Github user davies commented on the pull request:
https://github.com/apache/spark/pull/11870#issuecomment-200522669
@JoshRosen Had updated the benchmark result for BroadcastHashJoin in local
mode, which use the HashMap before this patch, it become 50% slower (same for
ShuffledHashJoin). The good part is that we are using less memory (also less
objects), and more GC friendly, also support OffHeap, That's the same reason we
use BytesToBytesMap for aggregate.
---
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]
