Abstract: Techniques for managing configurable data windows for streams and/or archived relations are provided. In some examples, a query that identifies at least a data stream or an archived relation may be identified. Additionally, a configurable window size may be identified. In some instances, the query may be initialized with at least a portion of the historical data based at least in part on the window size. Further, the query may be evaluated based at least in part on the data stream and the portion of the historical data.

Abstract: A method may include receiving a continuous query identified by an archived relation associated with an application. The method may also include generating a physical query plan. Additionally, the method may include constructing a structured query language (SQL) equivalent expression corresponding to an attribute utilized by the operator and/or constructing an output SQL expression for the identified operator based at least in part on the SQL equivalent expression. Additionally, the method may include constructing the archiver query for the identified operator based at least in part on the output SQL expression. Further, the method may include executing the archiver query to obtain a result set of data records related to the application and/or generating a snapshot output of one or more data values related to the application based at least in part on the result set of data records.

Abstract: Techniques for managing continuous queries that include subqueries are provided. In some examples, a continuous query that includes at least a subquery may be identified. Additionally, the subquery may be processed to obtain a first result or generate a logical subquery plan. Further, in some instances, the continuous query may then be processed based at least in part on the first result from the subquery or by merging a logical continuous query plan with the logical subquery plan. This may result in obtaining a second result via querying a data source with the continuous query that is based at least in part on the first result from the subquery and/or the merged plans.

Abstract: Techniques for counting event changes with archived relations are provided. In some examples, a query that identifies at least a data object may be identified. Additionally, the query may be evaluated against historical data associated with the data object. Additionally, in some instances, a listening service may be registered with the data object. Further, the query may be evaluated based at least in part on the data object and the historical data.

Abstract: A method may include receiving a continuous query identified by an archived relation associated with an application. The method may also include generating a physical query plan. Additionally, the method may include constructing a structured query language (SQL) equivalent expression corresponding to an attribute utilized by the operator and/or constructing an output SQL expression for the identified operator based at least in part on the SQL equivalent expression. Additionally, the method may include constructing the archiver query for the identified operator based at least in part on the output SQL expression. Further, the method may include executing the archiver query to obtain a result set of data records related to the application and/or generating a snapshot output of one or more data values related to the application based at least in part on the result set of data records.

Abstract: Some event ordering requirements can be determined based on continuous event processing queries. Other event ordering requirements can be determined based on distribution flow types being used to distribute events from event streams to node executing the queries. Events from event streams can be ordered according to ordering semantics that are based on a combination of all of these event ordering requirements. Additionally, virtual computing nodes can be associated with constraints, and computing processors can be associated with capabilities. Virtual computing nodes for processing event streams can be assigned to execute on various computing processors based on both these constraints and capabilities. Additionally, for each of several events in an event stream, a ratio between a total latency and a communication latency can be for determined. Based on an average of these ratios, a quantity of reducing nodes that will be involved in a map-reduce operation can be selected.

Abstract: A method may include receiving a continuous query identified by an archived view. The method may also include creating the archived view, the archived view identified by a join query related to two or more archived relations associated with an application and/or generating a query plan for the continuous query. The method may also include identifying a view root operator in the archived view, the view root operator identified as a join operator in the archived view and/or identifying a query operator in the query plan that topologically precedes the view root operator. Further, the method may include constructing an archiver query for the identified query operator that topologically precedes the view root operator, executing the archiver query to obtain a result set of data records related to the application, and/or generating a snapshot output of one or more data values related to the application.

Abstract: Systems and methods for guaranteeing the event order for multi-stage processing in distributed systems are disclosed. In some examples, a warm-up period is used to accurately determine a starting point for ordered events of an event stream. Skip-beats may be utilized as dummy events so that the event processor does not wait too long for events that were filtered out at earlier stages.

Abstract: Systems and methods for query decomposition for scalability of continuous query processing are disclosed. In some examples, it is determined whether a query is fully stateful. If it is, the query may be divided into two functions, an aggregate function and a global function. The aggregate functions may be distributed across multiple distributed nodes and executed in parallel. The global function may then receive the results from the distributed nodes and join the results to achieve the fully stateful result.

Abstract: Systems and methods for guaranteeing the event order for multi-stage processing in distributed systems are disclosed. In some examples, a warm-up period is used to accurately determine a starting point for ordered events of an event stream. Skip-beats may be utilized as dummy events so that the event processor does not wait too long for events that were filtered out at earlier stages.

Abstract: An event processing system is disclosed that processes events of an event stream, performs the recovery of events during system failure and preserves the state of the system reliably and accurately while achieving desired system performance. In an embodiment, the event processing system processes a first batch of events of a continuous input stream of events using a continuous query and generates an output stream of events related to an application. The event processing system identifies one or more operators of the continuous query and determines that an operator is a journaled operator. The event processing system generates a journaled snapshot of a current state of the system based on execution of the journaled operator on at least the first batch of events and stores the journaled snapshot of the current state of the system.

Abstract: An event processing system is disclosed that processes events of an event stream and performs the recovery of events during system failure. The recovery of events is performed by generating output sequence numbers for each deterministic output event generated by the event processing system. In an embodiment, the event processing system determines a current output sequence number of a most recently transmitted output event in a output stream of events, a last output sequence number of an output event corresponding to a most recently processed batch of input events and determines a set of one or more output events of the output stream to be transmitted based on the current sequence number and the last output sequence number. The event processing system then transmits the output events related to the application.

Abstract: Techniques for managing value-based windows on relations are provided. In some examples, an input relation is generated. The input relation is a bounded set of data records related to an application. A continuous query that identifies the input relation may be received. Additionally, a configurable window operator associated with processing the input relation may be identified. Then, the continuous query may be executed based at least in part on the configurable window operator to generate an output relation. Further, in some instances, the data records of the output relation may be provided based at least in part on execution of the continuous query.

Abstract: In some examples, a method may include receiving a continuous query, the continuous query being identified based at least in part on an archived relation associated with an application. The method may also include generating a physical query plan for the continuous query. In some examples, the method may also include identifying a query operator in the physical query plan and/or constructing an archiver query for the identified query operator. In some aspects, the method may also include executing the archiver query to obtain a result set of data records related to the application and/or initializing a state of the query operator based at least in part on the result set of data records. Further, the method may also include generating a snapshot output of one or more data values related to the application based at least in part on the state of the identified query operator.

Abstract: Techniques for managing configurable data windows for streams and/or archived relations are provided. In some examples, a query that identifies at least a data stream or an archived relation may be identified. Additionally, a configurable window size may be identified. In some instances, the query may be initialized with at least a portion of the historical data based at least in part on the window size. Further, the query may be evaluated based at least in part on the data stream and the portion of the historical data.

Abstract: Some event ordering requirements can be determined based on continuous event processing queries. Other event ordering requirements can be determined based on distribution flow types being used to distribute events from event streams to node executing the queries. Events from event streams can be ordered according to ordering semantics that are based on a combination of all of these event ordering requirements. Additionally, virtual computing nodes can be associated with constraints, and computing processors can be associated with capabilities. Virtual computing nodes for processing event streams can be assigned to execute on various computing processors based on both these constraints and capabilities. Additionally, for each of several events in an event stream, a ratio between a total latency and a communication latency can be for determined. Based on an average of these ratios, a quantity of reducing nodes that will be involved in a map-reduce operation can be selected.

Abstract: Some event ordering requirements can be determined based on continuous event processing queries. Other event ordering requirements can be determined based on distribution flow types being used to distribute events from event streams to node executing the queries. Events from event streams can be ordered according to ordering semantics that are based on a combination of all of these event ordering requirements. Additionally, virtual computing nodes can be associated with constraints, and computing processors can be associated with capabilities. Virtual computing nodes for processing event streams can be assigned to execute on various computing processors based on both these constraints and capabilities. Additionally, for each of several events in an event stream, a ratio between a total latency and a communication latency can be for determined. Based on an average of these ratios, a quantity of reducing nodes that will be involved in a map-reduce operation can be selected.

Abstract: A continuous query may be received, the continuous query being identified based at least in part on an archived view. The archived view may be created and/or identified based at least in part on a join query related to two or more archived relations associated with an application, at least one of the two or more archived relations being identified as a dimension relation. A query plan for the continuous query may be generated. A join operator in the query plan may be identified based at least in part on the dimension relation. A state of an operator corresponding to the dimension relation may be initialized. It may be identified if the state of the operator identifies an event that detects a change to the dimension relation. The continuous query may be re-started based at least in part on the event that detects the change to the dimension relation.

Abstract: Techniques for managing configurable data windows for streams and/or archived relations are provided. In some examples, a query that identifies at least a data stream or an archived relation may be identified. Additionally, a configurable window size may be identified. In some instances, the query may be initialized with at least a portion of the historical data based at least in part on the window size. Further, the query may be evaluated based at least in part on the data stream and the portion of the historical data.

Abstract: Techniques for performing non-event pattern matching on continuous event streams using variable duration. The duration value used in non-event pattern matching can be variable. Accordingly, a first pattern match candidate can have a different associated duration from a second pattern match candidate for matches arising from events received via an event stream. In certain embodiments, the duration for a candidate pattern match may be based upon one or more attributes of an event that started the candidate pattern match or based upon an expression (e.g., an arithmetic expression) involving one or more attributes of the event.