Abstract: In one example in accordance with the present disclosure, a system for auto-negotiation over extended backplane includes an enclosure and a switch external to the enclosure. The enclosure has a NIC (network interface controller) for a server in the enclosure and a DEM (downlink extension module). The DEM has a single DEM PHY connected to the NIC via a backplane and also connected to the switch via an external connection. The DEM PHY facilitates auto-negotiation between the switch and the NIC.

Abstract: Example implementations relate to generating a completion prediction of a task. A computing device may comprise a processing resource and a memory resource storing non-transitory machine-readable instructions to cause the processing resource to receive task data about a task, analyze the task data using machine learning to generate a data model for the task, and generate a completion prediction based on the generated data model for the task.

Abstract: In one example in accordance with the present disclosure, a system for auto-negotiation over extended backplane includes an enclosure and a switch external to the enclosure. The enclosure has a NIC (network interface controller) for a server in the enclosure and a DEM (downlink extension module). The DEM has a single DEM PHY connected to the NIC via a backplane and also connected to the switch via an external connection. The DEM PHY facilitates auto-negotiation between the switch and the NIC.

Abstract: In one example in accordance with the present disclosure, a system for auto-negotiation over extended backplane includes an enclosure and a switch external to the enclosure. The enclosure has a NIC (network interface controller) for a server in the enclosure and a DEM (downlink extension module). The DEM has a single DEM PHY connected to the NIC via a backplane and also connected to the switch via an external connection. The DEM PHY facilitates auto-negotiation between the switch and the NIC.

Abstract: Various examples disclosed herein relate to determining switch load values for a switch according to a weighted score for categorized network traffic. In some examples, traffic volume information is determined for a switch in a network. The traffic volume information can include volume of network traffic for the switch for multiple time parameters. The network can include multiple switches. The switches can be associated with loss potential information based on a topology of the switches. The traffic volume information can be categorized into multiple categories. Multiple switch load values can be determined for the switch. Each switch load value can correspond to one of the multiple time parameters. Further, each switch load value can be determined according to a weighted score for each categorized network traffic and according to the loss potential information.

Abstract: In one example in accordance with the present disclosure, a system for auto-negotiation over extended backplane includes an enclosure and a switch external to the enclosure. The enclosure has a NIC (network interface controller) for a server in the enclosure and a DEM (downlink extension module). The DEM has a single DEM PHY connected to the NIC via a backplane and also connected to the switch via an external connection. The DEM PHY facilitates auto-negotiation between the switch and the NIC.

Abstract: Various examples disclosed herein relate to determining switch load values for a switch according to a weighted score for categorized network traffic. In some examples, traffic volume information is determined for a switch in a network. The traffic volume information can include volume of network traffic for the switch for multiple time parameters. The network can include multiple switches. The switches can be associated with loss potential information based on a topology of the switches. The traffic volume information can be categorized into multiple categories. Multiple switch load values can be determined for the switch. Each switch load value can correspond to one of the multiple time parameters. Further, each switch load value can be determined according to a weighted score for each categorized network traffic and according to the loss potential information.

Abstract: Systems and methods for distributed configuration of one or more network interface cards (NICs) are disclosed. An exemplary method comprises issuing a request frame including at least a current configuration generation for the NICs from a host computing device to a network device. The method also comprises returning at least one configuration frame including a newer network configuration for the NICs from the network device to the host computing device. The method also comprises configuring the NICs at the host computing device with the newer network configuration.

Abstract: A method and system that comprises a central processing unit (CPU) and a first and second network adapter that are teamed together is disclosed. The network adapters in the team may be adapted to offload connections to transfer a plurality of packets. A program, executing on the CPU, may reload an offloaded connection established by the first network adapter onto the second network adapter if one of a plurality of packets associated with the offloaded connection was received on the second network adapter.

Abstract: Embodiments include methods, apparatus, and systems for managing connectivity in a virtual network. One embodiment determines if information received from a device in a virtual land area network (VLAN) matches a configuration of a virtual connect domain (VCD) in order to label links as being either internal or external.

Abstract: A computer system aggregates a plurality of network resources of a computer system. The computer system has a plurality of processing nodes. Each of the processing nodes includes one or more of the plurality of network resources. The one or more resources of each processing node makes up a bypass protocol stack operable to provide offloaded connections over a network to instances of one or more applications running on the system. Each of the applications is uniquely associated with a first port number. The system is identified on the network by a global IP address and each of the plurality of nodes is identified by a unique local IP address. Each of the plurality of resources is uniquely identified by an assigned private IP address. At each of the processing nodes, a listening socket is created for each instance of the plurality of applications running on the node.

Abstract: Embodiments include methods, apparatus, and systems for managing connectivity in a virtual network. One embodiment determines if information received from a device in a virtual land area network (VLAN) matches a configuration of a virtual connect domain (VCD) in order to label links as being either internal or external.

Abstract: A computer system aggregates a plurality of network resources of a computer system. The plurality of network resources forms a bypass stack operable to provide offloaded connections to one or more applications available on the computer system. Each of the applications is associated with a first port number. The computer system itself is addressable on the network by a public IP address. The system assigns private IP addresses to uniquely identify each of the plurality of network resources. The system creates a socket for each application by which the application can communicate with the network. The socket is associated with a first endpoint tuple that includes the public IP address and the first port number associated with the application for which the socket is created. The socket is further associated with a set of bypass endpoint tuples that are translated from the first endpoint tuple, each of the set including a different one of the private IP addresses.

Abstract: Systems and methods for distributed configuration of one or more network interface cards (NICs) are disclosed. An exemplary method comprises issuing a request frame including at least a current configuration generation for the NICs from a host computing device to a network device. The method also comprises returning at least one configuration frame including a newer network configuration for the NICs from the network device to the host computing device. The method also comprises configuring the NICs at the host computing device with the newer network configuration.

Abstract: A method is presented that enhances the survivability of system software components, even in the event of catastrophic failure of the computing element on which they reside. In particular, the combination of a distributed operating system (Non Stop Clusters) and a fault-tolerant interconnect (ServerNet) provides an environment conducive to posthumous recovery strategies that have been unavailable in previous distributed computing environments. The specific strategy outlined here is called resource harvesting, and involves a novel approach that retrieve critical data structures of memory from a failed computing element for reconstruction on a non-failed computing element, allowing such critical data structures to continue with their original function.

Abstract: A data communication system embodying an apparatus and a method provides simultaneous paths between a plurality of transmit ports and a plurality of receive ports for transmitting therebetween data identifying their destination receive ports. Such data are signals which are constructed in accordance with a standard serial protocol for frame element communication, such as HDLC (High-level Data Link Control). The system is assembled in a chassis containing a backplane and multiple cards having transmit and receive ports through which the cards couple the backplane.