Production Manager Tools (New Architecture)

Slides:



Advertisements
Similar presentations
A Workflow Engine with Multi-Level Parallelism Supports Qifeng Huang and Yan Huang School of Computer Science Cardiff University
Advertisements

Database System Concepts and Architecture
1 OBJECTIVES To generate a web-based system enables to assemble model configurations. to submit these configurations on different.
Setting up of condor scheduler on computing cluster Raman Sehgal NPD-BARC.
Grid and CDB Janusz Martyniak, Imperial College London MICE CM37 Analysis, Software and Reconstruction.
DataGrid is a project funded by the European Union 22 September 2003 – n° 1 EDG WP4 Fabric Management: Fabric Monitoring and Fault Tolerance
David Adams ATLAS DIAL Distributed Interactive Analysis of Large datasets David Adams BNL March 25, 2003 CHEP 2003 Data Analysis Environment and Visualization.
Rheeve: A Plug-n-Play Peer- to-Peer Computing Platform Wang-kee Poon and Jiannong Cao Department of Computing, The Hong Kong Polytechnic University ICDCSW.
Interpret Application Specifications
K.Harrison CERN, 23rd October 2002 HOW TO COMMISSION A NEW CENTRE FOR LHCb PRODUCTION - Overview of LHCb distributed production system - Configuration.
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Overview of Database Languages and Architectures.
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.
Bookkeeping data Monitoring info Get jobs Site A Site B Site C Site D Agent Production service Monitoring service Bookkeeping service Agent © Andrei Tsaregorodtsev.
Large scale data flow in local and GRID environment V.Kolosov, I.Korolko, S.Makarychev ITEP Moscow.
Database System Concepts and Architecture Lecture # 3 22 June 2012 National University of Computer and Emerging Sciences.
3 Sept 2001F HARRIS CHEP, Beijing 1 Moving the LHCb Monte Carlo production system to the GRID D.Galli,U.Marconi,V.Vagnoni INFN Bologna N Brook Bristol.
Computing Infrastructure Status. LHCb Computing Status LHCb LHCC mini-review, February The LHCb Computing Model: a reminder m Simulation is using.
3rd June 2004 CDF Grid SAM:Metadata and Middleware Components Mòrag Burgon-Lyon University of Glasgow.
QCDGrid Progress James Perry, Andrew Jackson, Stephen Booth, Lorna Smith EPCC, The University Of Edinburgh.
Cosener’s House – 30 th Jan’031 LHCb Progress & Plans Nick Brook University of Bristol News & User Plans Technical Progress Review of deliverables.
Nick Brook Current status Future Collaboration Plans Future UK plans.
1 DIRAC – LHCb MC production system A.Tsaregorodtsev, CPPM, Marseille For the LHCb Data Management team CHEP, La Jolla 25 March 2003.
LHCb week, 27 May 2004, CERN1 Using services in DIRAC A.Tsaregorodtsev, CPPM, Marseille 2 nd ARDA Workshop, June 2004, CERN.
Stuart Wakefield Imperial College London Evolution of BOSS, a tool for job submission and tracking W. Bacchi, G. Codispoti, C. Grandi, INFN Bologna D.
Introduction to dCache Zhenping (Jane) Liu ATLAS Computing Facility, Physics Department Brookhaven National Lab 09/12 – 09/13, 2005 USATLAS Tier-1 & Tier-2.
Status of the LHCb MC production system Andrei Tsaregorodtsev, CPPM, Marseille DataGRID France workshop, Marseille, 24 September 2002.
November SC06 Tampa F.Fanzago CRAB a user-friendly tool for CMS distributed analysis Federica Fanzago INFN-PADOVA for CRAB team.
PROGRESS: ICCS'2003 GRID SERVICE PROVIDER: How to improve flexibility of grid user interfaces? Michał Kosiedowski.
Hands-On Microsoft Windows Server Implementing Microsoft Internet Information Services Microsoft Internet Information Services (IIS) –Software included.
4/5/2007Data handling and transfer in the LHCb experiment1 Data handling and transfer in the LHCb experiment RT NPSS Real Time 2007 FNAL - 4 th May 2007.
And Tier 3 monitoring Tier 3 Ivan Kadochnikov LIT JINR
LHCb Software Week November 2003 Gennady Kuznetsov Production Manager Tools (New Architecture)
The Experiments – progress and status Roger Barlow GridPP7 Oxford 2 nd July 2003.
© Geodise Project, University of Southampton, Knowledge Management in Geodise Geodise Knowledge Management Team Barry Tao, Colin Puleston, Liming.
T3 analysis Facility V. Bucard, F.Furano, A.Maier, R.Santana, R. Santinelli T3 Analysis Facility The LHCb Computing Model divides collaboration affiliated.
1 DIRAC Job submission A.Tsaregorodtsev, CPPM, Marseille LHCb-ATLAS GANGA Workshop, 21 April 2004.
Tier3 monitoring. Initial issues. Danila Oleynik. Artem Petrosyan. JINR.
The GridPP DIRAC project DIRAC for non-LHC communities.
K. Harrison CERN, 22nd September 2004 GANGA: ADA USER INTERFACE - Ganga release status - Job-Options Editor - Python support for AJDL - Job Builder - Python.
+ AliEn site services and monitoring Miguel Martinez Pedreira.
ATLAS-specific functionality in Ganga - Requirements for distributed analysis - ATLAS considerations - DIAL submission from Ganga - Graphical interfaces.
INFSO-RI Enabling Grids for E-sciencE Using of GANGA interface for Athena applications A. Zalite / PNPI.
© Geodise Project, University of Southampton, Workflow Application Fenglian Xu 07/05/03.
Gennaro Tortone, Sergio Fantinel – Bologna, LCG-EDT Monitoring Service DataTAG WP4 Monitoring Group DataTAG WP4 meeting Bologna –
Markus Frank (CERN) & Albert Puig (UB).  An opportunity (Motivation)  Adopted approach  Implementation specifics  Status  Conclusions 2.
© Geodise Project, University of Southampton, Workflow Support for Advanced Grid-Enabled Computing Fenglian Xu *, M.
Ganga/Dirac Data Management meeting October 2003 Gennady Kuznetsov Production Manager Tools and Ganga (New Architecture)
The Database Project a starting work by Arnauld Albert, Cristiano Bozza.
Geant4 GRID production Sangwan Kim, Vu Trong Hieu, AD At KISTI.
SAM architecture EGEE 07 Service Availability Monitor for the LHC experiments Simone Campana, Alessandro Di Girolamo, Nicolò Magini, Patricia Mendez Lorenzo,
9 Copyright © 2004, Oracle. All rights reserved. Getting Started with Oracle Migration Workbench.
Advanced Computing Facility Introduction
Business System Development
L’analisi in LHCb Angelo Carbone INFN Bologna
Chapter 2: Database System Concepts and Architecture - Outline
Belle II Physics Analysis Center at TIFR
Database System Concepts and Architecture
DIRAC Production Manager Tools
TYPES OF SERVER. TYPES OF SERVER What is a server.
The Ganga User Interface for Physics Analysis on Distributed Resources
Database System Concepts and Architecture
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Database System Concepts and Architecture.
Monitoring of the infrastructure from the VO perspective
Distributed Systems Bina Ramamurthy 11/30/2018 B.Ramamurthy.
Wide Area Workload Management Work Package DATAGRID project
Status and plans for bookkeeping system and production tools
Production client status
Sending data to EUROSTAT using STATEL and STADIUM web client
The LHCb Computing Data Challenge DC06
Presentation transcript:

Production Manager Tools (New Architecture) LHCb Data Management Meeting 30 September 2003 Gennady Kuznetsov

Lessons Learnt © Andrei Tsaregorodtsev DataGRID instability problems persisting : MDS information system failures ; Site miss configuration ; Outbound IP connectivity is not available on all sites : Needed for the LHCb software installation on per job basis ; Needed for jobs exchanging messages with production services . Data transfer : bbftp file transport replaced by the replica manager tools ; Next run of tests will hopefully be more successful : better understanding of the system ; Use other schema for job delivery to a worker node . © Andrei Tsaregorodtsev Presenter Name: Gennady Kuznetsov Facility Name: PPD

Other Schema Other schema Flexible component architecture Full forward and backward compatibility of jobs. No needs for installation of the control or monitoring software on the node or site Workflows, Steps, Modules stored on server or in Production Manager Library as XML file. Job is Python code generated from XML during submission. Monitoring code got embedded into Jobs automatically Agent (for development) Agents can be run on any computer local or remote Single agent can control one or many sites simultaneously Agent implements Andrey’s pool job submission schema. Presenter Name: Facility Name:

Components Step Workflow Production Module Job Step We add Module as additional component of the architecture Module Step Levels of usage: Module – Programmer Step – Production manager Workflow – User Step Workflow Job Production This module structure allow as to construct any algorithm as combination of modules. Each step generates job as a Python program. Presenter Name: Facility Name: Presenter Name: Gennady Kuznetsov Facility Name: PPD

Python code of single module. Can be many classes. Module Editor Python code of single module. Can be many classes. Module Name Stored as XML file Description Module variables. Presenter Name: Facility Name:

Step Editor Stored as XML file, where all modules are embedded Graphical representation of Module relationship (not ready) Stored as XML file, where all modules are embedded Step Name Description Variables of currently selected instance Definitions of Modules Instances of Modules Selected instance Presenter Name: Facility Name:

Workflow Editor Not ready yet. It will links all jobs in a workflow instance. The simplest workflow is a single step. It will combine workflow and “Vector” and generate as many instances of workflow as many members in a vector. For example it can be list of numbers (job number or name) or it can be a list of files for reconstructions or analysis. Presenter Name: Facility Name:

Architecture Central Services DIRAC Personal Desktop Node IDL+Python scoreboard Architecture Production Manager Agent on the Node replaced by automatically generated Python program No any software required except PYTHON Central Services DIRAC Personal Desktop Node Node Grid Front End IDL+Python via SSH Node DIRAC Personal Agent Node Node Batch Front End shell+Python via SSH Node Presenter Name: Gennady Kuznetsov Facility Name: PPD

DIRAC Personal Desktop Language C++ with QT Provides tools to create Module Library for the experiment (for Programmer). Provides tools to construct Steps and Workflows from Module Library. (for Production Manager) Saves all objects as XML files. Generates batch of Python jobs for the submission into GRID or Batch System. DIRAC Personal Desktop Module Editor Step Editor Workflow Editor Production Manager Monitoring Manager Code Generator Presenter Name: Gennady Kuznetsov Facility Name: PPD

Personal Agent Language Java. Represent User or Production Manager in the network on a permanent basis (jobs does not crash without agent). Provides means to submit and monitor jobs to any number of Batch or GRID front ends via SSH of local calls. Provides local disk space for data retrieval. Allow job dependency. DIRAC Personal Agent Job Dependency Service Job Submission Service Internal Monitoring Srv. Data Retrieval Service Local Disk Job pool New Not ready Ready Submitted Running Output ready Done Job states: Presenter Name: Gennady Kuznetsov Facility Name: PPD

Central Services (CERN) Job Pool Prepackaged Applications archive Central Services Production Service Monitoring Service Bookkeeping Service Storage Service Application distr. ser. Data base with web front-end Oracle at CERN CASTOR or Replica Manager Presenter Name: Gennady Kuznetsov Facility Name: PPD