Abstract: A flow control information routing system includes a receiver node device coupled to a sender node device by intermediate node devices that receive data traffic directed downstream, transmit the data traffic downstream, and provide flow control information upstream that is based on the data traffic transmitted downstream. The sender node device may perform a first layer 3 routing decision to direct a traffic flow to the receiver node device along a first traffic flow path that includes first intermediate node device(s). The sender node device may then receive flow control information provided by the first intermediate node device(s) and, in response, perform a second layer 3 routing decision using the flow control information in order to direct the traffic flow to the receiver node device along a second traffic flow path that includes second intermediate node device(s) and that does not include the first intermediate node device(s).

Abstract: An information handling system is provided. The information handling system includes a first network device that forms at least part of a first set of network devices. The first network device provides an interface between a local first server rack and a cloud and has one or more processors in communication with a memory. The first network device is configured to receive information from a second set of network devices that identifies a default gateway for a virtual machine running on a remote server rack. The first network device is also configured to create a local destination address entry associated with information, to store the entry in an address table in the memory, and to receive a packet having the information identifying the default gateway as a destination address. The first network device is further configured to forward the packet into the cloud on in proxy for the default gateway.

Abstract: A method of routing traffic for multi-cast routing through a node of a network that utilizes loop-free alternative paths is presented. The method includes receiving a join in the node from a second node in the network on a shortest path between the node and the second node; retrieving loop-free alternative paths to the second node; and adding an entry to a multi-cast routing table at the node that is based on a group that includes the shortest path to the second node and the loop-free alternative paths to the second node as cost equivalent paths.

Abstract: The present invention relates generally to an information handling system. Aspects of the present invention include an adaptive credit-based flow control in an information handling system. In embodiments, a request/grant credit system can be eliminated since the receiver can dynamically allocate credits based on demand at the sender. In embodiments, the sender can provide information related to its queue size to the receiver. The receiver can estimate queue size and demand based on the estimated queue size. In embodiments, the receiver allocates credits based on sender demand.

Abstract: An N-port, shared-memory switch allocates a shared headroom buffer pool (Ps) for a priority group (PG). Ps is smaller than a worst case headroom buffer pool (Pw), where Pw equals the sum of worst case headrooms corresponding to each port-priority tuple (PPT) associated with the PG. Each worst case headroom comprises headroom required to buffer worst case, post-pause, traffic received on that PPT. Subject to a PPT maximum, each PPT may consume Ps as needed. Because rarely will all PPTs simultaneously experience worst case traffic, Ps may be significantly smaller than Pw, e.g., Ps<(Pw/A) where M>=2. Ps may be size-adjusted based on utilization of Ps, without halting traffic to or from the switch. If Ps utilization exceeds an upper utilization threshold, Ps may be increased, subject to a maximum threshold (Pmax). Conversely, if utilization falls below a lower utilization threshold, Ps may be decreased.

Abstract: The present invention relates generally to an information handling system. Aspects of the present invention include an adaptive credit-based flow control in an information handling system. In embodiments, a request/grant credit system can be eliminated since the receiver can dynamically allocate credits based on demand at the sender. In embodiments, the sender can provide information related to its queue size to the receiver. The receiver can estimate queue size and demand based on the estimated queue size. In embodiments, the receiver allocates credits based on sender demand.

Abstract: An information handling system is provided. The information handling system includes a plurality of forwarding processors, the plurality of forwarding processors each including a memory having a forwarding host table and a forwarding route table. The information handling system also includes at least one switching device coupled to the plurality of forwarding processors, the at least one switching device including a memory having a destination module and port table, a switching device host table and a switching device route table, wherein the at least one switching device is configured to perform an extended lookup in at least one of the switching device host table and switching device route table based on values included in a fabric header of information routed to the switching device to determine a destination of the information. A method for extending lookup tables is also provided that adds lookup tables in a switching device.

Abstract: An N-port, shared-memory switch allocates a shared headroom buffer pool (Ps) for a priority group (PG). Ps is smaller than a worst case headroom buffer pool (Pw), where Pw equals the sum of worst case headrooms corresponding to each port-priority tuple (PPT) associated with the PG. Each worst case headroom comprises headroom required to buffer worst case, post-pause, traffic received on that PPT. Subject to a PPT maximum, each PPT may consume Ps as needed. Because rarely will all PPTs simultaneously experience worst case traffic, Ps may be significantly smaller than Pw, e.g., Ps<(Pw/A) where M>=2. Ps may be size-adjusted based on utilization of Ps, without halting traffic to or from the switch. If Ps utilization exceeds an upper utilization threshold, Ps may be increased, subject to a maximum threshold (Pmax). Conversely, if utilization falls below a lower utilization threshold, Ps may be decreased.

Abstract: Aspects of the present invention include increasing the number of hops that can be specifically defined in a multiprotocol label switching stack. In embodiments of the present invention, a label space can be used to represent two or more labels. In embodiments of the present invention, the label space can be used by concatenating two or more labels and redefining the multiprotocol label switching stack operations and outgoing labels.

Abstract: A system and method for forwarding network traffic includes receiving a first flow of network traffic at an ingress port on a switch, collecting flow control metrics for a plurality of egress ports assigned to a link aggregation group of the switch, selecting a first egress port from the plurality of egress ports using a hashing strategy based on at least information associated with the flow control metrics, assigning the first flow to the first egress port, directing the first flow to the first egress port, and transmitting network traffic associated with the first flow using the first egress port.

Abstract: An extended bridge structure that includes a controlling bridge and port extenders is disclosed. A port extender according to some embodiments of the present invention includes a processor that processes receives packets in a way that executes at least one procedure that substitutes for a function of the controlling bridge. A controlling bridge according to the present invention provides data to the port extender that enables it to execute the at least one procedure that substitutes for a function of the controlling bridge.

Abstract: An information handling system is provided. The information handling system includes a plurality of aggregation devices configured to distribute information in a virtual link trunk and a plurality of nodes coupled to the aggregation devices. When one of the plurality of aggregation devices received a reboot command, that aggregation device is configured to transmit a first message to the nodes indicating that the aggregation device is rebooting, receive a first acknowledgement message from the nodes indicating that they will not send any information to the rebooting aggregation device.

Abstract: An information handling system is provided. The information handling system includes a first hypervisor running on a first host and a second hypervisor running on a second host. The first hypervisor managing a first virtual switch, and the second hypervisor managing a second virtual switch. The information handling system also includes a plurality of virtual machines (VMs), including a first VM, which is part of a first tenant, running on the first host, and a second VM, part of a second tenant, running on the second host. The first virtual switch has a mapping in memory that maps a customer-specific multicast IP address, used by the plurality of VMs to indicate a multicast group that includes VMs on the first and second tenants, to a global multicast IP address used by the first and second hosts.

Abstract: A method of routing traffic for multi-cast routing through a node of a network that utilizes loop-free alternative paths is presented. The method includes receiving a join in the node from a second node in the network on a shortest path between the node and the second node; retrieving loop-free alternative paths to the second node; and adding an entry to a multi-cast routing table at the node that is based on a group that includes the shortest path to the second node and the loop-free alternative paths to the second node as cost equivalent paths.

Abstract: In non-minimal routing, a switch determines outgoing links for preferred paths (e.g. shortest paths). Then, for another node in a preferred path, the switch determines outgoing links for paths to that node in a modified network in which each link in a previously determined path to the node is cut off. Packets can be tunneled on non-preferred paths to that node. Other features and embodiments are also provided.

Abstract: Aspects of the present invention include an arbitrary N-Node virtual link trunking (VLT) system comprising a set of N nodes collectively provide a logical fabric-level view that is consistent across the set of N nodes. Embodiments of the arbitrary N-Node VLT system comprise a control plane mechanism to provide Layer 2 multipathing between access network devices (switches or servers) and the core network. The N-Node VLT system provides a loop-free topology with active-active load-sharing of uplinks from access to the core. Accordingly, the N-Node VLT system eliminates the disadvantage of Spanning Tree Protocol (STP) (active-standby links) by allowing link aggregation group (LAG) terminations on multiple separate distribution or core switches and also supporting a loop-free topology. Additional benefits of an N-Node VLT system include, but are not limited to, higher resiliency, improved link utilization, and improved manageability of the network.

Abstract: Aspects of the present invention include an n-node link aggregation group (LAG) system comprising a set of N nodes collectively provide a logical fabric-level view that is consistent across the set of N nodes. Embodiments of the n-node system comprise a control plane mechanism to provide Layer 2 multipathing between access network devices and the core network. The n-node system provides a loop-free topology with active-active load-sharing of uplinks from access to the core.

Abstract: A method of routing traffic for multi-cast routing through a node of a network that utilizes loop-free alternative paths is presented. The method includes receiving a join in the node from a second node in the network on a shortest path between the node and the second node; retrieving loop-free alternative paths to the second node; and adding an entry to a multi-cast routing table at the node that is based on a group that includes the shortest path to the second node and the loop-free alternative paths to the second node as cost equivalent paths.

Abstract: Aspects of the present invention include extending routing capabilities to improve networking efficiencies. In embodiments, a spine-leaf network configuration may be provisioned as a single router to solve at least two issues: (1) local routing within a leaf; and (2) scalability of the hardware ARP table. In embodiments, one or more tables in the leaf node may be programmed so that data traffic coming from a first host in a first subnet or VLAN on the leaf and intended for a second host in a second subnet or VLAN on the leaf may be forwarded locally to the second host in the second subnet or VLAN without traversing to the spine layer.

Abstract: Embodiments of the present invention provide methods and system to reduce needless data traffic in leaf-spine switch fabric. In embodiments, in a static solution, data rates of data flows having a common destination port may be measured and responsive to the data flows having a combined data rate that exceeding a rate limit of the common destination port, one or more of the data flows may be limited. Embodiments may also comprise a global scheduler to provide dynamic data rate controls of traffic flows from source ports to destination ports in which to reduce the handling of data traffic that would otherwise be discarded due to oversubscription.