Grid Services Overview & Introduction Ian Foster Argonne National Laboratory University of Chicago...

Grid ServicesOverview & Introduction

Ian FosterArgonne National Laboratory

University of Chicago

Univa Corporation

OOSTech, Baltimore, October 26, 2005

2

What’s This About “Grid Services”?

I will describe Web service interfaces that implement useful behaviors Primitives: resources, state, security Services: program execution, data movement, data

access, … I will also describe open source software that

implements those interfaces In particular, Globus Toolkit (GT4)

This is all standard Web services! “Grid is a use case for Web services, focused on

resource management”

3

RR

R

R

R

R

R

RR

R

What Grid is About:Aggregation in Virtual Organizations• Distributed resources and people• Linked by networks, crossing admin domains• Sharing resources, common goals• Dynamic behaviors

VO-BVO-A

R

R

R

R

4

R RR

R

R

R

R

R

RRR

R

VO-A VO-B

• Distributed resources and people• Linked by networks, crossing admin domains• Sharing resources, common goals• Dynamic behaviors• Fault tolerant

What Grid is About:Aggregation in Virtual Organizations

5

Grid Technology:Take Services Seriously

Model the world as a collection of services Computations, computers, instruments, storage,

data, communities, agreements, … Focus on what these things have in common

E.g., state modeling & lifecycle: Negotiation, deployment/creation, modeling, monitoring, management, termination

E.g., security: Authentication, authorization, audit, …

Result is Grid infrastructure Using Web services as a platform

6

“Stateless” vs. “Stateful” Services

Without state, how does client: Determine what happened (success/failure)? Find out how many files completed? Receive updates when interesting events arise? Terminate a request?

Few useful services are truly “stateless”, but WS interfaces alone do not provide built-in support for state

Client

FileTransferService

move (A to B)move

7

FileTransferService (without WSRF)

Developer reinvents wheel for each new service Custom management and identification of state: transferID Custom operations to inspect state synchronously

(whatHappen) and asynchronously (tellMeWhen) Custom lifetime operation (cancel)

Client

FileTransferService

move (A to B) : transferIDmove

statewhatHappen

tellMeWhen

cancel

8

WSRF in a Nutshell Service State representation

Resource Resource Property

State identification Endpoint Reference

State Interfaces GetRP, QueryRPs,

GetMultipleRPs, SetRP Lifetime Interfaces

SetTerminationTime ImmediateDestruction

Notification Interfaces Subscribe Notify

ServiceGroups

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

9

FileTransferService (w/ WSRF)

Developer specifies custom method to createResource and leaves the rest to WSRF standards:

State exposed as Resource + Resource Properties and identified by Endpoint Reference (EPR)

State inspected by standard interfaces (GetRP, QueryRPs) Lifetime management by standard interfaces (Destroy)

ClientFileTransferService

createResource (A to B) : EPRcreateResource

RPs

Transfer getRP

queryRPs

destroy

10

Grid Infrastructure:Open Standards

Web services(WSDL, SOAP, WS-Security, WS-ReliableMessaging, …)

WS-Resource Framework & WS-Notification*(Resource identity, lifetime, inspection, subscription, …)

WS-Agreement(Agreement negotiation)

WS Distributed Management(Lifecycle, monitoring, …)

Applications of the framework(Compute, network, storage provisioning,

job reservation & submission, data management,application service QoS, …)

*WS-Transfer, WS-Enumeration, WS-Eventing, WS-Management define similar functions

11

Data Mgmt

SecurityCommonRuntime

Execution Mgmt

Info Services

GridFTPAuthenticationAuthorization

ReliableFile

Transfer

Data Access& Integration

Grid ResourceAllocation &

ManagementIndex

CommunityAuthorization

DataReplication

CommunitySchedulingFramework

Delegation

ReplicaLocation

Trigger

Java Runtime

C Runtime

Python Runtime

WebMDS

WorkspaceManagement

Grid Telecontrol

Protocol

Globus Toolkit v4www.globus.org

CredentialMgmt

Globus Toolkit: Open Source Grid Infrastructure

Tools for building WSRF

services

12

GT4 WS Core in a Nutshell

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

Implementation of WSRF: Resources,

EndpointReferences, ResourceProperties

Operation Providers: pre-build implementations of

WSRF operations

Notification implementation: Topics, TopicSet, Embedded

Notification Consumer service

Implementations of Resources (ReflectionResource,

PersistentReflectionResource) and ResourceProperties

(SimpleResourceProperty, ReflectionResourceProperty)

14

Service Container


RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

Service Container: host multiple services in container; one JVM

process

…more details: based on AXIS service

container, processes SOAP messages, ResourceContext

extension.

15

Service Container


RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

Secure Communication: Transport, Message,

Conversation (Transport demonstrates best

performance)

PIP

PDP

Configurable Security Policies: Policy Information

Points (PIPs), Policy Decision Points (PDP) -- chained

Example authorization PDPs: GridMap, SAML

implementations,XACML policies

16

Service Container


RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

PIP

PDP

WorkManager DB Conn Pool JNDI Directory

WorkManager: “thread pool”, site independent

“work” manager

Apache Database Connection Pool library

(JDBC “DataSource” implementation)

JNDI Directory: manages internal, shared objects

(ResourceHomes, WorkManager,

Configuration objects,…)

17

Apache Tomcat

Service Container


RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

RPs

Resource

ServiceGetRP

GetMultRPs

SetRP

QueryRPs

Subscribe

SetTermTime

Destroy

EPREPR

EPR

ResourceHome

PIP

PDP

WorkManager DB Conn Pool JNDI Directory

Deploy Service Container “standalone”

or within Apache Tomcat

18

Data Mgmt


Execution Mgmt

Info Services


ReliableFile

Transfer



ManagementIndex


DataReplication


Delegation

ReplicaLocation

Trigger

Java Runtime

C Runtime

Python Runtime

WebMDS

WorkspaceManagement

Grid Telecontrol

Protocol


CredentialMgmt


19

GT4 Security Public-key-based authentication Extensible authorization framework based on Web

services standards SAML-based authorization callout

As specified in GGF OGSA-Authz WG

Integrated policy decision engine XACML policy language, per-operation policies, pluggable

Credential management service MyProxy (One time password support)

Community Authorization Service Standalone delegation service

20

GT4 Use of Security Standards

Supported, Supported, Fastest, but slow but insecure so default

21

GT-XACML Integration

eXtensible Access Control Markup Language OASIS standard, open source implementations

XACML: sophisticated policy language Globus Toolkit ships with XACML runtime

Included in every client and server built on GT Turned-on through configuration

… that can be called transparently from runtime and/or explicitly from application …

… and we use the XACML-”model” for our Authz Processing Framework

22

Data Mgmt


Execution Mgmt

Info Services


ReliableFile

Transfer



ManagementIndex


DataReplication


Delegation

ReplicaLocation

Trigger

Java Runtime

C Runtime

Python Runtime

WebMDS

WorkspaceManagement

Grid Telecontrol

Protocol


CredentialMgmt

I. Foster, Globus Toolkit Version 4: Software for Service-Oriented Systems, LNCS 3779, 2-13, 2005


23

Managing Computers & Computation

GRAM (Grid Resource Allocation & Management) service Negotiate access Stage code Monitor service Manage service Collect accounting data

Can negotiate access to clusters,creation of virtual machines,establishment of virtual networks, …

GRAM

Client

24

CMS DC04

ATLASDC2

Usa

ge:

CP

Us

Dynamic Provisioning ofComputational Services

Open Science Grid use over 6 months

25

Dynamic Service Deployment

CommunityA

CommunityZ

…

• Community scheduling logic• Data distribution• Community management• Science services• PlanetLab nodes• ...

Requirements:• Community control• Persistence• Resource guarantees• Non- interference

26

Data Mgmt


Execution Mgmt

Info Services


ReliableFile

Transfer



ManagementIndex


DataReplication


Delegation

ReplicaLocation

Trigger

Java Runtime

C Runtime

Python Runtime

WebMDS

WorkspaceManagement

Grid Telecontrol

Protocol


CredentialMgmt


27

Managing Storage & Data

Service interfaces for managing storage & data movement Storage management (SRM, NeST) Data movement (GridFTP, RFT) Replica management (RLS, DRS)

Service interfaces for accessing data in diverse formats OGSA Data Access & Integration GridFTP data access & movement

28

GridFTP in GT4 100% Globus code

No licensing issues Stable, extensible

IPv6 Support XIO for different transports Striping multi-Gb/sec wide area transport

27 Gbit/s on 30 Gbit/s link Pluggable

Front-end: e.g., future WS control channel Back-end: e.g., HPSS, cluster file systems Transfer: e.g., UDP, NetBLT transport

Bandwidth Vs Striping

0

2000

4000

6000

8000

10000

12000

14000

16000

18000

20000

0 10 20 30 40 50 60 70

Degree of Striping

Ba

nd

wid

th (

Mb

ps

)

# Stream = 1 # Stream = 2 # Stream = 4

# Stream = 8 # Stream = 16 # Stream = 32

Disk-to-disk onTeraGrid

29Reliable File Transfer:Third Party Transfer

RFT Service

RFT Client

SOAP Messages

Notifications(Optional)

DataChannel

Protocol Interpreter

MasterDSI

DataChannel

SlaveDSI

IPCReceiver

IPC Link

MasterDSI

Protocol Interpreter

Data Channel

IPCReceiver

SlaveDSI

Data Channel

IPC Link

GridFTP Server GridFTP Server

Fire-and-forget transfer Web services interface Many files & directories Integrated failure recovery Has transferred 900K files

30

Replica Location Service

Identify location of files via logical to physical name map

Distributed indexing of names, fault tolerant update protocols

GT4 version scalable & stable

Managing ~40 million files across ~10 sites

IndexIndex

Local DB

Update send (secs)

Bloom filter

(secs)

Bloom filter (bits)

10K <1 2 1 M

1 M 2 24 10 M

5 M 7 175 50 M

31

Cardiff

AEI/Golm

Birmingham•

Reliable Wide Area Data Replication

Replicating >1 Terabyte/day to 8 sites>30 million replicas so farMTBF = 1 month

LIGO Gravitational Wave Observatory

32

Data Replication Service:An Example of Service Composition

At requesting site, deploy: WSRF services

Data Replication Service

Delegation Service Reliable File Transfer

Service

Pre-WSRF components Replica Location

Service (Local Replica Catalog and Replica Location Index)

GridFTP Server

Web Service Container

Data Replication

Service

Replicator Resource

Reliable File

Transfer Service

RFT Resource

Local Replica Catalog

Replica Location

Index

GridFTP Server

Delegation Service

Delegated Credential

Local Site

33

Data Replication Service:WSDL (PortType)

<?xml version=“1.0” encoding=“utf-8”?><wsdl:definitions name=“Replication” …>

…

<wsdl:portType name=“ReplicatorPortType” wsrp:ResourceProperties=“ReplicatorResourceProperties”>

<wsdl:operation name=“createReplicator”> … <wsdl:operation name=“start” … <wsdl:operation name=“stop”> … <wsdl:operation name=“suspend”> … <wsdl:operation name=“resume”> … <wsdl:operation name=“findItems”> … <wsdl:operation name=“SetTerminationTime”> <wsdl:operation name=“Destroy”> … <wsdl:operation name=“QueryResourceProperties”> … <wsdl:operation name=“GetMultipleResourceProperties”> … <wsdl:operation name=“GetResourceProperty”> … <wsdl:operation name=“Subscribe”> … <wsdl:operation name=“GetCurrentMessage”> … </wsdl:portType>

</wsdl:definitions>

34

Data Replication Service:WSDL (Resource Properties)

<?xml version=“1.0” encoding=“utf-8”?><wsdl:definitions name=“Replication” …>

…

<wsdl:portType name=“ReplicatorPortType” wsrp:ResourceProperties=“ReplicatorResourceProperties”>

<wsdl:operation name=“createReplicator”> … <wsdl:operation name=“start” … <wsdl:operation name=“stop”> … <wsdl:operation name=“suspend”> … <wsdl:operation name=“resume”> … <wsdl:operation name=“findItems”> … <wsdl:operation name=“SetTerminationTime”> <wsdl:operation name=“Destroy”> … <wsdl:operation name=“QueryResourceProperties”> … <wsdl:operation name=“GetMultipleResourceProperties”> … <wsdl:operation name=“GetResourceProperty”> … <wsdl:operation name=“Subscribe”> … <wsdl:operation name=“GetCurrentMessage”> … </wsdl:portType>

</wsdl:definitions>

<xsd:element name="ReplicatorResourceProperties“> … <xsd:element name=“status” …/> <xsd:element name=“stage” …/> <xsd:element name=“result” …/> <xsd:element name=“errorMessage” …/> <xsd:element name=“count” …/> <xsd:element name=“Topic” …/> <xsd:element name=“TopicExprDialect” …/> <xsd:element name=“TeminationTime” …/> <xsd:element name=“CurrentTime” …/> <xsd:element name=“FixedTopicSet” …/> …</xsd:element>

35

Data Mgmt


Execution Mgmt

Info Services


ReliableFile

Transfer



ManagementIndex


DataReplication


Delegation

ReplicaLocation

Trigger

Java Runtime

C Runtime

Python Runtime

WebMDS

WorkspaceManagement

Grid Telecontrol

Protocol


CredentialMgmt


36

GT4 Container

GT4 Monitoring & Discovery

GRAM User

MDS-Index

GT4 Cont.

RFT

MDS-Index

GT4 Container

MDS-Index

GridFTP

adapter

Registration &WSRF/WSN Access

Custom protocolsfor non-WSRF entities

Clients(e.g., WebMDS)

Automatedregistrationin container

WS-ServiceGroup

37

Summary

Services are typically stateful, but WS standards did not support stateful entities

WSRF provides standards for management, identification, lifetime, inspection, & manipulation of stateful entities

GT4 WS Core provides a rich environment for developing stateful services

GT4 provides a rich set of services based on WSRF & WS-Notification

38

For More Information

Globus Alliance www.globus.org

Global Grid Forum www.ggf.org

Background information www.mcs.anl.gov/~foster

2nd Editionwww.mkp.com/grid2

Grid Services Overview & Introduction Ian Foster Argonne National Laboratory University of Chicago...

Documents

Transcript of Grid Services Overview & Introduction Ian Foster Argonne National Laboratory University of Chicago...