Gridenabled Research Activities in CAS Kai Nan Computer
Grid-enabled Research Activities in CAS Kai Nan Computer Network Information Center (CNIC) Chinese Academy of Sciences (CAS) Shanghai, 21 Feb 2006
Outline • I. Background – CAS Informatization Program 2001 -2005 – CAS e-Science Initiative 2006 -2010 • II. Grid-enabled Research Activities – Middleware – Applications • III. Collaborations with EU
Vision of CAS Informatization • e-Science + ARP →Digital CAS • e-Science represents Informatization of Research Activities • ARP (Academia Resource Planning) represents Informatization of Administrative Activities for Research
CAS Informatization Program (2001 -2005) • Major Projects – emphasis on Upgrade of Infrastructure
Progress Infrastructure Networking Item 1 Gbps 2. 5 Gbps backbone 2 Mbps N*155 M+2. 5 G 55 Mbps 620 M+12 G Peak TFLOPS 0. 13 5. 5 Linpack TFLOPS 0. 05 4. 3 2. 1 TB 182 TB 21 >45 180 400+ 725 GB 15 TB+ Storage Member institutes Scientific Database 2005 core Oversea link HPC By 2000 Databases Data volume
Resources • Lenovo 6800 Superserver • Storage • Viz. Wall • Scientific Data (SDB) • Science Digital Lib (CSDL)
CAS e-Science Initiative 2006 -2010 • e-Science would be applications-driven • focus on implementation of e-Science Virtual Labs, the way for scientists to use • infrastructure may need refactoring
e-Science Virtual Labs • “Virtual Labs” • special meanings in the e-Science context • the key position in our e-Science framework • the core component to make e-Science a reality
v. Labs Requirements • Infrastructure may be (almost) ready, but e-Science is not yet. – so many existing resources in place, but just a few could be brought into full play even now, with an advanced infrastructure ready. • bottleneck may be the gap between products by computer experts and end users of domain scientists • much more effort than expected to bridge this gap • Virtual Lab is proposed to be – a basic unit of research activity in the e-Science environment – the right user interface between scientists and their e-Science environment
v. Labs Goals • With Virtual Labs, – all kinds of resources could be integrated into a single access point; – customized and flexible services would be provided according to the specific requirements of different domains in an easier way than ever before; – multidisciplinary, multi-site and multiorganization collaboration could be carried out on a routine basis.
Grid Middleware
Scientific Database (SDB) & Scientific Data Grid (SDG) 45 institutes participated 503 databases 16. 6 TB 236 -CPU Superserver (1 TF) 20 TB Disk Array 50 TB Tape Library Viz. Wall & Access Grid
Requirements and SDG • How to FIND the data I want from hundreds or thousands of databases • How to ACCESS large-scale, distributed and heterogeneous scientific data uniformly and conveniently • How to make sure all this goes always in a SECURE and proper way
SDG Software Architecture
Data Access Service (DAS) • • Uniform Access Interface (read-only) Rich metadata Easy publish on web flexible configuration and extensibility
DAS modules Data. View Data Access Interface Virtual Database Mapping. Builder Physical Database
grid-enabled Applications
e-Science applications • • • High Energy Physics Astronomy Biology Natural Resources Disaster Reduction …
YBJ-ARGO/AS • Italy, Japan-China cosmic ray observatories in Tibet. • 200 TB raw data per year. • Data transferred to IHEP and processed with 400 CPUs. • Rec. data accessible by collaborators.
YBJ-ARGO • Established a 8 Mb/s link from Tibet to Beijing, by CNIC of CAS. To be upgraded to 155 Mb/s soon. Stopped bringing tapes half year agao. • Building a computing system based on LCG, collaboration of IHEP of CAS, CNIC of CAS, INFN of Italia , EU-China Grid application under EU FP 6 project
LCG Tier-1/2 • to build a LCG Tier-1/2 node in China • Institute of High Energy Physics of CAS • CNIC providing support and working together with IHEP
LCG 2 production site @CNIC http: //goc. grid. sinica. edu. tw/gstat/BEIJING-CNIC-LCG 2 -IA 64/ Monitoring Info on BEIJING-CNIC-LCG 2 -IA 64
VO=World Wide Telescope Chandr Whipple -raya Oak Ridge 1. 2 m C O MMT SIRTF Hubble VLA Smm array Antartica submm Magellan 6. 5 m
China Virtual Observatory at SDG Portal Data Services Application Tools Grid Services Catalog
Avian Bird Flu Alarming & Predicating System By: Institute of Microbiology, CAS Institute of Zoology, CAS Institute of Virology, CAS CNIC, CAS
Avian Bird Flu in Gangcha, Qinghai Province, May 2005 上千支鱼鸥、棕鸥、斑头雁死亡
Tasks • Integrate bird-flu basic databases from multiple institutes • Field survey on bird-flu • Establish bioinformatics comprehensive analysis system for bird-flu • Establish bird-flu alarming and predicting system • Establish international cooperative work environment • Establish information publishing system (web)
Bird-flu basic databases • Standards – Bird-flu basic database’s model and data standard – Metadata specification and description language of bird-flu information • Data resources – – – – Bird-flu virus resource database Bird-flu virus inherent resource database Bird-flu history database Bird-flu dynamic monitoring database Bird-flu host database Bird-flu information database Bird-flu international DNA database Bird-flu international research progress database
Technical architecture Model Database Model verifica tion Model Storage Host data Model Evaluation System Survey data Virus data avian trade routes Distribute Model Winter Survey Data Survey on source Predicting SDB
IAP Program “Global Natural Hazards and Disaster Reduction”
East Asia Resource Environment Collaborative Research Network • a network connecting a dozen of institutes and stations from China, Russia and Mongolia • a series of data products which integrate many relevant databases in this area and support application research • a platform for int’l collaborative research
Global Natural Hazards and Disaster Reduction • issues in disaster reduction – – Development of mechanism of major natural disaster Prediction of major natural disaster; Assessment of major natural disaster; Pre-warning and emergency response of major natural disaster – Regional integrated research on major natural disaster • Database Construction & Application on “Natural Disaster Mitigation” • Disaster simulation
Collaborations with EU • Ongoing – EUChina. Grid: Interconnection and Interoperability of Grids between Europe & China – Infrastructure is being better • Look forward to – further more on MIDDLEWARE & APPLICATIONS
Thank you!
- Slides: 37