Abstract: A network switch holds a routing table and a network topology table so that when a link failure is detected at the network switch, the network switch may independently reroute a packet intended for that failed link using the network topology table. This processing can be performed in the data plane at a speed that can eliminate dropped packets. Intercommunication with a central controller is not required and intercommunication with other network switches may be accomplished through data plane communication by embedding the link failure information in the affected packet.

Abstract: A network switch holds a routing table and a network topology table so that when a link failure is detected at the network switch, the network switch may independently reroute a packet intended for that failed link using the network topology table. This processing can be performed in the data plane at a speed that can eliminate dropped packets. Intercommunication with a central controller is not required and intercommunication with other network switches may be accomplished through data plane communication by embedding the link failure information in the affected packet.

Abstract: Aspects of the present invention provide high-performance indexing for data-intensive systems in which “slicing” is used to organize indexing data on an SSD such that related entries are located together. Slicing enables combining multiple reads into a single “slice read” of related items, offering high read performance. Small in-memory indexes, such as hash tables, bloom filters or LSH tables, may be used as buffers for insert operations to resolve slow random writes on the SSD. When full, these buffers are written to the SSD. The internal architecture of the SSD may also be leveraged to achieve higher performance via parallelism. Such parallelism may occur at the channel-level, the package-level, the die-level and/or the plane-level. Consequently, memory and compute resources are freed for use by higher layer applications, and better performance may be achieved.

Abstract: Aspects of the present invention provide high-performance indexing for data-intensive systems in which “slicing” is used to organize indexing data on an SSD such that related entries are located together. Slicing enables combining multiple reads into a single “slice read” of related items, offering high read performance. Small in-memory indexes, such as hash tables, bloom filters or LSH tables, may be used as buffers for insert operations to resolve slow random writes on the SSD. When full, these buffers are written to the SSD. The internal architecture of the SSD may also be leveraged to achieve higher performance via parallelism. Such parallelism may occur at the channel-level, the package-level, the die-level and/or the plane-level. Consequently, memory and compute resources are freed for use by higher layer applications, and better performance may be achieved.