weimingdiit commented on code in PR #7362:
URL: https://github.com/apache/hudi/pull/7362#discussion_r1105193398
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/BaseSparkCommitActionExecutor.java:
##########
@@ -418,4 +426,23 @@ public Partitioner getLayoutPartitioner(WorkloadProfile
profile, String layoutPa
protected void
runPrecommitValidators(HoodieWriteMetadata<HoodieData<WriteStatus>>
writeMetadata) {
SparkValidatorUtils.runValidators(config, writeMetadata, context, table,
instantTime);
}
+
+ private int dynamicSampleRecordSize(JavaRDD<HoodieRecord<T>> inputRecords) {
+ int dynamicSampleRecordSize = config.getCopyOnWriteRecordSizeEstimate();
+ long inputRecordsCount = inputRecords.count();
+ if (inputRecordsCount == 0) {
+ LOG.warn("inputRecords is empty.");
+ return dynamicSampleRecordSize;
+ }
+ int maxSampleRecordNum = (int) Math.ceil(Math.min(inputRecordsCount *
config.getRecordSizeDynamicSamplingRatio(),
config.getRecordSizeDynamicSamplingMaxnum()));
+ try {
+ List<HoodieRecord<T>> sampleRecords = inputRecords.takeSample(false,
maxSampleRecordNum);
+ dynamicSampleRecordSize = (int)
(ObjectSizeCalculator.getObjectSize(sampleRecords) / maxSampleRecordNum);
Review Comment:
@alexeykudinkin thanks Alexey! Got it. I'll optimize this code
--
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]
