A network device configured to perform scalable, in-network computations is described. The network device is configured to process pull requests and/or push requests from a plurality of endpoints connected to the network. A collective communication primitive from a particular endpoint can be received at a network device. The collective communication primitive is associated with a multicast region of a shared global address space and is mapped to a plurality of participating endpoints. The network device is configured to perform an in-network computation based on information received from the participating endpoints before forwarding a response to the collective communication primitive back to one or more of the participating endpoints. The endpoints can inject pull requests (e.g., load commands) and/or push requests (e.g., store commands) into the network. A multicast capability enables tasks, such as a reduction operation, to be offloaded to hardware in the network device.

A method and a device for multicast packet processing are disclosed. The method includes: A first network device obtains a data packet; and the first network device generates a first multicast packet and a second multicast packet based on the data packet. The first multicast packet includes first iFIT information and a first multi-level flow identifier. The second multicast packet includes the first iFIT information and a second multi-level flow identifier. The first multi-level flow identifier and the second multi-level flow identifier are different, to identify different forwarding paths of the generated first multicast packet and second multicast packet respectively. In the method, in a point-to-multipoint multicast data flow transmission scenario, a plurality of multicast data flows can be identified, to perform iFIT detection on each of the plurality of data flows, so as to implement packet loss and delay detection, path restoration, and the like for the multicast data flows.

A method for offloading multicast replication from multiple tiers of edge nodes implemented by multiple host machines to a physical switch is provided. Each of the multiple host machines implements a provider edge node and a tenant edge node. One host machine among the multiple host machines receives a packet having an overlay multicast group identifier. The host machine maps the overlay multicast group identifier to an underlay multicast group identifier. The host machine encapsulates the packet with an encapsulation header that includes the underlay multicast group identifier to create an encapsulated packet. The host machine forwards the encapsulated packet to a physical switch of the network segment. The physical switch forwards copies of the encapsulated packet to tenant edge nodes at one or more ports that are determined to be interested in the underlay multicast group identifier.

A network management system may allocate different amounts of bandwidth to different types of data traffic. The traffic types may be distinguished by their source device address, and whether the source device is part of, or external to, a first network. Packets may also be marked by their sender with information to identify a traffic type, and the marking may be used to determine the packet's treatment. The allocations given to the various types of traffic may be dynamically modified with changing traffic demands and conditions.

A method of transmitting multicast traffic to workloads of tenants communicating over overlay networks provisioned on top of a physical network includes the steps of: detecting the multicast traffic; determining that the multicast traffic is bound for workloads of a first tenant and workloads of a second tenant; encapsulating one instance of the multicast traffic using a Layer 2 (L2) over Layer 3 (L3) encapsulation protocol to generate encapsulated traffic, wherein the encapsulated traffic includes an identifier of a first backplane network corresponding to the first tenant and an identifier of a second backplane network corresponding to the second tenant in a header portion of each packet of the encapsulated traffic; and transmitting, to a first host computing device, the encapsulated traffic with the identifiers of the first and second overlay networks.

Method and apparatus for facilitating accessing home surveillance device data, preferably an IP camera video stream, by a remote user device at the remote user device's instigation, over the Internet through a home router, the facilitating including incorporating a smart gateway in local communication with the home router and in persistent or intermittent communication with a remote Internet server to facilitate communication of data over the Internet at the remote user device's request through direct communication between the remote user device and the smart gateway, the smart gateway in local communication With the home surveillance device such as an IP camera, the direct communication facilitated by a “hole punch” type of technique.

A method for offloading multicast replication from multiple tiers of edge nodes implemented by multiple host machines to a physical switch is provided. Each of the multiple host machines implements a provider edge node and a tenant edge node. One host machine among the multiple host machines receives a packet having an overlay multicast group identifier. The host machine maps the overlay multicast group identifier to an underlay multicast group identifier. The host machine encapsulates the packet with an encapsulation header that includes the underlay multicast group identifier to create an encapsulated packet. The host machine forwards the encapsulated packet to a physical switch of the network segment. The physical switch forwards copies of the encapsulated packet to tenant edge nodes at one or more ports that are determined to be interested in the underlay multicast group identifier.

Methods for directly mapping attributes from controllers connected to a switch are provided. Multicast protocols are combined with policy management and applied to systems with multiple host and source devices. Unnecessary data packets are dropped, while only necessary data packets are forwarded. These methods decrease the amount of resources needed to process requests received during multicasting, provide enhanced security options, and further integrate networking solutions.

A method for managing data transmission comprising making a bandwidth on a network resource available to at least one requestor for transmitting or receiving data according to a first request of a first type, the first type have a prescribed quality of service guarantee; transmitting first data in accordance with the first type to or from the at least one requestor on the network resource using a first portion of the bandwidth, if the first data are available to be transferred to or from the at least one requestor; transmitting second data according to a second request of a second type on the network resource to or from the at least one requestor or a second requestor, the second data transmitted without a quality of service guarantee using a second portion of the bandwidth, if the first portion of the prescribed bandwidth is less than the entire bandwidth.

Systems and methods are described for optimizing resource utilization in a communications network while also optimizing subscriber engagement with media content over the communications network. Requested content objects can be identified as delayable objects that can be queued for opportunistically delayed communication to both requesting and non-requesting subscribers. Queued delayed content objects are scored with an eye toward optimizing both subscriber engagement and utilization of opportunistically available communications link resources. For example, a storage manager calculates a likelihood that each subscriber will engage with the content if it is opportunistically delivered, and a scheduler calculates a priority order in which to queue each requested delayable content object. Content objects can then be multicast to the subscribers in priority order and with associated information that can be used by the subscribers to determine whether to locally store the content objects as they are opportunistically received.