A simple way to clone 10,000 files to cluster

# Generate 10,000 files from one seed and put them into 100 subdirectories

[hdfs@cdh1 tmp]$ for((i=1;i<=100;i++));do mkdir -p 10000files/F$i; for((j=1;j<=100;j++));do echo $i-$j; cp 1000line.csv 10000files/F$i/$i-$j.csv;done;done;

# Move them to cluster.  One sub-directory at one time.

[hdfs@cdh1 tmp]$ for((i=1;i<=100;i++));do echo $i; hadoop fs -mkdir /JohnZ/10000files/F$i; hadoop fs -copyFromLocal 10000files/F$i/* /JohnZ/10000files/F$i/.;done;