Dan Hecht has posted comments on this change. Change subject: IMPALA-3203: Part 1: Free list implementation ......................................................................
Patch Set 6: (3 comments) http://gerrit.cloudera.org:8080/#/c/6410/4/be/src/benchmarks/free-lists-benchmark.cc File be/src/benchmarks/free-lists-benchmark.cc: PS4, Line 58: > Added a comment to explain - it's the number of passes we do over the memor Sure, a comment explaining it is fine. It just wasn't clear without reading all the benchmark code. http://gerrit.cloudera.org:8080/#/c/6410/6/be/src/benchmarks/free-lists-benchmark.cc File be/src/benchmarks/free-lists-benchmark.cc: Line 58: // what conclusion should we draw from this benchmark if we end up memory bound much earlier than the normal 2MB buffer size? http://gerrit.cloudera.org:8080/#/c/6410/6/be/src/runtime/bufferpool/buffer-allocator.cc File be/src/runtime/bufferpool/buffer-allocator.cc: PS6, Line 37: BufferPool::BufferHandle buffer how does the caller know it must do a move() here? i.e. what prevents the caller from holding on to a dangling buffer.data reference? -- To view, visit http://gerrit.cloudera.org:8080/6410 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-MessageType: comment Gerrit-Change-Id: Ia89acfa4efdecb96d3678443b4748932b4133b9b Gerrit-PatchSet: 6 Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-Owner: Tim Armstrong <[email protected]> Gerrit-Reviewer: Dan Hecht <[email protected]> Gerrit-Reviewer: Jim Apple <[email protected]> Gerrit-Reviewer: Tim Armstrong <[email protected]> Gerrit-HasComments: Yes
