[
https://issues.apache.org/jira/browse/HIVE-24991?focusedWorklogId=608551&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-608551
]
ASF GitHub Bot logged work on HIVE-24991:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 08/Jun/21 15:59
Start Date: 08/Jun/21 15:59
Worklog Time Spent: 10m
Work Description: kasakrisz commented on a change in pull request #2264:
URL: https://github.com/apache/hive/pull/2264#discussion_r647582327
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/io/orc/VectorizedOrcAcidRowBatchReader.java
##########
@@ -281,16 +285,23 @@ private VectorizedOrcAcidRowBatchReader(JobConf conf,
OrcSplit orcSplit, Reporte
deleteEventReaderOptions.range(0, Long.MAX_VALUE);
deleteEventReaderOptions.searchArgument(null, null);
keyInterval = findMinMaxKeys(orcSplit, conf, deleteEventReaderOptions);
+ fetchDeletedRows = conf.getBoolean(Constants.ACID_FETCH_DELETED_ROWS,
false);
DeleteEventRegistry der;
try {
// See if we can load all the relevant delete events from all the
// delete deltas in memory...
+ ColumnizedDeleteEventRegistry.OriginalWriteIdLoader writeIdLoader;
+ if (fetchDeletedRows) {
+ writeIdLoader = new ColumnizedDeleteEventRegistry.BothWriteIdLoader();
Review comment:
done
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/io/orc/VectorizedOrcAcidRowBatchReader.java
##########
@@ -303,6 +314,12 @@ private VectorizedOrcAcidRowBatchReader(JobConf conf,
OrcSplit orcSplit, Reporte
VectorizedRowBatch.DEFAULT_SIZE, null, null, null);
}
rowIdProjected = areRowIdsProjected(rbCtx);
+ rowIsDeletedProjected = isVirtualColumnProjected(rbCtx,
VirtualColumn.ROWISDELETED);
Review comment:
done
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/io/orc/VectorizedOrcAcidRowBatchReader.java
##########
@@ -303,6 +314,12 @@ private VectorizedOrcAcidRowBatchReader(JobConf conf,
OrcSplit orcSplit, Reporte
VectorizedRowBatch.DEFAULT_SIZE, null, null, null);
}
rowIdProjected = areRowIdsProjected(rbCtx);
+ rowIsDeletedProjected = isVirtualColumnProjected(rbCtx,
VirtualColumn.ROWISDELETED);
+ if (rowIsDeletedProjected) {
+ rowIsDeletedVector = new RowIsDeletedColumnVector();
Review comment:
done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 608551)
Time Spent: 4h 20m (was: 4h 10m)
> Enable fetching deleted rows in vectorized mode
> -----------------------------------------------
>
> Key: HIVE-24991
> URL: https://issues.apache.org/jira/browse/HIVE-24991
> Project: Hive
> Issue Type: Improvement
> Components: Vectorization
> Reporter: Krisztian Kasa
> Priority: Major
> Labels: pull-request-available
> Fix For: 4.0.0
>
> Time Spent: 4h 20m
> Remaining Estimate: 0h
>
> HIVE-24855 enables loading deleted rows from ORC tables when table property
> *acid.fetch.deleted.rows* is true.
> The goal of this jira is to enable this feature in vectorized orc batch
> reader.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
