Abstract: Systems and methods are provided for controlling a network switch. At least one forwarding element of the distributed switch is positioned at a first location of a network. A control element of the distributed switch is positioned at a second location of the network. The at least one forwarding element is controlled from the control element by establishing a communication between the forwarding element and the control element via the network.

Abstract: Systems are provided for overlaying a virtual network on a physical network in a data center environment. An overlay system is arranged in an overlay virtual network to include an overlay agent and an overlay helper. The overlay agent is implemented in an access switch. The overlay helper is implemented in an end station that is in communication with the access switch. Overlay parameters in compliance with an in-band protocol are transmitted between the overlay agent and the overlay helper.

Abstract: Methods are provided for overlaying a virtual network on a physical network in a data center environment. An overlay system is arranged in an overlay virtual network to include an overlay agent and an overlay helper. The overlay agent is implemented in an access switch. The overlay helper is implemented in an end station that is in communication with the access switch. Overlay parameters in compliance with an in-band protocol are transmitted between the overlay agent and the overlay helper.

Abstract: A switching network includes an upper tier having a master switch and a lower tier including a plurality of lower tier entities. The master switch, which has a plurality of ports each coupled to a respective lower tier entity, implements on each of the ports a plurality of virtual ports each corresponding to a respective one of a plurality of remote physical interfaces (RPIs) at the lower tier entity coupled to that port. Data traffic communicated between the master switch and RPIs is queued within virtual ports that correspond to the RPIs with which the data traffic is communicated. The master switch applies data handling to the data traffic in accordance with a control policy based at least upon the virtual port in which the data traffic is queued, such that the master switch applies different policies to data traffic queued to two virtual ports on the same port of the master switch.

Abstract: A method for providing location independent dynamic port mirroring on distributed virtual switches is disclosed. A controller is provided to configure one or more virtual switches within a group of physical machines to appear as a set of distributed virtual switches. In response to the receipt of a data packet at a port of a physical machine, a determination is made whether or not the port has a monitor port located on the physical machine. If the port has a monitor port located on the same physical machine, a copy of the data packet is sent to the monitor port of the physical machine. If the port has a monitor port located on a different physical machine, a copy of the data packet along with an identification (ID) of the port and an ID of the monitor port are encapsulated, and the encapsulated information are sent to a controller.

Abstract: Packet processing logic of a host system's virtualization manager detects packets on the ingress or the egress path to/from a virtual port having three bitmap arrays for processing packets within a virtual local area network (VLAN). The logic checks the VLAN identifier (VID) of the packet to determine, based on an offset position within the corresponding bitmap array, whether the port supports the VLAN. Both the ingress array offset position and egress array offset positions correspond to the value of the VID, and are set within the specific bitmap array during configuration of the VLAN on the port. When the VLAN is supported by the port, the logic enables the packet to be processed by the port. Otherwise, the logic discards the packet. A strip bitmap array indicates when a packet's VID should be removed prior to forwarding the packet on the egress of a port (or destination port).

Abstract: A switching network includes an upper tier having a master switch and a lower tier including a plurality of lower tier entities. The master switch, which has a plurality of ports each coupled to a respective lower tier entity, implements on each of the ports a plurality of virtual ports each corresponding to a respective one of a plurality of remote physical interfaces (RPIs) at the lower tier entity coupled to that port. Data traffic communicated between the master switch and RPIs is queued within virtual ports that correspond to the RPIs with which the data traffic is communicated. The master switch applies data handling to the data traffic in accordance with a control policy based at least upon the virtual port in which the data traffic is queued, such that the master switch applies different policies to data traffic queued to two virtual ports on the same port of the master switch.

Abstract: A technique for operating a virtual switch includes determining network connection requirements for virtual machines controlled by a virtual machine monitor. Resources available, for processing data traffic of the virtual machines, are also determined. Finally, based on the network connection requirements and the resources available, a port of a virtual switch is selected to operate as a virtual Ethernet bridge or a virtual Ethernet port aggregator.

Abstract: A technique for operating a virtual switch includes determining network connection requirements for virtual machines controlled by a virtual machine monitor. Resources available, for processing data traffic of the virtual machines, are also determined. Finally, based on the network connection requirements and the resources available, a port of a virtual switch is selected to operate as a virtual Ethernet bridge or a virtual Ethernet port aggregator.

Abstract: Techniques for providing location independent dynamic port mirroring on distributed virtual switches is disclosed. A controller is provided to configure one or more virtual switches within a group of physical machines to appear as a set of distributed virtual switches. In response to the receipt of a data packet at a port of a physical machine, a determination is made whether or not the port has a monitor port located on the physical machine. If the port has a monitor port located on the same physical machine, a copy of the data packet is sent to the monitor port of the physical machine. If the port has a monitor port located on a different physical machine, a copy of the data packet along with an identification (ID) of the port and an ID of the monitor port are encapsulated, and the encapsulated information are sent to a controller.

Abstract: In a flow control method, operation flow is controlled on a per connection basis. The method comprises managing a sending peer to prevent overflow of a receiving peer's receiver credits and allocating a number of send buffers at the sending peer greater than or equal to the maximum number of receiver credits that can be indicated by the receiving peer. The technique prevents the sending peer from overflowing its set of send buffers, arising due to re-use, without taking completions on operations queued to a Send Queue.

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: In a flow control method, operation flow is controlled on a per connection basis. The method comprises managing a sending peer to prevent overflow of a receiving peer's receiver credits and allocating a number of send buffers at the sending peer greater than or equal to the maximum number of receiver credits that can be indicated by the receiving peer. The technique prevents the sending peer from overflowing its set of send buffers, arising due to re-use, without taking completions on operations queued to a Send Queue.

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: A computer system establishes offloaded connections over a network between requester applications running on client nodes and server applications running on a server node. The connections are established through an aggregated plurality of network resources of the server node. Each of the aggregated plurality of server resources is operable to provide offloaded connections over the network and each is assigned to a unique private IP address. Connect queries are generated on behalf of requesting applications. Each of the connect queries specifies one of the server applications using a first endpoint tuple. The first endpoint tuple includes one of one or more IP addresses identifying the server node publicly on the network and a first port number uniquely identifying the server application. A valid set of bypass endpoint tuples are obtained that are translated from the first endpoint tuple specified in the query. Each tuple of the set includes a different one of the assigned private IP addresses.