WO2017187222A1 - Robust method of distributing packet-ins in a software defined networking (sdn) network - Google Patents

Robust method of distributing packet-ins in a software defined networking (sdn) network Download PDF

Info

Publication number
WO2017187222A1
WO2017187222A1 PCT/IB2016/052337 IB2016052337W WO2017187222A1 WO 2017187222 A1 WO2017187222 A1 WO 2017187222A1 IB 2016052337 W IB2016052337 W IB 2016052337W WO 2017187222 A1 WO2017187222 A1 WO 2017187222A1
Authority
WO
WIPO (PCT)
Prior art keywords
controller
connection
group
sdn
packet
Prior art date
Application number
PCT/IB2016/052337
Other languages
French (fr)
Inventor
Ashutosh Bisht
Faseela K
Original Assignee
Telefonaktiebolaget Lm Ericsson (Publ)
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Telefonaktiebolaget Lm Ericsson (Publ) filed Critical Telefonaktiebolaget Lm Ericsson (Publ)
Priority to PCT/IB2016/052337 priority Critical patent/WO2017187222A1/en
Publication of WO2017187222A1 publication Critical patent/WO2017187222A1/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0895—Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements

Definitions

  • Embodiments of the invention relate to the field of Software Defined Networking (SDN); and more specifically to providing controller group output actions and connection group output actions in an SDN network.
  • SDN Software Defined Networking
  • SDN Software Defined Networking
  • the use of a split architecture network simplifies the network devices (e.g., switches) implementing the forwarding plane by shifting the intelligence of the network into one or more controllers that oversee the switches.
  • SDN facilitates rapid and open innovation at the network layer by providing a programmable network infrastructure.
  • OpenFlow is a protocol that enables controllers and switches in an SDN network to communicate with each other. OpenFlow enables dynamic programming of flow control policies in the network.
  • a switch may establish communication with a single controller or may establish communication with multiple controllers. Connecting to multiple controllers improves reliability, as the switch can continue to operate in OpenFlow mode even if a controller fails or a connection to a controller fails. Handover of switches between controllers is managed by the controllers, which enables fast recovery from failure and also load balancing among controllers.
  • a switch uses Packet-In messages to transfer control of a packet to the controller.
  • the controllers have very little control over the Packet-In messages received from the switches.
  • all controllers will receive all Packet-In messages from the switches, or using the OpenFlow Asynchronous Configuration, a controller can specify which Packet-In messages it wants to listen to.
  • An OpenFlow channel is a communication channel used to exchange OpenFlow messages between a switch and a controller.
  • the OpenFlow channel between a switch and a controller is a single network connection.
  • the OpenFlow channel may also be composed of a main connection and multiple auxiliary connections. Auxiliary connections are created by the switch and are helpful to improve the switch processing performance and exploit the parallelism of most switch implementations.
  • a switch that has multiple connections established with a controller will either transmit all Packet- In messages to the controller using the main connection or transmit the Packet- In messages to the controller using a randomly selected connection or using a connection that is chosen based on some algorithm on the switch side.
  • a method is implemented by a network device functioning as a switch in a Software Defined Networking (SDN) network to provide controller group output actions, where the switch is communicatively coupled to a plurality of SDN controllers in the SDN network.
  • the method includes generating an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the active SDN controller selected from the first controller group.
  • SDN Software Defined Networking
  • a method is implemented by a network device functioning as a switch in a Software Defined Networking (SDN) network to provide connection group output actions, where the switch has established a plurality of connections with an SDN controller in the SDN network.
  • the method includes generating an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the SDN controller using the active connection selected from the first connection group.
  • SDN Software Defined Networking
  • a network device is configured to function as a switch in a Software Defined
  • the network device includes a set of one or more processors and a non-transitory machine-readable storage medium having stored therein a controller group output action module, which when executed by the set of one or more processors, causes the network device to generate an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receive a packet for forwarding, determine whether the packet is to be processed according to the entry, select an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmit the packet to the active SDN controller selected from the first controller group.
  • SDN Networking
  • a network device is configured to function as a switch in a Software Defined
  • the network device includes a set of one or more processors and a non-transitory machine-readable storage medium having stored therein a connection group output action module, which when executed by the set of one or more processors, causes the network device to generate an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receive a packet for forwarding, determine whether the packet is to be processed according to the entry, select an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmit the packet to the SDN controller using the active connection selected from the first connection group.
  • SDN Networking
  • a non-transitory machine-readable medium has computer code stored therein, which when executed by a set of one or more processors of a network device that functions as a switch in a Software Defined Networking (SDN) network, causes the switch to perform operations for providing controller group output actions, where the switch is to be communicatively coupled to a plurality of SDN controllers in the SDN network.
  • SDN Software Defined Networking
  • the operations include generating an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the active SDN controller selected from the first controller group.
  • a non-transitory machine-readable medium has computer code stored therein, which when executed by a set of one or more processors of a network device that functions as a switch in a Software Defined Networking (SDN) network, causes the switch to perform operations for providing connection group output actions, where the switch is to establish a plurality of connections with an SDN controller in the SDN network.
  • SDN Software Defined Networking
  • the operations include generating an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the SDN controller using the active connection selected from the first connection group.
  • Fig. 1 is a block diagram illustrating an SDN network in which controller group output actions can be implemented, according to some embodiments.
  • Fig. 2 is a diagram illustrating a set of flow entries in a switch for providing controller group output actions, according to some embodiments.
  • FIG. 3 is a flow diagram of a process implemented by a switch for performing controller group output actions, according to some embodiments.
  • Fig. 4 is a flow diagram of a process implemented by a controller for configuring a switch to perform controller group output actions, according to some embodiments.
  • Fig. 5 is a block diagram illustrating an SDN network in which connection group output actions can be implemented, according to some embodiments.
  • Fig. 6 is a diagram illustrating a set of flow entries in a switch for providing connection group output actions, according to some embodiments.
  • Fig. 7 is a flow diagram of a process implemented by a switch for performing connection group output actions, according to some embodiments.
  • Fig. 8 is a flow diagram of a process implemented by a controller for programming a switch to perform connection group output actions, according to some embodiments.
  • Fig. 9A illustrates connectivity between network devices (NDs) within an exemplary network, as well as three exemplary implementations of the NDs, according to some
  • FIG. 9B illustrates an exemplary way to implement a special-purpose network device, according to some embodiments.
  • Fig. 9C illustrates various exemplary ways in which virtual network elements (VNEs) may be coupled, according to some embodiments.
  • VNEs virtual network elements
  • Fig. 9D illustrates a network with a single network element (NE) on each of the NDs, and within this straight forward approach contrasts a traditional distributed approach (commonly used by traditional routers) with a centralized approach for maintaining reachability and forwarding information (also called network control), according to some embodiments.
  • NE network element
  • Fig. 9E illustrates the simple case of where each of the NDs implements a single NE, but a centralized control plane has abstracted multiple of the NEs in different NDs into (to represent) a single NE in one of the virtual network(s), according to some embodiments.
  • Fig. 9F illustrates a case where multiple VNEs are implemented on different NDs and are coupled to each other, and where a centralized control plane has abstracted these multiple VNEs such that they appear as a single VNE within one of the virtual networks, according to some embodiments.
  • Fig. 10 illustrates a general purpose control plane device with centralized control plane (CCP) software, according to some embodiments.
  • SDN Software Defined Networking
  • references in the specification to "one embodiment,” “an embodiment,” “an example embodiment,” etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
  • Bracketed text and blocks with dashed borders may be used herein to illustrate optional operations that add additional features to embodiments of the invention. However, such notation should not be taken to mean that these are the only options or optional operations, and/or that blocks with solid borders are not optional in certain embodiments of the invention.
  • Coupled is used to indicate that two or more elements, which may or may not be in direct physical or electrical contact with each other, co-operate or interact with each other.
  • Connected is used to indicate the establishment of communication between two or more elements that are coupled with each other.
  • An electronic device stores and transmits (internally and/or with other electronic devices over a network) code (which is composed of software instructions and which is sometimes referred to as computer program code or a computer program) and/or data using machine-readable media (also called computer-readable media), such as machine-readable storage media (e.g., magnetic disks, optical disks, read only memory (ROM), flash memory devices, phase change memory) and machine-readable transmission media (also called a carrier) (e.g., electrical, optical, radio, acoustical or other form of propagated signals - such as carrier waves, infrared signals).
  • machine-readable media also called computer-readable media
  • machine-readable storage media e.g., magnetic disks, optical disks, read only memory (ROM), flash memory devices, phase change memory
  • machine-readable transmission media also called a carrier
  • carrier e.g., electrical, optical, radio, acoustical or other form of propagated signals - such as carrier waves, infrared signals.
  • an electronic device e.g., a computer
  • includes hardware and software such as a set of one or more processors coupled to one or more machine-readable storage media to store code for execution on the set of processors and/or to store data.
  • an electronic device may include non- volatile memory containing the code since the non-volatile memory can persist code/data even when the electronic device is turned off (when power is removed), and while the electronic device is turned on that part of the code that is to be executed by the processor(s) of that electronic device is typically copied from the slower nonvolatile memory into volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM)) of that electronic device.
  • volatile memory e.g., dynamic random access memory (DRAM), static random access memory (SRAM)
  • Typical electronic devices also include a set or one or more physical network interface(s) to establish network connections (to transmit and/or receive code and/or data using propagating signals) with other electronic devices.
  • One or more parts of an embodiment of the invention may be implemented using different combinations of software, firmware, and/or hardware.
  • a network device is an electronic device that communicatively interconnects other electronic devices on the network (e.g., other network devices, end-user devices).
  • Some network devices are "multiple services network devices" that provide support for multiple networking functions (e.g., routing, bridging, switching, Layer 2 aggregation, session border control, Quality of Service, and/or subscriber management), and/or provide support for multiple application services (e.g., data, voice, and video).
  • SDN Software defined networking
  • An SDN network typically includes multiple forwarding elements (e.g., switches) interconnected with each other and one or more controllers that control the forwarding behavior of the switches.
  • a controller can control the programming of flow tables in the switches to implement any forwarding protocol.
  • a switch forwards packets from an ingress port to an egress port according to the rules in the flow tables.
  • Each entry in a flow table (e.g., flow entry) includes a match field and a corresponding set of instructions. When an incoming packet matches the match field of a flow entry, the corresponding set of instructions are executed for that packet.
  • the set of instructions may instruct the switch to perform various operations on the packet including, but not limited to, forwarding the packet to a given port, modifying certain bits in the packet header, encapsulating the packet, and dropping the packet.
  • the switch When the switch receives a packet for which there is no matching flow entry, the switch typically forwards the packet to the controller to be analyzed. The controller then decides how the packet should be handled. The controller may decide to drop the packet, or the controller can program a flow entry in the switch that provides the switch with instructions on how to process the packet and similar packets in the future.
  • the controller in an SDN network can program a switch to add, update, or delete flow entries in a flow table both reactively (e.g., in response to the controller receiving a packet from the switch) or proactively.
  • SDN facilitates rapid innovation and deployment of network protocols by providing a programmable network infrastructure.
  • OpenFlow is a protocol that enables controllers and switches in an SDN network to communicate with each other.
  • a switch may establish communication with a single controller or may establish communication with multiple controllers. Connecting to multiple controllers improves reliability, as the switch can continue to operate in OpenFlow mode even if a controller fails or a connection to a controller fails. Handover of switches between controllers is managed by the controllers, which enables fast recovery from failure and also load balancing among controllers.
  • a switch transmits asynchronous messages such as a Packet-In message to all connected controllers.
  • a Packet-In message transfers control of a packet to the controller.
  • the Packet-In message is duplicated for each controller.
  • the controllers have very little control over the Packet-In messages received from the switches.
  • all controllers will receive all Packet-In messages from the switches, or using the OpenFlow Asynchronous Configuration, a controller can specify which Packet-In messages it wants to listen to.
  • ARP Address Resolution Protocol
  • LLDP LLC Discovery Protocol
  • DHCP Dynamic Host Configuration Protocol
  • One solution to this problem is to program a flow entry in a switch with an instruction to transmit packets matching the flow entry to a particular controller (which is referred to herein as a controller- specific output action).
  • the particular controller can be specified in the flow entry using a controller identifier assigned to that particular controller.
  • any traffic transmitted to that controller is lost.
  • other controllers need to re-program the flow entry in the switch (e.g., to transmit matching packets to a different controller) in order to avoid traffic loss.
  • Embodiments described herein improve upon the controller- specific output action mechanism described above by logically grouping controllers into controller groups and programming a flow entry in a switch with an instruction for the switch to transmit packets matching the flow entry to a controller to be selected from a particular controller group (which is referred to herein as a controller group output action).
  • the particular controller group may be specified in the flow entry using a controller group identifier assigned to the controller group.
  • the switch selects an active controller from the particular controller group and transmits the packet to the selected active controller (e.g., embedded in a Packet-In message).
  • the switch determines that a connection to a controller has been lost (e.g., due to link failure, node failure, process failure, etc.), the switch marks that controller as being inactive.
  • the switch does not select a controller that is marked as being inactive. In this way, traffic loss due to controller failure can be avoided, while still providing control over which controller the switch should transmit a packet to based on the packet type.
  • a flow entry need not be re-programmed when a controller fails, as long as there is at least one active controller remaining in the controller group.
  • Embodiments described herein further protect against a case where all of the controllers in a controller group fail by provisioning a fallback controller group for the controller group. In the case that all of the controllers in the controller group fail (e.g., are marked as being inactive), the switch may select an active controller from the fallback controller group.
  • An OpenFlow channel is a communication channel used to exchange OpenFlow messages between a switch and a controller.
  • the OpenFlow channel between a switch and a controller is composed of a single network connection.
  • the OpenFlow channel may also be composed of multiple connections (e.g., a main connection and multiple auxiliary connections).
  • OpenFlow does not provide a mechanism for the controller to specify on which connection of the OpenFlow channel it wishes to receive Packet-In messages from the switch. Rather, the decision of which connection to use is entirely up to the switch. As such, if the controller hosts multiple services, each having different latency requirements, it is not possible for the controller to assign Packet-In messages associated with a lower latency requirement service to a faster connection and assign Packet-In messages associated with a higher latency requirement service to a slower connection.
  • connection-specific output action One solution to this problem is to program flow entries in a switch with an instruction to transmit packets matching the flow entry to the controller using a particular connection (which is referred to herein as a connection- specific output action).
  • the particular connection can be specified in the flow entry using a connection identifier assigned to that particular connection.
  • any traffic transmitted to the controller using that connection is lost.
  • the impacted flow entries need to be re- programmed (e.g., to transmit matching packets to the controller using a different connection) in order to avoid traffic loss.
  • Embodiments described herein improve upon the connection- specific output action mechanism described above by logically grouping connections established with a controller into connection groups and programming a flow entry in a switch with an instruction for the switch to transmit packets matching the flow entry to the controller using a connection to be selected from a particular connection group (which is referred to herein as a connection group output action).
  • a connection group output action When an incoming packet matches the flow entry, the switch selects an active connection from the particular connection group and transmits the packet to the controller using the selected active connection (e.g., embedded in a Packet- In message). If the switch determines that a connection established with the controller has been lost (e.g., due to link failure, node failure, process failure, etc.), the switch marks that connection as being inactive.
  • the switch When selecting an active connection from a connection group, the switch does not select a connection that is marked as being inactive. In this way, traffic loss due to connection failure can be avoided, while still providing control over which connection the switch should use when transmitting a certain type of packet to the controller. Furthermore, a flow entry need not be re-programmed when a connection fails, as long as there is at least one active connection remaining in the connection group. Embodiments described herein further protect against a case where all of the connections in a connection group fail by provisioning a fallback connection group for the connection group. In the case that all of the connections in the connection group fail (e.g., are marked as being inactive), the switch may select an active connection from the fallback connection group.
  • a controller group output action or a connection group output action can be included in the set of instructions in any type of entry in the switch that is used for determining packet processing.
  • a controller group output action or a connection group output action can be included in the set of instructions in a flow entry or a group entry.
  • Fig. 1 is a block diagram illustrating an SDN network in which controller group output actions can be implemented, according to some embodiments.
  • a simple network topology of an SDN network 100 that includes three controllers (e.g., SDN controllers) (controllers 110X-Z) and three switches (switches 120A-C) is illustrated in Fig. 1.
  • Each of the controllers 110 may connect to the switches 120 over a network 115.
  • Each controller 110 is assigned a controller identifier that uniquely identifies the controller 110.
  • Controller 110X is assigned controller identifier X
  • controller 110Y is assigned controller identifier Y
  • controller 110Z is assigned controller identifier Z.
  • Each switch 120 includes a set of flow entries 130.
  • a flow entry 130 includes a packet matching criteria (e.g., match field) and a corresponding set of instructions to execute when a packet matches the packet matching criteria.
  • a packet is said to match a flow entry 130 if the packet matches the packet matching criteria of the flow entry 130.
  • the flow entries 130 are described in additional detail herein below with reference to Fig. 2.
  • the controllers 110 and the switches 120 communicate using a version of OpenFlow (e.g., OpenFlow 1.3) as the communication protocol.
  • OpenFlow can be extended as described herein below to support controller group output actions in the SDN network.
  • OpenFlow and extensions thereto
  • the controllers 110 and switches 120 can communicate using other types of protocols and that other protocols can be extended in a similar fashion to support controller group output actions.
  • the controller 110 when a controller 110 and a switch 120 first establish a connection, the controller 110 transmits an OFPT_FEATURES_REQUEST message to the switch 120 requesting that the switch 120 identify capabilities/features supported by the switch 120.
  • the switch 120 then responds to the controller with an OFPT_FEATURES_REQUEST message
  • OFPT_FEATURES_REPLY message that identifies the capabilities/features that the switch 120 supports. In OpenFlow 1.3, only certain capabilities/features are included as part of the
  • OFPT_FEATURES_REPLY message as defined by ofp_capabilities.
  • OpenFlow can be extended so that the controller 110 can be informed of additional
  • the controller 110 transmits a VENDOR_SPECIFIC_SWITCH_FEATURES_REQUEST message requesting that the switch 120 identify additional capabilities/features supported by the switch 120.
  • the switch 120 then responds to the controller 110 with a
  • VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY message includes an indication of whether the switch 120 supports controller group output action features.
  • a switch 120 maintains a logical grouping of controllers 110, which is referred to herein as a controller group.
  • Each switch 120 may maintain one or more controller groups.
  • Each controller group may be identified using a controller group identifier assigned to that controller group and may include one or more controllers 110.
  • controller 110 may be identified using a controller identifier assigned to that controller 110.
  • a switch 120 maintains a database that stores information regarding the configuration of controller groups.
  • the database may store an indication of the one or more controllers 110 included in a particular controller group.
  • the database is an Open vSwitch database (OVSDB).
  • OVSDB Open vSwitch database
  • the OVSDB can be managed using an OVSDB protocol.
  • embodiments will be described in the context where the switch 120 stores information regarding the configuration of controller groups in an OVSDB (and where an OVSDB protocol is used to manage the OVSDB).
  • the switch 120 can store information regarding the configuration of controller groups in a different type of database or storage and use a different type of protocol for managing the database or storage.
  • An OVSDB may maintain a controller table that stores configuration information regarding controllers.
  • the controller table may include fields for specifying values for various configuration parameters pertaining to a controller 110 (e.g., whether the controller 110 is a primary controller or a service controller, whether asynchronous messages are enabled for the controller 110, and a rate limit for the controller 110).
  • the other_config field of the controller table can be used to specify the controller groups to which a particular controller 110 belongs.
  • the following format can be used to specify the controller groups to which a particular controller 110 belongs.
  • Other_config "controller groups: ⁇ x>, ⁇ y>, ⁇ z>"
  • This configuration indicates that the controller 110 belongs to controller groups identified by controller group identifiers x, y, and z.
  • a controller 110 may program a switch 120 to generate a flow entry 130 in the switch 120 by transmitting an OFPT_FLOW_MOD message to the switch 120.
  • the OFPT_FLOW_MOD message includes a packet matching criteria (e.g., match field) and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from a particular controller group (e.g., a controller group output action).
  • the particular controller group may be specified using a controller group identifier assigned to that particular controller group.
  • the switch 120 selects an active controller 110 from the particular controller group and transmits the packet to the selected active controller 110 (e.g., embedded in a Packet- In message).
  • the switch 120 determines that the connection to a particular controller 110 has been lost, the switch 120 marks that particular controller 110 as being inactive. In one embodiment, the switch 120 determines that a connection to a particular controller 110 has been lost based on a determination that a Transmission Control Protocol (TCP) connection to that particular controller 110 has been terminated (e.g., which can be detected by an underlying operating system of the switch 120). In one embodiment, the switch 120 determines that a connection to a particular controller 110 has been lost based on detecting a loss of heartbeat message from that particular controller 110. In one embodiment, the switch 120 determines that a connection to a particular controller 110 has been lost based on detecting a link failure using a Bidirectional Forwarding Detection (BFD) protocol.
  • BFD Bidirectional Forwarding Detection
  • the switch 120 When selecting an active controller 110 from a controller group, the switch 120 does not select a controller 110 that is marked as being inactive. If the switch 120 determines that the connection to the particular controller 110 has been restored, the switch 120 marks that particular controller 110 as being active (e.g., by unmarking the particular controller 110 from being inactive).
  • controller CI belongs to controller groups 10 and 11.
  • Controller C2 belongs to controller groups 11 and 12.
  • Controller C3 belongs to controller groups 10 and 12.
  • controller group 10 includes two controllers (controllers CI and C3)
  • controller group 11 includes two controllers (controllers CI and C2)
  • controller group 12 includes two controllers
  • controllers C2 and C3 are controllers C2 and C3.
  • the switch 120 selects one of the active controllers 110 in controller group 10 (controller C 1 or controller C3 - assuming both of these controllers are active) and transmits the incoming packet to the selected active controller 110. If the switch 120 determines that the connection to controller C3 has been lost, the switch 120 marks controller C3 as being inactive. When a subsequent incoming packet matches the flow entry 130, the switch 120 selects one of the active controllers 110 in controller group 10 (which is only controller C3 in this example, since controller CI is marked as being inactive) and transmits the incoming packet to the selected active controller 110 (controller C3 in this example).
  • a fallback controller group is provisioned for a controller group.
  • a fallback controller group for a controller group provides protection against the case when all of the controllers 110 in the controller group fail (e.g., are all marked as being inactive). If all of the controllers 110 in a controller group fail, then the switch 120 may select an active controller 110 from the fallback controller group provisioned for the controller group and transmit the incoming packet to the selected active controller 110 from the fallback controller group.
  • a fallback controller group may be provisioned for another fallback controller group to provide additional protection against controller failures.
  • the other_config field of the Open_vSwitch table (since this configuration applies across controllers) can be used to specify the fallback controller group for a controller group.
  • the following format can be used to specify the fallback controller group for a controller group.
  • controller group identified by controller group identifier y is a fallback controller group for the controller group identified by controller group identifier x.
  • controller group 11 is provisioned as a fallback controller group for controller group 10.
  • all of the controllers 110 in controller group 10 are marked as being inactive.
  • the switch 120 will consider the controllers 110 in controller group 10 (controllers CI and C3) for selection, but all of the controllers 110 in controller group 10 are marked as being inactive.
  • Controller group 11 includes controllers CI and C2. Since controller CI is marked as being inactive, the switch 120 will not select controller CI, but select controller C2 (assuming controller C2 is active), and transmit the incoming packet to controller C2. By provisioning a fallback controller group for a controller group, traffic loss is avoided even when all of the controllers 110 in the controller group are marked as being inactive.
  • An advantage of the controller group output action mechanism is that traffic loss due to controller 110 failure can be avoided, while still providing control over which controller 110 the switch 120 should transmit a packet to based on the packet type (e.g., which enables load sharing among controllers). Another advantage is that a flow entry 130 need not be re- programmed when a controller 110 fails, as long as there is at least one active controller 110 remaining in the controller group. Yet another advantage is that the behavior of the switch 120 in terms of which controller 110 the switch 120 transmits a certain type of packet to can be dynamically modified by adding/deleting controllers 110 to/from a controller group, without modifying a flow entry 130. Also, the provisioning of a fallback controller group for a controller group protects against a case where all of the controllers 110 in a controller group fail.
  • the following exemplary structures can be used for the message exchange between a controller 110 and a switch 120 to support controller group output actions.
  • the exemplary structures extend OpenFlow to support controller group output actions.
  • VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST [0062]
  • Fig. 2 is a diagram illustrating a set of flow entries in a switch for providing controller group output actions, according to some embodiments. It is assumed that the switch 120 has three controller groups configured (controller group identified by controller group identifier X, controller group identified by controller group identifier Y, and controller group identified by controller group identifier Z). In one embodiment, the programming of the flow entries 130 in the switch 120 is controlled by one or more controllers 110. Each flow entry 130 includes a packet matching criteria and a corresponding set of instructions. When the switch 120 receives a packet that matches a packet matching criteria of a flow entry 130, the switch 120 executes the corresponding set of instructions of that flow entry 130. As illustrated, the switch 120 includes N flow entries 130.
  • the first flow entry has a packet matching criteria that matches packets that are associated with an ARP service and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from the controller group identified by controller group identifier X.
  • the switch 120 selects an active controller 110 from the controller group identified by controller group identifier X and transmits the packet to the selected active controller 110.
  • the second flow entry has a packet matching criteria that matches packets that are associated with an LLDP service and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from the controller group identified by controller group identifier Y.
  • the third flow entry has a packet matching criteria that matches packets that are associated with a DHCP service and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from a controller group identified by controller group identifier Z.
  • IP IP
  • UDP_SRC/UDP_DST 67/68
  • the fourth flow entry has a packet matching criteria that matches packet type A (which can be user-defined) and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from the controller group identified by controller group identifier Y.
  • packet type A which can be user-defined
  • the Nth flow entry is a catch-all entry that matches packets that did not match any of the other flow entries 130.
  • the corresponding instruction for this flow entry 130 is an instruction to transmit matching packets to a controller 110 to be selected from the controller group identified by controller group identifier Z.
  • the switch 120 receives an incoming packet that does not match any of the other flow entries 130 in the switch 120, the switch 120 selects an active controller 110 from the controller group identified by controller group identifier Z and transmits the packet to the selected active controller 110.
  • flow entries 130 can be programmed in a switch 120 to transmit packets associated with a given service or that match a given packet matching criteria to a controller 110 to be selected from a particular controller group.
  • This allows for an asymmetric cluster of controller groups, where each controller group handles specific services.
  • the flow entries 130 in the switch 120 are programmed such that ARP packets are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier X, LLDP packets are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Y, and DHCP packets are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Z.
  • packets having packet type A are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Y (similar to LLDP packets). Packets that do not match any of the above flow entries 130 are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Z (similar to DHCP packets).
  • the switch 120 may select an active controller 110 from a fallback controller group provisioned for the particular controller group (if one has been provisioned) and transmit the matching packet to the active controller 110 selected from the fallback controller group.
  • the flow entries 130 described herein are provided by way of example and not limitation, and that one having ordinary skill in the art will understand that the switch 120 can include any number of flow entries 130, and that the flow entries 130 can have any desired packet matching criteria.
  • the instructions of a flow entry 130 may include other instructions besides transmitting a packet to a controller 110 to be selected from a particular controller group.
  • a flow entry 130 can include instructions to push/pop tags, modify packet header fields, change the time-to-live (TTL) of the packet, and other packet processing instructions.
  • TTL time-to-live
  • a controller group output action can be included in the set of instructions in any type of entry in the switch 120 that is used for determining packet processing (and not just flow entries 130).
  • a controller group output action can be included in the set of instructions in a group entry.
  • Fig. 3 is a flow diagram of a process implemented by a switch for performing controller group output actions, according to some embodiments.
  • the operations of the flow diagram may be implemented by a network device functioning as a switch 120 in an SDN network 100, where the switch 120 is communicatively coupled to a plurality of SDN controllers 110 in the SDN network 100.
  • the operations in this and other flow diagrams will be described with reference to the exemplary embodiments of the other figures. However, it should be understood that the operations of the flow diagrams can be performed by embodiments of the invention other than those discussed with reference to the other figures, and the embodiments of the invention discussed with reference to these other figures can perform operations different than those discussed with reference to the flow diagrams.
  • the process is initiated when the switch 120 establishes a connection with an SDN controller 110.
  • the switch 120 receives a request from the SDN controller 110 to identify features supported by the switch 120 (block 305).
  • the request is in the form of the
  • the switch 120 then transmits a response to the SDN controller 110 that identifies the features supported by the switch 120 (block 310).
  • the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure.
  • the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field).
  • the switch 120 if the switch 120 supports controller group output action features, then the switch 120 includes an indication in the response transmitted to the SDN controller 110 that the switch 120 supports controller group output action features.
  • the switch 120 generates an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller 110 to be selected from a first controller group, where the first controller group includes one or more SDN controllers 110 from the plurality of SDN controllers 110 communicatively coupled to the switch 120 (block 315).
  • the entry is a flow entry 130 (e.g., OpenFlow flow entry).
  • the entry is a group entry (e.g., OpenFlow group entry).
  • the entry is generated in response to receiving an instruction from an SDN controller 110 to generate entry.
  • the instruction to generate the entry can come from any SDN controller 110 with which the switch 120 is connected.
  • the first controller group is specified in the entry using a controller group identifier assigned to the first controller group. In one
  • the instruction received from the SDN controller 110 to generate the entry includes a Controller Group Output Action structure described above, or similar structure.
  • the switch 120 receives a packet for forwarding (block 320), it determines whether the packet is to be processed according to the entry (decision block 325). In one embodiment, the switch 120 determines that the packet is to be processed according to the entry based on determining that the packet matches the packet matching criteria of the entry (e.g., when the entry is an OpenFlow flow entry). If the packet is not to be processed according to the entry, then the switch 120 may continue packet processing, as necessary (block 330).
  • the switch 120 selects an active SDN controller 110 from the first controller group (e.g., according to the instruction in the entry) (block 335) and transmits the packet to the active SDN controller 110 selected from the first controller group (block 340).
  • the switch 120 may then repeat blocks 320-340 for other packets that it receives.
  • the switch 120 marks an SDN controller 110 from the first controller group as being inactive in response to a determination that a connection to the SDN controller 110 has been lost.
  • the switch 120 does not select an SDN controller 110 that is marked as being inactive.
  • the determination that the connection to the SDN controller 110 has been lost is based on a determination that a TCP connection to the SDN controller 110 has been terminated (e.g., which can be detected by an underlying operating system of the switch 120).
  • the determination that the connection to the SDN controller 110 has been lost is based on detecting a loss of heartbeat message from the SDN controller 110.
  • the determination that the connection to the SDN controller 110 has been lost is based on detecting a link failure using Bidirectional Forwarding Detection (BFD) protocol.
  • BFD Bidirectional Forwarding Detection
  • a second controller group (that includes one or more SDN controllers 110 from the plurality of controllers communicatively coupled to the switch 120) is provisioned as a fallback controller group for the first controller group.
  • the switch 120 determines that the packet is to be processed according to the entry but that all of the one or more SDN controllers 110 in the first controller group are marked as being inactive, then the switch 120 selects an active SDN controller 110 from the second controller group and transmits the packet to the active SDN controller 110 selected from the second controller group.
  • the switch 120 maintains a database (or other type of storage) that stores information regarding the configuration of controller groups.
  • the database may store an indication of the one or more SDN controllers 110 included in a particular controller group (e.g., the first controller group and the second controller group).
  • the database may store an indication that a particular controller group is a fallback controller group for another controller group (e.g., the second controller group is a fallback controller group for the first controller group).
  • the database is an OVSDB and is managed using an OVSDB protocol.
  • Fig. 4 is a flow diagram of a process implemented by a controller for programming a switch to perform controller group output actions, according to some embodiments.
  • the operations of the flow diagram may be implemented by a network device functioning as an SDN controller 110 in an SDN network 100, where the SDN controller 110 is communicatively coupled to a switch 120 in the SDN network 100, and where the switch 120 is communicatively coupled to a plurality of SDN controllers 110 in the SDN network 100.
  • the process is initiated when the switch 120 establishes a connection with the SDN controller 110.
  • the SDN controller 110 transmits a request to the switch 120 to identify features supported by the switch 120 (block 405).
  • the request is in the form of the
  • the SDN controller 110 then receives a response from the switch 120 that identifies the features supported by the switch 120 (block 410).
  • the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure.
  • the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field).
  • the response received from the switch 120 includes an indication that the switch 120 supports controller group output action features.
  • the SDN controller 110 determines whether the switch 120 supports controller group output action features (e.g., based on the response from the switch 120 that identifies the features supported by the switch 120) (decision block 415). If the switch 120 does not support controller group output action features, then the SDN controller 110 proceeds with normal processing (e.g., without controller group output action features) (block 420).
  • controller group output action features e.g., based on the response from the switch 120 that identifies the features supported by the switch 120
  • the SDN controller 110 transmits an instruction to the switch 120 to generate an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller 110 to be selected from a first controller group, where the first controller group includes one or more SDN controllers 110 from the plurality of SDN controllers 110
  • the entry is a flow entry 130 (e.g., OpenFlow flow entry).
  • the entry is a group entry (e.g., OpenFlow group entry).
  • the first controller group is specified using a controller group identifier assigned to the first controller group.
  • the instruction transmitted to the switch 120 to generate the entry includes a Controller Group Output Action structure described above, or similar structure.
  • Fig. 5 is a block diagram illustrating an SDN network in which connection group output actions can be implemented, according to some embodiments.
  • the SDN network 100 includes three switches (switches 120A-C) and a controller 110 (e.g., SDN controller) that controls the switches 120.
  • the controller 110 has three services running on it (services 515A-C).
  • Each switch 120 may establish multiple connections with the controller 110.
  • Each connection between a switch 120 and the controller 110 is assigned a connection identifier.
  • the connection identifier uniquely identifies a connection between a switch 120 and the controller 110.
  • switch 120A has established three connections with the controller 110.
  • the first connection is assigned connection identifier X
  • the second connection is assigned connection identifier Y
  • the third connection is assigned connection identifier Z.
  • switch 120B has established three connections with the controller 110.
  • the first connection is assigned connection identifier A
  • the second connection is assigned connection identifier B
  • the third connection is assigned connection identifier C.
  • switch 120C has established three connections with the controller 110.
  • the first connection is assigned connection identifier J
  • the second connection is assigned connection identifier K
  • the third connection is assigned connection identifier L.
  • Each switch 120 includes a set of flow entries 130.
  • a flow entry 130 includes a packet matching criteria (e.g., match field) and a corresponding set of instructions to execute when a packet matches the packet matching criteria.
  • a packet is said to match a flow entry 130 if the packet matches the packet matching criteria of the flow entry 130.
  • the flow entries 130 are described in more detail herein below with reference to Fig. 6.
  • the controller 110 and the switches 120 communicate using a version of OpenFlow (e.g., OpenFlow 1.3) as the communication protocol.
  • OpenFlow can be extended as described herein below to support connection group output actions in the SDN network 100.
  • embodiments will primarily be described using OpenFlow (and extensions thereto) as the communication protocol between the controller 110 and the switches 120.
  • the controller 110 and the switches 120 can communicate using other types of protocols and that other types of protocols can be extended in a similar fashion to support connection group output actions without departing from the spirit and scope of the present disclosure.
  • the controller 110 transmits an OFPT_FEATURES_REQUEST message to the switch 120 requesting that the switch 120 identify capabilities/features supported by the switch 120.
  • the switch 120 responds to the controller 110 with an OFPT_FEATURES_REPLY message that identifies the capabilities/features supported by the switch 120.
  • the OFPT_FEATURES_REPLY message includes connection identifier information (e.g., auxiliary identifier) for the connection being established.
  • connection identifier information e.g., auxiliary identifier
  • capabilities/features are included as part of the OFPT_FEATURES_REPLY message, as defined by ofp_capabilities.
  • OpenFlow can be extended so that the controller 110 can be informed of additional capabilities/features supported by the switch 120 (e.g., vendor- specific capabilities).
  • the controller 110 transmits a
  • VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST message to the switch 120 requesting that the switch 120 identify additional capabilities/features supported by the switch 120.
  • the switch 120 then responds to the controller 110 with a
  • the switch 120 the
  • VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY message includes an indication of whether the switch 120 supports connection group output action features.
  • a switch 120 maintains a logical grouping of connections established with a controller 110, which is referred to herein as a connection group.
  • Each switch 120 may maintain one or more connection groups.
  • Each connection group may be identified using a connection group identifier assigned to that connection group and each connection group may include one or more connections.
  • Each connection may be identified using a connection identifier assigned to that connection.
  • a switch 120 maintains a database that stores information regarding the configuration of connection groups.
  • the database may store an indication of the one or more connections included in a particular connection group.
  • the database is an OVSDB.
  • the OVSDB can be managed using an OVSDB protocol.
  • embodiments will be described in the context where the switch 120 stores information regarding the configuration of connection groups in an OVSDB (and where an OVSDB protocol is used to manage the OVSDB).
  • the switch 120 can store information regarding the configuration of connection groups in a different type of database or storage and use a different type of protocol for managing the database or storage.
  • An OVSDB may maintain a controller table that stores configuration information regarding controllers 110.
  • the controller table may include fields for specifying values for various configuration parameters pertaining to a controller 110 (e.g., whether the controller 110 is a primary controller or a service controller, whether asynchronous messages are enabled for the controller 110, and a rate limit for the controller 110).
  • the other_config field of the controller table can be used to specify the connections that are included in a particular connection group.
  • the following format can be used to specify the connection that are included in a particular connection group.
  • Other_config "connection-group- ⁇ n>: ⁇ x>, ⁇ y>, ⁇ z>"
  • connection group identified by connection group identifier n includes the connections identified by connection identifiers x, y, and z.
  • a controller 110 may program a switch 120 to generate a flow entry 130 in the switch 120 by transmitting an OFPT_FLOW_MOD message to the switch 120.
  • the OFTP_FLOW_MOD message includes a packet matching criteria (e.g., match field) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from a particular connection group (e.g., a connection group output action).
  • the particular connection group may be specified using a connection group identifier assigned to that particular connection group.
  • the switch 120 selects an active connection from the particular connection group and transmits the packet to the controller 110 using the selected active connection (e.g., embedded in a Packet-In message). If the switch 120 determines that the connection has been lost, the switch 120 marks that particular connection as being inactive. In one embodiment, the switch 120 determines that a connection has been lost based on a determination that a TCP connection associated with that connection has been terminated (e.g., which can be detected by an underlying operating system of the switch 120). In one
  • the switch 120 determines that a connection has been lost based on detecting a loss of heartbeat message from the controller 110 over that connection. When selecting an active connection from a connection group, the switch 120 does not select a connection that is marked as being inactive. If the switch 120 determines that the connection has been restored, the switch 120 marks that particular connection as being active (e.g., by unmarking the particular connection from being inactive).
  • connection cl belongs to connection groups 10 and 11.
  • Connection c2 belongs to connection groups 11 and 12.
  • Connection c3 belongs to connection groups 10 and 12.
  • connection group 10 includes two connections (connections cl and c3)
  • connection group 11 includes two connections (connections cl and c2)
  • connection group 12 includes two connections (connections c2 and c3).
  • connection group 10 the switch 120 selects one of the active connections from connection group 10 (connection cl or connection c3 - assuming both of these connections are active) and transmits the incoming packet to the controller 110 using the selected active connection. If the switch 120 determines that connection c3 has been lost, the switch 120 marks connection c3 as being inactive. When a subsequent incoming packet matches the flow entry 130, the switch 120 selects one of the active connections from connection group 10 (which is only connection c3 in this example, since connection cl is marked as being inactive) and transmits the incoming packet to the controller 110 using the selected active connection (connection c3 in this example).
  • a fallback connection group is provisioned for a connection group.
  • a fallback connection group for a connection group provides protection against the case when all of the connections in the connection group fail (e.g., are all marked as being inactive). If all of the connections in a connection group fails, then the switch 120 may select an active connection from the fallback connection group provisioned for the connection group and transmit the incoming packet to the controller 110 using the active connection selected from the fallback connection group. In one embodiment, a fallback connection group may be provisioned for another fallback connection group to provide additional protection against connection failures.
  • the other_config field the controller table can be used to specify the fallback connection group for a connection group (since this configuration is per controller).
  • the following format can be used to specify the fallback connection group for a connection group.
  • connection group identified by connection group identifier y is a fallback connection group for the connection group identified by connection group identifier x.
  • connection group 11 is provisioned as a fallback connection group for connection group 10. Also assume that all of the connections in connection group 10 are marked as being inactive. When an incoming packet matches a flow entry 130 that instructs the switch 120 to transmit matching packets to the controller 110 using a connection to be selected from connection group 10, the switch 120 will consider the connections in connection group 10 (connections 1 and 3) for selection, but all of the connections in connection group 10 are marked as being inactive. As such, the switch 120 will instead consider the connections in connection group 11, which is provisioned as the fallback connection group for connection group 10. Connection group 11 includes
  • connection cl Since connection cl is marked as being inactive, the switch 120 will not select connection cl, but select connection c2 (assuming connection c2 is active) and transmit the incoming packet to the controller 110 using connection c2.
  • connection c2 By provisioning a fallback connection group for a connection group, traffic loss is avoided even when all of the connections in the connection group are marked as being inactive.
  • connection group output action mechanism An advantage of the connection group output action mechanism is that traffic loss due to connection failure can be avoided, while still providing control over which connection the switch 120 should use when transmitting a certain type of packet to the controller 110 (e.g., which enables load sharing among connections). Another advantage is that a flow entry 130 need not be re-programmed when a connection fails, as long as there is at least one active connection remaining in the connection group. Yet another advantage is that the behavior of the switch 120 in terms of which connection the switch 120 uses when transmitting a packet to a controller 110 can be dynamically modified by adding/deleting connections to/from a connection group, without modifying a flow entry 130. Also, the provisioning of a fallback connection group for a connection group protects against a case where all of the connections in a connection group fail.
  • the following exemplary structures can be used for the message exchange between the controller 110 and switches 120 for implementing connection group output actions.
  • the exemplary structures extend OpenFlow to support connection group output actions.
  • VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST [00103]
  • connection_group_id connection group from which a connection should be selected */
  • Fig. 6 is a diagram illustrating a set of flow entries in a switch for providing connection group output actions, according to some embodiments. It is assumed that the switch 120 has three connection groups configured (connection group identified by connection group identifier X, connection group identified by connection group identifier Y, and connection group identified by connection group identifier Z). In one embodiment, the programming of the flow entries 130 in the switch 120 is controlled by one or more controllers 110. Each flow entry 130 includes a packet matching criteria and a corresponding set of instructions. When the switch 120 receives a packet that matches a packet matching criteria of a flow entry 130, the switch 120 executes the corresponding set of instructions of that flow entry 130. As illustrated, the switch 120 includes N flow entries 130.
  • the first flow entry has a packet matching criteria that matches packets associated with an ARP service (e.g., service 515A) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier X.
  • the second flow entry has a packet matching criteria that matches packets associated with an LLDP service (e.g., service 515B) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y.
  • the third flow entry has a packet matching criteria that matches packets associated with a DHCP service (e.g., service 515C) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z.
  • IP IP
  • IP_PROTO 0xl l
  • UDP_SRC/UDP_DST 67/68
  • the fourth flow entry has a packet matching criteria that matches packet type A (which can be user-defined) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y.
  • packet type A which can be user-defined
  • the Nth flow entry is a catch-all entry that matches packets that did not match any of the other flow entries 130.
  • the corresponding instruction for this flow entry 130 is an instruction to transmit matching packets to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z.
  • the switch 120 receives an incoming packet that does not match any of the other flow entries 130 in the switch 120, then the switch 120 selects a connection from the connection group identified by connection group identifier Z and transmits the packet to the controller 110 using the selected active connection.
  • the flow entries 130 can be programmed in a switch 120 to transmit packets associated with a given service or that match a given packet matching criteria to the controller 110 using a connection to be selected from a particular connection group.
  • the flow entries 130 in the switch 120 are programmed such that ARP packets are transmitted to a controller 110 using a connection to be selected from the connection group identified by connection group identifier X, LLDP packets are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y, and DHCP packets are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z.
  • packets having packet type A (which may be any user-defined packet matching criteria), are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y (similar to LLDP packets).
  • Packets that do not match any of the other flow entries 130 in the switch 120 are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z (similar to DHCP packets).
  • the switch 120 may select an active connection from a fallback connection group provisioned for the particular connection group (if one has been provisioned) and transmit the matching packet to the controller 110 using the active connection selected from the fallback connection group.
  • the flow entries 130 described herein and illustrated in the diagram are provided by way of example and not limitation. It should be understood that the switch 120 can include any number of flow entries 130, and that the flow entries 130 can have any desired packet matching criteria. Also, the instructions of a flow entry 130 may include other instructions besides transmitting a packet to a controller 110 using a connection to be selected from a particular connection group. For example, a flow entry 130 can include instructions to push/pop tags, modify packet header fields, change the TTL of the packet, and other packet processing instructions.
  • a controller group output action can be included in the set of instructions in any type of entry in the switch 120 that is used for determining packet processing (and not just flow entries 130).
  • a controller group output action can be included in the set of instructions in a group entry.
  • Fig. 7 is a flow diagram of a process implemented by a switch for performing connection group output actions, according to some embodiments. In one embodiment, the operations of the flow diagram may be implemented by a network device functioning as a switch 120 in an SDN network 100, where the switch 120 has established a plurality of connections with an SDN controller 110 in the SDN network 100.
  • the process is initiated when the switch 120 establishes a connection with an SDN controller 110.
  • the switch 120 receives a request from the SDN controller 110 to identify features supported by the switch 120 (block 705).
  • the request is in the form of the
  • the switch 120 then transmits a response to the SDN controller 110 that identifies the features supported by the switch 120 (block 710).
  • the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure.
  • the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field).
  • the switch 120 if the switch 120 supports connection group output action features, then the switch 120 includes an indication in the response transmitted to the SDN controller 110 that the switch 120 supports connection group output action features.
  • the switch 120 generates an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller 110 using a connection to be selected from a first connection group, where the first connection group includes one or more
  • the entry is a flow entry 130 (e.g., OpenFlow flow entry).
  • the entry is a group entry (e.g., OpenFlow group entry).
  • the entry is generated in response to receiving an instruction from an SDN controller 110 to generate the entry.
  • the first connection group is specified in the entry using a connection group identifier assigned to the first connection group.
  • the instruction received from the SDN controller 110 to generate the entry includes a Connection Group Output Action structure described above, or similar structure.
  • the switch 120 When the switch 120 receives a packet for forwarding (block 720), it determines whether the packet is to be processed according to the entry (decision block 725). In one embodiment, the switch 120 determines that the packet is to be processed according to the entry based on determining that the packet matches the packet matching criteria of the entry (e.g., when the entry is an OpenFlow flow entry). If the packet is not to be processed according to the entry, then the switch 120 may continue packet processing, as necessary (block 730).
  • the switch 120 determines that the packet is to be processed according to the entry based on determining that the packet matches the packet matching criteria of the entry (e.g., when the entry is an OpenFlow flow entry). If the packet is not to be processed according to the entry, then the switch 120 may continue packet processing, as necessary (block 730).
  • the switch 120 selects an active connection from the first connection group (e.g., according to the instruction in the entry) (block 735) and transmits the packet to the SDN controller 110 using the active connection selected from the first connection group (block 740).
  • the switch 120 may then repeat blocks 720-740 for other packets that it receives.
  • the switch 120 marks a connection from the first connection group as being inactive in response to a determination that the connection has been lost.
  • the switch 120 does not select a connection that is marked as being inactive.
  • the determination that the connection has been lost is based on a determination that a TCP connection associated with the connection has been terminated (e.g., which can be detected by an underlying operating system of the switch 120).
  • the determination that the connection has been lost is based on detecting a loss of heartbeat message from the SDN controller 110 over the connection.
  • a second connection group (that includes one or more connection from the plurality of connections established with the SDN controller 110) is provisioned as a fallback connection group for the first connection group.
  • the switch 120 determines that the packet is to be processed according to the entry but that all of the one or more connections in the first connection group are marked as being inactive, then the switch 120 selects an active connection from the second connection group and transmits the packet to the SDN controller 110 using the active connection selected from the second connection group.
  • the switch 120 maintains a database (or other type of storage) that stores information regarding the configuration of connection groups.
  • the database may store an indication of the one or more connections included in a particular controller group (e.g., the first connection group and the second connection group).
  • the database may store an indication that a particular connection group is a fallback controller group for another connection group (e.g., the second connection group is a fallback connection group for the first connection group).
  • the database is an OVSDB and is managed using an OVSDB protocol.
  • Fig. 8 is a flow diagram of a process implemented by a controller for programming a switch to perform connection group output actions, according to some embodiments.
  • the operations of the flow diagram may be implemented by a network device functioning as an SDN controller 110 in an SDN network 100, where the controller has established a plurality of connections with a switch 120 in the SDN network 100.
  • the process is initiated when the switch 120 establishes a connection with the SDN controller 110.
  • the SDN controller 110 transmits a request to the switch 120 to identify features supported by the switch 120 (block 805).
  • the request is in the form of the
  • the SDN controller 110 then receives a response from the switch 120 that identifies the features supported by the switch 120 (block 810).
  • the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure.
  • the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field).
  • the response received from the switch 120 includes an indication that the switch 120 supports connection group output action features.
  • the SDN controller 110 determines whether the switch 120 supports connection group output action features (e.g., based on the response from the switch 120 that identifies the features supported by the switch 120) (decision block 815). If the switch 120 does not support connection group output action features, then the SDN controller 110 proceeds with normal processing (e.g., without connection group output action features) (block 820).
  • connection group output action features e.g., based on the response from the switch 120 that identifies the features supported by the switch 120
  • the SDN controller 110 transmits an instruction to the switch 120 to generate an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller 110 using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established between the SDN controller 110 and the switch 120 (block 825).
  • the entry is a flow entry 130 (e.g., OpenFlow flow entry).
  • the entry is a group entry (e.g., OpenFlow group entry).
  • the first connection group is specified using a connection group identifier assigned to the first connection group.
  • the instruction transmitted to the switch 120 to generate the entry includes a Connection Group Output Action structure described above, or similar structure.
  • FIG. 9A illustrates connectivity between network devices (NDs) within an exemplary network, as well as three exemplary implementations of the NDs, according to some
  • Fig. 9A shows NDs 900A-H, and their connectivity by way of lines between 900A-900B, 900B-900C, 900C-900D, 900D-900E, 900E-900F, 900F-900G, and 900A-900G, as well as between 900H and each of 900A, 900C, 900D, and 900G.
  • These NDs are physical devices, and the connectivity between these NDs can be wireless or wired (often referred to as a link).
  • NDs 900A, 900E, and 900F An additional line extending from NDs 900A, 900E, and 900F illustrates that these NDs act as ingress and egress points for the network (and thus, these NDs are sometimes referred to as edge NDs; while the other NDs may be called core NDs).
  • Two of the exemplary ND implementations in Fig. 9A are: 1) a special-purpose network device 902 that uses custom application-specific integrated-circuits (ASICs) and a special-purpose operating system (OS); and 2) a general purpose network device 904 that uses common off-the-shelf (COTS) processors and a standard OS.
  • ASICs application-specific integrated-circuits
  • OS special-purpose operating system
  • COTS common off-the-shelf
  • the special-purpose network device 902 includes networking hardware 910 comprising compute resource(s) 912 (which typically include a set of one or more processors), forwarding resource(s) 914 (which typically include one or more ASICs and/or network processors), and physical network interfaces (NIs) 916 (sometimes called physical ports), as well as non-transitory machine readable storage media 918 having stored therein networking software 920.
  • a physical NI is hardware in a ND through which a network connection (e.g., wirelessly through a wireless network interface controller (WNIC) or through plugging in a cable to a physical port connected to a network interface controller (NIC)) is made, such as those shown by the connectivity between NDs 900A-H.
  • WNIC wireless network interface controller
  • NIC network interface controller
  • networking software 920 may be executed by the networking hardware 910 to instantiate a set of one or more networking software instance(s) 922.
  • Each of the networking software instance(s) 922, and that part of the networking hardware 910 that executes that network software instance form a separate virtual network element 930A-R.
  • Each of the virtual network element(s) (VNEs) 930A-R includes a control communication and configuration module 932A- R (sometimes referred to as a local control module or control communication module) and forwarding table(s) 934A-R, such that a given virtual network element (e.g., 930A) includes the control communication and configuration module (e.g., 932A), a set of one or more forwarding table(s) (e.g., 934A), and that portion of the networking hardware 910 that executes the virtual network element (e.g., 930A).
  • a control communication and configuration module 932A- R sometimes referred to as a local control module or control communication module
  • forwarding table(s) 934A-R forwarding table(s) 934A-R
  • Software 920 can include code such as controller/connection group output action module 925, which when executed by networking hardware 910, causes the special-purpose network device 902 to perform operations of one or more embodiments of the present invention as part networking software instances 922.
  • the special-purpose network device 902 is often physically and/or logically considered to include: 1) a ND control plane 924 (sometimes referred to as a control plane) comprising the compute resource(s) 912 that execute the control communication and
  • a ND forwarding plane 926 (sometimes referred to as a forwarding plane, a data plane, or a media plane) comprising the forwarding resource(s) 914 that utilize the forwarding table(s) 934A-R and the physical NIs 916.
  • the ND is a router (or is implementing routing functionality)
  • the ND control plane 924 (the compute resource(s) 912 executing the control communication and configuration
  • module(s) 932A-R is typically responsible for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) and storing that routing information in the forwarding table(s) 934A-R, and the ND forwarding plane 926 is responsible for receiving that data on the physical NIs 916 and forwarding that data out the appropriate ones of the physical NIs 916 based on the forwarding table(s) 934A-R.
  • data e.g., packets
  • the ND forwarding plane 926 is responsible for receiving that data on the physical NIs 916 and forwarding that data out the appropriate ones of the physical NIs 916 based on the forwarding table(s) 934A-R.
  • Fig. 9B illustrates an exemplary way to implement the special-purpose network device 902 according to some embodiments of the invention.
  • Fig. 9B shows a special-purpose network device including cards 938 (typically hot pluggable). While in some embodiments the cards 938 are of two types (one or more that operate as the ND forwarding plane 926
  • a service card can provide specialized processing (e.g., Layer 4 to Layer 7 services (e.g., firewall, Internet Protocol Security (IPsec), Secure Sockets Layer (SSL) / Transport Layer Security (TLS), Intrusion Detection System (IDS), peer-to-peer (P2P), Voice over IP (VoIP) Session Border Controller, Mobile Wireless Gateways (Gateway General Packet Radio Service (GPRS) Support Node (GGSN), Evolved Packet Core (EPC) Gateway)).
  • Layer 4 to Layer 7 services e.g., firewall, Internet Protocol Security (IPsec), Secure Sockets Layer (SSL) / Transport Layer Security (TLS), Intrusion Detection System (IDS), peer-to-peer (P2P), Voice over IP (VoIP) Session Border Controller, Mobile Wireless Gateways (Gateway General Packet Radio Service (GPRS) Support Node (GGSN), Evolved Packet Core (EPC) Gateway)).
  • IPsec Internet Protocol
  • a service card may be used to terminate IPsec tunnels and execute the attendant authentication and encryption algorithms. These cards are coupled together through one or more interconnect mechanisms illustrated as backplane 936 (e.g., a first full mesh coupling the line cards and a second full mesh coupling all of the cards).
  • backplane 936 e.g., a first full mesh coupling the line cards and a second full mesh coupling all of the cards.
  • the general purpose network device 904 includes hardware 940 comprising a set of one or more processor(s) 942 (which are often COTS processors) and network interface controller(s) 944 (NICs; also known as network interface cards) (which include physical NIs 946), as well as non-transitory machine readable storage media 948 having stored therein software 950.
  • processor(s) 942 execute the software 950 to instantiate one or more sets of one or more applications 964A-R. While one embodiment does not implement virtualization, alternative embodiments may use different forms of virtualization.
  • the virtualization layer 954 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 962A-R called software containers that may each be used to execute one (or more) of the sets of applications 964A-R; where the multiple software containers (also called virtualization engines, virtual private servers, or jails) are user spaces (typically a virtual memory space) that are separate from each other and separate from the kernel space in which the operating system is run; and where the set of applications running in a given user space, unless explicitly allowed, cannot access the memory of the other processes.
  • the multiple software containers also called virtualization engines, virtual private servers, or jails
  • user spaces typically a virtual memory space
  • the virtualization layer 954 represents a hypervisor (sometimes referred to as a virtual machine monitor (VMM)) or a hypervisor executing on top of a host operating system, and each of the sets of applications 964A-R is run on top of a guest operating system within an instance 962A-R called a virtual machine (which may in some cases be considered a tightly isolated form of software container) that is run on top of the hypervisor - the guest operating system and application may not know they are running on a virtual machine as opposed to running on a "bare metal" host electronic device, or through para- virtualization the operating system and/or application may be aware of the presence of virtualization for optimization purposes.
  • a hypervisor sometimes referred to as a virtual machine monitor (VMM)
  • VMM virtual machine monitor
  • a hypervisor executing on top of a host operating system
  • each of the sets of applications 964A-R is run on top of a guest operating system within an instance 962A-R called a virtual machine (which may in some cases be considered a tightly
  • unikernel(s) which can be generated by compiling directly with an application only a limited set of libraries (e.g., from a library operating system (LibOS) including drivers/libraries of OS services) that provide the particular OS services needed by the application.
  • libraries e.g., from a library operating system (LibOS) including drivers/libraries of OS services
  • unikernel can be implemented to run directly on hardware 940, directly on a hypervisor (in which case the unikernel is sometimes described as running within a LibOS virtual machine), or in a software container
  • embodiments can be implemented fully with unikernels running directly on a hypervisor represented by virtualization layer 954, unikernels running within software containers represented by instances 962A-R, or as a combination of unikernels and the above-described techniques (e.g., unikernels and virtual machines both run directly on a hypervisor, unikernels and sets of applications that are run in different software containers).
  • the virtual network element(s) 960A-R perform similar functionality to the virtual network element(s) 930A-R - e.g., similar to the control communication and configuration module(s) 932A and forwarding table(s) 934A (this virtualization of the hardware 940 is sometimes referred to as network function virtualization (NFV)).
  • NFV network function virtualization
  • CPE customer premise equipment
  • each instance 962A-R corresponding to one VNE 960A-R
  • alternative embodiments may implement this correspondence at a finer level granularity (e.g., line card virtual machines virtualize line cards, control card virtual machine virtualize control cards, etc.); it should be understood that the techniques described herein with reference to a correspondence of instances 962A-R to VNEs also apply to embodiments where such a finer level of granularity and/or unikernels are used.
  • the virtualization layer 954 includes a virtual switch that provides similar forwarding services as a physical Ethernet switch. Specifically, this virtual switch forwards traffic between instances 962A-R and the NIC(s) 944, as well as optionally between the instances 962A-R; in addition, this virtual switch may enforce network isolation between the VNEs 960A-R that by policy are not permitted to communicate with each other (e.g., by honoring virtual local area networks (VLANs)).
  • VLANs virtual local area networks
  • Software 950 can include code such as controller/connection group output action module 963, which when executed by processor(s) 942, cause the general purpose network device 904 to perform operations of one or more embodiments of the present invention as part software instances 962A-R.
  • the third exemplary ND implementation in Fig. 9A is a hybrid network device 906, which includes both custom ASICs/special-purpose OS and COTS processors/standard OS in a single ND or a single card within an ND.
  • a platform VM e.g., a VM that that implements the functionality of the special-purpose network device 902 could provide for para-virtualization to the networking hardware present in the hybrid network device 906.
  • NE network element
  • each of the VNEs receives data on the physical NIs (e.g., 916, 946) and forwards that data out the appropriate ones of the physical NIs (e.g., 916, 946).
  • a VNE implementing IP router functionality forwards IP packets on the basis of some of the IP header information in the IP packet; where IP header information includes source IP address, destination IP address, source port, destination port (where "source port" and
  • destination port refer herein to protocol ports, as opposed to physical ports of a ND), transport protocol (e.g., user datagram protocol (UDP), Transmission Control Protocol (TCP), and differentiated services code point (DSCP) values.
  • transport protocol e.g., user datagram protocol (UDP), Transmission Control Protocol (TCP), and differentiated services code point (DSCP) values.
  • Fig. 9C illustrates various exemplary ways in which VNEs may be coupled according to some embodiments of the invention.
  • Fig. 9C shows VNEs 970A.1-970A.P (and optionally VNEs 970A.Q-970A.R) implemented in ND 900A and VNE 970H.1 in ND 900H.
  • VNEs 970A.1-970A.P and optionally VNEs 970A.Q-970A.R
  • VNEs 970A.1-P are separate from each other in the sense that they can receive packets from outside ND 900A and forward packets outside of ND 900A; VNE 970A.1 is coupled with VNE 970H.1, and thus they communicate packets between their respective NDs; VNE 970A.2- 970A.3 may optionally forward packets between themselves without forwarding them outside of the ND 900A; and VNE 970A.P may optionally be the first in a chain of VNEs that includes VNE 970A.Q followed by VNE 970A.R (this is sometimes referred to as dynamic service chaining, where each of the VNEs in the series of VNEs provides a different service - e.g., one or more layer 4-7 network services). While Fig. 9C illustrates various exemplary relationships between the VNEs, alternative embodiments may support other relationships (e.g., more/fewer VNEs, more/fewer dynamic service chains, multiple different dynamic service chains with some common VNEs and
  • the NDs of Fig. 9A may form part of the Internet or a private network; and other electronic devices (not shown; such as end user devices including workstations, laptops, netbooks, tablets, palm tops, mobile phones, smartphones, phablets, multimedia phones, Voice Over Internet Protocol (VOIP) phones, terminals, portable media players, GPS units, wearable devices, gaming systems, set-top boxes, Internet enabled household appliances) may be coupled to the network (directly or through other networks such as access networks) to communicate over the network (e.g., the Internet or virtual private networks (VPNs) overlaid on (e.g., tunneled through) the Internet) with each other (directly or through servers) and/or access content and/or services.
  • VOIP Voice Over Internet Protocol
  • Such content and/or services are typically provided by one or more servers (not shown) belonging to a service/content provider or one or more end user devices (not shown) participating in a peer-to-peer (P2P) service, and may include, for example, public webpages (e.g., free content, store fronts, search services), private webpages (e.g., username/password accessed webpages providing email services), and/or corporate networks over VPNs.
  • end user devices may be coupled (e.g., through customer premise equipment coupled to an access network (wired or wirelessly)) to edge NDs, which are coupled (e.g., through one or more core NDs) to other edge NDs, which are coupled to electronic devices acting as servers.
  • edge NDs which are coupled (e.g., through one or more core NDs) to other edge NDs, which are coupled to electronic devices acting as servers.
  • one or more of the electronic devices operating as the NDs in Fig. 9A may also host one or more such servers (
  • instances 962A-R may operate as servers; the same would be true for the hybrid network device 906; in the case of the special-purpose network device 902, one or more such servers could also be run on a virtualization layer executed by the compute resource(s) 912); in which case the servers are said to be co-located with the VNEs of that ND.
  • a virtual network is a logical abstraction of a physical network (such as that in Fig. 9A) that provides network services (e.g., L2 and/or L3 services).
  • a virtual network can be implemented as an overlay network (sometimes referred to as a network virtualization overlay) that provides network services (e.g., layer 2 (L2, data link layer) and/or layer 3 (L3, network layer) services) over an underlay network (e.g., an L3 network, such as an Internet Protocol (IP) network that uses tunnels (e.g., generic routing encapsulation (GRE), layer 2 tunneling protocol (L2TP), IPSec) to create the overlay network).
  • IP Internet Protocol
  • a network virtualization edge sits at the edge of the underlay network and participates in implementing the network virtualization; the network-facing side of the NVE uses the underlay network to tunnel frames to and from other NVEs; the outward-facing side of the NVE sends and receives data to and from systems outside the network.
  • a virtual network instance is a specific instance of a virtual network on a NVE (e.g., a NE/VNE on an ND, a part of a NE/VNE on a ND where that NE/VNE is divided into multiple VNEs through emulation); one or more VNIs can be instantiated on an NVE (e.g., as different VNEs on an ND).
  • a virtual access point is a logical connection point on the NVE for connecting external systems to a virtual network; a VAP can be physical or virtual ports identified through logical interface identifiers (e.g., a VLAN ID).
  • Examples of network services include: 1) an Ethernet LAN emulation service (an Ethernet-based multipoint service similar to an Internet Engineering Task Force (IETF)
  • IETF Internet Engineering Task Force
  • MPLS Multiprotocol Label Switching
  • EVPN Ethernet VPN
  • an NVE provides separate L2 VNIs (virtual switching instances) for different such virtual networks, and L3 (e.g., IP/MPLS) tunneling encapsulation across the underlay network); and 2) a virtualized IP forwarding service (similar to IETF IP VPN (e.g., Border Gateway Protocol (BGP)/MPLS IP VPN) from a service definition perspective) in which external systems are interconnected across the network by an L3 environment over the underlay network (e.g., an NVE provides separate L3 VNIs (forwarding and routing instances) for different such virtual networks, and L3 (e.g., IP/MPLS) tunneling encapsulation across the underlay network)).
  • IETF IP VPN e.g., Border Gateway Protocol (BGP)/MPLS IP VPN
  • Network services may also include quality of service capabilities (e.g., traffic classification marking, traffic conditioning and scheduling), security capabilities (e.g., filters to protect customer premises from network - originated attacks, to avoid malformed route announcements), and management capabilities (e.g., full detection and processing).
  • quality of service capabilities e.g., traffic classification marking, traffic conditioning and scheduling
  • security capabilities e.g., filters to protect customer premises from network - originated attacks, to avoid malformed route announcements
  • management capabilities e.g., full detection and processing
  • Fig. 9D illustrates a network with a single network element on each of the NDs of Fig. 9A, and within this straight forward approach contrasts a traditional distributed approach (commonly used by traditional routers) with a centralized approach for maintaining reachability and forwarding information (also called network control), according to some embodiments of the invention.
  • Fig. 9D illustrates network elements (NEs) 970A-H with the same connectivity as the NDs 900A-H of Fig. 9A.
  • Fig. 9D illustrates that the distributed approach 972 distributes responsibility for generating the reachability and forwarding information across the NEs 970A-H; in other words, the process of neighbor discovery and topology discovery is distributed.
  • the control communication and configuration module(s) 932A-R of the ND control plane 924 typically include a reachability and forwarding information module to implement one or more routing protocols (e.g., an exterior gateway protocol such as Border Gateway Protocol (BGP), Interior Gateway Protocol(s) (IGP) (e.g., Open Shortest Path First (OSPF), Intermediate System to Intermediate System (IS-IS), Routing Information Protocol (RIP), Label Distribution Protocol (LDP), Resource Reservation Protocol (RSVP) (including RS VP-Traffic Engineering (TE): Extensions to RSVP for LSP Tunnels and Generalized Multi-Protocol Label Switching
  • Border Gateway Protocol BGP
  • IGP Interior Gateway Protocol
  • OSPF Open Shortest Path First
  • IS-IS Intermediate System to Intermediate System
  • RIP Routing Information Protocol
  • LDP Label Distribution Protocol
  • RSVP Resource Reservation Protocol
  • TE Extensions to RSVP for LSP Tunnels and Generalized Multi-Protocol Label Switching
  • GPLS Signaling RSVP-TE
  • NEs 970A-H e.g., the compute resource(s) 912 executing the control communication and configuration
  • module(s) 932A-R perform their responsibility for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) by distributively determining the reachability within the network and calculating their respective forwarding information.
  • Routes and adjacencies are stored in one or more routing structures (e.g., Routing Information Base (RIB), Label Information Base (LIB), one or more adjacency structures) on the ND control plane 924.
  • the ND control plane 924 programs the ND forwarding plane 926 with information (e.g., adjacency and route information) based on the routing structure(s).
  • the ND control plane 924 programs the adjacency and route information into one or more forwarding table(s) 934A-R (e.g., Forwarding Information Base (FIB), Label Forwarding Information Base (LFIB), and one or more adjacency structures) on the ND forwarding plane 926.
  • the ND can store one or more bridging tables that are used to forward data based on the layer 2 information in that data. While the above example uses the special-purpose network device 902, the same distributed approach 972 can be implemented on the general purpose network device 904 and the hybrid network device 906.
  • Fig. 9D illustrates that a centralized approach 974 (also known as software defined networking (SDN)) that decouples the system that makes decisions about where traffic is sent from the underlying systems that forwards traffic to the selected destination.
  • the illustrated centralized approach 974 has the responsibility for the generation of reachability and forwarding information in a centralized control plane 976 (sometimes referred to as a SDN control module, controller, network controller, OpenFlow controller, SDN controller, control plane node, network virtualization authority, or management control entity), and thus the process of neighbor discovery and topology discovery is centralized.
  • a centralized control plane 976 sometimes referred to as a SDN control module, controller, network controller, OpenFlow controller, SDN controller, control plane node, network virtualization authority, or management control entity
  • the centralized control plane 976 has a south bound interface 982 with a data plane 980 (sometime referred to the infrastructure layer, network forwarding plane, or forwarding plane (which should not be confused with a ND forwarding plane)) that includes the NEs 970A-H (sometimes referred to as switches, forwarding elements, data plane elements, or nodes).
  • the centralized control plane 976 includes a network controller 978, which includes a centralized reachability and forwarding information module 979 that determines the reachability within the network and distributes the forwarding information to the NEs 970A-H of the data plane 980 over the south bound interface 982 (which may use the OpenFlow protocol).
  • the network intelligence is centralized in the centralized control plane 976 executing on electronic devices that are typically separate from the NDs.
  • the network controller 978 may include a controller/connection group output action module 981 that when executed by the network controller 978, causes the network controller 978 to perform operations of one or more embodiments described herein above.
  • each of the control communication and configuration module(s) 932A-R of the ND control plane 924 typically include a control agent that provides the VNE side of the south bound interface 982.
  • the ND control plane 924 (the compute resource(s) 912 executing the control communication and configuration module(s) 932A-R) performs its responsibility for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) through the control agent communicating with the centralized control plane 976 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 979 (it should be understood that in some embodiments of the invention, the control communication and configuration module(s) 932A-R, in addition to communicating with the centralized control plane 976, may also play some role in determining reachability and/or calculating forwarding information - albeit less so than in the case of a distributed approach; such embodiments are generally considered to fall under the centralized approach 974, but may also be considered a hybrid approach).
  • data e.g., packets
  • the control agent communicating with the centralized control plane 976 to receive the forward
  • the same centralized approach 974 can be implemented with the general purpose network device 904 (e.g., each of the VNE 960A-R performs its responsibility for controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) by communicating with the centralized control plane 976 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 979; it should be understood that in some embodiments of the invention, the VNEs 960A-R, in addition to communicating with the centralized control plane 976, may also play some role in determining reachability and/or calculating forwarding information - albeit less so than in the case of a distributed approach) and the hybrid network device 906.
  • the general purpose network device 904 e.g., each of the VNE 960A-R performs its responsibility for controlling how data (e.g., packets) is to be routed (e.g., the next hop for
  • NFV is able to support SDN by providing an infrastructure upon which the SDN software can be run
  • NFV and SDN both aim to make use of commodity server hardware and physical switches.
  • Fig. 9D also shows that the centralized control plane 976 has a north bound interface 984 to an application layer 986, in which resides application(s) 988.
  • the centralized control plane 976 has the ability to form virtual networks 992 (sometimes referred to as a logical forwarding plane, network services, or overlay networks (with the NEs 970A-H of the data plane 980 being the underlay network)) for the application(s) 988.
  • virtual networks 992 sometimes referred to as a logical forwarding plane, network services, or overlay networks (with the NEs 970A-H of the data plane 980 being the underlay network)
  • the centralized control plane 976 maintains a global view of all NDs and configured NEs/VNEs, and it maps the virtual networks to the underlying NDs efficiently (including maintaining these mappings as the physical network changes either through hardware (ND, link, or ND component) failure, addition, or removal).
  • Fig. 9D shows the distributed approach 972 separate from the centralized approach 974
  • the effort of network control may be distributed differently or the two combined in certain embodiments of the invention.
  • embodiments may generally use the centralized approach (SDN) 974, but have certain functions delegated to the NEs (e.g., the distributed approach may be used to implement one or more of fault monitoring, performance monitoring, protection switching, and primitives for neighbor and/or topology discovery); or 2) embodiments of the invention may perform neighbor discovery and topology discovery via both the centralized control plane and the distributed protocols, and the results compared to raise exceptions where they do not agree.
  • SDN centralized approach
  • Such embodiments are generally considered to fall under the centralized approach 974, but may also be considered a hybrid approach.
  • Fig. 9D illustrates the simple case where each of the NDs 900A-H implements a single NE 970A-H
  • the network control approaches described with reference to Fig. 9D also work for networks where one or more of the NDs 900A-H implement multiple VNEs (e.g., VNEs 930A-R, VNEs 960A-R, those in the hybrid network device 906).
  • the network controller 978 may also emulate the implementation of multiple VNEs in a single ND.
  • the network controller 978 may present the implementation of a VNE/NE in a single ND as multiple VNEs in the virtual networks 992 (all in the same one of the virtual network(s) 992, each in different ones of the virtual network(s) 992, or some combination).
  • the network controller 978 may cause an ND to implement a single VNE (a NE) in the underlay network, and then logically divide up the resources of that NE within the centralized control plane 976 to present different VNEs in the virtual network(s) 992 (where these different VNEs in the overlay networks are sharing the resources of the single VNE/NE implementation on the ND in the underlay network).
  • Figs. 9E and 9F respectively illustrate exemplary abstractions of NEs and VNEs that the network controller 978 may present as part of different ones of the virtual networks 992.
  • Fig. 9E illustrates the simple case of where each of the NDs 900A-H implements a single NE 970A-H (see Fig. 9D), but the centralized control plane 976 has abstracted multiple of the NEs in different NDs (the NEs 970A-C and G-H) into (to represent) a single NE 9701 in one of the virtual network(s) 992 of Fig. 9D, according to some embodiments of the invention.
  • Fig. 9E shows that in this virtual network, the NE 9701 is coupled to NE 970D and 970F, which are both still coupled to NE 970E.
  • Fig. 9F illustrates a case where multiple VNEs (VNE 970A.1 and VNE 970H.1) are implemented on different NDs (ND 900 A and ND 900H) and are coupled to each other, and where the centralized control plane 976 has abstracted these multiple VNEs such that they appear as a single VNE 970T within one of the virtual networks 992 of Fig. 9D, according to some embodiments of the invention.
  • the abstraction of a NE or VNE can span
  • NDs multiple NDs.
  • the centralized control plane 976 implements the centralized control plane 976 as a single entity (e.g., a single instance of software running on a single electronic device), alternative embodiments may spread the functionality across multiple entities for redundancy and/or scalability purposes (e.g., multiple instances of software running on different electronic devices).
  • the electronic device(s) running the centralized control plane 976 may be implemented a variety of ways (e.g., a special purpose device, a general-purpose (e.g., COTS) device, or hybrid device). These electronic device(s) would similarly include compute resource(s), a set or one or more physical NICs, and a non-transitory machine-readable storage medium having stored thereon the centralized control plane software. For instance, Fig.
  • a general purpose control plane device 1004 including hardware 1040 comprising a set of one or more processor(s) 1042 (which are often COTS processors) and network interface controller(s) 1044 (NICs; also known as network interface cards) (which include physical NIs 1046), as well as non-transitory machine readable storage media 1048 having stored therein centralized control plane (CCP) software 1050 and a controller/connection group output action module 1081.
  • processors 1042 which are often COTS processors
  • NICs network interface controller
  • NICs network interface controller
  • non-transitory machine readable storage media 1048 having stored therein centralized control plane (CCP) software 1050 and a controller/connection group output action module 1081.
  • CCP centralized control plane
  • the processor(s) 1042 typically execute software to instantiate a virtualization layer 1054 (e.g., in one embodiment the virtualization layer 1054 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 1062A-R called software containers (representing separate user spaces and also called virtualization engines, virtual private servers, or jails) that may each be used to execute a set of one or more
  • a virtualization layer 1054 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 1062A-R called software containers (representing separate user spaces and also called virtualization engines, virtual private servers, or jails) that may each be used to execute a set of one or more
  • the virtualization layer 1054 represents a hypervisor (sometimes referred to as a virtual machine monitor (VMM)) or a hypervisor executing on top of a host operating system, and an application is run on top of a guest operating system within an instance 1062A-R called a virtual machine (which in some cases may be considered a tightly isolated form of software container) that is run by the hypervisor ;
  • an application is implemented as a unikernel, which can be generated by compiling directly with an application only a limited set of libraries (e.g., from a library operating system (LibOS) including drivers/libraries of OS services) that provide the particular OS services needed by the application, and the unikernel can run directly on hardware 1040, directly on a hypervisor represented by virtualization layer 1054 (in which case the unikernel is sometimes described as running within a LibOS virtual machine), or in a software container represented by one of instances 1062A-R).
  • LibOS library operating system
  • CCP instance 1076A an instance of the CCP software 1050 (illustrated as CCP instance 1076A) is executed (e.g., within the instance 1062A) on the virtualization layer 1054.
  • CCP instance 1076A is executed, as a unikernel or on top of a host operating system, on the "bare metal" general purpose control plane device 1004. The instantiation of the CCP instance 1076A, as well as the virtualization layer 1054 and
  • instances 1062A-R if implemented, are collectively referred to as software instance(s) 1052.
  • the CCP instance 1076A includes a network controller instance 1078.
  • the network controller instance 1078 includes a centralized reachability and forwarding information module instance 1079 (which is a middleware layer providing the context of the network controller 978 to the operating system and communicating with the various NEs), and an CCP application layer 1080 (sometimes referred to as an application layer) over the middleware layer (providing the intelligence required for various network operations such as protocols, network situational awareness, and user - interfaces).
  • this CCP application layer 1080 within the centralized control plane 976 works with virtual network view(s) (logical view(s) of the network) and the middleware layer provides the conversion from the virtual networks to the physical view.
  • the controller/connection group output action module 1081 can be executed by hardware 1040 to perform operations of one or more embodiments of the present invention as part of software instances 1052.
  • the centralized control plane 976 transmits relevant messages to the data plane 980 based on CCP application layer 1080 calculations and middleware layer mapping for each flow.
  • a flow may be defined as a set of packets whose headers match a given pattern of bits; in this sense, traditional IP forwarding is also flow-based forwarding where the flows are defined by the destination IP address for example; however, in other implementations, the given pattern of bits used for a flow definition may include more fields (e.g., 10 or more) in the packet headers.
  • Different NDs/NEs/VNEs of the data plane 980 may receive different messages, and thus different forwarding information.
  • the data plane 980 processes these messages and programs the appropriate flow information and corresponding actions in the forwarding tables (sometime referred to as flow tables) of the appropriate NE/VNEs, and then the NEs/VNEs map incoming packets to flows represented in the forwarding tables and forward packets based on the matches in the forwarding tables.
  • Standards such as OpenFlow define the protocols used for the messages, as well as a model for processing the packets.
  • the model for processing packets includes header parsing, packet classification, and making forwarding decisions. Header parsing describes how to interpret a packet based upon a well-known set of protocols. Some protocol fields are used to build a match structure (or key) that will be used in packet classification (e.g., a first key field could be a source media access control (MAC) address, and a second key field could be a destination MAC address).
  • MAC media access control
  • Packet classification involves executing a lookup in memory to classify the packet by determining which entry (also referred to as a forwarding table entry or flow entry) in the forwarding tables best matches the packet based upon the match structure, or key, of the forwarding table entries. It is possible that many flows represented in the forwarding table entries can correspond/match to a packet; in this case the system is typically configured to determine one forwarding table entry from the many according to a defined scheme (e.g., selecting a first forwarding table entry that is matched).
  • Forwarding table entries include both a specific set of match criteria (a set of values or wildcards, or an indication of what portions of a packet should be compared to a particular value/values/wildcards, as defined by the matching capabilities - for specific fields in the packet header, or for some other packet content), and a set of one or more actions for the data plane to take on receiving a matching packet. For example, an action may be to push a header onto the packet, for the packet using a particular port, flood the packet, or simply drop the packet.
  • TCP transmission control protocol
  • an unknown packet for example, a "missed packet” or a "match- miss” as used in OpenFlow parlance
  • the packet (or a subset of the packet header and content) is typically forwarded to the centralized control plane 976.
  • the centralized control plane 976 will then program forwarding table entries into the data plane 980 to accommodate packets belonging to the flow of the unknown packet. Once a specific forwarding table entry has been programmed into the data plane 980 by the centralized control plane 976, the next packet with matching credentials will match that forwarding table entry and take the set of actions associated with that matched entry.
  • a network interface may be physical or virtual; and in the context of IP, an interface address is an IP address assigned to a NI, be it a physical NI or virtual NI.
  • a virtual NI may be associated with a physical NI, with another virtual interface, or stand on its own (e.g., a loopback interface, a point-to-point protocol interface).
  • a NI physical or virtual
  • a loopback interface (and its loopback address) is a specific type of virtual NI (and IP address) of a NE/VNE (physical or virtual) often used for management purposes; where such an IP address is referred to as the nodal loopback address.
  • IP addresses of that ND are referred to as IP addresses of that ND; at a more granular level, the IP address(es) assigned to NI(s) assigned to a NE/VNE implemented on a ND can be referred to as IP addresses of that NE/VNE.
  • An embodiment of the invention may be an article of manufacture in which a non- transitory machine-readable medium (such as microelectronic memory) has stored thereon instructions which program one or more data processing components (generically referred to here as a "processor") to perform the operations described above.
  • a non- transitory machine-readable medium such as microelectronic memory
  • program one or more data processing components (generically referred to here as a "processor") to perform the operations described above.
  • some of these operations might be performed by specific hardware components that contain hardwired logic (e.g., dedicated digital filter blocks and state machines). Those operations might alternatively be performed by any combination of programmed data processing components and fixed hardwired circuit components.

Abstract

A method is implemented by a network device functioning as a switch in a Software Defined Networking (SDN) network to provide controller group output actions, where the switch is communicatively coupled to a plurality of SDN controllers in the SDN network. The method includes generating an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the active SDN controller selected from the first controller group.

Description

ROBUST METHOD OF DISTRIBUTING PACKET-INS IN A SOFTWARE DEFINED
NETWORKING (SDN) NETWORK
TECHNICAL FIELD
[0001] Embodiments of the invention relate to the field of Software Defined Networking (SDN); and more specifically to providing controller group output actions and connection group output actions in an SDN network.
BACKGROUND
[0002] Software Defined Networking (SDN) is an approach to computer networking that employs a split architecture network in which the forwarding (data) plane is decoupled from the control plane. The use of a split architecture network simplifies the network devices (e.g., switches) implementing the forwarding plane by shifting the intelligence of the network into one or more controllers that oversee the switches. SDN facilitates rapid and open innovation at the network layer by providing a programmable network infrastructure.
[0003] OpenFlow is a protocol that enables controllers and switches in an SDN network to communicate with each other. OpenFlow enables dynamic programming of flow control policies in the network. In OpenFlow, a switch may establish communication with a single controller or may establish communication with multiple controllers. Connecting to multiple controllers improves reliability, as the switch can continue to operate in OpenFlow mode even if a controller fails or a connection to a controller fails. Handover of switches between controllers is managed by the controllers, which enables fast recovery from failure and also load balancing among controllers.
[0004] In OpenFlow, a switch uses Packet-In messages to transfer control of a packet to the controller. In a multiple controller environment, the controllers have very little control over the Packet-In messages received from the switches. Typically, all controllers will receive all Packet-In messages from the switches, or using the OpenFlow Asynchronous Configuration, a controller can specify which Packet-In messages it wants to listen to. However, there is no mechanism for a switch to transmit packets to a particular controller, for example, based on the type of service with which the packet is associated.
[0005] An OpenFlow channel is a communication channel used to exchange OpenFlow messages between a switch and a controller. By default, the OpenFlow channel between a switch and a controller is a single network connection. However, the OpenFlow channel may also be composed of a main connection and multiple auxiliary connections. Auxiliary connections are created by the switch and are helpful to improve the switch processing performance and exploit the parallelism of most switch implementations.
[0006] A switch that has multiple connections established with a controller will either transmit all Packet- In messages to the controller using the main connection or transmit the Packet- In messages to the controller using a randomly selected connection or using a connection that is chosen based on some algorithm on the switch side.
SUMMARY
[0007] A method is implemented by a network device functioning as a switch in a Software Defined Networking (SDN) network to provide controller group output actions, where the switch is communicatively coupled to a plurality of SDN controllers in the SDN network. The method includes generating an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the active SDN controller selected from the first controller group.
[0008] A method is implemented by a network device functioning as a switch in a Software Defined Networking (SDN) network to provide connection group output actions, where the switch has established a plurality of connections with an SDN controller in the SDN network. The method includes generating an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the SDN controller using the active connection selected from the first connection group.
[0009] A network device is configured to function as a switch in a Software Defined
Networking (SDN) network to provide controller group output actions, where the switch is to be communicatively coupled to a plurality of SDN controllers in the SDN network. The network device includes a set of one or more processors and a non-transitory machine-readable storage medium having stored therein a controller group output action module, which when executed by the set of one or more processors, causes the network device to generate an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receive a packet for forwarding, determine whether the packet is to be processed according to the entry, select an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmit the packet to the active SDN controller selected from the first controller group.
[0010] A network device is configured to function as a switch in a Software Defined
Networking (SDN) network to provide connection group output actions, where the switch is to establish a plurality of connections with an SDN controller in the SDN network. The network device includes a set of one or more processors and a non-transitory machine-readable storage medium having stored therein a connection group output action module, which when executed by the set of one or more processors, causes the network device to generate an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receive a packet for forwarding, determine whether the packet is to be processed according to the entry, select an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmit the packet to the SDN controller using the active connection selected from the first connection group.
[0011] A non-transitory machine-readable medium has computer code stored therein, which when executed by a set of one or more processors of a network device that functions as a switch in a Software Defined Networking (SDN) network, causes the switch to perform operations for providing controller group output actions, where the switch is to be communicatively coupled to a plurality of SDN controllers in the SDN network. The operations include generating an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, where the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the active SDN controller selected from the first controller group.
[0012] A non-transitory machine-readable medium has computer code stored therein, which when executed by a set of one or more processors of a network device that functions as a switch in a Software Defined Networking (SDN) network, causes the switch to perform operations for providing connection group output actions, where the switch is to establish a plurality of connections with an SDN controller in the SDN network. The operations include generating an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receiving a packet for forwarding, determining whether the packet is to be processed according to the entry, selecting an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmitting the packet to the SDN controller using the active connection selected from the first connection group.
BRIEF DESCRIPTION OF THE DRAWINGS
[0013] The invention may best be understood by referring to the following description and accompanying drawings that are used to illustrate embodiments of the invention. In the drawings:
[0014] Fig. 1 is a block diagram illustrating an SDN network in which controller group output actions can be implemented, according to some embodiments.
[0015] Fig. 2 is a diagram illustrating a set of flow entries in a switch for providing controller group output actions, according to some embodiments.
[0016] Fig. 3 is a flow diagram of a process implemented by a switch for performing controller group output actions, according to some embodiments.
[0017] Fig. 4 is a flow diagram of a process implemented by a controller for configuring a switch to perform controller group output actions, according to some embodiments.
[0018] Fig. 5 is a block diagram illustrating an SDN network in which connection group output actions can be implemented, according to some embodiments.
[0019] Fig. 6 is a diagram illustrating a set of flow entries in a switch for providing connection group output actions, according to some embodiments.
[0020] Fig. 7 is a flow diagram of a process implemented by a switch for performing connection group output actions, according to some embodiments.
[0021] Fig. 8 is a flow diagram of a process implemented by a controller for programming a switch to perform connection group output actions, according to some embodiments.
[0022] Fig. 9A illustrates connectivity between network devices (NDs) within an exemplary network, as well as three exemplary implementations of the NDs, according to some
embodiments. [0023] Fig. 9B illustrates an exemplary way to implement a special-purpose network device, according to some embodiments.
[0024] Fig. 9C illustrates various exemplary ways in which virtual network elements (VNEs) may be coupled, according to some embodiments.
[0025] Fig. 9D illustrates a network with a single network element (NE) on each of the NDs, and within this straight forward approach contrasts a traditional distributed approach (commonly used by traditional routers) with a centralized approach for maintaining reachability and forwarding information (also called network control), according to some embodiments.
[0026] Fig. 9E illustrates the simple case of where each of the NDs implements a single NE, but a centralized control plane has abstracted multiple of the NEs in different NDs into (to represent) a single NE in one of the virtual network(s), according to some embodiments.
[0027] Fig. 9F illustrates a case where multiple VNEs are implemented on different NDs and are coupled to each other, and where a centralized control plane has abstracted these multiple VNEs such that they appear as a single VNE within one of the virtual networks, according to some embodiments.
[0028] Fig. 10 illustrates a general purpose control plane device with centralized control plane (CCP) software, according to some embodiments.
DETAILED DESCRIPTION
[0029] The following description describes methods and apparatus for providing controller group output actions and connection group output actions in a Software Defined Networking (SDN) network. In the following description, numerous specific details such as logic implementations, opcodes, means to specify operands, resource partitioning/sharing/duplication implementations, types and interrelationships of system components, and logic
partitioning/integration choices are set forth in order to provide a more thorough understanding of the present invention. It will be appreciated, however, by one skilled in the art that the invention may be practiced without such specific details. In other instances, control structures, gate level circuits and full software instruction sequences have not been shown in detail in order not to obscure the invention. Those of ordinary skill in the art, with the included descriptions, will be able to implement appropriate functionality without undue experimentation.
[0030] References in the specification to "one embodiment," "an embodiment," "an example embodiment," etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
[0031] Bracketed text and blocks with dashed borders (e.g., large dashes, small dashes, dot- dash, and dots) may be used herein to illustrate optional operations that add additional features to embodiments of the invention. However, such notation should not be taken to mean that these are the only options or optional operations, and/or that blocks with solid borders are not optional in certain embodiments of the invention.
[0032] In the following description and claims, the terms "coupled" and "connected," along with their derivatives, may be used. It should be understood that these terms are not intended as synonyms for each other. "Coupled" is used to indicate that two or more elements, which may or may not be in direct physical or electrical contact with each other, co-operate or interact with each other. "Connected" is used to indicate the establishment of communication between two or more elements that are coupled with each other.
[0033] An electronic device stores and transmits (internally and/or with other electronic devices over a network) code (which is composed of software instructions and which is sometimes referred to as computer program code or a computer program) and/or data using machine-readable media (also called computer-readable media), such as machine-readable storage media (e.g., magnetic disks, optical disks, read only memory (ROM), flash memory devices, phase change memory) and machine-readable transmission media (also called a carrier) (e.g., electrical, optical, radio, acoustical or other form of propagated signals - such as carrier waves, infrared signals). Thus, an electronic device (e.g., a computer) includes hardware and software, such as a set of one or more processors coupled to one or more machine-readable storage media to store code for execution on the set of processors and/or to store data. For instance, an electronic device may include non- volatile memory containing the code since the non-volatile memory can persist code/data even when the electronic device is turned off (when power is removed), and while the electronic device is turned on that part of the code that is to be executed by the processor(s) of that electronic device is typically copied from the slower nonvolatile memory into volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM)) of that electronic device. Typical electronic devices also include a set or one or more physical network interface(s) to establish network connections (to transmit and/or receive code and/or data using propagating signals) with other electronic devices. One or more parts of an embodiment of the invention may be implemented using different combinations of software, firmware, and/or hardware. [0034] A network device (ND) is an electronic device that communicatively interconnects other electronic devices on the network (e.g., other network devices, end-user devices). Some network devices are "multiple services network devices" that provide support for multiple networking functions (e.g., routing, bridging, switching, Layer 2 aggregation, session border control, Quality of Service, and/or subscriber management), and/or provide support for multiple application services (e.g., data, voice, and video).
[0035] Software defined networking (SDN) is a network architecture in which the control plane is decoupled from the forwarding plane. An SDN network typically includes multiple forwarding elements (e.g., switches) interconnected with each other and one or more controllers that control the forwarding behavior of the switches. A controller can control the programming of flow tables in the switches to implement any forwarding protocol. A switch forwards packets from an ingress port to an egress port according to the rules in the flow tables. Each entry in a flow table (e.g., flow entry) includes a match field and a corresponding set of instructions. When an incoming packet matches the match field of a flow entry, the corresponding set of instructions are executed for that packet. The set of instructions may instruct the switch to perform various operations on the packet including, but not limited to, forwarding the packet to a given port, modifying certain bits in the packet header, encapsulating the packet, and dropping the packet. When the switch receives a packet for which there is no matching flow entry, the switch typically forwards the packet to the controller to be analyzed. The controller then decides how the packet should be handled. The controller may decide to drop the packet, or the controller can program a flow entry in the switch that provides the switch with instructions on how to process the packet and similar packets in the future.
[0036] The controller in an SDN network can program a switch to add, update, or delete flow entries in a flow table both reactively (e.g., in response to the controller receiving a packet from the switch) or proactively. Thus, SDN facilitates rapid innovation and deployment of network protocols by providing a programmable network infrastructure.
[0037] OpenFlow is a protocol that enables controllers and switches in an SDN network to communicate with each other. In OpenFlow, a switch may establish communication with a single controller or may establish communication with multiple controllers. Connecting to multiple controllers improves reliability, as the switch can continue to operate in OpenFlow mode even if a controller fails or a connection to a controller fails. Handover of switches between controllers is managed by the controllers, which enables fast recovery from failure and also load balancing among controllers.
[0038] Currently, when OpenFlow operation is initiated, the switch must connect to all controllers with which the switch is configured and try to maintain connectivity with all of these controllers concurrently. A switch transmits asynchronous messages such as a Packet-In message to all connected controllers. A Packet-In message transfers control of a packet to the controller. When a switch is connected to multiple controllers, the Packet-In message is duplicated for each controller. As such, in a multiple controller environment, the controllers have very little control over the Packet-In messages received from the switches. Typically, all controllers will receive all Packet-In messages from the switches, or using the OpenFlow Asynchronous Configuration, a controller can specify which Packet-In messages it wants to listen to. However, there is no mechanism for a switch to transmit packets to a particular controller, for example, based on the type of service with which the packet is associated. For example, in an SDN network that has a cluster of three controllers, it may be desirable to have Address Resolution Protocol (ARP) packets handled by the first controller, Link Layer
Discovery Protocol (LLDP) packets handled by the second controller, and Dynamic Host Configuration Protocol (DHCP) packets handled by the third controller. However, current OpenFlow specifications do not provide packet control at this level of granularity.
[0039] One solution to this problem is to program a flow entry in a switch with an instruction to transmit packets matching the flow entry to a particular controller (which is referred to herein as a controller- specific output action). The particular controller can be specified in the flow entry using a controller identifier assigned to that particular controller. However, with this solution, when there is an unplanned failure of the controller (e.g., due to link failure, node failure, process failure, etc.), any traffic transmitted to that controller is lost. Also, when there is an unplanned failure of the controller, other controllers need to re-program the flow entry in the switch (e.g., to transmit matching packets to a different controller) in order to avoid traffic loss.
[0040] Embodiments described herein improve upon the controller- specific output action mechanism described above by logically grouping controllers into controller groups and programming a flow entry in a switch with an instruction for the switch to transmit packets matching the flow entry to a controller to be selected from a particular controller group (which is referred to herein as a controller group output action). The particular controller group may be specified in the flow entry using a controller group identifier assigned to the controller group. When an incoming packet matches the flow entry, the switch selects an active controller from the particular controller group and transmits the packet to the selected active controller (e.g., embedded in a Packet-In message). If the switch determines that a connection to a controller has been lost (e.g., due to link failure, node failure, process failure, etc.), the switch marks that controller as being inactive. When selecting an active controller from a controller group, the switch does not select a controller that is marked as being inactive. In this way, traffic loss due to controller failure can be avoided, while still providing control over which controller the switch should transmit a packet to based on the packet type. Furthermore, a flow entry need not be re-programmed when a controller fails, as long as there is at least one active controller remaining in the controller group. Embodiments described herein further protect against a case where all of the controllers in a controller group fail by provisioning a fallback controller group for the controller group. In the case that all of the controllers in the controller group fail (e.g., are marked as being inactive), the switch may select an active controller from the fallback controller group.
[0041] An OpenFlow channel is a communication channel used to exchange OpenFlow messages between a switch and a controller. By default, the OpenFlow channel between a switch and a controller is composed of a single network connection. However, the OpenFlow channel may also be composed of multiple connections (e.g., a main connection and multiple auxiliary connections).
[0042] Currently, OpenFlow does not provide a mechanism for the controller to specify on which connection of the OpenFlow channel it wishes to receive Packet-In messages from the switch. Rather, the decision of which connection to use is entirely up to the switch. As such, if the controller hosts multiple services, each having different latency requirements, it is not possible for the controller to assign Packet-In messages associated with a lower latency requirement service to a faster connection and assign Packet-In messages associated with a higher latency requirement service to a slower connection.
[0043] One solution to this problem is to program flow entries in a switch with an instruction to transmit packets matching the flow entry to the controller using a particular connection (which is referred to herein as a connection- specific output action). The particular connection can be specified in the flow entry using a connection identifier assigned to that particular connection. However, with this solution, when there is an unplanned termination of the connection (e.g., due to a processing thread exception at the switch or the controller, connection timeout, etc.), any traffic transmitted to the controller using that connection is lost. Also, when there is an unplanned termination of the connection, the impacted flow entries need to be re- programmed (e.g., to transmit matching packets to the controller using a different connection) in order to avoid traffic loss.
[0044] Embodiments described herein improve upon the connection- specific output action mechanism described above by logically grouping connections established with a controller into connection groups and programming a flow entry in a switch with an instruction for the switch to transmit packets matching the flow entry to the controller using a connection to be selected from a particular connection group (which is referred to herein as a connection group output action). When an incoming packet matches the flow entry, the switch selects an active connection from the particular connection group and transmits the packet to the controller using the selected active connection (e.g., embedded in a Packet- In message). If the switch determines that a connection established with the controller has been lost (e.g., due to link failure, node failure, process failure, etc.), the switch marks that connection as being inactive. When selecting an active connection from a connection group, the switch does not select a connection that is marked as being inactive. In this way, traffic loss due to connection failure can be avoided, while still providing control over which connection the switch should use when transmitting a certain type of packet to the controller. Furthermore, a flow entry need not be re-programmed when a connection fails, as long as there is at least one active connection remaining in the connection group. Embodiments described herein further protect against a case where all of the connections in a connection group fail by provisioning a fallback connection group for the connection group. In the case that all of the connections in the connection group fail (e.g., are marked as being inactive), the switch may select an active connection from the fallback connection group.
[0045] It should be understood that a controller group output action or a connection group output action can be included in the set of instructions in any type of entry in the switch that is used for determining packet processing. For example, in the OpenFlow context, a controller group output action or a connection group output action can be included in the set of instructions in a flow entry or a group entry.
Controller Group Output Actions
[0046] Fig. 1 is a block diagram illustrating an SDN network in which controller group output actions can be implemented, according to some embodiments. A simple network topology of an SDN network 100 that includes three controllers (e.g., SDN controllers) (controllers 110X-Z) and three switches (switches 120A-C) is illustrated in Fig. 1. Each of the controllers 110 may connect to the switches 120 over a network 115. Each controller 110 is assigned a controller identifier that uniquely identifies the controller 110. Controller 110X is assigned controller identifier X, controller 110Y is assigned controller identifier Y, and controller 110Z is assigned controller identifier Z. Each switch 120 includes a set of flow entries 130. In one embodiment, a flow entry 130 includes a packet matching criteria (e.g., match field) and a corresponding set of instructions to execute when a packet matches the packet matching criteria. A packet is said to match a flow entry 130 if the packet matches the packet matching criteria of the flow entry 130. The flow entries 130 are described in additional detail herein below with reference to Fig. 2. [0047] In one embodiment, the controllers 110 and the switches 120 communicate using a version of OpenFlow (e.g., OpenFlow 1.3) as the communication protocol. In one embodiment, OpenFlow can be extended as described herein below to support controller group output actions in the SDN network. For clarity and ease of understanding, embodiments will primarily be described using OpenFlow (and extensions thereto) as the communication protocol between the controllers 110 and switches 120. However, it should be understood that the controllers 110 and switches 120 can communicate using other types of protocols and that other protocols can be extended in a similar fashion to support controller group output actions.
[0048] In one embodiment, when a controller 110 and a switch 120 first establish a connection, the controller 110 transmits an OFPT_FEATURES_REQUEST message to the switch 120 requesting that the switch 120 identify capabilities/features supported by the switch 120. The switch 120 then responds to the controller with an
OFPT_FEATURES_REPLY message that identifies the capabilities/features that the switch 120 supports. In OpenFlow 1.3, only certain capabilities/features are included as part of the
OFPT_FEATURES_REPLY message, as defined by ofp_capabilities. In one embodiment, OpenFlow can be extended so that the controller 110 can be informed of additional
capabilities/features of the switch 120 (e.g., vendor-specific capabilities). In one embodiment, the controller 110 transmits a VENDOR_SPECIFIC_SWITCH_FEATURES_REQUEST message requesting that the switch 120 identify additional capabilities/features supported by the switch 120. The switch 120 then responds to the controller 110 with a
VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY message identifying additional capabilities/features that the switch 120 supports. In one embodiment, the
VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY message includes an indication of whether the switch 120 supports controller group output action features.
[0049] In one embodiment, a switch 120 maintains a logical grouping of controllers 110, which is referred to herein as a controller group. Each switch 120 may maintain one or more controller groups. Each controller group may be identified using a controller group identifier assigned to that controller group and may include one or more controllers 110. Each
controller 110 may be identified using a controller identifier assigned to that controller 110.
[0050] In one embodiment, a switch 120 maintains a database that stores information regarding the configuration of controller groups. For example, the database may store an indication of the one or more controllers 110 included in a particular controller group. In one embodiment, the database is an Open vSwitch database (OVSDB). The OVSDB can be managed using an OVSDB protocol. For the sake of illustration, embodiments will be described in the context where the switch 120 stores information regarding the configuration of controller groups in an OVSDB (and where an OVSDB protocol is used to manage the OVSDB).
However, it should be understood that the switch 120 can store information regarding the configuration of controller groups in a different type of database or storage and use a different type of protocol for managing the database or storage.
[0051] An OVSDB may maintain a controller table that stores configuration information regarding controllers. The controller table may include fields for specifying values for various configuration parameters pertaining to a controller 110 (e.g., whether the controller 110 is a primary controller or a service controller, whether asynchronous messages are enabled for the controller 110, and a rate limit for the controller 110).
[0052] In one embodiment, the other_config field of the controller table can be used to specify the controller groups to which a particular controller 110 belongs. As an example, the following format can be used to specify the controller groups to which a particular controller 110 belongs. Other_config: "controller groups: <x>, <y>, <z>"
This configuration indicates that the controller 110 belongs to controller groups identified by controller group identifiers x, y, and z.
[0053] A controller 110 may program a switch 120 to generate a flow entry 130 in the switch 120 by transmitting an OFPT_FLOW_MOD message to the switch 120. In one embodiment, the OFPT_FLOW_MOD message includes a packet matching criteria (e.g., match field) and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from a particular controller group (e.g., a controller group output action). The particular controller group may be specified using a controller group identifier assigned to that particular controller group. Whenever a packet matches this flow entry 130, the switch 120 selects an active controller 110 from the particular controller group and transmits the packet to the selected active controller 110 (e.g., embedded in a Packet- In message). If the switch 120 determines that the connection to a particular controller 110 has been lost, the switch 120 marks that particular controller 110 as being inactive. In one embodiment, the switch 120 determines that a connection to a particular controller 110 has been lost based on a determination that a Transmission Control Protocol (TCP) connection to that particular controller 110 has been terminated (e.g., which can be detected by an underlying operating system of the switch 120). In one embodiment, the switch 120 determines that a connection to a particular controller 110 has been lost based on detecting a loss of heartbeat message from that particular controller 110. In one embodiment, the switch 120 determines that a connection to a particular controller 110 has been lost based on detecting a link failure using a Bidirectional Forwarding Detection (BFD) protocol. When selecting an active controller 110 from a controller group, the switch 120 does not select a controller 110 that is marked as being inactive. If the switch 120 determines that the connection to the particular controller 110 has been restored, the switch 120 marks that particular controller 110 as being active (e.g., by unmarking the particular controller 110 from being inactive).
[0054] For example, consider a switch 120 that is communicatively coupled to three controllers (controller CI, controller C2, and controller C3). In this example, controller CI belongs to controller groups 10 and 11. Controller C2 belongs to controller groups 11 and 12. Controller C3 belongs to controller groups 10 and 12. With this configuration, controller group 10 includes two controllers (controllers CI and C3), controller group 11 includes two controllers (controllers CI and C2), and controller group 12 includes two controllers
(controllers C2 and C3).
[0055] When an incoming packet matches a flow entry 130 that instructs the switch 120 to transmit matching packets to a controller 110 to be selected from controller group 10, the switch 120 selects one of the active controllers 110 in controller group 10 (controller C 1 or controller C3 - assuming both of these controllers are active) and transmits the incoming packet to the selected active controller 110. If the switch 120 determines that the connection to controller C3 has been lost, the switch 120 marks controller C3 as being inactive. When a subsequent incoming packet matches the flow entry 130, the switch 120 selects one of the active controllers 110 in controller group 10 (which is only controller C3 in this example, since controller CI is marked as being inactive) and transmits the incoming packet to the selected active controller 110 (controller C3 in this example).
[0056] In one embodiment, a fallback controller group is provisioned for a controller group. A fallback controller group for a controller group provides protection against the case when all of the controllers 110 in the controller group fail (e.g., are all marked as being inactive). If all of the controllers 110 in a controller group fail, then the switch 120 may select an active controller 110 from the fallback controller group provisioned for the controller group and transmit the incoming packet to the selected active controller 110 from the fallback controller group. In one embodiment, a fallback controller group may be provisioned for another fallback controller group to provide additional protection against controller failures.
[0057] In one embodiment, the other_config field of the Open_vSwitch table (since this configuration applies across controllers) can be used to specify the fallback controller group for a controller group. As an example, the following format can be used to specify the fallback controller group for a controller group.
Other_config: "fallback controller group: <x>, < >"
This configuration indicates that the controller group identified by controller group identifier y is a fallback controller group for the controller group identified by controller group identifier x. [0058] Returning to the example described above, assume that controller group 11 is provisioned as a fallback controller group for controller group 10. Also assume that all of the controllers 110 in controller group 10 are marked as being inactive. When an incoming packet matches a flow entry 130 that instructs the switch 120 to transmit matching packets to a controller 110 to be selected from controller group 10, the switch 120 will consider the controllers 110 in controller group 10 (controllers CI and C3) for selection, but all of the controllers 110 in controller group 10 are marked as being inactive. As such, the switch 120 will instead consider the controllers 110 in controller group 11, which is provisioned as the fallback controller group for controller group 10. Controller group 11 includes controllers CI and C2. Since controller CI is marked as being inactive, the switch 120 will not select controller CI, but select controller C2 (assuming controller C2 is active), and transmit the incoming packet to controller C2. By provisioning a fallback controller group for a controller group, traffic loss is avoided even when all of the controllers 110 in the controller group are marked as being inactive.
[0059] An advantage of the controller group output action mechanism is that traffic loss due to controller 110 failure can be avoided, while still providing control over which controller 110 the switch 120 should transmit a packet to based on the packet type (e.g., which enables load sharing among controllers). Another advantage is that a flow entry 130 need not be re- programmed when a controller 110 fails, as long as there is at least one active controller 110 remaining in the controller group. Yet another advantage is that the behavior of the switch 120 in terms of which controller 110 the switch 120 transmits a certain type of packet to can be dynamically modified by adding/deleting controllers 110 to/from a controller group, without modifying a flow entry 130. Also, the provisioning of a fallback controller group for a controller group protects against a case where all of the controllers 110 in a controller group fail.
[0060] In one embodiment, the following exemplary structures can be used for the message exchange between a controller 110 and a switch 120 to support controller group output actions. The exemplary structures extend OpenFlow to support controller group output actions.
[0061] Capabilities Flag:
enum vendor_specific_switch_features_capabilities flags {
CONTROLLER_GROUP_BASED_PACKET_PUNTING = 1 « 1
} ;
[0062] VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST:
/* Experimenter extension. */
/* For Vendor Specific Switch Features Request, send expjype is
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST */ struct ofp_experimenter_header {
struct ofpjieader header; /* Type OFPT_EXPERIMENTER. */
uint32_t experimenter; /* Experimenter ID:
* - MSB 0: low-order bytes are IEEE OUI.
* - MSB != 0: defined by ONF. */
uint32_t expjype; /* Experimenter defined. */
/* Experimenter-defined arbitrary additional data. */
} ;
OFP_ASSERT(sizeof(struct ofp_experimenter_header) == 16);
[0063] VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY:
struct vendor_switch_features_reply {
struct ofp_experimenter_header exp_header; /* expjype is
VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY */ uint64_t datapath_id; /* Datapath unique ID.*/
uint32_t length; /* length of exp_capabilities in bytes */
uint8_t pad[4] ; /* Align to 64 bits */
/* Followed by length bytes containing the capabilities data */
uint8_t exp_capabilities[0]; /* Bitmap of support
"vendor_switch_features_capabilities" . */
} ;
OFP_ASSERT(sizeof(struct vendor_switch_features_reply) == 32);
[0064] Common Header:
/* All messages in this extension use the following message header */
/* Common header for all messages */
struct vendor_header {
struct ofpjieader header; /* OFPT_EXPERIMENTER. */
uint32_t experimenter; /* VENDOR_EXPERIMENTER_ID. */
uint32_t exp_type; /* One of MSG_TYPE_* above. */
} ;
OFP_ASSERT(sizeof(struct vendor_header) == sizeof(struct ofp_experimenter_header));
[0065] Controller Group Output Action:
/* Message structure for controller group output action */
struct ofp_action_controller_group_output {
uintl6_t type; /* OFPAT_OUTPUT. */
uintl6_t len; /* Length is 16. */ uintl6_t port; /* CONTROLLER */
uint64_t controller_group_id /* controller group from which a controller should be selected */
uintl6_t max_len; /* Max length to send to controller. */
} ;
[0066] Fig. 2 is a diagram illustrating a set of flow entries in a switch for providing controller group output actions, according to some embodiments. It is assumed that the switch 120 has three controller groups configured (controller group identified by controller group identifier X, controller group identified by controller group identifier Y, and controller group identified by controller group identifier Z). In one embodiment, the programming of the flow entries 130 in the switch 120 is controlled by one or more controllers 110. Each flow entry 130 includes a packet matching criteria and a corresponding set of instructions. When the switch 120 receives a packet that matches a packet matching criteria of a flow entry 130, the switch 120 executes the corresponding set of instructions of that flow entry 130. As illustrated, the switch 120 includes N flow entries 130.
[0067] The first flow entry has a packet matching criteria that matches packets that are associated with an ARP service and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from the controller group identified by controller group identifier X. In one embodiment, the packet matching criteria identifies ARP packets by matching ETH_TYPE=0x806. Thus, if the switch 120 receives an incoming ARP packet, the switch 120 selects an active controller 110 from the controller group identified by controller group identifier X and transmits the packet to the selected active controller 110.
[0068] The second flow entry has a packet matching criteria that matches packets that are associated with an LLDP service and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from the controller group identified by controller group identifier Y. In one embodiment, the packet matching criteria identifies LLDP packets by matching ETH_TYPE=Ox88cc. Thus, if the switch 120 receives an incoming LLDP packet, the switch 120 selects an active controller 110 from the controller group identified by controller group identifier Y and transmits the packet to the selected active controller 110.
[0069] The third flow entry has a packet matching criteria that matches packets that are associated with a DHCP service and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from a controller group identified by controller group identifier Z. In one embodiment, the packet matching criteria identifies DHCP packets by matching ETH_TYPE=0x800 (IP), IP_PROTO=0xl l (UDP), and UDP_SRC/UDP_DST=67/68, depending on whether the packet is for client/server traffic. Thus, if the switch 120 receives an incoming DHCP packet, the switch 120 selects an active controller 110 from the controller group identified by controller group identifier Z and transmits the packet to the selected active controller 110.
[0070] The fourth flow entry has a packet matching criteria that matches packet type A (which can be user-defined) and a corresponding instruction to transmit packets matching the packet matching criteria to a controller 110 to be selected from the controller group identified by controller group identifier Y. Thus, if the switch 120 receives an incoming packet of packet type A, then the switch 120 selects an active controller 110 from the controller group identified by controller group identifier Y and transmits the packet to the selected active controller 110.
[0071] The Nth flow entry is a catch-all entry that matches packets that did not match any of the other flow entries 130. The corresponding instruction for this flow entry 130 is an instruction to transmit matching packets to a controller 110 to be selected from the controller group identified by controller group identifier Z. Thus, if the switch 120 receives an incoming packet that does not match any of the other flow entries 130 in the switch 120, the switch 120 selects an active controller 110 from the controller group identified by controller group identifier Z and transmits the packet to the selected active controller 110.
[0072] In this way, flow entries 130 can be programmed in a switch 120 to transmit packets associated with a given service or that match a given packet matching criteria to a controller 110 to be selected from a particular controller group. This allows for an asymmetric cluster of controller groups, where each controller group handles specific services. In the example given above, the flow entries 130 in the switch 120 are programmed such that ARP packets are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier X, LLDP packets are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Y, and DHCP packets are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Z. Furthermore, packets having packet type A (which may be any user-defined packet matching criteria), are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Y (similar to LLDP packets). Packets that do not match any of the above flow entries 130 are transmitted to a controller 110 to be selected from the controller group identified by controller group identifier Z (similar to DHCP packets).
[0073] In the above examples, if a particular controller group does not include any active controllers 110 (e.g., all controllers 110 in the particular controller group are marked as being inactive), then the switch 120 may select an active controller 110 from a fallback controller group provisioned for the particular controller group (if one has been provisioned) and transmit the matching packet to the active controller 110 selected from the fallback controller group.
[0074] It should be understood that the flow entries 130 described herein are provided by way of example and not limitation, and that one having ordinary skill in the art will understand that the switch 120 can include any number of flow entries 130, and that the flow entries 130 can have any desired packet matching criteria. Also, the instructions of a flow entry 130 may include other instructions besides transmitting a packet to a controller 110 to be selected from a particular controller group. For example, a flow entry 130 can include instructions to push/pop tags, modify packet header fields, change the time-to-live (TTL) of the packet, and other packet processing instructions.
[0075] It should also be understood that a controller group output action can be included in the set of instructions in any type of entry in the switch 120 that is used for determining packet processing (and not just flow entries 130). For example, in an OpenFlow context, a controller group output action can be included in the set of instructions in a group entry.
[0076] Fig. 3 is a flow diagram of a process implemented by a switch for performing controller group output actions, according to some embodiments. In one embodiment, the operations of the flow diagram may be implemented by a network device functioning as a switch 120 in an SDN network 100, where the switch 120 is communicatively coupled to a plurality of SDN controllers 110 in the SDN network 100. The operations in this and other flow diagrams will be described with reference to the exemplary embodiments of the other figures. However, it should be understood that the operations of the flow diagrams can be performed by embodiments of the invention other than those discussed with reference to the other figures, and the embodiments of the invention discussed with reference to these other figures can perform operations different than those discussed with reference to the flow diagrams.
[0077] In one embodiment, the process is initiated when the switch 120 establishes a connection with an SDN controller 110. In one embodiment, after a connection is established between the switch 120 and the SDN controller 110, the switch 120 receives a request from the SDN controller 110 to identify features supported by the switch 120 (block 305). In one embodiment, the request is in the form of the
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST structure described above, or similar structure. The switch 120 then transmits a response to the SDN controller 110 that identifies the features supported by the switch 120 (block 310). In one embodiment, the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure. The VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field). In one embodiment, if the switch 120 supports controller group output action features, then the switch 120 includes an indication in the response transmitted to the SDN controller 110 that the switch 120 supports controller group output action features.
[0078] The switch 120 generates an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller 110 to be selected from a first controller group, where the first controller group includes one or more SDN controllers 110 from the plurality of SDN controllers 110 communicatively coupled to the switch 120 (block 315). In one embodiment, the entry is a flow entry 130 (e.g., OpenFlow flow entry). In another embodiment, the entry is a group entry (e.g., OpenFlow group entry). In one embodiment, the entry is generated in response to receiving an instruction from an SDN controller 110 to generate entry. The instruction to generate the entry can come from any SDN controller 110 with which the switch 120 is connected. In one embodiment, the first controller group is specified in the entry using a controller group identifier assigned to the first controller group. In one
embodiment, the instruction received from the SDN controller 110 to generate the entry (e.g., an OFPT_FLOW_MOD message) includes a Controller Group Output Action structure described above, or similar structure.
[0079] When the switch 120 receives a packet for forwarding (block 320), it determines whether the packet is to be processed according to the entry (decision block 325). In one embodiment, the switch 120 determines that the packet is to be processed according to the entry based on determining that the packet matches the packet matching criteria of the entry (e.g., when the entry is an OpenFlow flow entry). If the packet is not to be processed according to the entry, then the switch 120 may continue packet processing, as necessary (block 330). On the other hand, if the packet is to be processed according to the entry, then the switch 120 selects an active SDN controller 110 from the first controller group (e.g., according to the instruction in the entry) (block 335) and transmits the packet to the active SDN controller 110 selected from the first controller group (block 340). The switch 120 may then repeat blocks 320-340 for other packets that it receives.
[0080] In one embodiment, the switch 120 marks an SDN controller 110 from the first controller group as being inactive in response to a determination that a connection to the SDN controller 110 has been lost. When selecting an active SDN controller 110 from a controller group, the switch 120 does not select an SDN controller 110 that is marked as being inactive. In one embodiment, the determination that the connection to the SDN controller 110 has been lost is based on a determination that a TCP connection to the SDN controller 110 has been terminated (e.g., which can be detected by an underlying operating system of the switch 120). In one embodiment, the determination that the connection to the SDN controller 110 has been lost is based on detecting a loss of heartbeat message from the SDN controller 110. In one embodiment, the determination that the connection to the SDN controller 110 has been lost is based on detecting a link failure using Bidirectional Forwarding Detection (BFD) protocol.
[0081] In one embodiment, a second controller group (that includes one or more SDN controllers 110 from the plurality of controllers communicatively coupled to the switch 120) is provisioned as a fallback controller group for the first controller group. In one embodiment, if the switch 120 determines that the packet is to be processed according to the entry but that all of the one or more SDN controllers 110 in the first controller group are marked as being inactive, then the switch 120 selects an active SDN controller 110 from the second controller group and transmits the packet to the active SDN controller 110 selected from the second controller group.
[0082] In one embodiment, the switch 120 maintains a database (or other type of storage) that stores information regarding the configuration of controller groups. For example, the database may store an indication of the one or more SDN controllers 110 included in a particular controller group (e.g., the first controller group and the second controller group). In one embodiment, the database may store an indication that a particular controller group is a fallback controller group for another controller group (e.g., the second controller group is a fallback controller group for the first controller group). In one embodiment, the database is an OVSDB and is managed using an OVSDB protocol.
[0083] Fig. 4 is a flow diagram of a process implemented by a controller for programming a switch to perform controller group output actions, according to some embodiments. In one embodiment, the operations of the flow diagram may be implemented by a network device functioning as an SDN controller 110 in an SDN network 100, where the SDN controller 110 is communicatively coupled to a switch 120 in the SDN network 100, and where the switch 120 is communicatively coupled to a plurality of SDN controllers 110 in the SDN network 100.
[0084] In one embodiment, the process is initiated when the switch 120 establishes a connection with the SDN controller 110. In one embodiment, after a connection is established between the switch 120 and the SDN controller 110, the SDN controller 110 transmits a request to the switch 120 to identify features supported by the switch 120 (block 405). In one embodiment, the request is in the form of the
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST structure described above, or similar structure. The SDN controller 110 then receives a response from the switch 120 that identifies the features supported by the switch 120 (block 410). In one embodiment, the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure. The VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field). In one embodiment, if the switch 120 supports controller group output action features, then the response received from the switch 120 includes an indication that the switch 120 supports controller group output action features.
[0085] The SDN controller 110 then determines whether the switch 120 supports controller group output action features (e.g., based on the response from the switch 120 that identifies the features supported by the switch 120) (decision block 415). If the switch 120 does not support controller group output action features, then the SDN controller 110 proceeds with normal processing (e.g., without controller group output action features) (block 420).
[0086] On the other hand, if the switch 120 supports controller group output action features, then the SDN controller 110 transmits an instruction to the switch 120 to generate an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller 110 to be selected from a first controller group, where the first controller group includes one or more SDN controllers 110 from the plurality of SDN controllers 110
communicatively coupled to the switch 120 (block 425). In one embodiment, the entry is a flow entry 130 (e.g., OpenFlow flow entry). In another embodiment, the entry is a group entry (e.g., OpenFlow group entry). In one embodiment, the first controller group is specified using a controller group identifier assigned to the first controller group. In one embodiment, the instruction transmitted to the switch 120 to generate the entry (e.g., an OFPT_FLOW_MOD message) includes a Controller Group Output Action structure described above, or similar structure.
Connection Group Output Actions
[0087] Fig. 5 is a block diagram illustrating an SDN network in which connection group output actions can be implemented, according to some embodiments. As illustrated, the SDN network 100 includes three switches (switches 120A-C) and a controller 110 (e.g., SDN controller) that controls the switches 120. The controller 110 has three services running on it (services 515A-C). Each switch 120 may establish multiple connections with the controller 110. Each connection between a switch 120 and the controller 110 is assigned a connection identifier. The connection identifier uniquely identifies a connection between a switch 120 and the controller 110. As illustrated, switch 120A has established three connections with the controller 110. The first connection is assigned connection identifier X, the second connection is assigned connection identifier Y, and the third connection is assigned connection identifier Z. Similarly, switch 120B has established three connections with the controller 110. The first connection is assigned connection identifier A, the second connection is assigned connection identifier B, and the third connection is assigned connection identifier C. Similarly, switch 120C has established three connections with the controller 110. The first connection is assigned connection identifier J, the second connection is assigned connection identifier K, and the third connection is assigned connection identifier L. These connections are shown by way of example and not limitation. It should be understood that each switch 120 can have any number of connections established with the controller 110 and that different switches 120 can have a different number of connections established with the controller 110. Each switch 120 includes a set of flow entries 130. In one embodiment, a flow entry 130 includes a packet matching criteria (e.g., match field) and a corresponding set of instructions to execute when a packet matches the packet matching criteria. A packet is said to match a flow entry 130 if the packet matches the packet matching criteria of the flow entry 130. The flow entries 130 are described in more detail herein below with reference to Fig. 6.
[0088] In one embodiment, the controller 110 and the switches 120 communicate using a version of OpenFlow (e.g., OpenFlow 1.3) as the communication protocol. In one embodiment, OpenFlow can be extended as described herein below to support connection group output actions in the SDN network 100. For clarity and ease of understanding, embodiments will primarily be described using OpenFlow (and extensions thereto) as the communication protocol between the controller 110 and the switches 120. However, it should be understood that the controller 110 and the switches 120 can communicate using other types of protocols and that other types of protocols can be extended in a similar fashion to support connection group output actions without departing from the spirit and scope of the present disclosure.
[0089] In one embodiment, when a controller 110 and a switch 120 establish a connection, the controller 110 transmits an OFPT_FEATURES_REQUEST message to the switch 120 requesting that the switch 120 identify capabilities/features supported by the switch 120. The switch 120 then responds to the controller 110 with an OFPT_FEATURES_REPLY message that identifies the capabilities/features supported by the switch 120. In one embodiment, the OFPT_FEATURES_REPLY message includes connection identifier information (e.g., auxiliary identifier) for the connection being established. In OpenFlow 1.3, only certain
capabilities/features are included as part of the OFPT_FEATURES_REPLY message, as defined by ofp_capabilities. In one embodiment, OpenFlow can be extended so that the controller 110 can be informed of additional capabilities/features supported by the switch 120 (e.g., vendor- specific capabilities). In one embodiment, the controller 110 transmits a
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST message to the switch 120 requesting that the switch 120 identify additional capabilities/features supported by the switch 120. The switch 120 then responds to the controller 110 with a
VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY message identifying additional capabilities/features supported by the switch 120. In one embodiment, the
VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY message includes an indication of whether the switch 120 supports connection group output action features.
[0090] In one embodiment, a switch 120 maintains a logical grouping of connections established with a controller 110, which is referred to herein as a connection group. Each switch 120 may maintain one or more connection groups. Each connection group may be identified using a connection group identifier assigned to that connection group and each connection group may include one or more connections. Each connection may be identified using a connection identifier assigned to that connection.
[0091] In one embodiment, a switch 120 maintains a database that stores information regarding the configuration of connection groups. For example, the database may store an indication of the one or more connections included in a particular connection group. In one embodiment, the database is an OVSDB. The OVSDB can be managed using an OVSDB protocol. For the sake of illustration, embodiments will be described in the context where the switch 120 stores information regarding the configuration of connection groups in an OVSDB (and where an OVSDB protocol is used to manage the OVSDB). However, it should be understood that the switch 120 can store information regarding the configuration of connection groups in a different type of database or storage and use a different type of protocol for managing the database or storage.
[0092] An OVSDB may maintain a controller table that stores configuration information regarding controllers 110. The controller table may include fields for specifying values for various configuration parameters pertaining to a controller 110 (e.g., whether the controller 110 is a primary controller or a service controller, whether asynchronous messages are enabled for the controller 110, and a rate limit for the controller 110).
[0093] In one embodiment, the other_config field of the controller table can be used to specify the connections that are included in a particular connection group. As an example, the following format can be used to specify the connection that are included in a particular connection group. Other_config: "connection-group-<n>: <x>, <y>, <z>"
This configuration indicates that the connection group identified by connection group identifier n includes the connections identified by connection identifiers x, y, and z.
[0094] A controller 110 may program a switch 120 to generate a flow entry 130 in the switch 120 by transmitting an OFPT_FLOW_MOD message to the switch 120. In one embodiment, the OFTP_FLOW_MOD message includes a packet matching criteria (e.g., match field) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from a particular connection group (e.g., a connection group output action). The particular connection group may be specified using a connection group identifier assigned to that particular connection group. Whenever a packet matches this flow entry 130, the switch 120 selects an active connection from the particular connection group and transmits the packet to the controller 110 using the selected active connection (e.g., embedded in a Packet-In message). If the switch 120 determines that the connection has been lost, the switch 120 marks that particular connection as being inactive. In one embodiment, the switch 120 determines that a connection has been lost based on a determination that a TCP connection associated with that connection has been terminated (e.g., which can be detected by an underlying operating system of the switch 120). In one
embodiment, the switch 120 determines that a connection has been lost based on detecting a loss of heartbeat message from the controller 110 over that connection. When selecting an active connection from a connection group, the switch 120 does not select a connection that is marked as being inactive. If the switch 120 determines that the connection has been restored, the switch 120 marks that particular connection as being active (e.g., by unmarking the particular connection from being inactive).
[0095] For example, consider a switch 120 that has established three different connections (connection cl, connection c2, and connection c3) with a controller 110. In this example, connection cl belongs to connection groups 10 and 11. Connection c2 belongs to connection groups 11 and 12. Connection c3 belongs to connection groups 10 and 12. With this configuration, connection group 10 includes two connections (connections cl and c3), connection group 11 includes two connections (connections cl and c2), and connection group 12 includes two connections (connections c2 and c3).
[0096] When an incoming packet matches a flow entry 130 that instructs the switch 120 to transmit matching packets to the controller 110 using a connection to be selected from
connection group 10, the switch 120 selects one of the active connections from connection group 10 (connection cl or connection c3 - assuming both of these connections are active) and transmits the incoming packet to the controller 110 using the selected active connection. If the switch 120 determines that connection c3 has been lost, the switch 120 marks connection c3 as being inactive. When a subsequent incoming packet matches the flow entry 130, the switch 120 selects one of the active connections from connection group 10 (which is only connection c3 in this example, since connection cl is marked as being inactive) and transmits the incoming packet to the controller 110 using the selected active connection (connection c3 in this example).
[0097] In one embodiment, a fallback connection group is provisioned for a connection group. A fallback connection group for a connection group provides protection against the case when all of the connections in the connection group fail (e.g., are all marked as being inactive). If all of the connections in a connection group fails, then the switch 120 may select an active connection from the fallback connection group provisioned for the connection group and transmit the incoming packet to the controller 110 using the active connection selected from the fallback connection group. In one embodiment, a fallback connection group may be provisioned for another fallback connection group to provide additional protection against connection failures.
[0098] In one embodiment, the other_config field the controller table can be used to specify the fallback connection group for a connection group (since this configuration is per controller). As an example, the following format can be used to specify the fallback connection group for a connection group.
Other_config: "fallback connection group: <x>, < >"
This configuration indicates that the connection group identified by connection group identifier y is a fallback connection group for the connection group identified by connection group identifier x.
[0099] Returning to the example described above, assume that connection group 11 is provisioned as a fallback connection group for connection group 10. Also assume that all of the connections in connection group 10 are marked as being inactive. When an incoming packet matches a flow entry 130 that instructs the switch 120 to transmit matching packets to the controller 110 using a connection to be selected from connection group 10, the switch 120 will consider the connections in connection group 10 (connections 1 and 3) for selection, but all of the connections in connection group 10 are marked as being inactive. As such, the switch 120 will instead consider the connections in connection group 11, which is provisioned as the fallback connection group for connection group 10. Connection group 11 includes
connections cl and c2. Since connection cl is marked as being inactive, the switch 120 will not select connection cl, but select connection c2 (assuming connection c2 is active) and transmit the incoming packet to the controller 110 using connection c2. By provisioning a fallback connection group for a connection group, traffic loss is avoided even when all of the connections in the connection group are marked as being inactive.
[00100] An advantage of the connection group output action mechanism is that traffic loss due to connection failure can be avoided, while still providing control over which connection the switch 120 should use when transmitting a certain type of packet to the controller 110 (e.g., which enables load sharing among connections). Another advantage is that a flow entry 130 need not be re-programmed when a connection fails, as long as there is at least one active connection remaining in the connection group. Yet another advantage is that the behavior of the switch 120 in terms of which connection the switch 120 uses when transmitting a packet to a controller 110 can be dynamically modified by adding/deleting connections to/from a connection group, without modifying a flow entry 130. Also, the provisioning of a fallback connection group for a connection group protects against a case where all of the connections in a connection group fail.
[00101] In one embodiment, the following exemplary structures can be used for the message exchange between the controller 110 and switches 120 for implementing connection group output actions. The exemplary structures extend OpenFlow to support connection group output actions.
[00102] Capabilities Flag:
enum vendor_specific_switch_features_capabilities flags {
CONNECTION_GROUP_B AS ED_P AC KET_PUNTING = 1 « 1
} ;
[00103] VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST:
/* Experimenter extension. */
/* For Vendor Specific Switch Features Request, send expjype is
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST */
struct ofp_experimenter_header {
struct ofpjieader header; /* Type OFPT_EXPERIMENTER. */
uint32_t experimenter; /* Experimenter ID:
* - MSB 0: low-order bytes are IEEE OUI.
* - MSB != 0: defined by ONF. */
uint32_t expjype; /* Experimenter defined. */
/* Experimenter-defined arbitrary additional data. */
} ;
OFP_ASSERT(sizeof(struct ofp_experimenter_header) == 16);
[00104] VENDOR_SPECIFIC_SWrrCH_FEATURES_REPLY:
struct vendor_switch_features_reply {
struct ofp_experimenter_header expjieader; /* expjype is
VENDOR _SPECIFIC_SWrrCH_FEATURES_REPLY */ uint64j datapathjd; /* Datapath unique ID.*/
uint32 J length; /* length of exp_capabilities in bytes */
uint8 J pad[4] ; /* Align to 64 bits */
/* Followed by length bytes containing the capabilities data */
uint8j exp_capabilities[0]; /* Bitmap of support
"vendor_switch eatures_capabilities" . */ } ;
OFP_ASSERT(sizeof(struct vendor_switch_features_reply) == 32);
[00105] Common Header:
/* All messages in this extension use the following message header */
/* Common header for all messages */
struct vendor_header {
struct ofpjieader header; /* OFPT_EXPERIMENTER. */
uint32_t experimenter; /* VENDOR_EXPERIMENTER_ID. */
uint32_t exp_type; /* One of MSG_TYPE_* above. */
} ;
OFP_ASSERT(sizeof(struct vendor_header) == sizeof(struct ofp_experimenter_header));
[00106] Connection Group Output Action:
/* Message structure for connection group output action */
struct ofp_action_connection_group_output {
uintl6_t type; /* OFPAT_OUTPUT. */
uintl6_t len; /* Length is 16. */
uintl6_t port; /* CONTROLLER */
uint64_t connection_group_id /* connection group from which a connection should be selected */
uintl6_t max_len; /* Max length to send to controller. */
} ;
[00107] Fig. 6 is a diagram illustrating a set of flow entries in a switch for providing connection group output actions, according to some embodiments. It is assumed that the switch 120 has three connection groups configured (connection group identified by connection group identifier X, connection group identified by connection group identifier Y, and connection group identified by connection group identifier Z). In one embodiment, the programming of the flow entries 130 in the switch 120 is controlled by one or more controllers 110. Each flow entry 130 includes a packet matching criteria and a corresponding set of instructions. When the switch 120 receives a packet that matches a packet matching criteria of a flow entry 130, the switch 120 executes the corresponding set of instructions of that flow entry 130. As illustrated, the switch 120 includes N flow entries 130.
[00108] The first flow entry has a packet matching criteria that matches packets associated with an ARP service (e.g., service 515A) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier X. In one embodiment, the packet matching criteria identifies ARP packets by matching ETH_TYPE=0x806. Thus, if the switch 120 receives an incoming ARP packet, then the switch 120 selects a connection from the connection group identified by connection group identifier X and transmits the packet to the controller 110 using the selected active connection.
[00109] The second flow entry has a packet matching criteria that matches packets associated with an LLDP service (e.g., service 515B) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y. In one embodiment, the packet matching criteria identifies LLDP packets by matching ETH_TYPE=Ox88cc. Thus, if the switch 120 receives an incoming LLDP packet, then the switch 120 selects a connection from the connection group identified by connection group identifier Y and transmits the packet to the controller 110 using the selected active connection.
[00110] The third flow entry has a packet matching criteria that matches packets associated with a DHCP service (e.g., service 515C) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z. In one embodiment, the packet matching criteria identifies DHCP packets by matching ETH_TYPE=0x800 (IP), IP_PROTO=0xl l (UDP), and UDP_SRC/UDP_DST=67/68, depending on whether the packet is client/server traffic. Thus, if the switch 120 receives an incoming DHCP packet, then the switch 120 selects a connection from the connection group identified by connection group identifier Z and transmits the packet to the controller 110 using the selected active connection.
[00111] The fourth flow entry has a packet matching criteria that matches packet type A (which can be user-defined) and a corresponding instruction to transmit packets matching the packet matching criteria to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y. Thus, if the switch 120 receives an incoming packet of packet type A, then the switch 120 selects a connection from the connection group identified by connection group identifier Y and transmits the packet to the controller 110 using the selected active connection.
[00112] The Nth flow entry is a catch-all entry that matches packets that did not match any of the other flow entries 130. The corresponding instruction for this flow entry 130 is an instruction to transmit matching packets to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z. Thus, if the switch 120 receives an incoming packet that does not match any of the other flow entries 130 in the switch 120, then the switch 120 selects a connection from the connection group identified by connection group identifier Z and transmits the packet to the controller 110 using the selected active connection.
[00113] In this way, the flow entries 130 can be programmed in a switch 120 to transmit packets associated with a given service or that match a given packet matching criteria to the controller 110 using a connection to be selected from a particular connection group. In the example given above, the flow entries 130 in the switch 120 are programmed such that ARP packets are transmitted to a controller 110 using a connection to be selected from the connection group identified by connection group identifier X, LLDP packets are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y, and DHCP packets are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z. Furthermore, packets having packet type A (which may be any user-defined packet matching criteria), are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Y (similar to LLDP packets).
Packets that do not match any of the other flow entries 130 in the switch 120 are transmitted to the controller 110 using a connection to be selected from the connection group identified by connection group identifier Z (similar to DHCP packets).
[00114] In the above examples, if a particular connection group does not include any active connections (e.g., all connections in the particular controller group are marked as being inactive), then the switch 120 may select an active connection from a fallback connection group provisioned for the particular connection group (if one has been provisioned) and transmit the matching packet to the controller 110 using the active connection selected from the fallback connection group.
[00115] It should be understood that the flow entries 130 described herein and illustrated in the diagram are provided by way of example and not limitation. It should be understood that the switch 120 can include any number of flow entries 130, and that the flow entries 130 can have any desired packet matching criteria. Also, the instructions of a flow entry 130 may include other instructions besides transmitting a packet to a controller 110 using a connection to be selected from a particular connection group. For example, a flow entry 130 can include instructions to push/pop tags, modify packet header fields, change the TTL of the packet, and other packet processing instructions.
[00116] It should also be understood that a controller group output action can be included in the set of instructions in any type of entry in the switch 120 that is used for determining packet processing (and not just flow entries 130). For example, in an OpenFlow context, a controller group output action can be included in the set of instructions in a group entry. [00117] Fig. 7 is a flow diagram of a process implemented by a switch for performing connection group output actions, according to some embodiments. In one embodiment, the operations of the flow diagram may be implemented by a network device functioning as a switch 120 in an SDN network 100, where the switch 120 has established a plurality of connections with an SDN controller 110 in the SDN network 100.
[00118] In one embodiment, the process is initiated when the switch 120 establishes a connection with an SDN controller 110. In one embodiment, after a connection is established between the switch 120 and the SDN controller 110, the switch 120 receives a request from the SDN controller 110 to identify features supported by the switch 120 (block 705). In one embodiment, the request is in the form of the
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST structure described above, or similar structure. The switch 120 then transmits a response to the SDN controller 110 that identifies the features supported by the switch 120 (block 710). In one embodiment, the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure. The VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field). In one embodiment, if the switch 120 supports connection group output action features, then the switch 120 includes an indication in the response transmitted to the SDN controller 110 that the switch 120 supports connection group output action features.
[00119] The switch 120 generates an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller 110 using a connection to be selected from a first connection group, where the first connection group includes one or more
connections from the plurality of connections established with the SDN controller 110
(block 715). In one embodiment, the entry is a flow entry 130 (e.g., OpenFlow flow entry). In another embodiment, the entry is a group entry (e.g., OpenFlow group entry). In one embodiment, the entry is generated in response to receiving an instruction from an SDN controller 110 to generate the entry. In one embodiment, the first connection group is specified in the entry using a connection group identifier assigned to the first connection group. In one embodiment, the instruction received from the SDN controller 110 to generate the entry (e.g., an OFPT_FLOW_MOD message) includes a Connection Group Output Action structure described above, or similar structure.
[00120] When the switch 120 receives a packet for forwarding (block 720), it determines whether the packet is to be processed according to the entry (decision block 725). In one embodiment, the switch 120 determines that the packet is to be processed according to the entry based on determining that the packet matches the packet matching criteria of the entry (e.g., when the entry is an OpenFlow flow entry). If the packet is not to be processed according to the entry, then the switch 120 may continue packet processing, as necessary (block 730). On the other hand, if the packet is to be processed according to the entry, then the switch 120 selects an active connection from the first connection group (e.g., according to the instruction in the entry) (block 735) and transmits the packet to the SDN controller 110 using the active connection selected from the first connection group (block 740). The switch 120 may then repeat blocks 720-740 for other packets that it receives.
[00121] In one embodiment, the switch 120 marks a connection from the first connection group as being inactive in response to a determination that the connection has been lost. When selecting an active connection from a connection group, the switch 120 does not select a connection that is marked as being inactive. In one embodiment, the determination that the connection has been lost is based on a determination that a TCP connection associated with the connection has been terminated (e.g., which can be detected by an underlying operating system of the switch 120). In one embodiment, the determination that the connection has been lost is based on detecting a loss of heartbeat message from the SDN controller 110 over the connection.
[00122] In one embodiment, a second connection group (that includes one or more connection from the plurality of connections established with the SDN controller 110) is provisioned as a fallback connection group for the first connection group. In one embodiment, if the switch 120 determines that the packet is to be processed according to the entry but that all of the one or more connections in the first connection group are marked as being inactive, then the switch 120 selects an active connection from the second connection group and transmits the packet to the SDN controller 110 using the active connection selected from the second connection group.
[00123] In one embodiment, the switch 120 maintains a database (or other type of storage) that stores information regarding the configuration of connection groups. For example, the database may store an indication of the one or more connections included in a particular controller group (e.g., the first connection group and the second connection group). In one embodiment, the database may store an indication that a particular connection group is a fallback controller group for another connection group (e.g., the second connection group is a fallback connection group for the first connection group). In one embodiment, the database is an OVSDB and is managed using an OVSDB protocol.
[00124] Fig. 8 is a flow diagram of a process implemented by a controller for programming a switch to perform connection group output actions, according to some embodiments. In one embodiment, the operations of the flow diagram may be implemented by a network device functioning as an SDN controller 110 in an SDN network 100, where the controller has established a plurality of connections with a switch 120 in the SDN network 100. [00125] In one embodiment, the process is initiated when the switch 120 establishes a connection with the SDN controller 110. In one embodiment, after a connection is established between the switch 120 and the SDN controller 110, the SDN controller 110 transmits a request to the switch 120 to identify features supported by the switch 120 (block 805). In one embodiment, the request is in the form of the
VENDOR_SPECIFIC_SWrrCH_FEATURES_REQUEST structure described above, or similar structure. The SDN controller 110 then receives a response from the switch 120 that identifies the features supported by the switch 120 (block 810). In one embodiment, the response is in the form of the VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure described above, or similar structure. The VENDOR_SPECIFIC_SWITCH_FEATURES_REPLY structure may include a field for identifying the features/capabilities supported by the switch 120 (e.g., exp_capabilities field). In one embodiment, if the switch 120 supports connection group output action features, then the response received from the switch 120 includes an indication that the switch 120 supports connection group output action features.
[00126] The SDN controller 110 then determines whether the switch 120 supports connection group output action features (e.g., based on the response from the switch 120 that identifies the features supported by the switch 120) (decision block 815). If the switch 120 does not support connection group output action features, then the SDN controller 110 proceeds with normal processing (e.g., without connection group output action features) (block 820).
[00127] On the other hand, if the switch 120 supports connection group output action features, then the SDN controller 110 transmits an instruction to the switch 120 to generate an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller 110 using a connection to be selected from a first connection group, where the first connection group includes one or more connections from the plurality of connections established between the SDN controller 110 and the switch 120 (block 825). In one embodiment, the entry is a flow entry 130 (e.g., OpenFlow flow entry). In another embodiment, the entry is a group entry (e.g., OpenFlow group entry). In one embodiment, the first connection group is specified using a connection group identifier assigned to the first connection group. In one embodiment, the instruction transmitted to the switch 120 to generate the entry (e.g., an OFPT_FLOW_MOD message) includes a Connection Group Output Action structure described above, or similar structure.
[00128] Fig. 9A illustrates connectivity between network devices (NDs) within an exemplary network, as well as three exemplary implementations of the NDs, according to some
embodiments of the invention. Fig. 9A shows NDs 900A-H, and their connectivity by way of lines between 900A-900B, 900B-900C, 900C-900D, 900D-900E, 900E-900F, 900F-900G, and 900A-900G, as well as between 900H and each of 900A, 900C, 900D, and 900G. These NDs are physical devices, and the connectivity between these NDs can be wireless or wired (often referred to as a link). An additional line extending from NDs 900A, 900E, and 900F illustrates that these NDs act as ingress and egress points for the network (and thus, these NDs are sometimes referred to as edge NDs; while the other NDs may be called core NDs).
[00129] Two of the exemplary ND implementations in Fig. 9A are: 1) a special-purpose network device 902 that uses custom application-specific integrated-circuits (ASICs) and a special-purpose operating system (OS); and 2) a general purpose network device 904 that uses common off-the-shelf (COTS) processors and a standard OS.
[00130] The special-purpose network device 902 includes networking hardware 910 comprising compute resource(s) 912 (which typically include a set of one or more processors), forwarding resource(s) 914 (which typically include one or more ASICs and/or network processors), and physical network interfaces (NIs) 916 (sometimes called physical ports), as well as non-transitory machine readable storage media 918 having stored therein networking software 920. A physical NI is hardware in a ND through which a network connection (e.g., wirelessly through a wireless network interface controller (WNIC) or through plugging in a cable to a physical port connected to a network interface controller (NIC)) is made, such as those shown by the connectivity between NDs 900A-H. During operation, the networking
software 920 may be executed by the networking hardware 910 to instantiate a set of one or more networking software instance(s) 922. Each of the networking software instance(s) 922, and that part of the networking hardware 910 that executes that network software instance (be it hardware dedicated to that networking software instance and/or time slices of hardware temporally shared by that networking software instance with others of the networking software instance(s) 922), form a separate virtual network element 930A-R. Each of the virtual network element(s) (VNEs) 930A-R includes a control communication and configuration module 932A- R (sometimes referred to as a local control module or control communication module) and forwarding table(s) 934A-R, such that a given virtual network element (e.g., 930A) includes the control communication and configuration module (e.g., 932A), a set of one or more forwarding table(s) (e.g., 934A), and that portion of the networking hardware 910 that executes the virtual network element (e.g., 930A).
[00131] Software 920 can include code such as controller/connection group output action module 925, which when executed by networking hardware 910, causes the special-purpose network device 902 to perform operations of one or more embodiments of the present invention as part networking software instances 922. [00132] The special-purpose network device 902 is often physically and/or logically considered to include: 1) a ND control plane 924 (sometimes referred to as a control plane) comprising the compute resource(s) 912 that execute the control communication and
configuration module(s) 932A-R; and 2) a ND forwarding plane 926 (sometimes referred to as a forwarding plane, a data plane, or a media plane) comprising the forwarding resource(s) 914 that utilize the forwarding table(s) 934A-R and the physical NIs 916. By way of example, where the ND is a router (or is implementing routing functionality), the ND control plane 924 (the compute resource(s) 912 executing the control communication and configuration
module(s) 932A-R) is typically responsible for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) and storing that routing information in the forwarding table(s) 934A-R, and the ND forwarding plane 926 is responsible for receiving that data on the physical NIs 916 and forwarding that data out the appropriate ones of the physical NIs 916 based on the forwarding table(s) 934A-R.
[00133] Fig. 9B illustrates an exemplary way to implement the special-purpose network device 902 according to some embodiments of the invention. Fig. 9B shows a special-purpose network device including cards 938 (typically hot pluggable). While in some embodiments the cards 938 are of two types (one or more that operate as the ND forwarding plane 926
(sometimes called line cards), and one or more that operate to implement the ND control plane 924 (sometimes called control cards)), alternative embodiments may combine
functionality onto a single card and/or include additional card types (e.g., one additional type of card is called a service card, resource card, or multi-application card). A service card can provide specialized processing (e.g., Layer 4 to Layer 7 services (e.g., firewall, Internet Protocol Security (IPsec), Secure Sockets Layer (SSL) / Transport Layer Security (TLS), Intrusion Detection System (IDS), peer-to-peer (P2P), Voice over IP (VoIP) Session Border Controller, Mobile Wireless Gateways (Gateway General Packet Radio Service (GPRS) Support Node (GGSN), Evolved Packet Core (EPC) Gateway)). By way of example, a service card may be used to terminate IPsec tunnels and execute the attendant authentication and encryption algorithms. These cards are coupled together through one or more interconnect mechanisms illustrated as backplane 936 (e.g., a first full mesh coupling the line cards and a second full mesh coupling all of the cards).
[00134] Returning to Fig. 9A, the general purpose network device 904 includes hardware 940 comprising a set of one or more processor(s) 942 (which are often COTS processors) and network interface controller(s) 944 (NICs; also known as network interface cards) (which include physical NIs 946), as well as non-transitory machine readable storage media 948 having stored therein software 950. During operation, the processor(s) 942 execute the software 950 to instantiate one or more sets of one or more applications 964A-R. While one embodiment does not implement virtualization, alternative embodiments may use different forms of virtualization. For example, in one such alternative embodiment the virtualization layer 954 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 962A-R called software containers that may each be used to execute one (or more) of the sets of applications 964A-R; where the multiple software containers (also called virtualization engines, virtual private servers, or jails) are user spaces (typically a virtual memory space) that are separate from each other and separate from the kernel space in which the operating system is run; and where the set of applications running in a given user space, unless explicitly allowed, cannot access the memory of the other processes. In another such alternative embodiment the virtualization layer 954 represents a hypervisor (sometimes referred to as a virtual machine monitor (VMM)) or a hypervisor executing on top of a host operating system, and each of the sets of applications 964A-R is run on top of a guest operating system within an instance 962A-R called a virtual machine (which may in some cases be considered a tightly isolated form of software container) that is run on top of the hypervisor - the guest operating system and application may not know they are running on a virtual machine as opposed to running on a "bare metal" host electronic device, or through para- virtualization the operating system and/or application may be aware of the presence of virtualization for optimization purposes. In yet other alternative embodiments, one, some or all of the
applications are implemented as unikernel(s), which can be generated by compiling directly with an application only a limited set of libraries (e.g., from a library operating system (LibOS) including drivers/libraries of OS services) that provide the particular OS services needed by the application. As a unikernel can be implemented to run directly on hardware 940, directly on a hypervisor (in which case the unikernel is sometimes described as running within a LibOS virtual machine), or in a software container, embodiments can be implemented fully with unikernels running directly on a hypervisor represented by virtualization layer 954, unikernels running within software containers represented by instances 962A-R, or as a combination of unikernels and the above-described techniques (e.g., unikernels and virtual machines both run directly on a hypervisor, unikernels and sets of applications that are run in different software containers).
[00135] The instantiation of the one or more sets of one or more applications 964A-R, as well as virtualization if implemented, are collectively referred to as software instance(s) 952. Each set of applications 964 A-R, corresponding virtualization construct (e.g., instance 962A-R) if implemented, and that part of the hardware 940 that executes them (be it hardware dedicated to that execution and/or time slices of hardware temporally shared), forms a separate virtual network element(s) 960A-R.
[00136] The virtual network element(s) 960A-R perform similar functionality to the virtual network element(s) 930A-R - e.g., similar to the control communication and configuration module(s) 932A and forwarding table(s) 934A (this virtualization of the hardware 940 is sometimes referred to as network function virtualization (NFV)). Thus, NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which could be located in Data centers, NDs, and customer premise equipment (CPE). While embodiments of the invention are illustrated with each instance 962A-R corresponding to one VNE 960A-R, alternative embodiments may implement this correspondence at a finer level granularity (e.g., line card virtual machines virtualize line cards, control card virtual machine virtualize control cards, etc.); it should be understood that the techniques described herein with reference to a correspondence of instances 962A-R to VNEs also apply to embodiments where such a finer level of granularity and/or unikernels are used.
[00137] In certain embodiments, the virtualization layer 954 includes a virtual switch that provides similar forwarding services as a physical Ethernet switch. Specifically, this virtual switch forwards traffic between instances 962A-R and the NIC(s) 944, as well as optionally between the instances 962A-R; in addition, this virtual switch may enforce network isolation between the VNEs 960A-R that by policy are not permitted to communicate with each other (e.g., by honoring virtual local area networks (VLANs)).
[00138] Software 950 can include code such as controller/connection group output action module 963, which when executed by processor(s) 942, cause the general purpose network device 904 to perform operations of one or more embodiments of the present invention as part software instances 962A-R.
[00139] The third exemplary ND implementation in Fig. 9A is a hybrid network device 906, which includes both custom ASICs/special-purpose OS and COTS processors/standard OS in a single ND or a single card within an ND. In certain embodiments of such a hybrid network device, a platform VM (e.g., a VM that that implements the functionality of the special-purpose network device 902) could provide for para-virtualization to the networking hardware present in the hybrid network device 906.
[00140] Regardless of the above exemplary implementations of an ND, when a single one of multiple VNEs implemented by an ND is being considered (e.g., only one of the VNEs is part of a given virtual network) or where only a single VNE is currently being implemented by an ND, the shortened term network element (NE) is sometimes used to refer to that VNE. Also in all of the above exemplary implementations, each of the VNEs (e.g., VNE(s) 930A-R, VNEs 960A-R, and those in the hybrid network device 906) receives data on the physical NIs (e.g., 916, 946) and forwards that data out the appropriate ones of the physical NIs (e.g., 916, 946). For example, a VNE implementing IP router functionality forwards IP packets on the basis of some of the IP header information in the IP packet; where IP header information includes source IP address, destination IP address, source port, destination port (where "source port" and
"destination port" refer herein to protocol ports, as opposed to physical ports of a ND), transport protocol (e.g., user datagram protocol (UDP), Transmission Control Protocol (TCP), and differentiated services code point (DSCP) values.
[00141] Fig. 9C illustrates various exemplary ways in which VNEs may be coupled according to some embodiments of the invention. Fig. 9C shows VNEs 970A.1-970A.P (and optionally VNEs 970A.Q-970A.R) implemented in ND 900A and VNE 970H.1 in ND 900H. In Fig. 9C, VNEs 970A.1-P are separate from each other in the sense that they can receive packets from outside ND 900A and forward packets outside of ND 900A; VNE 970A.1 is coupled with VNE 970H.1, and thus they communicate packets between their respective NDs; VNE 970A.2- 970A.3 may optionally forward packets between themselves without forwarding them outside of the ND 900A; and VNE 970A.P may optionally be the first in a chain of VNEs that includes VNE 970A.Q followed by VNE 970A.R (this is sometimes referred to as dynamic service chaining, where each of the VNEs in the series of VNEs provides a different service - e.g., one or more layer 4-7 network services). While Fig. 9C illustrates various exemplary relationships between the VNEs, alternative embodiments may support other relationships (e.g., more/fewer VNEs, more/fewer dynamic service chains, multiple different dynamic service chains with some common VNEs and some different VNEs).
[00142] The NDs of Fig. 9A, for example, may form part of the Internet or a private network; and other electronic devices (not shown; such as end user devices including workstations, laptops, netbooks, tablets, palm tops, mobile phones, smartphones, phablets, multimedia phones, Voice Over Internet Protocol (VOIP) phones, terminals, portable media players, GPS units, wearable devices, gaming systems, set-top boxes, Internet enabled household appliances) may be coupled to the network (directly or through other networks such as access networks) to communicate over the network (e.g., the Internet or virtual private networks (VPNs) overlaid on (e.g., tunneled through) the Internet) with each other (directly or through servers) and/or access content and/or services. Such content and/or services are typically provided by one or more servers (not shown) belonging to a service/content provider or one or more end user devices (not shown) participating in a peer-to-peer (P2P) service, and may include, for example, public webpages (e.g., free content, store fronts, search services), private webpages (e.g., username/password accessed webpages providing email services), and/or corporate networks over VPNs. For instance, end user devices may be coupled (e.g., through customer premise equipment coupled to an access network (wired or wirelessly)) to edge NDs, which are coupled (e.g., through one or more core NDs) to other edge NDs, which are coupled to electronic devices acting as servers. However, through compute and storage virtualization, one or more of the electronic devices operating as the NDs in Fig. 9A may also host one or more such servers (e.g., in the case of the general purpose network device 904, one or more of the software
instances 962A-R may operate as servers; the same would be true for the hybrid network device 906; in the case of the special-purpose network device 902, one or more such servers could also be run on a virtualization layer executed by the compute resource(s) 912); in which case the servers are said to be co-located with the VNEs of that ND.
[00143] A virtual network is a logical abstraction of a physical network (such as that in Fig. 9A) that provides network services (e.g., L2 and/or L3 services). A virtual network can be implemented as an overlay network (sometimes referred to as a network virtualization overlay) that provides network services (e.g., layer 2 (L2, data link layer) and/or layer 3 (L3, network layer) services) over an underlay network (e.g., an L3 network, such as an Internet Protocol (IP) network that uses tunnels (e.g., generic routing encapsulation (GRE), layer 2 tunneling protocol (L2TP), IPSec) to create the overlay network).
[00144] A network virtualization edge (NVE) sits at the edge of the underlay network and participates in implementing the network virtualization; the network-facing side of the NVE uses the underlay network to tunnel frames to and from other NVEs; the outward-facing side of the NVE sends and receives data to and from systems outside the network. A virtual network instance (VNI) is a specific instance of a virtual network on a NVE (e.g., a NE/VNE on an ND, a part of a NE/VNE on a ND where that NE/VNE is divided into multiple VNEs through emulation); one or more VNIs can be instantiated on an NVE (e.g., as different VNEs on an ND). A virtual access point (VAP) is a logical connection point on the NVE for connecting external systems to a virtual network; a VAP can be physical or virtual ports identified through logical interface identifiers (e.g., a VLAN ID).
[00145] Examples of network services include: 1) an Ethernet LAN emulation service (an Ethernet-based multipoint service similar to an Internet Engineering Task Force (IETF)
Multiprotocol Label Switching (MPLS) or Ethernet VPN (EVPN) service) in which external systems are interconnected across the network by a LAN environment over the underlay network (e.g., an NVE provides separate L2 VNIs (virtual switching instances) for different such virtual networks, and L3 (e.g., IP/MPLS) tunneling encapsulation across the underlay network); and 2) a virtualized IP forwarding service (similar to IETF IP VPN (e.g., Border Gateway Protocol (BGP)/MPLS IP VPN) from a service definition perspective) in which external systems are interconnected across the network by an L3 environment over the underlay network (e.g., an NVE provides separate L3 VNIs (forwarding and routing instances) for different such virtual networks, and L3 (e.g., IP/MPLS) tunneling encapsulation across the underlay network)). Network services may also include quality of service capabilities (e.g., traffic classification marking, traffic conditioning and scheduling), security capabilities (e.g., filters to protect customer premises from network - originated attacks, to avoid malformed route announcements), and management capabilities (e.g., full detection and processing).
[00146] Fig. 9D illustrates a network with a single network element on each of the NDs of Fig. 9A, and within this straight forward approach contrasts a traditional distributed approach (commonly used by traditional routers) with a centralized approach for maintaining reachability and forwarding information (also called network control), according to some embodiments of the invention. Specifically, Fig. 9D illustrates network elements (NEs) 970A-H with the same connectivity as the NDs 900A-H of Fig. 9A.
[00147] Fig. 9D illustrates that the distributed approach 972 distributes responsibility for generating the reachability and forwarding information across the NEs 970A-H; in other words, the process of neighbor discovery and topology discovery is distributed.
[00148] For example, where the special-purpose network device 902 is used, the control communication and configuration module(s) 932A-R of the ND control plane 924 typically include a reachability and forwarding information module to implement one or more routing protocols (e.g., an exterior gateway protocol such as Border Gateway Protocol (BGP), Interior Gateway Protocol(s) (IGP) (e.g., Open Shortest Path First (OSPF), Intermediate System to Intermediate System (IS-IS), Routing Information Protocol (RIP), Label Distribution Protocol (LDP), Resource Reservation Protocol (RSVP) (including RS VP-Traffic Engineering (TE): Extensions to RSVP for LSP Tunnels and Generalized Multi-Protocol Label Switching
(GMPLS) Signaling RSVP-TE)) that communicate with other NEs to exchange routes, and then selects those routes based on one or more routing metrics. Thus, the NEs 970A-H (e.g., the compute resource(s) 912 executing the control communication and configuration
module(s) 932A-R) perform their responsibility for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) by distributively determining the reachability within the network and calculating their respective forwarding information. Routes and adjacencies are stored in one or more routing structures (e.g., Routing Information Base (RIB), Label Information Base (LIB), one or more adjacency structures) on the ND control plane 924. The ND control plane 924 programs the ND forwarding plane 926 with information (e.g., adjacency and route information) based on the routing structure(s). For example, the ND control plane 924 programs the adjacency and route information into one or more forwarding table(s) 934A-R (e.g., Forwarding Information Base (FIB), Label Forwarding Information Base (LFIB), and one or more adjacency structures) on the ND forwarding plane 926. For layer 2 forwarding, the ND can store one or more bridging tables that are used to forward data based on the layer 2 information in that data. While the above example uses the special-purpose network device 902, the same distributed approach 972 can be implemented on the general purpose network device 904 and the hybrid network device 906.
[00149] Fig. 9D illustrates that a centralized approach 974 (also known as software defined networking (SDN)) that decouples the system that makes decisions about where traffic is sent from the underlying systems that forwards traffic to the selected destination. The illustrated centralized approach 974 has the responsibility for the generation of reachability and forwarding information in a centralized control plane 976 (sometimes referred to as a SDN control module, controller, network controller, OpenFlow controller, SDN controller, control plane node, network virtualization authority, or management control entity), and thus the process of neighbor discovery and topology discovery is centralized. The centralized control plane 976 has a south bound interface 982 with a data plane 980 (sometime referred to the infrastructure layer, network forwarding plane, or forwarding plane (which should not be confused with a ND forwarding plane)) that includes the NEs 970A-H (sometimes referred to as switches, forwarding elements, data plane elements, or nodes). The centralized control plane 976 includes a network controller 978, which includes a centralized reachability and forwarding information module 979 that determines the reachability within the network and distributes the forwarding information to the NEs 970A-H of the data plane 980 over the south bound interface 982 (which may use the OpenFlow protocol). Thus, the network intelligence is centralized in the centralized control plane 976 executing on electronic devices that are typically separate from the NDs. In one embodiment, the network controller 978 may include a controller/connection group output action module 981 that when executed by the network controller 978, causes the network controller 978 to perform operations of one or more embodiments described herein above.
[00150] For example, where the special-purpose network device 902 is used in the data plane 980, each of the control communication and configuration module(s) 932A-R of the ND control plane 924 typically include a control agent that provides the VNE side of the south bound interface 982. In this case, the ND control plane 924 (the compute resource(s) 912 executing the control communication and configuration module(s) 932A-R) performs its responsibility for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) through the control agent communicating with the centralized control plane 976 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 979 (it should be understood that in some embodiments of the invention, the control communication and configuration module(s) 932A-R, in addition to communicating with the centralized control plane 976, may also play some role in determining reachability and/or calculating forwarding information - albeit less so than in the case of a distributed approach; such embodiments are generally considered to fall under the centralized approach 974, but may also be considered a hybrid approach).
[00151] While the above example uses the special-purpose network device 902, the same centralized approach 974 can be implemented with the general purpose network device 904 (e.g., each of the VNE 960A-R performs its responsibility for controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) by communicating with the centralized control plane 976 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 979; it should be understood that in some embodiments of the invention, the VNEs 960A-R, in addition to communicating with the centralized control plane 976, may also play some role in determining reachability and/or calculating forwarding information - albeit less so than in the case of a distributed approach) and the hybrid network device 906. In fact, the use of SDN techniques can enhance the NFV techniques typically used in the general purpose network device 904 or hybrid network device 906 implementations as NFV is able to support SDN by providing an infrastructure upon which the SDN software can be run, and NFV and SDN both aim to make use of commodity server hardware and physical switches.
[00152] Fig. 9D also shows that the centralized control plane 976 has a north bound interface 984 to an application layer 986, in which resides application(s) 988. The centralized control plane 976 has the ability to form virtual networks 992 (sometimes referred to as a logical forwarding plane, network services, or overlay networks (with the NEs 970A-H of the data plane 980 being the underlay network)) for the application(s) 988. Thus, the centralized control plane 976 maintains a global view of all NDs and configured NEs/VNEs, and it maps the virtual networks to the underlying NDs efficiently (including maintaining these mappings as the physical network changes either through hardware (ND, link, or ND component) failure, addition, or removal).
[00153] While Fig. 9D shows the distributed approach 972 separate from the centralized approach 974, the effort of network control may be distributed differently or the two combined in certain embodiments of the invention. For example: 1) embodiments may generally use the centralized approach (SDN) 974, but have certain functions delegated to the NEs (e.g., the distributed approach may be used to implement one or more of fault monitoring, performance monitoring, protection switching, and primitives for neighbor and/or topology discovery); or 2) embodiments of the invention may perform neighbor discovery and topology discovery via both the centralized control plane and the distributed protocols, and the results compared to raise exceptions where they do not agree. Such embodiments are generally considered to fall under the centralized approach 974, but may also be considered a hybrid approach.
[00154] While Fig. 9D illustrates the simple case where each of the NDs 900A-H implements a single NE 970A-H, it should be understood that the network control approaches described with reference to Fig. 9D also work for networks where one or more of the NDs 900A-H implement multiple VNEs (e.g., VNEs 930A-R, VNEs 960A-R, those in the hybrid network device 906). Alternatively or in addition, the network controller 978 may also emulate the implementation of multiple VNEs in a single ND. Specifically, instead of (or in addition to) implementing multiple VNEs in a single ND, the network controller 978 may present the implementation of a VNE/NE in a single ND as multiple VNEs in the virtual networks 992 (all in the same one of the virtual network(s) 992, each in different ones of the virtual network(s) 992, or some combination). For example, the network controller 978 may cause an ND to implement a single VNE (a NE) in the underlay network, and then logically divide up the resources of that NE within the centralized control plane 976 to present different VNEs in the virtual network(s) 992 (where these different VNEs in the overlay networks are sharing the resources of the single VNE/NE implementation on the ND in the underlay network).
[00155] On the other hand, Figs. 9E and 9F respectively illustrate exemplary abstractions of NEs and VNEs that the network controller 978 may present as part of different ones of the virtual networks 992. Fig. 9E illustrates the simple case of where each of the NDs 900A-H implements a single NE 970A-H (see Fig. 9D), but the centralized control plane 976 has abstracted multiple of the NEs in different NDs (the NEs 970A-C and G-H) into (to represent) a single NE 9701 in one of the virtual network(s) 992 of Fig. 9D, according to some embodiments of the invention. Fig. 9E shows that in this virtual network, the NE 9701 is coupled to NE 970D and 970F, which are both still coupled to NE 970E.
[00156] Fig. 9F illustrates a case where multiple VNEs (VNE 970A.1 and VNE 970H.1) are implemented on different NDs (ND 900 A and ND 900H) and are coupled to each other, and where the centralized control plane 976 has abstracted these multiple VNEs such that they appear as a single VNE 970T within one of the virtual networks 992 of Fig. 9D, according to some embodiments of the invention. Thus, the abstraction of a NE or VNE can span
multiple NDs. [00157] While some embodiments of the invention implement the centralized control plane 976 as a single entity (e.g., a single instance of software running on a single electronic device), alternative embodiments may spread the functionality across multiple entities for redundancy and/or scalability purposes (e.g., multiple instances of software running on different electronic devices).
[00158] Similar to the network device implementations, the electronic device(s) running the centralized control plane 976, and thus the network controller 978 including the centralized reachability and forwarding information module 979, may be implemented a variety of ways (e.g., a special purpose device, a general-purpose (e.g., COTS) device, or hybrid device). These electronic device(s) would similarly include compute resource(s), a set or one or more physical NICs, and a non-transitory machine-readable storage medium having stored thereon the centralized control plane software. For instance, Fig. 10 illustrates, a general purpose control plane device 1004 including hardware 1040 comprising a set of one or more processor(s) 1042 (which are often COTS processors) and network interface controller(s) 1044 (NICs; also known as network interface cards) (which include physical NIs 1046), as well as non-transitory machine readable storage media 1048 having stored therein centralized control plane (CCP) software 1050 and a controller/connection group output action module 1081.
[00159] In embodiments that use compute virtualization, the processor(s) 1042 typically execute software to instantiate a virtualization layer 1054 (e.g., in one embodiment the virtualization layer 1054 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 1062A-R called software containers (representing separate user spaces and also called virtualization engines, virtual private servers, or jails) that may each be used to execute a set of one or more
applications; in another embodiment the virtualization layer 1054 represents a hypervisor (sometimes referred to as a virtual machine monitor (VMM)) or a hypervisor executing on top of a host operating system, and an application is run on top of a guest operating system within an instance 1062A-R called a virtual machine (which in some cases may be considered a tightly isolated form of software container) that is run by the hypervisor ; in another embodiment, an application is implemented as a unikernel, which can be generated by compiling directly with an application only a limited set of libraries (e.g., from a library operating system (LibOS) including drivers/libraries of OS services) that provide the particular OS services needed by the application, and the unikernel can run directly on hardware 1040, directly on a hypervisor represented by virtualization layer 1054 (in which case the unikernel is sometimes described as running within a LibOS virtual machine), or in a software container represented by one of instances 1062A-R). Again, in embodiments where compute virtualization is used, during operation an instance of the CCP software 1050 (illustrated as CCP instance 1076A) is executed (e.g., within the instance 1062A) on the virtualization layer 1054. In embodiments where compute virtualization is not used, the CCP instance 1076A is executed, as a unikernel or on top of a host operating system, on the "bare metal" general purpose control plane device 1004. The instantiation of the CCP instance 1076A, as well as the virtualization layer 1054 and
instances 1062A-R if implemented, are collectively referred to as software instance(s) 1052.
[00160] In some embodiments, the CCP instance 1076A includes a network controller instance 1078. The network controller instance 1078 includes a centralized reachability and forwarding information module instance 1079 (which is a middleware layer providing the context of the network controller 978 to the operating system and communicating with the various NEs), and an CCP application layer 1080 (sometimes referred to as an application layer) over the middleware layer (providing the intelligence required for various network operations such as protocols, network situational awareness, and user - interfaces). At a more abstract level, this CCP application layer 1080 within the centralized control plane 976 works with virtual network view(s) (logical view(s) of the network) and the middleware layer provides the conversion from the virtual networks to the physical view.
[00161] The controller/connection group output action module 1081 can be executed by hardware 1040 to perform operations of one or more embodiments of the present invention as part of software instances 1052.
[00162] The centralized control plane 976 transmits relevant messages to the data plane 980 based on CCP application layer 1080 calculations and middleware layer mapping for each flow. A flow may be defined as a set of packets whose headers match a given pattern of bits; in this sense, traditional IP forwarding is also flow-based forwarding where the flows are defined by the destination IP address for example; however, in other implementations, the given pattern of bits used for a flow definition may include more fields (e.g., 10 or more) in the packet headers. Different NDs/NEs/VNEs of the data plane 980 may receive different messages, and thus different forwarding information. The data plane 980 processes these messages and programs the appropriate flow information and corresponding actions in the forwarding tables (sometime referred to as flow tables) of the appropriate NE/VNEs, and then the NEs/VNEs map incoming packets to flows represented in the forwarding tables and forward packets based on the matches in the forwarding tables.
[00163] Standards such as OpenFlow define the protocols used for the messages, as well as a model for processing the packets. The model for processing packets includes header parsing, packet classification, and making forwarding decisions. Header parsing describes how to interpret a packet based upon a well-known set of protocols. Some protocol fields are used to build a match structure (or key) that will be used in packet classification (e.g., a first key field could be a source media access control (MAC) address, and a second key field could be a destination MAC address).
[00164] Packet classification involves executing a lookup in memory to classify the packet by determining which entry (also referred to as a forwarding table entry or flow entry) in the forwarding tables best matches the packet based upon the match structure, or key, of the forwarding table entries. It is possible that many flows represented in the forwarding table entries can correspond/match to a packet; in this case the system is typically configured to determine one forwarding table entry from the many according to a defined scheme (e.g., selecting a first forwarding table entry that is matched). Forwarding table entries include both a specific set of match criteria (a set of values or wildcards, or an indication of what portions of a packet should be compared to a particular value/values/wildcards, as defined by the matching capabilities - for specific fields in the packet header, or for some other packet content), and a set of one or more actions for the data plane to take on receiving a matching packet. For example, an action may be to push a header onto the packet, for the packet using a particular port, flood the packet, or simply drop the packet. Thus, a forwarding table entry for IPv4/IPv6 packets with a particular transmission control protocol (TCP) destination port could contain an action specifying that these packets should be dropped.
[00165] Making forwarding decisions and performing actions occurs, based upon the forwarding table entry identified during packet classification, by executing the set of actions identified in the matched forwarding table entry on the packet.
[00166] However, when an unknown packet (for example, a "missed packet" or a "match- miss" as used in OpenFlow parlance) arrives at the data plane 980, the packet (or a subset of the packet header and content) is typically forwarded to the centralized control plane 976. The centralized control plane 976 will then program forwarding table entries into the data plane 980 to accommodate packets belonging to the flow of the unknown packet. Once a specific forwarding table entry has been programmed into the data plane 980 by the centralized control plane 976, the next packet with matching credentials will match that forwarding table entry and take the set of actions associated with that matched entry.
[00167] A network interface (NI) may be physical or virtual; and in the context of IP, an interface address is an IP address assigned to a NI, be it a physical NI or virtual NI. A virtual NI may be associated with a physical NI, with another virtual interface, or stand on its own (e.g., a loopback interface, a point-to-point protocol interface). A NI (physical or virtual) may be numbered (a NI with an IP address) or unnumbered (a NI without an IP address). A loopback interface (and its loopback address) is a specific type of virtual NI (and IP address) of a NE/VNE (physical or virtual) often used for management purposes; where such an IP address is referred to as the nodal loopback address. The IP address(es) assigned to the NI(s) of a ND are referred to as IP addresses of that ND; at a more granular level, the IP address(es) assigned to NI(s) assigned to a NE/VNE implemented on a ND can be referred to as IP addresses of that NE/VNE.
[00168] Some portions of the preceding detailed descriptions have been presented in terms of algorithms and symbolic representations of transactions on data bits within a computer memory. These algorithmic descriptions and representations are the ways used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of transactions leading to a desired result. The transactions are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.
[00169] 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 above discussion, it is appreciated that throughout the description, discussions utilizing terms such as "processing" or "computing" or "calculating" or "determining" or "displaying" 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 into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.
[00170] The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method transactions. The required structure for a variety of these systems will appear from the description above. In addition, embodiments of the present invention are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of embodiments of the invention as described herein.
[00171] An embodiment of the invention may be an article of manufacture in which a non- transitory machine-readable medium (such as microelectronic memory) has stored thereon instructions which program one or more data processing components (generically referred to here as a "processor") to perform the operations described above. In other embodiments, some of these operations might be performed by specific hardware components that contain hardwired logic (e.g., dedicated digital filter blocks and state machines). Those operations might alternatively be performed by any combination of programmed data processing components and fixed hardwired circuit components.
[00172] In the foregoing specification, embodiments of the invention have been described with reference to specific exemplary embodiments thereof. It will be evident that various modifications may be made thereto without departing from the broader spirit and scope of the invention as set forth in the following claims. The specification and drawings are, accordingly, to be regarded in an illustrative sense rather than a restrictive sense.
[00173] Throughout the description, embodiments of the present invention have been presented through flow diagrams. It will be appreciated that the order of transactions and transactions described in these flow diagrams are only intended for illustrative purposes and not intended as a limitation of the present invention. One having ordinary skill in the art would recognize that variations can be made to the flow diagrams without departing from the broader spirit and scope of the invention as set forth in the following claims.

Claims

CLAIMS What is claimed is:
1. A method implemented by a network device functioning as a switch (120) in a Software Defined Networking (SDN) network (100) to provide controller group output actions, where the switch is communicatively coupled to a plurality of SDN controllers (110) in the SDN network, the method comprising:
generating (315) an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, wherein the first controller group includes one or more SDN controllers from the plurality of SDN controllers;
receiving (320) a packet for forwarding;
determining (325) whether the packet is to be processed according to the entry;
selecting (335) an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry; and transmitting (340) the packet to the active SDN controller selected from the first
controller group.
2. The method of claim 1, further comprising:
marking an SDN controller from the first controller group as being inactive in response to a determination that a connection to the SDN controller has been lost.
3. The method of claim 2, wherein the determination that the connection to the SDN controller has been lost is based on a determination that a Transmission Control Protocol (TCP) connection to the SDN controller has been terminated.
4. The method of claim 2, wherein the determination that the connection to the SDN controller has been lost is based on detecting a loss of heartbeat message from the SDN controller.
5. The method of claim 2, wherein the determination that the connection to the SDN controller has been lost is based on detecting a link failure using Bidirectional Forwarding Detection (BFD) protocol.
6. The method of claim 1, further comprising:
storing an indication of the one or more SDN controllers included in the first controller group.
7. The method of claim 1, further comprising:
selecting an active SDN controller from a second controller group that is provisioned as a fallback controller group for the first controller group in response to a determination that the packet is to be processed according to the entry and that all of the one or more SDN controllers in the first controller group are marked as being inactive, wherein the second controller group includes one or more SDN controllers from the plurality of SDN controllers; and
transmitting the packet to the active SDN controller selected from the second controller group.
8. The method of claim 7, further comprising:
storing an indication that the second controller group is a fallback controller group for the first controller group; and
storing an indication of one or more SDN controllers included in the second controller group.
9. A method implemented by a network device functioning as a switch (120) in a Software Defined Networking (SDN) network (100) to provide connection group output actions, where the switch has established a plurality of connections with an SDN controller (110) in the SDN network, the method comprising:
generating (715) an entry that includes an instruction to transmit packets processed
according to the entry to the SDN controller using a connection to be selected from a first connection group, wherein the first connection group includes one or more connections from the plurality of connections established with the SDN controller;
receiving (720) a packet for forwarding;
determining (725) whether the packet is to be processed according to the entry;
selecting (735) an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry; and transmitting (740) the packet to the SDN controller using the active connection selected from the first connection group.
10. The method of claim 9, further comprising:
marking a connection from the first connection group as being inactive in response to a determination that the connection has been lost.
11. The method of claim 10, wherein the determination that the connection has been lost is
based on a determination that a Transmission Control Protocol (TCP) connection associated with the connection has been terminated.
12. The method of claim 10, wherein the determination that the connection has been lost is
based on detecting a loss of heartbeat message from the SDN controller over the connection.
13. The method of claim 9, further comprising:
storing an indication of the one or more connections included in the first connection group.
14. The method of claim 9, further comprising:
selecting an active connection from a second connection group that is provisioned as a fallback connection group for the first connection group in response to a determination that the packet is to be processed according to the entry and that all of the one or more connections in the first connection group are marked as being inactive, wherein the second connection group includes one or more connections from the plurality of connections with the SDN controller; and
transmitting the packet to the SDN controller using the active connection selected from the second connection group.
15. The method of claim 14, further comprising:
storing an indication that the second connection group is a fallback connection group for the first connection group.
16. A network device (904) configured to function as a switch (120) in a Software Defined
Networking (SDN) network (100) to provide controller group output actions, where the switch is to be communicatively coupled to a plurality of SDN controllers (110) in the SDN network, the network device comprising:
a set of one or more processors (942); and a non-transitory machine-readable storage medium (948) having stored therein a controller group output action module (963), which when executed by the set of one or more processors, causes the network device to generate an entry that includes an instruction to transmit packets processed according to the entry to an SDN controller to be selected from a first controller group, wherein the first controller group includes one or more SDN controllers from the plurality of SDN controllers, receive a packet for forwarding, determine whether the packet is to be processed according to the entry, select an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry, and transmit the packet to the active SDN controller selected from the first controller group.
17. The network device of claim 16, wherein the controller group output action module, when executed by the set of one or more processors, further causes the network device to mark an SDN controller from the first controller group as being inactive in response to a
determination that a connection to the SDN controller has been lost.
18. A network device (904) configured to function as a switch (120) in a Software Defined
Networking (SDN) network (100) to provide connection group output actions, where the switch is to establish a plurality of connections with an SDN controller (110) in the SDN network, the network device comprising:
a set of one or more processors (942); and
a non-transitory machine-readable storage medium (948) having stored therein a
connection group output action module (963), which when executed by the set of one or more processors, causes the network device to generate an entry that includes an instruction to transmit packets processed according to the entry to the SDN controller using a connection to be selected from a first connection group, wherein the first connection group includes one or more connections from the plurality of connections established with the SDN controller, receive a packet for forwarding, determine whether the packet is to be processed according to the entry, select an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry, and transmit the packet to the SDN controller using the active connection selected from the first connection group.
19. The network device of claim 18, wherein the connection group output action module, when executed by the set of one or more processors, further causes the network device to mark a connection from the first connection group as being inactive in response to a determination that the connection has been lost.
20. A non-transitory machine-readable medium having computer code stored therein, which when executed by a set of one or more processors of a network device that functions as a switch (120) in a Software Defined Networking (SDN) network (100), causes the switch to perform operations for providing controller group output actions, where the switch is to be communicatively coupled to a plurality of SDN controllers (110) in the SDN network, the operations comprising:
generating (315) an entry that includes an instruction to transmit packets processed
according to the entry to an SDN controller to be selected from a first controller group, wherein the first controller group includes one or more SDN controllers from the plurality of SDN controllers;
receiving (320) a packet for forwarding;
determining (325) whether the packet is to be processed according to the entry;
selecting (335) an active SDN controller from the first controller group in response to a determination that the packet is to be processed according to the entry; and transmitting (340) the packet to the active SDN controller selected from the first
controller group.
21. The non-transitory machine -readable medium of claim 20, wherein the computer code, when executed by the set of one or more processors of the network device, causes the network device to perform further operations comprising:
selecting an active SDN controller from a second controller group that is provisioned as a fallback controller group for the first controller group in response to a determination that the packet is to be processed according to the entry and that all of the one or more SDN controllers in the first controller group are marked as being inactive, wherein the second controller group includes one or more SDN controllers from the plurality of SDN controllers; and
transmitting the packet to the active SDN controller selected from the second controller group.
22. A non-transitory machine-readable medium having computer code stored therein, which when executed by a set of one or more processors of a network device that functions as a switch (120) in a Software Defined Networking (SDN) network (100), causes the switch to perform operations for providing connection group output actions, where the switch is to establish a plurality of connections with an SDN controller (110) in the SDN network, the operations comprising:
generating (715) an entry that includes an instruction to transmit packets processed
according to the entry to the SDN controller using a connection to be selected from a first connection group, wherein the first connection group includes one or more connections from the plurality of connections established with the SDN controller;
receiving (720) a packet for forwarding;
determining (725) whether the packet is to be processed according to the entry;
selecting (735) an active connection from the first connection group in response to a determination that the packet is to be processed according to the entry; and transmitting (740) the packet to the SDN controller using the active connection selected from the first connection group.
23. The non-transitory machine -readable medium of claim 22, wherein the computer code, when executed by the set of one or more processors of the network device, causes the network device to perform further operations comprising:
selecting an active connection from a second connection group that is provisioned as a fallback connection group for the first connection group in response to a determination that the packet is to be processed according to the entry and that all of the one or more connections in the first connection group are marked as being inactive, wherein the second connection group includes one or more connections from the plurality of connections with the SDN controller; and
transmitting the packet to the SDN controller using the active connection selected from the second connection group.
PCT/IB2016/052337 2016-04-25 2016-04-25 Robust method of distributing packet-ins in a software defined networking (sdn) network WO2017187222A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/IB2016/052337 WO2017187222A1 (en) 2016-04-25 2016-04-25 Robust method of distributing packet-ins in a software defined networking (sdn) network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/IB2016/052337 WO2017187222A1 (en) 2016-04-25 2016-04-25 Robust method of distributing packet-ins in a software defined networking (sdn) network

Publications (1)

Publication Number Publication Date
WO2017187222A1 true WO2017187222A1 (en) 2017-11-02

Family

ID=55910301

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2016/052337 WO2017187222A1 (en) 2016-04-25 2016-04-25 Robust method of distributing packet-ins in a software defined networking (sdn) network

Country Status (1)

Country Link
WO (1) WO2017187222A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI677219B (en) * 2018-12-12 2019-11-11 中華電信股份有限公司 Monitoring system based on heterogeneous software defined network

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
MD. FAIZUL BARI ET AL: "Dynamic Controller Provisioning in Software Defined Networks", PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NETWORK AND SERVICE MANAGEMENT (CNSM 2013), 31 January 2013 (2013-01-31), pages 18 - 25, XP055111044, DOI: 10.1109/CNSM.2013.6727805 *
OBADIA MATHIS ET AL: "Failover mechanisms for distributed SDN controllers", 2014 INTERNATIONAL CONFERENCE AND WORKSHOP ON THE NETWORK OF THE FUTURE (NOF), IEEE, vol. Workshop, 3 December 2014 (2014-12-03), pages 1 - 6, XP032783626, DOI: 10.1109/NOF.2014.7119795 *
ONF: "OpenFlow Switch Specification - Version 1.5.1 (Protocol version 0x06)", 26 March 2015 (2015-03-26), XP055317414, Retrieved from the Internet <URL:https://www.opennetworking.org/images/stories/downloads/sdn-resources/onf-specifications/openflow/openflow-switch-v1.5.1.pdf> [retrieved on 20161108] *
YANYU CHEN ET AL: "Towards adaptive elastic distributed Software Defined Networking", 2015 IEEE 34TH INTERNATIONAL PERFORMANCE COMPUTING AND COMMUNICATIONS CONFERENCE (IPCCC), IEEE, 14 December 2015 (2015-12-14), pages 1 - 8, XP032867994, DOI: 10.1109/PCCC.2015.7410280 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI677219B (en) * 2018-12-12 2019-11-11 中華電信股份有限公司 Monitoring system based on heterogeneous software defined network

Similar Documents

Publication Publication Date Title
EP3879759B1 (en) Optimized datapath troubleshooting with trace policy engine
EP3391588B1 (en) Openflow configured horizontally split hybrid sdn nodes
EP3378205B1 (en) Service based intelligent packet-in buffering mechanism for openflow switches by having variable buffer timeouts
US11362945B2 (en) Dynamic lookup optimization for packet classification
US11115328B2 (en) Efficient troubleshooting in openflow switches
US20160315866A1 (en) Service based intelligent packet-in mechanism for openflow switches
US11362925B2 (en) Optimizing service node monitoring in SDN
WO2020012491A1 (en) Mechanism for hitless resynchronization during sdn controller upgrades between incompatible versions
US9313117B2 (en) Alternate method to give operators flexibility to choose LFAs
US11265104B2 (en) Mechanism for inline packet response generation in software defined networks
WO2016005926A1 (en) Prefix distribution-based table performance optimization in sdn
US20170149659A1 (en) Mechanism to improve control channel efficiency by distributing packet-ins in an openflow network
WO2019239189A1 (en) Robust node failure detection mechanism for sdn controller cluster
WO2020212998A1 (en) Network address allocation in a virtual layer 2 domain spanning across multiple container clusters
WO2018042230A1 (en) Configurable selective packet-in mechanism for openflow switches
US20220247679A1 (en) Method and apparatus for layer 2 route calculation in a route reflector network device
US20220311703A1 (en) Controller watch port for robust software defined networking (sdn) system operation
US9787577B2 (en) Method and apparatus for optimal, scale independent failover redundancy infrastructure
WO2017187222A1 (en) Robust method of distributing packet-ins in a software defined networking (sdn) network
US11968082B2 (en) Robust node failure detection mechanism for SDN controller cluster

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16720182

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16720182

Country of ref document: EP

Kind code of ref document: A1