Presentation is loading. Please wait.

Presentation is loading. Please wait.

A new model and architecture for data stream management.

Similar presentations


Presentation on theme: "A new model and architecture for data stream management."— Presentation transcript:

1 A new model and architecture for data stream management

2 Inspiration & Domain Sample Problem

3 Stream Processing Engines  HADP vs DAHP  Events & Triggers  Continuous Queries  Real-time processing  Transient data  Lossy information

4 Application Domains  Online Auctions  Network Traffic Management  Habitat Monitoring  Military Logistics  Immersive Environments  Road Traffic Monitoring  System Monitoring  Smart Energy Grid

5 Overview Aurora

6 The Topic  Aurora  The prototype  DBMS / SPE / DSMS  UI  The query language  The project  The authors

7 The Authors  M.I.T., Department of EECS and Laboratory of Computer Science  Michael Stonebraker  Brandeis University, Department of Computer Science  Daniel J. Abadi  Mitch Cherniack  Brown University, Department of Computer Science  Don Carney  Uğur Çetintemel  Christian Convey  Sangdon Lee  Nesime Tatbul  Stan Zdonik

8 Talk Overview  Stream Processing Engines  SQuAl  Runtime  Related work

9 SQuAl (Stream Query Algebra) Aurora

10 SQuAl Overview  Connection Points  Models  Continuous Query  View  Ad-hoc Query  Operators  Order-agnostic  Order-sensitive

11 SQuAl Operators  Order-agnostic  Filter  Map  Union  Order-sensitive  BSort  Aggregate  Join  Resample  Quirks!

12 Filter (Unordered)

13 Map (Unordered)

14 Union (Unordered)

15 BSort (Ordered)

16 Aggregate (Ordered)

17 Join (Ordered)

18 Resample (Ordered)  Based on RRDTool’s philosophy?  Paper:  Simple interpolation  Use The Force, Read The Source:  Average  Count  Sum  Max  Min  LastVal

19 SQuAl: Example

20 Runtime Aurora

21 Query Optimization  Dynamic Continuous Query Optimization  Inserting projections  Combining boxes  Reordering boxes  Ad-hoc query optimization

22 Real-time Scheduling  Timestamped Tuples  Train scheduling  Interbox nonlinearities  Intrabox nonlinearities  Superboxes  Introspection  Static  Run-time

23 Handling overload  QoS specifications  Response times  Tuple drops  Values produced  Load Shedding  Not Implemented at the time

24 Related work Aurora

25 Related work  STREAM  Stanford University, 2000-2006  Telegraph  UC Berkley, 2000-2007?  SASE  UC Berkley / Mass Amherst, 2006-2008?  Cayuga  Cornell University, 2005-2007?  PIPES  University of Marburg, 2003-2007?  NiagaraCQ  University of Wiscon-Madison, 1999-2002

26 Aurora’s Evolution TimespanProject 2002-2004Aurora (and Aurora*) 2003-2005Medusa 2005-2008Borealis (Medusa + Aurora*) 2003-presentStreamBase (Commercialized)

27 Complex Event Processing Today  Oracle  Oracle CEP  Microsoft  MS SQL Server StreamInsight  Open Source  OpenPDC  Aleri  Coral8  TruViso  StreamBase  Aurora’s Grandchild  IBM  SPADE  Active Middleware Technology

28


Download ppt "A new model and architecture for data stream management."

Similar presentations


Ads by Google