Details
-
Improvement
-
Status: Resolved
-
Major
-
Resolution: Fixed
-
None
-
ghx-label-5
Description
While working on IMPALA-12138 it turned out that the default settings of batch_size=1024 and fetch_size=10240 are not ideal for the coordinator (RowMaterializationTimer). My guess for the cause is that HS2 results vectors are rounded up to power of 2 sizes leading to extra allocations and copying.
query: select * from tpch_parquet.lineitem
RowMaterializationTimer (before and after IMPALA-12138)
fetch_size=10240: 3.6s ->3.2s
fetch_size=8192: 2.8s->2.6s
Attachments
Issue Links
- relates to
-
IMPALA-9818 Add fetch size as option to impala shell
- Resolved
-
IMPALA-12138 Suboptimal vector allocation of HS2 results
- Resolved