Grid3 update

1
Grid3 update

• Rob Gardner, iVDGL Coordinator
• University of Chicago
• rwg_at_hep.uchicago.edu

2
Steering Meetings Guidance

• December Steering meetings produced two planning
  documents two general paths forward indicated
• http//www.ivdgl.org/planning/ and links therein
• Production path (Grid3)
• Evolve the existing Grid3 infrastructure into a
  persistent grid laboratory
• Support near term data challenges and operations
• Development path, at much smaller scale
• Project yet to be defined (now have started
  Grid3dev)
• Most likely web services based (then need to
  revisit)

3
Grid3 history

• Joint project with USATLAS, USCMS, iVDGL, PPDG,
  GriPhyN
• Organized as a Project Grid2003
• Developed Summer/Fall 2003 project ended
  December 2003
• HPDC paper accepted
• Components
• VDT based (GRAM, Gridftp, MDS, Monitoring
  components) applications
• iGOC monitoring and VO level services
• Should federate with LCG
• successful use of USATLAS-Chimera runs on LCG-1
  last December, USCMS-LCG storage services
  demonstrator
• Installation
• pacman get iVDGLGrid3
• Plus post-install service configuration
• Takes 4 hours to bring up a site from scratch

4
Grid3 (extending Grid2003)

• Have developed plans in several areas VDT,
  Operations

• Planning document
• motivates plan for moving forward
• identification of Grid3 principles and strategy
• initial plan for project organization
• addressing Grid2003 lessons

5
Grid3, now underway

• Grid3 sites continue to operate
• Site charter developed
• specifies procedures for how sites and VOs join
• conditions by which they may be asked to leave
• how sites prepare to join requirements for
  installation
• Key Issues Documents
• collected from each stakeholder
• Weekly Ops meeting
• trouble ticket review
• site problems, Q/A, issues ID
• bi-weekly Taskforce meetings

6
Grid3 Operations

• Need to re-articulate and understand an interim
  operations model towards an Operations
  consortium perhaps
• Technical issues reviewed weekly at Monday ops
  meeting
• This has proven to be difficult traditional
  methods (service level agreements) dont fit the
  consortium model well
• igoc_at_ivdgl.org
• Multi-VO operations efforts, point of
  coordination, etc from the iGOC needs to be
  strengthened and supported
• Liaison operations among grid players Tier1s,
  sites, production managers, troubleshooters, VDT

7
Grid3 Results Jobs Run
Jobs from October 03 to April 04
ACDC monitor
8
Astrophysics Sloan Sky Survey

• Image stripes of the sky from telescope data
  sources
• galaxy cluster finding
• red shift analysis, weak lensing effects
• Analyze weighted images
• Increase sensitivity by 2 orders of magnitude
• with object detection and measurement code
• Workflow
• replicate sky segment data to Grid3 sites
• average, analyze, send output to Fermilab
• 44,000 jobs, 30 complete

9
Large Scale Grid3 Operations

• USCMS DC04 Challenge
• 15K GEANT simulation jobs of CMS detector
• Jobs last 1 day to 1 month (avg. 2-3 days)
• Mundane, Operational failures _at_ 30 rate
• NOT grid technology failures
• hardware, reboots, disks filling up

35K CPU-days in 3 months 04
10
Opportunistic use of Grid3
Grid3, non-CMS (blue)
Events produced vs. day
dedicated (red)
11
ATLAS Production System for DC2
prodDB
AMI
dms
Don Quixote
CERN
super
super
super
super
super
soap
jabber
jabber
jabber
soap
LCG exe
LCG exe
NG exe
Grid3 exe
LSF exe
Capone
Dulcinea
Lexor
RLS
RLS
RLS
LCG
NG
Grid3
LSF
system implemented, production starting this week
12
on behalf of collaborators from 23 institutes
Argonne National Laboratory Ian Foster, Jerry
Gieraltowski, Scott Gose, Natalia Maltsev, Ed
May, Alex Rodriguez, Dinanath Sulakhe Boston
University Jim Shank, Saul Youssef Brookhaven
National Laboratory David Adams, Rich Baker,
Wensheng Deng, Jason Smith, Dantong
Yu Caltech Iosif Legrand, Suresh Singh, Conrad
Steenberg, Yang Xia Fermi National Accelerator
Laboratory Anzar Afaq, Eileen Berman, James
Annis, Lothar Bauerdick, Michael Ernst, Ian Fisk,
Lisa Giacchetti, Greg Graham, Anne Heavey, Joe
Kaiser, Nickolai Kuropatkin, Ruth Pordes, Vijay
Sekhri, John Weigand, Yujun Wu Hampton
University Keith Baker, Lawrence Sorrillo
Harvard University John Huth Indiana
University Matt Allen, Leigh Grundhoefer, John
Hicks, Fred Luehring, Steve Peck, Rob Quick,
Stephen Simms Johns Hopkins University George
Fekete, Jan vandenBerg Kyungpook National
University / KISTI Kihyeon Cho, Kihwan Kwon,
Dongchul Son, Hyoungwoo Park Lawrence Berkeley
National Laboratory Shane Canon, Jason Lee, Doug
Olson, Iowa Sakrejda, Brian Tierney University at
Buffalo Mark Green, Russ Miller
University of California San Diego James Letts,
Terrence Martin University of Chicago David Bury,
Catalin Dumitrescu, Daniel Engh, Ian Foster,
Robert Gardner, Marco Mambelli, Yuri Smirnov,
Jens Voeckler, Mike Wilde, Yong Zhao, Xin
Zhao University of Florida Paul Avery, Richard
Cavanaugh, Bockjoo Kim, Craig Prescott, Jorge L.
Rodriguez, Andrew Zahn University of
Michigan Shawn McKee University of New
Mexico Christopher T. Jordan, James E. Prewett,
Timothy L. Thomas University of Oklahoma Horst
Severini University of Southern California Ben
Clifford, Ewa Deelman, Larry Flon, Carl
Kesselman, Gaurang Mehta, Nosa Olomu, Karan
Vahi University of Texas, Arlington Kaushik De,
Patrick McGuigan, Mark Sosebee University of
Wisconsin-Madison Dan Bradley, Peter Couvares,
Alan De Smet, Carey Kireyev, Erik Paulson, Alain
Roy University of Wisconsin-Milwaukee Scott
Koranda, Brian Moe Vanderbilt University Bobby
Brown, Paul Sheldon Contact authors
HPDC13 paper thanks to all
60 people working directly 8 full time, 10 half
time, 20 site admins ¼ time
13
Evolving Grid3 Grid3dev

• Need Laboratory prototype for introducing new
  services and environments, and applications
• New development grid platform begun in February
• Grid3 production resources unaffected
• so as not to disrupt challenge exercises
• Organized by iVDGL operations group
• Started with small sites in Grid3 but with
  parallel, development services
• Draw resources from VO development grids
• Grid-level tests of major VDT releases

14
Grid3dev what is it? http//www.ivdgl.org/grid3de
v/
Grid3 Common Environment
Grid3dev ? Grid3v2.1

• Authentication Service
• Approved VOMS servers
• Monitoring Service
• catalog
• MonALISA
• ganglia
• ACDC
• Stable Grid3 software cache

• Authentication Service
• test VOMS server
• Approved VOMS
• servers
• new VOMS server(s)
• Monitoring Service
• catalog (test vers)
• MonALISA (test vers)
• ganglia (test vers)
• Policy information provider
• Development s/w caches

VDT 1.1.11 based
VDT 1.1.14 based
15
Grid3dev to Grid3

• Grid3dev has undergone two major installation
  fests
• With site validation and catalog script
  development
• VDT 1.1.14 based now
• Grid3v2.1 blessed, upgrade in progress
• See status of site verify (GITS updates here)
• http//igoc.ivdgl.indiana.edu/upgrade/Tueup

16
Last weeks progress (ATLAS Grid3 sites upgrading)
17
Grid3dev next steps?

• Need to consider
• strengthening, extending from where we are in
  monitoring, information systems, grid software
  caches and installation, and operations
• introduction of new services as driven by the
  application stakeholders
• How iVDGL laboratory delivers its services into
  the larger OSG consortium