Clusters & Grid Computing

Transcription

1 Clusters & Grid Computing A brief introduction to computational grids June 15 th 2004 Lorenzo Muttoni Anno Accademico

2 Clusters Nowadays PC computing power has considerably increased and it is interesting their use for supercomputing Also the bandwidth available in modern communication systems offers interesting opportunities to interconnect computation nodes Cluster: a set of PC (or Workstations), interconnected by a network, collaborating with each other Lorenzo Muttoni Impianti Informatici - A.A

3 Cluster Computer Architecture Sequential Applications Sequential Applications Sequential Applications Parallel Applications Parallel Applications Parallel Applications Parallel Programming Environment Cluster Middleware (Single System Image and Availability Infrastructure) PC/Workstation PC/Workstation PC/Workstation PC/Workstation Communications Communications Communications Communications Software Software Software Software Network Interface Hardware Network Interface Hardware Network Interface Hardware Network Interface Hardware Cluster Interconnection Network/Switch Lorenzo Muttoni Impianti Informatici - A.A

4 Prominent Components of Cluster Computers Parallel Programming Environments and Tools Threads (PCs, SMPs, NOW..) POSIX Threads Java Threads MPI Linux, NT, almost all UNIX PVM Software DSMs (Distributed Shared Memory) Compilers C/C++/Java Fortran 77/90 - HPF RAD (Rapid Application Development tools) GUI based tools for Parallel Program modeling Debuggers Performance Analysis Tools Visualization Tools Lorenzo Muttoni Impianti Informatici - A.A

5 Key operational characteristics of clustering Pros: High Performance (per node) Expandability and Scalability High Throughput High Availability low cost, easily scalable, easy setup Cons: performance are (generally) lower than those of a supercomputer network is (generally) the bottleneck Lorenzo Muttoni Impianti Informatici - A.A

6 Clusters Classification Application Target High Performance (HP) Clusters Grand Challenging Applications High Availability (HA) Clusters Mission Critical Applications Node Ownership Dedicated Clusters Non-dedicated clusters Adaptive parallel computing Communal multiprocessing Lorenzo Muttoni Impianti Informatici - A.A

7 Clusters Classification (2) Node Hardware Clusters of PCs (CoPs) Piles of PCs (PoPs) Clusters of Workstations (COWs) Clusters of SMPs (CLUMPs) Node Operating System Linux Clusters (e.g., Beowulf) Solaris Clusters (e.g., Berkeley NOW) NT Clusters (e.g., HPVM) AIX Clusters (e.g., IBM SP2) SCO/Compaq Clusters (Unixware) Digital VMS Clusters HP-UX clusters Microsoft Wolfpack clusters Lorenzo Muttoni Impianti Informatici - A.A

8 Clusters Classification (3) Node Configuration Homogeneous Clusters All nodes will have similar architectures and run the same OSs Heterogeneous Clusters All nodes will have different architectures and run different OSs Lorenzo Muttoni Impianti Informatici - A.A

9 Clusters Classification (4) Levels of Clustering Group Clusters (#nodes: 2-99) Nodes are connected by SAN like Myrinet Departmental Clusters (#nodes: 10s to 100s) Organizational Clusters (#nodes: many 100s) National Metacomputers (WAN/Internet-based) International Metacomputers (Internet-based, #nodes: 1000s to many millions) Metacomputing / Grid Computing Web-based Computing Agent Based Computing Lorenzo Muttoni Impianti Informatici - A.A

10 Cluster of Clusters: Hyperclusters Cluster 1 Scheduler Master Daemon The communication system is the typical bottleneck of a cluster Submit Graphical Control Clients Execution Daemon Cluster 3 Cluster 2 Scheduler Master Daemon LAN/WAN Scheduler Master Daemon Submit Graphical Control Execution Daemon Submit Graphical Control Clients Execution Daemon Clients Lorenzo Muttoni Impianti Informatici - A.A

11 Network Exponentials Network vs. computer performance Computer speed doubles every 18 months Network speed doubles every 9 months Difference = order of magnitude per 5 years 1986 to 2000 Computers: x 500 Networks: x 340, to 2010 Computers: x 60 Networks: x 4000 Moore s Law vs. storage improvements vs. optical improvements. Graph from Scientific American (Jan- 2001) by Cleo Vilett, source Vined Khoslan, Kleiner, Caufield and Perkins. Lorenzo Muttoni Impianti Informatici - A.A

12 New Opportunities (fast network) demand New Technology (Grid) When the network is as fast as the computer's internal links, the machine disintegrates across the net into a set of special purpose appliances (George Gilder) Lorenzo Muttoni Impianti Informatici - A.A

13 Grid Computing Grid Computing is a paradigm/infrastructure enabling the sharing, selection & aggregation of geographically distributed resources Computers PCs, workstations, clusters, supercomputers, laptops, notebooks, mobile devices, PDA, etc; Software e.g., ASPs renting expensive special purpose applications on demand; Wide area Catalogued data and databases e.g. transparent access to human genome database; Special devices/instruments e.g., radio telescope SETI@Home searching for life in galaxy. People/collaborators. [depending on their availability, capability, cost, and user QoS requirements] for solving large-scale problems/applications. Lorenzo Muttoni Impianti Informatici - A.A

14 Facilities required to build and use grids Middleware that make the systems Grid enabled Security mechanisms that allow resources to be accessed only by authorized users. (New) programming tools that make our applications Grid enabled. Tools that can translate the requirements of an application into requirements for computers, networks, and storage. Tools that perform resource discovery, trading, composition, scheduling and distribution of jobs and collects results. Lorenzo Muttoni Impianti Informatici - A.A

15 A Typical Grid Computing Environment Supercomputer Information Service Resource Broker Database PC R 2 Scientific instrument R 3 R 4 R 5 R 7 Resource Broker Cluster R 6 R N R 1 Resource Broker Info query Info update Resource mgmt Information Service Application Lorenzo Muttoni Impianti Informatici - A.A

16 The Grid World: Current Status Dozens of major Grid projects in scientific & technical computing/research & education Deployment, application, technology Considerable consensus on key concepts and technologies No official standards exists but Open source Globus Toolkit is a de facto standard for major protocols & services Far from complete or perfect, but out there, evolving rapidly, and large tool/user base Global Grid Forum a significant force Industrial interest emerging rapidly Lorenzo Muttoni Impianti Informatici - A.A

17 Layered Grid Architecture (Analogy to Internet Architecture) Coordinating multiple resources : ubiquitous infrastructure services, app-specific distributed services Sharing single resources : negotiating access, controlling use Talking to things : communication (Internet protocols) & security Controlling things locally : Access to, & control of, resources Application Collective Resource Connectivity Fabric Application Transport Internet Link Internet Protocol Architecture Lorenzo Muttoni Impianti Informatici - A.A

18 The Systems Problem My users need to be able to use my computing resources in tandem with resources at other sites. Need of resource sharing mechanisms that Address security and policy concerns of both resource owners and users Are flexible enough to deal with many resource types and sharing modalities Scale to large number of resources, many participants, many program components Operate efficiently when dealing with large amounts of data & computation The Globus Toolkit provides Grid Services within a standard Grid architecture to meet this need. Lorenzo Muttoni Impianti Informatici - A.A

19 The Programming Problem Applications require resources (compute power, storage, data, instruments, displays) at many sites. Need (presumably) of: Abstractions and models to add to speed/robustness/etc. of development Tools to ease application development and diagnose common problems Code/tool sharing to allow reuse of code components developed by others The Globus Toolkit provides a Grid SDK (Software Development Kit) designed to meet this need. GRADS project Lorenzo Muttoni Impianti Informatici - A.A

20 The Globus Toolkit A software toolkit addressing key technical problems in the development of Grid enabled tools, services, and applications Offer a modular bag of technologies Enable incremental development of grid-enabled tools and applications Implement standard Grid protocols and APIs Make available under liberal open source license Lorenzo Muttoni Impianti Informatici - A.A

21 A Practical Perspective The Globus Toolkit is not everything you ll need to build a Grid (most likely) everything you ll need to develop a Grid application (most likely) a complete, out of the box solution finished The Globus Toolkit is commercially supported by Platform, IBM, and Compaq (so far) available in source and binary forms being developed with real users in mind a starting point for many successful Grid projects Lorenzo Muttoni Impianti Informatici - A.A

22 Globus Toolkit structure: service oriented view MDS GRAM GRIS GIIS GridFTP GSI Data Management Information Services Resource Management Security Services Lorenzo Muttoni Impianti Informatici - A.A

23 Security Services Data Management Information Services Resource Management Security Lorenzo Muttoni Impianti Informatici - A.A

24 Why Grid Security is Hard Resources being used may be valuable & the problems being solved sensitive Resources are often located in distinct administrative domains Each resource has own policies & procedures Set of resources used by a single computation may be large, dynamic, and unpredictable Not just client/server, requires delegation It must be broadly available & applicable Standard, well-tested, well-understood protocols; integrated with wide variety of tools Lorenzo Muttoni Impianti Informatici - A.A

25 Grid Security Requirements User View 1) Easy to use 2) Single sign-on 3) Run applications ftp,ssh,mpi,condor,web, 4) User based trust model 5) Proxies/agents (delegation) Resource Owner View 1) Specify local access control 2) Auditing, accounting, etc. 3) Integration w/ local system Kerberos, AFS, license mgr. 4) Protection from compromised resources Developer View API/SDK with authentication, flexible message protection, flexible communication, delegation,... Direct calls to various security functions (e.g. GSS-API) or security integrated into higher-level SDKs: e.g. GlobusIO, Condor-G, MPICH-G2, HDF5, etc. Lorenzo Muttoni Impianti Informatici - A.A

26 Grid Security Infrastructure (GSI) Overview GSI provides elements for secure authentication and communication in a grid Infrastructure based on public key cryptography mechanisms X.509 certificates and SSL To provide single sign-on and delegation support some extensions have been added Lorenzo Muttoni Impianti Informatici - A.A

27 GSI Overview (Cont.d) Once the authentication succeeded (X.509 certificates), communication occurs with no cryptography (for performance reasons) Nevertheless, secure communication can be enabled GSI feature supports a mechanism to guarantee communication integrity: overhead smaller than that introduced by cryptography communication is "in the clear" but it is sure that the message has not been altered Lorenzo Muttoni Impianti Informatici - A.A

28 Review of Public Key Cryptography Asymmetric keys A private key is used to encrypt data A public key can decrypt data encrypted with the private key An X.509 certificate includes Someone s subject name (user ID) Their public key A signature from a Certificate Authority (CA) that: Proves that the certificate came from the CA. Vouches for the subject name Vouches for the binding of the public key to the subject Lorenzo Muttoni Impianti Informatici - A.A

29 Mutual Authentication User A 1. Connection established 2. A sends B its certificate User B Certificate A (C A ) 3. B sends A a random plaintext Certificate B (C B ) 4. A encrypt the plaintext using C A and sends it to B 5. 1) check validity of CA based on digital signature of CA 2) extract the public key of A 6. B decrypt the encrypted message If this matches with the original message, B can trust A now Lorenzo Muttoni Impianti Informatici - A.A

30 Delegation and Single Sign-On Typically, a grid computation involves a number of resources, and each resource has to carry out mutual authentication In this case, a proxy may avoid requiring the password every time a resource is accessed Delegation is the remote creation of a user proxy Results in a new new pair of keys and X.509 proxy certificate, signed by the user private key instead of the CA private key Allows remote process to act on behalf of the user Avoids sending passwords or private keys across the network Lorenzo Muttoni Impianti Informatici - A.A

31 Delegation and Single Sign-On (Cont.d) A proxy certificate has a limited temporal validity it contains the expiration time The use of proxies slightly modifies the mutual authentication process The target node (remote) receives the proxy certificate (signed by the user) and the user certificate signed by the CA. the user's public key is used to verify the validity of the proxy the CA public key is used to validate the user's certificate. Lorenzo Muttoni Impianti Informatici - A.A

32 User Proxies The use of User Proxies minimize exposure of user s private key A temporary, X.509 proxy credential for use by our computations We call this a user proxy certificate Allows process to act on behalf of user User-signed user proxy cert stored in local file Created via grid-proxy-init command Proxy s private key is not encrypted Rely on file system security, proxy certificate file must be readable only by the owner Lorenzo Muttoni Impianti Informatici - A.A

33 Other GSI Features Rights of delegated proxy can be restricted to a subset of those associated with the issuer Delegation Tracing Often want to know through what entities a proxy certificate has been delegated Solved by adding information to the signed proxy certificate about each entity to which a proxy is delegated Lorenzo Muttoni Impianti Informatici - A.A

34 Resource Management Services Data Management Information Services Resource Management Security Layer Lorenzo Muttoni Impianti Informatici - A.A

35 Resource Management Overview The Grid Resource Allocation Management (GRAM) protocol and client API provide services for remote process activation and execution status monitoring Resource Specification Language (RSL) is used to communicate requirements A layered architecture allows applicationspecific resource brokers and co-allocators to be defined in terms of GRAM services Integrated with Condor, PBS, MPICH-G2, Lorenzo Muttoni Impianti Informatici - A.A

36 Resource Management Overview (Cont.d) When a job is submitted, the request is sent to the remote host and handled by the gatekeeper daemon located in the remote host. The gatekeeper creates a job manager that starts and monitors the job. When the job is finished, the job manager sends the status information back to the client and terminates. Lorenzo Muttoni Impianti Informatici - A.A

37 GRAM Architecture GRAM Client globusrun GRAM Server gatekeeper RSL RSL HTTP HTTP GSI GSI globusrun callback fork RSL RSL Parser Job Manager use (optional) HTTP GSI Output File Transfer job status/cancel bsub fork Local Resource Manager Process qsub GASS Input File Transfer GASS PBS Job LSF Job Lorenzo Muttoni Impianti Informatici - A.A

38 Resource Specification Language (RSL) Descriptive language for exchange of information between components Syntax similar to MDS/LDAP filters RSL provides two types of information: Resource requirements: Machine type, number of nodes, memory, etc. Job configuration: executable path, program parameters, arguments, information to select resources, e.g. the amount of memory needed to execute a job on a remote machine Globus Toolkit provides an API/SDK for manipulating RSL Lorenzo Muttoni Impianti Informatici - A.A

39 GRAM Protocol GRAM-1: Simple HTTP-based RPC Job request Returns a job contact : Opaque string that can be passed between clients, for access to job Job cancel, status, signal Event notification (callbacks) for state changes Pending, active, done, failed, suspended GRAM-1.5 (U Wisconsin contribution) Add reliability improvements Once-and-only-once submission Recoverable job manager service Reliable termination detection GRAM-2: Based on Web Services (SOAP) Lorenzo Muttoni Impianti Informatici - A.A

40 Information Services Data Management Information Services Resource Management Security Layer Lorenzo Muttoni Impianti Informatici - A.A

41 Information Services overview System information is critical to operation of the grid and construction of applications What resources are available? Resource discovery What is the state of the grid? Resource selection How to optimize resource use Application configuration and adaptation We need a general information infrastructure to answer these questions Requirements and characteristics Uniform, flexible access to information Scalable, efficient access to dynamic data Access to multiple information sources Decentralized maintenance Lorenzo Muttoni Impianti Informatici - A.A

42 Examples of Useful Information Characteristics of a compute resource IP address, software available, system administrator, networks connected to, OS version, load Characteristics of a network Bandwidth and latency, protocols, logical topology Characteristics of the Globus infrastructure Hosts, resource managers Lorenzo Muttoni Impianti Informatici - A.A

43 Grid Information: Facts & Issues Information is always old Time of flight, changing system state Need to provide quality metrics Distributed state hard to obtain Complexity of global snapshot Component will fail Scalability and overhead Many different usage scenarios Heterogeneous policy, different information organizations, etc. Lorenzo Muttoni Impianti Informatici - A.A

44 The GIS Problem: Many Information Sources, Many Views VO A VO C VO B Lorenzo Muttoni Impianti Informatici - A.A

45 Grid Information Service (GIS) Provide access to static and dynamic information regarding system components A basis for configuration and adaptation in heterogeneous, dynamic environments Requirements and characteristics Uniform, flexible access to information Scalable, efficient access to dynamic data Access to multiple information sources Decentralized maintenance Lorenzo Muttoni Impianti Informatici - A.A

46 What is a Virtual Organization? A group of users collaborating across multiple domains who share (some of) their resources to solve particular classes of problems Collates and presents information about these resources in a uniform view Lorenzo Muttoni Impianti Informatici - A.A

47 Globus implementation of the GIS: Metacomputing Directory Service Uses LDAP as Inquiry (LDAP 3.0 Protocol Engine) Based on OpenLDAP with custom backend Integrated caching Access information in a distributed directory Directory represented by collection of LDAP servers Each server optimized for particular function Information dynamically available to tools and applications Lorenzo Muttoni Impianti Informatici - A.A

48 Information providers MDS Components Deliver resource information to backend APIs for accessing & updating MDS contents C, Java, PERL (LDAP API, JNDI) Directory can be updated by: Information providers Applications (i.e., users): various tools for manipulating MDS contents (command line tools, shell scripts & GUIs) Lorenzo Muttoni Impianti Informatici - A.A

49 Two Classes Of MDS Servers Grid Resource Information Service (GRIS) Supplies information about a specific resource Configurable to support multiple information providers LDAP as inquiry protocol Grid Index Information Service (GIIS) Supplies collection of information which was gathered from multiple GRIS servers Supports efficient queries against information which is spread across multiple GRIS server LDAP as inquiry protocol Lorenzo Muttoni Impianti Informatici - A.A

50 Grid Resource Information Service Server which runs on each resource Given the resource DNS name, you can find the GRIS server (well known port = 2135) Provides resource specific information Much of this information may be dynamic Load, process information, storage information, etc. GRIS gathers this information on demand White pages lookup of resource information Ex: How much memory does machine have? Yellow pages lookup of resource options Ex: Which queues on machine allows large jobs? Lorenzo Muttoni Impianti Informatici - A.A

51 Grid Index Information Service GIIS describes a class of servers describes a class of servers Gathers information from multiple GRIS servers Each GIIS is optimized for particular queries Ex1: Which Alliance machines are >16 process SGIs? Ex2: Which Alliance storage servers have >100Mbps bandwidth to host X? Akin to web search engines Organization GIIS The Globus Toolkit ships with one GIIS Caches GRIS info with long update frequency Useful for queries across an organization that rely on relatively static information (Ex1 above) Can be merged into GRIS Lorenzo Muttoni Impianti Informatici - A.A

52 Logical MDS Deployment Programming high level frameworks Grads Gusto GIIS GRISes Lorenzo Muttoni Impianti Informatici - A.A

53 Data Management Services Data Management Information Services Resource Management Security Layer Lorenzo Muttoni Impianti Informatici - A.A

54 Data Grid Problem Enable a geographically distributed community [of thousands] to pool their resources in order to perform sophisticated, computationally intensive analyses on Petabytes of data Note that this problem: Is common to many areas of science Overlaps strongly with other Grid problems Lorenzo Muttoni Impianti Informatici - A.A

55 Globus Toolkit Components Two major Data Grid components: 1. Data Transport and Access Common protocol Secure, efficient, flexible, extensible data movement Family of tools supporting this protocol 2. Replica Management Architecture Simple scheme for managing: multiple copies of files collections of files Lorenzo Muttoni Impianti Informatici - A.A

56 Why FTP? GridFTP Ubiquity enables interoperation with many commodity tools Already supports many desired features, easily extended to support others Well understood and supported We use the term GridFTP to refer to Transfer protocol which meets requirements Family of tools which implement the protocol Note GridFTP > FTP Note that despite name, GridFTP is not restricted to file transfer! Lorenzo Muttoni Impianti Informatici - A.A

57 GridFTP: Basic Approach FTP protocol is defined by several IETF RFCs Start with most commonly used subset Standard FTP: get/put etc., 3 rd -party transfer Implement standard but often unused features GSS binding, extended directory listing, simple restart Extend in various ways, while preserving interoperability with existing servers Striped/parallel data channels, partial file, automatic & manual TCP buffer setting, progress monitoring, extended restart Lorenzo Muttoni Impianti Informatici - A.A

58 Replica Management Maintain a mapping between logical names for files and collections and one or more physical locations Important for many applications Example: CERN HLT data Multiple petabytes of data per year Copy of everything at CERN (Tier 0) Subsets at national centers (Tier 1) Smaller regional centers (Tier 2) Individual researchers will have copies Lorenzo Muttoni Impianti Informatici - A.A

59 Replica Manager Components Low-level Replica Location Service Represents logical-to-physical mappings in a replica catalog High-level Replica Management API globus_replica_manager library Combines calls to file transfer operations and calls to low-level API functions: create, destroy, etc. Lorenzo Muttoni Impianti Informatici - A.A

60 A Model Architecture for Data Grids Metadata Catalog Attribute Specification Logical Collection and Logical File Name GridFTP Control Channel Application Selected Replica Replica Catalog Multiple Locations Replica Selection Performance Information & Predictions MDS NWS Disk Array GridFTP Data Channel Disk Cache Tape Library Disk Cache Replica Location 1 Replica Location 2 Replica Location 3 Lorenzo Muttoni Impianti Informatici - A.A

61 Globus Toolkit: Evaluation (+) Good technical solutions for key problems, e.g. Authentication and authorization Resource discovery and monitoring Reliable remote service invocation High-performance remote data access This + good engineering is enabling progress Good quality reference implementation, multilanguage support, interfaces to many systems, large user base, industrial support Growing community code base built on tools Lorenzo Muttoni Impianti Informatici - A.A

62 Globus Toolkit: Evaluation (-) Protocol deficiencies, e.g. Heterogeneous basis: HTTP, LDAP, FTP No standard means of invocation, notification, error propagation, authorization, termination, Significant missing functionality, e.g. Databases, sensors, instruments, workflow, Virtualization of end systems (hosting envs.) Little work on total system properties, e.g. Dependability, end-to-end QoS, Reasoning about system properties Lorenzo Muttoni Impianti Informatici - A.A

63 Globus Toolkit 3.0 OGSA - Open Grid Service Architecture OGSI - Open Grid Service Infrastructure

64 Web Services Increasingly popular standards-based framework for accessing network applications W3C standardization; Microsoft, IBM, Sun, others WSDL: Web Services Description Language Interface Definition Language for Web services SOAP: Simple Object Access Protocol XML-based RPC protocol; common WSDL target WS-Inspection Conventions for locating service descriptions UDDI: Universal Desc., Discovery, & Integration Directory for Web services Lorenzo Muttoni Impianti Informatici - A.A

65 Transient Service Instances Web services address discovery & invocation of persistent services Interface to persistent state of entire enterprise In Grids, must also support transient service instances, created/destroyed dynamically Interfaces to the states of distributed activities E.g. workflow, video conf., dist. data analysis Significant implications for how services are managed, named, discovered, and used In fact, much of our work is concerned with the management of service instances Lorenzo Muttoni Impianti Informatici - A.A

66 Open Grid Services Architecture Service orientation to virtualize resources From Web services: Standard interface definition mechanisms: multiple protocol bindings, multiple implementations, local/remote transparency Building on Globus Toolkit: Grid service: semantics for service interactions Management of transient instances (& state) Factory, Registry, Discovery, other services Reliable and secure transport Multiple hosting targets: J2EE,.NET, C, Lorenzo Muttoni Impianti Informatici - A.A

67 OGSA Service Model System comprises (a typically few) persistent services & (potentially many) transient services All services adhere to specified Grid service interfaces and behaviors Reliable invocation, lifetime management, discovery, authorization, notification, upgradeability, concurrency, manageability Interfaces for managing Grid service instances Factory, registry, discovery, lifetime, etc. => Reliable, secure mgmt of distributed state Lorenzo Muttoni Impianti Informatici - A.A

68 The Grid Service A (potentially transient) Web service with specified interfaces & behaviors, including Creation (Factory) Global naming (GSH) & references (GSR) Lifetime management Registration & Discovery Authorization Notification Concurrency Manageability Lorenzo Muttoni Impianti Informatici - A.A

69 Globus Toolkit v3 (GT3) Open Source OGSA Technology Implement core OGSI interfaces Support primary GT2 interfaces High degree of backward compatibility Multiple platforms & hosting environments J2EE, Java, C,.NET, Python New services SLA negotiation (GRAM-2), registry, replica location, community authorization, data, Lorenzo Muttoni Impianti Informatici - A.A

70 Globus Toolkit Refactoring Grid Security Infrastructure (GSI) Used in Grid service network protocol bindings Meta Directory Service 2 (MDS-2) Native part of each Grid service: Discovery, Registry, RegistryManagement, Notification Grid Resource Allocation & Mgmt (GRAM) Gatekeeper -> Factory for job mgr instances GridFTP Refactor control channel protocol Other services refactored to used Grid services Lorenzo Muttoni Impianti Informatici - A.A

71 Comparing GT2 and GT3 The same GSI certificates Command-line tools GRAM service GASS features GridFTP service Information architecture Grid architecture Open source Community-driven Standards-based but different! Proxy certificates OGSI-compliant information services OGSI-compliant GRAM service Web Services integration Hosting environments RSL XML Lorenzo Muttoni Impianti Informatici - A.A