Abstract: Enhanced techniques for data retrieval in a distributed computing environment are described. A computing node of a distributed computing environment may receive a data request. The computing node may include one or more subsets of data. The computing node may be configured to search among the one or more subset of data for a beginning of a data range that is responsive to the data request. The computing node may be further configured to forward a data range responsive to the search to another computing node of the distributed computing system to be merged with one or more additional data ranges. Other embodiments are described and claimed.

Abstract: A method of generating a decision tree is provided. A leaf assignment for each proposed split in generating the decision tree is incremented using a Gray code.

Abstract: A regularizer process is started by a first thread executing at a computing device. The regularizer process is a separate process from a process executing on the first thread. The started regularizer process sends a presence announcement to a controller device and receives a presence acknowledgement from the controller device. The started regularizer process sends a notification to the first thread that it is ready to receive streamed data. The started regularizer process receives, from the controller device, an indicator of a data provider system that is to connect to it, receives a connection request from the data provider system, compares the received connection request to the received indicator, sends a connection acknowledgement to the data provider system when the received connection request matches the received indicator, accepts a connection from the data provider system, and receives the streamed data through the connection.

Abstract: In a computing device supporting distributed stream processing, a request is received from a controller device to redistribute blocks storing streamed data. The request indicates that a number of blocks stored on the computing device be sent to a second computing device. The controller device controls distribution of analytic results to a data access system. The analytic results are computed from the streamed data. The indicated number of blocks are selected from the blocks storing the streamed data. The selected blocks are sent to the second computing device. Pointers to remaining blocks of the blocks storing the streamed data are updated.

Abstract: In a computing device supporting distributed stream processing, a request is received from a controller device to redistribute blocks storing streamed data. The request indicates that a number of blocks stored on the computing device be sent to a second computing device. The controller device controls distribution of analytic results to a data access system. The analytic results are computed from the streamed data. The indicated number of blocks are selected from the blocks storing the streamed data. The selected blocks are sent to the second computing device. Pointers to remaining blocks of the blocks storing the streamed data are updated.

Abstract: In a computing device supporting distributed stream processing, a regularizer process is started by a first thread executing at a computing device. The regularizer process is a separate process from a process executing on the first thread. The started regularizer process, sends a presence announcement to a controller device; receives a presence acknowledgement from the controller device; sends a notification to the first thread that the started regularizer process is ready to receive streamed data; receives, from the controller device, an indicator of a data provider system that is to connect to the started regularizer process; receives a connection request from the data provider system; compares the received connection request to the received indicator; sends a connection acknowledgement to the data provider system when the received connection request matches the received indicator; accepts a connection from the data provider system; and receives the streamed data through the connection.

Abstract: A method of generating a decision tree is provided. A leaf assignment for each proposed split in generating the decision tree is incremented using a Gray code.

Abstract: Enhanced techniques for data retrieval in a distributed computing environment are described. A computing node of a distributed computing environment may receive a data request. The computing node may include one or more subsets of data. The computing node may be configured to search among the one or more subset of data for a beginning of a data range that is responsive to the data request. The computing node may be further configured to forward a data range responsive to the search to another computing node of the distributed computing system to be merged with one or more additional data ranges. Other embodiments are described and claimed.