[
https://issues.apache.org/jira/browse/HIVE-24991?focusedWorklogId=608548&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-608548
]
ASF GitHub Bot logged work on HIVE-24991:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 08/Jun/21 15:58
Start Date: 08/Jun/21 15:58
Worklog Time Spent: 10m
Work Description: kasakrisz commented on a change in pull request #2264:
URL: https://github.com/apache/hive/pull/2264#discussion_r647582032
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/io/orc/VectorizedOrcAcidRowBatchReader.java
##########
@@ -1940,39 +2091,38 @@ public boolean isEmpty() {
}
@Override
public void findDeletedRecords(ColumnVector[] cols, int size, BitSet
selectedBitSet) {
- if (rowIds == null || compressedOwids == null) {
+ if (rowIds == null || writeIds == null || writeIds.isEmpty()) {
return;
}
// Iterate through the batch and for each (owid, rowid) in the batch
// check if it is deleted or not.
long[] originalWriteIdVector =
- cols[OrcRecordUpdater.ORIGINAL_WRITEID].isRepeating ? null
- : ((LongColumnVector)
cols[OrcRecordUpdater.ORIGINAL_WRITEID]).vector;
+ cols[OrcRecordUpdater.ORIGINAL_WRITEID].isRepeating ? null
Review comment:
reverted
##########
File path:
ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestVectorizedOrcAcidRowBatchReader.java
##########
@@ -961,26 +966,41 @@ private void testDeleteEventOriginalFiltering2() throws
Exception {
@Test
public void testVectorizedOrcAcidRowBatchReader() throws Exception {
+ setupTestData();
+
+
testVectorizedOrcAcidRowBatchReader(ColumnizedDeleteEventRegistry.class.getName());
+
+ // To test the SortMergedDeleteEventRegistry, we need to explicitly set the
+ // HIVE_TRANSACTIONAL_NUM_EVENTS_IN_MEMORY constant to a smaller value.
+ int oldValue =
conf.getInt(HiveConf.ConfVars.HIVE_TRANSACTIONAL_NUM_EVENTS_IN_MEMORY.varname,
1000000);
+
conf.setInt(HiveConf.ConfVars.HIVE_TRANSACTIONAL_NUM_EVENTS_IN_MEMORY.varname,
1000);
+
testVectorizedOrcAcidRowBatchReader(SortMergedDeleteEventRegistry.class.getName());
+
+ // Restore the old value.
+
conf.setInt(HiveConf.ConfVars.HIVE_TRANSACTIONAL_NUM_EVENTS_IN_MEMORY.varname,
oldValue);
+ }
+
+ private void setupTestData() throws IOException {
conf.set("bucket_count", "1");
- conf.set(ValidTxnList.VALID_TXNS_KEY,
- new ValidReadTxnList(new long[0], new BitSet(), 1000,
Long.MAX_VALUE).writeToString());
+ conf.set(ValidTxnList.VALID_TXNS_KEY,
+ new ValidReadTxnList(new long[0], new BitSet(), 1000,
Long.MAX_VALUE).writeToString());
int bucket = 0;
AcidOutputFormat.Options options = new AcidOutputFormat.Options(conf)
- .filesystem(fs)
- .bucket(bucket)
- .writingBase(false)
- .minimumWriteId(1)
- .maximumWriteId(NUM_OWID)
- .inspector(inspector)
- .reporter(Reporter.NULL)
- .recordIdColumn(1)
- .finalDestination(root);
+ .filesystem(fs)
Review comment:
reverted
--
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: 608548)
Time Spent: 4h 10m (was: 4h)
> 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 10m
> 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)
