Marcelo R.N. Mendes. What is FINCoS? A set of tools for data generation, load submission, and performance measurement of CEP systems; Main Characteristics:

Slides:



Advertisements
Similar presentations
Current methods for negotiating firewalls for the Condor ® system Bruce Beckles (University of Cambridge Computing Service) Se-Chang Son (University of.
Advertisements

1 Computational Asset Description for Cyber Experiment Support using OWL Telcordia Contact: Marian Nodine Telcordia Technologies Applied Research
Module 5: Routing BizTalk Messages. Overview Lesson 1: Introduction to Message Routing Lesson 2: Configuring Message Routing Lesson 3: Monitoring Orchestrations.
NGAS – The Next Generation Archive System Jens Knudstrup NGAS The Next Generation Archive System.
1 Opentest Architecture Table of Content –The Design Basic Components High-Level Test Architecture Test Flow –Services provided by each Layer Test Mgt.
An End-User Perspective On Using NatQuery Building a Dynamic Variable T
Introduction to Network Analysis and Sniffer Pro
JAXB Java Architecture for XML Binding Andy Fanton Khalid AlBayat.
SWIM WEB PORTAL by Dipti Aswath SWIM Meeting ORNL Oct 15-17, 2007.
Yevgeny Petrilin Shay Dan Shadi Ibrahim. GUI : Graphical User Interface DAQ :Data Acquisition Data Acquisition device  a self-powered system that communicated.
A CHAT CLIENT-SERVER MODULE IN JAVA BY MAHTAB M HUSSAIN MAYANK MOHAN ISE 582 FALL 2003 PROJECT.
Chapter 12: ADO.NET and ASP.NET Programming with Microsoft Visual Basic.NET, Second Edition.
CHEP04 - Interlaken - Sep. 27th - Oct. 1st 2004T. M. Steinbeck for the Alice Collaboration1/20 New Experiences with the ALICE High Level Trigger Data Transport.
Chapter 11 - Monitoring Server Performance1 Ch. 11 – Monitoring Server Performance MIS 431 – created Spring 2006.
The new The new MONARC Simulation Framework Iosif Legrand  California Institute of Technology.
3.1 © 2004 Pearson Education, Inc. Exam Managing and Maintaining a Microsoft® Windows® Server 2003 Environment Lesson 3: Introducing Active Directory.
The OSI Model A layered framework for the design of network systems that allows communication across all types of computer systems regardless of their.
23 September 2004 Evaluating Adaptive Middleware Load Balancing Strategies for Middleware Systems Department of Electrical Engineering & Computer Science.
Overview SAP Basis Functions. SAP Technical Overview Learning Objectives What the Basis system is How does SAP handle a transaction request Differentiating.
DEMONSTRATION FOR SIGMA DATA ACQUISITION MODULES Tempatron Ltd Data Measurements Division Darwin Close Reading RG2 0TB UK T : +44 (0) F :
What is in Presentation What is IPsec Why is IPsec Important IPsec Protocols IPsec Architecture How to Implement IPsec in linux.
This presentation will guide you though the initial stages of installation, through to producing your first report Click your mouse to advance the presentation.
STRATEGIES INVOLVED IN REMOTE COMPUTATION
Performance and Exception Monitoring Project Tim Smith CERN/IT.
WINDOWS SERVICES. Introduction You often need programs that run continuously in the background Examples: – servers –Print spooler You often need.
1 Kaseya Advanced Workshop Developed by Kaseya University Powered by IT Scholars Kaseya Version 6.2 Last updated on June 25, 2012 DAY TWO.
COMP 410 & Sky.NET May 2 nd, What is COMP 410? Forming an independent company The customer The planning Learning teamwork.
11 SYSTEM PERFORMANCE IN WINDOWS XP Chapter 12. Chapter 12: System Performance in Windows XP2 SYSTEM PERFORMANCE IN WINDOWS XP  Optimize Microsoft Windows.
Objectives Configure routing in Windows Server 2008 Configure Routing and Remote Access Services in Windows Server 2008 Network Address Translation 1.
70-290: MCSE Guide to Managing a Microsoft Windows Server 2003 Environment, Enhanced Chapter 11: Monitoring Server Performance.
Module 10: Monitoring ISA Server Overview Monitoring Overview Configuring Alerts Configuring Session Monitoring Configuring Logging Configuring.
GUI For A Virtual Pipeline Simulation Testbed By, Revathi Manni Ranganathan Major Professor: Dr.Virgil Wallentine.
AUTOMATION OF WEB-FORM CREATION - KINNERA ANGADI – MS FINAL DEFENSE GUIDANCE BY – DR. DANIEL ANDRESEN.
1 st December 2003 JIM for CDF 1 JIM and SAMGrid for CDF Mòrag Burgon-Lyon University of Glasgow.
Monitoring Windows Server 2012
Marcelo R.N. Mendes. What is FINCoS? A Java-based set of tools for data generation, load submission, and performance measurement of event processing systems;
A Brief Documentation.  Provides basic information about connection, server, and client.
Maintaining and Updating Windows Server Monitoring Windows Server It is important to monitor your Server system to make sure it is running smoothly.
Server to Server Communication Redis as an enabler Orion Free
GLAST Science Support CenterJuly, 2003 LAT Ground Software Workshop Status of the D1 (Event) and D2 (Spacecraft Data) Database Prototypes for DC1 Robert.
Workshop BigSim Large Parallel Machine Simulation Presented by Eric Bohm PPL Charm Workshop 2004.
A university for the world real R © 2009, Chapter 9 The Runtime Environment Michael Adams.
NetNumen T31 Common Operations. Objectives Master Basic Configurations of T31 Master Common Operations of T31.
Apr. 8, 2002Calibration Database Browser Workshop1 Database Access Using D0OM H. Greenlee Calibration Database Browser Workshop Apr. 8, 2002.
CH 13 Server and Network Monitoring. Hands-On Microsoft Windows Server Objectives Understand the importance of server monitoring Monitor server.
Envision Tutorial Horner APG, LLC July 18, Introduction The Cscape Remote Viewer allows remote interaction with the user interface on Horner OCS.
Configuration Mapper Sonja Vrcic Socorro,
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.
August 2003 At A Glance The IRC is a platform independent, extensible, and adaptive framework that provides robust, interactive, and distributed control.
CCCognos Connection RSReport Studio ASAnalysis Studio QSQuery Studio ESEvent Studio CSContent Store FWM Framework.
Status & development of the software for CALICE-DAQ Tao Wu On behalf of UK Collaboration.
Reconfigurable Communication Interface Between FASTER and RTSim Dec0907.
Designing a Middleware Server for Abstract Database Connection.
Copyright 2007, Information Builders. Slide 1 iWay Web Services and WebFOCUS Consumption Michael Florkowski Information Builders.
1 Chapter Overview Monitoring Access to Shared Folders Creating and Sharing Local and Remote Folders Monitoring Network Users Using Offline Folders and.
Silberschatz, Galvin and Gagne ©2011 Operating System Concepts Essentials – 8 th Edition Chapter 2: The Linux System Part 5.
Event Management. EMU Graham Heyes April Overview Background Requirements Solution Status.
Marcelo R.N. Mendes. What is FINCoS? A Java-based set of tools for data generation, load submission, and performance measurement of event processing systems;
INFORMATION DEPLOYED. SOLUTIONS ADVANCED. MISSIONS ACCOMPLISHED. PDS Punch-Out v1.0 SPS Spotlight Series October 2014.
Scenario use cases Szymon Mueller PSNC. Agenda 1.General description of experiment use case. 2.Detailed description of use cases: 1.Preparation for observation.
LHC RT feedback(s) CO Viewpoint Kris Kostro, AB/CO/FC.
1 Copyright © 2008, Oracle. All rights reserved. Repository Basics.
Fermilab Scientific Computing Division Fermi National Accelerator Laboratory, Batavia, Illinois, USA. Off-the-Shelf Hardware and Software DAQ Performance.
SQL Database Management
SPS Spotlight Series October 2014
Detecting Web Attacks Using Multi-Stage Log Analysis
Databases and DBMSs Todd S. Bacastow January 2005.
Monitoring Windows Server 2012
Data Transport for Online & Offline Processing
Data, Databases, and DBMSs
Presentation transcript:

Marcelo R.N. Mendes

What is FINCoS? A set of tools for data generation, load submission, and performance measurement of CEP systems; Main Characteristics: Flexible; Independent of particular workloads; Neutral (not bound to any specific CEP product); Correctness check; Scalable. 2CISUC, University of Coimbra

FINCoS: Architecture 3CISUC, University of Coimbra Scalability: It is easy to increase the load: simply add more Drivers! Validation and Performance Measuring: Plug-and-Play Validators Independence of CEP Products and workloads Flexibility: Several Test Options

FINCoS: Components Controller Main Interface with the user. Allows to: Create reusable test setups; Control Drivers and Sinks (e.g., load, start, stop); Alter workload parameters on-the- fly (e.g., event submission rates, switch phases) 4CISUC, University of Coimbra

FINCoS: Components Driver Simulates external sources of events; Submits load to the SUT; Includes data generation mechanism; Sink Receives query results from CEP engine; Stores output events in log files or send them via network for subsequent validation; 5CISUC, University of Coimbra

FINCoS: Components Performance Monitor Collect Metrics of Performance Runs Two Modes: Online (network); Offline (log files). 6CISUC, University of Coimbra

FINCoS: Components January, 2012CISUC, University of Coimbra - Adapter On Input: converts from the framework neutral representation (CSV) to CEP system’s native representation On Ouput: converts output events from CEP system’s native format to neutral representation (CSV)

Lesson 1: Creating a Test Setup 1. Configure a Driver 1. Decomposable Workload 2. Synthetic vs. Thirdy-Party Dataset 3. Data Generation Options 4. Event Arrival Process 2. Configure a Sink January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - unique identifier number of threads used for load generation save generated data to disk? real time performance monitoring? to where Driver send the events machine that hosts the Driver

January, 2012CISUC, University of Coimbra - Workload can be split in independent phases

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Chooses the type of workload for this phase Sets events arrival process Event Mix Events are generated in a ordered way When data generation happens To ensure repeatability…

January, 2012CISUC, University of Coimbra - Configure event types…

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Configure Event Type Schema

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Column Name

January, 2012CISUC, University of Coimbra - Column Type

January, 2012CISUC, University of Coimbra - Data Generation Options

January, 2012CISUC, University of Coimbra - Add Values

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - unique identifier List of event types this Sink subscribes to from where Sink receive events machine that hosts the Sink Port used by Sink to receive events save generated data to disk? real time performance monitoring?

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Done!

Lesson 2: Connecting with a CEP engine 1. Configure Connection Properties 2. Load FINCoS Adapter application January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - List of input streamsList of output streams No Information Available Yet!

January, 2012CISUC, University of Coimbra - Retrieve list of streams…

January, 2012CISUC, University of Coimbra - … from the setup file created earlier

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Load vendor-specific connection properties …

January, 2012CISUC, University of Coimbra - Engine=Esper Configuration_file_path=C:\\FINCoS\\queries\\esper\\Q1\\Stream_Set.xml Queries_path=C:\\FINCoS\\queries\\esper\\Q1\\Query_Set.xml Event_format=Map Engine=Esper Configuration_file_path=C:\\FINCoS\\queries\\esper\\Q1\\Stream_Set.xml Queries_path=C:\\FINCoS\\queries\\esper\\Q1\\Query_Set.xml Event_format=Map

January, 2012CISUC, University of Coimbra - Connect to CEP engine…

January, 2012CISUC, University of Coimbra - The list of streams in the CEP engine is retrieved and matched against the configured ones in the test setup

January, 2012CISUC, University of Coimbra - Loads the Adapter: 1.Open Server Socket for Drivers (Input) 2.Subscribes to streams at the CEP engine (Output)

January, 2012CISUC, University of Coimbra - Done!

Lesson 3: Running Tests 1. Load Drivers and Sinks 2. Start Load Submission 3. Control Load Submission NOTE: At this point the following steps must have been completed: 1. Creation of a test setup; 2. Connection with a CEP engine; 3. Initialization of the FINCoS Daemon Service at the machines where Drivers and Sinks are intended to run; January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Load components

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Start Load Submission

January, 2012CISUC, University of Coimbra - Sent/Received counts

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

Lesson 4: Collecting Performance Metrics 1. Offline Performance Measurement 1. After test completion, use FINCoS Performance Monitor to process log files 2. Online Performance Measurement 1. Enable realtime monitoring at Drivers and Sinks; 2. Initialize FINCoS Performance Monitor in the Realtime Mode before test starts. January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Offline Performance Measurement

January, 2012CISUC, University of Coimbra - Add log files

January, 2012CISUC, University of Coimbra - Log file created after test completion

January, 2012CISUC, University of Coimbra - Configure M.I. here: Optionally, save collected metrics to a file Process log files

January, 2012CISUC, University of Coimbra - View Results

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Select the stream

January, 2012CISUC, University of Coimbra - Select the metric

January, 2012CISUC, University of Coimbra - Select exhibition scale

January, 2012CISUC, University of Coimbra - Add Metrics to the Chart

January, 2012CISUC, University of Coimbra - Change Visualization Options

Lesson 4: Collecting Performance Metrics (...cont) 1. Offline Performance Measurement 1. After test completion, use FINCoS Performance Monitor to process log files 2. Online Performance Measurement 1. Enable realtime monitoring at Drivers and Sinks; 2. Initialize FINCoS Performance Monitor in the Realtime Mode before test starts. January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Edit Driver Configuration

January, 2012CISUC, University of Coimbra - Enable Runtime Monitoring

January, 2012CISUC, University of Coimbra - To where send events Send only a fraction of events

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Edit Sink Configuration

January, 2012CISUC, University of Coimbra - Enable Runtime Monitoring

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Select a test setup file…

January, 2012CISUC, University of Coimbra - … the one we have just modified

January, 2012CISUC, University of Coimbra - Performance Monitor is now listening to connections of Drivers and Sinks

January, 2012CISUC, University of Coimbra - Add counters…

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra - Drivers and Sinks are now connected with Performance Monitor

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

Lesson 5: Setting Test Options 1. Response Time Measurement Mode 2. Communication Mode 3. Log Flushing January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

January, 2012CISUC, University of Coimbra -

Response Time Measurement January, 2012CISUC, University of Coimbra - DRIVER CEP ENGINE CEP ENGINE SINK ADAPTER send convert input convert output process input forward generate result forward send 1 1

Response Time Measurement January, 2012CISUC, University of Coimbra - DRIVER CEP ENGINE CEP ENGINE SINK ADAPTER send convert input convert output process input forward generate result forward send Δt = t4 – t1 End-to-end, in milliseconds: From Driver up to Sink

Response Time Measurement January, 2012CISUC, University of Coimbra - DRIVER CEP ENGINE CEP ENGINE SINK ADAPTER send convert input convert output process input forward generate result forward send Δt = t3 – t2 Inside Adapter, in nanoseconds: From immediately before the input event is forwarded to CEP engine to immediately after the result is received

When to use End-to-End RT Measurement Mode When communication mode is set to DIRECT (mandatory); When it is acceptable to have a less accurate response time measurement in order to reduce the overhead in the server machine; When you want to consider communication and conversion time as part of response time; When Drivers and Sinks run in the same machine (no problems with clock synchronization). January, 2012CISUC, University of Coimbra -

When to use “Inside Adapter” RT Measurement Mode When accurate response time measurement is required; When you want exclude communication and conversion times from response time; When Drivers and Sinks run in different machines (requires synchronization between machines: inherently inaccurate ≈10ms); When the server machine can afford with the additional overhead of response time measurement. January, 2012CISUC, University of Coimbra -