csun5285 commented on code in PR #27299:
URL: https://github.com/apache/doris/pull/27299#discussion_r1435495196
##########
be/src/olap/tablet.cpp:
##########
@@ -1332,6 +1332,49 @@ std::vector<RowsetSharedPtr>
Tablet::pick_candidate_rowsets_to_full_compaction()
return pick_candidate_rowsets_to_single_replica_compaction();
}
+std::vector<RowsetSharedPtr> Tablet::pick_first_consecutive_empty_rowsets(int
limit) {
+ std::vector<RowsetSharedPtr> consecutive_empty_rowsets;
+ std::vector<RowsetSharedPtr> candidate_rowsets;
+ traverse_rowsets([&candidate_rowsets, this](const auto& rs) {
+ if (rs->is_local() && rs->start_version() >= _cumulative_point) {
+ candidate_rowsets.emplace_back(rs);
+ }
+ });
+ std::sort(candidate_rowsets.begin(), candidate_rowsets.end(),
Rowset::comparator);
+ int len = candidate_rowsets.size();
+ for (int i = 0; i < len - 1; ++i) {
+ auto rowset = candidate_rowsets[i];
+ auto next_rowset = candidate_rowsets[i + 1];
+
+ // identify two consecutive rowsets that are empty
+ if (rowset->num_segments() == 0 && next_rowset->num_segments() == 0 &&
+ !rowset->rowset_meta()->has_delete_predicate() &&
+ !next_rowset->rowset_meta()->has_delete_predicate() &&
+ rowset->end_version() == next_rowset->start_version() - 1) {
+ consecutive_empty_rowsets.emplace_back(rowset);
+ consecutive_empty_rowsets.emplace_back(next_rowset);
+ rowset = next_rowset;
+ int next_index = i + 2;
+
+ // keep searching for consecutive empty rowsets
+ while (next_index < len &&
candidate_rowsets[next_index]->num_segments() == 0 &&
+
!candidate_rowsets[next_index]->rowset_meta()->has_delete_predicate() &&
+ rowset->end_version() ==
candidate_rowsets[next_index]->start_version() - 1) {
+
consecutive_empty_rowsets.emplace_back(candidate_rowsets[next_index]);
+ rowset = candidate_rowsets[next_index++];
+ }
+ if (consecutive_empty_rowsets.size() >= limit && next_index < len)
{
+ return consecutive_empty_rowsets;
+ } else {
+ i = next_index - 1;
+ consecutive_empty_rowsets.clear();
Review Comment:
done
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
