A%20Constraint%20Language%20Approach%20to%20Grid%20Resource%20Selection

1
A Constraint Language Approach toGrid Resource
Selection

• Chuang Liu, Ian Foster
• Distributed System Lab
• University of Chicago
• http//dsl.cs.uchicago.edu
• Work performed within the Grid Application
  Development Software (GrADS) Project of the NSF
  Next Generation Software Program

2
Problems

• Selection of resources whose properties are
  expressed by a feature set or range
• Co-selection of resources
• Description of requirement for a resource set for
  example, aggregation characteristics of a
  resource set.
• Efficient algorithm to locate resource set

3
Outline

• Problem
• Description Language (RedLine)
• Matchmaking
• Applications
• Summary

4
Description Language
ClassAds RedLine description language
A set of named Expressions called ClassAds A set of constraints on value of attribute called Description
Limited support for set expression data type set and related functions, such as Sum, Cardinality, Set_Intersection, etc.
5
Description Language

• Use constraints to describe attributes.

6
Description Language

• resource co-selection request.

7
Outline

• Problem
• Description Language
• Matchmaking
• Applications
• Summary

8
Description of Resources and Requests

• Both resources owners and requesters use RedLine
  syntax to describe their resources or requests
• The requestor and resource providers must use the
  same variable name to express a resource
  attribute and associate common meaning to
  responding values.

9
Definition of Match

• A constraint C is satisfiable if there exists a
  value assignment to every variable v Î vars(C)
  such that C holds. Otherwise, it is
  unsatisfiable. vars(C) denotes the set of
  variables occurring in constraint C.
• RedLine defines bilateral match Two descriptions
  C1 and C2 match each other if C1 ? C2 is
  satisfiable.

Scope of satisfying Capability
Scope of resource Capability
10
Example
11
Example
12
Definition of Match

• RedLine also defines multilateral match
  Descriptions D1, D2, , Dn match a description R
  if D1, D2, , Dn is an assignment to variables
  with description or description set type in
  description R and R is still satisfiable after
  replacing these variables with their values.

13
Example
14
Matchmaking Problem as CSP

• A constraint satisfaction problem, or CSP,
• A Constraint on variables
• Every variable has a finite value domain
• Matchmaking as CSP problem
• Associate a variable with every requested
  resource called resource variable
• Domain of every resource variable are available
  resources

15
Example
16
Matchmaking Process as Constraint Solving

• CSP Constraint solving
• Sound theory developed in AI, Logic programming
• Existing algorithms of constraint solving
• systematic search
• Backtracking algorithm
• heuristic and stochastic algorithms
• Hill-Climbing, Min-Coflict and Tabu-Search

17
Performance of Algorithms

• Evaluation of different algorithms
• Completion of algorithm
• Speed of algorithm
• Users controls on matchmaking process
• Search
• Distribution ltalgorithmgt
• SetConstruct ltalgorithmgt

18
Users Control on Matchmaking Process

• User controls matchmaking process by predicate

19
Summary

• Describe resource properties whose value is
  expressed as a feature set or a range
• Describe set-based requirement for a resource set
• Formalize matchmaking problem into a Constraint
  Satisfaction problem and utilize algorithms
  developed in CSP area to solve it
• Future Service Interface implementation,
  Organization of descriptions in matchmaker, and
  study performance of the algorithm in in
  realistic application settings
• Thanks to
• NSF Next Generation Software Program
• Alain Roy, GrADS colleagues
• http//dsl.cs.uchicago.edu

20
Outline

• Problem
• Description Language
• Matchmaking
• Redline System Applications
• Summary

21
RedLine System

• Layered structure

22
Applications

• Data Grid Example

23
Applications

• Access Grid Example

24
Applications

• Query Example

25
Summary

• Describe resource properties whose value is
  expressed as a feature set or a range
• Describe set-based requirement for a resource set
• Formalize matchmaking problem into a Constraint
  Satisfaction problem and utilize algorithms
  developed in CSP area to solve it
• Future Service Interface implementation,
  Organization of descriptions in matchmaker, and
  study performance of the algorithm in in
  realistic application settings
• Thanks to
• NSF Next Generation Software Program
• Alain Roy, GrADS colleagues
• http//dsl.cs.uchicago.edu

26
Constraint

• A constraint C is of the form c1 Ù Ù cn where n
  gt 0 and c1, , cn are primitive constraints. The
  symbol Ù denotes and, so a constraint C holds
  whenever all of the primitive constraints c1, ,
  cn hold.
• A constraint C is satisfiable if there exists a
  value assignment to every variable v Î vars(C)
  such that C holds. Otherwise, it is
  unsatisfiable. vars(C) denotes the set of
  variables occurring in constraint C.

27
Resource Selection Service Framework
RSS
GIIS
Resource
Information
Resource
Request
MDS
Set
GRISes
Resource
App
Matcher
Monitor
NWS
Result
Mapper