Eywek opened a new issue #6717:
URL: https://github.com/apache/incubator-pinot/issues/6717


   I'm using the 0.7.0-695ca390a8080409b3b76f250f2315b81b86b362.
   
   I have the following table schema:
   ```json
   {
     "schemaName": "schema_605b02ec0eb00003003bfc41",
     "dimensionFieldSpecs": [
       {
         "name": "key",
         "dataType": "STRING"
       },
       {
         "name": "name",
         "dataType": "STRING"
       },
       {
         "name": "url",
         "dataType": "STRING"
       },
       {
         "name": "tmpId",
         "dataType": "STRING"
       },
       {
         "name": "labels",
         "dataType": "STRING",
         "singleValueField": false
       },
       {
         "name": "ids",
         "dataType": "STRING",
         "singleValueField": false
       },
       {
         "name": "transId",
         "dataType": "STRING"
       },
       {
         "name": "clientId",
         "dataType": "STRING"
       },
       {
         "name": "blockId",
         "dataType": "STRING"
       },
       {
         "name": "intelliId",
         "dataType": "STRING"
       },
       {
         "name": "version",
         "dataType": "STRING"
       },
       {
         "name": "message",
         "dataType": "STRING"
       },
       {
         "name": "contentId",
         "dataType": "STRING"
       },
       {
         "name": "branchId",
         "dataType": "STRING"
       },
       {
         "name": "userId",
         "dataType": "STRING"
       },
       {
         "name": "eventId",
         "dataType": "STRING"
       },
       {
         "name": "v",
         "dataType": "FLOAT",
         "defaultNullValue": 0
       },
       {
         "name": "ua",
         "dataType": "STRING"
       },
       {
         "name": "labels_keys",
         "dataType": "STRING",
         "singleValueField": false
       },
       {
         "name": "agent_family",
         "dataType": "STRING"
       },
       {
         "name": "agent_major",
         "dataType": "STRING"
       },
       {
         "name": "agent_minor",
         "dataType": "STRING"
       },
       {
         "name": "agent_patch",
         "dataType": "STRING"
       },
       {
         "name": "agent_device_family",
         "dataType": "STRING"
       },
       {
         "name": "agent_device_major",
         "dataType": "STRING"
       },
       {
         "name": "agent_device_minor",
         "dataType": "STRING"
       },
       {
         "name": "agent_device_patch",
         "dataType": "STRING"
       },
       {
         "name": "agent_os_family",
         "dataType": "STRING"
       },
       {
         "name": "agent_os_major",
         "dataType": "STRING"
       },
       {
         "name": "agent_os_minor",
         "dataType": "STRING"
       },
       {
         "name": "agent_os_patch",
         "dataType": "STRING"
       }
     ],
     "metricFieldSpecs": [
       {
         "name": "value",
         "dataType": "FLOAT"
       }
     ],
     "dateTimeFieldSpecs": [
       {
         "name": "timestamp",
         "dataType": "LONG",
         "format": "1:MILLISECONDS:EPOCH",
         "granularity": "1:HOURS"
       }
     ]
   }
   ```
   On the following realtime table:
   ```json
   {
     "REALTIME": {
       "tableName": "datasource_605b02ec0eb00003003bfc41_REALTIME",
       "tableType": "REALTIME",
       "segmentsConfig": {
         "segmentPushFrequency": "HOURLY",
         "segmentPushType": "APPEND",
         "replicasPerPartition": "1",
         "timeColumnName": "timestamp",
         "timeType": "MILLISECONDS",
         "replication": "1",
         "schemaName": "schema_605b02ec0eb00003003bfc41"
       },
       "tenants": {
         "broker": "DefaultTenant",
         "server": "DefaultTenant"
       },
       "tableIndexConfig": {
         "sortedColumn": [
           "value",
           "timestamp"
         ],
         "invertedIndexColumns": [
           "name",
           "tmpId",
           "labels",
           "clientId",
           "blockId",
           "labels_keys"
         ],
         "autoGeneratedInvertedIndex": false,
         "createInvertedIndexDuringSegmentGeneration": false,
         "loadMode": "mmap",
         "streamConfigs": {
           "streamType": "kafka",
           "stream.kafka.consumer.type": "lowlevel",
           "stream.kafka.topic.name": 
"datasources-ingester-605b02ec0eb00003003bfc41",
           "stream.kafka.decoder.class.name": 
"org.apache.pinot.plugin.stream.kafka.KafkaJSONMessageDecoder",
           "stream.kafka.consumer.factory.class.name": 
"org.apache.pinot.plugin.stream.kafka20.KafkaConsumerFactory",
           "stream.kafka.broker.list": "pulsar.internal.reelevant.io:9092",
           "stream.kafka.consumer.prop.auto.offset.reset": "smallest",
           "realtime.segment.flush.threshold.time": "1d",
           "realtime.segment.flush.threshold.rows": "390000"
         },
         "enableDefaultStarTree": false,
         "enableDynamicStarTreeCreation": false,
         "aggregateMetrics": false,
         "nullHandlingEnabled": true
       },
       "metadata": {},
       "quota": {},
       "task": {
         "taskTypeConfigsMap": {
           "RealtimeToOfflineSegmentsTask": {
             "bucketTimePeriod": "1d",
             "bufferTimePeriod": "1d",
             "collectorType": "concat",
             "maxNumRecordsPerSegment": "390000"
           }
         }
       },
       "routing": {},
       "instanceAssignmentConfigMap": {
         "CONSUMING": {
           "tagPoolConfig": {
             "tag": "DefaultTenant_REALTIME",
             "poolBased": false,
             "numPools": 0
           },
           "replicaGroupPartitionConfig": {
             "replicaGroupBased": false,
             "numInstances": 1,
             "numReplicaGroups": 0,
             "numInstancesPerReplicaGroup": 0,
             "numPartitions": 0,
             "numInstancesPerPartition": 0
           }
         },
         "COMPLETED": {
           "tagPoolConfig": {
             "tag": "DefaultTenant_REALTIME",
             "poolBased": false,
             "numPools": 0
           },
           "replicaGroupPartitionConfig": {
             "replicaGroupBased": false,
             "numInstances": 2,
             "numReplicaGroups": 0,
             "numInstancesPerReplicaGroup": 0,
             "numPartitions": 0,
             "numInstancesPerPartition": 0
           }
         }
       },
       "isDimTable": false
     }
   }
   ```
   
   But all of my segments (except for the consuming one) are offline with 
following metadata:
   ```json
   {
     "segment.realtime.endOffset": "9223372036854775807",
     "segment.start.time": "-1",
     "segment.time.unit": null,
     "segment.flush.threshold.size": "390000",
     "segment.realtime.startOffset": "11329367812603904",
     "segment.end.time": "-1",
     "segment.total.docs": "-1",
     "segment.table.name": "datasource_605b02ec0eb00003003bfc41",
     "segment.realtime.numReplicas": "1",
     "segment.creation.time": "1616612105480",
     "segment.realtime.download.url": null,
     "segment.name": 
"datasource_605b02ec0eb00003003bfc41__0__4__20210324T1855Z",
     "segment.index.version": null,
     "segment.flush.threshold.time": null,
     "segment.type": "REALTIME",
     "segment.crc": "-1",
     "segment.realtime.status": "IN_PROGRESS"
   }
   ```
   
   On the logs I can see:
   ```
   2021/03/24 19:50:13.417 INFO [PinotLLCRealtimeSegmentManager] 
[grizzly-http-server-3] Marking CONSUMING segment: 
datasource_605b02ec0eb00003003bfc41__0__4__20210324T1855Z OFFLINE on instance: 
Server_10.1.1.13_8098
   ```
   ```
   2021/03/24 19:50:13.416 INFO [LLCSegmentCompletionHandlers] 
[grizzly-http-server-3] Processing segmentStoppedConsuming:Offset: 
11575658581037057,Segment name: 
datasource_605b02ec0eb00003003bfc41__0__4__20210324T1855Z,Instance Id: 
Server_10.1.1.13_8098,Reason: java.lang.NullPointerException,NumRows: 
-1,BuildTimeMillis: -1,WaitTimeMillis: -1,ExtraTimeSec: -1,SegmentLocation: 
null,MemoryUsedBytes: -1,SegmentSizeBytes: -1,StreamPartitionMsgOffset: 
11575658581037057
   ```
   ```
   Mar 25 08:50:30 pinot-hosts-3 bash[11610]: 2021/03/25 08:50:30.922 ERROR 
[LLRealtimeSegmentDataManager_datasource_605b02ec0eb00003003bfc41__0__17__20210325T0755Z]
 [datasource_605b02ec0eb00003003bfc41__0__17__20210325T0755Z] Exception while 
in work
   Mar 25 08:50:30 pinot-hosts-3 bash[11610]: java.lang.NullPointerException: 
null
   Mar 25 08:50:30 pinot-hosts-3 bash[11610]:         at 
org.apache.pinot.core.data.manager.realtime.SegmentBuildTimeLeaseExtender.addSegment(SegmentBuildTimeLeaseExtender.java:100)
 
~[pinot-all-0.7.0-jar-with-dependencies.jar:0.7.0-695ca390a8080409b3b76f250f2315b81b86b362]
   Mar 25 08:50:30 pinot-hosts-3 bash[11610]:         at 
org.apache.pinot.core.data.manager.realtime.LLRealtimeSegmentDataManager.buildSegmentForCommit(LLRealtimeSegmentDataManager.java:698)
 
~[pinot-all-0.7.0-jar-with-dependencies.jar:0.7.0-695ca390a8080409b3b76f250f2315b81b86b362]
   Mar 25 08:50:30 pinot-hosts-3 bash[11610]:         at 
org.apache.pinot.core.data.manager.realtime.LLRealtimeSegmentDataManager$PartitionConsumer.run(LLRealtimeSegmentDataManager.java:610)
 
[pinot-all-0.7.0-jar-with-dependencies.jar:0.7.0-695ca390a8080409b3b76f250f2315b81b86b362]
   Mar 25 08:50:30 pinot-hosts-3 bash[11610]:         at 
java.lang.Thread.run(Thread.java:748) [?:1.8.0_275]
   ```
   
   Do you have any idea why this happen? I don't really see why a 
NullPointerException is throwed.
   
   Thank you


-- 
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:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to