Load Shedding in Stream Databases – A Control-Based Approach

Slides:



Advertisements
Similar presentations
Feedback Control Real- time Scheduling James Yang, Hehe Li, Xinguang Sheng CIS 642, Spring 2001 Professor Insup Lee.
Advertisements

CprE 458/558: Real-Time Systems
Simulation of Feedback Scheduling Dan Henriksson, Anton Cervin and Karl-Erik Årzén Department of Automatic Control.
Feedback Control Real-Time Scheduling: Framework, Modeling, and Algorithms Chenyang Lu, John A. Stankovic, Gang Tao, Sang H. Son Presented by Josh Carl.
Analysis of : Operator Scheduling in a Data Stream Manager CS561 – Advanced Database Systems By Eric Bloom.
DEXA 2005 Control-based Quality Adaptation in Data Stream Management Systems (DSMS) Yicheng Tu†, Mohamed Hefeeda‡, Yuni Xia†, Sunil Prabhakar†, and Song.
Adaptive Monitoring of Bursty Data Streams Brian Babcock, Shivnath Babu, Mayur Datar, and Rajeev Motwani.
Load Shedding in a Data Stream Manager Kevin Hoeschele Anurag Shakti Maskey.
Karl Schnaitter and Neoklis Polyzotis (UC Santa Cruz) Serge Abiteboul (INRIA and University of Paris 11) Tova Milo (University of Tel Aviv) Automatic Index.
SIGMETRICS 2008: Introduction to Control Theory. Abdelzaher, Diao, Hellerstein, Lu, and Zhu. CPU Utilization Control in Distributed Real-Time Systems Chenyang.
AQM for Congestion Control1 A Study of Active Queue Management for Congestion Control Victor Firoiu Marty Borden.
Adaptive Sampling in Distributed Streaming Environment Ankur Jain 2/4/03.
Improving the Accuracy of Continuous Aggregates & Mining Queries Under Load Shedding Yan-Nei Law* and Carlo Zaniolo Computer Science Dept. UCLA * Bioinformatics.
1 Load Shedding in a Data Stream Manager Slides edited from the original slides of Kevin Hoeschele Anurag Shakti Maskey.
LDU Parametrized Discrete-Time Multivariable MRAC and Application to A Web Cache System Ying Lu, Gang Tao and Tarek Abdelzaher University of Virginia.
Applying Control Theory to Stream Processing Systems Wei Xu Bill Kramer Joe Hellerstein.
Open loop vs closed loop By Norbert Benei ZI5A58.
Unit 3a Industrial Control Systems
Computer Control: An Overview Wittenmark, Åström, Årzén Computer controlled Systems The sampling process Approximation of continuous time controllers Aliasing.
Efficient Scheduling of Heterogeneous Continuous Queries Mohamed A. Sharaf Panos K. Chrysanthis Alexandros Labrinidis Kirk Pruhs Advanced Data Management.
Applying Feedback Control to QoS management - an introduction -
Freshness-Aware Scheduling of Continuous Queries in the Dynamic Web Mohamed A. Sharaf Alexandros Labrinidis Panos K. Chrysanthis Kirk Pruhs Advanced Data.
Final Exam, May 25, 2007 Quality Management in Multimedia Databases and Data Stream Management Systems Yicheng Tu Department of Computer Sciences Purdue.
Brief Review of Control Theory
Budget-based Control for Interactive Services with Partial Execution 1 Yuxiong He, Zihao Ye, Qiang Fu, Sameh Elnikety Microsoft Research.
U N I V E R S I T Y O F S O U T H F L O R I D A The basic idea is to start from a difference equation with unknown parameters and orders in the following.
Runtime Optimization of Continuous Queries Balakumar K. Kendai and Sharma Chakravarthy Information Technology Laboratory Department of Computer Science.
Model Reference Adaptive Control (MRAC). MRAS The Model-Reference Adaptive system (MRAS) was originally proposed to solve a problem in which the performance.
Load Shedding in Stream Databases – A Control-Based Approach Yicheng Tu, Song Liu, Sunil Prabhakar, and Bin Yao Department of Computer Science, Purdue.
Control-Based Load Shedding in Data Stream Management Yicheng Tu †, Song Liu ‡, Sunil Prabhakar †, Bin Yao ‡ † Indiana Center of Database Systems, Department.
Adaptive Sleep Scheduling for Energy-efficient Movement-predicted Wireless Communication David K. Y. Yau Purdue University Department of Computer Science.
Aurora: a new model and architecture for data stream management Daniel J. Abadi 1, Don Carney 2, Ugur Cetintemel 2, Mitch Cherniack 1, Christian Convey.
Control-Based Load Shedding in Data Stream Management Systems Yicheng Tu and Sunil Prabhakar Department of Computer Sciences, Purdue University April 3,
UNIT: User-ceNtrIc Transaction Management in Web-Database Systems Huiming Qu, Alexandros Labrinidis, Daniel Mosse Advanced Data Management Technologies.
Towards Adaptive Optimal Control of the Scramjet Inlet Nilesh V. Kulkarni Advisors: Prof. Minh Q. Phan Dartmouth College Prof. Robert F. Stengel Princeton.
Control-based Quality Adaptation in Data Stream Management Systems (DSMS) Yicheng Tu†, Song Liu‡, Sunil Prabhakar†, and Bin Yao‡ † Department of Computer.
Control-Based Load Shedding in Data Stream Management Systems Yicheng Tu and Sunil Prabhakar Department of Computer Sciences, Purdue University April 3,
Name of Student : PATEL ARPITKUMAR RAJNIKANT Enrollment No
OPERATING SYSTEMS CS 3502 Fall 2017
Fall 2004 Backpropagation CS478 - Machine Learning.
Open loop vs closed loop
Introduction to Load Balancing:
International Conference on Data Engineering (ICDE 2016)
Action Breakout Session
Applying Control Theory to Stream Processing Systems
Chapter 12. Controlling the Process
SOUTHERN TAIWAN UNIVERSITY ELECTRICAL ENGINEERING DEPARTMENT
Load Shedding CS240B notes.
Measuring Service in Multi-Class Networks
Liang Chen Advisor: Gagan Agrawal Computer Science & Engineering
Quality management in database systems A thesis proposal
Supporting Fault-Tolerance in Streaming Grid Applications
Data Stream Management System (DSMS)
Load Shedding Techniques for Data Stream Systems
StreamApprox Approximate Stream Analytics in Apache Spark
Streaming Sensor Data Fjord / Sensor Proxy Multiquery Eddy
Brief Review of Control Theory
Brian Babcock, Shivnath Babu, Mayur Datar, and Rajeev Motwani
CPU SCHEDULING.
QuaSAQ: Enabling End-to-End QoS for Distributed Multimedia Databases
GATES: A Grid-Based Middleware for Processing Distributed Data Streams
Linköping University, IDA, ESLAB
CONTROL SYSTEM AN INTRODUCTION.
Dynamical Systems Basics
Load Shedding CS240B notes.
Control Theory in Log Processing Systems
Feedback Control Real-time Scheduling
Modeling IDS using hybrid intelligent systems
ECE 517: Reinforcement Learning in Artificial Intelligence Lecture 17: TRTRL, Implementation Considerations, Apprenticeship Learning November 3, 2010.
Presentation transcript:

Load Shedding in Stream Databases – A Control-Based Approach Yicheng Tu, Song Liu, Sunil Prabhakar, and Bin Yao Department of Computer Science, Purdue University Presented by Chris Mayfield VLDB Conference, Seoul, Korea September 14, 2006

Data stream management systems Applications Financial analysis Mobile services Sensor networks Network monitoring More … Continuous data, discarded after being processed Continuous query Data-active query-passive model

DSMS architecture Network of query operators (O1 – O3) Each operator has its own queue (q1 – q4) Scheduler decides which operator to execute Query results (Q1, Q2) pushed to clients Example systems: Aurora/Borealis STREAM

Quality in DSMS data processing Data processing in DSMS is quality-critical tuple delay data loss sampling rate, window size, … Overloading during spikes  degraded quality (delay) Solution: adjust data loss (i.e., load shedding) On DSMS side Eliminating excessive load by dropping data items The real problem is: tuple delay is the major concern: results generated from old data are useless! How to maintain processing delays while minimizing data loss ?

Related work (load shedding) Accuracy of aggregate queries under load shedding (Babcock et al., ICDE04) Data triage (Reiss & Hellerstein, ICDE05) Put data into an asylum upon overloading LoadStar (Chi et al., VLDB05) QoS-driven load shedding (Tatbul et al., VLDB03) Key questions - When? - How much? - Where? Use a load shedding roadmap (LSRM) to decide where Intuitive algorithm to decide when and how much

Example Limitations Highly dynamic environment is reality Bursty data input Variable unit processing cost Fails to capture current system status (queue length) and output (delay) Delay positively related to queue length Example 1. Unbounded increase of delay Example 2. Unnecessary data loss

Our approach View load shedding as a control theory problem Control: manipulation of system behavior by adjusting input Cruise control of automobiles, room temperature control, etc. Open-loop (preset) vs. closed-loop (feedback) control The feedback control loop: Plant Monitor Controller Actuator How it works Error (e) = desirable output (yr) - measured output (y) Focal point: controller, which maps e to control signal u Disturbances

Challenges (theory → practice) Can we model the system? Analytical model may not be easy to derive System identification: experimental methods How to design the controller? Use control theoretical tools for guaranteed performance DSMS-specific problems Lack of real-time measurement of output signal ( y ) How to set control period (T) Real system evaluation we use Borealis in our study

where q is the number of outstanding data tuples Modeling a DSMS Borealis data stream manager Round robin operator scheduler FIFO waiting queues For now, fix the per-tuple processing cost c Proposed model: y = qc where q is the number of outstanding data tuples Discrete form: y(k) = q(k-1) c Denote the input load as fi and system processing power as fo:

Controller design Design based on pole placement Locations tell how fast/well system responds Guaranteed performance targeting Convergence rate - responsiveness Damping - smoothness The controller: (see appendix for details)

Control period Provides more complete answer to the question “when to shed load”? Empirically set in previous studies Case-by-case decision with some systematic rules In our problem, a tradeoff between: Sampling theory (Nyquist-Shannon Theorem): in order to capture the moving trends of the disturbances, higher (shorter) sampling frequency (period) is preferred Stochastic feature of output ( y ) and parameter ( c ): more samples are needed  longer period is preferred The first factor should be given more weight

Input for experiments Controller and load shedder implemented in Borealis Synthetic (“Pareto”) and real (“Web”) data streams Small query network with variable average processing cost

Experimental results Experiments for comparison Target delay: 2 sec Aurora – open loop solution Baseline – a simple feedback method Target delay: 2 sec Control period: 1 sec Total time: 400 sec For both input types, data loss are almost the same for all three load shedding strategies

Future work Time-varying DSMS model For example, time-varying cost c Possible solution: adaptive control Adaptation other than load shedding New disturbances? Model changes? (i.e. at runtime) Other database problems

Summary Load shedding is an effective quality adaptation method Ad hoc solutions do not work well under dynamic load and system features We propose an approach to guide load shedding in a highly dynamic environment based on feedback control theory Initial experimental results performed in a real-world DSMS show promising potential of our approach

Backup - 1

Backup - 2 Lack of robustness of open-loop solution More optimistic policy adapted in Aurora Unstable performance Our solution is robust Under input streams with different burstiness

Backup - 3

Backup - 4 (Model verification) Feed Borealis with synthetic streams Input rate: step or sinusoidal function of time Average processing cost is fixed