spark

def getTotalSize(rdd: RDD[Row]): Long = {
  // This can be a parameter
  val NO_OF_SAMPLE_ROWS = 10l;
  val totalRows = rdd.count();
  var totalSize = 0l
  if (totalRows > NO_OF_SAMPLE_ROWS) {
    val sampleRDD = rdd.sample(true, NO_OF_SAMPLE_ROWS)
    val sampleRDDSize = getRDDSize(sampleRDD)
    totalSize = sampleRDDSize.*(totalRows)./(NO_OF_SAMPLE_ROWS)
  } else {
    // As the RDD is smaller than sample rows count, we can just calculate the total RDD size
    totalSize = getRDDSize(rdd)
  }

  totalSize
}

def getRDDSize(rdd: RDD[Row]) : Long = {
    var rddSize = 0l
    val rows = rdd.collect()
    for (i <- 0 until rows.length) {
       rddSize += SizeEstimator.estimate(rows.apply(i).toSeq.map { value => value.asInstanceOf[AnyRef] })
    }

    rddSize
}