HK1229970A1

HK1229970A1 - Data routing across multiple autonomous network systems

Info

Publication number: HK1229970A1
Application number: HK17103397.4A
Authority: HK
Inventors: 李明
Original assignee: 李明
Filing date: 2017-04-05
Publication date: 2017-11-24

Abstract

Systems and methods providing a route optimization mechanism for transmitting data traffic across different autonomous systems based on real-time route performance detection. Regarding a request for routing data between a source node that is coupled to a first autonomous system and a destination node located in a second autonomous system, each of a plurality of edge nodes in the first autonomous system operates to detect and evaluate real-time route performance. The evaluation results are compared and used to select an edge node and an associated link for transporting data between the source node and the destination node. The route optimization mechanism can be adopted in an SDN-based or other virtual network autonomous system.

Description

Data routing across multiple autonomous network systems

Technical Field

The present disclosure relates generally to the field of network traffic routing, and more particularly to the field of routing across multiple autonomous systems.

Background

An autonomous system refers to a network or collection of networks managed by a single entity or organization (e.g., an internet service provider). In general, an autonomous system is a heterogeneous network with many different subnetworks having combined routing logic and common routing policies. Each sub-network is assigned a globally unique autonomous system number. In general, information for one autonomous system, such as network topology, conditions, and status, required by conventional route determination processes is not readily available to another autonomous system.

The Border Gateway Protocol (BGP) is a standard exterior gateway protocol designed to exchange routing and reachability information between autonomous systems on the internet. BGP is used to make routing decisions based on paths, network policies, or rule sets configured by the network administrator, and is also involved in making core routing decisions. BGP may be used for routing within autonomous systems. In this application, it is referred to as the Internal Border Gateway Protocol (iBGP). In contrast, an internet application of a protocol (across multiple autonomous systems) may be referred to as the external border gateway protocol (eBGP).

In a Software Defined Network (SDN) architecture, the data forwarding plane and the control plane implementing the important network routing and switching functions are decoupled. The control plane may be logically centralized and implemented with various hardware components of different architectures. As a result, the data plane may utilize inexpensive and simplified network switches or routers that may be configured by the SDN controller. SDN paradigms are gaining popularity in both research and business environments due to their scalability, cost effectiveness, reliability, and flexibility in customizing and optimizing network services for specific user needs.

Unfortunately, BGP was not developed for SDN and thus cannot be used as a routing protocol for routing data across autonomous systems involving SDN. In general, there is a lack of efficient mechanisms to facilitate data delivery between different autonomous systems in which at least one system includes an SDN. As a result, the quality of service (QoS) requirements for such data transmission cannot be met.

Disclosure of Invention

Accordingly, it would be advantageous to provide a route optimization mechanism for communicating data across different autonomous systems involving a Software Defined Network (SDN).

Systems and methods for route detection for transmitting data across different autonomous systems are provided herein. For a given source node coupled to a first autonomous system and a destination node in a second autonomous system, the route detection includes selecting an egress edge node of the first autonomous system for routing data between the source and the destination. A plurality of edge nodes of the first autonomous system are configured to collect and evaluate real-time network performance information between the respective edge nodes and the destination node. The performance data and the evaluation results are supplied from each edge node to a central controller of the first autonomous system. Accordingly, the central controller selects the edge node according to quality of service (QoS) and/or other constraints for communicating outgoing traffic to the destination node. In one embodiment, the first autonomous system comprises a Software Defined Network (SDN) or a virtual network, and the edge node corresponds to a point of presence of the network comprising route detection logic and performance evaluation logic.

Thus, edge nodes and data routes providing superior transmission performance can be efficiently determined even in situations where topology information of the second autonomous system remains inaccessible to the first autonomous system. Furthermore, because the routes are selected based on real-time networking, the current conditions and states of the network elements and links are taken into account, which advantageously further ensures quality of service.

According to one embodiment, a computer-implemented method of routing data across different autonomous systems includes identifying a source node coupled to a first autonomous system and a destination node in a second autonomous system for routing data, wherein the first autonomous system includes a plurality of edge nodes. Each edge node of the plurality of edge nodes is instructed to detect network performance between the edge node and the destination node. The detected information is evaluated and compared and used to select an edge node from a plurality of edge nodes. A route for routing data between the selected edge node and the destination node is determined.

The foregoing is a summary and thus contains, by necessity, simplifications, generalizations, and omissions of detail; consequently, those skilled in the art will appreciate that the summary is illustrative only and is not intended to be in any way limiting. Other aspects, inventive features, and advantages of the present invention, as defined solely by the claims, will become apparent in the non-limiting detailed description set forth below.

Drawings

Embodiments of the present invention will be better understood from a reading of the following detailed description when taken in conjunction with the drawings in which like reference designators refer to like elements, and in which:

FIG. 1 illustrates an exemplary communication system in which data traffic may be routed across two autonomous systems according to one embodiment of the present disclosure;

FIG. 2 is a flow diagram depicting an exemplary computer-implemented method of discovering data routes across multiple autonomous systems according to one embodiment of the present disclosure;

figure 3 illustrates a configuration of an exemplary SDN-based autonomous system configured to discover optimized paths for routing data to another autonomous system, according to one embodiment of the present disclosure; and

figure 4 is a block diagram illustrating a configuration of an exemplary SDN central controller device capable of intelligently determining optimized routes across multiple autonomous systems based on real-time link performance data, according to one embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings. While the invention will be described in conjunction with the preferred embodiments, it will be understood that they are not intended to limit the invention to these embodiments. On the contrary, the invention is intended to cover alternatives, modifications and equivalents, which may be included within the spirit and scope of the invention as defined by the appended claims. Furthermore, in the following detailed description of embodiments of the invention, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, one of ordinary skill in the art will realize that the invention may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail as not to unnecessarily obscure aspects of the embodiments of the invention. Although the method is depicted as a sequence of numbered steps for clarity, the numbering does not necessarily dictate the order of the steps. It should be understood that certain steps may be skipped, performed in parallel, or performed without the requirement of maintaining a strict order of sequence. The drawings showing embodiments of the invention are semi-diagrammatic and not to scale and, particularly, some of the dimensions are for the clarity of presentation and are shown exaggerated in the drawing figs. Similarly, although the views in the drawings generally show a similar orientation for ease of description, this depiction in the drawings is arbitrary in large part. In general, the invention can be operated in any orientation.

Symbols and terms

It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the following discussions, it is appreciated that discussions utilizing terms such as "processing" or "accessing" or "executing" or "storing" or "rendering" or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories and other computer readable media into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices. When components appear in several embodiments, the use of the same reference numerals indicates that the components are the same as illustrated in the original embodiment.

Data routing across multiple autonomous network systems

Embodiments of the present disclosure provide a route optimization mechanism for transmitting data traffic across different autonomous systems based on real-time route performance detection. In connection with a request for routing data between a source node coupled to a first autonomous system and a destination node located in a second autonomous system, each of a plurality of edge nodes in the first autonomous system operates to detect and evaluate real-time routing (or link) performance. The evaluation results are compared and used to select edge nodes and associated links for transmitting data between the source node and the destination node.

Fig. 1 illustrates an exemplary communication system 100 in which data traffic may be routed across two autonomous systems 110 and 120 according to one embodiment of the disclosure. Each autonomous system 110 or 120 includes network elements within a defined domain that are owned, operated or managed by a particular entity (e.g., an internet service provider). Both autonomous systems 110 and 120 are coupled to a core network 130, and core network 130 may be a public access network such as the internet, a physically separate intranet, or other interconnection. First autonomous system 110 includes ingress edge node 112, egress edge node 113 and 116, and central controller 111. A source node (not explicitly shown) is communicatively coupled to the first autonomous system. The destination node 122 is located in a second autonomous system 120 comprising an ingress edge node 121.

For example, a route discovery request for data transmission between a source node and a destination node 122 is received at an ingress edge node 112 via a first autonomous system 110. In response to the request, each of the plurality of egress edge nodes 113 and 116 is equipped to collect real-time performance data for one or more routes linking the edge node to the destination node 122 in accordance with the present disclosure. Each egress edge node is also equipped to evaluate routing performance (e.g., by computing a set of metrics) based on the collected data. The performance data and evaluation results are communicated to the central controller 111 in the first autonomous system 110 and used to make a route determination that identifies the best egress edge node and associated route for routing subsequent data traffic between the selected egress node and the destination node 122. In addition, a link within the first autonomous system between the ingress edge node and the selected egress edge node is determined according to a route optimization procedure to achieve optimized end-to-end data transfer. As a result, a data transmission route is dynamically established between the source node and the destination node via the selected egress edge node, the public network 130, and the ingress edge node 121 of the autonomous system 2120. However, in some embodiments, more than one egress edge node of first autonomous system 110 may be selected for transmitting data in a load sharing and balancing manner.

Thus, an optimized data transmission route across multiple autonomous systems may be selected, regardless of the availability of network topology information of the autonomous systems involved. Furthermore, the transmission route is selected based on real-time network performance and advantageously takes into account the current conditions and states of the network elements and links. As a result, the selected route advantageously provides enhanced quality of service.

Additionally, the route between ingress edge node 112 and the selected egress edge node (e.g., node 113) may be determined in any suitable manner known in the art. In some embodiments, the ingress edge node 112 can collect real-time performance data and evaluate the collected performance data for one or more routes directed to the selected edge node 113. It will be appreciated that the evaluation process performed by the ingress edge node may use the same or different criteria or metrics as used by the egress edge node as described above. Based on the collected data and the evaluation results, a routing decision regarding data transmission within first autonomous system 110 is made, for example, by central controller 111, ingress edge node 112, or any other suitable network element in system 110. In this way, the entire source-to-destination transmission route is advantageously determined based on real-time network performance.

FIG. 2 is a flow diagram depicting an exemplary computer-implemented method 200 of discovering a data transmission route across multiple autonomous systems according to one embodiment of the disclosure. In this example, data will be routed through the first autonomous system to a target IP address (destination node) in the second autonomous system. At 201, a user request to access a destination is received at an ingress edge node of a first autonomous system. In response, a route discovery request is generated for discovering a route for transmitting data between the first autonomous system and the destination node.

At 202, a route detection request is broadcast to a plurality of edge nodes that qualify as egress nodes for a first autonomous system. At 203, each edge node of the plurality of edge nodes collects performance data regarding candidate links between the edge node and the destination node. At 204, each edge node processes the collected performance data and evaluates it according to evaluation criteria. The evaluation results and optionally the detected performance data are submitted to a central controller of the first autonomous system.

As will be appreciated by those skilled in the art, the present disclosure is not limited to any particular mechanism for obtaining routing performance data at an edge node (egress or ingress) of an autonomous system. In some embodiments, the egress edge node is configured to generate test packets (e.g., conforming to the Border Gateway Protocol (BGP)) and send them to candidate routes directed to destination nodes located in another autonomous system. Based on the routing behavior in response to the test packet, the egress edge node derives performance information about the link between the edge node and the destination along the route. The performance information may relate to quality of service policies regarding availability, throughput, bandwidth utilization, speed, stability, packet loss, Round Trip Time (RTT), reliability, unreachable time, latency, error rate, CPU and/or memory utilization and associated latency, and the like.

At 205, the central controller applies a policy or other constraint to the submitted evaluation results and selects edge nodes and associated links to the destination accordingly. In selecting an exit point, a path between the ingress edge node and the selected exit point may be further determined, for example, according to a route optimization process. At 207, data traffic is transmitted between the source node and the destination node via the selected egress edge node.

Those skilled in the art will recognize that the present disclosure is not limited to any particular type or architecture of network that includes mechanisms for discovering routes across different autonomous systems. The autonomous systems involved may be deployed on a Wireless Local Area Network (WLAN), a Local Area Network (LAN), a Wide Area Network (WAN), etc. An autonomous system according to the present disclosure may include a virtual network, a software defined network (overlaid on a physical network or natively as the primary network), a physical-only network, or a combination thereof. For autonomous systems deployed on a virtual network (and typically a virtual private network), the edge nodes may correspond to gateway nodes, virtual routers, or any other suitable network elements. For autonomous systems deployed on an SDN, an edge node may correspond to a SDN point of presence (POP) or any other suitable network element. For autonomous systems deployed exclusively on a physical network, an edge node may correspond to a proxy server or any other suitable network element.

Figure 3 illustrates a configuration of an exemplary SDN-based autonomous system configured to discover optimized paths for routing data to another autonomous system, according to one embodiment of the disclosure. The SDN in this example has a hierarchical control system and includes a central processor 310 and local controllers 323 and 333 distributed in POPs 320 and 330. As shown, POPs 320 and 330 act as edge nodes for the first autonomous system. The central controller 310 maintains a central routing database. Each of the POPs 320 or 330 is coupled to a respective physical router. For example, router 1325 is coupled to POP 320. The destination node is located in the second autonomous system and is coupled to router 2351, which is coupled with a target IP address (or destination node) 352. Both autonomous systems are coupled to the internet 340.

In accordance with the present disclosure, SDN POPs 320 and 330 have similar configurations and each include a route detection system, a performance evaluation system, a local controller system, and an SDNOpenflow switch. It will be appreciated that these components may be implemented as hardware logic, software programs, or a combination thereof. For example, in POP320, route detection system 321 is configured to detect route information in response to a route discovery request sent from central controller 310. The routing information to be detected may be specific to network applications and services. In some embodiments, the route discovery request is generated whenever a data packet is to be transmitted outside the first autonomous system.

In some embodiments, the SDN POP320 includes BGP logic (as indicated by arrowed line 1) for collecting path information defined in BGP. For example, BGP logic is used to detect the hop count of the path between the current POP320 and the destination node 352.

The SDN POP320 is configured to generate test packets (e.g., BGP compliant) and send them to candidate routes directed to destination nodes located in another autonomous system. Based on the routing behavior in response to the test packet, the route detection system may derive performance information about the route between the POP and the destination node. In some embodiments, the performance information may relate to one or more attributes selected from availability, throughput, bandwidth utilization, speed, stability, packet loss, RTT, reliability, unreachability time, latency, error rate, CPU and memory utilization, and associated latency.

In some embodiments, varying test packets may be generated at the POP320 based on the characteristics and performance of the respective routes selected to transmit the test packets. In some embodiments, the test packets have different lengths depending on the bandwidth of the route to be evaluated. In addition, the packet generator may send out packets of different sizes, e.g., 64 byte, 128 byte and 512 byte packets, for testing a particular route or link. Accordingly, delay data corresponding to each size of the packet can be obtained separately. The bandwidth usage of the link or route, and hence the available bandwidth, can then be derived by dividing the packet size by the delay. As will be appreciated by those skilled in the art, the packet generator may be implemented in any suitable way known in the art.

In some embodiments, microflow performance data relating to specific application availability, utilization, and performance, as well as performance characteristics of the underlying servers, may be selectively collected from network devices, infrastructure, and real-world servers. The route detection system may also be configured to collect macro-flow performance data related to the aggregated network traffic based on individual connections, users, protocols, or applications.

The performance evaluation system 322 is configured to determine the link performance between the POP320 and the destination node 352, for example, by using PING, RTT, or other performance detection methods (as indicated by the arrowed line 2). The performance evaluation system 322 analyzes the performance data collected by the detection module 321 according to any suitable model or algorithm and evaluates the routes against evaluation criteria. In some embodiments, the evaluation criteria is defined in terms of bandwidth, reachability, latency, cost, jitter, link usage, real-time logging, throughput, error rate, stability, technology, modulation technique, enhanced measurement, Mean Opinion Score (MOS), or any combination thereof.

BGP information (as indicated by arrow line 3) and performance information (as indicated by arrow line 4) are communicated to central controller 310. Based on the received information and according to a set of policy constraints, the central controller 310 may decide which POP is best for routing the data to the target IP 352. For example, if POP320 is determined to be preferred over POP 310, the central controller 310 signals the local controller 323 in POP320, indicating that POP320 is selected as the egress point for routing data to the destination node 352 (as indicated by arrow line 5). In response, the local controller 323 modifies the flow table with a new entry identifying the route used for the selection of the data packet. The flow table is sent to Openflow switch 324 and used to forward subsequent data packets. The Openflow switch 324 is, for example, a virtual router in the data plane of the SDN.

Once an exit point is determined, a link within the first autonomous system between the current ingress edge node and the selected exit point is further determined, for example, according to a route optimization process. In some embodiments, this internal link is determined by the local controller of the selected edge node, e.g., based on real-time link performance data. Alternatively, the internal link may be determined by a central controller of the SDN.

Based on the performance evaluation results, SDN controller 310 may intelligently select an optimized route for data transmission. Alternatively, the SDN controller may select multiple routes that meet the application requirements to transmit data simultaneously to improve network efficiency. In the latter case, the SDN controller may intelligently allocate data flows to multiple routes according to respective routing capabilities. For example, different workloads are assigned to different routes based on load balancing.

Figure 4 is a block diagram illustrating a configuration of an exemplary SDN central controller device 400 capable of intelligently determining optimized routes across multiple autonomous systems based on real-time link performance data, according to one embodiment of the present disclosure. The device 400 may be a general purpose server computer. The central controller 400 includes a main processor 401, system memory 402, a Graphics Processing Unit (GPU)403, I/O interfaces 404 and network circuitry 405, an operating system 406, and application software 410. The application software 410 includes a central control program 420 stored in the memory 402. When executed by the host processor 401, the central control program 420 may communicate with a SDN edge node (POP) and cooperate with a lower level controller disposed therein to control data flow from a first autonomous system to a second autonomous system.

More specifically, the program of the central control program 420 includes a central route database 421 of the first autonomous system, a detection request generation 422 module, a route detection module 423, a policy repository 424, and a flow table generation module 425. Central routing database 421 maintains information about the physical and logical structure of the first autonomous system and the arrangement and state of various components and dynamic link performance provided from SDN edge nodes. The detection request generation 422 module generates a route detection request, for example, whenever a data packet is to be routed outside the first autonomous system. Based on the information contained in the database 421 and the applicable policy constraints stored in the policy repository 424, the routing module 423 applies a set of policy constraints to the detected performance data in accordance with a route optimization procedure to make routing decisions. For example, the routing module 423 may compare the evaluation results provided from the candidate edge nodes to make the selection. A decision is made to identify a selected egress edge node and a selected link that points to a destination node in another autonomous system. The decision may also identify a link within the first autonomous system between the ingress node and the selected egress edge node. Accordingly, the flow table generation module 425 generates and sends a flow table to the local controller associated with the selected egress edge node. The central controller program 420 may perform various other functions and processes as discussed in detail with reference to fig. 1-3.

It will be appreciated that the central controller program 420 may include a wide range of other modules and functions known in the art. Techniques for implementing these programmed modules are well known in the art. As will be appreciated by one of ordinary skill in the art, the central controller program 420 may be implemented in any one or more suitable programming languages known to those skilled in the art, such as C, C + +, Java, Python, Perl, C #, SQL, and the like.

Although certain preferred embodiments and methods have been disclosed herein, it will be apparent to those skilled in the art from this disclosure that variations and modifications of such embodiments and methods may be made without departing from the spirit and scope of the invention. It is intended that the invention be limited only to the extent required by the appended claims and the rules and principles applicable thereto.

Claims

1. A computer-implemented method of routing data across different autonomous systems, the method comprising:

in response to a data routing request, identifying a source node coupled to a first autonomous system and a destination node in a second autonomous system for routing the data, wherein the first autonomous system comprises a plurality of edge nodes;

instructing respective ones of the plurality of edge nodes to detect network performance between the respective edge nodes and the destination node;

collecting information about network performance detected by the plurality of edge nodes;

selecting an edge node from the plurality of edge nodes by evaluating the information; and

a route for routing the data between the selected edge node and the destination node is determined.

2. The computer-implemented method of claim 1, wherein the first autonomous system comprises a Software Defined Network (SDN), and wherein the second autonomous system comprises a virtual network.

3. The computer-implemented method of claim 2, wherein the respective edge node corresponds to a SDN point of presence (POP).

4. The computer-implemented method of claim 1, wherein the respective edge node is configured to:

transmitting a test signal to the destination node in response to the indication; and

detecting a hop count for the test signal along a link between the SDN POP and the destination node.

5. The computer-implemented method of claim 1, wherein the information relates to one or more attributes of reachability, speed, load, latency, packet loss, stability, unreachability time, round trip time, reliability, link usage, throughput, cost, jitter, and/or Mean Opinion Score (MOS).

6. The computer-implemented method of claim 1, wherein the first autonomous system comprises a physical network, and wherein the respective edge node further corresponds to an edge proxy server of the physical network.

7. The computer-implemented method of claim 1, wherein the respective edge node corresponds to a virtual router of the first autonomous system.

8. The computer-implemented method of claim 1, further comprising determining a route for routing the data between an ingress edge node of the first autonomous system and the selected edge node according to a route optimization process.

9. An apparatus implemented as an egress edge node of a first autonomous system, the apparatus comprising:

a network interface communicatively coupled to the first autonomous system, wherein the first autonomous system comprises a plurality of egress edge nodes and a central controller;

detection logic coupled to the network interface and configured to detect network performance data between the egress edge node and a destination node in the second autonomous system based on a request sent from the central controller;

evaluation logic coupled to the detection logic and configured to evaluate the network performance data with reference to an evaluation criterion;

local control logic coupled to the evaluation logic and configured to send the network performance data and evaluation results to the central controller; and

network switching logic coupled to the local control logic and configured to forward data sent from a source node to the destination node based on an instruction from the central controller indicating that the edge node is selected, wherein the source node is coupled to the first autonomous system.

10. The apparatus of claim 9, wherein the first autonomous system is associated with an Internet Service Provider (ISP) and comprises a Software Defined Network (SDN), and wherein the egress edge node corresponds to a point of presence (POP) of the SDN.

11. The apparatus of claim 10, wherein the local control logic is further configured to maintain an updated flow table based on the instructions sent from the central controller, and wherein the central control logic is further configured to determine a route between an ingress node of the first autonomous system and the egress edge node, wherein the source node is communicatively coupled to the ingress edge node.

12. The apparatus of claim 10, wherein the second autonomous system is associated with a different ISP and comprises another SDN, virtual network, or physical network.

13. The apparatus of claim 9, wherein the first autonomous system comprises a physical network, and wherein the egress edge node further corresponds to an edge proxy server of the first autonomous system.

14. The apparatus of claim 9, wherein the detection logic comprises Border Gateway Protocol (BGP) logic.

15. The apparatus of claim 9, wherein the detection logic is further configured to send a test packet to the destination node to detect the network performance data.

16. The apparatus of claim 9, wherein the network performance data relates to reachability, speed, load, latency, packet loss, stability, unreachability time, round trip time, reliability, link usage, throughput, cost, jitter, and/or Mean Opinion Score (MOS).

17. A system, comprising:

a network circuit;

a processor coupled to the network circuit;

a memory coupled to the processor and comprising instructions that when executed by the processor cause the system to perform a method of facilitating data routing across a plurality of autonomous systems, the method comprising:

collecting information of network performance detected by the plurality of edge nodes;

18. The system of claim 17, wherein the first autonomous system comprises a Software Defined Network (SDN), and wherein the second autonomous system comprises a virtual network.

19. The system of claim 18, wherein the respective edge node comprises a SDN point of presence (POP), and wherein the respective edge node is further configured to send a test signal to the destination node in response to the indication.

20. The system of claim 17, wherein the method further comprises determining a route for transmitting the data between an ingress edge node of the first autonomous system and the selected edge node, wherein the source node is communicatively coupled to the ingress edge node.