Skip to content

refactor: optimize final aggregation for large datasets #19208

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
Draft
dqhl76 wants to merge 34 commits into
base: main
Choose a base branch
from
Draft

refactor: optimize final aggregation for large datasets #19208

dqhl76 wants to merge 34 commits into from

Conversation

@dqhl76
Copy link
Collaborator

@dqhl76 dqhl76 commented Jan 8, 2026 •
edited
Loading

I hereby agree to the terms of the CLA available at: https://docs.databend.com/dev/policies/cla/

Summary

This PR depends on #19155. Only Draft, performance test for
refactor: support partitioned HashIndex

Tests

  • Unit Test
  • Logic Test
  • Benchmark Test
  • No Test - Explain why

Type of change

  • Bug Fix (non-breaking change which fixes an issue)
  • New Feature (non-breaking change which adds functionality)
  • Breaking Change (fix or feature that could cause existing functionality not to work as expected)
  • Documentation Update
  • Refactoring
  • Performance Improvement
  • Other (please describe):

This change is Reviewable

dqhl76 added 30 commits December 25, 2025 16:44
@dqhl76
refactor: support row/bucket shuffle for aggregation
85cea16 
refactor: refactor spiller

row shuffle spill

tmp save

clean

pass bucket partial force spill

pass tpch

basic pass

feat: add support for partitioned aggregate serialization and deserialization

save

remove unused activate_worker

refactor: also add stats for final aggregate

feat: implement configurable aggregate shuffle mode

refactor: add basic bucket level shuffled agg

refactor: remove legacy final agg

feat: refactor aggregate function in build_aggregate to make it clear
@dqhl76
fmt
672b885
@dqhl76
enable_experiment_aggregate = 1
fc733c1
@dqhl76
license check
df270a0
@dqhl76
make clippy happy
40737d1
@dqhl76
make clippy happy
70710f5
@dqhl76
try fix hang when merge join is after agg
4075b59
@dqhl76
fmt
f427bb6
@dqhl76
fmt
d499dc8
@dqhl76
temp save
85d6c6e
@dqhl76
simplify AggregateShuffleMode
d2f3352
@dqhl76
simplify new partial aggregate
29cbbfb
@dqhl76
not finish
017cfe4
@dqhl76
save
6db6e57
@dqhl76
save
75d85b3
@dqhl76
fix
c6dd2c1
@dqhl76
fix
e7fc7d9
@dqhl76
row
156608f
@dqhl76
bucket
ac3d821
@dqhl76
finish
4bbc54d
@dqhl76
fmt + add test
307c3b7
@dqhl76
clean useless branch
b342d56
@dqhl76
try support final aggregate spill
7cc05d6
@dqhl76
feat: support final aggregate spill
b7b9866
@dqhl76
forget on_finish for output triggered finish
01ce590
@dqhl76
shuffle mode determination for not cluster aggregation
c80335f
@dqhl76
add more test
0be800a 
fixup
@dqhl76
fix
0b255dd
@dqhl76
add more test
82c47d5
@dqhl76
remove debug info
73888eb
@github-actions github-actions bot added the pr-refactor this PR changes the code base without new features or bugfix label Jan 8, 2026
@dqhl76 dqhl76 added the ci-cloud Build docker image for cloud test label Jan 8, 2026
@github-actions
Copy link
Contributor

github-actions bot commented Jan 8, 2026

Docker Image for PR

  • tag: pr-19208-1ce72ac-1767844912

note: this image tag is only available for internal use.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

ci-cloud Build docker image for cloud test pr-refactor this PR changes the code base without new features or bugfix

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@dqhl76