Build failed in Jenkins: Aurora #342

See -- [...truncated 3098 lines...] Ignoring header in: src/test/java/org/apache/aurora/scheduler/storage/backup/RecoveryTest.java Ignoring header in: src/test/java/org/apache/aurora/scheduler/storage/backup/Stor

Re: [jira] [Commented] (AURORA-366) ScheduledThreadPoolExecutor in AsyncModule does not log unhandled errors.

Hm... Does not repro locally. Looking. On Wed, Apr 30, 2014 at 12:26 PM, Bhuvan Arumugam (JIRA) wrote: > > [ > https://issues.apache.org/jira/browse/AURORA-366?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13985955#comment-13985955] > > Bhuvan Arumuga

Fwd: protecting mesos from fat fingers

+aurora dev list There are many mechanisms built into Aurora to prevent these scenarios, you may want to reach out to them for insight. We have discussed some API rate limiting within Mesos, but this is near the limit of policy that Mesos could enforce, as we don't understand the semantics of the

Aurora grabbing resources even when not scheduling

We observed that Aurora's CPU share in Mesos Master dashboard spikes upto 100%, even when Aurora is not running any Job. Looking at the code, I figured that scheduler holds on to the resourceOffers, even if there are no tasks to be scheduled and doesn't decline the offer immediately. It looks like

Re: Aurora grabbing resources even when not scheduling

Aurora holds offers for a few reasons: - To avoid blocking the mesos driver callback thread while matching offers to pending tasks - To enable preemption (determine whether cluster resources are exhausted, and a low priority task should be evicted for a high priority one) - To perform optimize sche

Jenkins build is back to normal : Aurora #343

See