Design and Implementation of PARK (PARallel Kernel for data fitting) Paul KIENZLE, Wenwu CHEN and Ziwen FU Reflectometry Group.

Slides:



Advertisements
Similar presentations
Tutorial for PARK data fitting Paul KIENZLE, Wenwu CHEN and Ziwen FU Reflectometry Group.
Advertisements

MAP REDUCE PROGRAMMING Dr G Sudha Sadasivam. Map - reduce sort/merge based distributed processing Best for batch- oriented processing Sort/merge is primitive.
Chess Problem Solver Solves a given chess position for checkmate Problem input in text format.
M-grid Using Ubiquitous Web Technologies to create a Computational Grid R J Walters and S Crouch 21 January 2009.
Spark: Cluster Computing with Working Sets
Summary Role of Software (1 slide) ARCS Software Architecture (4 slides) SNS -- Caltech Interactions (3 slides)
Experimental Facilities Division ANL-ORNL SNS Experimental Data Standards (Status) Richard Riedel SNS Data Acquisition Group Leader.
The new The new MONARC Simulation Framework Iosif Legrand  California Institute of Technology.
© DSRG 2001www.cs.agh.edu.pl Cross Grid Workshop - Kraków Krzysztof Zieliński, Sławomir Zieliński University of Mining and Metallurgy {kz,
Asynchronous Web Services Approach Enrique de Andrés Saiz.
DIRAC API DIRAC Project. Overview  DIRAC API  Why APIs are important?  Why advanced users prefer APIs?  How it is done?  What is local mode what.
DIANE Overview Germán Carrera, Alfredo Solano (CNB/CSIC) EMBRACE COURSE Monday 19th of February to Friday 23th. CNB-CSIC Madrid.
Apache Airavata GSOC Knowledge and Expertise Computational Resources Scientific Instruments Algorithms and Models Archived Data and Metadata Advanced.
GRAPPA Part of Active Notebook Science Portal project A “notebook” like GRAPPA consists of –Set of ordinary web pages, viewable from any browser –Editable.
Self Adaptivity in Grid Computing Reporter : Po - Jen Lo Sathish S. Vadhiyar and Jack J. Dongarra.
Resource Management and Accounting Working Group Working Group Scope and Components Progress made Current issues being worked Next steps Discussions involving.
Towards a Javascript CoG Kit Gregor von Laszewski Fugang Wang Marlon Pierce Gerald Guo
LOGO Scheduling system for distributed MPD data processing Gertsenberger K. V. Joint Institute for Nuclear Research, Dubna.
CS525: Special Topics in DBs Large-Scale Data Management Hadoop/MapReduce Computing Paradigm Spring 2013 WPI, Mohamed Eltabakh 1.
Process Management Working Group Process Management “Meatball” Dallas November 28, 2001.
DUCKS – Distributed User-mode Chirp- Knowledgeable Server Joe Thompson Jay Doyle.
Debugging and Profiling GMAO Models with Allinea’s DDT/MAP Georgios Britzolakis April 30, 2015.
INFSO-RI Enabling Grids for E-sciencE Workload Management System Mike Mineter
Some Design Notes Iteration - 2 Method - 1 Extractor main program Runs from an external VM Listens for RabbitMQ messages Starts a light database engine.
MACCE and Real-Time Schedulers Steve Roberts EEL 6897.
Parallel Kernels*: An Architecture for Parallel Distributed Computing N. Patel (University of Maryland)‏ M. McKerns (California Institute of Technology)‏
Grid Computing at Yahoo! Sameer Paranjpye Mahadev Konar Yahoo!
Giuseppe Codispoti INFN - Bologna Egee User ForumMarch 2th BOSS: the CMS interface for job summission, monitoring and bookkeeping W. Bacchi, P.
The perfSONAR Test Harness Brian Tierney, LBNL/ESnet.
A remote control robot with webcam. Responsibilities User Interface Communicate with server Webcam Display Server Web Server Collaborators Work: Harkins.
ABone Architecture and Operation ABCd — ABone Control Daemon Server for remote EE management On-demand EE initiation and termination Automatic EE restart.
ROOT-CORE Team 1 PROOF xrootd Fons Rademakers Maarten Ballantjin Marek Biskup Derek Feichtinger (ARDA) Gerri Ganis Guenter Kickinger Andreas Peters (ARDA)
Nguyen Tuan Anh. VN-Grid: Goals  Grid middleware (focus of this presentation)  Tuan Anh  Grid applications  Hoai.
A Utility-based Approach to Scheduling Multimedia Streams in P2P Systems Fang Chen Computer Science Dept. University of California, Riverside
PoC Induction 19-April VBrowser (VL-e Toolkit) The single point of access to the grid  Medical use case: functional MRI (fMRI)  VBrowser design  VBrowser.
Connect. Communicate. Collaborate PerfsonarUI plug-in tutorial Nina Jeliazkova ISTF, Bulgaria.
Interactive Workflows Branislav Šimo, Ondrej Habala, Ladislav Hluchý Institute of Informatics, Slovak Academy of Sciences.
Moving Web Apps From Synchronous to Asynchronous Processing Jason Carreira Architect, ePlus Systems OpenSymphony member.
UI Framework for Distributed Fitting Service Paul Kienzle Wenwu Chen, Ziwen Fu Reflectometry Group, NIST.
SWGData and Software Access - 1 UCB, Nov 15/16, 2006 THEMIS SCIENCE WORKING TEAM MEETING Data and Software Access Ken Bromund GST Inc., at NASA/GSFC.
AliEn AliEn at OSC The ALICE distributed computing environment by Bjørn S. Nilsen The Ohio State University.
Module: Software Engineering of Web Applications Chapter 2: Technologies 1.
Linux Operations and Administration
K. Harrison CERN, 22nd September 2004 GANGA: ADA USER INTERFACE - Ganga release status - Job-Options Editor - Python support for AJDL - Job Builder - Python.
Hadoop/MapReduce Computing Paradigm 1 CS525: Special Topics in DBs Large-Scale Data Management Presented By Kelly Technologies
Process Manager Specification Rusty Lusk 1/15/04.
Technical lssues for the Knowledge Engineering Competition Stefan Edelkamp Jeremy Frank.
IBM Express Runtime Quick Start Workshop © 2007 IBM Corporation Deploying a Solution.
David Adams ATLAS ATLAS Distributed Analysis and proposal for ATLAS-LHCb system David Adams BNL March 22, 2004 ATLAS-LHCb-GANGA Meeting.
Origami: Scientific Distributed Workflow in McIDAS-V Maciek Smuga-Otto, Bruce Flynn (also Bob Knuteson, Ray Garcia) SSEC.
RENKEI:UGI Takashi Sasaki. Project history The RENKEI project led by Prof. Ken Miura of NII is funded by MEXT during JFY The goal of the project.
Active-HDL Server Farm Course 11. All materials updated on: September 30, 2004 Outline 1.Introduction 2.Advantages 3.Requirements 4.Installation 5.Architecture.
Mind Q Systems Leaders in Training /7, 2nd Floor, Srinivasa Nagar Colony (W) Above HDFC Bank, S.R. Nagar Hyderabad Tel : /92.
Geant4 GRID production Sangwan Kim, Vu Trong Hieu, AD At KISTI.
Wednesday NI Vision Sessions
Review of PARK Reflectometry Group 10/31/2007. Outline Goal Hardware target Software infrastructure PARK organization Use cases Park Components. GUI /
ANALYSIS TRAIN ON THE GRID Mihaela Gheata. AOD production train ◦ AOD production will be organized in a ‘train’ of tasks ◦ To maximize efficiency of full.
1 Chapter 5: Threads Overview Multithreading Models & Issues Read Chapter 5 pages
Petr Škoda, Jakub Koza Astronomical Institute Academy of Sciences
Review of Last Year’s Midterm
Managing, Storing, and Executing DTS Packages
BOSS: the CMS interface for job summission, monitoring and bookkeeping
Async or Parallel? No they aren’t the same thing!
BOSS: the CMS interface for job summission, monitoring and bookkeeping
NGS computation services: APIs and Parallel Jobs
DUCKS – Distributed User-mode Chirp-Knowledgeable Server
Chapter 4 Multithreading programming
DiFX Python Interface John Spitzak (USNO).
Snippet Engine as a Database Server
DIBBs Brown Dog BDFiddle
Presentation transcript:

Design and Implementation of PARK (PARallel Kernel for data fitting) Paul KIENZLE, Wenwu CHEN and Ziwen FU Reflectometry Group

Distributed Computing Environment Service Server Master Node User Cluster Working Nodes User/Client ServiceServer Management WorkingServer User

Service Server WorkingServer WorkingClient Service User JobQueueSys MessageQueueSy s ServiceServer

Prototype Demo Download Source code: –svn co Edit cluster config file: –park/config/hosts Start service server –park/servers/mapServer.py Start client –park/client/AppJob.py Provide services –park/services

Further Improvement (working server) 3 running modes –Command: simple commands, short time ls, top, kill, … –Thread: python functions, short time Multithreading, not recommend –Process: normal services, long time any executable programs Task and task queue management: –Restrict the number of running commands, threads, and processes, and their running times –Kill the task by its task ID –Query the task queue status

Further Improvement (Service server) –More stable and efficient for the service server –More functions for service server Submit job Register as a listener Query job status and services Kill job by its ID Run job on specified node (s) –Better job queue and message queue management –Pluggable reduce functions –Restart the working node when it crashes

User Interface Service Server Scripting User Interface GUI Files Web External Apps data

Software Infrastructure of PARK for data fitting Service Server Service Working Nodes User Interface Scientist View DeveloperReduce Service Developer Data reduction Model Developer Data simulation Data presentation Data View

Procedure for data fitting dataset Reduction / filter metadata Theory parameter Experimental data Simulation data uniplexor multiplexor optimizer Variables Dependency Constraints

XML tree for data fitting DataFitting Optimizers* Multiplexor DataSet Variables* DataFilterFunctions* Dependency Constraints Uniplexors* Theory* Parameters* Uniplexors DataSource Variable

Base Classes for XML/ Object tree For the developer, XML tree is actual the object tree. It is the common task to transfer between the XML tree and object tree

Classes from XML tree DataFitting Optimizer Multiplexor DataSetVariables DataFilterFunction Dependency Constraints Uniplexor Theory Parameter DataSource Variable XmlObject XmlAttributeObject Model DeveloperReduction Developer

Basic functions for classes Datasource: –read(), write() :read/write to local file system –fetch(), send() : read/write to remote file system –getdata(hints:object), getmetadata(hints:object): Get the data and meta data DatafilterFunction: –filter (input:object, hints: object)

Basic functions for classes Theory: –calculate(): do the calculation –getSimulationData(): get the simulation data Parameter: –hasDerivative(order: int, hints:object) Query whether the its derivatives are available

Example: sans optimization

XML tree for request Request JobQuery JobSubmission* JobGroup* DataFitting JobRegister JobKill ReduceFunction Jobs* Task TaskQuery Command User Inputs* TaskKill Reduction function Developer External application Developer, UI Developer Service Server Working Server

XML tree for UI UI Request Viewer Viewer Developer, UI developer WebViewerFileViewer GUI Viewer Viewer

GUI (MVC pattern) OptimizerViewer ParameterViewer ModelViewer DataSetViewer Variables Dependency Constraints ReplyViewerRequestViewer GUIViewer StatusViewer

GUI Demo Prototype GUI MVC GUI