Clouds in High Energy Physics

24
Clouds in High Energy Physics Randall Sobie Institute of Particle Physics University of Victoria

description

 

Transcript of Clouds in High Energy Physics

Page 1: Clouds in High Energy Physics

Clouds in

High Energy Physics

Randall SobieInstitute of Particle Physics

University of Victoria

Page 2: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 2

High Energy Physics(Particle Physics)

The area of physics that studies the fundamental particles of nature and their

interactions.

SLAC Linear Accelerator

Accelerators

Sudbury Solar Neutrino Detector

Underground labs

Alpha Magnetic Spectrometer Space Station

Orbiting labs

Page 3: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 3

Is the Higgs boson the source of mass of our fundamental

particles?

Page 4: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 4

Why is the universe made of matter

and not equal amounts of matter/antimatter?

Page 5: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 5

What is origin of Dark Matter and Dark Energy?

TWe do not know the

composition of 95% of the universe

Temperature of the universeWMAP satellite

Page 6: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 6

Understanding our World

Page 7: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 7

Large Hadron Collider at CERN in Geneva

27 km in circumference100 m underground

Probes distances of 10-20 m

Page 8: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 8

Blue tubes contain the two beam pipes and magnets at 1.8 degrees Kelvin

Page 9: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 9

ATLAS Detector

44 m wide25 m diameter

Page 10: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 10

ATLAS detector during construction in 2005

Page 11: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 11

40 million collisions per second

100,000 collisions selected

200 events per second

WLCG Computing GridCERN Tier 0

10 Tier1 sites60+ Tier2 sites

140 PB data

Page 12: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 12

Higgs Discovery in 2012

The ATLAS and CMS experiments see evidence for a Higgs-like particle

Picture shows an event where the Higgs candidate decays to 4 electron-like particles

Page 13: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 13

Number of candidates (vertical axis)

Mass of the candidates(horizontal axis)

We observe an excess of candidates with a mass of

125 proton-masses

Search for Higgs decays to 4 “leptons” (electrons or muons)

Also observed in the CMS experiment

Page 14: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 14

July 4, 2012

Page 15: Clouds in High Energy Physics

15

Long-term preservation of software and data of HEP

experiments

Clouds in High Energy Physics

Randall Sobie IPP/UVictoria

Utilize special computing resources attached to the

detectors

Simplify the management of heterogeneous in-house

resources

Use commercial clouds for exceptional computing

demands

Distributed cloud computing using HEP and non-HEP

clouds

Page 16: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 16

Using Clouds for Data Preservation

SLAC Linear Accelerator BaBar Detector

Electron-positron collision

BaBar experiment stopped recording electron-positron collisions in 2008

Long Term Data Access system

Static SL5 VMs Full access to BaBar SW and data

Transparent to the userIn operation since 2010

http://today.slac.stanford.edu/feature/2010/babar-prototype-data-servers.asp

Page 17: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 17

ATLAS/CMS High Level Trigger Clouds

40 million collisions per second

100,000 collisions selected

200 events per second

HLT Farms

These systems are used in real-time when there is colliding beams

The aim is to use the resources during the idle periods for other purposes

Enabled as private OpenStack clouds

See talk by Toni Perez Wednesday 1100

50,000 cores ATLAS, CMS, LHCb

Page 18: Clouds in High Energy Physics

18

Private and commercial clouds

Randall Sobie IPP/UVictoria

Ibex @ CERN (J. van Eldik, T. Bell, B.Moreira)

OpenStack cloud with 5000 cores Provide batch services and cloud services

HEP using Amazon, Google, Rackspace and others

Star Experiment at RHIC (Brookhaven NL)Belle Experiment at KEK (Japan)ATLAS Experiment

Commercial clouds used for exceptional low I/O demands

Challenges: identity management, API compatibility, VM configuration and network connectivity

Costs are higher than our private resources

Page 19: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 19

Distributed cloud computingGrid of Clouds

Seamlessly use multiple, heterogeneous IaaS clouds

for batch workloadsSky ComputingK. Keahey etal

Use dedicated HEP and non-HEP opportunistic resources

Independent of the IaaS cloud type

Removes any application requirements from remote site

Support multiple projects

Page 20: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 20

Distributed cloud overview

CloudScheduler

IaaSClouds

HTCondor JobQueue

UserJob

UserVM

Discovers User-Job Boot User-VMon a cloud

Dispatches UserJobto VM

VM registers with HTCondor

Remote VM image repository (Nimbus clouds)Upload VMs to OpenStack cloudsRemote data repositories for all clouds

Page 21: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 21

Distributed cloud status

NimbusVictoria(3)

OttawaFutureGrid Chicago

FutureGrid SanDiegoFutureGrid Florida

OpenStackMelbourne-NECTAR

CERN-IbexCANARIE-WestCANARIE-EastOxford-GridPP

Amazon EC2Google GCE

Operational since Nov 2011

Approximately 250K jobs(Astronomy 500K jobs)

Using 10 clouds for ATLAS jobs500-1000 simultaneous jobs12 hour jobs

ATLAS jobs submitted from CERN

ç

MelbourneCERN--IbexCANARIE

WG-VictoriaNRC-Ottawa

VictoriaFG-San DiegoFG-Chicago

Victoria

April 8-15 2013100-150 8-core VMs

Page 22: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 22

Technology innovation for new science

The OpenStack developer community can help us

Common authentication Centralized VM image storage

Consistent meta-dataUnique cloud names

Simplify the integration of OpenStack clouds for us

We see ourselves as integrators rather than developers of cloud technology

Page 23: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 23

Summary

High Energy Physics

Understand our UniverseStudying the Higgs

Search for Dark MatterDifference between antimatter/matter

Impact on societyCERN is the birthplace of the WWWMedical physicsTechnology innovationHQP

ComputingLarge distributed systemsGlobal research network

Novel use of computing technologies

Page 24: Clouds in High Energy Physics

Randall Sobie IPP/UVictoria 24

Acknowledgements

Contact information: [email protected] sites:http://rjs.phys.uvic.ca/

http://heprc.phys.uvic.ca/home/