A Prediction Service For Remos and QuO Peter A. Dinda CMU SCS.

Slides:



Advertisements
Similar presentations
Welcome to Middleware Joseph Amrithraj
Advertisements

Database System Concepts and Architecture
An Evaluation of Linear Models for Host Load Prediction Peter A. Dinda David R. O’Hallaron Carnegie Mellon University.
The Case For Prediction-based Best-effort Real-time Peter A. Dinda Bruce Lowekamp Loukas F. Kallivokas David R. O’Hallaron Carnegie Mellon University.
Network Programming Chapter 11 Lecture 6. Networks.
ManageEngine TM Applications Manager 8 Monitoring Custom Applications.
Technical Architectures
Socket Programming.
1 Quality Objects: Advanced Middleware for Wide Area Distributed Applications Rick Schantz Quality Objects: Advanced Middleware for Large Scale Wide Area.
Understanding and Predicting Host Load Peter A. Dinda Carnegie Mellon University
CS3771 Today: network programming with sockets  Previous class: network structures, protocols  Next: network programming Sockets (low-level API) TODAY!
1 8/99 IMIC Workshop 6/22/2015 New Network ServicesJohn Zinky BBN Technologies The Need for A Network Resource Status Service IMIC Workshop 1999 Boston.
LYU9901-Travel Net LYU9901-Travel Net Supervisor: Prof. Michael R. Lyu Students: Ho Chi Ho Malcolm Lau Chi Ho Arthur (Presentation on )
Online Prediction of the Running Time Of Tasks Peter A. Dinda Department of Computer Science Northwestern University
Networks 1 CS502 Spring 2006 Network Input & Output CS-502 Operating Systems Spring 2006.
© Lethbridge/Laganière 2001 Chap. 3: Basing Development on Reusable Technology 1 Let’s get started. Let’s start by selecting an architecture from among.
VSP Video Station Protocol Presented by : Mittelman Dana Ben-Hamo Revital Ariel Tal Instructor : Sela Guy Presented by : Mittelman Dana Ben-Hamo Revital.
A Prediction-based Real-time Scheduling Advisor Peter A. Dinda Prescience Lab Department of Computer Science Northwestern University
Load Analysis and Prediction for Responsive Interactive Applications Peter A. Dinda David R. O’Hallaron Carnegie Mellon University.
Architectural Mismatch or Why it’s hard to build systems out of existing parts.
CGI Programming Languages Web Based Software Development July 21, 2005 Song, JaeHa.
NETWORK CENTRIC COMPUTING (With included EMBEDDED SYSTEMS)
FALL 2005CSI 4118 – UNIVERSITY OF OTTAWA1 Part 4 Web technologies: HTTP, CGI, PHP,Java applets)
1 4/20/98ISORC ‘98 BBN Technologies Specifying and Measuring Quality of Service in Distributed Object Systems Joseph P. Loyall, Richard E. Schantz, John.
1 05/01/02ISORC 2002 BBN Technologies Joe Loyall Rick Schantz, Michael Atighetchi, Partha Pal Packaging Quality of Service Control Behaviors for Reuse.
Cli/Serv.: JXTA/151 Client/Server Distributed Systems v Objective –explain JXTA, a support environment for P2P services and applications ,
Chapter 17 Networking Dave Bremer Otago Polytechnic, N.Z. ©2008, Prentice Hall Operating Systems: Internals and Design Principles, 6/E William Stallings.
1 Web Server Administration Chapter 1 The Basics of Server and Web Server Administration.
Understanding the CORBA Model. What is CORBA?  The Common Object Request Broker Architecture (CORBA) allows distributed applications to interoperate.
BBN Technologies Craig Rodrigues Gary Duzan QoS Enabled Middleware: Adding QoS Management Capabilities to the CORBA Component Model Real-time CCM Meeting.
Introduction to Interprocess communication SE-2811 Dr. Mark L. Hornick 1.
MILCOM 2001 October page 1 Defense Enabling Using Advanced Middleware: An Example Franklin Webber, Partha Pal, Richard Schantz, Michael Atighetchi,
Jozef Goetz, Application Layer PART VI Jozef Goetz, Position of application layer The application layer enables the user, whether human.
TANGO on embedded devices: the Bimorph Mirror application case Fulvio Billè Roberto Borghes, Roberto Pugliese, Lawrence Iviani Instrumentation & Measurement.
WDMS 2002 June page 1 Middleware Policies for Intrusion Tolerance QuO Franklin Webber, Partha Pal, Chris Jones, Michael Atighetchi, and Paul Rubel.
Hour 7 The Application Layer 1. What Is the Application Layer? The Application layer is the top layer in TCP/IP's protocol suite Some of the components.
New features for CORBA 3.0 by Steve Vinoski Presented by Ajay Tandon.
1 06/ /21/2015 ECOOP 2000 Workshop QoS in DOSJohn Zinky BBN Technologies Quality Objects (QuO) Middleware Framework ECOOP 2000 Workshop QoS in DOS.
1. I NTRODUCTION TO N ETWORKS Network programming is surprisingly easy in Java ◦ Most of the classes relevant to network programming are in the java.net.
Inter-process communication: Socket. socket Internet socket From Wikipedia, the free encyclopedia Jump to: navigation,
Introduction to Biometrics Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture #23 Biometrics Standards - II November 14, 2005.
Background: Operating Systems Brad Karp UCL Computer Science CS GZ03 / M th November, 2008.
Chapter 1 Computer Systems. Why study Computer Architecture? Examples Web Browsing - how does the browser access pages from a server? How can we create.
CORBA/IDL Common Object Resource Broker Architecture (CORBA) Interface Definition Language (IDL) Object Management Group (OMG) ( Specification.
1 Applying Adaptive Middleware, Modeling, and Real-Time CORBA Capabilities to Ensure End-to- End QoS Capabilities of Video Streams BBN Technologies Cambridge,
QuickTime The Joy of Streaming!. QuickTime Streaming Server Allows for real time delivery of media over a network. intranet internet Content can be prerecorded.
Remote Shell CS230 Project #4 Assigned : Due date :
Distributed Objects and Middleware. Sockets and Ports Source: G. Coulouris et al., Distributed Systems: Concepts and Design.
Hwajung Lee.  Interprocess Communication (IPC) is at the heart of distributed computing.  Processes and Threads  Process is the execution of a program.
Distributed Object Frameworks DCE and CORBA. Distributed Computing Environment (DCE) Architecture proposed by OSF Goal: to standardize an open UNIX envt.
DEVS Based Modeling and Simulation of the CORBA POA F. Bernardi, E. de Gentili, Pr. J.F. Santucci {bernardi, gentili, University.
 Common Object Request Broker Architecture  An industry standard developed by OMG to help in distributed programming.
Eric Tryon Brian Clark Christopher McKeowen. System Architecture The architecture can be broken down to three different basic layers Stub/skeleton layer.
Advanced Packet Analysis and Troubleshooting Using Wireshark 23AF
1 BBN Technologies Quality Objects (QuO): Adaptive Management and Control Middleware for End-to-End QoS Craig Rodrigues, Joseph P. Loyall, Richard E. Schantz.
CSI 3125, Preliminaries, page 1 SERVLET. CSI 3125, Preliminaries, page 2 SERVLET A servlet is a server-side software program, written in Java code, that.
Advanced Java Session 4 New York University School of Continuing and Professional Studies.
10-Jun-05 BWCTL (Bandwidth Test Control) Jeff Boote Network Performance Workshop.
Liang, Introduction to Java Programming, Fifth Edition, (c) 2005 Pearson Education, Inc. All rights reserved Chapter 29 Remote Method.
Client-Server Communication
Common Object Request Broker Architecture (CORBA)
File System Implementation
Common object request broker
Partially Predictable
Partially Predictable
Tiers vs. Layers.
Chapter 40 Remote Method Invocation
A tool for locating QoS failures on an Internet path
Chapter 46 Remote Method Invocation
Chapter 46 Remote Method Invocation
Presentation transcript:

A Prediction Service For Remos and QuO Peter A. Dinda CMU SCS

2 Outline Bette Davis Remos in QuO Peter’s Prediction Service in Remos Software abstractions Implementation Example

3 Bette Davis “Hello World” Program Choose whether to fetch a small or large image from the Bette Davis Server based on predicted network and host load 3 Systems (BBN QuO, CMU Remos, Peter’s Prediction Service) 10 Programming Languages (i386 assembly, C, C++, Java, Fortran 77, CORBA IDL, BBN SDL, BBN CDL, Perl, Sh) Network and Host Load Predictions

4 Client Delegate Abstract Model of QuO ORB and Other Magic Server Delegate Syscond Contract Syscond Contract

5 Client Contract Delegate Syscond Remos Modeler (Query Interface) Remos Collectors (LAN SNMP, WAN Bench, Host Load) Syscond... Remos in QuO ORB and Other Magic Server

6 Client Contract Delegate Syscond Remos Modeler (Query Interface) Syscond... Prediction in Remos ORB and Other Magic Server Remos Modeler (Query Interface) Collectors (LAN SNMP, WAN Bench, Host Load) PredictionMIB PastPresentFuture

7 What is this Impedence Mismatch? Prediction Pipeline (Inherently Stream Oriented) Measurement Stream Queries

8 PPL: Peter’s Prediction Library Data Sequence Model Data path Creates Modeler Predictor AbstractionsImplementations Best Mean, AR, MA, ARMA, ARIMA, ARFIMA EtaTheta Evaluator Data Stream Prediction Stream Statistical Metrics

9 A Prediction Service For Remos 1/2 Predictor Measurement Device (eg, Collector) ztzt z t+1 z t+2 z’ t,t+m z’ t,t+1 z’ t,t+2... z’ t+1,t+1+m z’ t+1,t+2 z’ t+1,t+3... z’ t+2,t+2+m z’ t+2,t+3 z’ t+2,t+4... ztzt z t+1 z t+2... Model Modeler Predictor Buffer... Evaluator Statistical Metrics Trigger Refit Output Measurement And Prediction Stream

10 A Prediction System For Remos 2/2 Output Measurement And Prediction Stream Buffer Remos Modeler Future Queries Remos Modeler Present and Near Past Queries

11 Implementation Goals Completely flexible component placement Flexible communication –No CORBA/Java/Whatever dependence –Support most internet protocols (UDP, TCP, Multicast, pipes, files, etc) Portability –No CORBA, no threads, no Java, minimal Unix assumptions Lessons learned after initial CORBA, LDOS implementation attempts

12 The Mirror C++ Template Class 1/2 UDP Streams TCP Streams File Streams Pipes Timed Callbacks Handler TCP UDP Handler TCP Stream Connection Reqs TCP Req/Resp Connection Reqs Data Forwarder Server UDP Streams TCP Streams File Streams Pipes Callbacks Req Resp Handler

13 The Mirror C++ Template Class 2/2 Parameterized by handlers Default handlers for 2 kinds of Mirrors –Raw Data –Serializeable Objects And several behaviors –Buffering, Req/Resp, Compute-on-input

14 Example: Measurement Buffer 1/2 template class Mirror : public AbstractMirror {…} template class GenericSerializeableInputComputeOutputMirror : public SerializeableMirror, GenericMirrorNewConnectionHandler,NullHandler, NullHandler> {}; template class BufferingSerializeableMirror : public SerializeableMirror,Gen ericMirrorNewConnectionHandler, BufferDataRequestResponseHandler, GenericMirrorNewRequestResponseConnectionHandler> {…} typedef BufferingSerializeableMirror MeasureBuffer;

15 Example: Measurement Buffer 1/2 MeasureBuffer mirror(depth); for (i=2;i<argc;i++) { ep = new EndPoint; if (ep->Parse(argv[i])) { exit(-1); } mirror.AddEndPoint(*ep); } mirror.Run(); Reference > ref; BufferDataRequest req; BufferDataReply repl; ref.ConnectTo((new EndPoint())->Parse(argv[2])); req.num=num; ref.Call(req,repl) for (i=0;i<repl.num;i++) { repl.data[i].Print(stderr); } Server Client

16 Command Lines From Hell % loadserver target:file:stdout connect:tcp:5000 target:udp: :5000 | load2measure 0 source:file:stdin connect:tcp:5001 target:file:stdout | measurebuffer 100 source:file:stdin target:file:stdout server:tcp:5002 | predserver 8 source:file:stdin target:file:stdout connect:tcp:5003 target:udp: :5003 | predbuffer 100 source:file:stdin target:file:stdout server:tcp:5004 | predclient source:file:stdin Measure Load and streams to stdout, multicast, connected TCP sessions Accept stream from stdin, make generic, stream to TCP and stdout Buffer stdin stream, stream to stdout, accept tcp requests for buffer contents Predict stdin stream 8 steps ahead, stream preds to stdout, TCP, and multicast Buffer predictions from stdin, stream to stdout, accept tcp requests for buffer contents Accept stdin pred stream and print

17 Meeting Implementation Goals Completely flexible component placement –Mostly, yes –Open implementation issues: Instantiation and naming problem: Who instantiates components, how do we find them, etc This is really a Remos/QuO issue - we all need to solve it Database? Flexible communication –Yes. You name it, you can communicate with it on as many channels as you want Portability –Yes. You only need g or later or similar C++ compiler –Running on: Linux, FreeBSD, Solaris, DUX

18 Zukunft Finish integration with Remos –Partially me Finish integration of Remos with QuO –NOT ME Address instantiation and naming problem –Database? Globus? –NOT ME Use prediction service to dynamically map a RT interactive application and show benefits –DV, OpenMap, DynBench, Feature tracking... –ME ME ME

19 Vergangenheit Host load study (LCR98, SciProg99) –Self-similarity, epochal behavior, etc. Study of linear models for host load prediction (TR , sub. to HPDC99) –Statistical statement: “AR(16) models or better are appropriate for Host Load Pred” Initial flailing on applications (WPDRTS99)