CN109728933B - Distributed application software network flow control method - Google Patents
Distributed application software network flow control method Download PDFInfo
- Publication number
- CN109728933B CN109728933B CN201811395113.0A CN201811395113A CN109728933B CN 109728933 B CN109728933 B CN 109728933B CN 201811395113 A CN201811395113 A CN 201811395113A CN 109728933 B CN109728933 B CN 109728933B
- Authority
- CN
- China
- Prior art keywords
- bandwidth
- time period
- transmission time
- server
- actual
- 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
Images
Landscapes
- Telephonic Communication Services (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
A distributed application software network flow control method relates to a computer communication technology. The invention controls the bandwidth according to the following steps: 1) in the primary transmission, each server in the node sets the bandwidth limit of the server to be the node bandwidth limit of the node where the server is located to transmit service data, and records the actual bandwidth; 2) each server obtains the actual total bandwidth C2 used by other servers in the last transmission time period; 3) each server takes the actual bandwidth used by itself in the last transmission time period as the own bandwidth quota transmission service data of the transmission time period in the step, and records the actual bandwidth; 4) each server obtains the actual total bandwidth C1 used by other servers in the transmission time period of the step 3); 5) c1< C2 increases the bandwidth limit of the terminal, and C1> C2 decreases the bandwidth limit of the terminal; and transmitting service data and recording the actual bandwidth of the data. The invention achieves maximum efficiency of bandwidth utilization.
Description
Technical Field
The invention relates to a computer communication technology.
Background
In the peer-to-peer clustering system, a plurality of communication servers in a local area network form a node, the nodes are connected through a wide area network to form the system, the nodes are connected through independent communication links, a plurality of types of applications are deployed on the servers in the nodes and a uniform network outlet is used, and the system structure and the network topology are schematically shown in fig. 1.
In an actual application environment, a plurality of service systems commonly share network resources, and a traditional flow control algorithm based on unified network equipment (a switch or a router) can solve the problem of bandwidth control of network traffic through each port and a target address, but cannot solve the problem of bandwidth allocation control between a plurality of servers (an application a on multiple servers) in the same type of distributed application.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a control method for controlling network traffic based on an application software layer, so as to meet the requirement of network bandwidth quota allocation among multiple service systems or the requirement of multiple distributed servers in the same service system for network bandwidth quota utilization, so as to avoid network congestion caused by bandwidth preemption among multiple types of different applications, thereby affecting the stability of operation of the service systems.
The technical scheme adopted by the invention for solving the technical problems is that the flow control method of the distributed application software network is characterized in that in a distributed node system, the bandwidth is controlled according to the following steps:
1) and (3) quota setting: in the initial transmission time period, each server in the node sets the bandwidth limit of the server to the node bandwidth limit of the node,
and (3) transmission: transmits the traffic data with its own bandwidth limit until the end of the initial transmission time period,
recording: recording the actual bandwidth used by the user in the transmission time period in the step;
2) information exchange: each server exchanges bandwidth use condition information in the last transmission time period to obtain the actual total bandwidth used by other servers in the last transmission time period, which is called as second external total bandwidth C2;
3) and (3) quota setting: each server takes the actual bandwidth used by itself in the last transmission time period as its own bandwidth limit for the transmission time period of this step,
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: recording the actual bandwidth used by the user in the transmission time period of the step;
4) information exchange: the servers exchange bandwidth use condition information to obtain the actual total bandwidth used by other servers in the transmission time period in the step 3), which is called as a first external total bandwidth C1;
5) and (3) quota adjustment: each server adjusts its own bandwidth limit for the transmission time period of this step in the following manner:
if C1< C2, then increase the bandwidth limit itself,
if C1> C2, reducing the bandwidth limit of the system;
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: recording the actual bandwidth used by the user in the transmission time period of the step;
6) if the transmission of the service data is finished, the operation is finished, and if the transmission of the service data is not finished, the operation returns to the step 2).
The actual bandwidth is an average bandwidth or a peak bandwidth.
In the step 5), the self bandwidth quota adjusting mode is as follows: if C1 is less than or equal to C2, the bandwidth limit of the system is increased; if C1> C2, then the bandwidth limit itself is lowered.
The invention has the beneficial effects that:
the technical scheme provided by the invention realizes the purpose of providing a distributed application software network flow control method based on the overdraft learning theory so as to meet the bandwidth allocation control problem among a plurality of servers (application A on a plurality of servers) in the same type of distributed application. Therefore, excessive consumption caused by bandwidth preemption among applications is avoided, and further the running stability of other service systems is influenced. The invention overcomes the problem that the prior art depends on communication hardware equipment to control the flow bandwidth and cannot meet the bandwidth management control problem of the merging, deploying and running of a plurality of complex application service systems, and realizes the bandwidth utilization with the maximum efficiency.
Drawings
Fig. 1 is a system configuration diagram.
Detailed Description
Referring to fig. 1, the system includes a plurality of peer-to-peer nodes, each node includes a plurality of peer-to-peer servers, each server deploys a plurality of types of applications, and node groups are connected through a wide area network or a private network.
The control method comprises two parts of overdraft and learning.
Overdraft: the strategy for configuring the network traffic quota of each distributed server is that, assuming that each server can use all the bandwidth in the node quota, when the server initially operates, the mode of maximizing the bandwidth quota according to the configuration is 'overdraft'. In the operation process, the bandwidth usage in each time period is also in an overdraft mode of maximizing the available credit, and if the available bandwidth is consumed in advance in a period, the next period available credit allocation is waited.
Learning: the instantaneous result caused by overdraft of each server in the node is network preemption, and the sum of the used bandwidths of a plurality of servers actually exceeds the set limit value, so the adjustment is needed. The plurality of servers in the node respectively calculate the actually used network bandwidth, carry out bandwidth data exchange among the servers, evaluate and analyze the bandwidth consumption of all the servers in the node, and then adjust the available network bandwidth of the server in a future period of time. If the bandwidth used by other servers is reduced, the server increases the bandwidth value of the server within the configured limit range, and if the bandwidth used by other servers is increased, the server decreases the bandwidth value of the server. Under the condition of ignoring external factors, the consumption requirements of the user are met in advance, the influence of the external factors on the user is evaluated, and the process of continuously adjusting the future bandwidth value of the user by continuously knowing the bandwidth consumption of all servers in the node is learning. Through the bandwidth consumption information interaction among the service software on a plurality of servers for a plurality of times, the whole system finally achieves a dynamic balance state.
The invention comprises the following steps:
1) distributing network bandwidth use limit to each service system, and controlling network flow by each service system;
2) for a distributed service system, each distributed application software actively calculates the bandwidth and time length which are consumed by external network message transmission within a period of time in the past;
3) each server distributed application software informs the distributed application software of other servers of the network traffic bandwidth consumption coordination of the server in a past time range;
4) each distributed application software evaluates the network traffic bandwidth of the distributed application software within a future period of time by evaluating the network consumption value of other distributed application software;
5) network communication of each distributed application software in a future time range is executed with the newly calculated bandwidth;
6) through information interactive learning in a plurality of time periods, the whole distributed application software system reaches a dynamic balance state under the condition of flow control.
Example (b):
the present embodiment adopts the following steps to control the bandwidth:
1) and (3) quota setting: in the initial transmission time period, each server in the node sets the bandwidth limit of the server to the node bandwidth limit of the node,
and (3) transmission: transmits the traffic data with its own bandwidth limit until the end of the initial transmission time period,
recording: recording the actual bandwidth used by the user in the transmission time period in the step;
2) information exchange: each server exchanges bandwidth use condition information in the last transmission time period to obtain the actual total bandwidth used by other servers in the last transmission time period, which is called as second external total bandwidth C2;
3) and (3) quota setting: each server takes the actual bandwidth used by itself in the last transmission time period as its own bandwidth limit for the transmission time period of this step,
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: recording the actual bandwidth used by the user in the transmission time period of the step;
4) information exchange: the servers exchange bandwidth use condition information to obtain the actual total bandwidth used by other servers in the transmission time period in the step 3), which is called as a first external total bandwidth C1;
5) and (3) quota adjustment: each server adjusts its own bandwidth limit for the transmission time period of this step in the following manner:
if C1< C2, then increase the bandwidth limit itself,
c1 is the bandwidth occupation of other servers under the condition of strictly limiting the own bandwidth of the server, C2 is the bandwidth occupation of other servers under the condition of loosely limiting the own bandwidth of the server, C1< C2 shows that the bandwidth occupation of other servers is not large, and the bandwidth occupation of the own server can be moderately improved. The increased amount can be flexibly preset, for example, by increasing the amount by 50% in proportion, or by increasing the fixed amount of a plurality of G until the limit of the node is reached, and the like.
Similarly, if C1> C2, then the bandwidth limit itself is reduced;
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: recording the actual bandwidth used by the user in the transmission time period of the step;
6) if the transmission of the service data is finished, the operation is finished, and if the transmission of the service data is not finished, the operation returns to the step 2).
The actual bandwidth is an average bandwidth or a peak bandwidth.
In the step 5), the self bandwidth quota adjusting mode is as follows: if C1 is less than or equal to C2, the bandwidth limit of the system is increased; if C1> C2, then the bandwidth limit itself is lowered.
Claims (3)
1. The method for controlling the network flow of the distributed application software is characterized in that in a distributed node system, the bandwidth is controlled according to the following steps:
1) and (3) quota setting: in the initial transmission time period, each server in the node sets the bandwidth limit of the server to the node bandwidth limit of the node,
and (3) transmission: transmits the traffic data with its own bandwidth limit until the end of the initial transmission time period,
recording: recording the actual bandwidth used by the user in the transmission time period in the step;
2) information exchange: each server exchanges bandwidth use condition information in the last transmission time period to obtain the actual total bandwidth used by other servers in the last transmission time period, which is called as second external total bandwidth C2;
3) and (3) quota setting: each server takes the actual bandwidth used by itself in the last transmission time period as its own bandwidth limit for the transmission time period of this step,
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: recording the actual bandwidth used by the user in the transmission time period of the step;
4) information exchange: the servers exchange bandwidth use condition information to obtain the actual total bandwidth used by other servers in the transmission time period in the step 3), which is called as a first external total bandwidth C1;
5) and (3) quota adjustment: each server adjusts its own bandwidth limit for the transmission time period of this step in the following manner:
if C1< C2, then increase the bandwidth limit itself,
if C1> C2, reducing the bandwidth limit of the system;
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: recording the actual bandwidth used by the user in the transmission time period of the step;
6) if the transmission of the service data is finished, the operation is finished, and if the transmission of the service data is not finished, the operation returns to the step 2).
2. The distributed application software network traffic control method of claim 1, wherein the actual bandwidth is an average bandwidth or a peak bandwidth.
3. The distributed application software network traffic control method according to claim 1, wherein the step 5) is:
5) and (3) quota adjustment: each server adjusts its own bandwidth limit for the transmission time period of this step in the following manner:
if C1 is less than or equal to C2, the bandwidth limit is increased,
if C1> C2, reducing the bandwidth limit of the system;
and (3) transmission: transmitting the service data by the bandwidth limitation of the service data until the transmission time period is finished,
recording: the actual bandwidth used by itself during the transmission time period of this step is recorded.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811395113.0A CN109728933B (en) | 2018-11-21 | 2018-11-21 | Distributed application software network flow control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811395113.0A CN109728933B (en) | 2018-11-21 | 2018-11-21 | Distributed application software network flow control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109728933A CN109728933A (en) | 2019-05-07 |
CN109728933B true CN109728933B (en) | 2021-09-24 |
Family
ID=66294609
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811395113.0A Active CN109728933B (en) | 2018-11-21 | 2018-11-21 | Distributed application software network flow control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109728933B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101248619A (en) * | 2005-12-23 | 2008-08-20 | 香港应用科技研究院有限公司 | Distributed wireless network with dynamic bandwidth allocation |
CN103152286A (en) * | 2013-02-21 | 2013-06-12 | 华为技术有限公司 | Message transmission rate scheduling method, equipment and system |
US9307013B1 (en) * | 2013-05-30 | 2016-04-05 | Google Inc. | Reducing batch completion time in a computer network with max-min fairness |
CN105847176A (en) * | 2016-05-20 | 2016-08-10 | 锐捷网络股份有限公司 | Service flow transmission method and network device |
CN107040479A (en) * | 2016-02-04 | 2017-08-11 | 华为软件技术有限公司 | A kind of method and apparatus of cloud computing resources regulation |
CN107493485A (en) * | 2016-06-13 | 2017-12-19 | 中兴通讯股份有限公司 | A kind of resource control method, device and IPTV server |
CN107872405A (en) * | 2016-09-23 | 2018-04-03 | 谷歌公司 | Distributed bandwidth allocation and regulation |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100571175C (en) * | 2006-09-30 | 2009-12-16 | 华为技术有限公司 | A kind of cordless communication network bandwidth allocation methods and device |
CN101159699B (en) * | 2007-11-27 | 2010-04-21 | 杭州华三通信技术有限公司 | Distributed equipment switch network bandwidth dynamic assignment method and apparatus |
-
2018
- 2018-11-21 CN CN201811395113.0A patent/CN109728933B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101248619A (en) * | 2005-12-23 | 2008-08-20 | 香港应用科技研究院有限公司 | Distributed wireless network with dynamic bandwidth allocation |
CN103152286A (en) * | 2013-02-21 | 2013-06-12 | 华为技术有限公司 | Message transmission rate scheduling method, equipment and system |
US9307013B1 (en) * | 2013-05-30 | 2016-04-05 | Google Inc. | Reducing batch completion time in a computer network with max-min fairness |
CN107040479A (en) * | 2016-02-04 | 2017-08-11 | 华为软件技术有限公司 | A kind of method and apparatus of cloud computing resources regulation |
CN105847176A (en) * | 2016-05-20 | 2016-08-10 | 锐捷网络股份有限公司 | Service flow transmission method and network device |
CN107493485A (en) * | 2016-06-13 | 2017-12-19 | 中兴通讯股份有限公司 | A kind of resource control method, device and IPTV server |
CN107872405A (en) * | 2016-09-23 | 2018-04-03 | 谷歌公司 | Distributed bandwidth allocation and regulation |
Also Published As
Publication number | Publication date |
---|---|
CN109728933A (en) | 2019-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101447939B (en) | Functional distribution method and load balancer | |
CN105208121A (en) | File access flow control method and system based on distributed file system | |
CN103560978B (en) | The method and apparatus of optical access network Bandwidth Dynamic Allocation | |
CN101984777B (en) | Passive optical network system, station equipment in passive optical network system, and a control method thereof | |
EP1633088A1 (en) | Method and device for improving quality-of-service management in peer-to-peer networks | |
US9264240B2 (en) | Power sharing with stackable switches | |
CN107787458A (en) | Service quality in wireless backhaul | |
US10735266B2 (en) | Dynamic bandwidth allocation for wireless mesh networks | |
WO2012129856A1 (en) | Method and system for regulating and controlling service license dynamically | |
CN105897612A (en) | Multi-service dynamic bandwidth allocation method and system based on SDN (Software Defined Network) | |
CN109392013A (en) | A kind of method of adjustment and communication device of service quality QoS | |
CN112565442A (en) | Time slot resource adjusting method based on load assessment | |
CN115413041A (en) | Centralized wireless ad hoc network resource allocation method and system | |
CN113709885B (en) | Multi-service network resource allocation method | |
CN103874133A (en) | Method and device for bandwidth control and access point | |
CN109728933B (en) | Distributed application software network flow control method | |
CN110177056A (en) | A kind of self-reacting band width control method | |
CN103905342A (en) | Uplink channel dynamic distribution method based on received statistics | |
CN110769023A (en) | Point-to-point content distribution network system based on intelligent home gateway | |
CN103067302A (en) | Method and device for achieving double-rate leaky bucket model | |
CN106330774A (en) | Method and device for microwave link to transmit business data | |
CN111800823B (en) | Priority-based power wireless terminal data transmission method and device | |
CN105338575A (en) | Control method, device and server | |
CN100459770C (en) | Method for improving interface bandwidth utilization rate between wireless network controller and base-station | |
CN100466860C (en) | A method for optimization of distribution user interface instance under the master-slave structure |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |