Pacific Rim Library

1
Pacific Rim Library

• Cindy Zheng, SDSC
• Reagan Moore, SDSC
• University of California, San Diego

2
Pacific Rim Library

• Status of collection at SDSC
• Size
• Costs
• Opportunity for use of data grids
• Replication
• Preservation

3
PRDLA Collection at SDSC

• Collection size
• 800 Gbytes
• 14 million files
• Server capacity
• Windows NT with 2 Tbytes disk
• AIT2 tape library for backup, 1 Tbyte of tape
• 3 web servers
• Access rate
• Average 1 million web page accesses per month
• Does not count Siku server

4
PRDLA Collection Support

• Original cost
• 22,000 for a 250 GB Windows server
• Current costs
• 2,700 for 1-TB Grid Brick - Linux
• 360/yr hardware maintenance
• 1020/yr operating system support
• 1800/yr web server support
• 3000/yr database support

5
Data Grid Opportunities

• Replicate collection to additional sites
• Provide uniform (logical) name space
• All sites use the same logical names to reference
  files
• Redirect access to alternate storage when systems
  off-line for maintenance
• Integrate file access with archive access
• Use same access mechanisms
• Support larger collections

6
Storage Resource Broker

• Preservation environments
• Manage technology evolution
• Provide authenticity mechanisms
• Automate preservation processes
• SRB provides abstractions needed to
• Replicate data onto new types of storage
• Support alternate access mechanisms (WSDL)

7
SRB Collections at SDSC
8
Grid Installations

• Australia - University of Queensland, APAC
• Japan - KEK (Tsukuba)
• Korea - KISTI, Korea Institute of Science and
  Technology Information
• Singapore - National University of Singapore
• Taiwan - National Taiwan University
• University of California - California Digital
  Library, UCSD