Shekharrajak commented on PR #3060:
URL:
https://github.com/apache/datafusion-comet/pull/3060#issuecomment-3730450657
### Query Plans ###
```
--- Spark (baseline) ---
AdaptiveSparkPlan isFinalPlan=true
+- == Final Plan ==
*(2) Project [id#9L, dim_key#10L, value#11, name#22]
+- *(2) BroadcastHashJoin [dim_key#10L], [id#21L], Inner, BuildRight,
false
:- *(2) Filter isnotnull(dim_key#10L)
: +- *(2) ColumnarToRow
: +- FileScan parquet [id#9L,dim_key#10L,value#11] Batched: true,
DataFilters: [isnotnull(dim_key#10L)], Format: Parquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(dim_key)], ReadSchema:
struct<id:bigint,dim_key:bigint,value:double>
+- BroadcastQueryStage 0
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0,
bigint, false]),false), [plan_id=108]
+- *(1) Filter isnotnull(id#21L)
+- *(1) ColumnarToRow
+- FileScan parquet [id#21L,name#22] Batched: true,
DataFilters: [isnotnull(id#21L)], Format: Parquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema:
struct<id:bigint,name:string>
+- == Initial Plan ==
Project [id#9L, dim_key#10L, value#11, name#22]
+- BroadcastHashJoin [dim_key#10L], [id#21L], Inner, BuildRight, false
:- Filter isnotnull(dim_key#10L)
: +- FileScan parquet [id#9L,dim_key#10L,value#11] Batched: true,
DataFilters: [isnotnull(dim_key#10L)], Format: Parquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(dim_key)], ReadSchema:
struct<id:bigint,dim_key:bigint,value:double>
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint,
false]),false), [plan_id=94]
+- Filter isnotnull(id#21L)
+- FileScan parquet [id#21L,name#22] Batched: true, DataFilters:
[isnotnull(id#21L)], Format: Parquet, Location: InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema:
struct<id:bigint,name:string>
--- Comet (auto scan) ---
AdaptiveSparkPlan isFinalPlan=true
+- == Final Plan ==
*(1) CometColumnarToRow
+- CometProject [id#9L, dim_key#10L, value#11, name#22], [id#9L,
dim_key#10L, value#11, name#22]
+- CometBroadcastHashJoin [dim_key#10L], [id#21L], Inner, BuildRight
:- CometFilter [id#9L, dim_key#10L, value#11],
isnotnull(dim_key#10L)
: +- CometScan [native_iceberg_compat] parquet
[id#9L,dim_key#10L,value#11] Batched: true, DataFilters:
[isnotnull(dim_key#10L)], Format: CometParquet, Location: InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(dim_key)], ReadSchema:
struct<id:bigint,dim_key:bigint,value:double>
+- BroadcastQueryStage 0
+- CometBroadcastExchange [id#21L, name#22]
+- CometFilter [id#21L, name#22], isnotnull(id#21L)
+- CometScan [native_iceberg_compat] parquet
[id#21L,name#22] Batched: true, DataFilters: [isnotnull(id#21L)], Format:
CometParquet, Location: InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema:
struct<id:bigint,name:string>
+- == Initial Plan ==
CometProject [id#9L, dim_key#10L, value#11, name#22], [id#9L,
dim_key#10L, value#11, name#22]
+- CometBroadcastHashJoin [dim_key#10L], [id#21L], Inner, BuildRight
:- CometFilter [id#9L, dim_key#10L, value#11], isnotnull(dim_key#10L)
: +- CometScan [native_iceberg_compat] parquet
[id#9L,dim_key#10L,value#11] Batched: true, DataFilters:
[isnotnull(dim_key#10L)], Format: CometParquet, Location: InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(dim_key)], ReadSchema:
struct<id:bigint,dim_key:bigint,value:double>
+- CometBroadcastExchange [id#21L, name#22]
+- CometFilter [id#21L, name#22], isnotnull(id#21L)
+- CometScan [native_iceberg_compat] parquet [id#21L,name#22]
Batched: true, DataFilters: [isnotnull(id#21L)], Format: CometParquet,
Location: InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema:
struct<id:bigint,name:string>
--- Comet (native_datafusion + DPP) ---
AdaptiveSparkPlan isFinalPlan=true
+- == Final Plan ==
*(1) CometColumnarToRow
+- CometProject [id#9L, dim_key#10L, value#11, name#22], [id#9L,
dim_key#10L, value#11, name#22]
+- CometBroadcastHashJoin [dim_key#10L], [id#21L], Inner, BuildRight
:- CometFilter [id#9L, dim_key#10L, value#11],
isnotnull(dim_key#10L)
: +- CometNativeScan parquet [id#9L,dim_key#10L,value#11] Batched:
true, DataFilters: [isnotnull(dim_key#10L)], Format: CometParquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(dim_key)], ReadSchema:
struct<id:bigint,dim_key:bigint,value:double>
+- BroadcastQueryStage 0
+- CometBroadcastExchange [id#21L, name#22]
+- CometFilter [id#21L, name#22], isnotnull(id#21L)
+- CometNativeScan parquet [id#21L,name#22] Batched: true,
DataFilters: [isnotnull(id#21L)], Format: CometParquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema:
struct<id:bigint,name:string>
+- == Initial Plan ==
CometProject [id#9L, dim_key#10L, value#11, name#22], [id#9L,
dim_key#10L, value#11, name#22]
+- CometBroadcastHashJoin [dim_key#10L], [id#21L], Inner, BuildRight
:- CometFilter [id#9L, dim_key#10L, value#11], isnotnull(dim_key#10L)
: +- CometNativeScan parquet [id#9L,dim_key#10L,value#11] Batched:
true, DataFilters: [isnotnull(dim_key#10L)], Format: CometParquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(dim_key)], ReadSchema:
struct<id:bigint,dim_key:bigint,value:double>
+- CometBroadcastExchange [id#21L, name#22]
+- CometFilter [id#21L, name#22], isnotnull(id#21L)
+- CometNativeScan parquet [id#21L,name#22] Batched: true,
DataFilters: [isnotnull(id#21L)], Format: CometParquet, Location:
InMemoryFileIndex(1
paths)[file:/private/var/folders/2l/scrh4gwd32lf1rrytysnzmjw0000gn/T/spark-b9...,
PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema:
struct<id:bigint,name:string>
```
--
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]
