A Large Hadron Collider Case Study - Where HPC and Big Data Converge Frank Würthwein Professor of Physics University of California San Diego November 15th,

Slides:



Advertisements
Similar presentations
High Performance Computing Course Notes Grid Computing.
Advertisements

SAN DIEGO SUPERCOMPUTER CENTER Using Gordon to Accelerate LHC Science Rick Wagner San Diego Supercomputer Center XSEDE 13 July 22-25, 2013 San Diego, CA.
Oliver Gutsche - CMS / Fermilab Analyzing Millions of Gigabyte of LHC Data for CMS - Discover the Higgs on OSG.
Randall Sobie The ATLAS Experiment Randall Sobie Institute for Particle Physics University of Victoria Large Hadron Collider (LHC) at CERN Laboratory ATLAS.
1 Software & Grid Middleware for Tier 2 Centers Rob Gardner Indiana University DOE/NSF Review of U.S. ATLAS and CMS Computing Projects Brookhaven National.
S. Gadomski, "ATLAS computing in Geneva", journee de reflexion, 14 Sept ATLAS computing in Geneva Szymon Gadomski description of the hardware the.
 Amazon Web Services announced the launch of Cluster Compute Instances for Amazon EC2.  Which aims to provide high-bandwidth, low- latency instances.
Open Science Grid Frank Würthwein UCSD. 2/13/2006 GGF 2 “Airplane view” of the OSG  High Throughput Computing — Opportunistic scavenging on cheap hardware.
Exploiting the Grid to Simulate and Design the LHCb Experiment K Harrison 1, N Brook 2, G Patrick 3, E van Herwijnen 4, on behalf of the LHCb Grid Group.
LHC’s Second Run Hyunseok Lee 1. 2 ■ Discovery of the Higgs particle.
Dynamically Creating Big Data Centers for the LHC Frank Würthwein Professor of Physics University of California San Diego September 25th, 2013.
CERN - IT Department CH-1211 Genève 23 Switzerland t The High Performance Archiver for the LHC Experiments Manuel Gonzalez Berges CERN, Geneva.
Open Science Grid For CI-Days Internet2: Fall Member Meeting, 2007 John McGee – OSG Engagement Manager Renaissance Computing Institute.
High Energy Physics At OSCER A User Perspective OU Supercomputing Symposium 2003 Joel Snow, Langston U.
José M. Hernández CIEMAT Grid Computing in the Experiment at LHC Jornada de usuarios de Infraestructuras Grid January 2012, CIEMAT, Madrid.
Computing and LHCb Raja Nandakumar. The LHCb experiment  Universe is made of matter  Still not clear why  Andrei Sakharov’s theory of cp-violation.
Preparation of KIPT (Kharkov) computing facilities for CMS data analysis L. Levchuk Kharkov Institute of Physics and Technology (KIPT), Kharkov, Ukraine.
TechFair ‘05 University of Arlington November 16, 2005.
1 Kittikul Kovitanggoon*, Burin Asavapibhop, Narumon Suwonjandee, Gurpreet Singh Chulalongkorn University, Thailand July 23, 2015 Workshop on e-Science.
IST E-infrastructure shared between Europe and Latin America High Energy Physics Applications in EELA Raquel Pezoa Universidad.
DOSAR Workshop, Sao Paulo, Brazil, September 16-17, 2005 LCG Tier 2 and DOSAR Pat Skubic OU.
10/24/2015OSG at CANS1 Open Science Grid Ruth Pordes Fermilab
1. Maria Girone, CERN  Q WLCG Resource Utilization  Commissioning the HLT for data reprocessing and MC production  Preparing for Run II  Data.
Data Logistics in Particle Physics Ready or Not, Here it Comes… Prof. Paul Sheldon Vanderbilt University Prof. Paul Sheldon Vanderbilt University.
November SC06 Tampa F.Fanzago CRAB a user-friendly tool for CMS distributed analysis Federica Fanzago INFN-PADOVA for CRAB team.
Tier-2  Data Analysis  MC simulation  Import data from Tier-1 and export MC data CMS GRID COMPUTING AT THE SPANISH TIER-1 AND TIER-2 SITES P. Garcia-Abia.
São Paulo Regional Analysis Center SPRACE Status Report 22/Aug/2006 SPRACE Status Report 22/Aug/2006.
And Tier 3 monitoring Tier 3 Ivan Kadochnikov LIT JINR
Storage, Networks, Data Management Report on Parallel Session OSG Meet 8/2006 Frank Würthwein (UCSD)
EGEE is a project funded by the European Union under contract IST HEP Use Cases for Grid Computing J. A. Templon Undecided (NIKHEF) Grid Tutorial,
CERN Using the SAM framework for the CMS specific tests Andrea Sciabà System Analysis WG Meeting 15 November, 2007.
Owen SyngeTitle of TalkSlide 1 Storage Management Owen Synge – Developer, Packager, and first line support to System Administrators. Talks Scope –GridPP.
Les Les Robertson LCG Project Leader High Energy Physics using a worldwide computing grid Torino December 2005.
Ruth Pordes November 2004TeraGrid GIG Site Review1 TeraGrid and Open Science Grid Ruth Pordes, Fermilab representing the Open Science.
1 User Analysis Workgroup Discussion  Understand and document analysis models  Best in a way that allows to compare them easily.
High Energy Physics and Grids at UF (Dec. 13, 2002)Paul Avery1 University of Florida High Energy Physics.
ATLAS is a general-purpose particle physics experiment which will study topics including the origin of mass, the processes that allowed an excess of matter.
US LHC OSG Technology Roadmap May 4-5th, 2005 Welcome. Thank you to Deirdre for the arrangements.
Claudio Grandi INFN Bologna CMS Computing Model Evolution Claudio Grandi INFN Bologna On behalf of the CMS Collaboration.
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.
High Energy FermiLab Two physics detectors (5 stories tall each) to understand smallest scale of matter Each experiment has ~500 people doing.
7. Grid Computing Systems and Resource Management
Performance of The NorduGrid ARC And The Dulcinea Executor in ATLAS Data Challenge 2 Oxana Smirnova (Lund University/CERN) for the NorduGrid collaboration.
Predrag Buncic Future IT challenges for ALICE Technical Workshop November 6, 2015.
Final Implementation of a High Performance Computing Cluster at Florida Tech P. FORD, X. FAVE, K. GNANVO, R. HOCH, M. HOHLMANN, D. MITRA Physics and Space.
LHC Computing, CERN, & Federated Identities
Computing Issues for the ATLAS SWT2. What is SWT2? SWT2 is the U.S. ATLAS Southwestern Tier 2 Consortium UTA is lead institution, along with University.
05 Novembre years of research in physics European Organization for Nuclear Research.
LHCbComputing Computing for the LHCb Upgrade. 2 LHCb Upgrade: goal and timescale m LHCb upgrade will be operational after LS2 (~2020) m Increase significantly.
CMS: T1 Disk/Tape separation Nicolò Magini, CERN IT/SDC Oliver Gutsche, FNAL November 11 th 2013.
Joint Institute for Nuclear Research Synthesis of the simulation and monitoring processes for the data storage and big data processing development in physical.
Meeting with University of Malta| CERN, May 18, 2015 | Predrag Buncic ALICE Computing in Run 2+ P. Buncic 1.
Nigel Lockyer Fermilab Operations Review 16 th -18 th May 2016 Fermilab in the Context of the DOE Mission.
1 Open Science Grid: Project Statement & Vision Transform compute and data intensive science through a cross- domain self-managed national distributed.
Opportunistic Computing Only Knocks Once: Processing at SDSC Ian Fisk FNAL On behalf of the CMS Collaboration.
CMS Experience with the Common Analysis Framework I. Fisk & M. Girone Experience in CMS with the Common Analysis Framework Ian Fisk & Maria Girone 1.
Nigel Lockyer Fermilab Operations Review 16 th -18 th May 2016 Fermilab in the Context of the DOE Mission.
SAM architecture EGEE 07 Service Availability Monitor for the LHC experiments Simone Campana, Alessandro Di Girolamo, Nicolò Magini, Patricia Mendez Lorenzo,
Grid technologies for large-scale projects N. S. Astakhov, A. S. Baginyan, S. D. Belov, A. G. Dolbilov, A. O. Golunov, I. N. Gorbunov, N. I. Gromova, I.
Scientific Computing at Fermilab Lothar Bauerdick, Deputy Head Scientific Computing Division 1 of 7 10k slot tape robots.
Computing infrastructures for the LHC: current status and challenges of the High Luminosity LHC future Worldwide LHC Computing Grid (WLCG): Distributed.
CERN IT Department CH-1211 Genève 23 Switzerland t EGEE09 Barcelona ATLAS Distributed Data Management Fernando H. Barreiro Megino on behalf.
Scientific Data Processing Portal and Heterogeneous Computing Resources at NRC “Kurchatov Institute” V. Aulov, D. Drizhuk, A. Klimentov, R. Mashinistov,
Data Federation & Data Management for the CMS Experiment at the LHC
Scaling Science Communities Lessons learned by and future plans of the Open Science Grid Frank Würthwein OSG Executive Director Professor of Physics UCSD/SDSC.
Grid site as a tool for data processing and data analysis
CERN presentation & CFD at CERN
Philippe Charpentier CERN – LHCb On behalf of the LHCb Computing Group
Dagmar Adamova (NPI AS CR Prague/Rez) and Maarten Litmaath (CERN)
Presentation transcript:

A Large Hadron Collider Case Study - Where HPC and Big Data Converge Frank Würthwein Professor of Physics University of California San Diego November 15th, 2013

Outline The Science Software & Computing Challenges Present Solutions Future Solutions November 15th 2013Frank Wurthwein - HP-CAST212

The Science

~67% of energy is “dark energy” ~29% of matter is “dark matter” All of what we know makes up Only about 4% of the universe. We have some ideas but no proof of what this is! We got no clue what this is. The Universe is a strange place! November 15th 2013Frank Wurthwein - HP-CAST214

To study Dark Matter we need to create it in the laboratory November 15th 2013Frank Wurthwein - HP-CAST215 Mont Blanc Lake Geneva ALICE ATLAS LHCb CMS

“Big bang” in the laboratory We gain insight by colliding particles at the highest energies possible to measure: –Production rates –Masses & lifetimes –Decay rates From this we derive the “spectroscopy” as well as the “dynamics” of elementary particles. Progress is made by going to higher energies and brighter beams. November 15th 2013Frank Wurthwein - HP-CAST217

Explore Nature over 15 Orders of magnitude Perfect agreement between Theory & Experiment Dark Matter expected somewhere below this line. November 15th 2013Frank Wurthwein - HP-CAST218

And for the Sci-Fi Buffs … Imagine our 3D world to be confined to a 3D surface in a 4D universe. Imagine this surface to be curved such that the 4 th D distance is short for locations light years away in 3D. Imagine space travel by tunneling through the 4 th D. The LHC is searching for evidence of a 4 th dimension of space. November 15th 2013Frank Wurthwein - HP-CAST219

Recap so far … The beams cross in the ATLAS and CMS detectors at a rate of 20MHz Each crossing contains ~10 collisions We are looking for rare events that are expected to occur in roughly 1/ collisions, or less. November 15th 2013Frank Wurthwein - HP-CAST2110

Software & Computing Challenges

The CMS Experiment

80 Million electronic channels x 4 bytes x 40MHz ~ 10 Petabytes/sec of information x 1/1000 zero-suppression x 1/100,000 online event filtering ~ Megabytes/sec raw data to tape 1 to 10 Petabytes of raw data per year written to tape, not counting simulations Scientists (1200 Ph.D. in physics) –~ 180 Institutions –~ 40 countries 12,500 tons, 21m long, 16m diameter November 15th 2013Frank Wurthwein - HP-CAST2113

Example of an interesting Event November 15th 2013Frank Wurthwein - HP-CAST2114 Higgs to γγ candidate

Zoomed in R-Z view of a busy event November 15th 2013Frank Wurthwein - HP-CAST2115 Yellow dots indicate individual collisions, all during the same beam crossing.

Active Scientists in CMS November 15th 2013Frank Wurthwein - HP-CAST % of the scientific members are actively doing large scale data analysis in any given week. ~1/4 of the collaboration, scientists and engineers, contributed to the common source code of ~3.6M C++ SLOC.

Evolution of LHC Science Program 150Hz 1000Hz 10000Hz Event Rate written to tape November 15th 2013Frank Wurthwein - HP-CAST2117

The Challenge How do we organize the processing of 10’s to 1000’s of Petabytes of data by a globally distributed community of scientists, and do so with manageable “change costs” for the next 20 years ? Guiding Principles for Solutions Chose technical solutions that allow computing resources as distributed as human resources. Support distributed ownership and control, within a global single sign-on security context. Design for heterogeneity and adaptability. November 15th 2013Frank Wurthwein - HP-CAST2118

Present Solutions

November 15th 2013Frank Wurthwein - HP-CAST2120 Federation of National Infrastructures. In the U.S.A.: Open Science Grid

November 15th 2013Frank Wurthwein - HP-CAST2121 Among the top 500 supercomputers there are only two that are bigger when measured by power consumption.

Tier-3 Centers Locally controlled resources not pledged to any of the 4 collaborations. –Large clusters at major research Universities that are time shared. –Small clusters inside departments and individual research groups. Requires global sign-on system to be open for dynamically adding resources. –Easy to support APIs –Easy to work around unsupported APIs November 15th 2013Frank Wurthwein - HP-CAST2122

Me -- My friends -- The grid/cloud O(10 4 ) Users O( ) Sites O( ) VOs Thin client Thin “Grid API” Thick VO Middleware & Support Me My friends The anonymous Grid or Cloud Domain science specific Common to all sciences and industry November 15th 2013Frank Wurthwein - HP-CAST2123

“My Friends” Services Dynamic Resource provisioning Workload management –schedule resource, establish runtime environment, execute workload, handle results, clean up Data distribution and access –Input, output, and relevant metadata File catalogue November 15th 2013Frank Wurthwein - HP-CAST2124

Optimize Data Structure for Partial Reads November 15th 2013Frank Wurthwein - HP-CAST2125

Fraction of a file that is read November 15th 2013Frank Wurthwein - HP-CAST2126 # of files read For vast majority of files, less than 20% of the file is read. 20% Average 20-35% Median 3-7% (depending on type of file) Overflow bin

Future Solutions

From present to future Initially, we operated a largely static system. –Data was placed quasi-static before it can be analyzed. –Analysis centers have contractual agreements with the collaboration. –All reconstruction is done at centers with custodial archives. Increasingly, we have too much data to afford this. –Dynamic data placement Data is placed at T2s based on job backlog in global queues. –WAN access: ”Any Data, Anytime, Anywhere” Jobs are started on the same continent as the data instead of the same cluster attached to the data. –Dynamic creation of data processing centers Tier-1 hardware bought to satisfy steady state needs instead of peak needs. Primary processing as data comes off the detector => steady state Annual Reprocessing of accumulated data => peak needs November 15th 2013Frank Wurthwein - HP-CAST2128

Any Data, Anytime, Anywhere November 15th 2013Frank Wurthwein - HP-CAST2129 Global redirection system to unify all CMS data into one globally accessible namespace. Is made possible by paying careful attention to IO layer to avoid inefficiencies due to IO related latencies.

Vision going forward Implemented vision for 1 st time in Spring 2013 using Gordon Supercomputer at SDSC. November 15th 2013Frank Wurthwein - HP-CAST2130

November 15th 2013Frank Wurthwein - HP-CAST2131

CMS “My Friends” Stack CMSSW release environment –NFS exported from Gordon IO nodes –Future: CernVM-FS via Squid caches J. Blomer et al.; 2012 J. Phys.: Conf. Ser J. Blomer et al.; 2012 J. Phys.: Conf. Ser Security Context (CA certs, CRLs) via OSG worker node clientOSG worker node client CMS calibration data access via FroNTier B. Blumenfeld et al; 2008 J. Phys.: Conf. Ser B. Blumenfeld et al; 2008 J. Phys.: Conf. Ser –Squid caches installed on Gordon IO nodes glideinWMS I. Sfiligoi et al.; doi: /CSIE doi: /CSIE –Implements “late binding” provisioning of CPU and job scheduling –Submits pilots to Gordon via BOSCO (GSI-SSH)BOSCO WMAgent to manage CMS workloadsWMAgent PhEDEx data transfer managementPhEDEx –Uses SRM and gridftpSRMgridftp November 15th 2013Frank Wurthwein - HP-CAST2132 Job environment Data and Job handling

CMS “My Friends” Stack CMSSW release environment –NFS exported from Gordon IO nodes –Future: CernVM-FS via Squid caches J. Blomer et al.; 2012 J. Phys.: Conf. Ser J. Blomer et al.; 2012 J. Phys.: Conf. Ser Security Context (CA certs, CRLs) via OSG worker node clientOSG worker node client CMS calibration data access via FroNTier B. Blumenfeld et al; 2008 J. Phys.: Conf. Ser B. Blumenfeld et al; 2008 J. Phys.: Conf. Ser –Squid caches installed on Gordon IO nodes glideinWMS I. Sfiligoi et al.; doi: /CSIE doi: /CSIE –Implements “late binding” provisioning of CPU and job scheduling –Submits pilots to Gordon via BOSCO (GSI-SSH)BOSCO WMAgent to manage CMS workloadsWMAgent PhEDEx data transfer managementPhEDEx –Uses SRM and gridftpSRMgridftp November 15th 2013Frank Wurthwein - HP-CAST2133 Job environment Data and Job handling This is clearly mighty complex !!! So let’s focus only on the parts that are specific to incorporating Gordon as a dynamic data processing center.

November 15th 2013Frank Wurthwein - HP-CAST2134 Items in red were deployed/modified to incorporate Gordon BOSCO Minor mod of PhEDEx config file Deploy Squid Export CMSSW & WN client

Gordon Results Work completed in February/March 2013 as a result of a “lunch conversation” between SDSC & US-CMS management –Dynamically responding to an opportunity 400 Million RAW events processed –125 TB in and ~150 TB out –~2 Million core hours of processing Extremely useful for both science results as well as proof of principle in software & computing. November 15th 2013Frank Wurthwein - HP-CAST2135

Summary & Conclusions Guided by the principles: –Support distributed ownership and control in a global single sign-on security context. –Design for heterogeneity and adaptability The LHC experiments very successfully developed and implemented a set of new concepts to deal with BigData. November 15th 2013Frank Wurthwein - HP-CAST2136

Outlook (I) The LHC experiments had to largely invent an island of BigData technologies with limited interactions with industry and other domain sciences. Is it worth building bridges to other islands ? –IO stack and HDF5 ? –MapReduce ? –What else ? Is there a mainland emerging that is not just another island ? November 15th 2013Frank Wurthwein - HP-CAST2137

Outlook (II) November 15th 2013Frank Wurthwein - HP-CAST2138 With increasing brightness of the beams, the number of simultaneous collisions increases from ~10 to ~140. The resulting increase in # of hits in the detector leads to an exponential growth in the CPU time needed to do the pattern recognition at the core of our reconstruction software. O(10 4 ) by 2023 O(10 4 ) ~ O(10) x O(10) x O(10) x O(10) Moore’s law New hardware architectures New algorithms Built a better detector Hoped for solution: Problem: