Zoltan Borok-Nagy has posted comments on this change. ( http://gerrit.cloudera.org:8080/21597 )
Change subject: IMPALA-13246: Smallify strings during broadcast exchange ...................................................................... Patch Set 6: Code-Review+2 (3 comments) http://gerrit.cloudera.org:8080/#/c/21597/4//COMMIT_MSG Commit Message: http://gerrit.cloudera.org:8080/#/c/21597/4//COMMIT_MSG@14 PS4, Line 14: it turned out that this is not true in some : cases) > I was wrong here, the problematic tuple was in a different part of the quer Thanks for tracking it down. http://gerrit.cloudera.org:8080/#/c/21597/4//COMMIT_MSG@17 PS4, Line 17: Measured >1% improvement in TPCH(42). > There was still some improvement after removing SmallifyStrings. Thanks for taking a look. Maybe for very wide tables with lots of string values SmallifyStrings() has more benefit, but this way the code is simpler and less error-prone. http://gerrit.cloudera.org:8080/#/c/21597/6/be/src/runtime/smallable-string.h File be/src/runtime/smallable-string.h: http://gerrit.cloudera.org:8080/#/c/21597/6/be/src/runtime/smallable-string.h@145 PS6, Line 145: SmallifiedLen nit: I find the name a bit confusing, maybe 'VarLen()', 'HeapLen()', 'RequiredHeapLen()', 'VarLenIfSmallified()' would be clearer. But it's quite subjective, so feel free to ignore if you disagree. -- To view, visit http://gerrit.cloudera.org:8080/21597 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-MessageType: comment Gerrit-Change-Id: I281d77c7a241ebfe8716eb5c975f0660601aec1b Gerrit-Change-Number: 21597 Gerrit-PatchSet: 6 Gerrit-Owner: Csaba Ringhofer <[email protected]> Gerrit-Reviewer: Csaba Ringhofer <[email protected]> Gerrit-Reviewer: Impala Public Jenkins <[email protected]> Gerrit-Reviewer: Zoltan Borok-Nagy <[email protected]> Gerrit-Comment-Date: Wed, 14 Aug 2024 13:25:10 +0000 Gerrit-HasComments: Yes
