danny0405 commented on code in PR #13232:
URL: https://github.com/apache/hudi/pull/13232#discussion_r2065684618
##########
hudi-common/src/main/java/org/apache/hudi/common/util/collection/ExternalSpillableMap.java:
##########
@@ -217,21 +217,18 @@ public R get(Object key) {
@Override
public R put(T key, R value) {
- if (this.estimatedPayloadSize == 0) {
- // At first, use the sizeEstimate of a record being inserted into the
spillable map.
- // Note, the converter may over-estimate the size of a record in the JVM
- this.estimatedPayloadSize = keySizeEstimator.sizeEstimate(key) +
valueSizeEstimator.sizeEstimate(value);
- } else if (this.inMemoryMap.size() %
NUMBER_OF_RECORDS_TO_ESTIMATE_PAYLOAD_SIZE == 0) {
- this.estimatedPayloadSize = (long) (this.estimatedPayloadSize * 0.9 +
(keySizeEstimator.sizeEstimate(key) + valueSizeEstimator.sizeEstimate(value)) *
0.1);
- this.currentInMemoryMapSize = this.inMemoryMap.size() *
this.estimatedPayloadSize;
- if (this.inMemoryMap.size() / NUMBER_OF_RECORDS_TO_ESTIMATE_PAYLOAD_SIZE
== 1) {
- LOG.info("{} : Updated Estimated Payload size {}", loggingContext,
this.estimatedPayloadSize);
- }
- }
-
if (this.inMemoryMap.containsKey(key)) {
this.inMemoryMap.put(key, value);
} else if (this.currentInMemoryMapSize < this.maxInMemorySizeInBytes) {
+ if (this.estimatedPayloadSize == 0) {
+ // At first, use the sizeEstimate of a record being inserted into the
spillable map.
+ // Note, the converter may over-estimate the size of a record in the
JVM
+ this.estimatedPayloadSize = keySizeEstimator.sizeEstimate(key) +
valueSizeEstimator.sizeEstimate(value);
+ } else if (this.inMemoryMap.size() %
NUMBER_OF_RECORDS_TO_ESTIMATE_PAYLOAD_SIZE == 0) {
+ this.estimatedPayloadSize = (long) (this.estimatedPayloadSize * 0.9 +
(keySizeEstimator.sizeEstimate(key) + valueSizeEstimator.sizeEstimate(value)) *
0.1);
+ this.currentInMemoryMapSize = this.inMemoryMap.size() *
this.estimatedPayloadSize;
Review Comment:
Move the `this.estimatedPayloadSize == 0` condition here too. Can you double
check it @the-other-tim-brown ~
--
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-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
