CN1787483A - Flow controlling method - Google Patents
Flow controlling method Download PDFInfo
- Publication number
- CN1787483A CN1787483A CNA2004101008647A CN200410100864A CN1787483A CN 1787483 A CN1787483 A CN 1787483A CN A2004101008647 A CNA2004101008647 A CN A2004101008647A CN 200410100864 A CN200410100864 A CN 200410100864A CN 1787483 A CN1787483 A CN 1787483A
- Authority
- CN
- China
- Prior art keywords
- flow control
- token
- token bucket
- control parameter
- bucket
- 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.)
- Granted
Links
Images
Abstract
This invention discloses a flow control method for realizing controlling the transmission rate of data flows transmitted in packets including: a, expanding the flow control parameters of token drum algorithm and increasing the flow control parameters of burst tolerance and threshold value of the token drum, b, carrying out limit to the token drum rate by the parameters containing said burst tolerance and threshold value to realize flow control to avoid congestion and delay dithering of the network.
Description
Technical field
The present invention relates to a kind of method of transfer of data, in particular, the present invention relates to a kind of method carrying out flow control with the bag data flow transmitted.
Background technology
In current communication system, the transfer of data of bottom generally adopts asynchronous transfer mode (ATM, Asynchronous Transfer Mode) or Internet protocol (IP, Internet Protocol), in addition, communication system inside also may adopt self-defining agreement to carry out transfer of data.
Usually, be cell according to the least unit of ATM protocol transmission, each cell size is identical, carries out flow control according to connection.And be bag according to the least unit of IP or custom protocol transmission, can adopt token bucket to carry out flow control for the data flow that sends with bag.
Token bucket is a kind of ideal tools of controlling the data flows, and its principle is to place token according to the speed of setting in bucket, and the capacity of token bucket preestablishes, and when the quantity of token in the bucket exceeded the capacity of token bucket, the token amount in the bucket no longer increased.When in token bucket, being full of token, the packet of all token representatives all can send in the bucket, after packet is handled by token bucket, if also have enough tokens to can be used for sending packet in the token bucket, then packet can go down by also continuing transmission, but the corresponding minimizing of token amount in the token bucket, when the token in the token bucket less when packet can not send again, then stop to send packet, have only by the time generate new token in the bucket after, packet just may send, therefore, the flow of packet can only be less than or equal to the speed that token generates, thereby realizes the purpose of limited flow.
The processing procedure of flow control function is carried out in following simple declaration with token bucket:
At first packet is classified, the discharge characteristic of specified data bag and send priority, and enter token bucket and handle.If there are enough tokens to can be used for sending packet in the token bucket, then packet can go down by also continuing transmission.In fact, the token quantity in the token bucket is along with the consumption of packet reduces gradually, and when the token in the token bucket no longer satisfied the transmission condition of packet, then packet was dropped.By this process, can control certain class data packet flow.
From the above, for the bag data flow transmitted, for example IP or custom protocol data flow, because the least unit of transmission is a bag, the size of the bag of each transmission all may be different, differ greatly, the bag that has has only tens bytes, and the bag that has has a few K bytes even tens K bytes.Above-mentioned token bucket flow control methods can't carry out flow control at the packet of variation length, is easy to form the congested and delay jitter that a large amount of bursts causes network, is difficult to guarantee service quality.
Summary of the invention
The technical problem that the present invention solves provides a kind of flow control methods of the packet at transform length, to prevent the congested and delay jitter of mass data bag burst to network, guarantees service quality.
For addressing the above problem, flow control methods of the present invention comprises:
A, expansion token bucket algorithm flow control parameter increase the burst tolerance of token bucket and the flow control parameter of threshold value;
B, data stream is carried out the token bucket rate limit, to realize flow control with the flow control parameter that comprises described burst tolerance and threshold value.
Wherein, step b comprises:
B1, default speed, token counts, refresh rate, burst tolerance and the threshold value flow control parameter value that is used for the token bucket of flow control, the initialization token bucket;
B2, token bucket is refreshed, determine new token counts flow control parameter value according to described refresh rate;
B3, data are flow to scanning frequency rate when restriction, whether judge in the current token bucket token counts less than described burst tolerance flow control parameter value with token bucket, if, direct execution in step b4, otherwise, remember that current token counts is the burst tolerance value, execution in step b4;
B4, judge that whether token counts is more than or equal to threshold value flow control parameter value in the current token bucket, if current token counts is designated as the token number that deducts behind the long data packet to be sent in the described data flow, and dispatches this packet and send, otherwise, do not dispatch.
In addition, step a expansion token bucket algorithm flow control parameter also comprises: increase the granularity flow control parameter of token bucket,
Step b1 also comprises the parameter value of default granularity flow control parameter, and determines and default token bucket refresh rate and refresh interval time according to described granularity parameter value,
Wherein the parameter value of Yu She described refresh rate flow control parameter is determined according to following formula:
Refresh rate=speed/granularity;
The parameter value of the flow control parameter of described refresh interval time is determined according to following formula:
Refresh interval time=8/ granularity.
Wherein, step b4 adopts weighted round ring or priority scheduling packet to send.
Compared with prior art, the present invention has following beneficial effect:
The present invention is by expansion token bucket algorithm flow control parameter, increase the burst tolerance of token bucket and the flow control parameter of threshold value, when data being flow to the restriction of scanning frequency rate, by described burst tolerance parameter is set with token bucket, the dispatch delay shake is reduced, guarantee that burst can be not too many; Simultaneously for the less parcel of length, by described threshold parameter is set, when the token number in the bucket during less than described threshold value, then can not give out a contract for a project, happen suddenly with the parcel that prevents excessive number, thereby carry out flow control at elongated bag, avoid the congested and delay jitter of network, guarantee service quality;
In addition, for preventing that token bucket from surpassing burst tolerance, also be provided with the granularity parameter among the present invention, determine the refresh rate and the refresh interval time of token bucket by described granularity calculation of parameter, refresh time is accelerated, can solve the token bucket refresh rate too slow, postpone the problem that token in excessive and the bucket surpasses burst tolerance.
Description of drawings
Fig. 1 is the network environment schematic diagram of the present invention's data packet dispatching of realizing flow control;
Fig. 2 is the flow chart of the present invention with data pack buffer to be sent;
Fig. 3 is the principle schematic of token bucket flow flow control shaping of the present invention;
Fig. 4 is a token bucket algorithm flow control flow chart of the present invention;
Fig. 5 is the flow chart that weighted round robin packet of the present invention sends.
Embodiment
With reference to figure 1, realize among the present invention that the data packet dispatching of flow control comprises three parts: go into formation part, flow control part, packet transmission scheduling part.Wherein go into the packet that formation part will send and go into the formation buffer memory, flow control partly utilizes token bucket that flow is carried out integer, the delivery time of determination data bag, when arriving delivery time, from formation, get bag, according to different QOS requirements, deliver to corresponding formation, partly being dispatched to port by data packet dispatching then sends, during specific implementation, described data packet dispatching part can be dispatched according to the weighted round robin algorithm, also can dispatch according to priority, require as long as satisfy different QOS, no longer carefully state here.
Fig. 2 has described the caching of going into the formation part, and the bag that send at first arrives into the formation part, goes into the formation part and judges earlier whether formation is full, just abandons this bag if expire, if formation is not full, then will wrap into formation, carries out buffer memory, waits for the scheduling transmission.
Flow control partly realizes the flow control function to data flow among the present invention, concrete, the flow control part is carried out integer according to default flow control parameter, the delivery time of each packet in the calculated data stream, and when delivery time arrives, packet is fallen out from the formation of buffer memory, deliver to corresponding scheduling queue and send.Token bucket algorithm is partly adopted in flow control among the present invention.The required default flow control parameter reference table one of specific implementation:
Table one
| Rate | Resolution | Refresh | BT | Count | Threshold |
The definition of each parameter is simply described as follows:
Rate: speed, promptly packets need sends according to this speed, the bps of unit;
Resolution: definition or granularity, difference can't make a distinction the bps of unit less than its two speed;
Refresh: token bucket refresh rate;
BT: burst tolerance, i.e. the maximum burst byte number that allows in the flow integer, unit byte;
Count: token counts, promptly leak the token number in the bucket;
Threshold: threshold value, promptly the minimum value of token in the token bucket then can not send data less than this value.
Need to prove, in the above-mentioned flow control parameter, Rate, Count and Refresh are the existing flow control parameters of prior art, BT, Threshold and Resolution are the parameters that expanded definition of the present invention increases, and are elaborated below in conjunction with the definition to each parameter of the principle of token bucket algorithm.
With reference to figure 3, deposits tokens in token bucket when needs send packet, need be got token from bucket, and each token can be sent out a byte.When enough tokens send current data packet, just can send.At regular intervals at interval, in bucket, put into Refresh token, i.e. Count=Count+Refresh, this time interval is definite by following method:
If the speed that sends is 1bps, promptly per second is sent out a bit, just sends out a byte so in 8 seconds.Because a token in the bucket can send a byte, if in bucket, put into a token, can reach speed 1bps every 8 seconds, this shows, put into the token number and the speed numerically equal of bucket in 8 seconds, can reach desired speed.For example require speed 1Mbps, i.e. 1000000bps then put into 1000000 tokens in the bucket in 8 seconds and just reaches 1Mbps speed, also was that Refresh equals Rate.But processing can cause in the bucket token too much like this, and refresh time is long, finally causes the dispatch delay shake big, and burst is big.
Increase B parameter T among the present invention, show the byte number of maximum burst, can guarantee that like this burst can be not too many, the token number in the bucket can not surpass BT.If token number reaches BT, then token no longer increases.Handle like this and bring a new problem to be, discuss from the top that refresh rate Refresh may be greater than BT as can be known.Increase the flow control parameter of granularity Resolution among the present invention, can determine refresh rate and refresh interval time according to described granularity Resolution, be refresh rate Refresh=Rate ÷ Resolution, the refresh interval time equals (8 ÷ Resolution) second.If be example also with speed 1Mbps, the long 3K byte of maximum data packet, if get BT is 4K, Resolution is 10Kbps, can obtain Refresh according to above-mentioned formula calculating and equal 100, refresh time 0.0008 second was put into 100 tokens in promptly 0.0008 second in bucket, refresh rate has accelerated, thereby has solved the problem that postpones and happen suddenly.
In addition, need to prove that BT can not be long less than the bag of maximum among the present invention,,, may not have enough tokens to send forever for big packet because if little long with maximum data packet.
Above-mentioned for big packet, may can only happen suddenly several bags, the bag of the longest 3K can only happen suddenly one, but for small data packets, when for example length had only tens bytes, hundreds of then once can happen suddenly.Burst on this bag number has problems equally.In order to control the burst of parcel excessive number, increased the flow control parameter of threshold value Threshold among the present invention.When giving out a contract for a project, see that earlier whether the token number in the bucket is greater than threshold value Threshold in the token bucket, if greater than and enough tokens are arranged, then from bucket, get token, upgrade Count=Count-Length (bag is long), then packet is delivered to packet and sent the scheduling part and dispatch,, then can not give out a contract for a project when the token number in the bucket during less than threshold value Threshold.
The flow control part also is responsible for refreshing token bucket among the present invention, every (8 ÷ Resolution) second time, in bucket, put into Refresh token, be Count=Count+Refresh, and judge whether that enough tokens send packet, if being arranged, enough tokens send out packet, will be from formation packet of dequeue, requiring to deliver to different scheduling queues according to different QOS dispatches, and upgrade token counts Count, below with reference to concrete flow process the flow control process that the present invention realizes is described.
Fig. 4 has described the flow chart that token bucket algorithm of the present invention carries out flow control.
In step 10, at first obtain the required flow control parameter of token bucket flow control, concrete, the flow control parameter comprises speed, granularity, burst tolerance and threshold value;
In step 11, determine refresh rate Refresh and refresh interval time according to the described flow control calculation of parameter of obtaining, with reference to above stated specification, can calculate according to Refresh=Rate ÷ Resolution and determine refresh rate, according to refresh interval time=8 ÷ Resolution;
In step 12, the initialization token bucket is initialized as 0 and the initialization refresh timer with token counts count;
In step 13, judge whether refresh time;
If be judged as refresh time in step 13, then according to the token counts in the definite refresh rate Refresh refreshing token bucket of step 12, execution in step 14 refreshes current token counts, be that current token counts count is revised as count=count+Refresh, execution in step 15 then;
If be judged as in step 13 and do not arrive refresh time, then execution in step 17;
In step 15, whether judge token counts count greater than described burst tolerance BT, if greater than described burst tolerance BT, then execution in step 16, current token counts count is designated as BT, execution in step 17; If not greater than described burst tolerance BT, then direct execution in step 17;
In step 17, judge that whether token counts count is more than or equal to threshold value Threshold;
If not more than or equal to threshold value Threshold, return step 13 at step 17 token counts count;
If not more than or equal to threshold value Threshold, continue execution in step 18 at step 17 token counts count;
In step 18, judge whether token counts count is long more than or equal to current data packet;
If judge that in step 18 token counts count is long more than or equal to current data packet, execution in step 19;
If judge that in step 18 token counts count is not long more than or equal to current data packet, return step 13;
In step 19, it is long that token counts count is revised as count=count-bag, the current bag and send packet to send scheduling queue and dispatch transmission according to service quality separately of falling out from the formation of preserving packet.
Fig. 5 has described the flow process that the present invention adopts the weighted round robin data to send, and is the QOS that guarantees service quality among the present invention, sends the scheduling part at packet and can adopt weighted round-robin algorithm to dispatch, and as shown, mainly comprises following flow process:
At first, in step 20,, then,, check whether formation is empty, if return step 20 in step 21 according to the current queue number that will send of WRR algorithm decision; Otherwise, enter step 22, from formation, get bag and deliver to the port transmission, return step 20 then.
The above only is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (4)
1, a kind of flow control methods is used to realize it is characterized in that controlling with the transmission rate of bag data flow transmitted, comprising:
A, expansion token bucket algorithm flow control parameter increase the burst tolerance of token bucket and the flow control parameter of threshold value;
B, data stream is carried out the token bucket rate limit, to realize flow control with the flow control parameter that comprises described burst tolerance and threshold value.
2, flow control methods according to claim 1 is characterized in that, step b comprises:
B1, default speed, token counts, refresh rate, burst tolerance and the threshold value flow control parameter value that is used for the token bucket of flow control, the initialization token bucket;
B2, token bucket is refreshed, determine new token counts flow control parameter value according to described refresh rate;
B3, data are flow to scanning frequency rate when restriction, whether judge in the current token bucket token counts less than described burst tolerance flow control parameter value with token bucket, if, direct execution in step b4, otherwise, remember that current token counts is the burst tolerance value, execution in step b4;
B4, judge that whether token counts is more than or equal to threshold value flow control parameter value in the current token bucket, if current token counts is designated as the token number that deducts behind the long data packet to be sent in the described data flow, and dispatches this packet and send, otherwise, do not dispatch.
3, flow control methods according to claim 2 is characterized in that, step a expansion token bucket algorithm flow control parameter also comprises: increase the granularity flow control parameter of token bucket,
Step b1 also comprises the parameter value of default granularity flow control parameter, and determines and default token bucket refresh rate and refresh interval time according to described granularity parameter value,
Wherein the parameter value of Yu She described refresh rate flow control parameter is determined according to following formula:
Refresh rate=speed/granularity;
The parameter value of the flow control parameter of described refresh interval time is determined according to following formula:
Refresh interval time=8/ granularity.
According to claim 2 or 3 described flow control methods, it is characterized in that 4, step b4 adopts weighted round ring or priority scheduling packet to send.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004101008647A CN100512207C (en) | 2004-12-10 | 2004-12-10 | Flow controlling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004101008647A CN100512207C (en) | 2004-12-10 | 2004-12-10 | Flow controlling method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1787483A true CN1787483A (en) | 2006-06-14 |
| CN100512207C CN100512207C (en) | 2009-07-08 |
Family
ID=36784799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2004101008647A Expired - Fee Related CN100512207C (en) | 2004-12-10 | 2004-12-10 | Flow controlling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100512207C (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008104100A1 (en) * | 2007-02-28 | 2008-09-04 | Zte Corporation | An apparatus and a method for realizing flow control based on rate restrict for mstp device |
| CN100450102C (en) * | 2006-10-09 | 2009-01-07 | 华为数字技术有限公司 | Method and apparatus for multiuser QOS dispatching |
| CN100518148C (en) * | 2007-04-13 | 2009-07-22 | 中国科学院软件研究所 | Token-based Internet traffic control method |
| CN101034975B (en) * | 2007-04-05 | 2010-05-26 | 华为技术有限公司 | Method and device for preventing the small message attack |
| CN101159675B (en) * | 2007-11-06 | 2010-06-02 | 中兴通讯股份有限公司 | Method of implementing improvement of user service quality in IP multimedia subsystem |
| CN101841461A (en) * | 2010-02-11 | 2010-09-22 | 北京星网锐捷网络技术有限公司 | Method and device for controlling update of token bucket |
| CN101873261A (en) * | 2010-06-07 | 2010-10-27 | 北京网康科技有限公司 | Method and equipment for improving fluid control effect of token bucket |
| CN101790075B (en) * | 2010-01-14 | 2011-10-19 | 北京东方广视科技股份有限公司 | Method and device for sending data |
| CN102291309A (en) * | 2011-08-26 | 2011-12-21 | 华为技术有限公司 | Token ring based network flow control method and system and node |
| CN102546411A (en) * | 2011-12-31 | 2012-07-04 | 华为数字技术有限公司 | Method and device for forwarding traffic |
| CN101778043B (en) * | 2010-01-19 | 2012-07-25 | 华为技术有限公司 | Method and device for dividing filling rate interval based on token bucket algorithm |
| CN101803313B (en) * | 2007-09-19 | 2012-09-05 | 英国电讯有限公司 | Methods and apparatus for providing congestion information |
| CN102724222A (en) * | 2011-03-29 | 2012-10-10 | 北京东方通科技股份有限公司 | Flow control method based on ESB |
| CN102970246A (en) * | 2012-11-23 | 2013-03-13 | 上海寰创通信科技股份有限公司 | Ethernet message flow control method |
| CN101959236B (en) * | 2009-07-13 | 2013-06-26 | 大唐移动通信设备有限公司 | Traffic control method and device |
| CN104038434A (en) * | 2013-03-08 | 2014-09-10 | 中兴通讯股份有限公司 | Traffic policing method and apparatus |
| US8837285B2 (en) | 2008-02-01 | 2014-09-16 | Interdigital Patent Holdings, Inc. | Method and apparatus for initializing, preserving, and reconfiguring token buckets |
| CN104243333A (en) * | 2013-06-24 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Traffic control method for address resolution protocol messages |
| CN104718734A (en) * | 2012-08-21 | 2015-06-17 | 惠普发展公司，有限责任合伙企业 | Congestion notification in a network |
| CN105574292A (en) * | 2016-01-29 | 2016-05-11 | 盛科网络（苏州）有限公司 | Method for achieving multi-channel any-bandwidth packet sending based on dynamic arrays |
| CN105635145A (en) * | 2015-12-31 | 2016-06-01 | 盛科网络（苏州）有限公司 | Chip-level safety protection method of CAPWAP DTLS tunnel |
| WO2016086542A1 (en) * | 2014-12-05 | 2016-06-09 | 中兴通讯股份有限公司 | Message transmission method and device, and computer storage medium |
| CN105721331A (en) * | 2016-01-21 | 2016-06-29 | 盛科网络（苏州）有限公司 | Method of controlling transmitting speed of built-in throughput capacity testing processing engine |
| WO2016197810A1 (en) * | 2016-01-13 | 2016-12-15 | 中兴通讯股份有限公司 | Packet sending method and apparatus |
| CN106254180A (en) * | 2016-08-10 | 2016-12-21 | 北京网迅科技有限公司杭州分公司 | Data transmission method and device |
| CN107948090A (en) * | 2017-11-23 | 2018-04-20 | 郑州云海信息技术有限公司 | A kind of band width control method and device of Ceph storage clusters volume |
| CN108183840A (en) * | 2017-12-28 | 2018-06-19 | 天津芯海创科技有限公司 | Verification method, device and the realization device of switch performance |
| WO2018195728A1 (en) * | 2017-04-24 | 2018-11-01 | 华为技术有限公司 | Client service transmission method and device |
-
2004
- 2004-12-10 CN CNB2004101008647A patent/CN100512207C/en not_active Expired - Fee Related
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100450102C (en) * | 2006-10-09 | 2009-01-07 | 华为数字技术有限公司 | Method and apparatus for multiuser QOS dispatching |
| WO2008104100A1 (en) * | 2007-02-28 | 2008-09-04 | Zte Corporation | An apparatus and a method for realizing flow control based on rate restrict for mstp device |
| CN101034975B (en) * | 2007-04-05 | 2010-05-26 | 华为技术有限公司 | Method and device for preventing the small message attack |
| CN100518148C (en) * | 2007-04-13 | 2009-07-22 | 中国科学院软件研究所 | Token-based Internet traffic control method |
| CN101803313B (en) * | 2007-09-19 | 2012-09-05 | 英国电讯有限公司 | Methods and apparatus for providing congestion information |
| CN101159675B (en) * | 2007-11-06 | 2010-06-02 | 中兴通讯股份有限公司 | Method of implementing improvement of user service quality in IP multimedia subsystem |
| TWI479865B (en) * | 2008-02-01 | 2015-04-01 | Interdigital Patent Holdings | Method and apparatus for initializing, preserving and reconfiguring token buckets |
| US8837285B2 (en) | 2008-02-01 | 2014-09-16 | Interdigital Patent Holdings, Inc. | Method and apparatus for initializing, preserving, and reconfiguring token buckets |
| CN101959236B (en) * | 2009-07-13 | 2013-06-26 | 大唐移动通信设备有限公司 | Traffic control method and device |
| CN101790075B (en) * | 2010-01-14 | 2011-10-19 | 北京东方广视科技股份有限公司 | Method and device for sending data |
| CN101778043B (en) * | 2010-01-19 | 2012-07-25 | 华为技术有限公司 | Method and device for dividing filling rate interval based on token bucket algorithm |
| CN101841461B (en) * | 2010-02-11 | 2012-05-30 | 北京星网锐捷网络技术有限公司 | Method and device for controlling update of token bucket |
| CN101841461A (en) * | 2010-02-11 | 2010-09-22 | 北京星网锐捷网络技术有限公司 | Method and device for controlling update of token bucket |
| CN101873261A (en) * | 2010-06-07 | 2010-10-27 | 北京网康科技有限公司 | Method and equipment for improving fluid control effect of token bucket |
| CN101873261B (en) * | 2010-06-07 | 2012-10-03 | 北京网康科技有限公司 | Method and equipment for improving fluid control effect of token bucket |
| CN102724222A (en) * | 2011-03-29 | 2012-10-10 | 北京东方通科技股份有限公司 | Flow control method based on ESB |
| WO2013029509A1 (en) * | 2011-08-26 | 2013-03-07 | 华为技术有限公司 | Network traffic control method, node and system based on token-ring |
| CN102291309B (en) * | 2011-08-26 | 2014-04-16 | 华为技术有限公司 | Token ring based network flow control method and system and node |
| CN102291309A (en) * | 2011-08-26 | 2011-12-21 | 华为技术有限公司 | Token ring based network flow control method and system and node |
| US9264363B2 (en) | 2011-08-26 | 2016-02-16 | Huawei Technologies Co., Ltd. | Method, node, and system for controlling network traffic based on token ring |
| CN102546411B (en) * | 2011-12-31 | 2014-08-13 | 北京华为数字技术有限公司 | Method and device for forwarding traffic |
| CN102546411A (en) * | 2011-12-31 | 2012-07-04 | 华为数字技术有限公司 | Method and device for forwarding traffic |
| CN104718734A (en) * | 2012-08-21 | 2015-06-17 | 惠普发展公司，有限责任合伙企业 | Congestion notification in a network |
| CN102970246A (en) * | 2012-11-23 | 2013-03-13 | 上海寰创通信科技股份有限公司 | Ethernet message flow control method |
| CN102970246B (en) * | 2012-11-23 | 2017-12-22 | 上海寰创通信科技股份有限公司 | A kind of Ethernet message flux control method |
| CN104038434A (en) * | 2013-03-08 | 2014-09-10 | 中兴通讯股份有限公司 | Traffic policing method and apparatus |
| CN104243333A (en) * | 2013-06-24 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Traffic control method for address resolution protocol messages |
| CN104243333B (en) * | 2013-06-24 | 2018-04-10 | 阿里巴巴集团控股有限公司 | A kind of flow control methods of address analysis protocol message |
| WO2016086542A1 (en) * | 2014-12-05 | 2016-06-09 | 中兴通讯股份有限公司 | Message transmission method and device, and computer storage medium |
| CN105635145A (en) * | 2015-12-31 | 2016-06-01 | 盛科网络（苏州）有限公司 | Chip-level safety protection method of CAPWAP DTLS tunnel |
| CN105635145B (en) * | 2015-12-31 | 2019-01-04 | 盛科网络（苏州）有限公司 | The chip-scale safety protecting method in the tunnel CAPWAP DTLS |
| WO2016197810A1 (en) * | 2016-01-13 | 2016-12-15 | 中兴通讯股份有限公司 | Packet sending method and apparatus |
| CN105721331A (en) * | 2016-01-21 | 2016-06-29 | 盛科网络（苏州）有限公司 | Method of controlling transmitting speed of built-in throughput capacity testing processing engine |
| CN105574292B (en) * | 2016-01-29 | 2018-12-11 | 盛科网络（苏州）有限公司 | A method of realizing that any bandwidth of multichannel is given out a contract for a project based on dynamic array |
| CN105574292A (en) * | 2016-01-29 | 2016-05-11 | 盛科网络（苏州）有限公司 | Method for achieving multi-channel any-bandwidth packet sending based on dynamic arrays |
| CN106254180A (en) * | 2016-08-10 | 2016-12-21 | 北京网迅科技有限公司杭州分公司 | Data transmission method and device |
| CN106254180B (en) * | 2016-08-10 | 2019-06-21 | 杭州熠芯科技有限公司 | Data transmission method and device |
| CN109314673A (en) * | 2017-04-24 | 2019-02-05 | 华为技术有限公司 | A kind of client traffic transmission method and device |
| WO2018195728A1 (en) * | 2017-04-24 | 2018-11-01 | 华为技术有限公司 | Client service transmission method and device |
| TWI680663B (en) * | 2017-04-24 | 2019-12-21 | 大陸商華為技術有限公司 | Method and apparatus for client service transmission |
| JP2020518172A (en) * | 2017-04-24 | 2020-06-18 | ホアウェイ・テクノロジーズ・カンパニー・リミテッド | Client service transmission method and apparatus |
| CN109314673B (en) * | 2017-04-24 | 2022-04-05 | 华为技术有限公司 | Customer service transmission method and device |
| US11785113B2 (en) | 2017-04-24 | 2023-10-10 | Huawei Technologies Co., Ltd. | Client service transmission method and apparatus |
| CN107948090A (en) * | 2017-11-23 | 2018-04-20 | 郑州云海信息技术有限公司 | A kind of band width control method and device of Ceph storage clusters volume |
| CN107948090B (en) * | 2017-11-23 | 2021-04-30 | 郑州云海信息技术有限公司 | Bandwidth control method and device for Ceph storage cluster volume |
| CN108183840A (en) * | 2017-12-28 | 2018-06-19 | 天津芯海创科技有限公司 | Verification method, device and the realization device of switch performance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100512207C (en) | 2009-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1787483A (en) | Flow controlling method | |
| US6092115A (en) | Method for supporting per-connection queuing for feedback-controlled traffic | |
| US8811411B2 (en) | Packet aggregation and fragmentation at layer-2 over a managed network | |
| CN108616458B (en) | System and method for scheduling packet transmissions on a client device | |
| US9565125B2 (en) | Multicast to unicast conversion technique | |
| CN1716914A (en) | Fair WRED for TCP and UDP traffic mix | |
| EP2641362B1 (en) | Dynamic flow redistribution for head line blocking avoidance | |
| EP1402396A1 (en) | Method and apparatus for allocating link bandwidth | |
| US20090010165A1 (en) | Apparatus and method for limiting packet transmission rate in communication system | |
| CN1878144A (en) | Multi-queue flow control method | |
| CN1918850A (en) | Methods and apparatus for controlling the flow of multiple signal sources over a single full duplex Ethernet link | |
| WO2000001120A9 (en) | Cbr/vbr traffic scheduler | |
| US10050896B2 (en) | Management of an over-subscribed shared buffer | |
| US20120099431A1 (en) | Method and device for controlling information channel flow | |
| CN1913489A (en) | Method of flow controlling for IUB-interface | |
| CN1913483A (en) | Deficit polling method of low delay boume small burst | |
| CN109873773A (en) | A kind of jamming control method for data center | |
| CN1777145A (en) | Router and method of managing packet queue using the same | |
| CN1866905A (en) | Method and apparatus for shaping transmission service stream in network | |
| WO2010017689A1 (en) | Over-loading control apparatus for value-added service message and its method | |
| CN110011924B (en) | Method and device for clearing cache congestion | |
| CN1518296A (en) | Method of implementing integrated queue scheduling for supporting multi service | |
| CN1194509C (en) | Method for controlling message transmitting spped rate in router interface | |
| WO2019029220A1 (en) | Network device | |
| EP3021540B1 (en) | Scheduler and method for layer-based scheduling queues of data packets |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090708 Termination date: 20191210 |