Abstract: According to one embodiment, a method includes performing functionality of a management plane and a control plane for a switch system using a processor of an external host coupled to the switch system via one or more peripheral component interconnect express (PCIe) ports. The method also includes providing a direct memory access (DMA) facility between the external host and switching logic of the switch system. The switch system includes a PCIe interface block coupled to PCIe ports configured to couple to external PCIe devices. Also, the PCIe interface block includes logic configured to provide DMA for each PCIe lane thereof. The switch system also includes multiple switched Ethernet ports configured to couple to one or more external Ethernet devices and switching logic configured to switch between the multiple switched Ethernet ports and the PCIe ports using DMA and a local processor coupled to the PCIe interface block.

Abstract: A distributed system includes first-tier entities, and a master entity in communication with each first-tier entity. The master entity provides a single access point through which an administrator can submit commands to manage all entities. The master entity maintains a table of virtual slots. Each virtual slot points to one of the first-tier entities, and each first-tier entity is pointed to by at least one virtual slot. The processor runs an RPC (remote procedure call) client to submit RPC requests to the first-tier entities, and determines a destination first-tier entity for a given RPC request in response to which virtual slot the administrator submits a command. The distributed system can include second-tier entities, each indirectly communicating with the master entity through a first-tier entity. The table has a virtual slot for each second-tier entity, which points to the first-tier entity acting as proxy for the second-tier entity.

Abstract: In one embodiment, a method includes extracting, by one or more processors, a class name from a uniform resource identifier (URI) of an application header of a standardized interface request that includes a command formatted in an application protocol. The application header includes meta-data that allows class declarations to function, at least in part, as a portion of interface description language. In another embodiment, a computer system for generating a RESTful interface includes a computer-readable memory and one or more processors in electrical communication with the memory. The one or more processors are configured to perform the method recited above. In yet another embodiment, a computer program product includes a computer-readable storage medium and program instructions stored on the computer-readable storage medium readable/executable by one or more processors to perform the method recited above.

Abstract: In one embodiment, a system for determining latency in paths includes logic integrated with and/or executable by a processor, the logic being adapted to synchronize clocks of two devices connected via two or more link aggregation (LAG) ports and/or multiple devices within paths through a network fabric, determine a transit delay for each LAG port and/or path, store the transit delay for each LAG port to a LAG structure along with an identifier for the LAG port and/or for each path to an equal cost multi-path (ECMP) structure along with an identifier of the path, sort the LAG ports according to each LAG port's transit delay and mark a LAG port having the lowest latency, and sort the paths according to each path's transit delay and mark a path having the lowest latency, wherein each path has an equal path cost factor.

Abstract: In one embodiment, a method includes receiving a request from a remote distributed fabric protocol (DFP) system master, using a dedicated processor of a DFP system member, to register local I2C devices on the DFP system member, and sending an acknowledgement including a list of local I2C bus devices back to the DFP system master using the dedicated processor of the DFP system member. The acknowledgement present on the DFP system member. In another embodiment, a system includes a local processor, one or more local I2C bus devices, and a dedicated processor electrically coupled to the local I2C bus devices. The dedicated processor is configured to route interrupts from the local I2C bus devices to the local processor, and expose the local I2C devices to a remote DFP system master by sending details of the local I2C bus devices to the remote DFP system master.

Abstract: A tool for packet transmission and delivery in a distributed system. The tool determines one or more packets is classified as a L3 packet. The tool determines translation of the one or more packets classified as L3 packets to one or more corresponding net devices. The tool sends the one or more packets classified as a non L3 packet to a user space packet dispatcher service.

Abstract: A method includes receiving a first packet having a first virtual local area network (VLAN) identifier (ID) directly from a first virtual switch using a first physical overlay switch located at an edge of an internet protocol (IP) network, encapsulating the first packet with an overlay header and tunneling the first encapsulated packet via Layer-3 operations across the IP network to a second physical overlay switch in response to a determination that a source of the packet is physically separated from a destination of the packet by the IP network, receiving a second encapsulated packet having a second overlay header from the second physical overlay switch, de-encapsulating the second encapsulated packet to create a second packet having a second VLAN ID, and sending the second packet having the second VLAN ID directly to the first virtual switch operating in the first hypervisor domain.

Abstract: In one embodiment, a computer program product includes a computer readable storage medium having program instructions embodied therewith. The embodied program instructions are readable/executable by a processor to receive, by the processor, a packet via a network fabric, the network fabric having a plurality of interconnected fabric switches. The embodied program instructions are also readable/executable by the processor to determine, by the processor, a path through the network fabric by consulting a source-routing table. Moreover, the embodied program instructions are readable/executable by the processor to store, by the processor, source-routing information to a packet header for the packet, the source-routing information including the path. In addition, the embodied program instructions are readable/executable by the processor to send, by the processor, the packet according to an indication in the source-routing information.

Abstract: In one embodiment, a system includes logic adapted for receiving, at a first end point station, an information exchange packet from each end point station in a virtual network having a specified virtual network identifier (VNID) and logic adapted for processing each received information exchange packet to retrieve information about connections at each end point station in the virtual network having the specified VNID, wherein each end point station either terminates or originates a tunnel shared by the first end point station in an overlay network. In this way, the information may be used to respond to address resolution protocol (ARP) requests sent locally in lieu of flooding the ARP request. Other systems, methods, and computer program products are also presented regarding the overlay tunnel information exchange protocol, according to various embodiments.

Abstract: In one embodiment, a method for exchanging overlay tunnel information includes receiving an information exchange packet, at a first end point station, from each end point station in a virtual network having a specified virtual network identifier (VNID); and processing each received information exchange packet to retrieve information about connections at each end point station in the virtual network having the specified VNID, wherein each end point station either terminates or originates a tunnel shared by the first end point station in an overlay network. In this way, the information may be used to respond to address resolution protocol (ARP) requests sent locally in lieu of flooding the ARP request. Other systems, methods, and computer program products are also presented regarding the overlay tunnel information exchange protocol, according to various embodiments.

Abstract: According to one embodiment, a switch system includes an external host connected via a peripheral component interconnect express (PCIe) port to a switch system, the external host being configured to perform functionality of a management plane and a control plane for the switch system, the external host having a processor. In another embodiment, a computer program product includes a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code including computer readable program code configured to perform functionality of a management plane and a control plane for a switch system using a processor of an external host. Other systems, computer program products, and methods are described according to more embodiments.

Abstract: In one embodiment, a system includes a hardware processor and logic integrated with and/or executable by the hardware processor. The logic is configured to create statistics about overlay-encapsulated packets which are received by or sent by the hardware processor across an overlay network. The logic is also configured to record the statistics with a virtual network identifier and a tunnel identifier associated with at least one overlay-encapsulated packet for which the statistics are created. Moreover, the logic is configured to maintain a table indexed for the virtual network identifier and the tunnel identifier. The table includes the virtual network identifier, the tunnel identifier, and statistic bucket identifiers pointing to locations where statistics associated with the virtual network identifier and the tunnel identifier are stored. Other systems, methods, and computer program products are disclosed according to more embodiments.

Abstract: One or more processors receive a standardized interface request that includes a command formatted in an application protocol. One or more processors extract a class name from a uniform resource identifier (URI) of an application header of the standardized interface request. The application header includes a meta-data that allows class declarations to function as a portion of interface description language. One or more processors identify a type of the command based, at least in part, on the application protocol of the command. One or more processors process the command based on the identified type of the command, the application protocol of the command, and the meta-data. One or more processors send a standardized interface response based on a result of the processing.

Abstract: In one embodiment, a system includes at least one processor and logic integrated with and/or executable by the processor, the logic being configured to instantiate, using an interface definition language (IDL) on a first server, a remote procedure call (RPC) function to exchange information between the first server and a second server, generate at least one stub on the first server using the RPC, and generate at least one stub on the second server using the RPC, wherein the at least one stub generated on the second server does not perform any marshalling or un-marshaling of data when endianess of the two servers is the same. Other systems, methods, and computer program products for exchanging information between servers using RPCs are described in more embodiments.

Abstract: In one embodiment, a method includes accessing every local I2C bus device, using a local processor of a distributed fabric protocol (DFP) system member, to ascertain which local I2C bus devices are present, receiving a request from a remote DFP system master, using a dedicated processor of the DFP system member, to register local I2C devices on the DFP system member in order to allow the DFP system master to have access to the local I2C devices, sending an acknowledgement to the request back to the DFP system master, receiving a read request from the DFP system master to read the local I2C bus devices and authenticating the read request, encapsulating details of the local I2C bus devices into a packet similar to that in which the read request was received, and sending the packet to a local network switch to be switched to the DFP system master.

Abstract: In one embodiment, a system includes a network fabric having a plurality of fabric switches interconnected in the network fabric and a switch controller having logic adapted to configure the network fabric, determine one or more paths through the network fabric between any two hosts connected thereto, and create a source-routing table to store the one or more paths through the network fabric between any two hosts connected thereto. In another embodiment, a method includes receiving or creating a packet using a NIC of a host connected to a network fabric having a plurality of fabric switches interconnected therein, determining a path through the network fabric by consulting a source-routing table stored to the host, storing source-routing information to a packet header for the packet, the source-routing information including the path, and sending the packet to a first device or hop indicated by the path in the source-routing information.

Abstract: In one embodiment, a switch includes a processor and logic integrated with and/or executable by the processor, the logic being configured to cause the processor to receive a packet at an ingress port of the switch, forward the packet to a buffered switch when at least one congestion condition is met, where the buffered switch is configured to evaluate congestion conditions of a fabric network, and forward the packet to a low-latency switch when the at least one congestion condition is not met, where the low-latency switch includes an additional policy table provided with forwarding decisions based on the congestion conditions of the fabric network. Other switches, systems, methods, and computer program products for providing low latency packet forwarding with guaranteed delivery are described according to more embodiments.

Abstract: A method includes receiving a packet having a VLAN ID at a first physical overlay switch located at an edge of an IP network, encapsulating the packet with an overlay header, and tunneling the encapsulated packet to a second physical overlay switch via IP network.

Abstract: In one embodiment, a method includes receiving first overlay network traffic via a first input overlay tunnel at a multi-protocol virtual tunnel end point (VTEP) implemented in an accelerated network interface card (NIC) of a server. The method also includes routing the first overlay network traffic to a second overlay network tunnel which adheres to a second overlay network protocol in response to a determination that a destination of the first overlay network traffic is specified as the second overlay network tunnel. Moreover, the method includes receiving second overlay network traffic via the first input overlay tunnel at the multi-protocol VTEP. The method also includes bridging the second overlay network traffic to a first destination overlay network tunnel terminated at the multi-protocol VTEP in response to a determination that a destination of the second overlay network traffic is specified as the first destination overlay network tunnel.

Abstract: In one embodiment, an apparatus includes a memory, a hardware processor, and logic integrated with and/or executable by the processor. The logic is configured to receive one or more software defined network (SDN) routes dictating a path through a network comprising a plurality of devices. The logic is also configured to store the one or more SDN routes to the memory along with one or more traditional routes learned by the apparatus and/or configured by an administrator, and indicate the one or more SDN routes as being of a type different from the traditional routes. Moreover, the logic is configured to receive a priority ordering for a plurality of routes stored in the memory from the SDN controller, the plurality of routes including at least one SDN route, and construct a route information base (RIB) based on the plurality of routes and the priority ordering.