Thomas Tauber-Marshall has posted comments on this change. ( http://gerrit.cloudera.org:8080/7793 )
Change subject: IMPALA-4252: Min-max runtime filters for Kudu ...................................................................... Patch Set 7: > > Patch Set 7: > > > > Perf results: > > ... > > I'm surprised that only a few queries saw significant speedups. Is > this in line with what you saw with Parquet runtime filters on > TPC-H? Or are we losing a lot by using min/max instead of bloom or > in-list style filters? Not sure about bloom filters perf, though I can run those numbers for comparison. One issue here is that tpch_100 isn't actually a very large dataset for a 9 node cluster. I've been having some trouble getting larger datasets loaded - making progress, but I'll reach out to some Kudu people if I can't get that working. Another issue is that I haven't tried playing around with our RUNTIME_FILTER_WAIT_TIME_MS tuning param yet (maybe Mostafa can speak to the advice we usually give customers here?) There were also some improvements to the handling of strings in the latest iteration of the review that aren't reflected here. I'll have updated numbers probably tomorrow. -- To view, visit http://gerrit.cloudera.org:8080/7793 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-MessageType: comment Gerrit-Change-Id: I02bad890f5b5f78388a3041bf38f89369b5e2f1c Gerrit-Change-Number: 7793 Gerrit-PatchSet: 7 Gerrit-Owner: Thomas Tauber-Marshall <[email protected]> Gerrit-Reviewer: Anonymous Coward #345 Gerrit-Reviewer: Lars Volker <[email protected]> Gerrit-Reviewer: Matthew Jacobs <[email protected]> Gerrit-Reviewer: Michael Ho <[email protected]> Gerrit-Reviewer: Mostafa Mokhtar <[email protected]> Gerrit-Reviewer: Thomas Tauber-Marshall <[email protected]> Gerrit-Reviewer: Tim Armstrong <[email protected]> Gerrit-Reviewer: Todd Lipcon <[email protected]> Gerrit-Comment-Date: Mon, 23 Oct 2017 21:35:58 +0000 Gerrit-HasComments: No
