[
https://issues.apache.org/jira/browse/HIVE-25977?focusedWorklogId=746490&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-746490
]
ASF GitHub Bot logged work on HIVE-25977:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 23/Mar/22 11:15
Start Date: 23/Mar/22 11:15
Worklog Time Spent: 10m
Work Description: klcopp commented on a change in pull request #3102:
URL: https://github.com/apache/hive/pull/3102#discussion_r833132738
##########
File path: ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/Cleaner.java
##########
@@ -444,57 +444,23 @@ private boolean removeFiles(String location,
ValidWriteIdList writeIdList, Compa
// Including obsolete directories for partitioned tables can result in
data loss.
obsoleteDirs = dir.getAbortedDirectories();
}
-
- if (obsoleteDirs.isEmpty()
- && !hasDataBelowWatermark(dir, fs, path, ci.highestWriteId,
writeIdList.getHighWatermark())) {
- LOG.info(idWatermark(ci) + " nothing to remove below watermark " +
ci.highestWriteId + ", ");
- return true;
- }
StringBuilder extraDebugInfo = new
StringBuilder("[").append(obsoleteDirs.stream()
.map(Path::getName).collect(Collectors.joining(",")));
- boolean success = remove(location, ci, obsoleteDirs, true, fs,
extraDebugInfo);
+ remove(location, ci, obsoleteDirs, true, fs, extraDebugInfo);
if (dir.getObsolete().size() > 0) {
AcidMetricService.updateMetricsFromCleaner(ci.dbname, ci.tableName,
ci.partName, dir.getObsolete(), conf,
txnHandler);
}
- return success;
- }
-
- private boolean hasDataBelowWatermark(AcidDirectory acidDir, FileSystem fs,
Path path, long highWatermark,
- long minOpenTxn)
- throws IOException {
- Set<Path> acidPaths = new HashSet<>();
- for (ParsedDelta delta : acidDir.getCurrentDirectories()) {
- acidPaths.add(delta.getPath());
- }
- if (acidDir.getBaseDirectory() != null) {
- acidPaths.add(acidDir.getBaseDirectory());
- }
- FileStatus[] children = fs.listStatus(path, p -> {
- return !acidPaths.contains(p);
- });
- for (FileStatus child : children) {
- if (isFileBelowWatermark(child, highWatermark, minOpenTxn)) {
- return true;
- }
- }
- return false;
- }
-
- private boolean isFileBelowWatermark(FileStatus child, long highWatermark,
long minOpenTxn) {
- Path p = child.getPath();
- String fn = p.getName();
- if (!child.isDirectory()) {
+ // Make sure there are no leftovers below the compacted highestWriteId
+ conf.set(ValidTxnList.VALID_TXNS_KEY, new ValidReadTxnList().toString());
+ dir = AcidUtils.getAcidState(fs, path, conf,
+ new ValidReaderWriteIdList(ci.getFullTableName(), new long[0], new
BitSet(), ci.highestWriteId, Long.MAX_VALUE),
+ Ref.from(false), false, hdfsDirSnapshots);
+
+ if (dir.getObsolete().isEmpty()) {
Review comment:
Might want to check for aborted directories too
##########
File path: ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/Cleaner.java
##########
@@ -444,57 +444,23 @@ private boolean removeFiles(String location,
ValidWriteIdList writeIdList, Compa
// Including obsolete directories for partitioned tables can result in
data loss.
obsoleteDirs = dir.getAbortedDirectories();
}
-
- if (obsoleteDirs.isEmpty()
- && !hasDataBelowWatermark(dir, fs, path, ci.highestWriteId,
writeIdList.getHighWatermark())) {
- LOG.info(idWatermark(ci) + " nothing to remove below watermark " +
ci.highestWriteId + ", ");
- return true;
- }
StringBuilder extraDebugInfo = new
StringBuilder("[").append(obsoleteDirs.stream()
.map(Path::getName).collect(Collectors.joining(",")));
- boolean success = remove(location, ci, obsoleteDirs, true, fs,
extraDebugInfo);
+ remove(location, ci, obsoleteDirs, true, fs, extraDebugInfo);
if (dir.getObsolete().size() > 0) {
AcidMetricService.updateMetricsFromCleaner(ci.dbname, ci.tableName,
ci.partName, dir.getObsolete(), conf,
txnHandler);
}
- return success;
- }
-
- private boolean hasDataBelowWatermark(AcidDirectory acidDir, FileSystem fs,
Path path, long highWatermark,
- long minOpenTxn)
- throws IOException {
- Set<Path> acidPaths = new HashSet<>();
- for (ParsedDelta delta : acidDir.getCurrentDirectories()) {
- acidPaths.add(delta.getPath());
- }
- if (acidDir.getBaseDirectory() != null) {
- acidPaths.add(acidDir.getBaseDirectory());
- }
- FileStatus[] children = fs.listStatus(path, p -> {
- return !acidPaths.contains(p);
- });
- for (FileStatus child : children) {
- if (isFileBelowWatermark(child, highWatermark, minOpenTxn)) {
- return true;
- }
- }
- return false;
- }
-
- private boolean isFileBelowWatermark(FileStatus child, long highWatermark,
long minOpenTxn) {
- Path p = child.getPath();
- String fn = p.getName();
- if (!child.isDirectory()) {
+ // Make sure there are no leftovers below the compacted highestWriteId
+ conf.set(ValidTxnList.VALID_TXNS_KEY, new ValidReadTxnList().toString());
+ dir = AcidUtils.getAcidState(fs, path, conf,
+ new ValidReaderWriteIdList(ci.getFullTableName(), new long[0], new
BitSet(), ci.highestWriteId, Long.MAX_VALUE),
+ Ref.from(false), false, hdfsDirSnapshots);
+
+ if (dir.getObsolete().isEmpty()) {
+ LOG.info(idWatermark(ci) + " All cleared below the watermark: " +
ci.highestWriteId + " from " + location);
Review comment:
It might be nice to have an informative log line about uncleared files
(highest write id, mintxnid, CompactionInfo, number of files, maybe even file
names).
In that case, maybe the "All cleared below the watermark" message could be
debug-level, since we can insinuate there's nothing else to clean?
--
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.
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 746490)
Time Spent: 2h 40m (was: 2.5h)
> Enhance Compaction Cleaner to skip when there is nothing to do #2
> -----------------------------------------------------------------
>
> Key: HIVE-25977
> URL: https://issues.apache.org/jira/browse/HIVE-25977
> Project: Hive
> Issue Type: Bug
> Reporter: Zoltan Haindrich
> Assignee: Zoltan Haindrich
> Priority: Major
> Labels: pull-request-available
> Time Spent: 2h 40m
> Remaining Estimate: 0h
>
> initially this was just an addendum to the original patch ; but got delayed
> and altered - so it should have its own ticket
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
