You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "yihua (via GitHub)" <gi...@apache.org> on 2025/08/25 16:44:39 UTC

Re: [PR] [HUDI-9739] Create meta client in Spark driver for FGReader based format to avoid performance degradation [hudi]

yihua commented on code in PR #13756:
URL: https://github.com/apache/hudi/pull/13756#discussion_r2298595455


##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedFileFormat.scala:
##########
@@ -255,15 +254,15 @@ class HoodieFileGroupReaderBasedFileFormat(tablePath: String,
 
             case _ =>
               readBaseFile(file, baseFileReader.value, requestedSchema, remainingPartitionSchema, fixedPartitionIndexes,
-                requiredSchema, partitionSchema, outputSchema, filters, storageConf)
+                requiredSchema, partitionSchema, outputSchema, filters, augmentedStorageConf)
           }
         // CDC queries.
         case hoodiePartitionCDCFileGroupSliceMapping: HoodiePartitionCDCFileGroupMapping =>
-          buildCDCRecordIterator(hoodiePartitionCDCFileGroupSliceMapping, fileGroupBaseFileReader.value, storageConf, fileIndexProps, requiredSchema)
+          buildCDCRecordIterator(hoodiePartitionCDCFileGroupSliceMapping, fileGroupBaseFileReader.value, augmentedStorageConf, fileIndexProps, requiredSchema, metaClient)

Review Comment:
   Similar here on using `storageConf`



##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedFileFormat.scala:
##########
@@ -255,15 +254,15 @@ class HoodieFileGroupReaderBasedFileFormat(tablePath: String,
 
             case _ =>
               readBaseFile(file, baseFileReader.value, requestedSchema, remainingPartitionSchema, fixedPartitionIndexes,
-                requiredSchema, partitionSchema, outputSchema, filters, storageConf)
+                requiredSchema, partitionSchema, outputSchema, filters, augmentedStorageConf)
           }
         // CDC queries.
         case hoodiePartitionCDCFileGroupSliceMapping: HoodiePartitionCDCFileGroupMapping =>
-          buildCDCRecordIterator(hoodiePartitionCDCFileGroupSliceMapping, fileGroupBaseFileReader.value, storageConf, fileIndexProps, requiredSchema)
+          buildCDCRecordIterator(hoodiePartitionCDCFileGroupSliceMapping, fileGroupBaseFileReader.value, augmentedStorageConf, fileIndexProps, requiredSchema, metaClient)
 
         case _ =>
           readBaseFile(file, baseFileReader.value, requestedSchema, remainingPartitionSchema, fixedPartitionIndexes,
-            requiredSchema, partitionSchema, outputSchema, filters, storageConf)
+            requiredSchema, partitionSchema, outputSchema, filters, augmentedStorageConf)

Review Comment:
   Similar



##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedFileFormat.scala:
##########
@@ -255,15 +254,15 @@ class HoodieFileGroupReaderBasedFileFormat(tablePath: String,
 
             case _ =>
               readBaseFile(file, baseFileReader.value, requestedSchema, remainingPartitionSchema, fixedPartitionIndexes,
-                requiredSchema, partitionSchema, outputSchema, filters, storageConf)
+                requiredSchema, partitionSchema, outputSchema, filters, augmentedStorageConf)

Review Comment:
   This should still use `storageConf`?



-- 
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: commits-unsubscribe@hudi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org