[ https://issues.apache.org/jira/browse/IMPALA-3610?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Tim Armstrong resolved IMPALA-3610. ----------------------------------- Resolution: Fixed [~mmokhtar] I'm going to close this one and use IMPALA-6412 to track future work so we have a clean history and have less confusion about which fixes are in which version. I'll add a note here that it didn't fully solve the problem. > Global runtime filters causing unaccounted memory pressure on the coordinator > ----------------------------------------------------------------------------- > > Key: IMPALA-3610 > URL: https://issues.apache.org/jira/browse/IMPALA-3610 > Project: IMPALA > Issue Type: Bug > Components: Backend > Affects Versions: Impala 2.5.0 > Reporter: Mostafa Mokhtar > Assignee: Tim Armstrong > Priority: Critical > Labels: runtime-filters, scalability, scale > Fix For: Impala 2.7.0 > > Attachments: TPC-DS Q25 Bolt 200.txt > > > When running queries on a 1000x node cluster I noticed that the coordinator > memory spikes due to global runtime filters, much of this memory is untracked > and can easily cause the coordinator to the hit process memory limit. -- This message was sent by Atlassian JIRA (v7.6.3#76005)