We get those messages every time we restart maui with jobs in the queues.
But we have not had them cause any crashing.
Tom
Michel Jouvin wrote:
Hi,
We are experience a very serious problem with our MAUI configuration.
Shortly after starting, MAUI crashes almost immediately after starting (let
say in the next 2 minutes generally). This happened suddendly. There was no
configuration changes compared to the previous day where it was running
just fine.
This is not the first time we observed this kind of behaviour. After some
time it is generally back in good shape. I did some strace just after MAUI
starts. I attach one of them with a qstat output and our maui.cfg, along
with maui.log.
Normally log level is 0 but for some unknown reasons it seems that a lot of
INFO messages reappeared (they seemed to be suppressed when we changed log
level from 1 to 0).
There is little information to help in the logs, the main problem being
this kind of message :
04/26 18:31:46 ALERT: job ' 94210' has invalid system queue
time (SQ: 1209219593 > ST: 1209197088)
It is not clear if the crash happens after one of these messages (but for
sure not every time).
Thanks in advance for any help.
Michel
*************************************************************
* Michel Jouvin Email : [EMAIL PROTECTED] *
* LAL / CNRS Tel : +33 1 64468932 *
* B.P. 34 Fax : +33 1 69079404 *
* 91898 Orsay Cedex *
* France *
*************************************************************
------------------------------------------------------------------------
_______________________________________________
mauiusers mailing list
[email protected]
http://www.supercluster.org/mailman/listinfo/mauiusers
_______________________________________________
mauiusers mailing list
[email protected]
http://www.supercluster.org/mailman/listinfo/mauiusers
