Cisco Technology, Inc.

Chia Alex Tsai

Yibin Yang

Rajagopalan Janakiraman

Vinay Parameswarannair

Yuchen Zhou

Liqin Dong

Shyam N Kapadia

Nilesh Shah

Pags Krishnamoorthy

Debashis Patnala Rao

Norman William Finn

Ajit Sanzgiri

Bhanu Gopalasetty

Minjie Lin

Weng Hong Chan

Yuefeng Jiang

Bhawani Sapkota

Fang Yang

Xiaopu Zhang

Jeffrey Cai

Vijay Nain

Jun Xie

Xinhua Zhao

In one embodiment, a copy of an original packet of a traffic flow is created at an ingress leaf node of a cloud switch. The ingress leaf node forwards the original packet along a less-specific path through the cloud switch, the less-specific path based on a domain index of an egress domain for the original packet. The copy of the original packet is modified to create a more specific path learn request packet. The ingress leaf node forwards the more specific path learn request packet along the less-specific path through the cloud switch. The ingress leaf node received back a more specific path learn request reply packet that includes an indication of a fabric system port. The ingress leaf node then programs a forwarding table based on the indication of the fabric system port, to have subsequent packets of the traffic flow forwarded along a more-specific path.

MSDC scaling through on-demand path update

In some embodiments, a data packet may be received at a leaf switch. A port-channel associated with a destination port for the data packet may be identified, and the data packet may be transmitted to the destination port via the identified port-channel.

Two-stage port-channel resolution in a multistage fabric switch

In one embodiment, a multiple spanning tree (MST) region is defined in a network, where the MST region includes a plurality of network nodes interconnected by links. A MST cluster is defined within the MST region, where the MST cluster includes a plurality of network nodes selected from the plurality of network nodes of the MST region. A network node of the MST cluster generates one or more MST bridge protocol data units (BPDUs) that present the MST cluster as a single logical entity to network nodes of the MST region that are not included in the MST cluster, yet enables per-multiple spanning tree instance (per-MSTI) load balancing of traffic across inter-cluster links that connect network nodes included in the MST cluster and network nodes of the MST region that are not included in the MST cluster.

Level of hierarchy in MST for traffic localization and load balancing

Techniques are presented for distributing host route information of virtual machines to routing bridges (RBridges). A first RBridge receives a routing message that is associated with a virtual machine and is sent by a second RBridge. The routing message comprises of mobility attribute information associated with a mobility characteristic of the virtual machine obtained from an egress RBridge that distributes the routing message. The first RBridge adds a forwarding table attribute to the routing message that indicates whether or not the first RBridge has host route information associated with the virtual machine in a forwarding table of the first RBridge. The first RBridge also distributes the routing message including the mobility attribute information and the forwarding table attribute, to one or more RBridges in the network.

Intelligent host route distribution for low latency forwarding and ubiquitous virtual machine mobility in interconnected data centers

Techniques are provided for managing movements of virtual machines in a network. At a first switch, a virtual machine (VM) is detected. The VM is hosted by a physical server coupled to the first switch. A message is sent to other switches and it indicates that the VM is hosted by the physical server. When the first switch is paired with a second switch as a virtual port channel (vPC) pair, the message includes a switch identifier that identifies the second switch. A receiving switch receives the message from a source switch in the network comprising a route update associated with the VM. A routing table of the receiving switch is evaluated to determine whether the host route is associated with a server facing the physical port. The message is examined to determine it contains the switch identifier.

Techniques for scalable and foolproof virtual machine move handling with virtual port channels

Techniques provided herein use aggregate endpoints in a virtual overlay network. In general, aggregate endpoints operate as a single receiving entity for certain packets/frames sent between different physical proximities of the virtual overlay network.

Scalable network virtualization with aggregate endpoints

In one embodiment, a period between periodic transmissions of protocol data units (PDUs) used to form or maintain a link aggregation group is initially set to a fixed value. When a stress condition is detected, the period between periodic transmissions of PDUs is increased from the initial value. When the stress condition is determined to have eased, the period between periodic transmissions of PDUs is reduced back toward the fixed value.

Method and apparatus for adaptive fast start in link aggregation

In one embodiment, one or more indicia of stress are monitored. Based on the one or more indicia of stress, it is determined a stress condition exists. In response to the stress condition, one or more link aggregation actors and partners are caused to enter a grace state for a grace period. While the one or more link aggregation actors and partners are in the grace state, link aggregation formation is paced on a plurality of links by delaying formation of one or more new link aggregation groups on the plurality of links until a hold is released. Upon expiration of the grace period, the grace state is exited.

Grace state and pacing in link aggregation

Growing community of inventors

Cupertino, CA, United States of America

Chia Alex Tsai