A conceptual model of grid resources and services

1
A conceptual model of grid resources and services

• Authors
• Sergio Andreozzi
• Massimo Sgaravatto
• Cristina Vistoli

Presenter Sergio Andreozzi INFN-CNAF Bologna
(Italy) sergio.andreozzi_at_cnaf.infn.it
2
OUTLINE

• Short introduction to the GLUE activity
• GLUE Schema overview
• The conceptual model
• The implementation status
• Deployment roadmap
• Related works
• Open issues

3
GLUE WHAT

• GLUE Grid Laboratory Uniform Environment
• collaboration effort focusing on interoperability
  between US and EU HENP Grid middlewares
• Targeted at core grid services
• Resource Discovery and Monitoring
• Authorization and Authentication
• Data movement infrastructure
• Common software deployment procedures
• Preserving coexistence for collective services

4
GLUE WHO and WHEN

• Promoted by DataTAG and iVDGL projects
• Activity started in April 2002 considering as
  first step common information service schema
  between EU and US HENP Grid projects
• Important contributions from the following
  projects DataGrid, Globus, GriPhyN, PPDG, SRM
• Main contributors (in alph order) J.Gordon,
  C.Kesselman, P.Kunstz, J.McGee, R.Pordes,
  A.Shoshani, J.Schopf, B.Tierney

5
GLUE Schema overview 1/2

• Conceptual model of grid resources to be used by
  the Grid Information Service for discovery and
  monitoring purposes
• Based on the experience of DataGrid and Globus
  schema proposals

6
GLUE Schema overview 2/2

• Conceptual model version 1.0
• Finalized in Oct 02
• Model of computing resources (Ref. CE)
• Model of storage resources (Ref. SE)
• Model of relationships among them (Ref. Close
  CE/SE)
• Currently working on version 1.1
• Extensions
• Model of network resources
• Possible other adjustements will come from
  experience (e.g. DataGrid v.2.0)

7
GLUE Computing resources requirements

• Separation between services and resources that
  implement it
• Needs for both detailed host info (monitoring
  issue) and aggregate view (discovery issue)

8
GLUE Computing Element

• Computing Element entry point into a queuing
  system
• There is one computing element per queue of a
  local resource management system
• The information associated with a computing
  element is limited only to information relevant
  to the queue
• All information about the physical resources
  accessed by a queue is represented by the Cluster
  information element

9
GLUECluster/Subcluster/Host

• Cluster container that groups together
  subclusters or hosts.  A cluster may be
  referenced by more than one computing element
• Subcluster collection of homogeneous hosts
• All hosts of a subcluster have the same value for
  the set of asserted attributes  
• Host characterizes the configuration of a
  computing node (e.g. processor, main memory,
  software)

10
Computing Resources in GLUE
Computing Element
Computing Element
Computing Element
subcluster2
subcluster1
Cluster 1
11
(No Transcript)
12
(No Transcript)
13
GLUEStorage Service/Space/Library

• Storage Service
• grid service identified by a URI that manages
  disk and tape resources in term of Storage Spaces
• all hardware details are masked
• the Storage Service performs file transfer in or
  out of its Storage Spaces using a specified set
  of third part data movement services (e.g.
  GridFTP)
• files are managed with respect to the lifetime
  policy specified for the Storage Space where they
  are kept
• a specific date and time lifetime policy can be
  specified for each file and this is applied
  against a compatibility rules table

14
GLUEStorage Service/Space/Library

• Storage Space portion of a logical storage
  extent identified by
• an association to a directory of the underlying
  file system (e.g. /permanent/CMS)
• a set of policies (MaxFileSize, MinFileSize,
  MaxData, MaxNumFiles, MaxPinDuration, Quota)
• an association to access control base rules

15
GLUEStorage Service/Space/Library

• Storage Library the machine providing for both
  storage space and storage service

16
GLUEStorage Service/Space/Library
Storage Service protocol info
Storage Space Status, Policies, Access Rules
Directory
Storage Library Architecture type file system
files
17
(No Transcript)
18
Computing/Storage Services relationships in Glue

• The problem
• Job executed on Computing Elements (CEs)
• Job may access files stored in Storage Space
• Several replicas of these files can be spread
  over the grid
• The best replica is CE-dependent
• Which strategy to assign the job to a CE and
  select the best replica for it?
• Current solution
• Computing-Storage Services association statically
  defined by SiteAdmins
• When the network resource model will be in place,
  this association could be dynamically defined

19
GLUE SchemaImplementation status

• Implementation status
• For Globus MDS 2.x
• LDAP Schema (DataTAG WP 4.1)
• Info providers for both computing and storage
  resources
• For EDG R-GMA
• Relational model implementation (DataGrid, both
  schema and information providers)
• For Globus OGSA
• XML Schema (Globus)

20
Deployment roadmap

• In DataTAG, a mixed testbed already in place
  with
• EDG 1.4.x ( Glue) nodes in Italy
• LCG-0 node at CERN
• VDT nodes in US (FNAL, Indiana University)
• CMS, ATLAS and ALICE experiment suites already
  successfully integrated with EDG Resource Broker,
  Glue schema based
• Grid middleware distributions and the Glue schema
• Already included in
• VDT 1.1.7
• LCG-0
• Will be soon included in
• EDG 2.0
• Globus 2.2.x

21
Related works

• EDT-LCG Monitoring collaboration
• development of a Grid monitoring tool in order to
  monitor the overall functioning of the Grid
• Will be presented here at CHEP
• Today, parallel session 1b-Monitoring, 4.50 PM
• Network resource modeling
• Definition of a network model that enables an
  efficient and scalable way of representing the
  communication capabilities between grid services
  for brokering activity
• Will be presented here at CHEP
• next Thursday, parallel session 1bMonitoring,
  4.10 PM

22
Main open issues

• Computing
• refine aggregated view of a cluster from the
  queue viewpoint
• Storage
• Gain better understanding of Storage Service,
  when mapping a disk space access or an SRM
  service
• High Level Grid Services, define a general grid
  service

23
REFERENCE

• DataTAG Project
• http//www.datatag.org
• Grid Laboratory Uniform Environment (GLUE)
  DataTAG WP4 and iVDGL Interoperability Group
  version 0.1.2
• http//www.hicb.org/glue/glue-v0.1.2.doc
• GLUE Schema documents
• http//www.cnaf.infn.it/sergio/datatag/glue
• EDT-LCG Monitoring
• http//gridmon.na.infn.it/lcg-edt
• GGF CIM Grid Schema WG
• http//www.isi.edu/flon/cgs-wg/