[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[condor-users] Speeding up DAGman submits


we are submitting a small DAG with very few jobs to DAGman (test jobs such as ls) and noticed
that it takes about 20-25 seconds for the CONDOR job that DAGman submits to the queue to go from the
idle to running state. I've tried to figure out which condor_config file options affect this time (by reading the comments in condor_config and the manual section defining all the parameters), but haven't had much luck. I've also straced and read log files, but this hasn't been particularly informative either.

Some of the ideas I had include:

0) tuning condor_config parameters to speed this up (less than 1-5 seconds is best); haven't been able to find the right tunables
1) using the 'test job feature' for fast turnaround time. Can this be applied to DAGman jobs?
2) Computing on Demand. This is a pretty confusion section of the manual and while the introduction suggests this would be useful,
closer reading of the functionality seems to suggest it's used for running jobs that can be preempted but quickly reactivated when needed;
not exactly a good match to DAGman.

Condor Support Information:
To Unsubscribe, send mail to majordomo@xxxxxxxxxxx with
unsubscribe condor-users <your_email_address>