high energy physics and grids at uf (dec. 13, 2002)paul avery1 university of florida avery/...
TRANSCRIPT
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 1
Paul AveryUniversity of Florida
http://www.phys.ufl.edu/~avery/[email protected]
High Energy Physics and Grid Projects at U of Florida
Dell Visit to University of FloridaDec. 13, 2002
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 2
High Energy PhysicsHEP data
Collected in large facilities: Fermilab, Brookhaven, CERN
Record collisions of opposite moving beams
Each collision stored & analyzed independently
100M – 1000M collisions/year collected
Particle
Parton(quark, gluon)
Proton
ll
jetjet
Bunch
SUSY.....
Higgs
Zo
Zoe+
e+
e-
e-
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 3
Today: High Energy Physics at Fermilab
CDF experiment International experiment, 600 physicists, several countries
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 4
Tomorrow: High Energy Physics at LHC
“Compact” Muon Solenoidat the LHC (CERN)
Smithsonianstandard man
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 5
CMS Data Complexity“Events” resulting from beam-beam collisions:
Signal event is obscured by 20 overlapping uninteresting collisions in same crossing (1 MB per event stored)
CPU time to analyze each event rises dramatically
2000 2007
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 6
All charged tracks with pt > 2 GeV
Reconstructed tracks with pt > 25 GeV
(+30 minimum bias events)
109 events/sec, selectivity: 1 in 1013
CMS Analysis: Higgs Decay to 4 muons
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 7
1800 Physicists150 Institutes32 Countries
LHC Computing ChallengesComplexity: Millions of detector channels, complex eventsScale: PetaOps (CPU), Petabytes (Data)Distribution: Global distribution of people & resources
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 8
Experiment (e.g., CMS)
Global LHC Data Grid
Online System
CERN Computer Center > 20 TIPS
USAKorea RussiaUK
Institute
100-200 MBytes/s
2.5 Gbits/s
0.1 - 1 Gbits/s
2.5 Gbits/s
~0.6 Gbits/s
Tier 0
Tier 1
Tier 3
Tier 4
Tier0/( Tier1)/( Tier2) ~ 1:1:1
Tier 2
Physics cachePCs, other portals
Institute
Institute
Institute
Tier2 Center
Tier2 Center
Tier2 Center
Tier2 Center Florida
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 9
Florida Tier2 Center (2003)
Router
GEth/FEth SwitchGEthSwitch
Da
ta S
erv
er
>1 RAID WA
N
“Hierarchical” switching topology
Switch Switch GEth/FEth
Florida in 2003300 CPUs>2.5 GHz P47 TBytes RAID
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 10
“Trillium”: US Data Grid ProjectsGriPhyN
Grid research, toolkits$12M, 15 institutions
iVDGLDeploy Global Grid lab$14M, 17 institutions
PPDGData Grid for HEP experiments$9.5M, 12 institutions
Data intensive experiments
Physicists + computer scientists
Infrastructure development & deployment
=
Florida leads
Florida leads
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 11
Goal: PetaScale Virtual-Data Grids
Virtual Data Tools
Request Planning &
Scheduling ToolsRequest Execution & Management Tools
Transforms
Distributed resources(code, storage, CPUs,networks)
Resource Management
Services
Resource Management
Services
Security and Policy
Services
Security and Policy
Services
Other Grid ServicesOther Grid
Services
Interactive User Tools
Production TeamIndividual Investigator Workgroups
Raw data source
~1 Petaflop~100 Petabytes
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 12
US-iVDGL Data Grid (Spring 2003)
UF
Wisconsin
Fermilab BNL
Indiana
Boston USKC
Brownsville
Hampton
PSU
J. Hopkins
Caltech
Tier1Tier2Tier3
FIU
FSUArlington
Michigan
LBL
Oklahoma
Argonne
Vanderbilt
UCSD/SDSC
NCSA
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 13
Florida-Led US-CMS Testbed
UCSD
Florida
Wisconsin
Caltech
Fermilab
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 14
CMS Production Simulations
Remote Site 2Master Site
Remote Site 1
IMPALA mop_submitterDAGManCondor-G
GridFTP
BatchQueue
GridFTP
BatchQueue
GridFTP
Remote Site NBatchQueue
GridFTP
Several productions in 2002• Sites in US & Europe• Uncovered many Grid problems• 1M events almost complete
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 15
WorldGridJoint US - Europe effort
Resources from both sides (15 sites)Use several visualization tools (Nagios, MapCenter,
Ganglia)Use several monitoring tools (Ganglia, MDS, NetSaint, …)
ApplicationsCMS: CMKIN, CMSIMATLAS:ATLSIM
Submit jobs from US or EU Jobs can run on any clusterDemonstrated at IST2002 (Copenhagen)Demonstrated at SC2002 (Baltimore)
Brochures available describing Grid projects
High Energy Physics and Grids at UF (Dec. 13, 2002)
Paul Avery 16
Collaborative Possibilities with DellRaw computing power for production simulations
100s of CPUs, Terabytes of RAID
High performance I/ONeed to move ~ 5 Gbytes/sec between remote sitesBottlenecks: network protocols, clusters, components,
software,…
Managed clustersGoal is high efficiency useCluster management tools, automatic operation, fewer
people, …
Campus Grid operationsLarge scale operation permits many interesting “stress”
tests of cluster, network and Grid software components
International Grid operationsTools for monitoring dozens of sitesAutomatic operation, fewer people, high throughput, …