Abstract: Systems and methods of communicating between a plurality of hosts comprising one or more first hosts controlled by a first control plane and one or more second hosts controlled by a second control plane are disclosed herein. Each of the one or more first hosts runs at least one tunneling endpoint of one or more first tunneling endpoints, and each of the one or more second hosts runs at least one tunneling endpoint of one or more second tunneling endpoint. The method includes storing, at each of the one or more first hosts, a global list identifying at least the one or more second tunneling endpoints. The method further includes receiving a packet at one of the one or more first tunneling endpoints. The method further includes replicating, encapsulating, and transmitting the packet to each of the one or more second tunneling endpoints based on the global list.

Abstract: Example methods are provided a network device to perform service insertion in a public cloud environment that includes a first virtual network and a second virtual network. In one example method, in response to receiving a first encapsulated packet from a first virtualized computing instance located in the first virtual network, the network device may generate a decapsulated packet by performing decapsulation to remove, from the first encapsulated packet. The method may also comprise identifying a service path specified by a service insertion rule, and sending the decapsulated packet to the service path to cause the service path to process the decapsulated packet according to one or more services. The method may further comprise: in response to the network device receiving the decapsulated packet processed by the service path, sending the decapsulated packet, or generating and sending a second encapsulated packet, towards a destination address.

Abstract: Example methods and systems are provided a network device to perform tunnel-based service insertion in a public cloud environment. An example method may comprise establishing a tunnel between the network device and a service path. The method may also comprise: in response to receiving a first encapsulated packet, identifying the service path specified by a service insertion rule; generating and sending a second encapsulated packet over the tunnel to cause the service path to process an inner packet according to one or more services. The method may further comprise: in response to receiving, from the service path via the tunnel, a third encapsulated packet that includes the inner packet processed by the service path, sending the inner packet processed by the service path, or a fourth encapsulated packet, towards a destination address of the inner packet.

Abstract: Some embodiments provide a method for a managed forwarding element (MFE). At the MFE, the method receives a first packet from a particular tunnel endpoint. The first packet originates from a particular data compute node associated with multiple tunnel endpoints including the particular tunnel endpoint. Based on the first packet, the method stores an association of the particular tunnel endpoint with the particular data compute node. The method uses the stored association to encapsulate subsequent packets received at the MFE and having the particular data compute node as a destination address with the particular tunnel endpoint as a destination tunnel endpoint.

Abstract: Example methods are provided a first host to perform packet flow monitoring in a software-defined networking (SDN) environment. One example may comprise the first host receiving a request to monitor a packet flow and triggering a telemetry process based on a predetermined event associated with the packet flow. The method may also comprise: in response to the triggered telemetry process and detecting an egress packet associated with the packet flow, generating an encapsulated packet by encapsulating the egress packet with an outer header; configuring a telemetry instruction in the outer header; and sending the encapsulated packet with the telemetry instruction to the second host via one or more intermediate network devices. The telemetry instruction may be configured to cause the one or more intermediate network devices to add, to the encapsulated packet, metadata associated with a network state experienced by the encapsulated packet.

Abstract: A physical host machine of a public cloud system includes a set of processing units for executing instructions stored in non-transitory machine readable media. The physical host machine also includes a physical network interface cars (PNIC) and a non-transitory machine readable medium that stores a data compute node (DCN). The DCN includes first and second applications, first and second logical interfaces, a network stack, and a managed forwarding element (MFE). The first application is connected to the pNIC through the network stack, the first logical interface, and the MFE. The second application is connected to the PNIC through the network stack, the second logical interface, and the MFE.

Abstract: Some embodiments provide a method for a first DCN operating in a first datacenter as a logical network gateway that processes messages between other DCNs of the logical network and external entities, which address the logical network gateway using a first address. The first DCN has an interface with a second address for use in the first datacenter. The method stores a mapping between the second address and a third address. A second DCN operates the logical network gateway in a second datacenter and has an interface with the third address for use in the second datacenter. From the second DCN, the method receives connection state data, describing connections between the external entities and the DCNs of the logical network, that uses the third address. The method replaces the third address with the second address in the connection state data using the stored mapping and stores the connection state data.

Abstract: Some embodiments provide a centralized overlay-network cloud gateway and a set of centralized services in a transit virtual cloud network (VCN) connected to multiple other compute VCNs hosting compute nodes (VMs, containers, etc.) that are part of (belong to) the overlay network. The centralized overlay-network cloud gateway provides connectivity between compute nodes of the overlay network (e.g., a logical network spanning multiple VCNs) and compute nodes in external networks. Some embodiments use the centralized overlay-network cloud gateway to provide transitive routing (e.g., routing through a transit VCN) in the absence of direct peering between source and destination VCNs. The overlay network, of some embodiments, uses the same subnetting and default gateway address for each compute node as the cloud provider network provided by the virtual private cloud provider.

Abstract: Some embodiments provide a centralized overlay-network cloud gateway and a set of centralized services in a transit virtual private cloud (VPC) connected to multiple other compute VPCs hosting compute nodes (VMs, containers, etc.) that are part of (belong to) the overlay network. The centralized overlay-network cloud gateway provides connectivity between compute nodes of the overlay network (e.g., a logical network spanning multiple VPCs) and compute nodes in external networks. Some embodiments use the centralized overlay-network cloud gateway to provide transitive routing (e.g., routing through a transit VPC) in the absence of direct peering between source and destination VPCs. The overlay network, of some embodiments, uses the same subnetting and default gateway address for each compute node as the cloud provider network provided by the virtual private cloud provider.

Abstract: A physical host machine of a public cloud system includes a set of processing units for executing instructions stored in non-transitory machine readable media. The physical host machine also includes a physical network interface cars (PNIC) and a non-transitory machine readable medium that stores a data compute node (DCN). The DCN includes first and second applications, first and second logical interfaces, a network stack, and a managed forwarding element (MFE). The first application is connected to the pNIC through the network stack, the first logical interface, and the MFE. The second application is connected to the PNIC through the network stack, the second logical interface, and the MFE.

Abstract: Some embodiments provide a method for a managed forwarding element (MFE) executing on a data compute node (DCN) that operates on a host computer in a public datacenter. The MFE implements a logical network that connects multiple DCNs within the public datacenter. The method receives a packet, directed to the DCN, that (i) has a first logical network source address and (ii) is encapsulated with a second source address associated with an underlying public datacenter network. The method determines whether the first logical network source address is a valid source address for the packet based on a mapping table that maps logical network addresses to underlying public datacenter network addresses. When the first source address is not a valid source address for the packet, the method drops the packet.

Abstract: The disclosure provides an approach for load balancing packets within a data center. The approach leverages dynamically collected and up-to-date health information on each virtual computing instance located within the data center. In one embodiment, health monitoring modules, located within hypervisors of each host computer, collect health statistics on local virtual computing instances. Each health monitoring module shares its locally collected health statistics with every other health monitoring module. Each health monitoring module provides the shared health statistics, on all virtual computing instances within the data center, to a local load balancing module located within the hypervisor of each host computer. Each load balancing module uses health statistics of all virtual computing instances to load balance packets within the data center.

Abstract: Some embodiments provide a method and system for configuring a plurality of managed forwarding elements (MFEs) in a plurality of cloud-provider virtual networks (CPVNs) to make routing decisions that efficiently use a peered transit CPVN and peering with other CPVNs in the plurality of CPVNs. In some embodiments, a controller set receives an identification of peering relationships between CPVNs in the plurality of CPVNs and generates configuration data for configuring each MFE. The configuration data is used to configure the MFE to forward data messages received at the MFE using a peering between a source CPVN and a destination CPVN when possible and to forward data messages received at the MFE to a transit gateway device in a transit CPVN when it is not possible to use a peering between the source and destination CPVNs.

Abstract: A data compute node executes (i) a set of tenant applications connected to a third party overlay network, (ii) a set of network manager applications, and (iii) a managed forwarding element that includes a pair of overlay and underlay network virtual adapters. A packet that is received from a network manager application and addressed to an underlay network destination is sent to the underlay network destination address through a physical NIC of the host without network address translation or encapsulation. A packet that is received from a tenant application and addressed to an underlay network destination is subject to SNAT and is sent to the underlay network destination address. A packet that is received from a tenant application and is addressed an overlay destination address is encapsulated with the header of the overlay network and is sent to the overlay network destination address through the underlay virtual adapter.

Abstract: Some embodiments provide a method for a network controller that manages a logical network implemented in a datacenter comprising forwarding elements to which the network controller does not have access. The method identifies a data compute node (DCN), that operates on a host machine in the datacenter, to attach to the logical network. The DCN has a network interface with a first network address provided by a management system of the datacenter, and executes (i) a workload application and (ii) a managed forwarding element (MFE). The method distributes configuration data for configuring the MFE to receive data packets sent from the workload application on the DCN and perform network security and forwarding processing on the data packets. The data packets sent by the workload application have a second network address as a source address when received by the MFE and are encapsulated by the MFE using the first network address.

Abstract: Some embodiments provide a method for a public cloud manager that interacts with a management system of a public datacenter. The method receives a notification from a network controller that a second data compute node is compromised. The second data compute node operates on a host machine in the public datacenter and executes a forwarding element managed by network controller. The method interacts with application programming interfaces (APIs) of the public datacenter to quarantine the data compute node.

Abstract: Example methods are provided for a source virtual tunnel endpoint (VTEP) to perform congestion-aware load balancing in a data center network. The method may comprise the source VTEP learning congestion state information associated with multiple paths provided by respective multiple intermediate switches connecting the source VTEP with a destination VTEP. The method may also comprise the source VTEP receiving second packets that are sent by a source endpoint and destined for a destination endpoint; and selecting a particular path from multiple paths based on the congestion state information. The method may further comprise the source VTEP generating encapsulated second packets by encapsulating each of the second packets with header information that includes a set of tuples associated with the particular path; and sending the encapsulated second packets to the destination endpoint.

Abstract: A novel method for performing replication of messages in a network that bridges one or more physical networks to an overlay logical network is provided. A physical gateway provides bridging between network nodes of a physical network and virtual machines in the overlay logical network by serving as an endpoint of the overlay logical network. The physical gateway does not replicate messages from the bridged physical network to destination endpoints in the overlay logical network directly, but instead tunnels the message-to-be-replicated to a designated tunnel endpoint in the overlay logical network. The designated tunnel endpoint in turn replicates the message that was tunneled to it to other endpoints in the overlay logical network.

Abstract: Some embodiments provide a method for a network controller that manages a logical network implemented in a datacenter having forwarding elements to which the network controller does not have access. The method identifies a data compute node (DCN) operating on a host machine in the datacenter, to attach to the logical network. The DCN has a network interface with an address provided by a datacenter management system. A workload application executes in a first namespace of the DCN. The method distributes configuration data for configuring a managed forwarding element (MFE) executing in a second namespace of the DCN to receive data packets sent from the application via an interface pairing between the first and second namespaces. The data packets sent by the application have the provided address as a source address when received by the MFE and are encapsulated by the MFE using the provided address as a source address.

Abstract: The present disclosure generally relates to applying global unified security policies across a plurality of virtual private clouds of a logical network. The logical network is deployed on a software-defined datacenter that constitute one or more private and/or public datacenters. The plurality of virtual private clouds of the logical network may have one or more overlapping internet protocol address blocks, with each virtual private cloud deploying one or more virtual machines and/or containers. A global unified security policy is disseminated to endpoints throughout the logical network using logical ports of the virtual machines and/or containers.