Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/13318#discussion_r65754375
--- Diff:
core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java ---
@@ -221,7 +221,8 @@ public BytesToBytesMap(
SparkEnv.get() != null ? SparkEnv.get().blockManager() : null,
SparkEnv.get() != null ? SparkEnv.get().serializerManager() : null,
initialCapacity,
- 0.70,
+ // In order to re-use the longArray for sorting, the load factor
cannot be larger than 0.5.
+ 0.5,
--- End diff --
This change also us to use radix sort when switching happens, so it's not
always regression of performance. It's hard to measure the impact for different
workloads, I'd like to prefer for robustness instead of small performance
improvements for some workload.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
