Aurora: a new model and architecture for data stream management

advertisement
Aurora: a new model and
architecture for data stream
management
Daniel J. Abadi1, Don Carney2, Ugur Cetintemel2,
Mitch Cherniack1, Christian Convey2, Sangdon Lee2,
Michael Stonebraker3, Nesime Tatbul2, Stan
Zdonik2
1
Department of Computer Science, Brandeis University
Department of Computer Science, Brown University
3 Department of EECS and Laboratory of Computer Science, M.I.T.
2
Presenter: Saurin Kadakia
ABOUT ME
MS CS STUDENT
GRADUATING IN DEC 08
INTERESTED IN DATABASES AND WEB
TECHNOLOGY
WHAT ARE MONITORING APPLICATIONS??
MONITORING APPLICATIONS ARE
APPLICATIONS THAT MONITOR
CONTINUOUS STREAMS OF DATA.
EXAMPLES??
 MILITARY APPLICATIONS
 FINANCIAL ANALYSIS APPLICATIONS
 TRACKING APPLICATIONS
TRADITIONAL DBMS ASSUMPTIONS
HUMAN ACTIVE, DBMS PASSIVE MODEL
ONLY CURRENT VALUE IMPORTANT
TRIGGERS/ASSERTIONS ARE SECONDARY
QUERIES MUST HAVE EXACT ANSWERS
NO REAL TIME SERVICE REQUIREMENTS
REALITY FOR MONITORING APPLICATIONS
DBMS ACTIVE, HUMAN PASSIVE MODEL
HISTORY OF VALUES REQUIRED
TRIGGER ORIENTED APPLICATIONS
APPROXIMATE ANSWERS TO QUERIES
REAL TIME REQUIREMENTS
SYSTEM MODEL
User application
QoS spec
Query spec
Aurora
System
External
data source
Historical
Storage
Operator
boxes
data flow
Continuous
& ad hoc queries
Application
administrator
QUERY MODEL


Traditional

Structured Query Language

Declarative query on static data
Aurora

Data flow model for data stream


Application manager will construct queries using GUI
Stream Query Algebra


Queries are processed by SQuAl operators on the data
stream
Some of the operators are filter, map, union, aggregate, join
bsort, resample.
AURORA QUERY MODEL
QoS spec
data input
b1
b2
b3
app
continuous query
Connection
point
b4
QoS spec
b5
view
b6
ad-hoc query
b7
b8
b9
app
QoS spec
AURORA QoS GRAPH TYPES
OPTIMIZATION
Aggregate
Map
Join
Filter
Hold
pull data
Union
Continuous query
Filter
Hold
Ad hoc query
Filter
BSort
Map
Static storage
Aggregate
Join
OPTIMIZATION
Dynamic continuous query optimization
Inserting projections
Combining boxes
Reordering boxes
AURORA RUNTIME ARCHITECTURE
inputs
Storage
Manager
outputs
Router
σ
μ
Q1
Q2
Scheduler
Qm
Buffer manager
Box Processors
Catalog
Persistent Store
Q1
Q2
Qn
Load
Shedder
QoS
Monitor
SUMMARY
Solution approach itself
Rethink about everything for the requirements
Query model
Data flow style query specification
Optimization
Dynamic runtime optimization
QoS specification based resource
management
QUESTIONS???
Download