// genned ad DS of some 20M short rows
df0.count
val ds1 = df0.repartition(765)
ds1.count
val ds2 = df0.repartition(765)
ds2.count
sqlContext.setConf("spark.sql.shuffle.partitions", "765")
// The above not included on 1st run, the above included on 2nd run.
ds1.rdd.partitions.size