Streams optional execution paths depending upon data rates

• US 9,930,081 B2
• Filed: 11/13/2012
• Issued: 03/27/2018
• Est. Priority Date: 11/13/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Branson, Michael J., Santosuosso, John M.
• Primary Examiner(s): Jakovac, Ryan
• Application Number:
  US13/675,872
• Publication Number:
  US 20140136723A1
• Time in Patent Office: 1,960 Days
• CPC Class Codes: H04L 65/612 for unicast
• CPC Class Codes: H04L 65/613 for the control of the source by the destination control signals issued by the client directed to the server or network components specially adapted for selective content distribution H04N21/637
• CPC Class Codes: H04L 65/70 Media network packetisation
• CPC Class Codes: H04L 67/61 taking into account QoS or priority requirements

Abstract

Processing elements in a streaming application may contain one or more optional code modules—i.e., computer-executable code that is executed only if one or more conditions are met. In one embodiment, an optional code module is executed based on evaluating data flow rate between components in the streaming application. As an example, the stream computing application may monitor the incoming data rate between processing elements and select which optional code module to execute based on this rate. For example, if the data rate is high, the stream computing application may choose an optional code module that takes less time to execute. Alternatively, a high data rate may indicate that the incoming data is important; thus, the streaming application may choose an optional code module containing a more rigorous data processing algorithm, even if this algorithm takes more time to execute.

Claims

1. A system, comprising:

a computer processor; and

a memory containing a program that, when executed on the computer processor, performs an operation for processing data, comprising;

receiving streaming data to be processed by a plurality of interconnected processing elements, each processing element comprising one or more operators that process at least a portion of the received data by operation of one or more computer processors, wherein each one of the plurality of interconnected processing elements is hosted on a corresponding compute node;

measuring, during a first time period, a data flow rate in a data path between at least two operators in the plurality of processing elements processing the streaming data;

processing, during the first time period, at least a portion of the streaming data using a first code module, wherein the streaming data comprises a plurality of data tuples where each of the plurality of data tuples comprises a plurality of attribute value pairs, wherein the first code module processes a first attribute value pair of the plurality of attribute value pairs;

selecting, based on the measured data flow rate, an inactive code module stored in a first one of the plurality of processing elements processing the streaming data, wherein the selected code module is maintained in an inactive state until the data flow rate satisfies a predefined threshold; and

activating, during a second time period, the selected code module on the first plurality of processing elements such that a second attribute value pair of the plurality of attribute value pairs in the streaming data received by the first processing element is processed by the selected code module, wherein the second time period occurs after the first time period, wherein the first code module processes the first attribute value pair during the second time period, and wherein the first attribute value pair is different from the second attribute value pair.

2. The system of claim 1, wherein each of the at least two operators are contained in respective processing elements such that the data path transmits the streaming data between the respective processing elements.

3. The system of claim 1, wherein the selected code module is in an operator in the first processing element, wherein the selected code module is used to process the data received by the first processing element only when the data flow rate satisfies the predefined threshold.

4. The system of claim 1, the program further comprising, upon determining that the data flow rate satisfies the predefined threshold, fusing an operator to the first processing element, wherein the fused operator is the selected code module.

5. The system of claim 4, the program further comprising, upon determining that the data flow rate no longer satisfies the predefined threshold, deactivating the fused operator from the first processing element by one of:

(i) unfusing the fused operator from the first processing element and (ii) instructing the fused operator to no longer process the data received by the first processing element.

6. The system of claim 1, wherein the data flow rate is compared to a plurality of predefined thresholds arranged in a hierarchy such that the predefined threshold satisfied by the data flow rate with the highest priority is used to select the inactive code module, wherein each predefined threshold is associated with a different inactive code module.

7. The system of claim 1, wherein the data flow rate is extrapolated from data flowing on at least two data paths, wherein each of the two data paths transmit data between at least two operators in the operator graph.

15. The system of claim 1, wherein the second attribute value pair of each of the data tuples is not processed by either the first one of the plurality of processing elements or the first code module during the first time period.

8. A computer program product for processing data, the computer program product comprising:

a non-transitory computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code comprising computer-readable program code configured to;

receive streaming data to be processed by a plurality of interconnected processing elements, each processing element comprising one or more operators that process at least a portion of the received data by operation of one or more computer processors, wherein each one of the plurality of interconnected processing elements is hosted on a corresponding compute node;

measure, during a first time period, a data flow rate in a data path between at least two operators in the plurality of processing elements processing the streaming data;

process, during the first time period, at least a portion of the streaming data using a first code module, wherein the streaming data comprises a plurality of data tuples where each of the plurality of data tuples comprises a plurality of attribute value pairs, wherein the first code module processes a first attribute value pair of the plurality of attribute value pairs

select, based on the measured data flow rate, an inactive code module stored in a first one of the plurality of processing elements processing the streaming data, wherein the selected code module is maintained in an inactive state until the data flow rate satisfies a predefined threshold; and

activate, during a second time period, the selected code module on the first plurality of processing elements such that a second attribute value pair of the plurality of attribute value pairs in the streaming data received by the first processing element is processed by the selected code module, wherein the second time period occurs after the first time period, wherein the first code module processes the first attribute value pair during the second time period, and wherein the first attribute value pair is different from the second attribute value pair.

9. The computer program product of claim 8, wherein each of the at least two operators are contained in respective processing elements such that the data path transmits data between the respective processing elements.

10. The computer program product of claim 8, wherein the selected code module is in an operator in the first processing element, wherein the selected code module is used to process the data received by the first processing element only when the data flow rate satisfies the predefined threshold.

11. The computer program product of claim 8, wherein the data flow rate is extrapolated from data flowing on at least two data paths, wherein each of the two data paths transmit data between at least two operators in the operator graph.

12. The computer program product of claim 8, wherein the measured data flow rate is compared to a plurality of predefined thresholds arranged in a hierarchy such that the predefined threshold satisfied by the data flow rate with the highest priority is used to select the inactive code module, wherein each predefined threshold is associated with a different inactive code module.

13. The computer program product of claim 8, the program further configured to, upon determining that the data flow rate satisfies the predefined threshold, fusing an operator to the first processing element, wherein the fused operator is the selected code module.

14. The computer program product of claim 13, the program further configured to, upon determining that the data flow rate no longer satisfies the predefined threshold, deactivating the fused operator from the first processing element by one of:

(i) unfusing the fused operator from the first processing element and (ii) instructing the fused operator to no longer process the data received by the first processing element.

16. The computer program product of claim 8, wherein the second attribute value pair of each of the data tuples is not processed by either the first one of the plurality of processing elements or the first code module during the first time period.