INFSO-RI Enabling Grids for E-sciencE Grid Interoperations Cook Book Markus Schulz, Laurence Field EGEE SA3 CERN-IT-GD

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 2 Overview Interoperability –Speaking the same language (or using a translator) –Middleware problem Interoperation –Using interoperating infrastructures –Need the above, but needs operational links

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 3 Why Different production Grids have been established worldwide –Funding based on regions and application domains Grid infrastructures are based on different middleware –Often confused with the infrastructures (EGEE, gLite, LCG-xx….) –Historical fact Several user communities depend on these infrastructures –Main computing resource  Cycles and storage –User communities span multiple regions and funding agencies

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 4 Why is there diversity? The infrastructures outpaced standardization We discovered how to do grid computing on the go –First there where NO standards –Then there where standards that didn’t reflect experience –Then there where active users  Active users drive the infrastructures  Mandate functional and performance evolution Standardization work is not a directly visible advantage As is security….. –Then users discovered other infrastructures  And things got complicated –Now usable standards start to emerge….  But infrastructures can only convert slowly

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 5 Why is there diversity? This is not surprising: –Grid computing is about interoperability/interoperation.  Different Batch Systems  Different Storage Systems  Different Administrative domains –Grid Middleware is the implementation of the abstract interface. –Grid Interoperability, abstracting the abstract interfaces

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 6 Hourglass Model Site Specific Systems VO/Grid Specific Middleware MonitoringService Discovery Job Submission File Transfer Security Popular: But tells only half of the story 1/4 of cost Policies and operational procedures Support…. Hidden assumptions Network access from WN nodes Security & Availability Policy Usage Rules Certification Authorities Audit Requirements Incident Response User Registration & VO Management Application Development & Network Admin Guide VO Security

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 7 Why Interoperation? Simple, because there is a clear need VOs started to interoperate on their own “Keyhole” adapters emerged –Minimal interfaces Problematic –Requirements change –Many adapters need to be maintained  1 per VO/Infrastructure  Grids evolve at different pace Change, change,change –Workflow debugging becomes (almost) impossible  Different error messages  Small surface of the keyholes –VOs can’t follow operations easily  Different tools –Many more synchronization work (meetings)

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 8 Why Interoperation? Because it steers the development of standards into the right direction Linking the infrastructures –Helps to establish practical, usable standards  For the people, by the people –Helps to establish working policies  Sites and users –Reflects different experiences –Keeps the middleware modular  Domain separation DATA, JOBS, INFORATION…..

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 9 Why EGEE? DEISA TeraGrid Related infrastructure projects

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 10 How? Understanding the differences –Compatibility matrix Domains that have to be linked for interoperability –Security –Information Services –Job Management –Data Management For interoperation you have to add –Monitoring –Accounting –Operational links and joint policies –Trouble ticket systems –Operational security

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 11 GIN OGF’s Grid Interoperability Now Six international teams met for the first time at GGF-16 in Feb 2006 –Application Use Cases –Authentication/Identity Mgmt –Job Description Language –Data Location/Movement –Information Schemas –Testbeds GINGIN

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 12 Interoperability Matrix Simple example: ARCOSGEGEE Job SubmissionGridFTPGRAM Service DiscoveryLDAP/GIIS LDAP/BDII SchemaARCGLUE Storage Transfer ProtocolGridFTP Storage Control ProtocolSRM SecurityGSI/VOMS

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 13 Select Strategy For each domain select one strategy Common Interfaces –seems to be the most straightforward –absence of established standards  which interface do you choose  grid infrastructures have heavily invested in one interface  this is the ultimate goal, but will require a long time We have to provide services NOW  Good standards are hard to get See SRM and GLUE discussions on semantic details Adapters and Translators –adapters and translators can be used in the higher level services  Condor approach Adapters for condor, GRAM, ARC, UNICORE,….. –Changes confined to higher level interfaces –Infrastructure “un-touched”  But environments and client libs. have to be adapted –Good indicator for area that should be standardized  Adapters and translators can only work if same functionality is provided

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 14 Select Strategy Grid Gateways –Used when concepts are too different  Different security models are hard to “translate”  No corresponding services –Technically close to adapters and translators –Standalone, trusted service(s) –Scalability is problematic  All jobs go through one/a few gateways (bottleneck) –Robustness can be an issue  Russian doll (layered software) –Only one step ahead of users “keyhole” adapters  Short term solution  Demonstrates potential of interoperability –Gateways are indicators for different domains  Maybe concepts have to be re-evaluated

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 15 Example GIN-INFO Starting from bi-lateral work –EGEE / OSG already interoperating since Autumn 2005  Both are using an LDAP based information system  Both are using the Glue schema ( different boot strapping) OSG site URLs generated from OSG GOC DB EGGE site URLs generated from EGEE GOC DB –EGEE /NDGF  Working on interoperability since Summer 2005  Both use an LDAP based information system But different schema  Trying schema translation approach

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 16 Example GIN-INFO Naregi working on interoperability with EGEE since winter 2006 –Naregi information system, “Cell domains”  Different Schema, (vendor extensions to CIM)  CIM providers  OGSA-DIA interface –schema translation Teragrid –MDS4 information system with Glue schema version 1.1 –Translator Pragma –WebSIM –Prototype translator finished

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 17 Initial Architecture GIN BDII ARC BDII EGEE Site OSG Site NDGF Site Naregi Grid Teragrid Grid Pragma Grid NDGF BDII EGEE BDII OSG BDII Naregi BDII Teragrid BDII Pragma BDII Translator

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 18 Current Architecture Generic Information Provider Provider EGEE Provider OSG Provider NDGF GIN BDII ARC BDII Provider Naregi Provider Teragrid Provider Pragma EGEE Site OSG Site NDGF Site Naregi Grid Teragrid Grid Pragma Grid Grids use GIN-BDII as the source See Naregi

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 19 Interoperating information systems DEISA EGEE Naregi Nordugrid OSG Pragma Teragrid

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 20 Performance Indicators EGEEOSGNDGFNaregiTeragridPragma QueryLDAP OGSA- DAI WSRFwget Sites Clusters Real20.3s11.0s16.8s74.7s24.4s21.1s User15.1s1.2s2.3s14.3s21.9s0.2s System4.9s0.7s1.5s0.4s3.1s0.2s Memory0.9%0.8%0.9%9.0%7.3%0.8% PIII 1GHz, 256Mb

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 21 Complexity Syntax Interoperability Matrix(Naregi) GridSchemaDataQuery Lang Client IFSoftware Tera-GridGLUEXMLXPathWSRF RP Queries MDS4 OSGGLUELDIFLDAP BDII NAREGI CIM 2.10+extRelationalSQLOGSA-DAI WS-I RUS CIMOM + OGSA-DAI EGEE/ LCG GLUELDIFLDAP BDII RelationalSQLR-GMA i/fR-GMA Nordu Grid ARCLDIFLDAP GIIS

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 22 Summary Info Systems Information systems are very similar Joining information systems is easy Translating information is tricky –Moving from one model to another is straight forward. –Showstopper if information doesn’t map, ie missing attributes We can live with different information systems –But we can’t live with different information How do we ensure good quality information? –Need to develop tests for the information  Based on the use cases How can we ensure the coordinates are correct for a site? – > grid operations!

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 23 Problematic Area Monitoring –Foundation of interoperation Many different tools –For each infrastructure more than one No well defined schema –Same attribute has different meanings –Security relevant information exposed Sites hate double monitoring

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 24 Interoperability Matrix SensorsLocal Transport Site CacheExternal Transport SchemaRepository MDSInformation Providers LDAPMemory LDAP DB LDAP R-GMAVariousHTTPMemory SQL HTTPR-GMAMySQL ApelCustom Scripts MySQL R-GMA HTTP R-GMAMySQL GridICEInformation Providers LemonLemmon Server MDS LDAP Postgresql Grid CatVariousCronSQL LiteGRAMGridCatPostgresql MonaLisaMonitoring Module ???SQL DBs???Java Objects SQL DBs

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 25 Interoperability Environment gLite Environment Resource Broker Node Network Server gLite UI glite-job-submit glite-job-status … Workload Manager MatchMaker Broker Job Adapter BDII File Catalogue UNICORE Information Provider UNICORE Trusted Agent UNICORE Environment Usite A Gateway Vsite A1 Target System NJS TSI File System Batch System Workflow Engine User Certificate Incarnation Database Job Controller - Condor-U VOMS UUDB gLite to Unicore

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 26 What does it take? OSG –Very similar middleware –Close link via main users ARC (NDGF) NAREGI UNICORE (DEISA) OGF-GIN

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 27 OSG November and December 2004 –Initial meeting with OSG to discuss interoperability  A common information schema was the key –Proposal for version 1.2 of the Glue Schema was discussed  Include new attributes required by OSG, Marco Mambelli January 2005 –Proof of concept was tried, Leigh Grundhoefer (Indiana)  Installed Generic Information Provider (GIP) on an OSG CE  OSG CE was configured to support the dteam VO  “Hello world” job, submitted through the LCG RB and ran on an OSG CE  Installed the LCG clients available on OSG from a tarball Oliver Keeble (CERN)  Submitted test job that did basic data management operations

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 28 OSG Modifications to the OSG and LCG software releases –Updated the GIP to publish version 1.2 of the Glue Schema  The GridFTP server on the OSG CE advertised as an LCG SE –Automatically configure the GIP in the OSG release  Information scavenger script, Shaowen Wang (Iowa) August 2005 (month of focussed activity) –Included first OSG sites into the LCG operational framework –Set up a BDII that represented these OSG sites –Included this BDII to the LCG information system –All OSG sites found in this BDII were automatically tested  Using the Site Functional Tests (SFT) framework –Created a script to install the LCG clients on OSG CEs November 2005 –First user jobs from GEANT4 arrived on OSG –GIP validator for OSG operations. Shaowen Wang (Iowa)

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 29 OSG March 2006, Operations Progress –Information system bootstrapping.  Dynamic web page from OSG GOC DB. –Routing of trouble tickets. –Joint operations VO  For running tests.  Deployment of client libraries. –OSG joined the Monday WLCG operations meeting to report on WLCG issues Summer 2006 –CMS successfully taking advantage interoperations  Without being aware of it

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 30 Summary EGEE OSG How to maintain interoperation? –Grids evolve –Different release cycles Testbed for interoperation is needed NOW Interoperability took 6 month –Technical a simple use case Interoperation took 6 month

Enabling Grids for E-sciencE INFSO-RI Interoperation CookBook 3/29/07 31 Next Steps Continue bi-lateral work where needed –OSG-EGEE  Add certification testbeds –ARC - EGEE  Funded by EGEE –Unicore - EGEE  Funded by EGEE –Naregi -EGEE Long term work and standardization via OGF –GIN was already extremely useful Virtualized user environments via Xen Interoperation is as complex as interoperability –Monitoring, support, accounting, security, policies……