Cisco Technology, Inc.

Sandisk Technologies Inc.

Mediatek Singapore Pte. Ltd.

Ming Zhang

Chengelpet Ramesh

Shyam N Kapadia

Jonathan Chang

Flavio Giovanni Bonomi

Nilesh Shah

Awais Bin Nemat

Ram Krisnan

Rong Pan

Putu Harry Subagio

Qing Li

Rajesh Babu Nataraja

Yung-Chin Chen

Xiaoyu Yang

Valentina Alaria

David Edward Bliss

Chiara Piglione

Abhijit V Warkhedi

Jui-Yang Lu

Feng Gao

Sankararaman Jayaraman

Stephanie W Ti

Ganesh P Murthy

Yaonan Liang

Chengelpet V Ramesh

Apparatuses, systems, methods, and computer program products are disclosed for selective temperature compensation. An apparatus includes a compensation circuit that applies temperature compensation to an operation based on a temperature detected by a temperature sensor. An apparatus includes a command circuit that receives a lock command. An apparatus includes a lock circuit that locks a temperature compensation applied to an operation in response to receiving a lock command such that the temperature compensation is based on a fixed temperature.

Selective temperature compensation

A distributed neighbor discovery module is disclosed where all neighbor discovery operations and functionalities may be distributed to a switch device processor. Each neighbor discovery process on a switch device may run as an individual neighbor discovery router node. There may be no coordination between neighbor discovery processes occurring on different switch devices. All other traffic, including both IPv6 control traffic and data traffic destined to the router may be processed by the central controller processor.

Neighbor discovery for IPV6 switching systems

Some implementations provide a method for managing switches in a data center that includes: (1) establishing a connection from one switch to another switch in the data center, the data center providing a plurality of virtual local area networks (VLANs), each VLAN including at least one Virtual Machine and capable of spanning across more than one of the plurality of switches; (2) provisioning device prefixes for IPv6 addresses, a given device prefix corresponding to a particular VLAN on a particular switch in the data center, the given device prefix included in a host address of a particular virtual machine, the particular virtual machine hosted on a server computer, the sever computer connected to the particular switch without additional intervening switches; (3) configuring a hardware memory to include prefix information and address information; and (4) transferring packets by using the prefix information and the address information.

System and method for scaling IPV6 on a three-tier network architecture at a large data center

An example method for routing IPv6 link-local addresses in a network environment is provided and includes receiving a packet at a first switch from an attached first host in a virtual local area network (VLAN) associated with a virtual routing and forwarding (VRF) instance of a network environment, where the packet is destined to an Internet Protocol version 6 (IPv6) link-local address of a remote second host in the VLAN, and routing the packet at Layer 3 to a second switch, to which the second host is attached. In specific embodiments, the second switch routes the packet at Layer 3 to the second host if the VRF does not include duplicate IPv6 link-local addresses corresponding to the IPv6 link-local address of the second host; the second switch bridges the packet at Layer 2 to the second host if the VRF includes at least one duplicate IPv6 link-local address.

Routing internet protocol version 6 link-local addresses in a network environment

Techniques are provided for sending address information of virtual machines to a physical switch. A migration of a virtual machine to a physical server is detected. The physical server obtains address information of the virtual machine, and upon obtaining the address information of the virtual machine, the physical server sends the address information to a first physical switch that is connected to the physical server.

Optimizing handling of virtual machine mobility in data center environments

A packet forwarding apparatus has a path selection device used to generate a path selection signal for selecting a destination path from egress paths of an egress path group. The path selection device has a flow group based path selection circuit and a flow subgroup based path selection circuit. The flow group based path selection circuit sets the path selection signal based on a flow group into which a packet is categorized when a dynamic load balancing function is not applied to forwarding of the packet. The flow subgroup based path selection circuit sets the path selection signal based on a flow subgroup into which the packet is categorized when the dynamic load balancing function is applied to forwarding of the packet. Flows associated with the egress path group are categorized into flow subgroups, the flow subgroups are categorized into flow groups, and each flow includes packets with same tuple(s).

Packet forwarding apparatus and method using flow subgroup based path selection for dynamic load balancing

A method for optimizing within subnet communication in a network environment is provided and includes receiving, at a Top-Of-Rack (ToR) switch, an advertisement from an attached host belonging to a subnet of a network environment, seeking a Media Access Control (MAC) address of a remote host in the subnet, looking up a host information database in a control plane of the ToR switch, and responding to the advertisement with the MAC address of the remote host. If the MAC address is not found, the ToR switch may not respond to the advertisement. The method can further include receiving, at the ToR switch from a remote ToR switch in the subnet, a host information of the remote host in the subnet, including an IP address and the MAC address of the remote host, the Layer 2 broadcast domain it belongs to, and storing the host information in the host information database.

System and method for optimizing within subnet communication in a network environment

Techniques are provided for optimizing storage of address information in switch device databases. A control packet is received from a source host. An address associated with a host is determined. The address comprises a first and second address component. The first address component is stored in a first database and is mapped to an index value that is stored in the first database. The index value is also stored in a second database along with the second address component. The first database may also be examined to determine whether the first address component is stored in the first database. If the first address component is stored in the first database, the index value mapped to the first address component is retrieved. The second database is examined to determine whether the index value and the second address component are stored in the second database.

Increasing internet protocol version 6 host table scalability in top of rack switches for data center deployments

In one embodiment, a method includes receiving from a server, flow data for a plurality of flows at a network device, the flow data comprising for each flow, a destination address and a time indicating when a last packet was processed for the flow at the server, updating a flow table at the network device, identifying one of the flows in the flow table as an inactive flow, and removing a route for the inactive flow from a forwarding information base at the network device. An apparatus and logic are also disclosed herein.

Forwarding table optimization with flow data

System and method for scaling IPv6 on a three-tier network architecture at a large data center

In one embodiment, a method includes tracking at a network device in communication with a plurality of virtual machines, virtual machine movement based on a device identifier in a packet received from one of the virtual machines and storing location information for the virtual machine in a virtual machine move list at the network device. The location information from the virtual machine move list is inserted into a forwarding information base for use in optimized forwarding of packets destined for the virtual machine. An apparatus and logic are also disclosed herein.

Packet forwarding optimization with virtual machine mobility by comparing device identifiers to determine VM movement

Systems and methods are provided to support a large number of hosts while keeping the size of the FIB CAM low. Higher scalability may be achieved by consuming less FIB CAM space as hosts are added to a network. An L3 switching module may be provided capable of supporting a large number of virtual machines and/or hosts while maintaining a small FIB CAM size on a multiple device virtual switching system with device level aggregation.

Scaling IPV4 at large datacenters with device level aggregation

Systems and methods are provided to detect when a virtual machine moves across a switch device boundary, keep existing application sessions alive, and provide optimal forwarding for new application sessions with graceful address migration. Virtual machine movement can be detected on the new switching device by comparing the Device ID in the Source Address of the ND-NA with the Device ID of the new switching device. A temporary hardware forwarding sub-optimal path is maintained for existing application sessions. A new IP address is assigned to the moved virtual machine and an optimal forwarding path is programmed in hardware for new application sessions. The temporary sub-optimal hardware forwarding path is removed after all old application are terminated.

Method of IPv6 at data center network with VM mobility using graceful address migration

Systems and methods are provided for scaling IPv4 networks for large data centers to reach hosts in a directly connected subnet. ToRs may be dynamically selected in a load balanced manner to ensure that any host may deliver packets to any other host in two or less hops.

Scaling IPv4 in data center networks employing ECMP to reach hosts in a directly connected subnet

An example method is provided and includes receiving, at an ingress switch in a network, a packet from an attached host that is coupled to a destination host, where the packet includes an Internet Protocol version 6 (IPv6) address of a destination host, comparing the IPv6 address with a plurality of entries in a longest prefix match (LPM) table, in which each entry includes a value string and a corresponding mask string configured to detect a match for a specific combination of a segment prefix and a switch-id in the IPv6 address, identifying an egress switch from a matching entry in the LPM table, and forwarding the packet to the egress switch. The IPv6 address includes a combination of segment prefix and switch-id associated with the egress switch. The segment prefix corresponds to an identifier of a network segment, and the switch-id corresponds to an identifier of a switch in the network.

Growing community of inventors

San Jose, CA, United States of America

Ming Zhang