Shreyansh1004 opened a new issue, #19035:
URL: https://github.com/apache/druid/issues/19035

   I am trying to ingest data in druid datasource using index_parallel but the 
ingestion is getting failed again and again in merge phase 
   
   Here is the task spec : 
   
   {
     "type": "index_parallel",
     "spec": {
       "dataSchema": {
         "dataSource": "X",
         "timestampSpec": {
           "column": "timestamp",
           "format": "auto"
         },
         "dimensionsSpec": {
           "dimensions": [
             "segment",
             "region",
             "deviceIdType",
             "scope"
           ]
         },
         "metricsSpec": [
           {
             "fieldName": "X",
             "type": "thetaSketch",
             "name": "X",
             "isInputThetaSketch": true,
             "size": 65536
           }
         ],
         "granularitySpec": {
           "type": "uniform",
           "segmentGranularity": "day",
           "queryGranularity": "day",
           "intervals": ["PLACEHOLDER"],
           "rollup": false
         }
       },
       "ioConfig": {
         "type": "index_parallel",
         "inputSource": {
           "type": "combining",
           "delegates": [
             {
               "type": "druid",
               "dataSource": "X",
               "interval": "PLACEHOLDER",
               "filter": {
                 "type": "not",
                 "field": {
                   "type": "in",
                   "dimension": "X",
                   "values": ["X"]
                 }
               }
             },
               }
             }
           ]
         },
         "inputFormat": {
           "type": "parquet",
           "binaryAsString": false
         },
         "appendToExisting": false
       },
       "tuningConfig": {
         "type": "index_parallel",
         "forceGuaranteedRollup": true,
         "maxRowsInMemory": 25000,        
         "maxBytesInMemory": 500000000,
         "partitionsSpec": {
           "type": "hashed",
           "targetRowsPerSegment": 6000
         },
         "maxNumConcurrentSubTasks": 10,
         "maxRetry": 3,
         "taskStatusCheckPeriodMs": 1000,
         "chatHandlerTimeout": "PT10S",
         "chatHandlerNumRetries": 5,
         "pushTimeout": 0,
         "ignoreInvalidRows": true,
         "buildV9Directly": true
       }
     }
   }
   
   I am using a single middle manager with r6gd.8xlarge instance type with 12 
worker slots, with 4GB heap for middle manager and 20GB ( 16GB heap + 4GB 
direct ) for peon task


-- 
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]

Reply via email to