MIT Media Laboratory: Petabyte-scale IP Storage

"MIT Has Big Plans for IP Storage", Enterprise Storage Forum, May 15, 2006
　http://www.enterprisestorageforum.com/ipstorage/news/article.php/3606236
"MIT demos 1 PB IP SAN", SearchStorage.com, 15 May 2006
　http://searchstorage.techtarget.com/originalContent/0,289142,sid5_gci1188277,00.html?track=NL-52&ad=551907


"Media Lab project explores language acquisition", May 15, 2006
　http://web.mit.edu/newsoffice/2006/minding-baby.html
　"Roy is recording nearly all of his new son's waking hours in an ambitious attempt to use these data
　 to unravel the mystery of how humans naturally acquire language within the context of their primary
　 social setting. He will pay particular attention to the role of physical and social context in how his son,
　 9 months old, learns early words and early grammatical constructions."
　"Roy's vast recording and analysis effort, known as "The Human Speechome Project" (speech + home),
　 will yield some 400,000 hours of audio and video data over three years."
　"Roy and his wife have already gathered more than 300 gigabytes per day of compressed data by recording
　 an average of 12-14 hours a day."
　"Once at the Media Lab, the data is stored in a massive petabyte (1 million gigabyte) disk storage system
　 donated by several companies: Bell Microproducts, Seagate Technology, Marvell and Zetera."
　""It is not enough to simply capture and store all these data using conventional means," Roy noted.
　 "Instead we need to keep all the information online so that we can do rapid exploration of patterns
　 hidden within the data.""

Deb Roy, Associate Professor of Media Arts and Sciences
　http://web.media.mit.edu/~dkroy/
　AT&T Career Development Professor
　Director, Cognitive Machines Group
　MIT Media Laboratory

　The Human Speechome Project (May 2006)
　　PRESS ARCHIVE: HUMAN SPEECHOME PROJECT
　　http://www.media.mit.edu/press/speechome/
　"The Human Speechome Project",
　　Deb Roy, et al., To appear in the Proceedings of the 28th Annual Cognitive Science Conference, July 2006.
　　http://www.media.mit.edu/press/speechome/speechome-cogsci.pdf
　　　300 Gigabytes per day:
　　　　132 hours of motion-compressed video per day (12 hours x 14 cameras)
　　　　182 hours of audio (13 hours x 14 microphones)
　Joint Sponsor Press Release, May 15, 2006
　　http://www.media.mit.edu/press/speechome/speechome-sponsor.pdf
　　　Bell Microproducts: http://www.bellmicro.com/
　　　Marvell: http://www.marvell.com/　　　　
　　　Seagate Technology: http://www.seagate.com/
　　　Zetera: http://www.zetera.com/
　　　　Computer News/メモ, 06/03/01, 2006-03-01
　　　　　"Storage-Over-IP (SoIP) Set To Transform Storage Industry", February 22, 2006
　　　　"Netgear launches dirt-cheap IP SAN", SearchStorage.com, 14 Sep 2005
　　　　　http://searchstorage.techtarget.com/originalContent/0,289142,sid5_gci1124555,00.html?track=NL-52&ad=551907
　　システム構成
　　　Seagate SATA drives: 3,000(以上)
　　　Bell Microproducts Hammer Z-Rack storage enclosures: 300
　　　　700 terabytes of data during each 12-hour overnight analytical run
　　　　150-drive stripes (aggregated virtual volumes)
　　　　　Zetera Z-SANの仮想化技術を採用
　　　　RAID 10 mirrors: raw video data, transform data and metadata files
　　　Marvell-based 10G/GbE switches: 100
　　　　Storage over Internetworking Protocol (SoIP) processing nodes and XGE connectivity mesh
　　　　Marvell Switching Products
　　　　　http://www.marvell.com/products/switching/index.jsp
　　　Blade processors: 約 400