[ https://issues.apache.org/jira/browse/AURORA-1932?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jordan Ly updated AURORA-1932: ------------------------------ Issue Type: Task (was: Story) > Failure accrual detection mechanism for bad agents > -------------------------------------------------- > > Key: AURORA-1932 > URL: https://issues.apache.org/jira/browse/AURORA-1932 > Project: Aurora > Issue Type: Task > Components: Scheduler > Reporter: Jordan Ly > Assignee: Jordan Ly > > With the introduction of different OfferManager orderings (see > https://reviews.apache.org/r/59480/), we run the risk of repeatedly assigning > the same task to a bad agent. > We should develop some sort of 'failure accrual' mechanism where we can track > how many times tasks fail on a agent. If it reaches some sort of threshold, > we should blacklist that agent for some time so that it can be investigated > and the task can be assigned to a different agent. -- This message was sent by Atlassian JIRA (v6.3.15#6346)