cis6930fa11_SciDB - Sci,* ¡¢ R1OT£ assembly by Morgan...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Sci,* ¡¢ R1OT£ assembly by Morgan Bauer Outline ● Use Case ● Raison¡d¢etre of SciDB ● Requirements of SciDB ● System Description £High Level¤ ● Features of SciDB ● RIOT Description ¥ Comparison Use +ase" LSST ● Large Synoptic Survey Telescope ● Not built yet¡ expected before end of decade ¢~£¤¥7¦ ● §¨£ gigapixel image every ¥© seconds ● §¤ terabytes a night ● £¤¤¡¤¤¤ pictures ¢¥¨£8 petabytes¦ a year ○ vast preponderance of data cannot be human analyzed ● Sensor Data ¢£ªdimensional¦ ○ Must be cooked to be useful ○ many methods of cooking ● Time series ● Celestial ¢Spherical¦ Coordinates Why' ● Science Workload ○ Standard ○ Data ■ Petabyte V ■ Highly Structured ■ Arrays¡ not tables ○ Different Requirements ■ Complex Analytics ■ Open Source ■ No Overwrite ■ Provenance¡ lineage ■ Uncertainty ¢ Error bars ■ Version Control Why not R,*MS' ● Explicitly do not cater to scientific workloads ○ No money¡ ¢A zero billion dollar industry¢ ● Wrong data model ○ don£t want a table¡ want arrays¡ ¤¥¡ ¦¥¡ n¥dimensional ● Wrong operators ○ need linear algebra¡ not joins ○ we£ve seen with MADlib¡ that LA in a DB is possible ■ not optimal ● Wrong capabilities ○ nested arrays¡ custom Data types¡ UDFs Requirements ● Open Source ● No Overwrite ● Version Control ● Provenance¡ lineage ● Uncertainty ¢ Error bars Open Source ● Bad experiece with Oracle at LHC ● Unique support requirements ○ multi¡decade support for large science projects ○ inability to recompile entire software stack at will ○ difficulties in maintaining closed¡source software with large collaborations encompassing tens to hundreds of institutes No Overwrite ¡ Versioning ● Update¡able Arrays ● Never throw data away¢ even when bad ○ Recalculate a new answer¢ save the old for analysis ● Provenance £ Lineage purposes...
View Full Document

This note was uploaded on 11/09/2011 for the course CIS 6930 taught by Professor Staff during the Fall '08 term at University of Florida.

Page1 / 31

cis6930fa11_SciDB - Sci,* ¡¢ R1OT£ assembly by Morgan...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online