[Mauiusers] standing reservation corruption

Ramon Bastiaans ramon.bastiaans at sara.nl
Fri Feb 29 07:04:33 MST 2008


We keep on receiving these errors from maui:

event type: RESERVATIONCORRUPTION:  reservation corruption detected in reservation 'express.0.0'  Req/Detected TC 9/2


This is the standing reservation he is talking about:

# express queue
SRCFG[express]          TASKCOUNT=1 RESOURCES=PROCS:1
SRCFG[express]          STARTTIME=0:00:00 ENDTIME=24:00:00
SRCFG[express]          PERIOD=INFINITY
SRCFG[express]          CLASSLIST=express
SRCFG[express]          NODEFEATURES=express

In our Torque 'nodes' file we have given 1 node the 'express' feature 
and most of the time it seems to work.
However when the cluster gets full, sometimes more than 1 job/task is 
run in the express queue (while the task and proc count is 1 max) and we 
get the 'reservationcorruption' errors. I can't seem to figure out what 
is causing this..

Anyone have any ideas? What does the error "Req/Detected TC 9/2" mean?

This is the queue as setup in Torque:

create queue express
set queue express queue_type = Execution
set queue express resources_max.walltime = 00:20:00
set queue express resources_default.neednodes = express
set queue express resources_default.walltime = 00:20:00
set queue express enabled = True
set queue express started = True

Kind regards,
- Ramon.

-- 
ing. R. Bastiaans

Systems Programmer / High Performance Computing & Visualisation /
SARA                 Computing and Networking Services
Kruislaan 415        PO Box 194613
1098 SJ Amsterdam    1090 GP Amsterdam
P.+31 (0)20 592 3000 F.+31 (0)20 668 3167
---
There are really only three types of people:

  Those who make things happen, those who watch things happen
  and those who say, "What happened?"



More information about the mauiusers mailing list