Red Hat, Inc.

Mircea Markus

William Rosenquist Burns

Manik Surtani

A node including a memory to store data of the node and a processor coupled to the memory. The processor can receive, from a listener in a data grid system, a filter defined by search criteria of a search query. The processor can also communicate, to the listener, data from the memory that is filtered using the filter. The processor can further identify changes to the filtered data. The processor can further record, into a queue, the changes to the filtered data in the memory after the filtered data is communicated to the listener. The processor can further communicate, to the listener, the queue of changes to the filtered data.

Registering data modification listener in a data-grid

A method of communicating data in a node cluster of a data grid is described. The method includes receiving, at a listener of a first node, data from a second node that is filtered using the filter during a search query of a node cluster. The method further includes determining, at the listener, that a third node has joined the node cluster during the search query. The method further includes communicating the filter the third node joining the node cluster in response to the third node joining the cluster.

Non-blocking listener registration in the presence of data grid nodes joining the cluster

The method including, receiving a transfer command at a transfer coordinator node of a first node cluster at a first site to initiate a transfer of data from the first node cluster to a second node cluster at a second site. The method further including causing a status of the second site to be switched from an inactive status to an active status at the nodes of the first node cluster. The method further including initiating a transfer of the data from the first node cluster to the second node cluster. The method further including determining that the second node cluster has the active status at the nodes of the first node cluster and causing the data transaction request to be transferred from the nodes at the first node cluster to the second node cluster during the transfer of the data.

Transferring data between sites

A processing device to receive, from a second node in the data grid system, a first filter. The processing device may detect a failure of a third node of the data grid system. The processing device may determine that the backup data stored at the first node matches the first filter. The processing device may send, to the second node, a duplicate data notification indicating that the backup data comprises, at least in part, first data duplicative to second data communicated to the second node from the third node.

Fault tolerant listener registration in the presence of node crashes in a data grid

A method of communicating data in a node cluster of a data grid. The method includes receiving, at a listener of a first node, data from a second node that is filtered using the filter during a search query of a node cluster. The method further includes determining, at the listener, that a third node has joined the node cluster during the search query. The method further includes communicating the filter the third node joining the node cluster in response to the third node joining the cluster. The method further includes receiving memory entry data from the third node. The method further includes determining, at the listener, search results using the filtered data and queued data from the second node and the memory entry data from the from the third node.

A processing device to perform operations comprising receive, from a listener of a second node in a data grid system, a filter defined by search criteria of a search query. The operations can include determine, at the first node, that a third node in the data grid has crashed. The operations can further include iterate over backup data of the third node that is stored at a memory of the first node to determine the backup data that matches the filter. The operations can further include communicate, to the listener, the backup data that matches the filter.

A node a data grid receives a prepare request identifying data to lock for a first transaction. The prepare request indicates a locking order that is different from a locking order indicated by a prior prepare request of a second transaction using the same data. The node identifies keys that correspond to the data. The keys are co-located on the node. The node ranks the keys to define an order for acquiring locks for the data based on key identifiers that correspond to the keys. The defined order matches a locking order used by the second transaction. The node acquires locks for the data using the defined order.

Lock reordering for optimistic locking of data on a single node to avoid transaction deadlock

A first process executing in a computer system in a data grid receives a request to perform at least one transaction operation of a transaction based on remote transaction data of at least one other process in the data grid. The at least one other process is capable to perform a prepare operation for a transaction. The first process identifies a local copy of the remote transaction data in a local data structure and performs the at least one transaction operation using the local copy of the remote transaction data without acquiring a lock on the remote transaction data.

Supporting transactions in distributed environments using a local copy of remote transaction data and optimistic locking

A transaction originator node identifies multiple data elements distributed at multiple enlisted nodes to lock for a transaction managed by the transaction originator node. The transaction originator node determines which of the enlisted nodes is a first enlisted node in a lock order for the transaction and sends an update request to the first enlisted node in the lock order to lock a data element residing at the first enlisted node. The transaction originator node sends update requests to remaining enlisted nodes in the lock order to cache the update requests until the remaining enlisted nodes receive a message to perform a lock.

Incremental optimistic locking of data distributed on multiple nodes to avoid transaction deadlock

A client computing system identifies a start of a multi-operational transaction pertaining to access of data stored in caches being managed by nodes residing in Java Virtual Machines in an in-memory data grid. The client computing system stores transaction context data indicating the start of the multi-operational transaction and identifies an application request to perform an operation pertaining to the multi-operational transaction. The application request is from an application that resides outside of the Java Virtual Machines of the nodes. The client computing system determines the transaction context of the operation based on the transaction context data and sends an operation request over a network to a managing node in the in-memory data grid to manage the multi-operational transaction. The operation request includes header data based on the transaction context data.

Multi-operational transactional access of in-memory data grids in a client-server environment

A data grid node that is hosted by a computing system receives a request to prepare transaction operations for a multi-operational transaction for a commit. The transaction operations are associated with other data grid nodes in the data grid. The data grid node stores transaction state data for the multi-operational transaction in local memory associated with the data grid node and identifies other data grid nodes in the data grid that manage the data pertaining to the transaction operations for the multi-operational transaction. The data grid node sends the transaction state data to the other data grid nodes and the other data grid nodes store the transaction state data in local memory associated with the corresponding data grid node.

Growing community of inventors

London, United Kingdom

Mircea Markus