Alexey Serbin has posted comments on this change. ( http://gerrit.cloudera.org:8080/16063 )
Change subject: [util] improved performance of BlockingQueue ...................................................................... Patch Set 5: (3 comments) http://gerrit.cloudera.org:8080/#/c/16063/5//COMMIT_MSG Commit Message: http://gerrit.cloudera.org:8080/#/c/16063/5//COMMIT_MSG@20 PS5, Line 20: Before this patch: > Nice improvement! I'm curious: did you get a sense for which of the deque v As for the blocking_queue-test, I don't think the move improvement was the main contributing factor. The test uses uin64_t type as the element type, so the methods used there are const reference ones, which existed before the patch. In addition, I verified that re-jiggling of the sequence sending/broadcasting on condition variables and releasing the lock is not crucial either (I returned std::list back and ran the test, and the results looked exactly like the pre-patch ones). http://gerrit.cloudera.org:8080/#/c/16063/5/src/kudu/consensus/log.cc File src/kudu/consensus/log.cc: http://gerrit.cloudera.org:8080/#/c/16063/5/src/kudu/consensus/log.cc@845 PS5, Line 845: entry_batch_raw > If we've already transferred ownership of the unique_ptr to the blocking qu Right, here the pointer servers as ID for the trace, and in the trace it's represented as uint64_t/uintptr_t (basically, the address). I added a comment. http://gerrit.cloudera.org:8080/#/c/16063/5/src/kudu/util/blocking_queue.h File src/kudu/util/blocking_queue.h: http://gerrit.cloudera.org:8080/#/c/16063/5/src/kudu/util/blocking_queue.h@145 PS5, Line 145: #if 0 > Remove? Done -- To view, visit http://gerrit.cloudera.org:8080/16063 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: kudu Gerrit-Branch: master Gerrit-MessageType: comment Gerrit-Change-Id: Ie80620e5e86cd72c29320096dcdcc712eea1b0f2 Gerrit-Change-Number: 16063 Gerrit-PatchSet: 5 Gerrit-Owner: Alexey Serbin <aser...@cloudera.com> Gerrit-Reviewer: Alexey Serbin <aser...@cloudera.com> Gerrit-Reviewer: Andrew Wong <aw...@cloudera.com> Gerrit-Reviewer: Bankim Bhavsar <ban...@cloudera.com> Gerrit-Reviewer: Kudu Jenkins (120) Gerrit-Reviewer: Todd Lipcon <t...@apache.org> Gerrit-Comment-Date: Fri, 12 Jun 2020 05:06:20 +0000 Gerrit-HasComments: Yes