Oracle International Corporation

Oracle America, Inc.

Bjørn Dag Johnsen

Ernst Gunnar Gran

Line Holen

Bartosz Bogdanski

Feroz Zahid

Dag Georg Moxnes

Evangelos Tasoulas

Ajoy Siddabathuni

Avneesh Pant

Arvind Srinivasan

Shimon Muller

Brian Manula

Andreas V Bechtolsheim

Martin Paul Mayhead

Sumanta Kumar Chatterjee

Ola Tørudbakken

Richard P Mousseau

Jean De Lavarene

Predrag Hodoba

Harald Høeg

Vadim Makhervaks

Kant C Patel

Feroz Alam Khan

Amarnath Jolad

David Brean

Bhaskar Mathur

Prabhunandan Narasimhamurthy

Tor Skeie

Sudeep Vatsanath Reguna

Pramod Venkatesh

Kurt Tjemsland

Stephen McKinty

Prabhunandan B Narasimhamurthy

Harald HØEG

Systems and methods for supporting target groups for congestion control in a private fabric in a high performance computing environment. An exemplary method can provide, at one or more microprocessors, a first subnet, the first subnet comprising a plurality of switches, a plurality of host channel adapters, and a plurality of end nodes, including a plurality of virtual machines. The method can define a target group on one of an inter-switch link or at a port of a switch of the plurality of switches, wherein the target group defines a bandwidth limit on the at least one of an inter-switch link between two switches of the plurality of switches or at a port of a switch of the plurality of switches. The method can provide a target group repository stored in a memory of the host channel adapter where the defined target group in the target group repository is recorded.

System and method for supporting target groups for congestion control in a private fabric in a high performance computing environment

Systems and methods for supporting heterogeneous and asymmetric dual rail fabric configurations in a high performance computing environment. A method can provide, comprising at one or more computers each including one or more microprocessors, a plurality hosts, each of the plurality of hosts comprising at least one dual port adapter, a private fabric, the private fabric comprising two or more switches, and a public fabric, the public fabric comprising a cloud fabric. A workload can be provisioned at a host of the plurality of hosts. A placement policy can be assigned to the provisioned workload. Then, network traffic between peer nodes of the provisioned workload can be assigned to one or more of the private fabric and the public fabric in accordance with the placement policy.

System and method for supporting heterogeneous and asymmetric dual rail fabric configurations in a high performance computing environment

A system and method for supporting load balancing in a multi-tenant cluster environment, in accordance with an embodiment. One or more tenants can be supported and each associated with a partition, which are each in turn associated with one or more end nodes. The method can provide a plurality of switches, the plurality of switches comprising a plurality of leaf switches and at least one switch at another level, wherein each of the plurality of switches comprise at least one port. The method can assign each node a weight parameter, and based upon this parameter, the method can route the plurality of end nodes within the multi-tenant cluster environment, wherein the routing attempts to preserve partition isolation.

System and method for efficient network isolation and load balancing in a multi-tenant cluster environment

System and method for supporting scalable bitmap based P_Key table in a high performance computing environment. A method can provide, at least one subnet comprising one or more switches, a plurality of host channel adapters, and a plurality of end nodes. The method can associate the plurality of end nodes with at least one of a plurality of partitions, wherein each of the plurality of partitions are associated with a P_Key value. The method can associate each of the one or more switches with a bitmap based P_Key table of a plurality of bitmap based P_Key tables. The method can associate each of the host channel adapters with a bitmap based P_Key table of the plurality of bitmap based P_Key tables.

System and method for supporting scalable bit map based P_Key table in a high performance computing environment

Methods and systems for supporting efficient load balancing among a plurality of switches and a plurality of end nodes arranged in a tree topology in a network environment. The methods and systems can sort the plurality of end nodes, wherein the plurality of end nodes are sorted in a decreasing order of a receive weight. The method and system may further route, in the decreasing order of receive weights, the plurality of end nodes, wherein the routing comprises selecting at least one down-going port and at least one up-going port. Further, the method and system can increase an accumulated downward weight on each selected down-going port by the receive weight of the routed end node, and increase an accumulated upward weight on each selected up-going port by the receive weight of the routed end node.

System and method for supporting efficient load-balancing in a high performance computing (HPC) environment

Systems and methods for using queue pair 1 (QP1) for receiving multicast based announcements in multiple partitions in a high performance computing. In accordance with an embodiment, by extending the scope of QP1 to also include receiving and sending multicast packets in any partition defined for the port, it is possible to implement generic MC based announcement and discovery without requiring the complexity of unique QPs for individual partitions, nor any update of QP configuration as a consequence of change of partition membership.

System and method to use queue pair 1 for receiving multicast based announcements in multiple partitions in a high performance computing environment

Systems and methods for providing multicast group (MCG) membership relative to partition membership in a high performance computing environment. In allowing a subnet manager of a local subnet to be instructed that all ports that are members of the relevant partition should be set up as members for a specific multicast group, the SM can perform a more efficient multicast-routing process. It is also possible to limit the IB client interaction with subnet administration conventionally required to handle join and leave operations. Additionally, subnet manager overhead can be reduced by creating a spanning tree for the routing of multicast packets that includes each of the partition members added to the multicast group, instead of creating a spanning tree after each multicast group join request is received, as conventionally required.

System and method to provide multicast group membership defined relative to partition membership in a high performance computing environment

Systems and methods for multicast send duplication instead of replication in a high performance computing environment. A method can provide a plurality of switches, a plurality of hosts, the plurality of hosts being interconnected via the plurality of switches, wherein a host of the plurality of hosts comprises a multicast sender node, the sender node comprising a system image generation module and a current message sequence module. The method can organize the plurality of switches into two rails, the two or more rails providing redundant connectivity between the plurality of hosts. The method can send two or more duplicate multicast packets on different rails. Upon a receiving node receiving at least two versions of the same multicast packet, only one will be delivered to the communication stack/clients above the layer that handles the encapsulation header.

System and method for a multicast send duplication instead of replication in a high performance computing environment

Systems and methods are provided for supporting efficient reconfiguration of an interconnection network having a pre-existing routing. An exemplary method can provide a plurality of switches, a plurality of end nodes, and one or more subnet managers, including a master subnet manager. The method can calculate, via the master subnet manager, a first set of one or more leaf-switch to leaf-switch multipaths. The method can store this first set of one or more leaf-switch to leaf-switch multipaths at a metabase. The method can detect a reconfiguration triggering event, and call a new routing for the interconnection network. Finally, the method can reconfigure the network according to the new routing for the interconnection network.

System and method for efficient network reconfiguration in fat-trees

Systems and methods for supporting efficient virtualization in a lossless interconnection network. An exemplary method can provide, one or more switches, including at least a leaf switch, a plurality of host channel adapters, wherein each of the host channel adapters comprise at least one virtual function, at least one virtual switch, and at least one physical function, a plurality of hypervisors, and a plurality of virtual machines, wherein each of the plurality of virtual machines are associated with at least one virtual function. The method can arrange the plurality of host channel adapters with one or more of a virtual switch with prepopulated local identifiers (LIDs) architecture or a virtual switch with dynamic LID assignment architecture. The method can assign each virtual switch with a LID. The method can calculate one or more linear forwarding tables based at least upon the LIDs assigned to each of the virtual switches.

System and method for efficient virtualization in lossless interconnection networks

Systems and methods for using InfiniBand routing algorithms for Ethernet fabrics in a high performance computing environment. The method can provide, at a computer comprising one or more microprocessors, a plurality of switches, a plurality of hosts, a topology provider (TP) module, a routing engine (RE) module, and a switch initializer (SI) module. The method can perform a discovery sweep, by the TP, of the plurality of hosts and the plurality of switches and assigns an address to each of the plurality of hosts and the plurality of switches. The method can calculate, by the routing engine, a routing map, based upon a routing scheme, for the plurality of hosts and the plurality of switches, the routing map comprising a plurality of forwarding tables. The method can configure, each of the plurality of switches with a forwarding table of the plurality of forwarding tables calculated by the routing engine.

System and method for using infiniband routing algorithms for ethernet fabrics in a high performance computing environment

System and method for using multiple global identification subnet prefix values in a network switch environment in a high performance computing environment. A packet is received from a network fabric by a first Host Channel Adapter (HCA). The packet has a header portion including a destination subnet prefix identifying a destination subnet of the network fabric. The network HCA is allowed to receive the first packet from a port of the network HCA by selectively determining a logical state of a flag and, selectively in accordance with a predetermined logical state of the flag, ignoring the destination subnet prefix identifying the destination subnet of the network fabric.

System and method for allowing multiple global identifier (GID) subnet prefix values concurrently for incoming packet processing in a high performance computing environment

Systems and methods for dynamically assigning membership in a data partition to an end-port of a requesting host channel adapter. An exemplary embodiment can provide a subnet manager configured to operate within a subnet of a network fabric. The subnet can include a plurality of nodes, and the plurality of nodes can include at least one switch and a plurality of end-nodes, where the subnet manager executes on one of the plurality of nodes. A host channel adapter of a node in the subnet can request membership for an end-port of the host channel adapter. In response to the request, the subnet manager can request data from the data store to confirm that the end-port is a member of an admin partition and that the admin partition is associated with the data partition in which membership was requested.

System and method for supporting on-demand setup of local host channel adapter port partition membership in a high-performance computing environment

System and method for supporting configurable legacy P_Key table abstraction using a bitmap based hardware implementation in a high performance computing environment. A mapping table in DRAM can be provided through the use of a software based SMA that implements the mapping table. With this mapping table, it is possible to provide a legacy compliant view of a bit map based P_Key table. Such a legacy compliant view can be called a virtual P_Key table, or a configurable legacy P_Key table abstraction.

System and method for supporting configurable legacy P_Key table abstraction using a bitmap based hardware implementation in a high performance computing environment

Growing community of inventors

Oslo, Norway

Bjørn Dag Johnsen