LCG Milestones for Deployment, Fabric,

1
LCG Milestonesfor Deployment, Fabric, Grid
Technology

• Ian Bird
• LCG Deployment Area Manager
• Presentation to LHCC Referees
• 25-Nov-2002

2
M1.1 First Global Service Initial
AvailabilityJuly 2003

• This comprises the construction and commissioning
  of the 1st LHC computing service for physics
  usage. The service must offer reliably 24x7
  availability to all 4 LHC experiments and include
  some 10 Regional Centres in Europe, North
  America, and Asia.
• The milestone includes delivery of the associated
  Technical Design, containing description of the
  architecture, functionality and quantified
  technical specifications of performance
  (capacity, throughput, reliability,
  availability). It must also include middleware
  specifications, agreed as a common toolkit by
  Europe and US.
• The service must prove functional, providing a
  batch service for event production and analysis
  of the simulated data set. For the milestone to
  be met, operation must be sustained reliably
  during a 7 day period stress tests and user
  productions will be executed, with a failure rate
  below 1.

3
L2 milestones for M1.1

• Define LCG-1 in terms of
• functionality, resources, operations, security,
  support
• Series of evolving pilot services for testing,
  with increasing resources
• Testing, certification, packaging and release of
  software
• Set up infrastructure and operational procedures
• Set up operations centre and help desk (call
  centre)
• LCG-1 commissioning and acceptance

4
M1.1 (a)

• Define LCG-1 functionality, resources,
  operations, security
• The 5 working groups of the Grid Deployment Board
  will define LCG-1.
• Functionality needed by the experiments for their
  data challenges identify VDT, EDG components to
  provide it negotiate support agreements with
  providers.
• Resources and Regional Centres to participate in
  LCG-1 deployment schedule and resource ramp-up.
  Define resource request and review process.
• Negotiate initial security model (authentication,
  authorization etc.) acceptable to all centres,
  provide a plan to achieve the full requirements
  of the centres.
• Define operating procedures, negotiate agreements
  with centres to put these into place.
• Define the user support model.
• WG1-4 will provide an interim report on Dec 9,
  final report Feb 1, 2003, WG5 3 months later

5
M1.1 (b)

• Series of evolving pilot services for testing,
  with increasing resources
• Pilot-1 service February 1, 2003.
• 50 machines (CE), 10 TB (SE). Runs middleware
  currently on LCG testbeds. Initial testbed at
  CERN.
• Add 1 remote site by February 28, 2003.
• Pilot-2 service March 15, 2003.
• 100 machines (CE), 10 TB (SE). CERN service
  will run full prototype of WP4 installation and
  configuration system.
• Add 1 US site to pilot March 30, 2003
• Add 1 Asian site to pilot April 15, 2003
• Add 2-3 more EU and US sites April May, 2003
• Service includes 6-7 sites June 1, 2003
• LCG-1 initial production system July 2003.
• 200 machines (CE), 20 TB (SE). Uses full WP4
  system with fully integrated fabric
  infrastructure. Global service has 6-7 sites in
  3 continents.

6
M1.1 (c)

• Testing, certification, packaging and release of
  software
• This is the process by which we make the service
  reliable and supportable (production service)
• Certification, testing, release process defined
  January 2003.
• To verify functionality, robustness, etc.
  Essential to provide production service. Process
  defined for EDG, modify for LCG.
• Packaging/configuration mechanism defined March
  2003.
• Needed to automate installation and
  configuration. A collaborative activity LCGgrid
  projects. Requirements gathering in progress.
• Delivery of middleware software packages March
  1, 2003
• This is delivery to LCG from the grid middleware
  providers
• Iterative, incremental release cycle, with major
  functional releases
• V1.0 June 1, 2003
• V1.1 October 1, 2003
• Incremental releases to improve stability,
  robustness, fix problems.

7
M1.1 (d)

• Set up Infrastructure Operational procedures
  January June 2003
• Schedule and details driven by outcome of GDB
  working groups
• Certificate Authorities and VO management systems
  in place May 2003
• Based on existing EU and US inter-operating
  systems
• Deploy grid services to participating sites
• As they come online according to WG2 schedule
• Agreement on responsibilities for management of
  services
• This is the outcome from WG 4 February 1, 2003
• Resource accounting and reporting procedures set
  up May 2003
• Security procedures defined and agreed June
  2003
• Incident response and security management

8
M1.1 (e)

• Set up operations centre and help desk (call
  centre)
• Identify operations and call centre locations
  February 1, 2003
• A call centre to provide operational and helpdesk
  support
• Distributed across 2 sites initially to provide
  reasonable coverage
• Monitoring system based on tools used in testbeds
  and recent demonstrations
• Existing experience in Teragrid and iVDGL,
  DataTAG
• Needs a problem tracking database several
  candidate systems
• In place by June 2003

9
M1.1 (f)

• LCG-1 commissioning and acceptance June 2003
• 30 day commissioning period with user productions
  and stress tests, including
• 7 day acceptance period

10
M1.4 Fully Operational LCG-1 ServiceNovember 2003

• This comprises the availability of LCG-1 as a
  fully operational and performant 24x7 production
  service. Operation must be sustained for a
  period of 1 month. This service would be used
  for the 5 data challenges of the LHC
  experiments. LCG-1 will be operated
  continuously, evolving in terms of capacity,
  performance and functionality. It includes the
  addition of Regional Centres as they come on-line
  as defined in GDB Working Group 2
• It include the delivery of the technical service
  specifications and user documentation, and
  deployment/consolidation of an appropriate user
  support infrastructure. It also includes
  incremental releases of middleware to improve
  reliability, robustness, and performance.
• The service level must be as required for the
  2004 data challenges. The determination and
  acceptance of the milestone should be done with a
  review of the service by representatives of the
  experiments, regional centres, and LCG.

11
L2 Milestones for M1.4

• Define LCG-1 performance goals July 2003
• In concert with experiments and their data
  challenge requirements, set performance goals in
  terms of capacity, throughput, reliability, etc.
  A GDB working group.
• 10 Regional Centres participating October 2003
• WG2 defines the implementation schedule may be
  adjusted in July. Add centres 1 at a time until
  October.
• LXBatch service merged into LCG-1 October 2003
• All resources of LXBATCH will be grid-enabled and
  accessible as part of the LCG-1 service.
• Milestone release of middleware October 2003
• V1.1 release with improved functionality
  October 2003
• Review of service November 2003
• The LCG-1 service level should be that required
  for the 2004 data challenges. The determination
  and acceptance of achieving the target will be
  done in a review of the service by
  representatives from the experiments, the
  regional centres and LCG.

12
M1.6 Fully Operational LCG-3 ServiceJanuary 2005

• This comprises the construction and commissioning
  of a fully operational full-size prototype
  (LCG-3) of what will be the initial LHC computing
  production service. Operation must be sustained
  24x7 reliably for a period of 1 month.
• LCG-3 will be used as a proof that the LHC
  computing model will work, including Tier 0,1,2
  and 3 regional centres, providing practical
  backup for the computing service TDR. LCG-3 will
  use the LHC Grid toolkit, will have 50 of the
  components required for the 2007 production
  service of CMS or ATLAS, and will be used for the
  20 milestones of the experiments.

13
L2 Milestones for M1.6

• Define LCG-3 February 2004
• Functionality middleware packages
• Resources, Regional Centre participants
• Performance goals
• LCG-3 pilot system available July 2004
• Operate in parallel with LCG-1 production
  service. Used for integration and functional
  tests by experiments.
• Decision on new batch system software (CERN)
  December 2004
• Following a review of scheduler software
  alternatives
• Upgrade LCG-1 service to LCG-3
• December 2004 January 2005. This is a major
  upgrade that can only be done at a quiet time.

14
M1.8 Completion of the Computing Service TDRJune
2005

• The Computing Service TDR will specify the
  requirements for the Grid that will be used for
  the first production services for the four LHC
  experiments. It will include details of the
  architecture, functionality, capacity,
  performance, throughput and availability.
• It will include the Regional Centre plans that
  will have been developed to meet these
  requirements, and will provide cost estimates and
  an overall installation and verification
  schedule. It is assumed that the TDR will be
  approved by the LHCC within three months
  following its availability, and may be used to
  provide data for the Memorandum of Understanding
  for Phase 2 of the project.
• The full process from acquisition to service
  verification is expected to take 12-18 months
  (according to the administrative procedures of
  the Regional Centres). The initial service must
  be in full production by September 2006 (6
  months before data taking). The TDR will
  therefore be approved after the acquisition
  procedures have started, but before orders are
  placed.

15
L2 Milestones for M1.8 - TDR

• Complete proposals for NSF-ITR and EU-FP6 April
  2003
• Programs at proposal stage to re-engineer,
  robustify, improve grid middleware
• Report on comprehensive reviews of grid
  technologies, define strategy for missing
  functionality July 2003
• Reviews to identify technology providers,
  capabilities and strategies for LCG-3. Includes
  a plan to provide functions not provided above.
• Review of status of progress July 2004
• Experiments final analysis models December
  2003
• In the light of 1st 6 months experience with
  LCG-1, the experiments should provide updated
  analysis models
• SC2 Review December 2004
• Comprehensive review of experience in the
  experiments and at the Regional Centres in
  deploying, operating, and using LCG services.
  Update the requirements and service model for
  deployment and operation of the final system.

16
Timelines
Incremental middleware releases
Incrementally add regional centres ?