[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-08-29 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-683283412 @cloud-fan, @maropu, @viirya, can you please help me how to move forward with this PR? The latest commit updates expected plans of PlanStability suites where you can see t

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-08-03 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-667885549 @cloud-fan, @maryannxue, @maropu, @viirya could you please help and review this PR? This is an automated mes

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-10 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-656634873 @cloud-fan, @maryannxue, @maropu, @viirya could you please review this PR? This is an automated message from

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-16 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-659332636 I've added a few more comments to explain how the PR works. @cloud-fan, @maryannxue, @maropu, @viirya please let me know if you have any concerns, suggestions or you ar

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-17 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-660103057 I've updated the description and added some simpler test cases than TPCDS Q14a to repro the issue and test the fix. -

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-22 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-662605898 @cloud-fan, @maryannxue, @maropu, @viirya please let me know if you have any concerns, suggestions or you are missing something from this PR. ---

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-23 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-662911048 Thanks @squito for the review, very appreciated. > I discussed this offline with Peter a little bit. This is not my area of expertise, so take my comments with a grain

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-23 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-662961454 Commit https://github.com/apache/spark/pull/28885/commits/eaf4ad046ce4de55f71fc195daa18d6b9a8af520 adds UT coverage to `ReuseMap`. -

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-10-08 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-705422879 retest this please This is an automated message from the Apache Git Service. To respond to the message, pleas

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-10-09 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-705422879 retest this please This is an automated message from the Apache Git Service. To respond to the message, pleas

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-06-28 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-650733793 > Thanks for doing this! I think the idea of whole plan reuse is good and your approach is correct, but I think some parts can be done differently IMO, I left some comments.

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-06-30 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-651701192 > Changes look good to me, added 3 minor comments. Thanks @dbaliafroozeh. @cloud-fan, @maryannxue could you review this PR?

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-07-01 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-652575800 retest this please This is an automated message from the Apache Git Service. To respond to the message, pleas

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2020-10-15 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-709412919 @cloud-fan, @maropu, @viirya any thoughts on this PR? This is an automated message from the Apache Git Servic

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-06-18 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-863555729 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For quer

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-06-21 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-864803292 > thanks, merging to master! Thanks for the review! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHu

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-06-22 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-864803292 > thanks, merging to master! Thanks for the review! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHu

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-02-10 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-776590219 @cloud-fan could you please help me with this PR? The incorrect reuse nodes cause performance issues currently and in special cases they can even cause performance regr

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-01-20 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-763437539 I've updated this PR with minor changes due to AQE is now enabled by default. Without this PR invalid reuse nodes are in many TPCDS queries causing performance degradat

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-01-26 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-767530441 Now that https://github.com/apache/spark/pull/31243 got merged the invalid reuse references (`Reuses operator id: unknown`) show up in many golden files. Each of them mean a

[GitHub] [spark] peter-toth commented on pull request #28885: [SPARK-29375][SPARK-28940][SPARK-32041][SQL] Whole plan exchange and subquery reuse

2021-03-19 Thread GitBox
peter-toth commented on pull request #28885: URL: https://github.com/apache/spark/pull/28885#issuecomment-802798305 This is till a serious issue in Spark 3. I've updated the PR with the latest commit from `master`. -- This is an automated message from the Apache Git Service. To respond t