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.

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

Revert SortShuffleManager changes in ColumnarShuffleManager #6149

Merged
merged 1 commit into from
Jun 20, 2024

Conversation

acvictor
Copy link
Contributor

What changes were proposed in this pull request?

Revert ColumnarShuffleManager changes in #6022 to mitigate issue #6140

Copy link

Thanks for opening a pull request!

Could you open an issue for this pull request on Github Issues?

https://github.com/apache/incubator-gluten/issues

Then could you also rename commit message and pull request title in the following format?

[GLUTEN-${ISSUES_ID}][COMPONENT]feat/fix: ${detailed message}

See also:

Copy link

Run Gluten Clickhouse CI

@acvictor
Copy link
Contributor Author

@zhli1142015 @marin-ma @ulysses-you can you please review this PR? Will working on investigating the regression separately.

Copy link
Contributor

@ulysses-you ulysses-you left a comment

Choose a reason for hiding this comment

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

it's interesting.. I'm fine to revert it first

@ulysses-you ulysses-you merged commit 716dd9a into apache:main Jun 20, 2024
37 of 38 checks passed
@GlutenPerfBot
Copy link
Contributor

===== Performance report for TPCH SF2000 with Velox backend, for reference only ====

query log/native_6149_time.csv log/native_master_06_19_2024_27c32f1b15_time.csv difference percentage
q1 33.76 34.61 0.856 102.54%
q2 27.25 25.46 -1.790 93.43%
q3 37.19 38.59 1.407 103.79%
q4 35.69 33.98 -1.711 95.21%
q5 71.09 70.97 -0.115 99.84%
q6 8.10 6.54 -1.560 80.75%
q7 82.26 85.08 2.820 103.43%
q8 87.65 87.11 -0.540 99.38%
q9 121.81 123.67 1.867 101.53%
q10 44.75 44.85 0.099 100.22%
q11 22.30 20.56 -1.744 92.18%
q12 25.53 27.28 1.753 106.87%
q13 40.18 39.58 -0.605 98.49%
q14 19.17 18.81 -0.362 98.11%
q15 34.99 33.35 -1.641 95.31%
q16 14.67 14.28 -0.385 97.38%
q17 103.12 105.60 2.473 102.40%
q18 147.60 144.60 -2.996 97.97%
q19 13.72 13.77 0.046 100.33%
q20 29.28 29.04 -0.232 99.21%
q21 267.06 265.23 -1.834 99.31%
q22 14.54 12.88 -1.664 88.56%
total 1281.71 1275.86 -5.856 99.54%

@acvictor
Copy link
Contributor Author

it's interesting.. I'm fine to revert it first

Thanks! I am also puzzled, will keep you updated on any findings.

@FelixYBW
Copy link
Contributor

PR6022 caused performance regression in our nightly test.

@acvictor acvictor deleted the acvictor/revertShuffle branch June 20, 2024 07:41
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.

4 participants