1. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 1 Declarative Grid Service Orchestration with OGSA-DQP Alvaro A A Fernandes Department of Computer Science University of Manchester Service-Based Distributed Query Processing on the Grid

2. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 2 places, people, funding, projects Manchester M Nedim Alpdemir Anastasios Gounaris Norman W Paton Alvaro A A Fernandes Rizos Sakellariou Newcastle upon Tyne Arijit Mukherjee Jim Smith Paul Watson

3. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 3 acknowledgement Much of the content in many of the slides has been authored co- workers, especially M N Alpdemir, A Gounaris and N W Paton. Errors are mine, of course.

4. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 4 outline Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

5. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 5 motivation Pull by applications: –overwhelming amounts of semantically complex data in –very diverse, structurally dissimilar, and autonomous, geographically dispersed data sources –requiring computationally demanding analysis. Push from context and infrastructure: –Web service impetus combined with –Grid abstractions and protocols that enable, –not just dynamic resource discovery but also, –dynamic resource allocation and use.

6. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 6 context 1.High-level data access and integration services are needed if applications that have data with complex structure and complex semantics are to benefit from the Grid. 2.Standards for data access are emerging, and middleware products that are reference implementations of such standards are already available. 3.Distributed query processing technology is one approach to delivering (1.) given the availability of (2.). 4.Declarative service orchestration falls out.

7. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 7 background: federation One DQP approach is to federate. This is complex to manage because there always is an autonomous DBMS at every node. Resource allocation is static. Query optimisation cannot take evolving circumstances into account. DBMS data DBMS data DBMS data QueryResults

8. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 8 background: mediation Another approach is to use mediator/wrapper middleware. Autonomy is now less of an issue because the wrappers reconcile differences and impose a global schema. Often there is only one mediator in one fixed location, which is limiting. Query optimisation is not as hard. DBMS data mediator DBMS data QueryResults wrapper

9. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 9 OGSA-DQP approach OGSA-DQP uses a middleware approach. It can be seen as a mediator over OGSA- DAI wrappers. It promises bottom- lines regarding: –efficiency: leave to it to schedule in parallel; –effectiveness: leave to it to orchestrate your services; –usability: use it as a Grid data service. DBMS data OGSA-DQP DBMS data QueryResults OGSA-DAI

10. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 10 where we are Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

11. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 11 DQPE design issues A DQP engine (DQPE) is a distributed data- flow engine. How to map distributed query processing concepts and techniques to a service-based infrastructure? –What are DQPE components internally realized as? –What is the DQPE externally exposed as? How to partition functionalities and responsibilities among components? What interaction discipline to impose on components? Which control flows and which data flows among components? What component lifetime management policies to adopt?

12. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 12 DQPE design challenges To take decisions dynamically, on a as- needed basis; To automate complex, onerous, expert configuration decisions on behalf of users; To obtain the right grain when partitioning and scheduling computation loads; To keep interoperation overheads and context switches low; To achieve efficient throughput in data movements; To allocate resources lazily and free them up as early as possible.

13. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 13 OGSA-DQP goals 1.To benefit from homogeneous access to heterogeneous data sources [OGSA-DAI]. 2.To benefit from Grid abstractions for on- demand allocation of resources required for a task [OGSA/OGSI/GT3]. 3.To provide transparent, implicit support for parallelism and distribution. [Polar*] 4.To orchestrate the composition of data retrieval and analysis services. 5.To expose this orchestration capability as a Grid data service.

14. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 14 OGSA-DQP innovations OGSA-DQP dynamically allocates evaluators to do work on behalf of the mediator. This allows for runtime circumstances to be taken into account when the optimiser decides how to partition and schedule. OGSA-DQP uses a parallel physical algebra: most mediator-based query processors do not.

15. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 15 where we are Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

16. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 16 OGSA-DQP example Given two DBMSs and one analysis tool (e.g., a WS): –proteinTerm to a GO Gene Ontology running as a remote mySQL DB, –protein to a GIMS Genome Warehouse running as a remote ODMG-compliant DB, –Blast (sequence alignment scoring); We can obtain alignment scores for a sequence against proteins of a certain kind: select p.proteinId, Blast(p.sequence) from protein p, proteinTerm t where t.termId = GO:0005942 and p.proteinId = t.proteinId Then, OGSA-DQP acts as an enactor of a declarative orchestration of services on the Grid: index_scan termId=GO:0005942 (proteinTerm) table_scan (protein) reduce hash_join (proteinId) op_call (Blast) reduce exchange 3,4 2 1 5

17. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 17 OGSA-DQP extends/depends on extends Leonidas Fegarass - DB system and OPTGEN optimiser generator. [1997-2000] Polar: a parallel query processing engine. [1998-2001] Polar*: an MPICH-G distributed extension of Polar. [2002] depends on OGSA/OGSI/GT3 Grid Services (GSs). OGSA-DAI Grid Data Services (GDSs). Leonidas Fegaras and David Maiers work on a formal semantics for OQL. [TODS 25(4),2000]

18. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 18 OGSA-DQP manages/provides provides Grid Distributed Query Services (GDQSs) that: –interact with clients; –find and retrieve service descriptions; –parse, compile, partition and schedule the query execution over a union of distributed data sources. The query plan is an orchestration of GQESs manages Grid Query Evaluation Services (GQESs) that: –implement the physical query algebra; –implement the query execution model and semantics; –run a partition of a query execution plan generated by a GDQS; –interact with other GQESs/GDSs/WSs but not with clients.

19. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 19 OGSA-DQP a brief tour (1) It builds upon GDSs which build upon GSs. A GDS is a leaf in a query execution plan up from which data ultimately flows. Data resources are, thereby, virtualised. Since they are GSs, they can be dynamically created by dynamically discovered factories and then disposed of. A GDQS is a GDS capable of integration and distributed retrieval and analysis of data. To perform a request a GDQS spawns as many GQESs in as many hosts as the partitioning and scheduling policies of the GDQS recommend for that request.

20. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 20 OGSA-DQP a brief tour (2) To obtain an execution plan, a GDQS: –Interacts with registries to fetch information about the data and computational services deemed of interest by the requestor; –Interacts with GDSs and (in future) Index Services to acquire relevant metadata; –Compiles, optimises, partitions and schedules the query execution.

21. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 21 OGSA-DQP a brief tour (3) Given a distributed query plan, a GDQS: –Interacts with GDS factories to create the leaf services in the plan; –Interacts with WSs that front-end analysis capabilities; –Commands the creation of GQESs as stipulated by the partitioning and scheduling decided on by the compiler; –Coordinates the GQESs into executing the plan.

22. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 22 where we are Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

23. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 23 how do clients get a GDS to do work? GDS GridService Port GridDataTransport Port Client GridDataService Port findServiceData perform getFully

24. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 24 what happens behind the scenes?

25. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 25 how does it work, broadly? Initialisation stage: –An instance of a Grid Distributed Query Service is created; –Service instance (i.e., data resource) descriptions are imported. Query compilation stage: –Query plan is optimised, partitioned and scheduled. Query evaluation stage: –Instances of Grid Distributed Query Evaluation services are created as specified by the query execution plan. –Partitions are allocated to service instances (i.e., computational nodes) for execution according to schedule.

26. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 26 what engineering effort is involved? Developing corresponding factories; Implementing the GDS port types for both GDQS and GQES services; Supporting the importing of service descriptions by the GDQS; Implementing (or wrapping) a query compiler in the GQDS; Implementing a query partition evaluator in the GQES.

27. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 27 how does a GDQS spring into action?

28. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 28 can I ask more questions on that? When is a GDQS bound to a particular GDS? –When the schema of the GDS is imported. What is the lifespan of a GDS used by a GDQS? –The GDS is kept alive until the GDQS expires. Are GDSs shared by multiple GDQSs? –No. When is a GQES created? –When a query is about to be evaluated that needs it. What is the lifespan of a GQES? –It lasts only as long as a single query. Is a GQES shared among several queries or GDQSs? –No.

29. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 29 where we are Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

30. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 30 how is a query compiled? logical optimiser physical optimiser partitionerscheduler evaluators parser single-node optimiser multi-node optimiser query query results

31. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 31 what is logical optimisation? Plan is expressed using a logical algebra. By heuristic-based application of equivalence laws; Multiple equivalent plans are generated. scan termId=GO:0005942 (proteinTerm) scan (protein) reduce join (proteinId) op_call (Blast) reduce

32. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 32 what is physical optimisation? Plan is expressed using a physical algebra, With logical operators replaced by physical operators. By cost-based ranking of equivalent plans, a probably, acceptably efficient execution plan is chosen. index_scan termId=GO:0005942 (proteinTerm) table_scan (protein) reduce hash_join (proteinId) op_call (Blast) reduce

33. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 33 what is query partitioning? Plan is expressed in a parallel algebra, Where parallel algebra = physical algebra + data exchange. Exchange operators are placed where movement of data between evaluator nodes is required. index_scan termId=GO:0005942 (proteinTerm) table_scan (protein) reduce hash_join (proteinId) op_call (Blast) reduce exchange

34. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 34 what is query scheduling Plan is expressed by decorating parallel algebra expression with allocated Grid nodes. Using a heuristic algorithm based on memory use and network costs, an allocation of sub- plans to nodes is decided. index_scan termId=GO:0005942 (proteinTerm) table_scan (protein) reduce hash_join (proteinId) op_call (Blast) reduce exchange 3,4 2 15

35. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 35 how is a query evaluated? Query installation stage: –As many GQES instances are created as there are partitions specified. –Each partition is sent to the GQES instance it is scheduled for. Query evaluation stage: –Each GQES evaluates its partition using an iterator model. –Queries execute under pipelined and partitioned parallelism. –Results are conveyed to client.

36. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 36 what is query evaluation All algebraic operators are implemented using the iterator model. The iterator model supports three standard operators: –open() –next() –close() Remote data sources and computational resources are accessed through iterator-based wrappers. Calls propagate upwards through the tree. Many nodes may be active at any one time. Since the algebra includes an exchange operator partitioned and pipelined parallelism are supported.

37. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 37 what do exchange operators do? exchange marks the intersection of partitions. It encapsulates: –control flow; –data distribution policies; –inter-process communication. It is often immediately preceded by a reduce operator to minimise network costs.

38. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 38 what parallelisms do I benefit from? 3 4 partitioned parallelism pipelined parallelism table_scan termId=GO:0005942 (proteinTerm) table_scan (protein) reduce hash_join (proteinId) op_call (Blast) reduce exchange 3,4 2 15

39. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 39 what is going on behind the scenes (1)

40. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 40 what is going on behind the scenes (2)

41. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 41 where we are Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

42. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 42 design choices (1) Resource virtualisation through a service-oriented architecture: –Data Resource Discovery using service registries; –Computational Resource Discovery via Index Services (not implemented yet); –Reliance on GDSs for metadata and data access.

43. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 43 design choices (2) OGSA-DQP uses coarse-grained services with document-oriented interfaces. By acquiring and manipulating data in a data- flow architecture that is constructed dynamically, OGSA-DQP constructs, on-the-fly, a lightweight DQPE. Lightweight in the sense that the resources required for query plan execution are acquired at runtime, by instantiating GQESs, and disposed of on a per-query basis.

44. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 44 design choices (3) Similarly, metadata acquisition and management is performed per GDQS instance. Thus, there is no need for sophisticated mechanisms for maintaining consistency. It should be possible to layer on top of (or inside) OGSA-DQP any schema integration framework (e.g., local-as-view, global-as-view, etc.). OGSA-DQP performs its functions via an orchestration of loosely-coupled Grid services.

45. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 45 design consequences (1) OGSA-DQP design opts for a fairly thick data processing layer that aims to: –provides a generic framework, –effectively exploit Grid resources and dynamism; As opposed to a relatively thin, pre- configured data federation layer that: –delegates most of the data processing to data servers, and –only controls data flow.

46. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 46 design consequences (2) Greater benefits are possible if data is replicated, because only then parallel data access and parallel execution of joins show their true value. The existence of multiple instances of the same analysis service (or the ability to create instances of it dynamically) would also boost the performance because it would be possible to stream data simultaneously to multiple services for processing. So, the benefit of OGSA-DQP would be more sizeable in the presence of such replicated data sources and services and where large amounts of data are processed.

47. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 47 design consequences (3) OGSA-DQP assumes that computational resources can be acquired and used dynamically, which implies that application staging is possible. –In the case of true application staging sophisticated, policies may be required that would guarantee that the staged services are properly bound to service providers, both in legal terms and in technical terms (resource provision, security etc.)

48. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 48 design consequences (4) Since, currently, true application staging is not supported by Globus Toolkit 3, OGSA-DQP assumes that GQES factories already exist on Grid nodes. –Consequently, it is implied that whoever provides OGSA-DQP has either multiple servers with many data sources and evaluators installed on them (less likely), or service level agreements with providers of GDSs as well as of computational resources that host evaluator factories. –This implies B2B agreements are in place.

49. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 49 design consequences (5) One performance bottleneck is the lack of an efficient data transfer mechanism. –As OGSA-DQP is essentially a data flow system, efficient data movement is critical. Currently underlying technology is not mature enough to provide this capability. –For example, block delivery does not working efficiently, because: the block size is not configurable; the data is transferred as XML documents using SOAP over HTTP.

50. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 50 where we are Motivation, Context, Background Issues, Challenges, Innovation OGSA-DQP: –Example, relationships, a brief tour –Mediator/wrapper interactions –Query compilation and evaluation –Design choices –Design consequences OGSA-DQP as a service aggregator Summary

51. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 51 the Khalaf-Leymann taxonomy for web services aggregation unconstrained constrained aggregation agreementsgroupingrecursive wiring choreographyservice domains

52. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 52 web service aggregation types Grouping –Typically is either interface inheritance or instance grouping. –It leads to a portal- style of aggregation: no structure, no flow, no synergy. Recursive wiring –Resembles behind- the-scenes choreography: leads to internal synergy from encapsulated structure and flow.

53. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 53 web service aggregation types Choreography –Amounts to published orchestration: leads to structure, flow and constraints being made explicit. Service domains –Are characterized by one-to-many mapping to instances: leads to competition to perform service requests. Agreements –Are opportunity-driven with short lifespans.

54. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 54 OGSA-DQP various kinds of service aggregation There is interface inheritance from GSs and GDSs. The execution plan can be seen as encapsulating a wiring of GQESs, But constrained, and constructed on-the- fly, as in an an orchestration. As in service domains, there is competition of GQESs for a role to play in the orchestration. As is agreements, the orchestration is opportunistic, responsive to the obtaining resource levels and short- lived.

55. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 55 some related work DQP SkyQuery is a web- service-based (and hence, no dynamic resource allocation) DQP application ObjectGlobe has very similar aims, but has had to code in Java much infrastructure which OGSA-DQP obtains from the OGSI and OGSA-DAI. Orchestration On the Grid, the first choice has been instance grouping: as Grid portals that form problem-solving environments. [C&C:P&E 14(13-15),2002: GCE Special Issue] GSFL is Argonnes WSFL-on-the-Grid (and a BPEL4GS may yet emerge).

56. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 56 possible future work More functional: –Semi-structured data; –Streams. More dynamic: –Use Index Services; –Dynamically install factories. More application test-beds: –Metabolomics; –Sensor networks. More adaptive: –Queries may be long running, environment is constantly changing, and charging: static optimisation is likely to become stale fast. –So: monitor, assess and respond (e.g., switch operators/ algorithms, spawn more copies, relocate). More deployable: –As a web service, e.g..

57. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 57 summary OGSA-DQP is a service-based distributed query processor for the Grid that is: –Exposed as a service; –Implemented as an orchestration of services. OGSA-DQP is an enactor of declarative Grid service orchestrations that: –Improves on Grid portals when only retrieval and analysis is involved; –Fills the gap left by the lack of a service orchestration framework in the OGSA.

58. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 58 where to find out more: papers 1.M N Alpdemir, A Mukherjee, A Gounaris, A A A Fernandes, N W Paton, P Watson, J Smith. An Experience Report on Designing and Building OGSA-DQP: A Service Based Distributed Query Processor for the Grid. GGF9 Workshop on Designing and Building Grid Services, 2003. 2.M N Alpdemir, A Mukherjee, A Gounaris, N W Paton, P Watson, A A A Fernandes, J Smith. Service-Based Distributed Querying on the Grid. 1st Int. Conf. on Service Oriented Computing, 2003. LNCS, to appear 3.M N Alpdemir, A Mukherjee, A Gounaris, N W Paton, P Watson, A A A Fernandes, J Smith. OGSA-DQP: A Service-Based Distributed Query Processor for the Grid. 2nd UK e-Science All Hands Meeting, 2003. 4.J Smith, A Gounaris, P Watson, N W Paton, A A A Fernandes, R Sakellariou. Distributed Query Processing on the Grid. GRID 2002, LNCS 2536 (papers available from http://www.cs.man.ac.uk/~alvaro/publications.html )http://www.cs.man.ac.uk/~alvaro/publications.html

59. 16-17 October 2003 Grids and Applied Language Theory: Declarative Grid Service Orchestration with OGSA-DQP (A A A Fernandes) 59 where to find out more: software OGSA-DQP Grid middleware to query distributed data sources www.ogsadai.org.uk/dqp OGSA-DAI Grid middleware to interface with data(bases) www.ogsadai.org.uk/ Globus Toolkit Open-source implementation of OGSA/OGSI www.globustoolkit.org/