Methods for application defined virtual network service among multiple transport in sd-wan

Abstract

Some embodiments provide a method of selecting data links for an application in a network. The method receives, from a machine implementing the application, a set of identifiers of required link characteristics. Based on at least one of the identifiers, the method selects a transport group that includes a set of optional links matching the identifiers. From the selected transport group, the method selects a link matching the set of identifiers.

Description

In recent years, datacenters have come to use a large variety of types of data links to connect to external networks. These links may be wired or wireless. They may use specific types of wired connection such as Ethernet, DSL, etc. These links may have other distinguishing characteristics such as available bandwidth, expected error rates, etc. However, in the prior art, datacenters have not been able to provide applications running on machines of the data center (e.g., running on machines implemented by hosts of the datacenter) with an option to identify particular link characteristics that the application requires for most efficient functioning. Accordingly, there is a need in the art for a method that allows applications to define their link requirements and to identify a link for the application to use from groups of links selected for some defining characteristic(s).

BRIEF SUMMARY

Some embodiments provide a method of selecting data links for an application in a network. The method receives, from a machine implementing the application, a set of identifiers of required link characteristics. In some embodiments, the applications hosted on the machines leverage the Generic Networking Virtualization Encapsulation (Geneve) protocol to specify custom messages in the type-length-value (TLV) format, encapsulating each of the application packets, which can carry a specification of link characteristics towards edge forwarding nodes. Based on at least one of the identifiers, the method selects a transport group that includes a set of optional links matching the identifiers. From the selected transport group, the method selects a link matching the set of identifiers.

The method of various embodiments selects the transport group based on different characteristics. For example, the method may select the transport group based on one or more identifiers of: (1) a security and/or encryption characteristic of links in the transport group, (2) a filtering capability of links in the transport group, (3) an identifier of a presence of proxies on the links in the transport group, (4) an identifier of a lowest maximum transmission unit (MTU) size of links of the transport group, (5) a minimum throughput of the links of the transport group, (6) a maximum rate of packet drops of links of the transport group, and/or (7) a maximum rate of interface errors of links of the transport group.

The method of some embodiments also sends an identifier of the application and the selected link for the application to an edge node of the logical network. The edge node may then identify packets of the application and route the packets of the application to the selected link.

The preceding Summary is intended to serve as a brief introduction to some embodiments of the invention. It is not meant to be an introduction or overview of all inventive subject matter disclosed in this document. The Detailed Description that follows and the Drawings that are referred to in the Detailed Description will further describe the embodiments described in the Summary as well as other embodiments. Accordingly, to understand all the embodiments described by this document, a full review of the Summary, the Detailed Description, the Drawings, and the Claims is needed. Moreover, the claimed subject matters are not to be limited by the illustrative details in the Summary, the Detailed Description, and the Drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

The novel features of the invention are set forth in the appended claims. However, for purposes of explanation, several embodiments of the invention are set forth in the following figures.

FIG. 1 illustrates an example of a virtual network that is created for a particular entity using a hub that is deployed in a public cloud datacenter of a public cloud provider.

FIG. 2 illustrates a datacenter with multiple links to one or more external networks.

FIG. 3 conceptually illustrates a process of some embodiments for providing transport group identifiers to link policy analyzers of edge nodes.

FIG. 4 conceptually illustrates a process of some embodiments for selecting a link for an application.

FIG. 5 illustrates the multiple applications using links selected by a link policy analyzer.

FIG. 6 illustrates a link requirement set of some embodiments.

FIG. 7 illustrates a set of transport group identifiers of some embodiments.

FIG. 8 conceptually illustrates a computer system with which some embodiments of the invention are implemented.

DETAILED DESCRIPTION

In the following detailed description of the invention, numerous details, examples, and embodiments of the invention are set forth and described. However, it will be clear and apparent to one skilled in the art that the invention is not limited to the embodiments set forth and that the invention may be practiced without some of the specific details and examples discussed.

Some embodiments provide a method of selecting data links for an application in a network. The method receives, from a machine implementing the application, a set of identifiers of required link characteristics. In some embodiments, the applications hosted on the machines leverage the Geneve protocol to specify custom messages in the TLV format, encapsulating each of the application packets, which can carry a specification of link characteristics towards edge forwarding nodes. Based on at least one of the identifiers, the method selects a transport group that includes a set of optional links matching the identifiers. From the selected transport group, the method selects a link matching the set of identifiers.

The method of various embodiments selects the transport group based on different characteristics. For example, the method may select the transport group based on one or more identifiers of: (1) a security and/or encryption characteristic of links in the transport group, (2) a filtering capability of links in the transport group, (3) an identifier of a presence of proxies on the links in the transport group, (4) an identifier of a lowest maximum transmission unit (MTU) size of links of the transport group, (5) a minimum throughput of the links of the transport group, (6) a maximum rate of packet drops of links of the transport group, and/or (7) a maximum rate of interface errors of links of the transport group.

The method of some embodiments also sends an identifier of the application and the selected link for the application to an edge node of the logical network. The edge node may then identify packets of the application and route the packets of the application to the selected link.

As used in this document, data messages refer to a collection of bits in a particular format sent across a network. One of ordinary skill in the art will recognize that the term data message may be used herein to refer to various formatted collections of bits that may be sent across a network, such as Ethernet frames, IP packets, TCP segments, UDP datagrams, etc. Also, as used in this document, references to L2, L3, L4, and L7 layers (or layer 2, layer 3, layer 4, layer 7) are references, respectively, to the second data link layer, the third network layer, the fourth transport layer, and the seventh application layer of the OSI (Open System Interconnection) layer model.

FIG. 1 illustrates an example of a virtual network 100 that is created for a particular entity using SD-WAN forwarding elements deployed at branch sites (sometimes called “branches” or “sites”), datacenters, and public clouds. Examples of entities include a company (e.g., corporation, partnership, etc.), an organization (e.g., a school, a non-profit, a government entity, etc.), etc. In some embodiments, an SD-WAN is the application of software based network technologies that virtualize WAN connections. An SD-WAN decouples network software services from underlying hardware to create a virtualized network overlay. An SD-WAN in some embodiments connects different sites (e.g., different buildings, or locations in different neighborhood, cities, states, countries, continents, etc.) through software tools that deploy forwarding elements in the cloud (e.g., one or more public clouds, such as public clouds provided by Amazon Web Services (AWS), Microsoft, Google, and/or one or more private clouds) and connect these forwarding elements through route records.

The SD-WANs of some embodiments employ a hub and spoke architecture, in which the hubs serve as focal/intermediary points for connecting edge forwarding elements (in some embodiments, the edge forwarding elements could be routers, gateways, or other routing devices) at branch sites that serve as the spokes of the SD-WAN architecture. The branches themselves may be implemented as sites to support manufacturing, Points of Sale (POS), medical facilities such as hospitals and clinics, or other scenarios. In some embodiments, hubs act as a central point of management for some or all connected branch sites. Hubs of some embodiments are set up by a centralized management plane orchestrator. The orchestrator notifies all the edge forwarding elements on the branches about the hubs, and the edge forwarding elements build secure overlay (in some embodiments, multi-path) tunnels to the hubs. The hubs themselves include edge forwarding elements, typically deployed in datacenters to allow branches to access the datacenters' resources and to route traffic within and outside the SD-WAN.

The edge forwarding elements connect to each other either directly or through a hub (meaning traffic from one branch site would go through that site's edge forwarding element to a hub forwarding element at a datacenter, and this hub forwarding element would then relay the traffic to another branch site through that site's edge forwarding element). Similarly, in some embodiments, traffic from branches passes through a hub, then out of the SD-WAN, over an external network to an external (outside the SD-WAN) machine.

In FIG. 1, the SD-WAN forwarding elements include cloud gateway 105 and SD-WAN forwarding elements 130, 132, 134, and 136. The cloud gateway (CGW) in some embodiments is a forwarding element that is in a private or public datacenter 110. The CGW 105 in some embodiments has secure connection links (e.g., tunnels) with edge forwarding elements (e.g., SD-WAN edge forwarding elements (FEs) 130, 132, 134, and 136) at the particular entity's multi-machine sites (e.g., SD-WAN edge sites 120, 122, and 124), such as branch offices, datacenters, etc. These multi-machine sites are often at different physical locations (e.g., different buildings, different cities, different states, etc.) and are referred to below as multi-machine sites or nodes.

Four multi-machine sites 120-126 are illustrated in FIG. 1, with three of them being branch sites 120-124, and one being a datacenter 126. Each branch site is shown to include an edge forwarding node 130-134, while the datacenter site 126 is shown to include a hub forwarding node 136. Each branch site 120-124 and the datacenter 126 includes resources 150-156 respectively. These resources 150-156 may include servers, hosts, routers, switches, and/or other physical or logical elements (e.g., virtual machines, containers, etc.). The resources 150-156 may communicate with resources of other branches and/or other resources outside of their own site through the forwarding elements 130-136, respectively. The datacenter SD-WAN forwarding node 136 is also referred to as a hub node 136 because in some embodiments this forwarding node can be used to connect (e.g., through a VPN tunnel) to other edge forwarding nodes of the branch sites 120-124. The hub node 136 in some embodiments provides services (e.g., middlebox services) for packets that it forwards from one branch site to another branch site. The hub node 136 also provides access to the datacenter resources 156, as further described below.

Each edge forwarding element (e.g., SD-WAN edge FEs 130-134) exchanges data messages with one or more cloud gateways 105 through one or more connection links 115 (e.g., multiple connection links available at the edge forwarding element). In some embodiments, these connection links include secure and unsecure connection links, while in other embodiments they only include secure connection links. As shown by edge node 134 and gateway 105, multiple secure connection links (e.g., multiple secure tunnels that are established over multiple physical links) can be established between one edge node and a gateway.

When multiple such links are defined between an edge node and a gateway, each secure connection link in some embodiments is associated with a different physical network link between the edge node and an external network. For instance, to access external networks, an edge node in some embodiments has one or more commercial broadband Internet links (e.g., a cable modem, a fiber optic link) to access the Internet, an MPLS (multiprotocol label switching) link to access external networks through an MPLS provider's network, and/or a wireless cellular link (e.g., a 5G LTE network). In some embodiments, the different physical links between the edge node 134 and the cloud gateway 105 are the same type of links (e.g., are different MPLS links).

In some embodiments, one edge forwarding node 130-134 can also have multiple direct links 115 (e.g., secure connection links established through multiple physical links) to another edge forwarding node 130-134, and/or to a datacenter hub node 136. Again, the different links in some embodiments can use different types of physical links or the same type of physical links. Also, in some embodiments, a first edge forwarding node of a first branch site can connect to a second edge forwarding node of a second branch site (1) directly through one or more links 115, or (2) through a cloud gateway or datacenter hub to which the first edge forwarding node connects through two or more links 115. Hence, in some embodiments, a first edge forwarding node (e.g., 134) of a first branch site (e.g., 124) can use multiple SD-WAN links 115 to reach a second edge forwarding node (e.g., 130) of a second branch site (e.g., 120), or a hub forwarding node 136 of a datacenter site 126.

The cloud gateway 105 in some embodiments is used to connect two SD-WAN forwarding nodes 130-136 through at least two secure connection links 115 between the gateway 105 and the two forwarding elements at the two SD-WAN sites (e.g., branch sites 120-124 or datacenter site 126). In some embodiments, the cloud gateway 105 also provides network data from one multi-machine site to another multi-machine site (e.g., provides the accessible subnets of one site to another site). Like the cloud gateway 105, the hub forwarding element 136 of the datacenter 126 in some embodiments can be used to connect two SD-WAN forwarding nodes 130-134 of two branch sites through at least two secure connection links 115 between the hub 136 and the two forwarding elements at the two branch sites 120-124.

In some embodiments, each secure connection link between two SD-WAN forwarding nodes (i.e., CGW 105 and edge forwarding nodes 130-136) is formed as a VPN (virtual private network) tunnel between the two forwarding nodes. In this example, the collection of the SD-WAN forwarding nodes (e.g., forwarding elements 130-136 and cloud gateway 105) and the secure connections between the forwarding nodes forms the virtual network 100 for the particular entity that spans at least public or private cloud datacenter 110 to connect the branch and datacenter sites 120-126.

In some embodiments, secure connection links are defined between gateways in different public cloud datacenters to allow paths through the virtual network to traverse from one public cloud datacenter to another, while no such links are defined in other embodiments. Also, in some embodiments, the cloud gateway 105 is a multi-tenant gateway that is used to define other virtual networks for other entities (e.g., other companies, organizations, etc.). Some such embodiments use tenant identifiers to create tunnels between a gateway and edge forwarding element of a particular entity, and then use tunnel identifiers of the created tunnels to allow the gateway to differentiate data message flows that it receives from edge forwarding elements of one entity from data message flows that it receives along other tunnels of other entities. In other embodiments, gateways are single-tenant and are specifically deployed to be used by just one entity.

FIG. 1 illustrates a cluster of controllers 140 that serves as a central point for managing (e.g., defining and modifying) configuration data that is provided to the edge nodes 130-0136 and/or gateways to configure some or all of the operations. In some embodiments, this controller cluster 140 is in one or more public cloud datacenters, while in other embodiments it is in one or more private datacenters. In some embodiments, the controller cluster 140 has a set of manager servers that define and modify the configuration data, and a set of controller servers that distribute the configuration data to the edge forwarding elements (FEs), hubs and/or gateways. In some embodiments, the controller cluster 140 directs edge forwarding elements and hubs to use certain gateways (i.e., assigns a gateway to the edge forwarding elements and hubs). The controller cluster 140 also provides next hop forwarding rules in some embodiments.

FIG. 2 illustrates a datacenter 200 with multiple links 230 to one or more external networks 235. The datacenter 200 includes host computers 202A and 202B and an edge node 215. The edge node 215 connects the datacenter 200 to external networks 235 through multiple links 230. Each of the links 230 may have some or all of their characteristics (e.g., MTU bandwidth, error rate, presence of proxies on the link, etc.) different from the characteristics of the other links 230. The host computers 202A and 202B implement machines (e.g., VMs) 205A-205C. The machines 205A-205C in turn implement applications 210A-210C, respectively. The applications 210A-210C communicate with external networks 235 (e.g., to machines on the external networks) by accessing one or more of the links 230 through the SD-WAN edge FE 220 of the edge node 215. The applications 210A-210C may further communicatively connect to applications or other software or hardware of machines of another datacenter 250 (or other network connected computer or set of computers) through the external networks 235.

As further described with respect to FIG. 3, the characteristics of available links may change over time. To respond to these changes, in some embodiments, the SD-WAN edge FE 220, of FIG. 2, updates the transport groups dynamically. In some such embodiments, the configuration of the transport groups is facilitated by the network controller 240. Further, in some embodiments, reports detailing the results of the link monitoring and/or transport group monitoring are provided to an end user or administrator so that the end user or administrator can react to changes in the link characteristics or transport groups if necessary.

The host computers 202A and 202B send link requirements 212A-212C for each app 210A-210C to the SD-WAN edge FE 220, which in turn sends the link requirements to a link policy analyzer 225. The link policy analyzer 225 also receives transport group identifiers 245 from a network controller 240. The process of some embodiments for generating the transport group identifiers 245 is described with respect to FIG. 3. The process of selecting a link for a particular application, performed by the link policy analyzer 225 is described with respect to FIG. 4. Characteristics of the link requirements for applications of some embodiments are described with respect to FIG. 6. Characteristics of the transport group identifiers of some embodiments are described with respect to FIG. 7.

FIG. 3 conceptually illustrates a process 300 of some embodiments for providing transport group identifiers to link policy analyzers of edge nodes. In some embodiments, the process 300 is performed by a network controller such as network controller 240 of FIG. 2. The process 300, of FIG. 3, identifies (at 305) characteristics of available links. For example, the process 300 may identify characteristics such as throughput, error rate, security features, etc. Characteristics of links are further described with respect to FIGS. 6 and 7, below. The process 300 then groups (at 310) the available links (e.g., links 230 of FIG. 2 that SD-WAN FE 220 uses to communicate with external networks) into multiple transport groups.

In the process 300 of FIG. 3, links are assigned to a particular transport group based on the links having the characteristics that define that transport group. In some embodiments, the defining characteristics of each transport group include at least one characteristic that is not based on the physical nature of the links (e.g., not based on whether the link is wireless, wired, or using a particular type of physical interface). The transport groups of some embodiments are not exclusive, so any particular link may be assigned to multiple transport groups so long as the link has the defining characteristic of each transport group to which it is assigned. A defining characteristic of a transport group could be a threshold value (i.e., a minimum or maximum value of some characteristic of the links in the group). A defining characteristic could also be the presence or absence of some feature, such as the presence of a particular security protocol that is applied to some links or the absence of proxies on some links.

Once the links are assigned to the transport groups, the process 300 provides (at 315) the transport group identifiers to link policy analyzers of edge nodes. In some embodiments, the transport group identifiers specify the defining characteristic(s) of each transport group, as well as identifiers of the links in each transport group. The identifier of each link of a transport group, in some embodiments, is accompanied by identifiers of additional characteristics of the link. In other embodiments, the link is identified as being a link of that transport group, but no identifiers of additional characteristics of the link are sent with the transport group identifier. The process 300 then ends.

Although for the sake of description, the process 300 is shown as a linear flow chart with a start and an end, in some embodiments, the process 300 is repeated as long as applications need links. That is, the state of the available links is dynamic as various link characteristics may change over time (e.g., throughput may improve or degrade, features may be added or removed in response to network conditions, etc.). These changes may qualify or disqualify the links for inclusion in different transport groups over time. Therefore the links in some embodiments are repeatedly or continuously monitored and the transport group members are adjusted in accord with changed characteristics of the monitored links. Thus, such embodiments produce more resilient matches between the required link characteristics for the applications and their assigned links at any given point of time.

In some embodiments, the active link monitoring continuously keeps track of various link characteristics and metrics. In other embodiments, this mechanism is extended to actively probe and monitor link state/attributes related to various links and transport groups.

Once the process 300 is complete, a link policy analyzer (e.g., link policy analyzer 225 of FIG. 2) uses the transport group identifiers (e.g., transport group identifiers 245 of FIG. 2) and other data to select links for each application using the SD-WAN edge FE served by the link policy analyzer. FIG. 4 conceptually illustrates a process 400 of some embodiments for selecting a link for an application. The process 400 in some embodiments is provided by a link policy analyzer that acts as a separate module from the SD-WAN edge FE. However, one of ordinary skill in the art will understand that in other embodiments, the link policy analyzer may be a subsystem of an SD-WAN edge FE, or may be a subsystem of some other component present in a datacenter.

The process 400 receives (at 405) the transport group identifiers (e.g., from a network controller or other component implementing process 300 of FIG. 3). The process 400, of FIG. 4, also receives (at 410) a set of identifiers of required link characteristics for applications operating on VMs of host computers. Identifiers of required link characteristics of some embodiments are further described with respect to FIG. 6. In some embodiments, the applications themselves supply the required link characteristics (e.g., pre-programed required link characteristics or required link characteristics derived from an analysis of network conditions and/or other data by the applications). In other embodiments, the VM or the host computer determines the required link characteristics from a database of required link characteristics for specific applications or by analyzing the application and/or traffic generated by the application and/or in response to the application.

The process 400, of FIG. 4, selects (at 415), based on at least one required link characteristic, a transport group. For example, the defining characteristic of a transport group may be a specified minimum MTU of the links. An MTU is the size of the largest packet that can be sent on a network path without fragmenting the packet. The required link characteristic for an application could be a minimum MTU. In that example, a transport group with a minimum MTU that was at or greater than the minimum MTU of the required link characteristic would be selected by the process 400.

Once a particular transport group was selected, the process 400 would select (at 420), from the particular transport group, a link matching the rest of the required link characteristics for that application (if any). In some embodiments, when more than one link in a transport group satisfies all required link characteristics of an application, some default characteristic of the links is used to determine which of multiple satisfactory links is used. That is, in some embodiments, the network controller implements an attribute/characteristic hierarchy for a set of links, based on the set of required or preferred link characteristics of the incoming data and/or the application. The link analyzer of such embodiments ranks the importance of at least a subset of those characteristics when determining which transport group/link to assign the data from a particular application to. In some embodiments, the ranking may be based on the specific requirements for a particular application and in order of decreasing importance of the characteristics to that application. For example, an application that requires high throughput but is tolerant of a high error rate would use a link ranking list that placed the throughput ranking of the links in a transport group above the error rate ranking. The node then sends the data to the most appropriate transport group link based on the progressive ranking of each characteristic. The link analyzers of some embodiments track changes to link characteristics (e.g., determining when throughput of a link drops, when error rates increase, etc.).

In some embodiment, an application may be assigned to a different link if the characteristics of the link it had been using and/or the characteristics of the new link have changed so as to make the new link a better match for the characteristics required/preferred for the app. Additionally, in some embodiments, the rules for determining the hierarchy of links for an application could be adjusted dynamically (e.g., by the network controller or the link analyzer) throughout a period of time depending on particular circumstances or external pressures going on. In still other embodiments, one of multiple satisfactory links may be chosen at random.

In some embodiments, the required link characteristics may include preferences as well as absolute requirements. For example, a set of required link characteristics may include a requirement that a link include a particular security protocol, and a preference for a link with an MTU of at least 1300. In that example, the link policy analyzer would provide a link with that security protocol and minimum MTU if such a link were available, but would still provide a link with that security protocol and a lower MTU if a link with both the required security protocol and preferred minimum MTU were not available.

In some embodiments, when no link with all required link characteristics is available, the process 400 will provide an error message informing a user or network administrator that no satisfactory links are available for a particular application. In other embodiments when no link with all required link characteristics is available, the process 400 will select (at 420) a link that meets as many of the required link characteristics as possible. The process then ends.

The following are examples of transport groups and applications that may select particular transport groups. In the example case, there are 6 links/interfaces (Link 1, Link 2, Link 3, Link 4, Link 5, and Link 6). Links 1-3 provide larger MTUs (1450 bytes or above) while links 4-6 provide smaller MTUs (300-400 bytes). Real-time transport protocol (RTP) is a kind of data traffic which typically has small to medium sized packets (e.g., at or under 300 bytes). An application which primarily sends such RTP data traffic could use any of the links in a transport group called TG1 (which includes links with a minimum MTU of 300 and thus includes Link 1, Link 2, Link 3, Link 4, Link 5, and Link 6). In contrast, a bulk transaction type TCP application typically sends large sized packets (e.g., 1450 bytes). An application that sends such TCP traffic could require links with large MTUs. Such an application could use a transport group called TG2 (which includes links with a minimum MTU of 1450 and thus includes only Link 1, Link 2, and Link 3, which provide larger MTUs) so that the application can access maximum throughput. Within the transport group, some embodiments make use of an Adaptive Path MTU which would be the minimum native MTU within the transport group.

These link characteristic-based groups define a set of links that are acceptable for use with an application which has requirements matching the transport group's defining characteristics. This alerts the link policy analyzer that no links outside the transport group should be used for a particular application. However, within a particular transport group, the link policy analyzer of some embodiments may quickly switch the selected link for an application based on changing network conditions. For example, if the defining characteristic of a transport group is minimum path MTU for all links within a particular group, for an application that requires at least that minimum value, any link in the group is appropriate to switch the application to in the event that the originally assigned link becomes inoperative or otherwise undesirable. Similarly, in some embodiments, any TCP based applications are subject to maximum segment size (MSS) adjustments based on an adaptive path MTU within the transport group, which effectively improves and maximizes throughput utilization for the application traffic.

FIG. 5 illustrates the multiple applications using links selected by a link policy analyzer. Application 210A has been assigned to link 510. Applications 210B and 210C have been assigned to link 520. Each of the applications 210A-210C connects to the external network through SD-WAN edge FE 220. SD-WAN edge FE 220 identifies packets sent from each of the application 210A-210C and sends the packets to one or more external networks 235 through the link assigned to that application. In this embodiment, more than one application can be assigned to the same link, such as applications 210B and 210C being assigned to link 520. Such an assignment could be because both application 210B and application 210C have required link characteristics that resulted in both applications being assigned to the same transport group or because link 520 is included in multiple transport groups, with application 210B assigned to one transport group and application 210C assigned to another transport group.

FIG. 6 illustrates a link requirement set 600 of some embodiments. The link requirements set 600 is one example of a structure of a link requirements data set. The link requirements set 600 includes an application identifier 601, minimum bandwidth 602, minimum MTU 604, maximum allowed number of proxies 606, security protocols 608 and 610, and other features 612 and 614. Any or all of these values may be required for a link for the application associated with link requirements set 600.

Although the link requirement set 600 is shown as an ordered data structure with the specific type of requirements identified by their location in the data structure, one of ordinary skill in the art will understand that other orders are possible within the scope of the invention as well as alternate data structures such as using a code to identify a type of data requirement and a number to represent a particular magnitude of that requirement (e.g., an identifier such as “02” to identify a requirement as a MTU requirement followed by the number 1450 to indicate the minimum required value for the MTU).

FIG. 7 illustrates a set of transport group identifiers 700 of some embodiments. The transport group identifiers set 700 is one example of a structure of a transport group identifiers data set. Transport group identifiers set 700 includes a group identifier 701, minimum bandwidth 702, minimum MTU 704, maximum allowed number of proxies 706, security protocols 708 and 710, and other features 712 and 714. Any or all of these values may be used as the defining characteristics of the transport group defined by the transport group identifiers set 700. In addition to the specified defining characteristics of the transport group, the transport group identifiers set 700, of some embodiments, includes, for the links, link identifiers 721A-721B, link minimum bandwidth 722A-722B, a link minimum MTU 724A-724B, a link maximum allowed number of proxies 726A-726B, link security protocols 728A-728B and 730A-730B, and other link features 732A-732B and 734A-734B.

In FIG. 7, the transport group identifiers set 700 includes identifiers of multiple characteristics of the available links, such as characteristics 722A-734A of link1, in some embodiments, the transport group identifiers set 700 only contains characteristics of the group (e.g., characteristics 701-714) and identifiers of the individual links (e.g., 721A) rather than the characteristics of each link. In some such embodiments, the link characteristics are still provided by the network controller, but in separate data sets from the transport group identifiers. Such a separation of the link characteristics from the transport group identifiers would be more efficient in cases where multiple transport groups included the same links. Rather than sending all link characteristics in each transport group that includes the link, the network controller would send a set of link characteristics once, and the link policy analyzer would use the link identifiers (e.g., 721A-721B) to retrieve the link characteristics for the identified link from the set of link characteristics.

Although the transport group identifiers set 700 is shown as an ordered data structure with the specific type of transport group characteristics identified by their location in the data structure, one of ordinary skill in the art will understand that other orders are possible within the scope of the invention as well as alternate data structures such as using a code to identify a type of data characteristic and a number to represent a particular magnitude of that characteristic (e.g., an identifier such as “02” to identify a requirement as a MTU requirement followed by the number 1450 to indicate the minimum required value for the MTU).

This specification refers throughout to computational and network environments that include virtual machines (VMs). However, virtual machines are merely one example of data compute nodes (DCNs) or data compute end nodes, also referred to as addressable nodes. DCNs may include non-virtualized physical hosts, virtual machines, containers that run on top of a host operating system without the need for a hypervisor or separate operating system, and hypervisor kernel network interface modules. Therefore, it should be understood that where the specification refers to VMs, the examples given could be any type of DCNs, including physical hosts, VMs, non-VM containers, and hypervisor kernel network interface modules. In fact, the example networks could include combinations of different types of DCNs in some embodiments.

Although the above figures show the transport group identifiers being generated by a network controller and sent to a link policy analyzer, in other embodiments, the link policy analyzer itself or the SD-WAN edge FE generates the transport croup identifiers based on the links connected to the SD-WAN edge FE. In other embodiments, the network controller identifies the link characteristics to the link policy analyzer and then the link policy analyzer generates the transport group identifiers. In still other embodiments, the network controller identifies the link characteristics to the SD-WAN edge FE, which then generates the transport group identifiers or forwards the link characteristics to the link policy analyzer (which then generates the transport group identifiers).

VMs, in some embodiments, operate with their own guest operating systems on a host using resources of the host virtualized by virtualization software (e.g., a hypervisor, virtual machine monitor, etc.). The tenant (i.e., the owner of the VM) can choose which applications to operate on top of the guest operating system. Some containers, on the other hand, are constructs that run on top of a host operating system without the need for a hypervisor or separate guest operating system. In some embodiments, the host operating system uses name spaces to isolate the containers from each other and therefore provides operating-system level segregation of the different groups of applications that operate within different containers. This segregation is akin to the VM segregation that is offered in hypervisor-virtualized environments that virtualize system hardware, and thus can be viewed as a form of virtualization that isolates different groups of applications that operate in different containers. Such containers are more lightweight than VMs.

Hypervisor kernel network interface modules, in some embodiments, are non-VM DCNs that include a network stack with a hypervisor kernel network interface and receive/transmit threads. One example of a hypervisor kernel network interface module is the vmknic module that is part of the ESXi™ hypervisor of VMware, Inc.

Many of the above-described features and applications are implemented as software processes that are specified as a set of instructions recorded on a computer-readable storage medium (also referred to as computer-readable medium). When these instructions are executed by one or more processing unit(s) (e.g., one or more processors, cores of processors, or other processing units), they cause the processing unit(s) to perform the actions indicated in the instructions. Examples of computer-readable media include, but are not limited to, CD-ROMs, flash drives, RAM chips, hard drives, EPROMs, etc. The computer-readable media does not include carrier waves and electronic signals passing wirelessly or over wired connections.

In this specification, the term “software” is meant to include firmware residing in read-only memory or applications stored in magnetic storage, which can be read into memory for processing by a processor. Also, in some embodiments, multiple software inventions can be implemented as sub-parts of a larger program while remaining distinct software inventions. In some embodiments, multiple software inventions can also be implemented as separate programs. Finally, any combination of separate programs that together implement a software invention described here is within the scope of the invention. In some embodiments, the software programs, when installed to operate on one or more electronic systems, define one or more specific machine implementations that execute and perform the operations of the software programs.

FIG. 8 conceptually illustrates a computer system 800 with which some embodiments of the invention are implemented. The computer system 800 can be used to implement any of the above-described hosts, controllers, gateway and edge forwarding elements. As such, it can be used to execute any of the above-described processes. This computer system 800 includes various types of non-transitory machine-readable media and interfaces for various other types of machine-readable media. Computer system 800 includes a bus 805, processing unit(s) 810, a system memory 825, a read-only memory 830, a permanent storage device 835, input devices 840, and output devices 845.

The bus 805 collectively represents all system, peripheral, and chipset buses that communicatively connect the numerous internal devices of the computer system 800. For instance, the bus 805 communicatively connects the processing unit(s) 810 with the read-only memory 830, the system memory 825, and the permanent storage device 835.

From these various memory units, the processing unit(s) 810 retrieve instructions to execute and data to process in order to execute the processes of the invention. The processing unit(s) may be a single processor or a multi-core processor in different embodiments. The read-only-memory (ROM) 830 stores static data and instructions that are needed by the processing unit(s) 810 and other modules of the computer system. The permanent storage device 835, on the other hand, is a read-and-write memory device. This device is a non-volatile memory unit that stores instructions and data even when the computer system 800 is off. Some embodiments of the invention use a mass-storage device (such as a magnetic or optical disk and its corresponding disk drive) as the permanent storage device 835.

Other embodiments use a removable storage device (such as a floppy disk, flash drive, etc.) as the permanent storage device 835. Like the permanent storage device 835, the system memory 825 is a read-and-write memory device. However, unlike storage device 835, the system memory 825 is a volatile read-and-write memory, such as random access memory. The system memory 825 stores some of the instructions and data that the processor needs at runtime. In some embodiments, the invention's processes are stored in the system memory 825, the permanent storage device 835, and/or the read-only memory 830. From these various memory units, the processing unit(s) 810 retrieve instructions to execute and data to process in order to execute the processes of some embodiments.

The bus 805 also connects to the input and output devices 840 and 845. The input devices 840 enable the user to communicate information and select commands to the computer system 800. The input devices 840 include alphanumeric keyboards and pointing devices (also called “cursor control devices”). The output devices 845 display images generated by the computer system 800. The output devices 845 include printers and display devices, such as cathode ray tubes (CRT) or liquid crystal displays (LCD). Some embodiments include devices such as touchscreens that function as both input and output devices 840 and 845.

Finally, as shown in FIG. 8, bus 805 also couples computer system 800 to a network 865 through a network adapter (not shown). In this manner, the computer 800 can be a part of a network of computers (such as a local area network (“LAN”), a wide area network (“WAN”), or an Intranet), or a network of networks (such as the Internet). Any or all components of computer system 800 may be used in conjunction with the invention.

Some embodiments include electronic components, such as microprocessors, storage and memory that store computer program instructions in a machine-readable or computer-readable medium (alternatively referred to as computer-readable storage media, machine-readable media, or machine-readable storage media). Some examples of such computer-readable media include RAM, ROM, read-only compact discs (CD-ROM), recordable compact discs (CD-R), rewritable compact discs (CD-RW), read-only digital versatile discs (e.g., DVD-ROM, dual-layer DVD-ROM), a variety of recordable/rewritable DVDs (e.g., DVD-RAM, DVD-RW, DVD+RW, etc.), flash memory (e.g., SD cards, mini-SD cards, micro-SD cards, etc.), magnetic and/or solid state hard drives, read-only and recordable Blu-Ray® discs, ultra-density optical discs, any other optical or magnetic media, and floppy disks. The computer-readable media may store a computer program that is executable by at least one processing unit and includes sets of instructions for performing various operations. Examples of computer programs or computer code include machine code, such as is produced by a compiler, and files including higher-level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter.

While the above discussion primarily refers to microprocessors or multi-core processors that execute software, some embodiments are performed by one or more integrated circuits, such as application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs). In some embodiments, such integrated circuits execute instructions that are stored on the circuit itself.

As used in this specification, the terms “computer”, “server”, “processor”, and “memory” all refer to electronic or other technological devices. These terms exclude people or groups of people. For the purposes of the specification, the terms “display” or “displaying” mean displaying on an electronic device. As used in this specification, the terms “computer-readable medium,” “computer-readable media,” and “machine-readable medium” are entirely restricted to tangible, physical objects that store information in a form that is readable by a computer. These terms exclude any wireless signals, wired download signals, and any other ephemeral or transitory signals.

While the invention has been described with reference to numerous specific details, one of ordinary skill in the art will recognize that the invention can be embodied in other specific forms without departing from the spirit of the invention. For instance, several of the above-described embodiments deploy gateways in public cloud datacenters. However, in other embodiments, the gateways are deployed in a third-party's private cloud datacenters (e.g., datacenters that the third-party uses to deploy cloud gateways for different entities in order to deploy virtual networks for these entities). Thus, one of ordinary skill in the art would understand that the invention is not to be limited by the foregoing illustrative details, but rather is to be defined by the appended claims.

Claims

1. A method of selecting for an application operating at a first site one of a plurality of data links used by an edge router at the first site, the edge router connected to a set of one or more other sites through a software-defined wide area network (SD-WAN), the method comprising: at the first site: identifying, for an application, a set of one or more link characteristics;based on the identified set of link characteristics, selecting a transport group comprising a set of one or more candidate links with a matching set of link characteristics; andfrom the selected transport group, selecting one of the links in the transport group;using the selected link to forward data messages associated with the application.

2. The method of claim 1, wherein the received set of link characteristics is associated with an identifier of the application, received at the edge forwarding node.

3. The method of claim 2, wherein the edge router identifies packets from the application and routes the packets from the application to the selected link.

4. The method of claim 1, wherein the first site comprises a link analyzer that analyzes the links.

5. The method of claim 1, wherein the transport group is selected based on at least a required link characteristic comprising a lowest maximum transmission unit (MTU) size of links of the transport group.

6. The method of claim 1, wherein the set of link characteristics comprises at least two of a minimum throughput, a maximum rate of packet drops, a maximum rate of interface errors, and security characteristic, and filtering capability.

7. The method of claim 1, wherein the set of link characteristic comprises a presence of a proxy on a link.

8. The method of claim 1, wherein the link is selected based on a default ranking characteristic of the link.

9. The method of claim 1, wherein the link is selected based on one or more ranking characteristics specific to the application, wherein the ranking characteristics are weighted by the importance of the characteristics to that application.

10. The method of claim 1, wherein the link is selected at random from the links in the transport group.

11. A non-transitory machine readable medium storing a program that when executed by at least one processing unit of a device at a first site selects for an application operating at the first site one of a plurality of data links used by an edge router at the first site, the edge router connected to a set of one or more other sites through a software-defined wide area network (SD-WAN), the program comprising sets of instructions for: identifying, for an application, a set of one or more link characteristics;based on the identified set of link characteristics, selecting a transport group comprising a set of one or more candidate links with a matching set of link characteristics; andfrom the selected transport group, selecting one of the links in the transport group;using the selected link to forward data messages associated with the application;monitoring and updating the link characteristics during the operation of the application; andselecting the link based on latency and jitter for the application.

12. The non-transitory machine readable medium of claim 11, wherein the received set of link characteristics is associated with an identifier of the application, received at the edge forwarding node.

13. The non-transitory machine readable medium of claim 12, wherein the edge router identifies packets from the application and routes the packets from the application to the selected link.

14. The non-transitory machine readable medium of claim 11, wherein the first site comprises a link analyzer that analyzes the links.

15. The non-transitory machine readable medium of claim 11, wherein the transport group is selected based on at least a required link characteristic comprising a lowest maximum transmission unit (MTU) size of links of the transport group.

16. The non-transitory machine readable medium of claim 11, wherein the set of link characteristics comprises at least two of a minimum throughput, a maximum rate of packet drops, a maximum rate of interface errors, and security characteristic, and filtering capability.

17. The non-transitory machine readable medium of claim 11, wherein the set of link characteristic comprises a presence of a proxy on a link.

18. The non-transitory machine readable medium of claim 11, wherein the link is selected based on a default ranking characteristic of the link.

19. The non-transitory machine readable medium of claim 11, wherein the link is selected based on one or more ranking characteristics specific to the application, wherein the ranking characteristics are weighted by the importance of the characteristics to that application.

20. The non-transitory machine readable medium of claim 11, wherein the link is selected at random from the links in the transport group.