spark-instrumented-optimizer/core/src/main/scala
Matei Zaharia dc28a3ac0a Modified shuffle to limit the maximum outstanding data size in bytes,
instead of the maximum number of outstanding fetches. This should make
it faster when there are many small map output files, as well as more
robust to overallocating memory on large map outputs.
2012-10-06 20:07:10 -07:00
..
spark Modified shuffle to limit the maximum outstanding data size in bytes, 2012-10-06 20:07:10 -07:00