Tim Armstrong has posted comments on this change. Change subject: IMPALA-4026: Implement double-buffering for BlockingQueue. ......................................................................
Patch Set 3: (8 comments) http://gerrit.cloudera.org:8080/#/c/4350/2/be/src/util/blocking-queue.h File be/src/util/blocking-queue.h: Line 155: > It's always racy as we never hold read_lock when reading the size of read_l Ah, good point. http://gerrit.cloudera.org:8080/#/c/4350/3/be/src/util/blocking-queue.h File be/src/util/blocking-queue.h: PS3, Line 188: put_list shouldn't these members have _ at the end? Line 197: boost::mutex get_lock; Shouldn't we align get_lock? http://gerrit.cloudera.org:8080/#/c/4350/3/be/src/util/condition-variable.h File be/src/util/condition-variable.h: Line 28: /// Simple wrapper around POSIX pthread condition variable. Explain briefly how it differs from the boost cv? PS3, Line 29: struct class? PS3, Line 29: __attribute__ ((aligned(64))) What do you think about putting this in compiler-util.h as CACHE_ALIGN or something along those lines? PS3, Line 61: cv cv_ PS3, Line 62: ConditionVariable This and the typedef shouldn't be necessary in C++, it automatically lets you use the short name of the class/struct. -- 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: 3 Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-Owner: Michael Ho <k...@cloudera.com> Gerrit-Reviewer: Alex Behm <alex.b...@cloudera.com> Gerrit-Reviewer: Chen Huang <paulhuan...@utexas.edu> Gerrit-Reviewer: Dan Hecht <dhe...@cloudera.com> Gerrit-Reviewer: Michael Ho <k...@cloudera.com> Gerrit-Reviewer: Mostafa Mokhtar <mmokh...@cloudera.com> Gerrit-Reviewer: Tim Armstrong <tarmstr...@cloudera.com> Gerrit-HasComments: Yes