Dan Hecht has posted comments on this change. Change subject: IMPALA-4862: make resource profile consistent with backend behaviour ......................................................................
Patch Set 14: (2 comments) http://gerrit.cloudera.org:8080/#/c/7223/14/common/thrift/Frontend.thrift File common/thrift/Frontend.thrift: PS14, Line 401: node thanks, this is clearer, though now I see that maybe "node" is ambigious (could mean "host" i.e. node of the cluster). Maybe we should say "operator" instead? Though is this accurate? It looks like this value incorporates the number of fragment instances, so I'm still not 100% sure I understand this. i.e. it doesn't seem to match the computation in Planner.computeResourceReqs(). http://gerrit.cloudera.org:8080/#/c/7223/14/fe/src/main/java/org/apache/impala/planner/Planner.java File fe/src/main/java/org/apache/impala/planner/Planner.java: PS14, Line 374: fragment.getNumInstances(mtDop) that seems to contradict the comment in the thrift file. -- To view, visit http://gerrit.cloudera.org:8080/7223 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-MessageType: comment Gerrit-Change-Id: I492cf5052bb27e4e335395e2a8f8a3b07248ec9d Gerrit-PatchSet: 14 Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-Owner: Tim Armstrong <[email protected]> Gerrit-Reviewer: Alex Behm <[email protected]> Gerrit-Reviewer: Dan Hecht <[email protected]> Gerrit-Reviewer: Tim Armstrong <[email protected]> Gerrit-HasComments: Yes
