[
https://issues.apache.org/jira/browse/DRILL-6644?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16568919#comment-16568919
]
ASF GitHub Bot commented on DRILL-6644:
---------------------------------------
ilooner commented on a change in pull request #1409: DRILL-6644: Don't reserve
space for incoming probe batches unnecessarily during the build phase.
URL: https://github.com/apache/drill/pull/1409#discussion_r207689140
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/physical/impl/join/HashJoinMemoryCalculatorImpl.java
##########
@@ -391,7 +391,7 @@ private void calculateMemoryUsage()
// probe batch we sniffed.
// TODO when batch sizing project is complete we won't have to sniff
probe batches since
// they will have a well defined size.
- reservedMemory = incompletePartitionsBatchSizes + maxBuildBatchSize +
maxProbeBatchSize;
+ reservedMemory = incompletePartitionsBatchSizes + maxBuildBatchSize +
probeSizePredictor.getBatchSize();
Review comment:
@Ben-Zvi thought about this a bit more and there is a complication with
spilling. If we are doing the join on a spilled partition the HashJoin operator
will actually own the probe batch. So during the first cycle we don't want to
account for the probe batch because the upstream operator will own it, but
during the other spill cycles we do want to account for them because we will
own them.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
> In Some Cases The HashJoin Memory Calculator Over Reserves Memory For The
> Probe Side During The Build Phase
> -----------------------------------------------------------------------------------------------------------
>
> Key: DRILL-6644
> URL: https://issues.apache.org/jira/browse/DRILL-6644
> Project: Apache Drill
> Issue Type: Improvement
> Reporter: Timothy Farkas
> Assignee: Timothy Farkas
> Priority: Major
>
> There are two cases where the HashJoin Memory calculator over reserves memory:
> 1. It reserves a maximum incoming probe batch size during the build phase.
> This is not really necessary because we will not fetch probe data until the
> probe phase. We only have to account for the data received during
> OK_NEW_SCHEMA.
> 2. https://issues.apache.org/jira/browse/DRILL-6646
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
