nsivabalan commented on code in PR #8837: URL: https://github.com/apache/hudi/pull/8837#discussion_r1254985856
########## hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java: ########## @@ -653,37 +608,57 @@ private static void processRestoreMetadata(HoodieActiveTimeline metadataTableTim */ public static Map<MetadataPartitionType, HoodieData<HoodieRecord>> convertMetadataToRecords( HoodieEngineContext engineContext, HoodieActiveTimeline metadataTableTimeline, - HoodieRollbackMetadata rollbackMetadata, MetadataRecordsGenerationParams recordsGenerationParams, - String instantTime, Option<String> lastSyncTs, boolean wasSynced) { + HoodieTableMetaClient dataTableMetaClient, + HoodieRollbackMetadata rollbackMetadata, String instantTime) { final Map<MetadataPartitionType, HoodieData<HoodieRecord>> partitionToRecordsMap = new HashMap<>(); - Map<String, List<String>> partitionToDeletedFiles = new HashMap<>(); - Map<String, Map<String, Long>> partitionToAppendedFiles = new HashMap<>(); - List<HoodieRecord> filesPartitionRecords = - convertMetadataToRollbackRecords(metadataTableTimeline, rollbackMetadata, partitionToDeletedFiles, partitionToAppendedFiles, instantTime, lastSyncTs, wasSynced); + List<HoodieRecord> filesPartitionRecords = convertMetadataToRollbackRecords(rollbackMetadata, instantTime); + + List<HoodieRecord> reAddedRecords = getHoodieRecordsForLogFilesFromRollbackPlan(dataTableMetaClient, instantTime); + filesPartitionRecords.addAll(reAddedRecords); final HoodieData<HoodieRecord> rollbackRecordsRDD = engineContext.parallelize(filesPartitionRecords, 1); + partitionToRecordsMap.put(MetadataPartitionType.FILES, rollbackRecordsRDD); return partitionToRecordsMap; } + private static List<HoodieRecord> getHoodieRecordsForLogFilesFromRollbackPlan(HoodieTableMetaClient dataTableMetaClient, String instantTime) { + /*List<HoodieInstant> instants = dataTableMetaClient.reloadActiveTimeline().filterRequestedRollbackTimeline() + .filter(instant -> instant.getTimestamp().equals(instantTime) && instant.isRequested()).getInstants();*/ + + HoodieInstant rollbackInstant = new HoodieInstant(HoodieInstant.State.REQUESTED, HoodieTimeline.ROLLBACK_ACTION, instantTime); + + // HoodieInstant rollbackInstant = instants.get(0); + HoodieInstant requested = HoodieTimeline.getRollbackRequestedInstant(rollbackInstant); + try { + HoodieRollbackPlan rollbackPlan = TimelineMetadataUtils.deserializeAvroMetadata( + dataTableMetaClient.getActiveTimeline().readRollbackInfoAsBytes(requested).get(), HoodieRollbackPlan.class); + + Map<String, Map<String, Long>> partitionToLogFilesMap = new HashMap<>(); + + rollbackPlan.getRollbackRequests().forEach(rollbackRequest -> { + partitionToLogFilesMap.computeIfAbsent(rollbackRequest.getPartitionPath(), s -> new HashMap<>()); + // fetch only log files that are expected to be RB'd in DT as part of this rollback. these log files will not be deleted, but rendered + // invalid once rollback is complete. + partitionToLogFilesMap.get(rollbackRequest.getPartitionPath()).putAll(rollbackRequest.getLogBlocksToBeDeleted()); + }); Review Comment: it refers to full log file name. Sample rollback.requested ``` avrocat /tmp/hudi_trips_mor/.hoodie/20230705160035431.rollback.requested {"instantToRollback": {"HoodieInstantInfo": {"commitTime": "20230705160008665", "action": "deltacommit"}}, "RollbackRequests": {"array": [{"partitionPath": "americas/brazil/sao_paulo", "fileId": {"string": "0c717479-0609-4dd5-8ea4-f2edcf17986c-0"}, "latestBaseInstant": {"string": "20230705155904980"}, "filesToBeDeleted": [], "logBlocksToBeDeleted": {"map": {"file:/tmp/hudi_trips_mor/americas/brazil/sao_paulo/.0c717479-0609-4dd5-8ea4-f2edcf17986c-0_20230705155904980.log.2_0-81-113": -1}}}, {"partitionPath": "asia/india/chennai", "fileId": {"string": "27df1310-75f0-4353-9834-b0736fd3f6f3-0"}, "latestBaseInstant": {"string": "20230705155904980"}, "filesToBeDeleted": [], "logBlocksToBeDeleted": {"map": {"file:/tmp/hudi_trips_mor/asia/india/chennai/.27df1310-75f0-4353-9834-b0736fd3f6f3-0_20230705155904980.log.2_2-81-115": -1}}}, {"partitionPath": "americas/united_states/san_francisco", "fileId": {"string": "ff8f1c4b-c2e8-4f7d-b7ad-7ecb385a5f1d-0"}, "latestBaseInstant": {"string": "2023 0705155904980"}, "filesToBeDeleted": [], "logBlocksToBeDeleted": {"map": {"file:/tmp/hudi_trips_mor/americas/united_states/san_francisco/.ff8f1c4b-c2e8-4f7d-b7ad-7ecb385a5f1d-0_20230705155904980.log.2_1-81-114": -1}}}]}, "version": {"int": 1}} ``` -- 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: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org