diff options
author | Reynold Xin <rxin@databricks.com> | 2015-08-20 07:53:27 -0700 |
---|---|---|
committer | Yin Huai <yhuai@databricks.com> | 2015-08-20 07:53:27 -0700 |
commit | b4f4e91c395cb69ced61d9ff1492d1b814f96828 (patch) | |
tree | b2bb168c15a9105377eb8cf2c1e318d1d8204007 /python/pyspark/sql/types.py | |
parent | 43e0135421b2262cbb0e06aae53523f663b4f959 (diff) | |
download | spark-b4f4e91c395cb69ced61d9ff1492d1b814f96828.tar.gz spark-b4f4e91c395cb69ced61d9ff1492d1b814f96828.tar.bz2 spark-b4f4e91c395cb69ced61d9ff1492d1b814f96828.zip |
[SPARK-10100] [SQL] Eliminate hash table lookup if there is no grouping key in aggregation.
This improves performance by ~ 20 - 30% in one of my local test and should fix the performance regression from 1.4 to 1.5 on ss_max.
Author: Reynold Xin <rxin@databricks.com>
Closes #8332 from rxin/SPARK-10100.
Diffstat (limited to 'python/pyspark/sql/types.py')
0 files changed, 0 insertions, 0 deletions