Abstract: A system for a distributed partitioned map reduce includes a plurality of nodes, a plurality of partitions, and a service node. The one or more partitions of the plurality of partitions are stored on a first node of the plurality of nodes. The service node is configured to receive a task from a client application system. The client application system receives a request to perform the task from a requestor. The client application system selects a service node to manage execution of the task. The client application system provides the service node the task. The service node is configured to provide partition task logic to the plurality of partitions. The partition task logic includes a partition task map reduce. The service node is configured to receive partition results from the plurality of partitions, execute a service node reduce to determine a service node result, and provide the service node result.

Abstract: A system includes an interface and a processor. The interface is configured to receive an indication that a change has occurred to partition data on a first node, wherein the partition data is stored on a partition on the first node. The processor is configured to: determine whether the change to the partition data causes a change to a predetermined partition result of a set of predetermined partition results stored by the partition; and in response to a determination that the change to partition data affects the predetermined partition result stored by the partition: determine a new value for the predetermined partition result; store the new value; and provide an indication to a service node that the new value for the predetermined partition result has been determined, wherein the service node is selected by a client application system to manage execution of a task.

Abstract: A system includes an interface and a processor. The interface is configured to receive an indication that a change has occurred to partition data on a first node, wherein the partition data is stored on a partition on the first node. The processor is configured to: determine whether the change to the partition data causes a change to a predetermined partition result of a set of predetermined partition results stored by the partition; and in response to a determination that the change to partition data affects the predetermined partition result stored by the partition: determine a new value for the predetermined partition result; store the new value; and provide an indication to a service node that the new value for the predetermined partition result has been determined, wherein the service node is selected by a client application system to manage execution of a task.

Abstract: A system for a distributed real time partitioned map reduce includes a plurality of nodes, a service node, and a plurality of partitions. The service node is selected by a client application system to manage execution of a task. One or more partitions of the plurality of partitions are stored on a first node of the plurality of nodes. A partition stored on the first node is configured to receive a request for a partition result from the service node; determine the partition result by querying a set of predetermined partition results stored by the partition; and provide the partition result to the service node.

Abstract: A system for performing a computation includes an interface and a processor. The interface is configured to receive an indication of the computation. The processor is configured to determine whether the computation is with respect to a computation version number. In response to a determination that the computation is with respect to a computation version number: 1) determine whether the system has been updated to at least the computation version number; and 2) in response to a determination that the system has been updated to at least the computation version number: a) determine a set of data values for the computation associated with the computation version number; b) perform a partition reduce operation on the set of data values to determine a partition result; and c) provide the partition result.

Abstract: A system and method can support resettable acknowledgements for synchronizing data between clusters in a distributed data grid. The system can use one or more unique identifiers (IDs) to support message passing between different clusters in the distributed data grid. A first cluster can receive a first replication message from a second cluster, wherein the replication message indicates that the replication message is from a new cluster. Then, the system can reset the first cluster to preserve idempotence in possessing one or more replication messages that are received from the second cluster, following the first replication message.

Abstract: A system for a distributed partitioned map reduce includes a plurality of nodes, a plurality of partitions, and a service node. The one or more partitions of the plurality of partitions are stored on a first node of the plurality of nodes. The service node is configured to receive a task from a client application system. The client application system receives a request to perform the task from a requestor. The client application system selects a service node to manage execution of the task. The client application system provides the service node the task. The service node is configured to provide partition task logic to the plurality of partitions. The partition task logic includes a partition task map reduce. The service node is configured to receive partition results from the plurality of partitions, execute a service node reduce to determine a service node result, and provide the service node result.

Abstract: An event distribution pattern is described for use with a distributed data grid. The grid can be comprised of a cluster of computer devices having a cache for storing data entries. An event distributor residing on at least one of those computer devices provides a domain for sending events to a desired end point destination and also provides the store and forward semantics for ensuring asynchronous delivery of those events. An event channel controller resides as an entry in the cache on at least one of computers in the cluster. This event channel controller receives the events defined by said application from the event distributor and provides the events to a set of event channels. Each event channel controller can include multiple event channel implementations for distributing the events to different destinations. The destinations can include local caches, remote caches, standard streams, files and JMS components.

Abstract: A system and method can support partition level journaling for synchronizing data between clusters in a distributed data grid. The system can associate a journal cache with one or more user caches in a local cluster, wherein said one or more user caches are split into a plurality of partitions. Furthermore, the system can capture one or more data changes that are applied to different partitions of said one or more user caches, and can store said one or more data changes in the journal cache that supports synchronization with remote clusters.

Abstract: A system and method can support failover during synchronization between autonomous clusters in a distributed data grid. The system allows a cluster member in a source cluster to take over as an owner of a partition in a source cluster, when another cluster member in the source cluster becomes unavailable. Then, a cluster member in the destination cluster can receive one or more replication messages from said cluster member in the source cluster, wherein said one or more replication messages include one or more data changes. Furthermore, the cluster member in the destination cluster may ignore said one or more replication messages, if said one or more replication messages have already been received and successfully processed in the destination cluster.

Abstract: A system and method can support parallel asynchronous synchronization between autonomous clusters in a distributed data grid. The system can track one or more data changes, which are applied on one or more user caches in a source cluster, at a partition level. Furthermore, one or more cluster members in the source cluster can send one or more replication messages to one or more destination clusters, wherein said one or more replication messages include the one or more data changes. Then, the one or more destination clusters can process the received one or more data changes.

Abstract: A system and method can handle storage events in a distributed data grid. The distributed data grid cluster includes a plurality of cluster nodes storing data partitions distributed throughout the cluster, each cluster node being responsible for a set of partitions. A service thread, executing on at least one of said cluster nodes in the distributed data grid, is responsible for handling one or more storage events. The service thread can use a worker thread to accomplish synchronous event handling without blocking the service thread.

Abstract: A server-side event model provides a general-purpose event framework which simplifies the server-side programming model in a distributed data grid storing data partitions distributed throughout a cluster of nodes. A system provides event interceptors which handle events associated with operations and maps the event interceptors to event dispatchers placed in the cluster. Advantageously, the system supports handling critical path events without the need for interactions from the client-side thereby avoiding unnecessary delays waiting for client responses. Additionally, the system can defer completion of an operation in the distributed data grid pending completion of event handling by an event interceptor. The system enables the data grid to employ more types of events and define different event interceptors for handling the events while avoiding client interaction overhead.

Abstract: A system and method can provide a server-side event model in a distributed data grid with a plurality of cluster nodes storing data partitions distributed throughout the cluster, each cluster node being responsible for a set of partitions. The system can map one or more event interceptors to an event dispatcher placed in the cluster. The one or more event interceptors can handle at least one event dispatched from the event dispatcher, wherein the at least one event is associated with an operation in the distributed data grid. The system can defer completion of the operation in the distributed data grid pending completion of the handling of the at least one event by said one or more event interceptors.

Abstract: A server-side event model provides a general-purpose event framework which simplifies the server-side programming model in a distributed data grid storing data partitions distributed throughout a cluster of nodes. A system provides event interceptors which handle events associated with operations and maps the event interceptors to event dispatchers placed in the cluster. Advantageously, the system supports handling critical path events without the need for interactions from the client-side thereby avoiding unnecessary delays waiting for client responses. Additionally, the system can defer completion of an operation in the distributed data grid pending completion of event handling by an event interceptor. The system enables the data grid to employ more types of events and define different event interceptors for handling the events while avoiding client interaction overhead.

Abstract: A processing pattern is described for dispatching and executing tasks in a distributed computing grid, such as a cluster network. The grid includes a plurality of computer nodes that store a set of data and perform operations on that data. The grid provides an interface that allows clients to submit tasks to the cluster for processing. The interface can be used to establish a session between the client and the cluster, which will be used to submit a task for processing by the plurality of computer nodes of the cluster. A dispatcher receives a submission of the task over the interface and routes the task to at least one node in the cluster that is designated to process the task. A task processor then processes the task on the designated node(s), generates a submission outcome and indicates to the client that the submission outcome is available.

Abstract: Push replication techniques are described for use in an in-memory data grid. When applications on a cluster perform insert, update or delete operations in the cache, a push replication provider asynchronously pushes updates from the source cluster to one or more remote destination clusters. The push replication provider includes a pluggable internal transport to send the updates to the destination cluster. This pluggable transport can be switched to employ a different communication service or protocol. A publishing transformer can chain multiple filters and apply filters on a stream of updates from source cluster to the destination cluster. A batch publisher can be used to receive batches multiple updates and replicate those batch to the destination cluster. XML based configuration can be provided to configure the push replication techniques on a cluster.

Abstract: A system and method can support partition level journaling for synchronizing data between clusters in a distributed data grid. The system can associate a journal cache with one or more user caches in a local cluster, wherein said one or more user caches are split into a plurality of partitions. Furthermore, the system can capture one or more data changes that are applied to different partitions of said one or more user caches, and can store said one or more data changes in the journal cache that supports synchronization with remote clusters.

Abstract: A system and method can support resettable acknowledgements for synchronizing data between clusters in a distributed data grid. The system can use one or more unique identifiers (IDs) to support message passing between different clusters in the distributed data grid. A first cluster can receive a first replication message from a second cluster, wherein the replication message indicates that the replication message is from a new cluster. Then, the system can reset the first cluster to preserve idempotence in possessing one or more replication messages that are received from the second cluster, following the first replication message.

Abstract: A system and method can support failover during synchronization between autonomous clusters in a distributed data grid. The system allows a cluster member in a source cluster to take over as an owner of a partition in a source cluster, when another cluster member in the source cluster becomes unavailable. Then, a cluster member in the destination cluster can receive one or more replication messages from said cluster member in the source cluster, wherein said one or more replication messages include one or more data changes. Furthermore, the cluster member in the destination cluster may ignore said one or more replication messages, if said one or more replication messages have already been received and successfully processed in the destination cluster.