wangyum commented on PR #9278:
URL: 
https://github.com/apache/incubator-gluten/pull/9278#issuecomment-2904607798

   It seems I can reproduce this issue:
   ```sql
   create table t_decimal_tt11 as
   SELECT Cast(id AS DECIMAL(18, 0)) id
   FROM   Range(10000000);
   
   create table t_decimal_tt12 as
   SELECT Cast(id AS DECIMAL(18, 0)) id
   FROM   Range(2103627078L);
   insert into t_decimal_tt12 values(-998), (-999), (-1), (-10), (-9999), 
(-1003), (-2), (-1005), (-1006), (-1007), (-1008), (-1009);
   
   SELECT Count(*)
   FROM  t_decimal_tt11 t_decimal_tt1
   LEFT JOIN t_decimal_tt12 t_decimal_tt2
         ON t_decimal_tt1.id = t_decimal_tt2.id;
   ```
   
   
   Key | Value
   -- | --
   spark.driver.maxResultSize | 50g
   spark.driver.memory | 170g
   spark.executor.cores | 18
   spark.executor.maxNumFailures | 2147483647
   spark.executor.memory | 45g
   spark.executor.memoryOverhead | 14336
   spark.gluten.enabled | true
   spark.gluten.memory.conservative.task.offHeap.size.in.bytes | 1640438897
   spark.gluten.memory.offHeap.size.in.bytes | 5.9056E+10
   spark.gluten.memory.task.offHeap.size.in.bytes | 3280877795
   spark.gluten.memoryOverhead.size.in.bytes | 1.5032E+10
   spark.gluten.numTaskSlotsPerExecutor | 18
   spark.gluten.sql.columnar.backend.velox.IOThreads | 0
   spark.memory.fraction | 0.75
   spark.memory.offHeap.enabled | true
   spark.memory.offHeap.size | 55g
   spark.plugins | org.apache.gluten.GlutenPlugin
   spark.shuffle.manager | org.apache.spark.shuffle.sort.ColumnarShuffleManager
   spark.shuffle.service.enabled | true
   spark.shuffle.service.port | 7338
   spark.shuffle.service.removeShuffle | true
   spark.shuffle.spill.numElementsForceSpillThreshold | 10000000
   spark.shuffle.useOldFetchProtocol | false
   spark.speculation | true
   spark.speculation.interval | 5000
   spark.speculation.minTaskRuntime | 5000
   spark.speculation.multiplier | 2
   spark.speculation.quantile | 0.95
   spark.sql.adaptive.coalescePartitions.initialPartitionNum | 10000
   spark.sql.adaptive.coalescePartitions.minPartitionNum | 200
   spark.sql.adaptive.customCostEvaluatorClass | 
org.apache.spark.sql.execution.adaptive.GlutenCostEvaluator
   spark.sql.adaptive.enabled | true
   
   


-- 
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