Skip to content

branch-4.0: [opt](memory) set source content column by column when flush memtable for partial update #59547

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

Merged
yiguolei merged 1 commit into from
Jan 5, 2026
Merged

branch-4.0: [opt](memory) set source content column by column when flush memtable for partial update #59547

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
24 changes: 20 additions & 4 deletions be/src/olap/rowset/segment_v2/vertical_segment_writer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -528,15 +528,15 @@ Status VerticalSegmentWriter::_append_block_with_partial_content(RowsInBlock& da
for (auto i : including_cids) {
full_block.replace_by_position(i, data.block->get_by_position(input_id++).column);
}
RETURN_IF_ERROR(_olap_data_convertor->set_source_content_with_specifid_columns(
&full_block, data.row_pos, data.num_rows, including_cids));

bool have_input_seq_column = false;
// write including columns
std::vector<vectorized::IOlapColumnDataAccessor*> key_columns;
vectorized::IOlapColumnDataAccessor* seq_column = nullptr;
uint32_t segment_start_pos = 0;
for (auto cid : including_cids) {
RETURN_IF_ERROR(_olap_data_convertor->set_source_content_with_specifid_columns(
&full_block, data.row_pos, data.num_rows, std::vector<uint32_t> {cid}));
// here we get segment column row num before append data.
segment_start_pos = cast_set<uint32_t>(_column_writers[cid]->get_next_rowid());
// olap data convertor alway start from id = 0
Expand All @@ -554,6 +554,15 @@ Status VerticalSegmentWriter::_append_block_with_partial_content(RowsInBlock& da
RETURN_IF_ERROR(_column_writers[cid]->append(column->get_nullmap(), column->get_data(),
data.num_rows));
RETURN_IF_ERROR(_finalize_column_writer_and_update_meta(cid));
// Don't clear source content for key columns and sequence column here,
// as they will be used later in _full_encode_keys() and _generate_primary_key_index().
// They will be cleared at the end of this method.
bool is_key_column = (cid < _num_sort_key_columns);
bool is_seq_column = (_tablet_schema->has_sequence_col() &&
cid == _tablet_schema->sequence_col_idx() && have_input_seq_column);
if (!is_key_column && !is_seq_column) {
_olap_data_convertor->clear_source_content(cid);
}
}

bool has_default_or_nullable = false;
Expand Down Expand Up @@ -629,9 +638,9 @@ Status VerticalSegmentWriter::_append_block_with_partial_content(RowsInBlock& da

// convert missing columns and send to column writer
const auto& missing_cids = _opts.rowset_ctx->partial_update_info->missing_cids;
RETURN_IF_ERROR(_olap_data_convertor->set_source_content_with_specifid_columns(
&full_block, data.row_pos, data.num_rows, missing_cids));
for (auto cid : missing_cids) {
RETURN_IF_ERROR(_olap_data_convertor->set_source_content_with_specifid_columns(
&full_block, data.row_pos, data.num_rows, std::vector<uint32_t> {cid}));
auto [status, column] = _olap_data_convertor->convert_column_data(cid);
if (!status.ok()) {
return status;
Expand All @@ -644,6 +653,13 @@ Status VerticalSegmentWriter::_append_block_with_partial_content(RowsInBlock& da
RETURN_IF_ERROR(_column_writers[cid]->append(column->get_nullmap(), column->get_data(),
data.num_rows));
RETURN_IF_ERROR(_finalize_column_writer_and_update_meta(cid));
// Don't clear source content for sequence column here if it will be used later
// in _generate_primary_key_index(). It will be cleared at the end of this method.
bool is_seq_column = (_tablet_schema->has_sequence_col() && !have_input_seq_column &&
cid == _tablet_schema->sequence_col_idx());
if (!is_seq_column) {
_olap_data_convertor->clear_source_content(cid);
}
}

_num_rows_updated += stats.num_rows_updated;
Expand Down
Loading