News for hackers. Stuff that matters.
Re:MapReduce and Spark by fintler on Thursday January 02, 2014 @10:16PM (#7003941)
Although spark is nice, I'm also looking forward to mpi/orted integration with hadoop...

"Performance: Launches ~1000x faster, runs ~10x faster"

"Launch scaling: Hadoop (~N), MR+ (~logN)"

"Wireup: Hadoop (~N2), MR+ (~logN)"

http://slurm.schedmd.com/slurm_ug_2012/MapRedSLURM.pdf

There are no comments on this comment yet.