deniskuzZ commented on code in PR #4091:
URL: https://github.com/apache/hive/pull/4091#discussion_r1161664755
##########
ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/handler/CompactionCleaner.java:
##########
@@ -259,49 +247,11 @@ private void cleanUsingAcidDir(CompactionInfo ci, String
location, long minOpenT
*/
// Creating 'reader' list since we are interested in the set of 'obsolete'
files
- ValidReaderWriteIdList validWriteIdList = getValidCleanerWriteIdList(ci,
validTxnList);
- LOG.debug("Cleaning based on writeIdList: {}", validWriteIdList);
-
- Path path = new Path(location);
- FileSystem fs = path.getFileSystem(conf);
-
- // Collect all the files/dirs
- Map<Path, AcidUtils.HdfsDirSnapshot> dirSnapshots =
AcidUtils.getHdfsDirSnapshotsForCleaner(fs, path);
- AcidDirectory dir = AcidUtils.getAcidState(fs, path, conf,
validWriteIdList, Ref.from(false), false,
- dirSnapshots);
+ ValidReaderWriteIdList validWriteIdList =
getValidCleanerWriteIdListForCompactionCleaner(ci, validTxnList);
Table table = metadataCache.computeIfAbsent(ci.getFullTableName(), () ->
resolveTable(ci.dbname, ci.tableName));
- boolean isDynPartAbort = CompactorUtil.isDynPartAbort(table, ci.partName);
-
- List<Path> obsoleteDirs = CompactorUtil.getObsoleteDirs(dir,
isDynPartAbort);
- if (isDynPartAbort || dir.hasUncompactedAborts()) {
- ci.setWriteIds(dir.hasUncompactedAborts(), dir.getAbortedWriteIds());
- }
-
- List<Path> deleted = fsRemover.clean(new
CleanupRequestBuilder().setLocation(location)
-
.setDbName(ci.dbname).setFullPartitionName(ci.getFullPartitionName())
- .setRunAs(ci.runAs).setObsoleteDirs(obsoleteDirs).setPurge(true)
- .build());
-
- if (!deleted.isEmpty()) {
- AcidMetricService.updateMetricsFromCleaner(ci.dbname, ci.tableName,
ci.partName, dir.getObsolete(), conf,
- txnHandler);
- }
-
- // Make sure there are no leftovers below the compacted watermark
- boolean success = false;
- 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, dirSnapshots);
+ LOG.debug("Cleaning based on writeIdList: {}", validWriteIdList);
- List<Path> remained = subtract(CompactorUtil.getObsoleteDirs(dir,
isDynPartAbort), deleted);
- if (!remained.isEmpty()) {
- LOG.warn("{} Remained {} obsolete directories from {}. {}",
- idWatermark(ci), remained.size(), location,
CompactorUtil.getDebugInfo(remained));
- } else {
- LOG.debug("{} All cleared below the watermark: {} from {}",
idWatermark(ci), ci.highestWriteId, location);
- success = true;
- }
+ boolean success = cleanAndVerifyObsoleteDirectories(ci, location,
validWriteIdList, table);
Review Comment:
1 line below no need to check for `isDynPartAbort `
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
