Date: | Mon, 5 May 2014 22:23:59 -0400 |
---|---|
From: | Ben Cotton <ben.cotton@xxxxxxxxxxxxxxxxxx> |
Subject: | [HTCondor-devel] Continue a DAG on removing a node? |
One of our customers has a set of thousands of jobs where one or two of them are sometimes edge cases for their application and the results are fine even though the application exits with an error code. Effectively, the job will always go held even though it's safe to continue on with the remaining steps. I thought (hoped) that removing the job would allow the DAG to proceed, but instead it goes to complete. I didn't see much in the manual about this. Is it possible to have DAGman proceed when a job is removed? Is there another way to handle these edge cases? (Preferably automatically or in a way invokable from the CycleServer console) Thanks, BC -- Ben Cotton main: 888.292.5320 Cycle Computing Leader in Utility HPC Software http://www.cyclecomputing.com twitter: @cyclecomputing |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | , (nil) |
---|---|
Next by Date: | Re: [HTCondor-devel] Continue a DAG on removing a node?, Igor Sfiligoi |
Previous by Thread: | , (nil) |
Next by Thread: | Re: [HTCondor-devel] Continue a DAG on removing a node?, Igor Sfiligoi |
Indexes: | [Date] [Thread] |