<div>'ncpus' still exists but only in 17 'old' jobs - ones that were submitted before we made the 'unset' change. I guess I should wait until these will end and re-test the system?</div>
<div> </div>
<div>diagnose -n says for example, on node28 :</div>
<div> </div>
<div>node28 Busy 0:4 2926:3950 1:1 3871:7641 1.00 DEFAUL [NONE] DEF 2.19 002 [heavy_2:4][light_4:4][b_que [DEFAULT] [NONE]<br>WARNING: node 'node28' has more processors utilized than dedicated (4 > 2)<br>
----- --- 6:86 72602:98716 26:26 142420:212774<br><br>But this node is running 2 jobs which both does not have 'ncpus' settings if I use qstat -f on them.</div>
<div> </div>
<div>About the MEM requirement: do you mean to unset it to? other than that we don't use any MEM requierment in our qsub script.</div>
<div><br> </div>
<div class="gmail_quote">On Jan 29, 2008 8:13 PM, Jan Ploski <<a href="mailto:Jan.Ploski@offis.de">Jan.Ploski@offis.de</a>> wrote:<br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div class="Ih2E3d"><br><br> </div>I suppose you did check with qstat -f that 'ncpus' is not mentioned<br>anywhere any longer?<br><br>
<div>
<div class="Wj3C7c"><br> </div></div>Maybe it has something to do with the MEM requirement (just a wild<br>guess... but try removing it). What does diagnose -n say for a node<br>which is incorrectly rejecting the job? Does it have enough free<br>
"tokens" (not sure if this is what they are called officially) to run<br>the job in this b_que class?<br><br>Regards,<br><font color="#888888">Jan Ploski<br></font></blockquote></div><br>