Riza Suminto has posted comments on this change. ( http://gerrit.cloudera.org:8080/17195 )
Change subject: IMPALA-10584: Defer advancing read page when reservation is tight. ...................................................................... Patch Set 4: (2 comments) Patch set 4 submitted. http://gerrit.cloudera.org:8080/#/c/17195/3/be/src/runtime/buffered-tuple-stream-test.cc File be/src/runtime/buffered-tuple-stream-test.cc: http://gerrit.cloudera.org:8080/#/c/17195/3/be/src/runtime/buffered-tuple-stream-test.cc@1237 PS3, Line 1237: TEST_F(SimpleTupleStreamTest, UnpinReadPage) { > It is possible to reproduce the bug with some changes in this test? Added DeferAdvancingReadPage to test this corner case. http://gerrit.cloudera.org:8080/#/c/17195/3/be/src/runtime/buffered-tuple-stream.cc File be/src/runtime/buffered-tuple-stream.cc: http://gerrit.cloudera.org:8080/#/c/17195/3/be/src/runtime/buffered-tuple-stream.cc@723 PS3, Line 723: > Does this assume the size of the read page is default_page_len_? Should we That is a good point, thanks! However, replacing it with read_it_.read_page_->len() caught this DCHECK failure: "buffer-pool.cc:93] Check failed: is_open()". I think this because the the page handle has been closed in AttachBufferToBatch(). I made a work around by memorizing the page len in last_attached_page_len_ variable. -- To view, visit http://gerrit.cloudera.org:8080/17195 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-MessageType: comment Gerrit-Change-Id: I16137b6e423f190f60c3115a06ccd0f77e9f585a Gerrit-Change-Number: 17195 Gerrit-PatchSet: 4 Gerrit-Owner: Riza Suminto <[email protected]> Gerrit-Reviewer: Bikramjeet Vig <[email protected]> Gerrit-Reviewer: Impala Public Jenkins <[email protected]> Gerrit-Reviewer: Joe McDonnell <[email protected]> Gerrit-Reviewer: Quanlong Huang <[email protected]> Gerrit-Reviewer: Riza Suminto <[email protected]> Gerrit-Comment-Date: Tue, 13 Apr 2021 19:07:49 +0000 Gerrit-HasComments: Yes
