rdblue commented on code in PR #12298:
URL: https://github.com/apache/iceberg/pull/12298#discussion_r2756599319
##########
spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/source/BaseBatchReader.java:
##########
@@ -76,79 +73,38 @@ protected CloseableIterable<ColumnarBatch> newBatchIterable(
Expression residual,
Map<Integer, ?> idToConstant,
@Nonnull SparkDeleteFilter deleteFilter) {
- CloseableIterable<ColumnarBatch> iterable;
- switch (format) {
- case PARQUET:
- iterable =
- newParquetIterable(
- inputFile, start, length, residual, idToConstant,
deleteFilter.requiredSchema());
- break;
- case ORC:
- iterable = newOrcIterable(inputFile, start, length, residual,
idToConstant);
- break;
- default:
- throw new UnsupportedOperationException(
- "Format: " + format + " not supported for batched reads");
+ ReadBuilder<ColumnarBatch, ?> readBuilder;
+ if (parquetConf != null) {
+ readBuilder =
+ parquetConf.readerType() == ParquetReaderType.COMET
+ ? FormatModelRegistry.readBuilder(
+ format,
VectorizedSparkParquetReaders.CometColumnarBatch.class, inputFile)
+ : FormatModelRegistry.readBuilder(format, ColumnarBatch.class,
inputFile);
+
+ readBuilder = readBuilder.recordsPerBatch(parquetConf.batchSize());
+ } else {
+ readBuilder = FormatModelRegistry.readBuilder(format,
ColumnarBatch.class, inputFile);
+ if (orcConf != null) {
+ readBuilder = readBuilder.recordsPerBatch(orcConf.batchSize());
+ }
}
- return CloseableIterable.transform(iterable, new
BatchDeleteFilter(deleteFilter)::filterBatch);
- }
+ CloseableIterable<ColumnarBatch> iterable =
+ readBuilder
+ .project(deleteFilter.requiredSchema())
+ .idToConstant(idToConstant)
+ .split(start, length)
+ .caseSensitive(caseSensitive())
+ .filter(residual)
+ // Spark eagerly consumes the batches. So the underlying memory
allocated could be
+ // reused without worrying about subsequent reads clobbering over
each other. This
+ // improves read performance as every batch read doesn't have to
pay the cost of
+ // allocating memory.
Review Comment:
Nit: Did this need to be reformatted? It's less of a problem if there aren't
substantive changes mixed together with reformatting.
--
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]
