Update PySpark to be less OOM-prone as well

Author: ash211

python/pyspark/rdd.py

@@ -1035,7 +1035,7 @@ def take(self, num):
                 # try all partitions next. Otherwise, interpolate the number
                 # of partitions we need to try, but overestimate it by 50%.
                 if len(items) == 0:
-                    numPartsToTry = totalParts - 1
+                    numPartsToTry = partsScanned * 2
                 else:
                     numPartsToTry = int(1.5 * num * partsScanned / len(items))