vzayaz

val res = spark
  .range(1000L * 1000 * 1000)
  .filter(x => x % 2 == 0) // note that the condition changed
  .select(count(col("id"))) 
  .first()
  .getAs[Long](0)

vzayaz

val res = spark.range(1000L * 1000 * 1000)
    .rdd
    .filter(_ %2 == 0)
    .count()

vzayaz

public Object generate(Object[] references) {
  return new GeneratedIteratorForCodegenStage1(references);
}

/*wsc_codegenStageId*/
final class GeneratedIteratorForCodegenStage1 extends org.apache.spark.sql.execution.BufferedRowIterator {
  private Object[] references;
  private scala.collection.Iterator[] inputs;
  private boolean agg_initAgg_0;
  private boolean agg_bufIsNull_0;

vzayaz

def pseudo_rdd_count(rdd: RDD[T]): Long = {
  val iter = rdd.compute
  var result = 0
  while (iter.hasNext) result += 1
  result
}

vzayaz

abstract class RDD[T: ClassTag]
def compute(…): Iterator[T]

vzayaz

val res = spark.range(1000L * 1000 * 1000)
  .filter(col("id") % 2 === 0)
  .select(count(col("id")))
  .first().getAs[Long](0)

vzayaz

val res = spark.sparkContext
  .range(0L, 1000L * 1000 * 1000)
  .filter(_ % 2 == 0)
  .count()

vzayaz

var res: Long = 0L
var i: Long  = 0L
while (i < 1000L * 1000 * 1000) {
  if (i % 2 == 0) res += 1
  i += 1L
}