diff options
| -rw-r--r-- | core/src/main/scala/org/apache/spark/rdd/RDD.scala | 7 | ||||
| -rw-r--r-- | python/pyspark/rdd.py | 8 |
2 files changed, 7 insertions, 8 deletions
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index af9e31ba7b..1cf55e86f6 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -1064,11 +1064,10 @@ abstract class RDD[T: ClassTag]( // greater than totalParts because we actually cap it at totalParts in runJob. var numPartsToTry = 1 if (partsScanned > 0) { - // If we didn't find any rows after the first iteration, just try all partitions next. - // Otherwise, interpolate the number of partitions we need to try, but overestimate it - // by 50%. + // If we didn't find any rows after the previous iteration, quadruple and retry. Otherwise, + // interpolate the number of partitions we need to try, but overestimate it by 50%. if (buf.size == 0) { - numPartsToTry = totalParts - 1 + numPartsToTry = partsScanned * 4 } else { numPartsToTry = (1.5 * num * partsScanned / buf.size).toInt } diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index dff6fc26fc..04f13523b4 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1089,11 +1089,11 @@ class RDD(object): # we actually cap it at totalParts in runJob. numPartsToTry = 1 if partsScanned > 0: - # If we didn't find any rows after the first iteration, just - # try all partitions next. Otherwise, interpolate the number - # of partitions we need to try, but overestimate it by 50%. + # If we didn't find any rows after the previous iteration, + # quadruple and retry. Otherwise, interpolate the number of + # partitions we need to try, but overestimate it by 50%. if len(items) == 0: - numPartsToTry = totalParts - 1 + numPartsToTry = partsScanned * 4 else: numPartsToTry = int(1.5 * num * partsScanned / len(items)) |