H04L45/021

SYSTEM AND METHOD TO PROVIDE HOMOGENEOUS FABRIC ATTRIBUTES TO REDUCE THE NEED FOR SA ACCESS IN A HIGH PERFORMANCE COMPUTING ENVIRONMENT
20210399909 · 2021-12-23 ·

Systems and methods for InfiniBand fabric optimizations to minimize SA access and startup failover times. A system can comprise one or more microprocessors, a first subnet, the first subnet comprising a plurality of switches, a plurality of host channel adapters, a plurality of hosts, and a subnet manager, the subnet manager running on one of the one or more switches and the plurality of host channel adapters. The subnet manager can be configured to determine that the plurality of hosts and the plurality of switches support a same set of capabilities. On such determination, the subnet manager can configure an SMA flag, the flag indicating that a condition can be set for each of the host channel adapter ports.

System and method for distribution of routes in a telecommunications network
11201813 · 2021-12-14 · ·

A traffic controller device for distributing or otherwise controlling the distribution of routing information may be included in a telecommunications network. The traffic controller may receive routing tables from a plurality of network devices, such as one or more provider edge devices of the network. The traffic controller, upon receiving the routing information from the provider edge devices, may generate a routing table associated with each device providing the routing information. The traffic controller may also provide updates to one or more of the networking devices associated with the controller. The traffic controller may alter or update, at the traffic controller, the routing table associated with the target provider edge device based on the network policy. The routing information in the routing table for that device and maintained by the traffic controller may be updated with a new route or new local preferred parameter value.

LOCK-FREE METHOD OF TRANSMITTING HIERARCHICAL COLLECTIONS THROUGH SHARED MEMORY

Systems and methods for creating a new entry in a hierarchical state data structure with object entries is disclosed. The method includes allocating a shared memory buffer for a new entry in a shared memory. A request to create the new entry for a child object in a hierarchical state data structure in the shared memory is received. The new entry is to span at least one shared memory buffer uniquely identifiable in a location of the shared memory. The child object is a logical representation of a state of a system. In response to a request for an allocation of a shared memory buffer within a region of the shared memory for the new entry, a location identifier corresponding to a location of a parent entry holding a parent object to the child object in the hierarchical state data structure of an allocated region is received. The child object is created in the shared memory buffer for the new entry, and the new entry is available for concurrent access by one or more readers of the shared memory.

SPLIT-BRAIN PREVENTION IN A HIGH AVAILABILITY SYSTEM DURING WORKLOAD MIGRATION
20210385164 · 2021-12-09 ·

In some embodiments, a method receives a control message from a second host. The control message includes a first address to use as a next hop to reach an active workload that has migrated to the second host from another host. The method reprograms a local route table to include a policy to send packets to check a liveness of the active workload with the next hop of the first address. A packet is sent from a standby workload to the active workload using the next hop of the first address to check the liveness of the active workload. The packet is encapsulated and sent between the first host and the second host using an overlay channel between a first endpoint of the overlay channel on the first host and a second endpoint of the channel on the second host.

PACKET FORWARDING ON NON-COHERENT PATHS
20220210048 · 2022-06-30 ·

A node in a network includes a memory to store information representing the topology of a network that includes the node. The node also includes a processor that determines one or more coherent as through the network to a destination by applying a distributed path algorithm to the information representing the topology. The processor also determines one or more non-coherent paths through the network to the destination. The node also includes a transceiver that selectively transmits a first packet along the coherent path or the non-coherent path to the destination. The memory stores information representing an address or identifier of the destination, one or more next-hop nodes for the coherent paths, and one or more ordered lists of links or nodes traversed by one or more non-coherent paths. The ordered lists are appended to packets transmitted along the non-coherent paths.

Data Transmission Control Method and Apparatus
20220200893 · 2022-06-23 ·

In a data transmission control method, one or more pieces of identification information are added to determine an interface resource object for forwarding a data packet on an interface of a network device. The added one or more pieces of identification information include one piece of global identification information. The global identification information may correspond to a network slice, and different network slices correspond to different values of global identification information. A global network identifier corresponds to one or more interface resource objects. One interface resource object may be occupied by one network slice alone, or one interface resource object may be jointly shared by a plurality of network slices.

Data Transmission Control Method and Apparatus
20220200893 · 2022-06-23 ·

In a data transmission control method, one or more pieces of identification information are added to determine an interface resource object for forwarding a data packet on an interface of a network device. The added one or more pieces of identification information include one piece of global identification information. The global identification information may correspond to a network slice, and different network slices correspond to different values of global identification information. A global network identifier corresponds to one or more interface resource objects. One interface resource object may be occupied by one network slice alone, or one interface resource object may be jointly shared by a plurality of network slices.

End of Train to Head of Train Communication Over a Train Control Network
20220201587 · 2022-06-23 ·

A wireless train control network is adapted for forwarding data between a remote radio in an EOT unit and remote radio at the head of train using the base stations of the wireless train control network. A base station's current table of base station radios and remote radios that it hears or has a connection is distributed to neighboring base stations by a routing information exchange application. Tables are sent to and received from the application using a messaging service of the wireless train control network. A base station builds from the tables of neighboring base stations a route to a remote radio to which it is not connected, and forwards wireless data packets received for it by transmitting it to another base station radio.

End of Train to Head of Train Communication Over a Train Control Network
20220201587 · 2022-06-23 ·

A wireless train control network is adapted for forwarding data between a remote radio in an EOT unit and remote radio at the head of train using the base stations of the wireless train control network. A base station's current table of base station radios and remote radios that it hears or has a connection is distributed to neighboring base stations by a routing information exchange application. Tables are sent to and received from the application using a messaging service of the wireless train control network. A base station builds from the tables of neighboring base stations a route to a remote radio to which it is not connected, and forwards wireless data packets received for it by transmitting it to another base station radio.

Switch with network services packet processing by service software instances

Virtual machine environments are provided in the switches that form a network, with the virtual machines executing network services previously performed by dedicated appliances. The virtual machines can be executed on a single multi-core processor in combination with normal switch functions or on dedicated services processor boards. Packet processors analyze incoming packets and add a services tag containing services entries to any packets. Each switch reviews the services tag and performs any network services resident on that switch. This allows services to be deployed at the optimal locations in the network. The network services may be deployed by use of drag and drop operations. A topology view is presented, along with network services that may be deployed. Services may be selected and dragged to a single switch or multiple switches. The management tool deploys the network services software, with virtual machines being instantiated on the switches as needed.