6/2/2015 Michael Diesburg HCP 2005 1 Distributed Computing at the Tevatron D0 Computing and Event Model Michael Diesburg, Fermilab For the D0 Collaboration.

Slides:



Advertisements
Similar presentations
GridPP July 2003Stefan StonjekSlide 1 SAM middleware components Stefan Stonjek University of Oxford 7 th GridPP Meeting 02 nd July 2003 Oxford.
Advertisements

Amber Boehnlein, FNAL D0 Computing Model and Plans Amber Boehnlein D0 Financial Committee November 18, 2002.
Duke Atlas Tier 3 Site Doug Benjamin (Duke University)
Grid and CDB Janusz Martyniak, Imperial College London MICE CM37 Analysis, Software and Reconstruction.
23/04/2008VLVnT08, Toulon, FR, April 2008, M. Stavrianakou, NESTOR-NOA 1 First thoughts for KM3Net on-shore data storage and distribution Facilities VLV.
EventStore Managing Event Versioning and Data Partitioning using Legacy Data Formats Chris Jones Valentin Kuznetsov Dan Riley Greg Sharp CLEO Collaboration.
Chapter 1 and 2 Computer System and Operating System Overview
DATA PRESERVATION IN ALICE FEDERICO CARMINATI. MOTIVATION ALICE is a 150 M CHF investment by a large scientific community The ALICE data is unique and.
Ian M. Fisk Fermilab February 23, Global Schedule External Items ➨ gLite 3.0 is released for pre-production in mid-April ➨ gLite 3.0 is rolled onto.
The SAM-Grid Fabric Services Gabriele Garzoglio (for the SAM-Grid team) Computing Division Fermilab.
Ian Fisk and Maria Girone Improvements in the CMS Computing System from Run2 CHEP 2015 Ian Fisk and Maria Girone For CMS Collaboration.
The D0 Monte Carlo Challenge Gregory E. Graham University of Maryland (for the D0 Collaboration) February 8, 2000 CHEP 2000.
GLAST LAT ProjectDOE/NASA Baseline-Preliminary Design Review, January 8, 2002 K.Young 1 LAT Data Processing Facility Automatically process Level 0 data.
9/16/2000Ian Bird/JLAB1 Planning for JLAB Computational Resources Ian Bird.
The SAMGrid Data Handling System Outline:  What Is SAMGrid?  Use Cases for SAMGrid in Run II Experiments  Current Operational Load  Stress Testing.
Remote Production and Regional Analysis Centers Iain Bertram 24 May 2002 Draft 1 Lancaster University.
Grid Job and Information Management (JIM) for D0 and CDF Gabriele Garzoglio for the JIM Team.
03/27/2003CHEP20031 Remote Operation of a Monte Carlo Production Farm Using Globus Dirk Hufnagel, Teela Pulliam, Thomas Allmendinger, Klaus Honscheid (Ohio.
Central Reconstruction System on the RHIC Linux Farm in Brookhaven Laboratory HEPIX - BNL October 19, 2004 Tomasz Wlodek - BNL.
CDF data production models 1 Data production models for the CDF experiment S. Hou for the CDF data production team.
November 7, 2001Dutch Datagrid SARA 1 DØ Monte Carlo Challenge A HEP Application.
Building a distributed software environment for CDF within the ESLEA framework V. Bartsch, M. Lancaster University College London.
D0 Farms 1 D0 Run II Farms M. Diesburg, B.Alcorn, J.Bakken, T.Dawson, D.Fagan, J.Fromm, K.Genser, L.Giacchetti, D.Holmgren, T.Jones, T.Levshina, L.Lueking,
D0 SAM – status and needs Plagarized from: D0 Experiment SAM Project Fermilab Computing Division.
3rd June 2004 CDF Grid SAM:Metadata and Middleware Components Mòrag Burgon-Lyon University of Glasgow.
Snapshot of the D0 Computing and Operations Planning Process Amber Boehnlein For the D0 Computing Planning Board.
CHEP 2003Stefan Stonjek1 Physics with SAM-Grid Stefan Stonjek University of Oxford CHEP th March 2003 San Diego.
CHEP'07 September D0 data reprocessing on OSG Authors Andrew Baranovski (Fermilab) for B. Abbot, M. Diesburg, G. Garzoglio, T. Kurca, P. Mhashilkar.
DØ RAC Working Group Report Progress Definition of an RAC Services provided by an RAC Requirements of RAC Pilot RAC program Open Issues DØRACE Meeting.
Finnish DataGrid meeting, CSC, Otaniemi, V. Karimäki (HIP) DataGrid meeting, CSC V. Karimäki (HIP) V. Karimäki (HIP) Otaniemi, 28 August, 2000.
GridPP18 Glasgow Mar 07 DØ – SAMGrid Where’ve we come from, and where are we going? Evolution of a ‘long’ established plan Gavin Davies Imperial College.
DØ Computing Model & Monte Carlo & Data Reprocessing Gavin Davies Imperial College London DOSAR Workshop, Sao Paulo, September 2005.
21 st October 2002BaBar Computing – Stephen J. Gowdy 1 Of 25 BaBar Computing Stephen J. Gowdy BaBar Computing Coordinator SLAC 21 st October 2002 Second.
6/26/01High Throughput Linux Clustering at Fermilab--S. Timm 1 High Throughput Linux Clustering at Fermilab Steven C. Timm--Fermilab.
Integrating JASMine and Auger Sandy Philpott Thomas Jefferson National Accelerator Facility Jefferson Ave. Newport News, Virginia USA 23606
RAL Site Report John Gordon IT Department, CLRC/RAL HEPiX Meeting, JLAB, October 2000.
D0RACE: Testbed Session Lee Lueking D0 Remote Analysis Workshop February 12, 2002.
Operating Systems David Goldschmidt, Ph.D. Computer Science The College of Saint Rose CIS 432.
16 September GridPP 5 th Collaboration Meeting D0&CDF SAM and The Grid Act I: Grid, Sam and Run II Rick St. Denis – Glasgow University Act II: Sam4CDF.
JLAB Computing Facilities Development Ian Bird Jefferson Lab 2 November 2001.
What is SAM-Grid? Job Handling Data Handling Monitoring and Information.
Data reprocessing for DZero on the SAM-Grid Gabriele Garzoglio for the SAM-Grid Team Fermilab, Computing Division.
GridPP11 Liverpool Sept04 SAMGrid GridPP11 Liverpool Sept 2004 Gavin Davies Imperial College London.
6/23/2005 R. GARDNER OSG Baseline Services 1 OSG Baseline Services In my talk I’d like to discuss two questions:  What capabilities are we aiming for.
Status of the Bologna Computing Farm and GRID related activities Vincenzo M. Vagnoni Thursday, 7 March 2002.
UTA MC Production Farm & Grid Computing Activities Jae Yu UT Arlington DØRACE Workshop Feb. 12, 2002 UTA DØMC Farm MCFARM Job control and packaging software.
Outline: Status: Report after one month of Plans for the future (Preparing Summer -Fall 2003) (CNAF): Update A. Sidoti, INFN Pisa and.
Adapting SAM for CDF Gabriele Garzoglio Fermilab/CD/CCF/MAP CHEP 2003.
Batch Software at JLAB Ian Bird Jefferson Lab CHEP February, 2000.
A UK Computing Facility John Gordon RAL October ‘99HEPiX Fall ‘99 Data Size Event Rate 10 9 events/year Storage Requirements (real & simulated data)
D0 Farms 1 D0 Run II Farms M. Diesburg, B.Alcorn, J.Bakken, R. Brock,T.Dawson, D.Fagan, J.Fromm, K.Genser, L.Giacchetti, D.Holmgren, T.Jones, T.Levshina,
Distributed Physics Analysis Past, Present, and Future Kaushik De University of Texas at Arlington (ATLAS & D0 Collaborations) ICHEP’06, Moscow July 29,
D0 File Replication PPDG SLAC File replication workshop 9/20/00 Vicky White.
LHCC Referees Meeting – 28 June LCG-2 Data Management Planning Ian Bird LHCC Referees Meeting 28 th June 2004.
Meeting with University of Malta| CERN, May 18, 2015 | Predrag Buncic ALICE Computing in Run 2+ P. Buncic 1.
A Data Handling System for Modern and Future Fermilab Experiments Robert Illingworth Fermilab Scientific Computing Division.
Jianming Qian, UM/DØ Software & Computing Where we are now Where we want to go Overview Director’s Review, June 5, 2002.
CDF SAM Deployment Status Doug Benjamin Duke University (for the CDF Data Handling Group)
Apr. 25, 2002Why DØRAC? DØRAC FTFM, Jae Yu 1 What do we want DØ Regional Analysis Centers (DØRAC) do? Why do we need a DØRAC? What do we want a DØRAC do?
DØ Computing Model and Operational Status Gavin Davies Imperial College London Run II Computing Review, September 2005.
DØ Grid Computing Gavin Davies, Frédéric Villeneuve-Séguier Imperial College London On behalf of the DØ Collaboration and the SAMGrid team The 2007 Europhysics.
Dag Toppe Larsen UiB/CERN CERN,
Progress on NA61/NA49 software virtualisation Dag Toppe Larsen Wrocław
Dag Toppe Larsen UiB/CERN CERN,
DØ Computing & Analysis Model
Grid Canada Testbed using HEP applications
Support for ”interactive batch”
DØ MC and Data Processing on the Grid
Lee Lueking D0RACE January 17, 2002
Presentation transcript:

6/2/2015 Michael Diesburg HCP Distributed Computing at the Tevatron D0 Computing and Event Model Michael Diesburg, Fermilab For the D0 Collaboration HCP 2005 Les Diablerets, Switzerland

6/2/2015 Michael Diesburg HCP Outline Computing Infrastructure Data Model and Formats Large Scale Global Processing A little background on infrastructure (It’s old news…) Evolution of the data model and formats (Maybe some valuable hints as to where you could go wrong…) Real world experience with large scale remote production (What are the hard parts? What’s it really going to cost you?)

6/2/2015 Michael Diesburg HCP Computing Infrastructure Hardware configuration is canonical setup for a large experiment: –Central analysis farms of dual processor linux nodes –Linux disk cache servers (4TB each) –High speed tape storage (STK 9940, 9940B, ADIC LTO, LTO2) –Large, central event/configuration/calibration database (Oracle, Sun) –Linux RedHat desktops –Central production farms of dual processor linux nodes (separate from analysis farms, but identical) –Gb Ethernet interconnections on central systems, 100Mb to desktop –Similar, smaller scale, installations at collaborating institutions worldwide Current capacities: –~ 1 PB data on tape, 1.4G raw events –~ 40 TB/week tape I/O –~ 120 TB disk cache –~ 1500 GHz production farm cpu –~ 1500 GHz analysis farm cpu

6/2/2015 Michael Diesburg HCP Computing Infrastructure Two key pieces of software infrastructure: Enstore, SAM Enstore is storage management system based on software originally developed at DESY. –Provides all access to tape based storage –No direct user interaction with Enstore SAM (Serial Access via Metadata) is the glue tying everything together –Provides transparent global access to data –Disk caching and file replication –Local and wide area data transport –Comprehensive metadata catalog for both real and MC data –Provides dataset definition capabilities and processing histories –User interfaces via command line, web and python API –Supports operation under PBS, Condor, LSF, FBS batch systems (others via a standard batch adapter)

6/2/2015 Michael Diesburg HCP Data Model (Historical Perspective) As initially envisioned normal processing chain would be: –Raw data processed by reconstruction program to produce STA = raw data + all reconstructed info ( too big, for a subset of data only) DST = reconstructed objects plus enough info to redo reconstruction TMB = compact format of selected reconstructed objects. All catalogued and accessible via SAM Above formats supported by a standard C++ framework Analysis groups would produce and maintain specific tuples for their use Life doesn’t always turn out the way you want it to: –STA never implemented –TMB wasn’t ready when data started coming in –DST was ready, but initially people wanted extra info in raw data. –Root tuple output intended for debugging was available and many began using it for analysis (but too big and too slow to produce for all data) –Threshold for using the standard framework and SAM was high (complex and documentation inadequate)

6/2/2015 Michael Diesburg HCP Data Model (Historical Perspective) TMB was pushed to finalization ~8 months after data taking began –Late enough that many were already wedded to the debugging root tuple –Specification is an ugly process, someone is always left unhappy –Result was great for physical data access (everything disk resident) and algorithm development –Slow for analysis (unpacking times large, changes required slow relinks) Divergence between those using standard framework and those using root tuples –Lead to incompatibilities and complications. Most notably in standard object IDs. –Need for common format was universally recognized Effort was made to introduce a common analysis format in the form of TMBTree –Compatibility issues and inertia prevented most root tuple users from embracing it –Did not have clear support model –Never caught on

6/2/2015 Michael Diesburg HCP Data Model Recently have expanded TMB to TMB+ –Includes tracking hits allowing reconstruction –Dropped DST Another attempt to introduce a common format via ROOT –Better thought out, broader support –Had we done this 5 years ago… –Might have a better chance, but inertia may be too great Lessons: –Need a well thought out, common analysis format that meets needs of all users and all agree on from day one. –Must support trivial access operations with minimal impedance to user –Documentation has to be ready at start

6/2/2015 Michael Diesburg HCP Remote Processing First attempt at remote production processing of real data was done in Fall of ’03 –Goal was to reprocess ~500M –Some compromises made to simplify remote jobs: Reprocess from DSTs (no calibration DB needed) No storage of DSTs, only TMBs (less to transport back to FNAL) Merging of TMBs and final storage to tape done at FNAL –Final scope of remote activity: ~ 100M events processed at 5 sites (UK, WestGrid, IN2P3, GridKa, NIKHEF) ~ 25TB data transported ~ 2 months setup required for ~ 6 weeks actual processing Very manpower intensive, but successful ROI appeared to be positive

6/2/2015 Michael Diesburg HCP Remote Processing Lessons learned from first pass: –Endeavor is very manpower intensive –ROI could be considered positive, but it is a hard call to make Compare estimated manpower costs to cost of expanding FNAL farm to handle load Equipment stays bought –Network is a limiting factor. Prestaging of files necessary –Well defined plans finalized early are critical to success Last minute changes in priorities, processing modes cause ripple effects across entire system –Restage files –Recertification of sites –Certification requires major effort What constitutes an acceptable discrepancy? Who decides? If a discrepancy is found, who is “right” (maybe neither) Hard to do high statistics certification. Total resources are large, but individual sites may not be able process much for certification When is recertification necessary

6/2/2015 Michael Diesburg HCP Remote Processing Let’s do it again, but get serious this time: –~ 1G events to process remotely –~ 250 TB raw data to move –Do reconstruction from raw data with normal configuration and calibration DB accesses –All steps done remotely including TMB merging and initiation of final store to tape at FNAL. –All bookkeeping done with SAM –Use common, Grid enabled software everywhere –Expect ~ 6 months processing time, several months setup time –Will be manpower intensive. Expect ~ 1 FTE for each major site for the duration of the project How efficient do you need to be? Except for prestaging of files this is no different than normal first pass reconstruction on FNAL farm

6/2/2015 Michael Diesburg HCP Remote Production Using SAMGrid software for operation of this pass. –Includes Job Information Monitoring (JIM) –Grid job submission –Execution control package (RunJob) –Uses VDT for underlying services –Requires each site to provide a head node for installation –Installation is very time and manpower intensive. Access to experts is necessary –Head node is the choke point in the system –Much effort has gone into alleviating load problems on head node –Still scalability issues to be resolved. Functionality needs to be distributable across multiple nodes

6/2/2015 Michael Diesburg HCP Remote Production In spite of effort required and problems, it’s working –Started production of 1G event sample early March –Currently ~450M events processed, merged, and stored to tape at FNAL –Should finish early October –Next step is Grid enabled user analysis Lessons: –Large scale production of real data in a Grid environment is practical –Could even do first pass reconstruction if necessary –Cheap hardware wise (at least for first user…) –Expensive manpower wise What color is your money?