[
https://issues.apache.org/jira/browse/HDDS-9711?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Saketa Chalamchala reassigned HDDS-9711:
----------------------------------------
Assignee: Hemant Kumar
> [snapshot] RuntimeException encountered when generating snapshotDiff report
> between 2 snapshots
> -----------------------------------------------------------------------------------------------
>
> Key: HDDS-9711
> URL: https://issues.apache.org/jira/browse/HDDS-9711
> Project: Apache Ozone
> Issue Type: Bug
> Components: Snapshot
> Reporter: Jyotirmoy Sinha
> Assignee: Hemant Kumar
> Priority: Major
> Labels: ozone-snapshot
>
> RuntimeException encountered when generating snapshotDiff report between 2
> snapshots
> OM Log error stacktrace -
> {code:java}
> 2023-11-16 22:54:06,804 INFO [IPC Server handler 32 on
> 9862]-org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager: Submitting
> snap diff report generation request for volume: voly6zr4, bucket:
> buckety6zr4, fromSnapshot: snap-wfiql and toSnapshot: snap-ohtc8
> 2023-11-16 22:54:06,804 INFO
> [snapshot-diff-job-thread-id-12]-org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager:
> Started snap diff report generation for volume: 'voly6zr4', bucket:
> 'buckety6zr4', fromSnapshot: 'snap-wfiql', toSnapshot: 'snap-ohtc8'
> 2023-11-16 22:54:06,805 INFO
> [snapshot-diff-job-thread-id-12]-org.apache.hadoop.ozone.om.snapshot.SnapshotCache:
> Loading snapshot. Table key: /voly6zr4/buckety6zr4/snap-wfiql
> 2023-11-16 22:54:06,805 INFO
> [snapshot-diff-job-thread-id-12]-org.apache.hadoop.ozone.om.snapshot.SnapshotCache:
> Loading snapshot. Table key: /voly6zr4/buckety6zr4/snap-ohtc8
> 2023-11-16 22:54:06,837 ERROR
> [snapshot-diff-job-thread-id-12]-org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager:
> Caught unchecked exception during diff report generation for volume:
> voly6zr4 bucket: buckety6zr4, fromSnapshot: snap-wfiql and toSnapshot:
> snap-ohtc8
> java.lang.RuntimeException: java.io.IOException:
> RocksDatabase[/var/lib/hadoop-ozone/om/data159041/db.snapshots/checkpointState/om.db-b5edff31-58ff-458d-b431-141634b48006]:
> Failed to get
> /-9223372036853507328/-9223372036853506816/-9223372036853506303/vectortab_txt
> from ColumnFamily-directoryTable; status : IOError; message : While pread
> offset 0 len 518:
> /var/lib/hadoop-ozone/om/data159041/db.snapshots/checkpointState/om.db-b5edff31-58ff-458d-b431-141634b48006/001614.sst:
> Bad file descriptor
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.lambda$7(SnapshotDiffManager.java:1170)
> at java.base/java.util.Iterator.forEachRemaining(Iterator.java:133)
> at
> java.base/java.util.Spliterators$IteratorSpliterator.forEachRemaining(Spliterators.java:1801)
> at
> java.base/java.util.stream.ReferencePipeline$Head.forEach(ReferencePipeline.java:658)
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.addToObjectIdMap(SnapshotDiffManager.java:1137)
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.getDeltaFilesAndDiffKeysToObjectIdToKeyMap(SnapshotDiffManager.java:1078)
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.lambda$4(SnapshotDiffManager.java:958)
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.generateSnapshotDiffReport(SnapshotDiffManager.java:1014)
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.lambda$2(SnapshotDiffManager.java:741)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:834)
> Caused by: java.io.IOException:
> RocksDatabase[/var/lib/hadoop-ozone/om/data159041/db.snapshots/checkpointState/om.db-b5edff31-58ff-458d-b431-141634b48006]:
> Failed to get
> /-9223372036853507328/-9223372036853506816/-9223372036853506303/vectortab_txt
> from ColumnFamily-directoryTable; status : IOError; message : While pread
> offset 0 len 518:
> /var/lib/hadoop-ozone/om/data159041/db.snapshots/checkpointState/om.db-b5edff31-58ff-458d-b431-141634b48006/001614.sst:
> Bad file descriptor
> at
> org.apache.hadoop.hdds.utils.HddsServerUtil.toIOException(HddsServerUtil.java:667)
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.toIOException(RocksDatabase.java:90)
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.get(RocksDatabase.java:750)
> at org.apache.hadoop.hdds.utils.db.RDBTable.get(RDBTable.java:134)
> at
> org.apache.hadoop.hdds.utils.db.TypedTable.lambda$getFromTable$0(TypedTable.java:313)
> at
> org.apache.hadoop.hdds.utils.db.CodecBuffer.putFromSource(CodecBuffer.java:422)
> at
> org.apache.hadoop.hdds.utils.db.TypedTable.getFromTable(TypedTable.java:312)
> at
> org.apache.hadoop.hdds.utils.db.TypedTable.getFromTable(TypedTable.java:344)
> at
> org.apache.hadoop.hdds.utils.db.TypedTable.getFromTable(TypedTable.java:318)
> at org.apache.hadoop.hdds.utils.db.TypedTable.get(TypedTable.java:228)
> at
> org.apache.hadoop.ozone.om.snapshot.SnapshotDiffManager.lambda$7(SnapshotDiffManager.java:1139)
> ... 11 more
> Caused by: org.rocksdb.RocksDBException: While pread offset 0 len 518:
> /var/lib/hadoop-ozone/om/data159041/db.snapshots/checkpointState/om.db-b5edff31-58ff-458d-b431-141634b48006/001614.sst:
> Bad file descriptor
> at org.rocksdb.RocksDB.getDirect(Native Method)
> at org.rocksdb.RocksDB.get(RocksDB.java:1251)
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.get(RocksDatabase.java:743)
> ... 19 more {code}
> {code:java}
> 2023-11-16 22:54:16,652 ERROR [Timer for 'OzoneManager' metrics
> system]-org.apache.hadoop.hdds.utils.RocksDBStoreMetrics: Failed to get
> property mem-table-flush-pending from rocksdb
> java.io.IOException: Rocks Database is closed
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.assertClose(RocksDatabase.java:444)
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.getProperty(RocksDatabase.java:807)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.getDBPropertyData(RocksDBStoreMetrics.java:214)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.getMetrics(RocksDBStoreMetrics.java:151)
> at
> org.apache.hadoop.metrics2.impl.MetricsSourceAdapter.getMetrics(MetricsSourceAdapter.java:200)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.snapshotMetrics(MetricsSystemImpl.java:419)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.sampleMetrics(MetricsSystemImpl.java:406)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.onTimerEvent(MetricsSystemImpl.java:381)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl$4.run(MetricsSystemImpl.java:368)
> at java.base/java.util.TimerThread.mainLoop(Timer.java:556)
> at java.base/java.util.TimerThread.run(Timer.java:506)
> 2023-11-16 22:54:16,653 ERROR [Timer for 'OzoneManager' metrics
> system]-org.apache.hadoop.hdds.utils.RocksDBStoreMetrics: Failed to compute
> sst file stat
> java.io.IOException: Rocks Database is closed
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.assertClose(RocksDatabase.java:444)
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.getLiveFilesMetaData(RocksDatabase.java:642)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.computeSstFileStat(RocksDBStoreMetrics.java:251)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.getDBPropertyData(RocksDBStoreMetrics.java:235)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.getMetrics(RocksDBStoreMetrics.java:151)
> at
> org.apache.hadoop.metrics2.impl.MetricsSourceAdapter.getMetrics(MetricsSourceAdapter.java:200)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.snapshotMetrics(MetricsSystemImpl.java:419)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.sampleMetrics(MetricsSystemImpl.java:406)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.onTimerEvent(MetricsSystemImpl.java:381)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl$4.run(MetricsSystemImpl.java:368)
> at java.base/java.util.TimerThread.mainLoop(Timer.java:556)
> at java.base/java.util.TimerThread.run(Timer.java:506)
> 2023-11-16 22:54:16,653 ERROR [Timer for 'OzoneManager' metrics
> system]-org.apache.hadoop.hdds.utils.RocksDBStoreMetrics: Failed to get
> latest sequence number
> java.io.IOException: Rocks Database is closed
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.assertClose(RocksDatabase.java:444)
> at
> org.apache.hadoop.hdds.utils.db.RocksDatabase.getLatestSequenceNumber(RocksDatabase.java:834)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.getLatestSequenceNumber(RocksDBStoreMetrics.java:302)
> at
> org.apache.hadoop.hdds.utils.RocksDBStoreMetrics.getMetrics(RocksDBStoreMetrics.java:152)
> at
> org.apache.hadoop.metrics2.impl.MetricsSourceAdapter.getMetrics(MetricsSourceAdapter.java:200)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.snapshotMetrics(MetricsSystemImpl.java:419)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.sampleMetrics(MetricsSystemImpl.java:406)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.onTimerEvent(MetricsSystemImpl.java:381)
> at
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl$4.run(MetricsSystemImpl.java:368)
> at java.base/java.util.TimerThread.mainLoop(Timer.java:556)
> at java.base/java.util.TimerThread.run(Timer.java:506) {code}
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]