Abstract: Various components are provided to manage a clustered environment. These components include a System Registry that provides a global data storage; a Configuration manager that stores data locally on nodes of the clustered environment and globally within the System Registry; a Liveness component to provide status of communications paths of the cluster; a Group Services component that provides services to one or more other components of the clustered environment; and a Resource Management component that communicates with one or more resource controllers of the clustered environment. Each of the components of the clustered environment has one or more data and/or functional dependencies on one or more other components of the environment. However, relationships between the components are created such that the data and functional dependencies form an acyclic graph (i.e., a cycle of dependency relationships is avoided).

Abstract: The management and use of replicated distributed transactions is facilitated. A distributed synchronous transaction system protocol is provided to manage the replication of distributed transactions for client application instances. The distributed synchronous transaction system allows transactions to be replicated without having the client application instances be aware of other instances to receive the transaction. Further, if a failure occurs during processing of a distributed replicated transaction, the distributed synchronous transaction system manages the recovery of the failure.

Abstract: The management and use of replicated distributed transactions is facilitated. A distributed synchronous transaction system protocol is provided to manage the replication of distributed transactions for client application instances. The distributed synchronous transaction system allows transactions to be replicated without having the client application instances be aware of other instances to receive the transaction. Further, if a failure occurs during processing of a distributed replicated transaction, the distributed synchronous transaction system manages the recovery of the failure.

Abstract: Various components are provided to manage a clustered environment. These components include a System Registry that provides a global data storage; a Configuration manager that stores data locally on nodes of the clustered environment and globally within the System Registry; a Liveness component to provide status of communications paths of the cluster; a Group Services component that provides services to one or more other components of the clustered environment; and a Resource Management component that communicates with one or more resource controllers of the clustered environment. Each of the components of the clustered environment has one or more data and/or functional dependencies on one or more other components of the environment. However, relationships between the components are created such that the data and functional dependencies form an acyclic graph (i.e., a cycle of dependency relationships is avoided).

Abstract: Various components are provided to manage a clustered environment. These components include a System Registry that provides a global data storage; a Configuration manager that stores data locally on nodes of the clustered environment and globally within the System Registry; a Liveness component to provide status of communications paths of the cluster; a Group Services component that provides services to one or more other components of the clustered environment; and a Resource Management component that communicates with one or more resource controllers of the clustered environment. Each of the components of the clustered environment has one or more data and/or functional dependencies on one or more other components of the environment. However, relationships between the components are created such that the data and functional dependencies form an acyclic graph (i.e., a cycle of dependency relationships is avoided).

Abstract: A method for building a hierarchical multicast tree which is centered around a specific node in an Internet Protocol (IP) communications network. The method on a subnetwork comprising dynamically electing a subnetwork leader node for each subnetwork using multicast communications confined to the subnetwork. Receiving a configuration file containing a list of all the network addresses of the nodes in a network. Receiving a number of permissible connections each subnetwork leader node in the network is permitted with other subnetwork leader nodes. And establishing a multicast connection between each subnetwork leader node as identified in the configuration file so that there is a multicast connection path from each subnetwork leader node for each subnetwork and a subnetwork containing a network leader node. In another embodiment, a system and computer readable medium is disclosed to carry out the above method.

Abstract: A facility is provided for managing a service connection between a client process having a single threaded library and a server process. The facility includes monitoring activity of a client code of the client process by the client library, and commensurate therewith monitoring activity of the client library across a service connection to the server process, wherein activity of the client library on the service connection is indicative of activity of the client code. The service connection between the client process and the server process is terminated if a message is not received at the server process from the single threaded client library within a defined tolerance interval. Upon termination of the service connection, any locked client resource is recovered at the server process.

Abstract: A method and apparatus for managing communications in a distributed computing system wherein a plurality of computers are interconnected with a communications network. At least a portion of the network is established as a subnetwork with at least one node attached to the subnetwork. The node in the subnetwork multicast a verification message over the subnetwork in which it is attached. A subnetwork leader for each subnetwork is identified and gathers the verification message sent from each node in the subnetwork. The subnetwork leader assembles each verification received into a subnetwork list. The subnetwork list is sent a node identified as the network leader. The network leader assembles each subnetwork list received into a master list and sends this master list out to the subnetwork leaders. In turn, the subnetwork leaders for each subnetwork multicast the master list out to each node. In one embodiment, the communications between each subnetwork leader and the network leader is over multicast.

Abstract: A method for maintaining the reachability of IP multicast communications across a communications network with one or more subnetworks wherein each subnetwork comprises at least one node coupled thereto and a node identified as a subnetwork leader and the communications network comprises one node identified as a network leader. The method comprising the steps of: receiving a host address list containing a list of all the network addresses of the, nodes in a network including at least two subnetworks, and a node in each subnetwork identified as a subnetwork leader; using the host address list for determining which subnetworks the subnetwork leaders are associated therewith. The reachability of at least one subnetwork leader in the network is periodically monitored.

Abstract: Various components are provided to manage a clustered environment. These components include a System Registry that provides a global data storage; a Configuration manager that stores data locally on nodes of the clustered environment and globally within the System Registry; a Liveness component to provide status of communications paths of the cluster; a Group Services component that provides services to one or more other components of the clustered environment; and a Resource Management component that communicates with one or more resource controllers of the clustered environment. Each of the components of the clustered environment has one or more data and/or functional dependencies on one or more other components of the environment. However, relationships between the components are created such that the data and functional dependencies form an acyclic graph (i.e., a cycle of dependency relationships is avoided).

Abstract: At least a portion of a table stored in a global data repository is selected to be accessed and modified. The selected portion is stored in a local table in local memory of a node of a client-server environment. The local table is modified, and then at least a portion of the modified local table is merged with the global table. The merger is performed without requiring any user locking of the global table.

Abstract: Dynamic reconfiguration of a quorum group of processors and recovery procedure therefore are provided for a shared nothing distributed computing system. Dynamic reconfiguration proceeds notwithstanding unavailability of at least one processor of the quorum group of processors assuming that a quorum of the remaining processors exists. Recovery processing is implementing by the group of processors so that the at least one processor which was unavailable during the dynamic reconfiguration of the group is able to obtain current state information once becoming active. Each processor of the group of processors includes an incarnation number and a list of member processors which participated in a commit process resulting in its incarnation number. The recovery processing includes exchanging the processors' incarnation numbers and lists of processors for propagation of the current state of the quorum group of processors to the at least one processor now becoming available.

Abstract: Dynamic reconfiguration of a quorum group of processors and recovery procedure therefore are provided for a shared nothing distributed computing system. Dynamic reconfiguration proceeds notwithstanding unavailability of at least one processor of the quorum group of processors assuming that a quorum of the remaining processors exists. Recovery processing is implementing by the group of processors so that the at least one processor which was unavailable during the dynamic reconfiguration of the group is able to obtain current state information once becoming active. Each processor of the group of processors includes an incarnation number and a list of member processors which participated in a commit process resulting in its incarnation number. The recovery processing includes exchanging the processors' incarnation numbers and lists of processors for propagation of the current state of the quorum group of processors to the at least one processor now becoming available.

Abstract: Methods and arrangements for facilitating notification among at least two nodes in a distributed network, involving the designation of one of the nodes as a publisher node, the designation of at least one other of the nodes as at least one subscriber node, and the propagation of a transmission from the publisher node to the at least one subscriber node via at least one link. The propagation is undertaken via only one distinct transmission along any single link.

Abstract: Methods and arrangements for monitoring at least one interconnection between at least two nodes in a distributed network. At least one subscriber node is prompted to ascertain the integrity of an interconnection with at least one parent node.

Abstract: Methods and arrangements for establishing group collaboration between different distributed networks. At least two publisher nodes are prompted to generate individual distribution trees associated with each publisher node, wherein each individual distribution tree includes at least one subscriber node.

Abstract: Methods and arrangements for facilitating the further development of a distribution tree among at least three nodes in a distributed network. A path is ascertained between a publisher node and a joining subscriber node, and each path between the publisher node and each existing subscriber node is also ascertained. These paths are compared and, on the basis of the comparison, the subscriber node is established as a child of another node.

Abstract: Methods and arrangements for facilitating the further development of a distribution tree among at least three nodes in a distributed network. A network performance measurement associated with the propagation of a message between the publisher node and the joining subscriber node is ascertained, as well as each network performance measurement associated with the propagation of messages between the publisher node and each existing subscriber node. The network performance measurement between the publisher node and the joining subscriber node is compared with each network performance measurement between the publisher node and each existing subscriber node, and a joining subscriber node is established as a child of another node based on the comparison of network performance measurements.

Abstract: Methods and arrangements for propagating a data stream among a plurality of nodes in a distributed network at different rates. A first group of at least one subscriber node receives a data stream from a publisher node at a first rate, at least one additional group of at least one subscriber node receives a data stream from the publisher node at a second rate. For each of a plurality of frames in the data stream, it is ascertained as to which of the groups of at least one subscriber node are to receive each frame in the data stream. A single multicast transmission of each frame in the data stream is then propagated.

Abstract: Methods and arrangements for facilitating subscription among at least two nodes in a distributed network, involving the designation of one of the nodes as a publisher node, the designation of one of the nodes as a subscriber node, and the recordation of a path between the subscriber node and the publisher node. The path includes at least one link between the subscriber node and the publisher node, and the recordation involves recording each distinct link in the path between the subscriber node and the publisher node.