Tim Armstrong has posted comments on this change. Change subject: IMPALA-4026: Implement double-buffering for BlockingQueue ......................................................................
Patch Set 5: Code-Review+1 (3 comments) http://gerrit.cloudera.org:8080/#/c/4350/5/be/src/util/blocking-queue.h File be/src/util/blocking-queue.h: PS5, Line 75: NotitfyAll NotifyAll(). PS5, Line 98: This may : // imply that some writers may be sleeping on a partially empty queue Maybe "If this race occurs, a writer can stay blocked on a partially empty queue until the next BlockingGet() call." And I think it would be clearer if the consequence of the race was explained before why it was benign. PS5, Line 99: Given the major : // use case is with HDFS scan node which has multiple producers and one consumer, it's : // expected that some producers can make progress. Maybe more simply: "This should only occur when producers are faster than consumers, so is unlikely to affect overall throughput". -- To view, visit http://gerrit.cloudera.org:8080/4350 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-MessageType: comment Gerrit-Change-Id: Ib9f4cf351455efefb0f3bb791cf9bc82d1421d54 Gerrit-PatchSet: 5 Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-Owner: Michael Ho <[email protected]> Gerrit-Reviewer: Alex Behm <[email protected]> Gerrit-Reviewer: Chen Huang <[email protected]> Gerrit-Reviewer: Dan Hecht <[email protected]> Gerrit-Reviewer: Michael Ho <[email protected]> Gerrit-Reviewer: Mostafa Mokhtar <[email protected]> Gerrit-Reviewer: Tim Armstrong <[email protected]> Gerrit-HasComments: Yes
