Introduction to the Grid Roy Williams, Caltech

1
Introduction to the Grid Roy Williams, Caltech
2
Enzo Case Study

• Simulated dark matter density in early universe
• N-body gravitational dynamics (particle-mesh
  method)
• Hydrodynamics with PPM and ZEUS
  finite-difference
• Up to 9 species of H and He
• Radiative cooling
• Uniform UV background (Haardt Madau)
• Star formation and feedback
• Metallicity fields

3
Enzo Features

• N-body gravitational dynamics (particle-mesh
  method)
• Hydrodynamics with PPM and ZEUS finite-difference
• Up to 9 species of H and He
• Radiative cooling
• Uniform UV background (Haardt Madau)
• Star formation and feedback
• Metallicity fields

4
Adaptive Mesh Refinement (AMR)

• multilevel grid hierarchy
• automatic, adaptive, recursive
• no limits on depth,complexity of grids
• C/F77
• Bryan Norman (1998)

Source J. Shalf
5
Distributed Computing Zoo

• Grid Computing
• Also called High-Performance Computing
• Big clusters, Big data, Big pipes, Big centers
• Globus backbone, which now includes Services and
  Gateways
• Decentralized control
• Cluster Computing
• local interconnect between identical cpus
• Peer-to-Peer (Napster, Kazaa)
• Systems for sharing data without centeral server
• Internet Computing
• Screensaver cycle scavenging
• eg SETI_at_home, Einstein_at_home, ClimatePrediction.net
  , etc
• Access Grid
• A videoconferencing system
• Globus
• A popular software package to federate resources
  into a grid
• TeraGrid
• A 150M award from NSF to the Supercomputer
  centers (NCSA, SCSC, PSC, etc etc)

6
What is the Grid?

• The World Wide Web provides seamless access to
  information that is stored in many millions of
  different geographical locations
• In contrast, the Grid is an emerging
  infrastructure that provides seamless access to
  computing power and data storage capacity
  distributed over the globe.

7
What is the Grid?

• Grid was coined by Ian Foster and Carl
  Kesselman The Grid blueprint for a new
  computing infrastructure.
• Analogy with the electric power grid plug-in to
  computing power without worrying where it comes
  from, like a toaster.
• The idea has been around under other names for a
  while (distributed computing, metacomputing, ).
• Technology is in place to realise the dream on a
  global scale.

8
How will it work?

• The Grid relies on advanced software, called
  middleware, which ensures seamless communication
  between different computers and different parts
  of the world

• The Grid search engine will not only find the
  data the scientist needs, but also the data
  processing techniques and the computing power to
  carry them out

• It will distribute the computing task to
  wherever in the world there is spare capacity,
  and send the result to the scientist

9
How will it work?

• The GRID middleware
• Finds convenient places for the scientists job
  (computing task) to be run
• Optimises use of the widely dispersed resources
• Organises efficient access to scientific data
• Deals with authentication to the different sites
  
• Interfaces to local site authorisation /
  resource allocation
• Runs the jobs
• Monitors progress
• Recovers from problems
• and .
• Tells you when the work is complete and transfers
  the result back!

10
Benefits for Science

• More effective and seamless collaboration of
  dispersed communities, both scientific and
  commercial
• Ability to run large-scale applications
  comprising thousands of computers, for wide range
  of applications
• Transparent access to distributed resources from
  your desktop, or even your mobile phone
• The term e-Science has been coined to express
  these benefits

11
Five Big Ideas of Grid

• Federated sharing
• independent management
• Trust and Security
• access policy authentication authorization
• Load balancing and efficiency
• Condor, queues, prediction, brokering
• Distance doesnt matter
• 20 Mbyte/sec, global certificates,
• Open standards
• NVO, FITS, MPI, Globus, SOAP

12
Grid as Federation

• Grid as a federation
• independent centers
• ? flexibility
• unified interface
• power and strength
• Large/small state compromise

13
Grid projects in the world

• NASA Information Power Grid
• DOE Science Grid
• NSF National Virtual Observatory
• NSF GriPhyN
• DOE Particle Physics Data Grid
• NSF TeraGrid
• DOE ASCI Grid
• DOE Earth Systems Grid
• DARPA CoABS Grid
• NEESGrid
• DOH BIRN
• NSF iVDGL

• UK e-Science Grid
• Netherlands VLAM, PolderGrid
• Germany UNICORE, Grid proposal
• France Grid funding approved
• Italy INFN Grid
• Eire Grid proposals
• Switzerland - Network/Grid proposal
• Hungary DemoGrid, Grid proposal
• Norway, Sweden - NorduGrid

• DataGrid (CERN, ...)
• EuroGrid (Unicore)
• DataTag (CERN,)
• Astrophysical Virtual Observatory
• GRIP (Globus/Unicore)
• GRIA (Industrial applications)
• GridLab (Cactus Toolkit)
• CrossGrid (Infrastructure Components)
• EGSO (Solar Physics)

14
TeraGrid Wide Area Network
15
TeraGrid Resources
16
The TeraGrid VisionDistributing the resources is
better than putting them at one site

• Recently awarded 150M by NSF
• Build new, extensible, grid-based infrastructure
  to support grid-enabled scientific applications
• New hardware, new networks, new software, new
  practices, new policies
• Expand centers to support cyberinfrastructure
• Distributed, coordinated operations center
• Exploit unique partner expertise and resources to
  make whole greater than the sum of its parts
• Leverage homogeneity to make the distributed
  computing easier and simplify initial development
  and standardization
• Run single job across entire TeraGrid
• Move executables between sites

17
TeraGrid Allocations Policies

• Any US researcher can request an allocation
• Policies/procedures posted at
• http//www.paci.org/Allocations.html
• Online proposal submission
• https//pops-submit.paci.org/
• NVO has an account on Teragrid
• (just ask RW)

18
Wide Variety of Usage Scenarios

• Tightly coupled simulation jobs storing vast
  amounts of data, performing visualization
  remotely as well as making data available through
  online collections (ENZO)
• Thousands of independent jobs using data from a
  distributed data collection (NVO)
• Science Gateways "not a Unix prompt"!
• from web browser with security
• SOAP client for scripting
• from application eg IRAF, IDL

19
Cluster Supercomputer
job submission and queueing (Condor, PBS, ..)
login node
100s of nodes
user
purged /scratch
parallel I/O
parallel file system
/home (backed-up)
metadata node
20
MPI parallel programming

• Each node runs same program
• first finds its number (rank)
• and the number of coordinating nodes (size)
• Laplace solver example

Algorithm Each value becomes average of neighbor
values
node 0
node 1
Serial for each point, compute average remember
boundary conditions
Parallel Run algorithm with ghost points Use
messages to exchange ghost points
21
Storage Resource Broker (SRB)

• Single logical namespace while accessing
  distributed archival storage resources
• Effectively infinite storage
• Data replication
• Parallel Transfers
• Interfaces command-line, API, SOAP, web/portal.

22
Storage Resource Broker (SRB)Virtual Resources,
Replication
Similar to NVO VOStore concept
certificate
casjobs at JHU
Browser SOAP client Command-line ....
tape at sdsc
File may be replicated File comes with
metadata ... may be customized
myDisk
23
Globus

• Security
• Single-sign-on, certificate handling, CAS,
  MyProxy
• Execution Management
• Remote jobs GRAM and Condor-G
• Data Management
• GridFTP, reliable FT, 3rd party FT
• Information Services
• aggregating information from federated grid
  resources
• Common Runtime Components
• New web service

24
Public Grids for Astronomy

• Data Pipelines
• split into independent pieces, send to scheduler
• Condor, PBS, Condor-G, DAGman, Pegasus
• big data storage
• infinite tape, purged disk, scratch disk
• no permanent TByte disk
• Services
• VOStore, SIAP
• Science gateways
• asynchronous, secure, web, scripted

25
Public Grids for Astronomy

• Databases
• Not really supported (note ask audience if this
  is true)
• VO effort for this (Casjobs, VOStore)
• Simulation
• Forward 100s synchronized nodes, MPI
• Inverse Independent trials, 1000s of jobs