Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: Reduce duplicate PKs in segcore #34267

Merged
merged 5 commits into from
Jul 1, 2024
Merged

fix: Reduce duplicate PKs in segcore #34267

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
ad4fc40
fix: Reduce duplicate PKs in segcore
bigsheeper Jun 28, 2024
5cd1bf9
update
bigsheeper Jun 28, 2024
0f936eb
update
bigsheeper Jun 28, 2024
d6aac26
Merge branch 'master' of https://github.com/milvus-io/milvus into 240…
bigsheeper Jul 1, 2024
c35af35
fix ut
bigsheeper Jul 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 9 additions & 10 deletions internal/core/src/segcore/InsertRecord.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,9 +116,9 @@ class OffsetOrderedMap : public OffsetMap {
bool false_filtered_out) const override {
std::shared_lock<std::shared_mutex> lck(mtx_);

// if (limit == Unlimited || limit == NoLimit) {
// limit = map_.size();
// }
if (limit == Unlimited || limit == NoLimit) {
limit = map_.size();
}

// TODO: we can't retrieve pk by offset very conveniently.
// Selectivity should be done outside.
Expand All @@ -142,15 +142,15 @@ class OffsetOrderedMap : public OffsetMap {
if (!false_filtered_out) {
cnt = size - bitset.count();
}
if (limit == Unlimited || limit == NoLimit) {
limit = cnt;
}
limit = std::min(limit, cnt);
std::vector<int64_t> seg_offsets;
seg_offsets.reserve(limit);
auto it = map_.begin();
for (; hit_num < limit && it != map_.end(); it++) {
for (auto seg_offset : it->second) {
// Offsets in the growing segment are ordered by timestamp,
// so traverse from back to front to obtain the latest offset.
for (int i = it->second.size() - 1; i >= 0; --i) {
auto seg_offset = it->second[i];
if (seg_offset >= size) {
// Frequently concurrent insert/query will cause this case.
continue;
Expand All @@ -159,9 +159,8 @@ class OffsetOrderedMap : public OffsetMap {
if (!(bitset[seg_offset] ^ false_filtered_out)) {
seg_offsets.push_back(seg_offset);
hit_num++;
if (hit_num >= limit) {
break;
}
// PK hit, no need to continue traversing offsets with the same PK.
break;
}
}
}
Expand Down
2 changes: 1 addition & 1 deletion internal/core/unittest/test_c_api.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -888,7 +888,7 @@ TEST(CApiTest, DeleteRepeatedPksFromGrowingSegment) {
auto suc = query_result->ParseFromArray(retrieve_result->proto_blob,
retrieve_result->proto_size);
ASSERT_TRUE(suc);
ASSERT_EQ(query_result->ids().int_id().data().size(), 6);
ASSERT_EQ(query_result->ids().int_id().data().size(), 3);
DeleteRetrieveResult(retrieve_result);
retrieve_result = nullptr;

Expand Down
Loading