CN103475654B - Network path optimization method, equipment and network system - Google Patents

Abstract

The invention discloses a network path optimization method, equipment and network system. The network system includes multiple node servers and an RTT monitoring server. Among them, the node server is used to optimize the network path from the client to the source server, including: an RTT statistics unit, which is suitable for counting the RTT values from each client to the node server; an RTT sending unit, which is suitable for sending all Statistical RTT value. The RTT monitoring server includes: an RTT receiving unit adapted to receive RTT values sent by multiple node servers; an RTT calculation unit adapted to each client to calculate the node server with the smallest RTT value for the client. The invention can optimize the network path from the client to the origin server via the node server.

Description

Network path optimization method, device and network system

technical field

The invention relates to the field of Internet applications, in particular to a network path optimization method, equipment and network system.

Background technique

The rapid development of the Internet is no longer the same as when it was created. Both enterprises and ordinary Internet users have higher requirements for Internet speed. And different networks (such as China Telecom and China Unicom) need to be interconnected. In the process of interconnection and intercommunication, the current network enters another network, considering that the network itself has network jitter or failure problems, and the network is busy during peak hours of business, which may lead to network congestion.

There are many reasons for network congestion, such as: there are loops in the network that cause the network speed to slow down, broadcast storms caused by network equipment hardware failures cause the network speed to slow down, a certain port in the network forms a bottleneck and the network speed slows down, etc. .

In the face of such a changeable network situation, how to provide users with a stable access process has not yet been resolved.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a network system, a node server, an RTT monitoring server and a corresponding network path optimization method that overcome the above problems or at least partially solve the above problems.

According to one aspect of the present invention, a node server in a network system is provided, which is used to optimize the network path from the client to the source station server, including: an RTT statistical unit, which is suitable for counting each client to the node The RTT value of the server; the RTT sending unit is suitable for sending the counted RTT value.

Optionally, the network system includes an origin station server and a plurality of node servers, wherein the origin station server provides content to each client by distributing the content to the plurality of node servers, and each client passes through the node server server to retrieve content.

Optionally, the RTT value is the time interval value from when the client establishes a TCP/IP connection with the node server, from when the node server sends a handshake confirmation signal to when it receives a confirmation signal from the client for the handshake confirmation signal.

Optionally, the client is a plurality of clients distributed in different geographical regions.

According to another aspect of the present invention, an RTT monitoring server is provided, including: an RTT receiving unit, adapted to receive RTT values sent by multiple node servers; an RTT calculation unit, adapted to each client, and calculating for the client In terms of the node server with the smallest RTT value.

Optionally, the above-mentioned RTT monitoring server also includes: a network congestion assessment unit, adapted to determine whether the RTT value of a client connected to a node server according to a route associated with the client exceeds a threshold; a route modification unit, adapted to When the network congestion assessment unit determines that the RTT value of the client connecting to the node server exceeds a threshold, it modifies the route associated with the client so that the client connects to the node server with the smallest RTT value for the client.

Optionally, the route modification unit modifies the route associated with the client by modifying the DNS associated with the client.

According to another aspect of the present invention, a network path optimization method is provided, which is applied to optimize the network path from a client to an origin server via a node server, including:

Receive the RTT value from the client to the node server counted by each node server;

For each client, calculate the node server with the smallest RTT for the client;

Judging whether the RTT value of a client connecting to the node server according to the route associated with the client exceeds a threshold;

If the threshold is exceeded, modify the route associated with the client so that the client connects to the node server with the smallest RTT value for the client.

Optionally, the route associated with the client specifies the node server that the client should connect to.

Optionally, the RTT value is a time interval value from when the client establishes a TCP/IP connection with the node server, from when the node server sends a handshake confirmation signal to when the client sends a confirmation signal to the handshake confirmation signal.

Optionally, the client is a plurality of clients distributed in different geographical regions.

In the embodiment of the present invention, the RTT statistics unit can be used to calculate the RTT value from each client to the node server, and then the optimal path of the network can be selected by calculating the RTT value. Compared with the network congestion situation mentioned in the prior art, the embodiment of the present invention automatically diagnoses by calculating the RTT value, can quickly and accurately select the optimal path, avoid network access on an unstable path, and ensure the stability of the network during the access process , improve user experience.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 shows a schematic structural diagram of a network system according to an embodiment of the present invention;

Fig. 2 shows the processing flowchart of the method for network path optimization according to one embodiment of the present invention;

Fig. 3 shows the processing flowchart of the RTT value calculating method according to one embodiment of the present invention;

FIG. 4 shows a schematic structural diagram of a network path optimization system according to an embodiment of the present invention;

Fig. 5 shows a detailed flowchart of network path optimization according to an embodiment of the present invention.

detailed description

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the Content Delivery Network (hereinafter referred to as CDN), the main method currently adopted is to achieve the purpose of improving network congestion through mirroring. Specifically, the CDN improves the access speed by mirroring and caching the user's website content. However, when the CDN cache expires, the user's website content cannot be continuously cached, and it is necessary to request the corresponding content from the user's origin site. At this time, if there is a sudden network jitter, the problem of unstable network speed or even network congestion will still occur.

To solve the above technical problem, an embodiment of the present invention provides a network system. Fig. 1 shows a schematic structural diagram of a network system according to an embodiment of the present invention. As shown in FIG. 1 , the network system includes at least an active station server 110 , multiple node servers 120 , a Round-Trip Time (RTT) monitoring server 130 and a client 140 . The number of node servers 120 shown in FIG. 1 is three, which is only used as an example. In practical applications, the specific number of node servers 120 may be any integer value, which is set according to specific situations. The architecture of each node server 120 is similar, and will not be repeated here.

Now introduce the functions of each device or component in the network system and the connection relationship between each part. Firstly, the origin server 110 is coupled to multiple node servers 120 respectively, and distributes content to the multiple node servers 120 . The RTT statistics unit 121 in the node server 120 counts the RRT values from each client to the node server, and then the RTT sending unit 122 in the node server 120 sends the counted RTT values.

The specific definition of the RTT value needs to be explained here. In the embodiment of the present invention, the calculation method of the RTT value is as follows: when the client 140 establishes a Transmission Control Protocol/Internet Protocol (TCP/IP for short) connection with any node server 120, from the The time interval between the node server 120 sending the handshake confirmation signal and receiving the confirmation signal from the client 140 for the handshake confirmation signal. In the network system shown in FIG. 1 , the origin server 110 distributes the content to multiple node servers 120 , and multiple node servers 120 provide content to each client 140 . Correspondingly, on the other side, each client 140 acquires content via the node server 120 . Meanwhile, each client 140 may be a plurality of clients distributed in different geographic regions, and does not need to be limited to a specified or the same geographic region.

It can be seen from the above that in the embodiment of the present invention, the RTT statistics unit 121 can be used to calculate the RTT value from each client 140 to the corresponding node server 120, and then the optimal path of the network can be selected by calculating the RTT value. Compared with the network congestion situation mentioned in the prior art, the embodiment of the present invention automatically diagnoses by calculating the RTT value, can quickly and accurately select the optimal path, avoid network access on an unstable path, and ensure the stability of the network during the access process , improve user experience.

Secondly, in the network system shown in FIG. 1 , the RTT monitoring server 130 is coupled with each node server 120 . The RRT monitoring server 130 uses its own RTT receiving unit 131 to receive the RTT value sent by the node server 120 . After receiving the above RTT value, the RTT calculation unit 134 calculates the minimum value among all the returned RTT values, that is, obtains the node server with the minimum RTT value for the client 140 . At the same time, the client 140 sends the RTT value returned by the default connection computer room to the network congestion evaluation unit 132 in the RTT monitoring server 130 . The network congestion evaluation unit 132 evaluates the received RTT value, and performs different processing according to different evaluation results. If the evaluation result obtained by the network congestion evaluation unit 132 is that the evaluated RTT value exceeds the preset threshold, the route modification unit 133 is triggered to modify the route associated with the client 140 so as to select an optimal network path.

Specifically, the network congestion evaluation unit 132 evaluates whether the RTT value returned by the network system default and the computer room that establishes a connection with the client 140 exceeds a preset threshold, and if it exceeds the preset threshold, the route modification unit 133 is triggered; If the threshold is set, the current route will continue to be used. When the network congestion evaluation unit 132 evaluates that the current RRT value exceeds the preset threshold, the route modification unit 133 modifies the route associated with the client 140 so that the client 140 is connected to a node server with a smaller relative RTT value, of course , preferably, connect to the node server with the smallest RTT value.

In a preferred embodiment, before performing the operation of route modification, the route modification unit 133 sends a query request to the RTT calculation unit 134 to query the node server with the smallest current RTT value for the client 140 . After receiving the query request, the RTT calculation unit 134 returns a response message to the route modification unit 133 , which carries the information of the node server with the smallest RTT value for the current client 140 . The route modification unit 133 modifies the DNS associated with the client 140 to modify the route associated with the client 140 according to the result returned by the RTT calculation unit 134 .

In the embodiment of the present invention, each server is independent and does not depend on the network system mentioned herein. The node server can independently count and send the sent RTT value, and the RTT monitoring server can independently receive, calculate, judge whether the received RTT value exceeds the preset threshold and find the minimum RTT value.

Based on the network systems and servers provided by the preferred embodiments above, and based on the same inventive concept, this embodiment of the present invention provides a network path optimization method, which is used to optimize the network path from the client to the origin server via the node server. optimize. Fig. 2 shows a processing flowchart of a network path optimization method according to an embodiment of the present invention. Referring to Fig. 2, the method includes step S202 to step S208.

In the process shown in FIG. 2 , step S202 is first executed to receive the RTT value from the client to the node server counted by each node server. The number of RTT values that can be received in step S202 depends on the number of clients and the number of node servers.

For each client, since there are multiple node servers, there are multiple corresponding RTT values. When there are multiple RTT values, step S204 is executed, and for each client, among the RTT values received in step S202, the node server with the smallest RTT value for the client is calculated.

Further, it is determined whether each client needs to change the route. That is, step S206 is executed to determine whether the RTT value of a client connecting to the node server according to the route associated with the client exceeds a threshold. The route associated with the client specifies the node server the client should connect to. Follow-up operations are performed according to the judgment result. If the judgment result is yes, step S208 is triggered. If the judgment result is no, the process ends. When the RTT value exceeds the threshold, step S208 is executed. At this time, the route associated with the client is modified so that the client connects to the node server with the smallest RTT value for the client, and the process ends.

It is worth noting that the calculation method of the RTT value in the embodiment of the present invention is: when the client establishes a TCP/IP connection with the node server, from the node server sending the handshake confirmation signal to receiving the handshake confirmation signal from the client The time interval between acknowledgment signals. Fig. 3 shows a processing flowchart of a method for calculating an RTT value according to an embodiment of the present invention. The specific calculation method is: after three handshakes by TCP, the RTT value counts the time between the third handshake and the second handshake. Referring to Fig. 3, the method includes step S302 to step S306.

In the process shown in Figure 3, step S302 is first executed. When the client establishes a TCP/IP connection with the node server, that is, at time t0, the client sends a Synchronize Sequence Numbers (SYN for short) packet to the node server, And enter the SYN_SEND (SEND, send) state, waiting for the confirmation of the node server, this is the first handshake. Referring to Fig. 3, it can be seen that the first handshake interval is t1-t0.

After the first handshake ends, step S304 is executed. When the node server receives the SYN packet (that is, at time t1), it must confirm the client's SYN, and at the same time, the node server itself sends a SYN packet, that is, SYN+ACK (Acknowledgment, confirmation) package, at this point the node server enters the SYN_RECV (Receive, received) state, which is the second handshake. Referring to FIG. 3, it can be seen that the interval between the second handshake and the first handshake is t2-t1.

Finally, when the client receives the SYN+ACK packet from the node server (that is, at time t3), step S306 is executed, that is, the client sends an acknowledgment packet ACK to the node server. When the confirmation packet ACK from the client is sent, the client and the node server enter the ESTABLISHED (successful connection) state (that is, time t3), which is the third handshake. Referring to FIG. 3, it can be seen that the interval between the third handshake and the second handshake is t3-t2. After the third handshake is completed, the RTT value can be calculated according to the above calculation method, that is, the time interval between the third handshake and the second handshake.

After the third handshake, the client and the node server enter the data transmission stage, the client requests content from the node server, and accordingly, the node server distributes the content to the client. Referring to FIG. 3 , it is mentioned in step S308 that after time t3, the client sends data (DATA) to the node server. In step S310, the node server receives the DATA at time t4, and returns a data acknowledgment (DATA ACK) message to the client during time t4-t5.

In order to illustrate the network path optimization method and device provided by the embodiments of the present invention more clearly and clearly, specific embodiments are used to describe it.

Embodiment one

In this example, the specific application environment is a situation where users from multiple provinces and cities perform network access. For convenience of description, a control center is added to the above network system shown in FIG. 1 . There is one and only one control center, which is used to monitor the operation of each part and the whole of the network system.

In this example, the flow of the network path optimization method is as follows:

Step 1, count the RTT delay;

Wherein, the subject of statistics may be each client, and each client may make statistics by itself and report to the control center, or the control center may directly make statistics, or the node server may make statistics and then report to the control center.

Step 2, report the monitoring results to the control center;

Step 3. According to the monitoring results, the control center evaluates and calculates the provinces and cities where each node accesses relatively slowly;

Among them, the relatively slow here is compared with the predetermined threshold, that is, the control center will determine whether the access speed of each province and city is slow according to whether the value of a predetermined route exceeds the predetermined threshold, and then confirm whether to change the corresponding routing.

Step 4. For provinces and cities with relatively slow access, calculate the node with the smallest RTT;

Step 5. The control center controls and modifies DNS (Domain Name System, domain name resolution system) resolution, and resolves this node to the node with the smallest RTT.

The optimal node in step 5 is to resolve to the node with the smallest RTT. If under special circumstances, the node with the smallest RTT cannot provide access services, for example, the node has a hardware failure, or machine maintenance or other status, then it can be resolved to The node with the second smallest RTT, and so on.

It should be noted that the nodes involved in the various steps in this embodiment are the abbreviations of the node server above.

FIG. 4 shows an exemplary diagram of a system structure for network path optimization according to an embodiment of the present invention. As shown in FIG. 4 , the user is a Guangdong user 410 and is assigned to node one 420 by default. When the network is congested, according to the data sent by the user's origin site 440 (equivalent to the origin server above), the calculated node with the smallest RTT value is node 2 430, then modify the DNS resolution to resolve the Guangdong user 410 to the node Two 430.

Embodiment two

In this embodiment, a user in Hunan Province is taken as an example to describe a network path optimization method in detail. This embodiment is implemented relying on the network system shown in FIG. 1 .

Fig. 5 shows a detailed flowchart of a method for network path optimization according to an embodiment of the present invention. Referring to Fig. 5, the method at least includes step S502 to step S520.

In this embodiment, users in Hunan Province are assigned to the computer room in Beijing by default. Execute step S502 now, when the client of user in Hunan Province establishes TCP/IP connection with the node server of Beijing computer room, calculate from node server send handshake confirmation signal to receive from the confirmation signal that client side sends to handshake confirmation signal Time interval value, that is, RTT value.

Subsequently, step S504 is executed, and the RTT statistics unit in the node server is used to count the RTT values corresponding to Hunan users sent by the origin server and returned by computer rooms in various places. The RTT statistics unit in the node server performs statistics on the received multiple RTT values, and then sends the statistical results to the RTT sending unit of the node server. In step S506, the RTT sending unit in the node server sends all the RTT values counted by the RTT statistical unit in step S504. Correspondingly, in step S508, the RTT receiving unit in the RTT monitoring server receives the RTT values sent by multiple node servers, as in the embodiment of the present invention: the RTT of Hunan users accessing the Shanghai computer room is 85ms, and the Hunan user accessing the Beijing computer room RTT is 800ms.

After the RTT monitoring server receives the RTT value after the connection between the Hunan user and the computer rooms in various places, step S510 is executed, and the RTT calculation unit in the RTT monitoring server is used to calculate the node server with the smallest RTT value for the Hunan user client. It should be noted that, in this embodiment, the minimum RTT node is the optimal node for the client. For example, after step S510 confirms that the RTT of the Hunan user accessing the Shanghai computer room in the embodiment of the present invention is 80ms, which is the minimum value among all RTT values, then the path established between the Hunan user and the Shanghai computer room is the optimal network path to be selected.

Subsequently, in step S512, the network congestion evaluation unit calculates currently according to the route associated with the client, whether the RTT delay between the Hunan user and the Beijing computer room exceeds a preset threshold, if not, execute step S514, and if so, execute step S516.

Step S514. If the RTT value does not exceed the preset threshold, it is confirmed that the path is the best path at this time, the route does not need to be changed, and the process ends.

Step S516, if the RTT value exceeds the preset threshold, it is necessary to use the route modification unit to modify the route associated with the client, so that the client can connect to the node server with the smallest RTT value for the client. In this step, the route changing unit sends a query request to the RTT calculation unit to query the node with the smallest RTT.

When step S518 is executed, after receiving the query request sent by the route modification unit in step S516, the RTT calculation unit sends the calculated data of the node server with the smallest RTT value to the route modification unit. For example, as confirmed in step S510, for the Hunan user, the RTT between the Hunan user and the Shanghai computer room is the smallest. Therefore, the RTT calculation unit sends the minimum RTT value of 80ms returned by the Shanghai computer room to the routing change unit.

After the routing modification unit receives the minimum RTT value sent by the RTT calculation unit, step S520 is executed. Specifically, the route modification unit modifies the route associated with the client by modifying the DNS associated with the client, and modifies the route associated with the Hunan user client so that the client connects to the RTT The node server with the smallest value. So far, network path optimization is realized, and the process ends.

It should be noted that the nodes involved in the various steps in this embodiment are the abbreviations of the node server above.

Using the above method and equipment, the embodiments of the present invention can bring the following beneficial effects:

In the embodiment of the present invention, the RTT statistics unit can be used to calculate the RTT value from each client to the node server, and then the optimal path of the network can be selected by calculating the RTT value. Compared with the network congestion situation mentioned in the prior art, the embodiment of the present invention automatically diagnoses by calculating the RTT value, can quickly and accurately select the optimal path, avoid network access on an unstable path, and ensure the stability of the network during the access process , improve user experience.

Further, the RTT value calculated in the embodiment of the present invention is the time interval between two handshakes, which can ensure the accuracy of the calculation of the response time between the origin server and the client. In addition, the clients in the embodiment of the present invention are multiple clients distributed in different geographic regions, which can ensure that users in any region can choose the optimal route at any time, and are not limited to clients in one or several designated regions. End, wide application.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings), as well as any method or method so disclosed, may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components in the device for network path optimization according to the embodiment of the present invention. The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Claims (10)

1. the node server in network system, this network system include source station server and Multiple node servers, wherein said source station server is by taking content distribution to multiple nodes Business device comes provide content to each client, and each client is via described node server Obtaining content, described node server includes:

Round-trip delay RTT statistic unit, is suitable to add up each client to this node server RTT value；

RTT transmitting element, is suitable to send the RTT value added up；

Described network system also includes that RTT monitor server, described RTT monitor server are sentenced The RTT that a disconnected client is connected to node server according to the route being associated with this client Whether value exceedes threshold value, and the wherein said route being associated with client specifies this client should When the node server connected, however, it is determined that this client is connected to the RTT value of node server and surpasses When crossing threshold value, the route that amendment is associated with this client, in order to this client is connected to this The node server that for client, RTT value is minimum.

Node server the most according to claim 1, described RTT value is in client Transmission control protocol/internet protocol TCP/IP is set up when being connected, from joint with node server Point server sends confirmation signal of shaking hands and sends out described confirmation signal of shaking hands from client to receiving The time interval value of the confirmation signal gone out.

Node server the most according to claim 1 and 2, described client is multiple points Cloth is in the client of different geographic regions.

4. a round-trip delay RTT monitor server, including:

RTT receives unit, be suitable to receive multiple claim 1-3 arbitrary as described in node The RTT value that server sends；

RTT computing unit, is suitable to, to each client, be calculated for this client The node server that RTT value is minimum；

Network congestion assessment unit, is suitable to judge that a client is according to being associated with this client Route and be connected to the RTT value of node server and whether exceed threshold value, wherein said and client The route being associated specifies the node server that this client should connect；

Route change unit, is suitable to determine that this client connects at described network congestion assessment unit When RTT value to node server exceedes threshold value, the route that amendment is associated with this client, So that this client is connected to the node server that RTT value is minimum for this client.

RTT monitor server the most according to claim 4, wherein said route change The domain name analysis system DNS that unit is associated with this client by amendment revises and this client The route that end is associated.

6. a network system, including multiple claim 1-3 arbitrary as described in node clothes Business device and the RTT monitor server as described in claim 4 or 5.

7. a network path optimization method, for connecting via node server from client Network path to source station server is optimized, including:

Receive by each node server add up from client to this node server round time Prolong RTT value；

For each client, it is calculated the node that RTT value is minimum for this client Server；

Judge that a client is connected to node server according to the route being associated with this client RTT value whether exceed threshold value, the wherein said route being associated with client specifies this visitor The node server that family end should connect；

As exceeded threshold value, the route that amendment is associated with this client, in order to this client connects To the node server that RTT value for this client is minimum.

Network path optimization method the most according to claim 7, described RTT value be Client sets up transmission control protocol/internet protocol TCP/IP when being connected with node server, Confirmation signal of shaking hands is sent to receiving from client described confirmation letter of shaking hands from node server The time interval value of number confirmation signal sent.

9. according to the network path optimization method described in claim 7 or 8, wherein by amendment The domain name analysis system DNS being associated with this client revises the road being associated with this client By.

10. according to the network path optimization method described in claim 7 or 8, described client For multiple clients being distributed in different geographic regions.