Skip to content

[fix](regression) check partition minmax only#65229

Open
shuke987 wants to merge 1 commit into
apache:branch-4.1from
shuke987:fix-branch41-partition-key-minmax
Open

[fix](regression) check partition minmax only#65229
shuke987 wants to merge 1 commit into
apache:branch-4.1from
shuke987:fix-branch41-partition-key-minmax

Conversation

@shuke987

@shuke987 shuke987 commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

Proposed changes

Backport #65180 to branch-4.1. On branch-4.1, partition_key_minmax still lives under nereids_p0/stats, so this applies the same final fix to the branch-specific path instead of directly picking the master file path.

The case is intended to validate partition-pruned partition-key min/max. The previous checks also depended on ndv/count, which can vary with async physical row-count reporting. This patch keeps the existing RANGE/LIST queries and checks only the partition-key min/max invariants.

Testing

  • git diff --check -- regression-test/suites/nereids_p0/stats/partition_key_minmax.groovy
  • git diff --check HEAD^ HEAD -- regression-test/suites/nereids_p0/stats/partition_key_minmax.groovy

Targeted regression was not run locally; CI will cover it.

Backport apache#65180 to branch-4.1, where partition_key_minmax still lives under nereids_p0/stats.

The case should assert partition-key min/max only because ndv/count depends on async physical row-count reporting.

(cherry picked from commit 3f0200c)
@shuke987 shuke987 requested a review from yiguolei as a code owner July 6, 2026 03:29
@hello-stephen

Copy link
Copy Markdown
Contributor

Thank you for your contribution to Apache Doris.
Don't know what should be done next? See How to process your PR.

Please clearly describe your PR:

  1. What problem was fixed (it's best to include specific error reporting information). How it was fixed.
  2. Which behaviors were modified. What was the previous behavior, what is it now, why was it modified, and what possible impacts might there be.
  3. What features were added. Why was this function added?
  4. Which code was refactored and why was this part of the code refactored?
  5. Which functions were optimized and what is the difference before and after the optimization?

@shuke987

shuke987 commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator Author

run buildall

@shuke987

shuke987 commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator Author

/review

@github-actions github-actions Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reviewed PR 65229. I did not find a blocking issue in this single-file regression-test backport.

The changed explain { check { ... } } assertions still fail when the expected partition-key min/max line is absent, because ExplainAction.check throws on a false Boolean result. The relaxed assertions match the stated intent: keep coverage for RANGE/LIST partition-key min/max while avoiding brittle ndv/count values that depend on async physical row-count reporting.

Validation performed:

  • Read the review bundle context, existing review threads/comments, changed-file list, required AGENTS list, and shared ledger.
  • Used GitHub PR metadata/patch as authoritative scope; local HEAD matches 44a76c2f97f2c9bc60ef968d693854daf30d6662.
  • Reviewed regression-test/suites/nereids_p0/stats/partition_key_minmax.groovy, ExplainAction.check behavior, and the upstream PR 65180 backport shape.
  • Ran git diff --check -- regression-test/suites/nereids_p0/stats/partition_key_minmax.groovy.

Limits: I did not run the targeted regression suite in this runner, and git diff --check HEAD^ HEAD could not be run because HEAD^ is unavailable in this grafted checkout.

User focus: no additional review focus was provided.

Subagent conclusions: the optimizer/rewrite subagent and the tests/session-config subagent both reported NO_NEW_VALUABLE_FINDINGS; no subagent candidate became an inline comment, and no duplicate candidate was merged. Final convergence round 1 ended with both live subagents reporting NO_NEW_VALUABLE_FINDINGS for this same no-inline-comment set.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants