I have to do copy of an S3 to HDFS of an cluster EMR. I'm trying to smaller the execution time of my job. Looking in the logs the map input of the job is 1_000_
google-patent-search
markup-extensions
blazor-client-side
tiles
naming-strategy
jscoq
admin-bro
trainingloss
readxml
django-custom-tags
function-attributes
oracle-service-bus
android-contacts
groupbox
groovy-console
xinput
reset-button
bisection
systems-programming
d
dllmain
geopackage
tags
distributive
virus
virtual-environment
internet-explorer-8
cross-device
specialized-annotation
web-manifest