aokolnychyi commented on a change in pull request #2248:
URL: https://github.com/apache/iceberg/pull/2248#discussion_r580608379
##########
File path: spark2/src/main/java/org/apache/iceberg/spark/source/Reader.java
##########
@@ -338,12 +330,50 @@ public boolean enableBatchRead() {
boolean hasNoDeleteFiles =
tasks().stream().noneMatch(TableScanUtil::hasDeletes);
+ boolean batchReadsEnabled = batchReadsEnabled(allParquetFileScanTasks,
allOrcFileScanTasks);
+
this.readUsingBatch = batchReadsEnabled && hasNoDeleteFiles &&
(allOrcFileScanTasks ||
(allParquetFileScanTasks && atLeastOneColumn && onlyPrimitives));
}
return readUsingBatch;
}
+ private boolean batchReadsEnabled(boolean isParquetOnly, boolean isOrcOnly) {
+ if (isParquetOnly) {
+ return isVectorizationEnabled(FileFormat.PARQUET);
+ } else if (isOrcOnly) {
+ return isVectorizationEnabled(FileFormat.ORC);
+ } else {
+ return false;
+ }
+ }
+
+ public boolean isVectorizationEnabled(FileFormat fileFormat) {
+ String readOptionValue =
options.get(SparkReadOptions.VECTORIZATION_ENABLED).orElse(null);
+ if (readOptionValue != null) {
+ return Boolean.parseBoolean(readOptionValue);
+ }
+
+ RuntimeConfig sessionConf = SparkSession.active().conf();
+ String sessionConfValue =
sessionConf.get("spark.sql.iceberg.vectorization.enabled", null);
+ if (sessionConfValue != null) {
+ return Boolean.parseBoolean(sessionConfValue);
+ }
+
+ switch (fileFormat) {
+ case PARQUET:
+ return PropertyUtil.propertyAsBoolean(
+ table.properties(),
+ TableProperties.PARQUET_VECTORIZATION_ENABLED,
+ TableProperties.PARQUET_VECTORIZATION_ENABLED_DEFAULT);
+ case ORC:
+ // TODO: add a table property to enable/disable ORC vectorized reads
+ return false;
Review comment:
I'll submit a flag in a follow-up PR. Just wanted to have Spark specific
changes in this one.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
