remaining bandwidth, thereby avoid the waste of bandwidth, make that the formation of low priority also can be used its bandwidth reserved under the high-priority queue congestion situation.Connecting the enterprising uplink bandwidth restriction of cpu port, make the CPU total bandwidth be no more than CPU peak load bandwidth, avoid cpu load overweight, can't correctly handle the CPU message of submitting.
Embodiment two, and a kind of bandwidth scheduling device of message queue comprises:
Module is set, and the formation that is used to each to need to guarantee bandwidth is provided with minimum bandwidth guarantee value and maximum bandwidth guarantee value respectively; For individual queue is provided with weight proportion respectively;
First bandwidth allocation module is used to each to need to guarantee that the queue assignment of bandwidth equals the bandwidth of its minimum bandwidth guarantee value at least;
Second bandwidth allocation module is used for when having idle queues, and the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Described first, second bandwidth allocation module is distributed to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
In the present embodiment, described be provided with module when the minimum bandwidth guarantee value is set with the maximum bandwidth guarantee value can but be not limited to satisfy following condition: for each needs guarantees minimum bandwidth guarantee value sum that the formation of bandwidth is set and guarantees that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the port that is connected cpu port and goes out speed limit for each needs.
Other realizes that details can be with embodiment one.
Embodiment three, and a kind of message reporting method as shown in Figure 2, comprising:
With on send to CPU message distribute into different formations according to the internal priority of this message;
For each need guarantee the formation of bandwidth minimum bandwidth guarantee value and maximum bandwidth guarantee value are set respectively; For individual queue is provided with weight proportion respectively;
For need guaranteeing the queue assignment of bandwidth, each equals the bandwidth of its minimum bandwidth guarantee value at least;
Adopt weighting round-robin scheduling pattern, the message in the individual queue is adopted as on the bandwidth resources of this queue assignment and gives CPU;
When having idle queues, the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Wherein, distribute to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
In the present embodiment, described method can also comprise:
The port that connects cpu port is set speed limit;
When the minimum bandwidth guarantee value is set with the maximum bandwidth guarantee value can but be not limited to satisfy following condition: for each needs guarantees minimum bandwidth guarantee value sum that the formation of bandwidth is set and guarantees that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the described port that is connected cpu port and goes out speed limit for each needs.
In the present embodiment, described will on send to CPU message distribute according to the internal priority of this message in the step of into different formations and can also comprise step:
Revise the internal priority of this message according to the reason of message.
In the present embodiment, can set in advance the corresponding relation between a variety of causes and the priority, the internal priority of message is revised as this reason corresponding priorities according to the reason of message; Also can set in advance the corresponding relation between the operation of a variety of causes and priority modification, revise the internal priority of this message according to the reason of message, such as the reason correspondence that has is that the internal priority of message is improved one or multistage, the reason correspondence that has be that the internal priority of message is reduced by one or multistage, the reason correspondence that has be the internal priority that does not change message.
In the present embodiment, described will on send to CPU message distribute according to the internal priority of this message in the step of into different formations, a plurality of engines identification messages that can be by hardware also are provided with the message internal priority; By use ACL(Access Control List at the outgoing direction that connects cpu port, Access Control List (ACL)) rule, promptly saved valuable hardware ACL clauses and subclauses, also can attack message have been filtered or the reduction message priority by the application of ACL matched rule flexibly.
In the example of present embodiment, described will on send to CPU message distribute the step of into different formations specifically can to may further comprise the steps as shown in Figure 3 according to the internal priority of this message:
Step 301: according to the configuration of message entry port, according to trusting COS(Class of Service, the grade of service), DSCP(Differentiated Services Code Point, differentiated services code points) or different pattern such as port priority, (there are mapping relations in the formation of message internal priority and outbound port to revise the message internal priority, thereby the formation that decision enters), trust COS such as port, then equipment can be according to entering message VLAN(Virtual Local Area Network, VLAN) the COS value in the label, the internal priority of decision message, other trust modes are similar.
Step 302: the acl rule setting of Inbound mainly contains two purposes: the one, and can be with some protocol massages, action by acl rule QoS is submitted CPU with message, also can revise the message internal priority, make message enter the expection formation by the action of acl rule QoS; Be used on the other hand to prevent that attack message from submitting CPU or reducing the internal priority of attack message, make attack message enter Low Priority Queuing.Carrying out the configuration of attack protection ACL on Inbound, be not supported on the equipment that connects application outgoing direction acl rule on the cpu port for some, is an effective solution.
Step 303: can reach the purpose of step 302 equally by the outgoing direction acl rule that connects cpu port is set, but compare step 302, this step can significantly reduce the use clauses and subclauses of acl rule, thereby has saved valuable hardware ACL resource.Because present numerous chips have all been supported the acl rule of outgoing direction, and field that can the flexible configuration coupling, such as based on two layers, three layers and User Defined are based on the field of message skew.So can effectively avoid numerous network attack messages by disposing this step.
Step 304: can also revise the internal priority of this message according to the type of submitting the message of CPU by this step, such as, according to submitting the CPU type of message, then this type of message can be configured in the lower formation of priority for being mirrored to the CPU class; Can also revise the internal priority of this message according to the reason of submitting the message of CPU.
Step 305: message enters corresponding formation according to the mapping relations of internal priority and actual dequeue, and when the connection cpu port was congested, equipment just can be dispatched the message that enters different queue according to the configured QOS scheduling strategy.
In the above-mentioned example, described will on send to CPU message specifically can may further comprise the steps as shown in Figure 4 distribute the step of into different formations according to the internal priority of this message after:
Step 401: the port that configuration connects cpu port goes out speed limit (PortRate), and the value that goes out speed limit should be less than CPU peak load ability, makes CPU under with PortRate speed receiving situation, does not influence the normal operation of system business.
Step 402: configuration connects minimum bandwidth guarantee value MinRate and the maximum bandwidth guarantee value MaxRate of the formation N of cpu port to formation M.Wherein, for needing to guarantee the formation of bandwidth, MinRate is the individual queue bandwidth reserved to N, and MinRate to M
N+ MinRate
N-1+ ... + MinRate
M＜=PortRate, MaxRate
N＜=PortRate.
Even the minimum bandwidth guarantee value makes under congested situation, the minimum bandwidth that each needs the formation of assurance bandwidth all can obtain reserving.If all maximum bandwidth guarantee value and minimum bandwidth guarantee value are provided with consistent, even there is idle queues and since other formation maximum configured also be minimum bandwidth guarantee value (bandwidth reserved), so can't share the free time bandwidth.So formation maximum bandwidth guarantee value is set to be less than or equal to the maximum speed limit of port, purpose is for after having satisfied the minimum bandwidth guarantee, shares remaining bandwidth.And according to the situation of submitting the CPU message, it is easier and accurate with respect to configuration individual queue weight to set a bandwidth reserved.
Step 403: the scheduling method that configuration connects cpu port is WRR, after having used minimum bandwidth assurance and maximum bandwidth assurance function, because for bandwidth has been reserved in the formation of high priority, so, also can guarantee minimum utilizable bandwidth even do not use the SP scheduling method.
Step 404: it is W that configuration connects cpu port individual queue weight ratio
n: W
N-1W
1: W
0(annotate: W
nBe the weight of formation n, by that analogy).According to the analysis of each formation operating position, the proportion between can each formation of flexible configuration makes and is satisfying under the prerequisite of minimum bandwidth, shares remaining bandwidth.
Embodiment four, and a kind of message reporting device comprises:
Queue management module, be used for on send to CPU message distribute into different formations according to the internal priority of this message;
Module is set, and the formation that is used to each to need to guarantee bandwidth is provided with minimum bandwidth guarantee value and maximum bandwidth guarantee value respectively; For individual queue is provided with weight proportion respectively;
First bandwidth allocation module is used to each to need to guarantee that the queue assignment of bandwidth equals the bandwidth of its minimum bandwidth guarantee value at least;
Sending module is used to adopt weighting round-robin scheduling pattern, the message in the individual queue is adopted as on the bandwidth resources of this queue assignment and gives CPU;
Second bandwidth allocation module is used for when having idle queues, and the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Described first, second bandwidth allocation module is distributed to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
In the present embodiment, the described module that is provided with can also be used to be provided with the port that connects cpu port and goes out speed limit; Described be provided with module when the minimum bandwidth guarantee value is set with the maximum bandwidth guarantee value can but be not limited to satisfy following condition: for each needs guarantees minimum bandwidth guarantee value sum that the formation of bandwidth is set and guarantees that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the described port that is connected cpu port and goes out speed limit for each needs.
In the present embodiment, described queue management module can also be used for revising according to the reason of message the internal priority of this message.
In the present embodiment, can set in advance the corresponding relation between a variety of causes and the priority, described queue management module is revised as this reason corresponding priorities according to the reason of message with the internal priority of message; Also can set in advance the corresponding relation between the operation of a variety of causes and priority modification, described queue management module is revised the internal priority of this message according to the reason of message, such as the reason correspondence that has is that the internal priority of message is improved one or multistage, the reason correspondence that has be that the internal priority of message is reduced by one or multistage, the reason correspondence that has be the internal priority that does not change message.
Other realizes that details can be with embodiment three.
One of ordinary skill in the art will appreciate that all or part of step in the said method can instruct related hardware to finish by program, described program can be stored in the computer-readable recording medium, as read-only memory, disk or CD etc.Alternatively, all or part of step of the foregoing description also can use one or more integrated circuits to realize.Correspondingly, each the module/unit in the foregoing description can adopt the form of hardware to realize, also can adopt the form of software function module to realize.The present invention is not restricted to the combination of the hardware and software of any particular form.
Certainly; the present invention also can have other various embodiments; under the situation that does not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection range of claim of the present invention.
Claims (10)
1. the bandwidth scheduling method of a message queue comprises:
For each need guarantee the formation of bandwidth minimum bandwidth guarantee value and maximum bandwidth guarantee value are set respectively; For individual queue is provided with weight proportion respectively;
For need guaranteeing the queue assignment of bandwidth, each equals the bandwidth of its minimum bandwidth guarantee value at least;
When having idle queues, the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Wherein, distribute to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
2. the method for claim 1 is characterized in that:
For each need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set and for each need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the port that connects cpu port and goes out speed limit.
3. the bandwidth scheduling device of a message queue is characterized in that, comprising:
Module is set, and the formation that is used to each to need to guarantee bandwidth is provided with minimum bandwidth guarantee value and maximum bandwidth guarantee value respectively; For individual queue is provided with weight proportion respectively;
First bandwidth allocation module is used to each to need to guarantee that the queue assignment of bandwidth equals the bandwidth of its minimum bandwidth guarantee value at least;
Second bandwidth allocation module is used for when having idle queues, and the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Described first, second bandwidth allocation module is distributed to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
4. device as claimed in claim 3 is characterized in that:
Describedly be provided with that module need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set for each and for each need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to the port that connects cpu port and goes out speed limit.
5. message reporting method comprises:
With on send to CPU message distribute into different formations according to the internal priority of this message;
For each need guarantee the formation of bandwidth minimum bandwidth guarantee value and maximum bandwidth guarantee value are set respectively; For individual queue is provided with weight proportion respectively;
For need guaranteeing the queue assignment of bandwidth, each equals the bandwidth of its minimum bandwidth guarantee value at least;
Adopt weighting round-robin scheduling pattern, the message in the individual queue is adopted as on the bandwidth resources of this queue assignment and gives CPU;
When having idle queues, the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Wherein, distribute to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
6. method as claimed in claim 5 is characterized in that, also comprises:
The port that connects cpu port is set speed limit;
For each need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set and go out speed limit for each port that need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to described connection cpu port.
7. as claim 5 or 6 described methods, it is characterized in that, described will on send to CPU message distribute according to the internal priority of this message and also comprise step in the step of into different formations:
Revise the internal priority of this message according to the reason of message.
8. a message reporting device is characterized in that, comprising:
Queue management module, be used for on send to CPU message distribute into different formations according to the internal priority of this message;
Module is set, and the formation that is used to each to need to guarantee bandwidth is provided with minimum bandwidth guarantee value and maximum bandwidth guarantee value respectively; For individual queue is provided with weight proportion respectively;
First bandwidth allocation module is used to each to need to guarantee that the queue assignment of bandwidth equals the bandwidth of its minimum bandwidth guarantee value at least;
Sending module is used to adopt weighting round-robin scheduling pattern, the message in the individual queue is adopted as on the bandwidth resources of this queue assignment and gives CPU;
Second bandwidth allocation module is used for when having idle queues, and the bandwidth of distributing to this idle queues is distributed to not idle formation according to described weight proportion; If idle queues then keeps the bandwidth that equals its minimum bandwidth guarantee value at least for this formation for needing to guarantee the formation of bandwidth;
Described first, second bandwidth allocation module is distributed to the maximum bandwidth guarantee value that bandwidth that needs guarantee the formation of bandwidth is no more than this formation.
9. device as claimed in claim 8 is characterized in that:
The described module that is provided with also is used to be provided with the port that connects cpu port and goes out speed limit; For each need guarantee minimum bandwidth guarantee value sum that the formation of bandwidth is set and go out speed limit for each port that need guarantee that the set maximum bandwidth guarantee value of formation of bandwidth all is less than or equal to described connection cpu port.
10. install as claimed in claim 8 or 9, it is characterized in that:
Described queue management module also is used for revising according to the reason of message the internal priority of this message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101636754A CN102231697A (en) | 2011-06-17 | 2011-06-17 | Bandwidth dispatching method of message queues as well as message reporting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101636754A CN102231697A (en) | 2011-06-17 | 2011-06-17 | Bandwidth dispatching method of message queues as well as message reporting method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102231697A true CN102231697A (en) | 2011-11-02 |
Family
ID=44844235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011101636754A Pending CN102231697A (en) | 2011-06-17 | 2011-06-17 | Bandwidth dispatching method of message queues as well as message reporting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102231697A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102497259A (en) * | 2011-12-02 | 2012-06-13 | 中国科学院微电子研究所 | Subcarrier distribution method and device applied to power line communication |
| CN103812750A (en) * | 2014-02-21 | 2014-05-21 | 上海斐讯数据通信技术有限公司 | Message receiving and sending protecting system and method for CPU of data communication equipment |
| CN104396187A (en) * | 2012-07-31 | 2015-03-04 | 惠普发展公司，有限责任合伙企业 | Bandwidth guarantee and work conservation |
| CN104869079A (en) * | 2015-06-11 | 2015-08-26 | 烽火通信科技股份有限公司 | Queue scheduling method and device based on dynamic weighted round robin |
| CN106559354A (en) * | 2015-09-28 | 2017-04-05 | 中兴通讯股份有限公司 | A kind of method and device for preventing CPU packet congestions |
| CN106789724A (en) * | 2016-01-29 | 2017-05-31 | 新华三技术有限公司 | A kind of message data retransmission method and device |
| CN107251634A (en) * | 2015-08-04 | 2017-10-13 | 华为技术有限公司 | The method and apparatus for controlling schedules message |
| CN108040019A (en) * | 2017-12-21 | 2018-05-15 | 杭州迪普科技股份有限公司 | The method and device of message forwarding |
| CN109039953A (en) * | 2018-07-24 | 2018-12-18 | 新华三技术有限公司 | bandwidth scheduling method and device |
| CN109391555A (en) * | 2017-08-08 | 2019-02-26 | 迈普通信技术股份有限公司 | Method for dispatching message, device and communication equipment |
| CN110609742A (en) * | 2019-09-25 | 2019-12-24 | 苏州浪潮智能科技有限公司 | Method and device for configuring queues of Kubernetes scheduler |
| CN110855685A (en) * | 2019-11-18 | 2020-02-28 | 苏州盛科科技有限公司 | Method and device for realizing CoPP (co-polypropylene) by multiple Slice exchange chips |
| CN111131083A (en) * | 2019-12-27 | 2020-05-08 | 广东浪潮大数据研究有限公司 | Method, device and equipment for data transmission between nodes and computer readable storage medium |
| WO2022062978A1 (en) * | 2020-09-27 | 2022-03-31 | 华为技术有限公司 | Data processing method and electronic device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852228A (en) * | 2005-09-28 | 2006-10-25 | 华为技术有限公司 | Band-width or buffer-storage distribution processing method in communication network |
| CN1901505A (en) * | 2006-07-17 | 2007-01-24 | 华为技术有限公司 | Distributing method for VOIP service band width |
| CN101577670A (en) * | 2008-05-07 | 2009-11-11 | 华为技术有限公司 | Method, device and system for bandwidth allocation |
| CN101616096A (en) * | 2009-07-31 | 2009-12-30 | 中兴通讯股份有限公司 | Array dispatching method and device |
| CN101651615A (en) * | 2009-09-14 | 2010-02-17 | 中兴通讯股份有限公司 | Method and device for scheduling messages |
| CN101707807A (en) * | 2009-12-14 | 2010-05-12 | 中兴通讯股份有限公司 | Method and device for scheduling service queue |
| CN101826999A (en) * | 2010-04-26 | 2010-09-08 | 瑞斯康达科技发展股份有限公司 | Method and device for online message flow monitoring and bandwidth compensation |
-
2011
- 2011-06-17 CN CN2011101636754A patent/CN102231697A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852228A (en) * | 2005-09-28 | 2006-10-25 | 华为技术有限公司 | Band-width or buffer-storage distribution processing method in communication network |
| CN1901505A (en) * | 2006-07-17 | 2007-01-24 | 华为技术有限公司 | Distributing method for VOIP service band width |
| CN101577670A (en) * | 2008-05-07 | 2009-11-11 | 华为技术有限公司 | Method, device and system for bandwidth allocation |
| CN101616096A (en) * | 2009-07-31 | 2009-12-30 | 中兴通讯股份有限公司 | Array dispatching method and device |
| CN101651615A (en) * | 2009-09-14 | 2010-02-17 | 中兴通讯股份有限公司 | Method and device for scheduling messages |
| CN101707807A (en) * | 2009-12-14 | 2010-05-12 | 中兴通讯股份有限公司 | Method and device for scheduling service queue |
| CN101826999A (en) * | 2010-04-26 | 2010-09-08 | 瑞斯康达科技发展股份有限公司 | Method and device for online message flow monitoring and bandwidth compensation |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102497259A (en) * | 2011-12-02 | 2012-06-13 | 中国科学院微电子研究所 | Subcarrier distribution method and device applied to power line communication |
| CN104396187B (en) * | 2012-07-31 | 2017-08-25 | 慧与发展有限责任合伙企业 | The method and device that Bandwidth guaranteed and work are kept |
| CN104396187A (en) * | 2012-07-31 | 2015-03-04 | 惠普发展公司，有限责任合伙企业 | Bandwidth guarantee and work conservation |
| US9794185B2 (en) | 2012-07-31 | 2017-10-17 | Hewlett Packard Enterprise Development Lp | Bandwidth guarantee and work conservation |
| CN103812750A (en) * | 2014-02-21 | 2014-05-21 | 上海斐讯数据通信技术有限公司 | Message receiving and sending protecting system and method for CPU of data communication equipment |
| CN103812750B (en) * | 2014-02-21 | 2020-04-21 | 上海斐讯数据通信技术有限公司 | System and method for protecting data communication equipment CPU receiving and transmitting message |
| CN104869079A (en) * | 2015-06-11 | 2015-08-26 | 烽火通信科技股份有限公司 | Queue scheduling method and device based on dynamic weighted round robin |
| CN104869079B (en) * | 2015-06-11 | 2018-03-20 | 烽火通信科技股份有限公司 | Array dispatching method and device based on dynamic weighting round-robin method |
| CN107251634A (en) * | 2015-08-04 | 2017-10-13 | 华为技术有限公司 | The method and apparatus for controlling schedules message |
| CN107251634B (en) * | 2015-08-04 | 2019-12-24 | 华为技术有限公司 | Method and device for controlling scheduling message |
| US10389648B2 (en) | 2015-08-04 | 2019-08-20 | Huawei Technologies Co., Ltd. | Method and apparatus for controlling scheduling packet |
| CN106559354A (en) * | 2015-09-28 | 2017-04-05 | 中兴通讯股份有限公司 | A kind of method and device for preventing CPU packet congestions |
| CN106789724A (en) * | 2016-01-29 | 2017-05-31 | 新华三技术有限公司 | A kind of message data retransmission method and device |
| CN106789724B (en) * | 2016-01-29 | 2021-10-15 | 新华三技术有限公司 | Message data forwarding method and device |
| CN109391555A (en) * | 2017-08-08 | 2019-02-26 | 迈普通信技术股份有限公司 | Method for dispatching message, device and communication equipment |
| CN109391555B (en) * | 2017-08-08 | 2022-08-12 | 迈普通信技术股份有限公司 | Message scheduling method and device and communication equipment |
| CN108040019A (en) * | 2017-12-21 | 2018-05-15 | 杭州迪普科技股份有限公司 | The method and device of message forwarding |
| CN109039953A (en) * | 2018-07-24 | 2018-12-18 | 新华三技术有限公司 | bandwidth scheduling method and device |
| CN109039953B (en) * | 2018-07-24 | 2022-06-10 | 新华三技术有限公司 | Bandwidth scheduling method and device |
| CN110609742A (en) * | 2019-09-25 | 2019-12-24 | 苏州浪潮智能科技有限公司 | Method and device for configuring queues of Kubernetes scheduler |
| CN110609742B (en) * | 2019-09-25 | 2023-01-06 | 苏州浪潮智能科技有限公司 | Method and device for configuring queues of Kubernetes scheduler |
| CN110855685A (en) * | 2019-11-18 | 2020-02-28 | 苏州盛科科技有限公司 | Method and device for realizing CoPP (co-polypropylene) by multiple Slice exchange chips |
| CN110855685B (en) * | 2019-11-18 | 2021-08-27 | 苏州盛科科技有限公司 | Method and device for realizing CoPP (co-polypropylene) by multiple Slice exchange chips |
| CN111131083A (en) * | 2019-12-27 | 2020-05-08 | 广东浪潮大数据研究有限公司 | Method, device and equipment for data transmission between nodes and computer readable storage medium |
| CN111131083B (en) * | 2019-12-27 | 2023-02-28 | 广东浪潮大数据研究有限公司 | Method, device and equipment for data transmission between nodes and computer readable storage medium |
| WO2022062978A1 (en) * | 2020-09-27 | 2022-03-31 | 华为技术有限公司 | Data processing method and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102231697A (en) | Bandwidth dispatching method of message queues as well as message reporting method and device | |
| US7936770B1 (en) | Method and apparatus of virtual class of service and logical queue representation through network traffic distribution over multiple port interfaces | |
| US8553543B2 (en) | Traffic shaping method and device | |
| US11516151B2 (en) | Dynamically switching queueing systems for network switches | |
| EP2608467B1 (en) | System and method for hierarchical adaptive dynamic egress port and queue buffer management | |
| US20080196033A1 (en) | Method and device for processing network data | |
| US8284789B2 (en) | Methods and apparatus for providing dynamic data flow queues | |
| CN107454015B (en) | OF-DiffServ model-based QoS control method and system | |
| JP7288980B2 (en) | Quality of Service in Virtual Service Networks | |
| EP2362589B1 (en) | Priority and source aware packet memory reservation and flow control | |
| CN101471854A (en) | Method and device for forwarding message | |
| Homg et al. | An adaptive approach to weighted fair queue with QoS enhanced on IP network | |
| US20150103646A1 (en) | Allocating network bandwith | |
| CN102934403A (en) | Controlling data transmission over a network | |
| CN101272338B (en) | Method for port band width configuration on non-line speed interface plate and non-line speed interface plate | |
| CN112165435A (en) | Bidirectional flow control method and system based on network service quality of virtual machine | |
| CN109922003A (en) | A kind of data transmission method for uplink, system and associated component | |
| EP1978682B9 (en) | QoS CONTROL METHOD AND SYSTEM | |
| Apostolaki et al. | FB: A flexible buffer management scheme for data center switches | |
| CN110753007B (en) | QoS-based flow strategy configuration method and device | |
| CN113765796A (en) | Flow forwarding control method and device | |
| JP2006094304A (en) | Transmission band control method and transmission band control system | |
| CN103973590A (en) | QoS (Quality of Service) scheduling method and QoS scheduling device | |
| WO2024011907A1 (en) | Data scheduling method, and electronic device and storage medium | |
| Liu et al. | Deployment of Asynchronous Traffic Shapers in Data Center Networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20111102 |