zhangjun0x01 commented on code in PR #584:
URL: https://github.com/apache/incubator-paimon/pull/584#discussion_r1145077502
##########
paimon-flink/paimon-flink-common/src/main/java/org/apache/paimon/flink/source/DataTableSource.java:
##########
@@ -163,15 +167,44 @@ public ScanRuntimeProvider
getScanRuntimeProvider(ScanContext scanContext) {
.withProjection(projectFields)
.withPredicate(predicate)
.withLimit(limit)
- .withParallelism(
- Options.fromMap(table.schema().options())
-
.get(FlinkConnectorOptions.SCAN_PARALLELISM))
+ .withParallelism(inferParallelism())
.withWatermarkStrategy(watermarkStrategy);
return new PaimonDataStreamScanProvider(
!streaming, env -> sourceBuilder.withEnv(env).build());
}
+ private Integer inferParallelism() {
+ Options options = Options.fromMap(this.table.schema().options());
+ Integer parallelism =
options.get(FlinkConnectorOptions.SCAN_PARALLELISM);
+
+ if (options.get(FlinkConnectorOptions.INFER_SCAN_PARALLELISM)) {
+ // for streaming mode, set the default parallelism to the bucket
number.
+ if (streaming) {
+ parallelism = options.get(CoreOptions.BUCKET);
+ } else {
+ int splitSize = 1;
+ if (table instanceof AbstractFileStoreTable) {
+ List<Split> splitList = ((AbstractFileStoreTable)
table).splits();
+ if (null != splitList) {
+ splitSize = splitList.size();
+ }
+ }
+ parallelism = splitSize;
+
+ if (null != limit && limit > 0) {
+ int limitCount =
+ limit >= Integer.MAX_VALUE ? Integer.MAX_VALUE :
limit.intValue();
+ parallelism = Math.min(parallelism, limitCount);
+ }
+
+ // parallelism must be positive.
+ parallelism = Math.max(1, parallelism);
Review Comment:
To prevent the user set an incorrect value for `scan.parallelism`, for -1 or
0.
--
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: issues-unsubscr...@paimon.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
