Tim Armstrong has posted comments on this change. ( http://gerrit.cloudera.org:8080/10256 )
Change subject: PREVIEW - IMPALA-6957: calc thread resource requirement in planner ...................................................................... Patch Set 4: (1 comment) I think we would want to allow rejection based on the per-host value (I'm not sure if that would use an upper bound or the actual max based on the schedule - maybe the first would be more robust), and also based on the global aggregate across fragments. One would protect any single daemon from resource exhaustive, the other would be more useful to protect a cluster from being overwhelmed. http://gerrit.cloudera.org:8080/#/c/10256/4/testdata/workloads/functional-planner/queries/PlannerTest/spillable-buffer-sizing.test File testdata/workloads/functional-planner/queries/PlannerTest/spillable-buffer-sizing.test: http://gerrit.cloudera.org:8080/#/c/10256/4/testdata/workloads/functional-planner/queries/PlannerTest/spillable-buffer-sizing.test@6 PS4, Line 6: Max Per-Host Resource Reservation: Memory=18.97MB Threads=5 > what does the "Max" here refer to? This is the maximum possible if all fragment instances were scheduled on a single backend. -- To view, visit http://gerrit.cloudera.org:8080/10256 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-MessageType: comment Gerrit-Change-Id: I982837ef883457fa4d2adc3bdbdc727353469140 Gerrit-Change-Number: 10256 Gerrit-PatchSet: 4 Gerrit-Owner: Tim Armstrong <[email protected]> Gerrit-Reviewer: Bikramjeet Vig <[email protected]> Gerrit-Reviewer: Dan Hecht <[email protected]> Gerrit-Reviewer: Tim Armstrong <[email protected]> Gerrit-Comment-Date: Mon, 07 May 2018 21:17:45 +0000 Gerrit-HasComments: Yes
