hank williams wrote:
I am developing an application that is currently based on mysql. I
believe
it will require significant scaling and so I am exploring hadoop.
I know nothing about map-reduce and am trying to figure out how it
conceptually relates to simple things like CRUD. I guess I am just
looking
for a document or some simple explanation of how you use the map-reduce
metaphor to do basic index, search, sort, insert type things.
Any info and pointers greatly appreciated.
Hank
The best way to learn what map reduce is and what is not, is to read the
original paper by google :
http://labs.google.com/papers/mapreduce.html
then you may want to red :
http://www.cs.virginia.edu/~pact2006/program/mapreduce-pact06-keynote.pdf
and yet a paper by microsoft employee:
http://www.cs.vu.nl/~ralf/MapReduce/paper.pdf
and finally
Hung-Chih Yang, Ali Dasdan, Ruey-Lung Hsiao, D. Stott Parker (2007).
"Map-Reduce-Merge: Simplified Relational Data Processing on Large
Clusters". To appear in Proc. of SIGMOD'07. (This paper shows how to
extend MapReduce for relational data processing.)
