Scalable and extendable stream processing

• US 8,930,563 B2
• Filed: 10/27/2011
• Issued: 01/06/2015
• Est. Priority Date: 10/27/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Harrington, Timothy
• Primary Examiner(s): Vostal, Ondrej
• Application Number:
  US13/282,483
• Publication Number:
  US 20130111054A1
• Time in Patent Office: 1,167 Days
• Field of Search: 709/231, 709/200, 709/226, 370/396
• US Class Current: 709/231
• CPC Class Codes: G06F 15/16 Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs coordinating program control therefor G06F9/52; in regulating and control system G05B
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 65/765 intermediate
• CPC Class Codes: H04L 67/1031 Controlling of the operation of servers by a load balancer, e.g. adding or removing servers that serve requests
• CPC Class Codes: H04L 67/566 Grouping or aggregating service requests, e.g. for unified processing
• CPC Class Codes: H04L 67/567 Integrating service provisioning from a plurality of service providers

Abstract

An extensible architecture that enables developers to focus solely on the domain-specific nature of the stream processing algorithm to be implemented. It is positioned as an intermediary component between streaming data feeds and stream algorithms, thereby aggregating demand on data sources and hiding the complexity involved in managing active connections to different data sources. Per-algorithm stream throttling is provided so that individual algorithms do not get overloaded; thus, ensuring that algorithms receive fresh items from the data feeds to which the algorithms subscribe. Feed items can be discarded when an algorithm is not able to process the items in realtime to ensure that feed items are sampled at the fastest processing rate of the algorithm. Thus, a single instance of an algorithm can handle an entire data stream. Moreover, redundancy can be achieved by running the same configuration on multiple machines.

Claims

1. A computer-implemented system, comprising:

a streaming data processing component that receives streaming data from streaming data feeds and performs lossy per-algorithm stream throttling of streaming data feeds to enable stream processing algorithms to receive most recent data from the streaming data feeds, the streaming data processing component including an output data bus component that

(i) processes algorithm output into result sets and

(ii) manages expiration policies defined for each result set; and

a microprocessor that executes computer-executable instructions associated with the streaming data processing component.

2. The system of claim 1, wherein the stream processing algorithms include an algorithm that receives streaming data from one or more data feeds.

3. The system of claim 1, wherein the stream processing algorithms include an algorithm that provides one or more outputs.

4. The system of claim 1, wherein the streaming data processing component provides realtime streaming data for each algorithm to process.

5. The system of claim 1, wherein the streaming data processing component includes an input data bus component that consumes the data feeds and routes the streaming data to the algorithms.

6. The system of claim 1, wherein the streaming data processing component includes a buffer management component that monitors buffer consumption for each algorithm and manages data flow to maintain realtime stream processing in one or more of the algorithms.

7. The system of claim 1, wherein the streaming data processing component includes a web service that enables retrieval of the results sets by consuming systems.

8. A computer-implemented system, comprising:

a streaming data processing component that receives streaming data from streaming data feeds and performs lossy per-algorithm stream throttling of streaming data feeds to enable stream processing algorithms to receive most recent data from the streaming data feeds, the streaming data processing component further comprising;

an input data bus component that consumes the data feeds and routes the streaming data to the algorithms;

a buffer management component that monitors buffer consumption for each algorithm and manages data flow to maintain realtime stream processing in one or more of the algorithms;

an output data bus component that processes algorithm output into result sets and manages expiration policies defined for each result set; and

a web service that enables retrieval of the results sets by consuming systems; and

a microprocessor that executes computer-executable instructions associated with the streaming data processing component.

9. The system of claim 8, wherein the stream processing algorithms include an algorithm that at least one of receives streaming data from one or more data feeds or provides one or more outputs.

10. The system of claim 8, wherein the output data bus component publishes the result sets to the web service and to the input data bus component.

11. The system of claim 8, wherein the input data bus component enables an algorithm to subscribe to at least one of a data feed or an output of another algorithm.

12. A computer-implemented method, comprising acts of:

receiving data for routing to stream processing algorithms;

monitoring consumption of data by an algorithm for realtime stream data processing;

managing, using lossy throttling, input of the data to the algorithm based on the consumption by performing lossy per-algorithm stream throttling of the received data to enable the stream processing algorithms to receive most recent data from the received data;

processing algorithm output into result sets and managing expiration policies defined for each result set; and

utilizing a processor that executes instructions stored in memory to perform at least one of the acts of monitoring, processing or managing.

13. The method of claim 12, further comprising routing all the data to the algorithm based on realtime consumption of all the data by the algorithm.

14. The method of claim 12, further comprising discarding a portion of the data input to the algorithm to maintain the realtime stream data processing by the algorithm of most recent feed data.

15. The method of claim 12, further comprising monitoring consumption of each algorithm, and managing data input to each of the algorithms to maintain realtime stream data processing at each algorithm.

16. The method of claim 12, further comprising receiving the data from a data feed and from an output of at least one of the algorithms.

17. The method of claim 12, further comprising implementing management of data to the algorithms and the algorithms as a plug-in software module in combination with a configuration file.

18. The method of claim 12, further comprising generating result sets from the data and exposing the result sets to consuming systems via either a web service or a storage medium.

19. One or more computer-readable storage media encoded with processing instruction that, when executed by a processor, cause the execution of a method, the method comprising:

receiving data for routing to stream processing algorithms;

monitoring consumption of data by an algorithm for realtime stream data processing;

managing, using lossy throttling, input of the data to the algorithm based on the consumption by performing lossy per-algorithm stream throttling of the received data to enable the stream processing algorithms to receive most recent data from the received data; and

processing algorithm output into result sets and managing expiration policies defined for each result set.