Abstract: A system and method for partitioned snapshot creation of caches in a distributed data grid is provided. The system and method enables a snapshot to be created in a running system without quiescing a cache service. Moreover for each particular partition, execution of read/write requests are not blocked during the period that a snapshot creation task is being performed for the particular partition. The cache service thread continues to execute read requests for all partitions with write requests for the partition under snapshot experiencing delayed response. The system and method reduces the period of time for which partitions are unavailable during a snapshot process and increases the availability of cache services provided by a distributed data grid compared to prior snapshot systems.

Abstract: In accordance with an embodiment, the system supports use of an in-memory data grid or other distributed memory environment, for example Oracle Coherence. A partition provides a runtime and administrative subdivision or slice of an application server domain. An application can be deployed to a particular partition, or otherwise associated with a particular domain partition name. The domain partition name can be used by the data grid to enable a separation of data between different partitions or between tenants associated with those partitions. In some embodiments, one or more data grid services, for example caches and clustered services, can be shared across multiple partitions. Alternatively, the data grid can provide read-shared/write-specific access to data grid services, in which multiple partitions can share an initial set of data, but their subsequent modifications to that data are then isolated from each other.

Abstract: A system and method for supporting an association-aware executor service in a distributed computing environment comprising. The system can provide an executor service associated with a thread pool, the thread pool containing a plurality of threads. The system can receive, at the executor service, a plurality of work requests, each work request being associated with a key of a plurality of keys. The system can define groups of work requests, each group of work requests comprising one or more work requests having a same key. The system can queue, on the plurality of threads in the thread pool, the groups of work requests, each group of work requests being queued on a different thread. All work requests in a particular group are executed on the same thread.

Abstract: A system and method can support recovery of persisted data from persistent storage of a distributed data grid, and provide persistent store versioning and integrity. A coordinator in the distributed data grid can receive a plurality of identifiers from one or more members of the distributed data grid, wherein each said identifier is associated with a persisted partition in a persistent storage for the distributed data grid. Then, the coordinator can select an identifier for each partition, wherein each selected identifier is associated with a most recent valid version of a partition. Furthermore, the coordinator can determine an active member in the distributed data grid that is responsible for recovering said partition from a persisted partition associated with the selected identifier.

Abstract: A system and method supports key management in a distributed computing environment such as a distributed data grid. A binary radix tree is used to intern a plurality of binary keys. The binary radix tree is serialized to a byte buffer and a view of the binary is created. A byte sequence interface to the nodes of the serialized binary radix tree allows use of references which refer to positions in the serialized binary radix tree instead of requiring byte array copes of the interned keys. Use of references into the byte array in place of a byte array copies of interned keys reduces the memory overhead associated with referrers such as reverse indices which make reference to values associated with the plurality of binary keys. The reduction in memory overhead enhances performance and capabilities of a distributed computing environment such as a distributed data grid.

Abstract: A system and method for automatic recovery of actively persisted data in a distributed data grid. A dynamic active recovery quorum function determines the number of cluster storage members that must be available before recovery starts. The use of the dynamic active recovery quorum allows time for a cluster to start and ensures that partitions can be recovered gracefully without overloading too few storage members. The dynamic active recovery quorum function automatically configures the recovery quorum based on a predefined algorithm and data collected about cluster membership during cluster operation prior to the catastrophic failure or shut down for planned maintenance.

Abstract: A system and method can support persistence in a distributed data grid. A plurality of members in the distributed data grid can persist a plurality of partitions associated with one or more cache services in persistent storage. Furthermore, a coordinator, which may be a member in the distributed data grid, can synchronize a view of partition ownership among the plurality of members in the distributed data grid, and form a distributed consensus on which partition can be recovered from which member in the distributed data grid.

Abstract: A system and method for supporting persistent store archival and retrieval in a distributed computing environment. The system provides a central portal operative to initiate the archiving (or retrieval) which is executed in parallel across all members with access to persisted stores, either being sent or gathered from an archive repository. The system and method can include an archive coordinator associated with an in-memory data grid. The archive coordinator receives an instruction to store a snapshot of a current state of the in-memory data grid, the instruction including a storage location, the storage location being a destination selected from the group consisting of a local disk and a shared disk. The system can archive the snapshot of the current state of the in-memory data grid at the storage location.

Abstract: A system and method for providing a message bus component or version thereof (referred to herein as an implementation), and a messaging application program interface, for use in an enterprise data center, middleware machine system, or similar environment that includes a plurality of processor nodes together with a high-performance communication fabric (or communication mechanism) such as InfiniBand. In accordance with an embodiment, the messaging application program interface enables features such as asynchronous messaging, low latency, and high data throughput, and supports the use of in-memory data grid, application server, and other middleware components.

Abstract: A system and method for supporting a scalable thread pool in a multi-threaded processing environments such as a distributed data grid. A work distribution system utilizes a collection of association piles to hold elements communicated between a service thread and multiple worker threads. Worker threads associated with the association piles poll elements in parallel. Polled elements are not released until returned from the worker thread. First in first out ordering of operations is maintained with respect to related elements by ensuring related elements are held in the same association pile and preventing polling of related elements until any previously polled and related elements have been released. By partitioning the elements across multiple association piles while ensuring proper ordering of operations with respect to related elements the scalable thread pool enables the use of large thread pools with reduced contention compared to a conventional single producer multiple consumer queue.

Abstract: Systems, methods, and other embodiments are disclosed that use constraint programming to dynamically distribute cache throughout a data grid. In one embodiment, modeling logic is configured to generate a constraint programming model based at least in part on a set of constraints that limits assignment of a plurality of data partitions to a plurality of virtual machines hosted on a plurality of physical machines in a data grid. Solver logic is configured to generate at least one solution for assigning the plurality of data partitions to the plurality of virtual machines by operating on the constraint programming model using constraint programming techniques.

Abstract: A system and method can support recovery of persisted data from persistent storage of a distributed data grid, and provide persistent store versioning and integrity. A coordinator in the distributed data grid can receive a plurality of identifiers from one or more members of the distributed data grid, wherein each said identifier is associated with a persisted partition in a persistent storage for the distributed data grid. Then, the coordinator can select an identifier for each partition, wherein each selected identifier is associated with a most recent valid version of a partition. Furthermore, the coordinator can determine an active member in the distributed data grid that is responsible for recovering said partition from a persisted partition associated with the selected identifier.

Abstract: A system and method for automatic recovery of actively persisted data in a distributed data grid. A dynamic active recovery quorum function determines the number of cluster storage members that must be available before recovery starts. The use of the dynamic active recovery quorum allows time for a cluster to start and ensures that partitions can be recovered gracefully without overloading too few storage members. The dynamic active recovery quorum function automatically configures the recovery quorum based on a predefined algorithm and data collected about cluster membership during cluster operation prior to the catastrophic failure or shut down for planned maintenance.

Abstract: A system and method can support persistence in a distributed data grid, such as persistent store versioning and integrity. A resolver in the distributed data grid can receive a plurality of identifiers from one or more members of the distributed data grid, wherein each said identifier is associated with a persisted partition in a persistent storage for the distributed data grid. Then, the resolver can select an identifier for each partition, wherein each selected identifier is associated with a most recent valid version of a partition. Furthermore, the resolver can determine a member in the distributed data grid that is responsible for recovering said partition from a persisted partition associated with the selected identifier.

Abstract: A system and method for supporting multi-version remote function execution control in a distributed computing environment is provided. Remote functions are provided with a version identifier which uniquely identifies the version of the remote function. The version identifier can be a digest of the class definition of the remote function. The version identifier is used by an executor and/or class loader to ensure execution of correct class versions when on a node in a distributed computing environment. The definitive identification of class versions also provides for conditional transmission of class definition thereby reducing communication overhead for distribution of remote functions.

Abstract: A system and method for partitioned snapshot creation of caches in a distributed data grid is provided. The system and method enables a snapshot to be created in a running system without quiescing a cache service. Moreover for each particular partition, execution of read/write requests are not blocked during the period that a snapshot creation task is being performed for the particular partition. The cache service thread continues to execute read requests for all partitions with write requests for the partition under snapshot experiencing delayed response. The system and method reduces the period of time for which partitions are unavailable during a snapshot process and increases the availability of cache services provided by a distributed data grid compared to prior snapshot systems.

Abstract: A system and method can support metadata compression in a distributed data grid. The system can store a plurality of keys in compact data structure (such as a radix tree) in a heap, wherein each said key is associated with an entry in a journal off-heap. Furthermore, the system can look up the tree for a key, wherein the key is associated with a journal ticket that represents a virtual address of an entry in the journal. Then, the system can use the journal ticket to manage the entry in the journal that is associated with said key.

Abstract: A system and method for supporting a scalable thread pool in a multi-threaded processing environments such as a distributed data grid. A work distribution system utilizes a collection of association piles to hold elements communicated between a service thread and multiple worker threads. Worker threads associated with the association piles poll elements in parallel. Polled elements are not released until returned from the worker thread. First in first out ordering of operations is maintained with respect to related elements by ensuring related elements are held in the same association pile and preventing polling of related elements until any previously polled and related elements have been released. By partitioning the elements across multiple association piles while ensuring proper ordering of operations with respect to related elements the scalable thread pool enables the use of large thread pools with reduced contention compared to a conventional single producer multiple consumer queue.

Abstract: A system and method supports key management in a distributed computing environment such as a distributed data grid. A binary radix tree is used to intern a plurality of binary keys. The binary radix tree is serialized to a byte buffer and a view of the binary is created. A byte sequence interface to the nodes of the serialized binary radix tree allows use of references which refer to positions in the serialized binary radix tree instead of requiring byte array copes of the interned keys. Use of references into the byte array in place of a byte array copies of interned keys reduces the memory overhead associated with referrers such as reverse indices which make reference to values associated with the plurality of binary keys. The reduction in memory overhead enhances performance and capabilities of a distributed computing environment such as a distributed data grid.

Abstract: A system and method support a reference store in a distributed computing environment such as a distributed data grid. The system associates a ticket with the reference store, wherein the reference store contains a plurality of references. Furthermore, the system uses the ticket to expose the reference store to one or more consumers in the distributed computing environment. The reference store type is selected in response to the number of references required to be stored and access overhead. Each reference store can be inflated or deflated according to the number of references it contains. Selection of different reference store types allows for reduced memory overhead while still providing acceptable reference retrieval times. The reduction in memory overhead enhances performance and capabilities of a distributed computing environment such as a distributed data grid.