bersprockets commented on a change in pull request #34659:
URL: https://github.com/apache/spark/pull/34659#discussion_r779180183
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java
##########
@@ -103,9 +104,14 @@ public void initialize(InputSplit inputSplit,
TaskAttemptContext taskAttemptCont
fileReader.setRequestedSchema(requestedSchema);
String sparkRequestedSchemaString =
configuration.get(ParquetReadSupport$.MODULE$.SPARK_ROW_REQUESTED_SCHEMA());
- this.sparkSchema =
StructType$.MODULE$.fromString(sparkRequestedSchemaString);
+ StructType sparkRequestedSchema =
StructType$.MODULE$.fromString(sparkRequestedSchemaString);
+ ParquetToSparkSchemaConverter converter = new
ParquetToSparkSchemaConverter(configuration);
+ this.parquetColumn = converter.convertParquetColumn(requestedSchema,
Review comment:
Yes, you've eliminated the schema lookup penalty.
There still seems to be the remaining 10-15% performance penalty. Earlier, I
speculated on the cause of this particular penalty:
>this PR is still 10% slower than the baseline when testing the wide row
case. I haven't confirmed it, but I think this is due to the extra
OnHeapColumnVector instances created in ParquetColumnVector, for which you
already have a TODO.
So maybe that will get resolved once the TODO is resolved.
--
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]
