Abstract: An administrator can define or modify one or more service graphs. Next, the administrator can register service appliances along with their device package files with a controller. Then, the controller can establish the capabilities of the service devices, and classify the service devices as legacy or service tag switching (STS) capable devices. Then, the controller can create one or more instances of the service graph, by populating the service nodes into the service graph. Then, the application owner can attach their endpoint groups (EPGs) to the service graphs created by the administrator. Then, a service in the network can be automatically provisioned using the service graph to configure one or more nodes in an associated service chain of the service according to information in the service graph.

Abstract: An administrator can define or modify one or more service graphs. Next, the administrator can register service appliances along with their device package files with a controller. Then, the controller can establish the capabilities of the service devices, and classify the service devices as legacy or service tag switching (STS) capable devices. Then, the controller can create one or more instances of the service graph, by populating the service nodes into the service graph. Then, the application owner can attach their endpoint groups (EPGs) to the service graphs created by the administrator. Then, a service in the network can be automatically provisioned using the service graph to configure one or more nodes in an associated service chain of the service according to information in the service graph.

Abstract: Techniques are provided to prevent switches in a data center fabric path environment with fabric path extension devices from media access control (MAC) address flooding and MAC address table overflow. In such an environment, endpoints associated with virtual port channels are connected to multiple switches which normally would perform MAC address flooding across all switch forwarding engines. The switches in the fabric path exchange MAC synchronization messages based on source/destination specific connectivity such that MAC broadcast messages that advertise source/destination MAC addresses for endpoints do not have to be repeatedly sent and their corresponding MAC lookup tables do not have to be updated or include unnecessary MAC table entries.

Abstract: Techniques are provided to prevent switches in a data center fabric path environment with fabric path extension devices from media access control (MAC) address flooding and MAC address table overflow. In such an environment, endpoints associated with virtual port channels are connected to multiple switches which normally would perform MAC address flooding across all switch forwarding engines. The switches in the fabric path exchange MAC synchronization messages based on source/destination specific connectivity such that MAC broadcast messages that advertise source/destination MAC addresses for endpoints do not have to be repeatedly sent and their corresponding MAC lookup tables do not have to be updated or include unnecessary MAC table entries.

Abstract: In one embodiment, a method includes configuring a first network device for operation in a first logical group with a second network device, receiving information from other network devices configured for operation in a second logical group, the information uniquely identifying each of the other network devices within the second logical group, and assigning a priority to each link connecting the first network device to the second logical group network devices. A portion of the links are selected as active links based on the link priorities and the link priorities are assigned such that a balance of active links is maintained across the second logical group network devices. An apparatus for maintaining a balance of active links across the network devices is also disclosed.

Abstract: In one embodiment, a method includes receiving a packet at an input port of a network device, the input port having a plurality of queues with at least one queue for each output port at the network device, identifying a port group for transmitting the packet from the network device, the port group having a plurality of members each associated with one of the output ports, and selecting one of the queues based on utilization of the members. An apparatus for load balancing is also disclosed.

Abstract: Two or more network devices can automatically coordinate to aggregate ports into virtual port channels. Ports of the port channel can be automatically assigned priorities to achieve about an equal distribution of active links across the two or more network devices.

Abstract: In one embodiment, a method includes receiving a packet at a fabric extender, performing a look up in a flow table at the fabric extender for a flow associated with the packet, processing the packet at the fabric extender based on an entry in the flow table if an entry for the flow is found in the flow table, and forwarding the packet to an upstream network device configured to forward the packet if an entry for the flow is not found in the flow table. An apparatus is also disclosed.

Abstract: In one embodiment, a method includes receiving a multi-destination packet at a switch in communication with a plurality of servers through a network device, identifying a port receiving the multi-destination packet at the switch or a forwarding topology for the multi-destination packet, selecting a bit value based on the identified port or forwarding topology, inserting the bit value into a field in a virtual network tag in the multi-destination packet, and forwarding the multi-destination packet with the virtual network tag to the network device. The network device is configured to forward the multi-destination packet to one or more of the servers based on the bit value in the multi-destination packet. An apparatus for forwarding multi-destination packets is also disclosed.

Abstract: In one embodiment, a method includes receiving a packet at an input port of a network device, the input port having a plurality of queues with at least one queue for each output port at the network device, identifying a port group for transmitting the packet from the network device, the port group having a plurality of members each associated with one of the output ports, and selecting one of the queues based on utilization of the members. An apparatus for load balancing is also disclosed.

Abstract: In one embodiment, an apparatus includes one or more ports for connection to one or more links in communication with a network device, a multi-chassis trunk (MCT) port for connection to an MCT in communication with a switch, and an MCEC manager for creating an MCEC comprising the one or more links in communication with the network device and one or more links connecting the switch to the network device, and transmitting messages to the switch to synchronize state for the MCEC. The apparatus further includes a control plane and a data plane configured for operation independent from a control plane and a data plane at the switch. A method is also disclosed.

Abstract: In one embodiment, a method includes configuring a first network device for operation in a first logical group with a second network device, receiving information from other network devices configured for operation in a second logical group, the information uniquely identifying each of the other network devices within the second logical group, and assigning a priority to each link connecting the first network device to the second logical group network devices. A portion of the links are selected as active links based on the link priorities and the link priorities are assigned such that a balance of active links is maintained across the second logical group network devices. An apparatus for maintaining a balance of active links across the network devices is also disclosed.

Abstract: In one embodiment, a method includes receiving a multi-destination packet at a switch in communication with a plurality of servers through a network device, identifying a port receiving the multi-destination packet at the switch or a forwarding topology for the multi-destination packet, selecting a bit value based on the identified port or forwarding topology, inserting the bit value into a field in a virtual network tag in the multi-destination packet, and forwarding the multi-destination packet with the virtual network tag to the network device. The network device is configured to forward the multi-destination packet to one or more of the servers based on the bit value in the multi-destination packet. An apparatus for forwarding multi-destination packets is also disclosed.

Abstract: Two or more network devices can automatically coordinate to aggregate ports into virtual port channels. Ports of the port channel can be automatically assigned priorities to achieve about an equal distribution of active links across the two or more network devices.