CN106789650B - Wide area network acceleration method and device based on IP - Google Patents
Wide area network acceleration method and device based on IP Download PDFInfo
- Publication number
- CN106789650B CN106789650B CN201611208461.3A CN201611208461A CN106789650B CN 106789650 B CN106789650 B CN 106789650B CN 201611208461 A CN201611208461 A CN 201611208461A CN 106789650 B CN106789650 B CN 106789650B
- Authority
- CN
- China
- Prior art keywords
- forwarding
- path
- service type
- devices
- optimal
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/123—Evaluation of link metrics
Abstract
The invention discloses a wide area network acceleration method and a device based on IP, wherein the method comprises the following steps: selecting a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network; acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices; determining an optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to parameter values of link dynamic parameters of links in two directions between two adjacent second IP forwarding devices and a proportion set of each service type; determining whether the existing forwarding paths of each service type in two directions between every two second IP forwarding devices need to be switched to the corresponding optimal forwarding paths; and if the switching to the corresponding optimal forwarding path is required, notifying the optimal forwarding path required to be switched, which corresponds to the service type in the corresponding direction, to a second IP forwarding device included in the optimal forwarding path required to be switched. The wide area network acceleration effect of the scheme is good.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for accelerating a wide area network based on an Internet Protocol (IP).
Background
Wide area networks, also known as telnets, typically span a large physical area, can connect multiple cities or countries, or across several continents, and can provide long-range communications, forming an international long-range network. For enterprise users, communication subnets of the wide area network are generally maintained by an operator, but the network of the operator is invisible to the users, and the users cannot control the transmission quality of the users, and only want to trust the Service Level Agreement (SLA) provided by the operator. However, in a transient network environment, the actual network transmission quality often does not meet the SLA index of the operator, and users often need to adopt additional acceleration technology in order to obtain access speed close to that of the local area network.
At present, a Content Delivery Network (CDN) technology is often used for accelerating a wide area Network. CDN technology refers to deploying Point of Presence (POP) points around the world and caching the content of a source station on these POP points. When a user accesses a certain website, the website is analyzed to the POP close to the user through the DNS technology, and the user can obtain a faster access speed by accessing the cache content.
The CDN technology has the best acceleration effect on static content that is not changed frequently, but more and more data are generated dynamically, for example, when a live video is watched, a good acceleration effect cannot be obtained by caching, that is, the CDN technology is not good for any type of service acceleration effect; moreover, in the manner of constructing the CDN, POP needs to be deployed, which results in high hardware cost.
Disclosure of Invention
The embodiment of the invention provides an IP-based wide area network acceleration method and device, which are used for solving the problems that the CDN technology is not good in any type of service acceleration effect and high in hardware cost.
According to an embodiment of the present invention, an IP-based method for accelerating a wide area network is provided, where the wide area network includes an IP scheduling device and a first IP forwarding device, and the method is applied in the IP scheduling device, and the method includes:
selecting a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network;
acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices;
determining an optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of two directional links between two adjacent second IP forwarding devices and a proportion set of each service type;
determining whether the existing forwarding paths of each service type in two directions between every two second IP forwarding devices need to be switched to the corresponding optimal forwarding path;
if the existing forwarding path of at least one service type in at least one direction between the two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path, the optimal forwarding path needing to be switched in the corresponding direction and corresponding to the service type is notified to the second IP forwarding devices included in the optimal forwarding path needing to be switched, so that the second IP forwarding devices included in the optimal forwarding path needing to be switched perform message forwarding according to the optimal forwarding path needing to be switched.
Specifically, selecting a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network, specifically includes:
respectively establishing connection channels with the first IP forwarding equipment;
acquiring first IP forwarding equipment which successfully establishes a connection channel to obtain second IP forwarding equipment;
and constructing the second IP forwarding equipment into a virtual forwarding network.
Specifically, the obtaining of the parameter values of the link dynamic parameters of two directional links between two adjacent second IP forwarding devices specifically includes:
sending a link dynamic parameter to the second IP forwarding device, so that the second IP forwarding device obtains a parameter value of the link dynamic parameter from a directional link of an adjacent second IP forwarding device and sends the parameter value to the IP scheduling device;
and receiving the parameter value of the link dynamic parameter sent by the second IP forwarding equipment.
Specifically, determining an optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of two directional links between two adjacent second IP forwarding devices and a specific gravity set of each service type, specifically includes:
determining possible forwarding paths and path qualities of the service types in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of the two directional links between two adjacent second IP forwarding devices, link inherent attributes of the two directional links between every two second IP forwarding devices and a proportion set of each service type;
and determining the possible forwarding path with the highest path quality of each service type in two directions between every two second IP forwarding devices as the optimal forwarding path corresponding to the corresponding direction and the corresponding service type between every two second IP forwarding devices.
Specifically, determining whether the existing forwarding path of each service type in two directions between every two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path specifically includes:
determining whether the existing forwarding paths corresponding to the service types in two directions between every two second IP forwarding devices are the same as the optimal forwarding path;
if the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices is different from the optimal forwarding path, calculating a difference value between the path quality of the existing forwarding path corresponding to the one service type in the one direction between the two second IP forwarding devices and the path quality of the optimal forwarding path, and obtaining a path quality difference value corresponding to the one service type in the one direction between the two second IP forwarding devices;
determining whether a path quality difference value of the one service type in the one direction between the two second IP forwarding devices is greater than an anti-oscillation threshold value;
if the path quality difference value of the service type in the one direction between the two second IP forwarding devices is greater than the anti-oscillation threshold value, determining that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path; if the difference value of the path quality of the service type in the one direction between the two second IP forwarding devices is less than or equal to the anti-oscillation threshold, it is determined that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices does not need to be switched to the corresponding optimal forwarding path.
According to an embodiment of the present invention, there is also provided an IP-based wide area network acceleration apparatus, where the wide area network includes an IP scheduling device and a first IP forwarding device, and the apparatus is applied in the IP scheduling device, and the apparatus includes:
the building module is used for selecting a second IP forwarding device from the first IP forwarding devices to build a virtual forwarding network;
the acquisition module is used for acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices;
the first determining module is used for determining the optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to the parameter values of the link dynamic parameters of the links in two directions between two adjacent second IP forwarding devices and the proportion set of each service type;
a second determining module, configured to determine whether an existing forwarding path of each service type in two directions between every two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path;
and the notification module is configured to notify the optimal forwarding path to be switched in the corresponding direction and corresponding to the service type to the second IP forwarding device included in the optimal forwarding path to be switched if the existing forwarding path of at least one service type needs to be switched to the corresponding optimal forwarding path in at least one direction between the two second IP forwarding devices, so that the second IP forwarding device included in the optimal forwarding path to be switched performs packet forwarding according to the optimal forwarding path to be switched.
Specifically, the building module is specifically configured to:
respectively establishing connection channels with the first IP forwarding equipment;
acquiring first IP forwarding equipment which successfully establishes a connection channel to obtain second IP forwarding equipment;
and constructing the second IP forwarding equipment into a virtual forwarding network.
Specifically, the obtaining module is specifically configured to:
sending a link dynamic parameter to the second IP forwarding device, so that the second IP forwarding device obtains a parameter value of the link dynamic parameter from a directional link of an adjacent second IP forwarding device and sends the parameter value to the IP scheduling device;
and receiving the parameter value of the link dynamic parameter sent by the second IP forwarding equipment.
Specifically, the first determining module is specifically configured to:
determining possible forwarding paths and path qualities of the service types in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of the two directional links between two adjacent second IP forwarding devices, link inherent attributes of the two directional links between every two second IP forwarding devices and a proportion set of each service type;
and determining the possible forwarding path with the highest path quality of each service type in two directions between every two second IP forwarding devices as the optimal forwarding path corresponding to the corresponding direction and the corresponding service type between every two second IP forwarding devices.
Specifically, the second determining module is specifically configured to:
determining whether the existing forwarding paths corresponding to the service types in two directions between every two second IP forwarding devices are the same as the optimal forwarding path;
if the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices is different from the optimal forwarding path, calculating a difference value between the path quality of the existing forwarding path corresponding to the one service type in the one direction between the two second IP forwarding devices and the path quality of the optimal forwarding path, and obtaining a path quality difference value corresponding to the one service type in the one direction between the two second IP forwarding devices;
determining whether a path quality difference value of the one service type in the one direction between the two second IP forwarding devices is greater than an anti-oscillation threshold value;
if the path quality difference value of the service type in the one direction between the two second IP forwarding devices is greater than the anti-oscillation threshold value, determining that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path; if the difference value of the path quality of the service type in the one direction between the two second IP forwarding devices is less than or equal to the anti-oscillation threshold, it is determined that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices does not need to be switched to the corresponding optimal forwarding path.
The invention has the following beneficial effects:
the embodiment of the invention provides a wide area network acceleration method and a wide area network acceleration device based on IP.A second IP forwarding device is selected from first IP forwarding devices to construct a virtual forwarding network; acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices; determining an optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of two directional links between two adjacent second IP forwarding devices and a proportion set of each service type; determining whether the existing forwarding paths of each service type in two directions between every two second IP forwarding devices need to be switched to the corresponding optimal forwarding path; if the existing forwarding path of at least one service type in at least one direction between the two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path, the optimal forwarding path needing to be switched in the corresponding direction and corresponding to the service type is notified to the second IP forwarding devices included in the optimal forwarding path needing to be switched, so that the second IP forwarding devices included in the optimal forwarding path needing to be switched perform message forwarding according to the optimal forwarding path needing to be switched. In the scheme, the optimal forwarding paths of different service types in two directions between two second IP forwarding devices can be determined in real time, and switching is carried out as required, so that the effect of bilateral acceleration is achieved, and the wide area network acceleration effect is good no matter which type of service is targeted; and hardware equipment such as POP (point of presence) is not required to be deployed, so that the hardware cost is reduced.
Drawings
FIG. 1 is a flow chart of a method for IP-based WAN acceleration in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart of S11 in an embodiment of the present invention;
FIG. 3 is a flowchart of S12 in an embodiment of the present invention;
FIG. 4 is a flowchart of S13 in an embodiment of the present invention;
FIG. 5 is a flowchart of S14 in an embodiment of the present invention;
FIG. 6 is a diagram illustrating an application scenario according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an IP-based wan accelerator in an embodiment of the present invention.
Detailed Description
In order to solve the problem that the CDN technique is not good for any type of service acceleration effect and the hardware cost is high, an embodiment of the present invention provides an IP-based wide area Network acceleration method, where a wide area Network includes an IP scheduling device and a first IP forwarding device, where the first IP forwarding device undertakes forwarding of service traffic, and may be a hardware device such as a switch and a router, or may also be forwarding software such as a Virtual user terminal device (VCPE), and the first IP forwarding device may be connected to one or more IP scheduling devices, and a connection Protocol used in the connection may be an open flow (flow) Protocol, a Network Configuration Protocol (Network Configuration Protocol, Network conf) Protocol, a Simple Network Management Protocol (SNMP) Protocol, and the like. The IP scheduling device may be a Software Defined Network (SDN) SDN controller or the like, and the forwarding path between the first IP forwarding devices is determined by the IP scheduling device. The IP forwarding device has two deployment modes: the side-hang mode and the direct connection mode are distinguished according to the connection mode with the existing network outlet equipment. In the bypass mode, a route-dependent redistribution technology guides traffic needing accelerated scheduling to a first IP forwarding device, including but not limited to Open Shortest Path First (OSPF) route redistribution, Border Gateway Protocol (BGP) route redistribution, Intermediate System to Intermediate System (ISIS) route redistribution; in the direct connection mode, the first IP forwarding device directly replaces an outlet of an original network to perform scheduling optimization on all traffic.
The wide area network acceleration method based on the IP is applied to IP scheduling equipment, the flow is shown as figure 1, and the execution steps are as follows:
s11: and selecting a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network.
Because the IP address on the wide area network is a public network IP address, the message transmission among the IP forwarding devices is performed by routing through public network routing information, the routing of the public network is controlled by an operator, and a user cannot control the forwarding behavior of the service message of the user. Therefore, it is necessary to implement control of forwarding paths between IP forwarding devices by constructing a Virtual forwarding Network, and the Virtual forwarding Network construction technologies adopted in the embodiment of the present invention include, but are not limited to, technologies such as General Routing Encapsulation (GRE), IP-in-IP, Internet Protocol Security (IPSec), and Virtual eXtensible Local Area Network (VXLAN), and implement control of forwarding paths by encapsulating IP packets of a user's own service in a Virtual forwarding Network for transmission.
Some first IP forwarding devices in the wide area network do not meet the condition for constructing the virtual forwarding network, so a part of the first IP forwarding devices can be selected from the wide area network and is selected as second IP forwarding devices, and the second IP forwarding devices are constructed into the virtual forwarding network.
S12: and acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices.
The transmission between the IP forwarding devices in the wide area network is directional, and if two second forwarding IP forwarding devices A and B are provided, the link from A to B and the link from B to A are different, and the IP scheduling device can acquire parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices.
S13: and determining the optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to the parameter values of the link dynamic parameters of the links in two directions between two adjacent second IP forwarding devices and the proportion set of each service type.
The accuracy of the link dynamic parameters directly affects the accuracy of the finally determined optimal forwarding path of each service type in two directions between every two second IP forwarding devices. In this embodiment, the link dynamic parameters may include time delay, packet loss, jitter, throughput, available bandwidth, and the like, and the following briefly introduces the calculation methods of the three link dynamic parameters:
the time delay is a unidirectional index, the second IP forwarding equipment can be obtained by comparing the time stamp of the received message with the sending time stamp carried in the message, and then the time delay values of other messages obtained in the same message group are comprehensively calculated to obtain the unidirectional time delay values of two directional links between the two second IP forwarding equipment. In order to ensure the consistency of the timestamps, the present embodiment uses a time synchronization protocol to complete time synchronization between IP forwarding devices.
The packet loss is a one-way indicator, and the second IP forwarding device obtains the value by calculating the number of messages in the received message group and comparing the number of messages expected to be received.
The available bandwidth is a one-way indicator, and the second IP forwarding device is obtained by recording the traffic peak and the current available bandwidth.
In order to perform refinement and acceleration on each service type, a proportion set of each service type may be configured in advance, and then an optimal forwarding path of each service type in two directions between every two second IP forwarding devices is determined. The service types can be distinguished based on one or more combinations of IP destination addresses, IP destination network segments, IP source addresses, IP source network segments, destination ports, source ports, application types and the like, and can also be distinguished according to the priority of the service.
S14: and determining whether the existing forwarding paths of each service type in two directions between every two second IP forwarding devices need to be switched to the corresponding optimal forwarding paths.
The existing forwarding paths of each service type in two directions between every two second IP forwarding devices are not necessarily the corresponding optimal forwarding paths, and in order to achieve a better acceleration effect, it is determined whether the existing forwarding paths need to be switched to the corresponding optimal forwarding paths.
S15: if the existing forwarding path of at least one service type in at least one direction between two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path, the optimal forwarding path needing to be switched in the corresponding direction and corresponding to the service type is notified to the second IP forwarding devices included in the optimal forwarding path needing to be switched, so that the second IP forwarding devices included in the optimal forwarding path needing to be switched perform message forwarding according to the optimal forwarding path needing to be switched.
For example, the existing forwarding path in the direction from the second IP forwarding device a to B is a → C → B, and the corresponding optimal forwarding path is a → C → D → B, in order to implement more optimal forwarding, the optimal forwarding path from a → C → D → B may pass through A, B, C and four second IP forwarding devices from D, and the four second IP forwarding devices may forward a packet according to the optimal forwarding path.
In the scheme, the optimal forwarding paths of different service types in two directions between two second IP forwarding devices can be determined in real time, and switching is carried out as required, so that the effect of bilateral acceleration is achieved, and the wide area network acceleration effect is good no matter which type of service is targeted; and hardware equipment such as POP (point of presence) is not required to be deployed, so that the hardware cost is reduced.
Specifically, the implementation manner in which the second IP forwarding device is selected from the first IP forwarding devices in S11 to construct the virtual forwarding network specifically includes, as shown in fig. 2:
s111: and respectively establishing connection channels with the first IP forwarding equipment.
S112: and acquiring the first IP forwarding equipment which successfully establishes the connection channel to obtain second IP forwarding equipment.
S113: and constructing the second IP forwarding equipment into a virtual forwarding network.
Some first IP forwarding devices cannot establish communication connection with the IP scheduling device, and therefore, only the first IP forwarding devices (called second IP forwarding devices) that can successfully establish a connection channel with the IP scheduling device can construct a virtual forwarding network.
The connection channel is used for transmitting message contents required between the IP forwarding device and the IP scheduling device. This unit is responsible for encapsulating and decapsulating the interacted messages.
Alternatively, a keep-alive period may be set for the connection channel to determine the connection status of the connection channel.
Alternatively, in order to improve the security of transmission, the connection channel may adopt an encrypted transmission mode.
The connection form of the second IP forwarding device in the virtual forwarding network may be a full interconnection form or a half interconnection form.
Specifically, the implementation manner of obtaining the parameter values of the link dynamic parameters of the two directional links between two adjacent second IP forwarding devices in S12 specifically includes, as shown in fig. 3:
s121: and sending the link dynamic parameters to the second IP forwarding equipment so that the second IP forwarding equipment obtains the parameter values of the link dynamic parameters of the directional link from the adjacent second IP forwarding equipment and sends the parameter values to the IP scheduling equipment.
S122: and receiving the parameter value of the link dynamic parameter sent by the second IP forwarding equipment.
Two acquisition modes are provided for the parameter values of the link dynamic parameters of the two directional links between two adjacent second IP forwarding devices, wherein in the first mode, the two adjacent second IP forwarding devices can send messages in a set period by simulating service, and calculate the parameter values of the link dynamic parameters of the directional links from the second IP forwarding device at the opposite end according to the received messages, and then transmit the parameter values to the IP scheduling device; in the second mode, two adjacent second IP forwarding devices forward the received message to the IP scheduling device, and the IP scheduling device calculates parameter values of link dynamic parameters of two directional links between the two adjacent second IP forwarding devices. The method of the two modes of calculation is the same, but the execution subject is different. The set period is configurable, a group of messages is sent in each period, each message carries a timestamp during sending and carries the same message group identifier, and after receiving the content in the message group, the adjacent second IP forwarding equipment in the first mode performs local calculation, so that the calculated amount of the IP scheduling equipment can be shared. In order to better simulate service Transmission, in this embodiment, detection of different types of messages and settings of different message lengths are supported, such as an Internet Control Message Protocol (ICMP), a User Datagram Protocol (UDP), a Transmission Control Protocol (TCP), and the like.
Specifically, the determining, in S13, an implementation manner of determining an optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to parameter values of link dynamic parameters of links in two directions between two adjacent second IP forwarding devices and a specific gravity set of each service type specifically includes, as shown in fig. 4:
s131: and determining possible forwarding paths and path quality of each service type in two directions between every two second IP forwarding devices according to parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices, link inherent attributes of two directional links between every two second IP forwarding devices and a proportion set of each service type.
There may be multiple possible forwarding paths from one second IP forwarding device to another second IP forwarding device. For example, there are three second IP forwarding devices A, B and C, then there are two possible forwarding paths from a to B: a → B and A → C → B.
Link dynamic parameters have been introduced in S13, and link intrinsic properties such as link cost, node load, traffic, etc. may be considered in addition to the parameter values of the link dynamic parameters when determining the path quality of each possible forwarding path.
The proportion set of each service type comprises proportion of each link dynamic parameter and link inherent attribute which are configured in advance, and the path quality of each possible forwarding path can be obtained by weighting and summing the parameter values of the link dynamic parameters and the link inherent attributes.
S132: and determining the possible forwarding path with the highest path quality of each service type in two directions between every two second IP forwarding devices as the optimal forwarding path corresponding to the direction and the service type between every two second IP forwarding devices.
One way to determine the optimal forwarding path for each service type in both directions between two pairs of second IP forwarding devices is enumerated by S131-S132. Other ways may also be used to determine, for example, that traffic may be shared among all possible forwarding paths, where the optimal forwarding path is the set of possible forwarding paths.
Specifically, the implementation manner of determining whether the existing forwarding path of each service type in two directions between every two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path in S14, as shown in fig. 5, specifically includes:
s141: and determining whether the existing forwarding paths corresponding to the service types in two directions between every two second IP forwarding devices are the same as the optimal forwarding path.
S142: if the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices is different from the optimal forwarding path, calculating a difference value between the path quality of the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices and the path quality of the optimal forwarding path, and obtaining a path quality difference value corresponding to one service type in one direction between the two second IP forwarding devices.
When one direction and one service type of the existing forwarding path between the two second IP forwarding devices are the same as the corresponding optimal forwarding path, the problem of forwarding path switching does not need to be considered, and only when one direction and one service type of the existing forwarding path between the two second IP forwarding devices are different from the corresponding optimal forwarding path, the difference value between the path quality of the one direction and one service type of the existing forwarding path between the two second IP forwarding devices and the path quality of the corresponding optimal forwarding path is further calculated, so that the path quality difference value is obtained.
S143: determining whether a path quality difference value of one service type in one direction between two second IP forwarding devices is greater than an anti-oscillation threshold, and if the path quality difference value of one service type in one direction between the two second IP forwarding devices is greater than the anti-oscillation threshold, performing S144; if the path quality difference value of one service type in one direction between the two second IP forwarding devices is less than or equal to the anti-oscillation threshold, S145 is executed.
The anti-oscillation threshold value can be set according to actual needs.
S144: and determining that the existing forwarding path of one service type in one direction between the two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path.
S145: and determining that the existing forwarding path of one service type in one direction between the two second IP forwarding devices does not need to be switched to the corresponding optimal forwarding path.
When the path quality difference does not exceed the anti-oscillation threshold, the existing forwarding path can be continuously adopted for message forwarding, and only when the path quality difference is greater than the anti-oscillation threshold, the forwarding path needs to be switched.
Through S141-S145, it can be realized that the existing forwarding path of a service type in one direction between two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path.
The beneficial effects of the above method are described in the following application scenario as shown in fig. 6, where the second IP forwarding devices in the virtual forwarding network are A, B, C, D and E:
first, the IP transmission is accelerated.
In the prior art, mutual access on the wide area network depends on the transmission quality of the wide area network itself, for example, when a server with an IP address of 100.1.1.1 accesses a server with an IP address of 200.1.1.1, after a message reaches a, when the message is sent from a to C, the access performance is uncontrollable. In the embodiment of the invention, a plurality of forwarding paths from IP forwarding equipment A to C or from C to A exist by constructing the virtual forwarding network by using the tunnel technology. After the virtual forwarding network is constructed, the IP scheduling equipment issues the detected link dynamic parameters, acquires the parameter values of the link dynamic parameters by the IP forwarding equipment, reports the parameter values to the IP scheduling equipment, determines whether the forwarding path switching is needed or not by the IP scheduling equipment, and then issues the parameters to the IP forwarding equipment for transmission acceleration.
After the whole IP message is encapsulated by adopting a tunnel encapsulation technology, various different services such as TCP, UDP and the like can be borne, the transmission optimization range is expanded, and the technical complexity of transmission optimization is reduced.
As shown in fig. 6, assuming that the transmission delay of the packet after tunnel encapsulation between a and C is 10ms and the packet loss is 2%, while the transmission delay of the packet after tunnel encapsulation between a and B is 3ms and the packet loss is 0%, and the transmission delay of the packet after tunnel encapsulation between B and C is 4% and the packet loss is 0%, the IP scheduling device may find the packet sent from a to C, and the transmission performance after transit through B may be better. The embodiment of the invention firstly schedules the message to the B for transferring, optimizes the transmission from the C to the A in the same way and achieves the effect of bilateral acceleration.
Second, enhance the reliability of IP transmission
The embodiment of the invention supports load sharing and path redundancy among a plurality of forwarding paths. When one of the forwarding paths fails, the other forwarding path can be switched to quickly. As shown in fig. 6, after creating the virtual forwarding network by using the tunneling technique, there are multiple possible forwarding paths from a to C (assuming that only one-level transit is considered at most, the possible forwarding paths are: a → C, A → B → C, A → D → C, A → E → C), and in the embodiment of the present invention, the load sharing can be performed among these possible forwarding paths according to the proportion. Or only selecting the optimal path, when the selected optimal path fails, the IP scheduling device sends new path information to the IP forwarding device, thereby realizing path redundancy and enhancing transmission reliability.
Thirdly, flexible regulation and control mode
The embodiment of the invention supports scheduling and routing based on the service type. The service type is identified by the IP quintuple and the application type, and different acceleration strategies are set, for example, the packet loss tolerance of a certain service is higher, so that the calculation proportion of the path occupied by the packet loss rate can be reduced. Thereby meeting the scheduling and optimizing requirements of different services.
Based on the same inventive concept, an embodiment of the present invention provides an IP-based wide area network acceleration apparatus, where a wide area network includes an IP scheduling device and a first IP forwarding device, and the apparatus is applied in the IP scheduling device, and a structure of the apparatus is shown in fig. 7, and includes:
a constructing module 71, configured to select a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network;
an obtaining module 72, configured to obtain parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices;
a first determining module 73, configured to determine, according to parameter values of link dynamic parameters of links in two directions between two adjacent second IP forwarding devices and a specific gravity set of each service type, an optimal forwarding path of each service type in two directions between every two second IP forwarding devices;
a second determining module 74, configured to determine whether the existing forwarding path of each service type in two directions between every two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path;
the notifying module 75 is configured to notify, if an existing forwarding path of at least one service type in at least one direction between two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path, the optimal forwarding path that needs to be switched in the corresponding direction and corresponds to the service type to a second IP forwarding device included in the optimal forwarding path that needs to be switched, so that the second IP forwarding device included in the optimal forwarding path that needs to be switched performs packet forwarding according to the optimal forwarding path that needs to be switched.
In the scheme, the optimal forwarding paths of different service types in two directions between two second IP forwarding devices can be determined in real time, and switching is carried out as required, so that the effect of bilateral acceleration is achieved, and the wide area network acceleration effect is good no matter which type of service is targeted; and hardware equipment such as POP (point of presence) is not required to be deployed, so that the hardware cost is reduced.
Specifically, the building block 71 is specifically configured to:
respectively establishing connection channels with first IP forwarding equipment;
acquiring first IP forwarding equipment which successfully establishes a connection channel to obtain second IP forwarding equipment;
and constructing the second IP forwarding equipment into a virtual forwarding network.
Specifically, the obtaining module 72 is specifically configured to:
sending the link dynamic parameters to second IP forwarding equipment so that the second IP forwarding equipment obtains parameter values of the link dynamic parameters of the directional link from the adjacent second IP forwarding equipment and sends the parameter values to IP scheduling equipment;
and receiving the parameter value of the link dynamic parameter sent by the second IP forwarding equipment.
Specifically, the first determining module 73 is specifically configured to:
determining possible forwarding paths and path qualities of the service types in two directions between every two second IP forwarding devices according to parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices, link inherent attributes of the two directional links between every two second IP forwarding devices and a proportion set of each service type;
and determining the possible forwarding path with the highest path quality of each service type in two directions between every two second IP forwarding devices as the optimal forwarding path corresponding to the direction and the service type between every two second IP forwarding devices.
Specifically, the second determining module 74 is specifically configured to:
determining whether the existing forwarding paths corresponding to the service types in two directions between every two second IP forwarding devices are the same as the optimal forwarding path or not;
if the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices is different from the optimal forwarding path, calculating the difference value between the path quality of the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices and the path quality of the optimal forwarding path to obtain the path quality difference value corresponding to one service type in one direction between the two second IP forwarding devices;
determining whether the path quality difference value of one service type in one direction between two second IP forwarding devices is greater than an anti-oscillation threshold value;
if the path quality difference value of one service type in one direction between the two second IP forwarding devices is larger than the anti-oscillation threshold value, determining that the existing forwarding path of one service type in one direction between the two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path; and if the path quality difference value of one service type in one direction between the two second IP forwarding devices is smaller than or equal to the anti-oscillation threshold value, determining that the existing forwarding path of one service type in one direction between the two second IP forwarding devices does not need to be switched to the corresponding optimal forwarding path.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While alternative embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including alternative embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (8)
1. A wide area network acceleration method based on an Internet Protocol (IP), wherein the wide area network comprises an IP scheduling device and a first IP forwarding device, and the method is applied to the IP scheduling device, and is characterized in that the method comprises the following steps:
selecting a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network;
acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices;
determining an optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of two directional links between two adjacent second IP forwarding devices and a proportion set of each service type;
determining whether the existing forwarding paths of each service type in two directions between every two second IP forwarding devices need to be switched to the corresponding optimal forwarding path;
if the existing forwarding path of at least one service type in at least one direction between the two second IP forwarding devices needs to be switched to the corresponding optimal forwarding path, notifying the optimal forwarding path needing to be switched in the corresponding direction and corresponding to the service type to the second IP forwarding devices included in the optimal forwarding path needing to be switched, so that the second IP forwarding devices included in the optimal forwarding path needing to be switched perform message forwarding according to the optimal forwarding path needing to be switched;
the obtaining of the parameter values of the link dynamic parameters of two directional links between two adjacent second IP forwarding devices specifically includes:
sending a link dynamic parameter to the second IP forwarding device, so that the second IP forwarding device obtains a parameter value of the link dynamic parameter from a directional link of an adjacent second IP forwarding device and sends the parameter value to the IP scheduling device;
and receiving the parameter value of the link dynamic parameter sent by the second IP forwarding equipment.
2. The method according to claim 1, wherein selecting a second IP forwarding device from the first IP forwarding devices to construct a virtual forwarding network, specifically comprises:
respectively establishing connection channels with the first IP forwarding equipment;
acquiring first IP forwarding equipment which successfully establishes a connection channel to obtain second IP forwarding equipment;
and constructing the second IP forwarding equipment into a virtual forwarding network.
3. The method according to claim 1, wherein determining an optimal forwarding path for each service type in two directions between two adjacent second IP forwarding devices according to the parameter values of the link dynamic parameters of two directional links between the two adjacent second IP forwarding devices and the specific gravity set of each service type specifically includes:
determining possible forwarding paths and path qualities of the service types in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of the two directional links between two adjacent second IP forwarding devices, link inherent attributes of the two directional links between every two second IP forwarding devices and a proportion set of each service type;
and determining the possible forwarding path with the highest path quality of each service type in two directions between every two second IP forwarding devices as the optimal forwarding path corresponding to the corresponding direction and the corresponding service type between every two second IP forwarding devices.
4. The method according to any of claims 1 to 3, wherein determining whether existing forwarding paths of each service type in two directions between two pairs of the second IP forwarding devices need to be switched to corresponding optimal forwarding paths specifically comprises:
determining whether the existing forwarding paths corresponding to the service types in two directions between every two second IP forwarding devices are the same as the optimal forwarding path;
if the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices is different from the optimal forwarding path, calculating a difference value between the path quality of the existing forwarding path corresponding to the one service type in the one direction between the two second IP forwarding devices and the path quality of the optimal forwarding path, and obtaining a path quality difference value corresponding to the one service type in the one direction between the two second IP forwarding devices;
determining whether a path quality difference value of the one service type in the one direction between the two second IP forwarding devices is greater than an anti-oscillation threshold value;
if the path quality difference value of the service type in the one direction between the two second IP forwarding devices is greater than the anti-oscillation threshold value, determining that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path; if the difference value of the path quality of the service type in the one direction between the two second IP forwarding devices is less than or equal to the anti-oscillation threshold, it is determined that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices does not need to be switched to the corresponding optimal forwarding path.
5. An IP-based apparatus for accelerating a wide area network, the wide area network comprising an IP scheduling device and a first IP forwarding device, the apparatus being applied in the IP scheduling device, the apparatus comprising:
the building module is used for selecting a second IP forwarding device from the first IP forwarding devices to build a virtual forwarding network;
the acquisition module is used for acquiring parameter values of link dynamic parameters of two directional links between two adjacent second IP forwarding devices;
the first determining module is used for determining the optimal forwarding path of each service type in two directions between every two second IP forwarding devices according to the parameter values of the link dynamic parameters of the links in two directions between two adjacent second IP forwarding devices and the proportion set of each service type;
a second determining module, configured to determine whether an existing forwarding path of each service type in two directions between every two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path;
a notification module, configured to notify, if an existing forwarding path of at least one service type in at least one direction between two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path, the optimal forwarding path to be switched in the corresponding direction and corresponding to the service type to the second IP forwarding device included in the optimal forwarding path to be switched, so that the second IP forwarding device included in the optimal forwarding path to be switched performs packet forwarding according to the optimal forwarding path to be switched;
the obtaining module is specifically configured to:
sending a link dynamic parameter to the second IP forwarding device, so that the second IP forwarding device obtains a parameter value of the link dynamic parameter from a directional link of an adjacent second IP forwarding device and sends the parameter value to the IP scheduling device;
and receiving the parameter value of the link dynamic parameter sent by the second IP forwarding equipment.
6. The apparatus of claim 5, wherein the building block is specifically configured to:
respectively establishing connection channels with the first IP forwarding equipment;
acquiring first IP forwarding equipment which successfully establishes a connection channel to obtain second IP forwarding equipment;
and constructing the second IP forwarding equipment into a virtual forwarding network.
7. The apparatus of claim 5, wherein the first determining module is specifically configured to:
determining possible forwarding paths and path qualities of the service types in two directions between every two second IP forwarding devices according to parameter values of the link dynamic parameters of the two directional links between two adjacent second IP forwarding devices, link inherent attributes of the two directional links between every two second IP forwarding devices and a proportion set of each service type;
and determining the possible forwarding path with the highest path quality of each service type in two directions between every two second IP forwarding devices as the optimal forwarding path corresponding to the corresponding direction and the corresponding service type between every two second IP forwarding devices.
8. The apparatus of any one of claims 5-7, wherein the second determining module is specifically configured to:
determining whether the existing forwarding paths corresponding to the service types in two directions between every two second IP forwarding devices are the same as the optimal forwarding path;
if the existing forwarding path corresponding to one service type in one direction between the two second IP forwarding devices is different from the optimal forwarding path, calculating a difference value between the path quality of the existing forwarding path corresponding to the one service type in the one direction between the two second IP forwarding devices and the path quality of the optimal forwarding path, and obtaining a path quality difference value corresponding to the one service type in the one direction between the two second IP forwarding devices;
determining whether a path quality difference value of the one service type in the one direction between the two second IP forwarding devices is greater than an anti-oscillation threshold value;
if the path quality difference value of the service type in the one direction between the two second IP forwarding devices is greater than the anti-oscillation threshold value, determining that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices needs to be switched to a corresponding optimal forwarding path; if the difference value of the path quality of the service type in the one direction between the two second IP forwarding devices is less than or equal to the anti-oscillation threshold, it is determined that the existing forwarding path of the service type in the one direction between the two second IP forwarding devices does not need to be switched to the corresponding optimal forwarding path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611208461.3A CN106789650B (en) | 2016-12-23 | 2016-12-23 | Wide area network acceleration method and device based on IP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611208461.3A CN106789650B (en) | 2016-12-23 | 2016-12-23 | Wide area network acceleration method and device based on IP |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106789650A CN106789650A (en) | 2017-05-31 |
| CN106789650B true CN106789650B (en) | 2020-05-26 |
Family
ID=58920065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611208461.3A Active CN106789650B (en) | 2016-12-23 | 2016-12-23 | Wide area network acceleration method and device based on IP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106789650B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109561057A (en) * | 2017-09-27 | 2019-04-02 | 中兴通讯股份有限公司 | A kind of content distributing network entities business processing method, apparatus and system |
| CN109104369B (en) * | 2017-11-30 | 2020-04-03 | 新华三技术有限公司 | Path selection method and device |
| CN111182607B (en) * | 2019-12-30 | 2021-09-24 | 四川速宝网络科技有限公司 | Double-path forwarding acceleration method based on 4G router |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101043236A (en) * | 2006-05-10 | 2007-09-26 | 华为技术有限公司 | Method for controlling emission power of mesh network node and mesh network node |
| CN103139301A (en) * | 2013-02-05 | 2013-06-05 | 华南师范大学 | Internet access accelerating method and device which are used in content distribution network system |
| CN104243345A (en) * | 2013-06-08 | 2014-12-24 | 中国移动通信集团公司 | Traffic scheduling method, system and device based on service types |
| CN104579961A (en) * | 2013-10-11 | 2015-04-29 | 中国移动通信集团公司 | Scheduling method and device for data message |
-
2016
- 2016-12-23 CN CN201611208461.3A patent/CN106789650B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101043236A (en) * | 2006-05-10 | 2007-09-26 | 华为技术有限公司 | Method for controlling emission power of mesh network node and mesh network node |
| CN103139301A (en) * | 2013-02-05 | 2013-06-05 | 华南师范大学 | Internet access accelerating method and device which are used in content distribution network system |
| CN104243345A (en) * | 2013-06-08 | 2014-12-24 | 中国移动通信集团公司 | Traffic scheduling method, system and device based on service types |
| CN104579961A (en) * | 2013-10-11 | 2015-04-29 | 中国移动通信集团公司 | Scheduling method and device for data message |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106789650A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9992103B2 (en) | Method for providing sticky load balancing | |
| EP2882150B1 (en) | Physical path determination for virtual network packet flows | |
| Qi et al. | Assessing container network interface plugins: Functionality, performance, and scalability | |
| CN106716376B (en) | Providing functional requirements for network connections from a local library | |
| US10178017B2 (en) | Method and control node for handling data packets | |
| CN114553752B (en) | Network performance test method and device based on simulation software and computer equipment | |
| CN106789650B (en) | Wide area network acceleration method and device based on IP | |
| Abdelsalam et al. | QUIC-proxy based architecture for satellite communication to enhance a 5G scenario | |
| CN116633934A (en) | Load balancing method, device, node and storage medium | |
| Hussein et al. | SDN for MPTCP: An enhanced architecture for large data transfers in datacenters | |
| CN113301000A (en) | Data transmission method, device, medium and equipment | |
| US20150372924A1 (en) | Network routing overlay | |
| Baggan et al. | A comprehensive analysis and experimental evaluation of routing information protocol: An elucidation | |
| CN110635972B (en) | Network testing method, network testing device, network tester and computer readable storage medium | |
| CN105208074A (en) | Path analysis method and device for asymmetric route based on Web server | |
| US10251105B2 (en) | Dynamic mobility management system | |
| Tripathi et al. | Ensuring reliability in cloud computing and comparison on IPv6 encouraged with protocols | |
| Kuri et al. | Performance Measurement of IoT Traffic Through SRv6 Network Programming | |
| CN112910791A (en) | Diversion system and method thereof | |
| Ashraf et al. | Performance analysis of network applications on IPv6 cloud connected virtual machine | |
| CN105765903A (en) | Topology discovery method and device | |
| Saini et al. | Implementation of Secured Wired and WLAN Network Using eNSP | |
| Muhambe et al. | Evaluation of routing performance using OSPF and multi-controller based network architecture | |
| Sulaeman | A highly-available multiple region multi-access edge computing platform with traffic failover | |
| KR101538667B1 (en) | Network system and method for controlling network |
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 |