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

Reduce virtual function call overhead for constructing columns in join probing #8682

Open
gengliqi opened this issue Jan 12, 2024 · 0 comments · May be fixed by #8683
Open

Reduce virtual function call overhead for constructing columns in join probing #8682

gengliqi opened this issue Jan 12, 2024 · 0 comments · May be fixed by #8683
Labels
type/enhancement Issue or PR for enhancement

Comments

@gengliqi
Copy link
Contributor

Enhancement

During join probing, some codes like the below call virtual function for each row. We can reduce this overhead through batching.

tiflash/dbms/src/Interpreters/JoinPartition.cpp

Lines 1313 to 1318 in 7779b00

auto add_one_row = [&]() {
for (size_t j = 0; j < num_columns_to_add; ++j)
added_columns[j]->insertFrom(
*current->block->getByPosition(right_indexes[j]).column.get(),
current->row_num);
};

@gengliqi gengliqi added the type/enhancement Issue or PR for enhancement label Jan 12, 2024
@gengliqi gengliqi linked a pull request Jan 12, 2024 that will close this issue
Open
12 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
type/enhancement Issue or PR for enhancement
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Reduce virtual function call overhead for constructing columns in join probing gengliqi/tiflash
1 participant
@gengliqi