danny0405 commented on code in PR #8422:
URL: https://github.com/apache/hudi/pull/8422#discussion_r1172021405
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/client/HoodieTimelineArchiver.java:
##########
@@ -475,7 +485,24 @@ private Stream<HoodieInstant> getCommitInstantsToArchive()
throws IOException {
HoodieTimeline.compareTimestamps(s.getTimestamp(),
LESSER_THAN, instantToRetain.getTimestamp()))
.orElse(true)
);
- return instantToArchiveStream.limit(commitTimeline.countInstants() -
minInstantsToKeep);
+ List<HoodieInstant> instantsToArchive =
instantToArchiveStream.limit(commitTimeline.countInstants() -
minInstantsToKeep).collect(Collectors.toList());
+ // If cleaner is based on hours, lets ensure hudi does not archive
commits yet to cleaned by the cleaner.
+ if (config.getCleanerPolicy() ==
HoodieCleaningPolicy.KEEP_LATEST_BY_HOURS && !instantsToArchive.isEmpty()) {
+ String latestCommitToArchive =
instantsToArchive.get(instantsToArchive.size() - 1).getTimestamp();
+ try {
+ Instant latestCommitInstant =
HoodieActiveTimeline.parseDateFromInstantTime(commitTimeline.lastInstant().get().getTimestamp()).toInstant();
+ ZonedDateTime currentDateTime =
ZonedDateTime.ofInstant(latestCommitInstant, ZoneId.systemDefault());
+ String earliestTimeToRetain =
HoodieActiveTimeline.formatDate(Date.from(currentDateTime.minusHours(config.getCleanerHoursRetained()).toInstant()));
+ if (HoodieTimeline.compareTimestamps(latestCommitToArchive,
GREATER_THAN_OR_EQUALS, earliestTimeToRetain)) {
+ throw new HoodieIOException("Please align your archival configs
based on cleaner configs. 'hoodie.keep.min.commits' : "
+ + config.getMinCommitsToKeep() + " + should be greater than "
Review Comment:
Can we not hardcode these config options ?
--
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]
