Ethan, you're not the only one, which is why I was asking about this! :-)
Matei, thanks for your response. your answer explains the performance jump
in my code, but shows I've missed something key in my understanding of
Spark!
I was not aware until just now that map output was saved to disk
Hi Diana,
Apart from these reasons, in a multi-stage job, Spark saves the map output
files from map stages to the filesystem, so it only needs to rerun the last
reduce stage. This is why you only saw one stage executing. These files are
saved for fault recovery but they speed up subsequent
Hey Matei,
Not sure i understand that. These are 2 separate jobs. So the second job
takes advantage of the fact that there is map output left somewhere on disk
from the first job, and re-uses that?
On Sat, May 3, 2014 at 8:29 PM, Matei Zaharia matei.zaha...@gmail.comwrote:
Hi Diana,
Apart
Yes, this happens as long as you use the same RDD. For example say you do the
following:
data1 = sc.textFile(…).map(…).reduceByKey(…)
data1.count()
data1.filter(…).count()
The first count() causes outputs of the map/reduce pair in there to be written
out to shuffle files. Next time you do a