You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pinot.apache.org by GitBox <gi...@apache.org> on 2022/05/12 12:23:10 UTC

[GitHub] [pinot] richardstartin commented on pull request #8687: deduplicate predicates pessimistically

richardstartin commented on PR #8687:
URL: https://github.com/apache/pinot/pull/8687#issuecomment-1124926098

   This doesn't have a huge impact but given that planning is single threaded, it could be worth it:, though it trades an improvement in the common case for what will be a regression in rare cases
   
   ```
   Benchmark               (_numRows)                                                                                                                                                      (_query)  (_scenario)  Mode  Cnt  Score   Error  Units
   BenchmarkQueries.query     1500000  SELECT INT_COL, SORTED_COL, SUM(RAW_INT_COL) FROM MyTable WHERE INT_COL = 0 and SORTED_COL = 1 GROUP BY INT_COL, SORTED_COL ORDER BY SORTED_COL, INT_COL ASC   EXP(0.001)  avgt    5  0.667 ± 0.141  ms/op
   BenchmarkQueries.query     1500000  SELECT INT_COL, SORTED_COL, SUM(RAW_INT_COL) FROM MyTable WHERE INT_COL = 0 and SORTED_COL = 1 GROUP BY INT_COL, SORTED_COL ORDER BY SORTED_COL, INT_COL ASC     EXP(0.5)  avgt    5  0.500 ± 0.255  ms/op
   BenchmarkQueries.query     1500000  SELECT INT_COL, SORTED_COL, SUM(RAW_INT_COL) FROM MyTable WHERE INT_COL = 0 and SORTED_COL = 1 GROUP BY INT_COL, SORTED_COL ORDER BY SORTED_COL, INT_COL ASC   EXP(0.999)  avgt    5  0.828 ± 0.117  ms/op
   ```
   
   ```
   Benchmark               (_numRows)                                                                                                                                                      (_query)  (_scenario)  Mode  Cnt  Score   Error  Units
   BenchmarkQueries.query     1500000  SELECT INT_COL, SORTED_COL, SUM(RAW_INT_COL) FROM MyTable WHERE INT_COL = 0 and SORTED_COL = 1 GROUP BY INT_COL, SORTED_COL ORDER BY SORTED_COL, INT_COL ASC   EXP(0.001)  avgt    5  0.435 ± 0.116  ms/op
   BenchmarkQueries.query     1500000  SELECT INT_COL, SORTED_COL, SUM(RAW_INT_COL) FROM MyTable WHERE INT_COL = 0 and SORTED_COL = 1 GROUP BY INT_COL, SORTED_COL ORDER BY SORTED_COL, INT_COL ASC     EXP(0.5)  avgt    5  0.458 ± 0.238  ms/op
   BenchmarkQueries.query     1500000  SELECT INT_COL, SORTED_COL, SUM(RAW_INT_COL) FROM MyTable WHERE INT_COL = 0 and SORTED_COL = 1 GROUP BY INT_COL, SORTED_COL ORDER BY SORTED_COL, INT_COL ASC   EXP(0.999)  avgt    5  0.598 ± 0.111  ms/op
   ```


-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@pinot.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@pinot.apache.org
For additional commands, e-mail: commits-help@pinot.apache.org