[Chtc-users] Partial HTC power outage


Date: Mon, 21 Sep 2015 13:20:02 -0500
From: chtc-users@xxxxxxxxxxx
Subject: [Chtc-users] Partial HTC power outage
Greetings Users,

We have determined that a unexpected power outage over the weekend temporarily took down a portion of the execute servers that run jobs in our HTCondor Pool. While most jobs running in our HTCondor Pool were completely unaffected by the outage, users of our HTC System may find that some jobs were interrupted and began resuming on a different execute server after HTCondor recovered them. Jobs should notÂhave failed due to the outageÂ(because of HTCondor's recovery mechanisms), and large batches of jobs should eventually complete after interrupted jobs have had a chance to re-run.

Users of our HPC ClusterÂwere completely unaffected by the power outage, as the HPC Cluster is not located in the Computer Sciences building.


As always, questions regarding CHTC's compute system can be sent to chtc@xxxxxxxxxxx

Happy Computing,
Your CHTC Team
[← Prev in Thread] Current Thread [Next in Thread→]
  • [Chtc-users] Partial HTC power outage, chtc-users <=