[ https://issues.apache.org/jira/browse/YARN-8059?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Yufei Gu updated YARN-8059: --------------------------- Description: Method Fairscheduler#shouldAttemptPreemption doesn't consider resources other than vcore and memory. We may need to rethink it in the resource type scenario. {code} if (context.isPreemptionEnabled()) { return (context.getPreemptionUtilizationThreshold() < Math.max( (float) rootMetrics.getAllocatedMB() / getClusterResource().getMemorySize(), (float) rootMetrics.getAllocatedVirtualCores() / getClusterResource().getVirtualCores())); } {code} was: Method Fairscheduler#shouldAttemptPreemption doesn't consider resources other than vcore and memory. We may need to rethink it. {code} if (context.isPreemptionEnabled()) { return (context.getPreemptionUtilizationThreshold() < Math.max( (float) rootMetrics.getAllocatedMB() / getClusterResource().getMemorySize(), (float) rootMetrics.getAllocatedVirtualCores() / getClusterResource().getVirtualCores())); } {code} > Resource type is ignored when FS decide to preempt > -------------------------------------------------- > > Key: YARN-8059 > URL: https://issues.apache.org/jira/browse/YARN-8059 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler > Affects Versions: 3.0.0 > Reporter: Yufei Gu > Priority: Major > > Method Fairscheduler#shouldAttemptPreemption doesn't consider resources other > than vcore and memory. We may need to rethink it in the resource type > scenario. > {code} > if (context.isPreemptionEnabled()) { > return (context.getPreemptionUtilizationThreshold() < Math.max( > (float) rootMetrics.getAllocatedMB() / > getClusterResource().getMemorySize(), > (float) rootMetrics.getAllocatedVirtualCores() / > getClusterResource().getVirtualCores())); > } > {code} -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org