<div dir="ltr"><div><div>Hi Jed,<br><br></div>Yes. It has been running fine for problems up to 3M triangles.<br></div><div>/var/log/messages does say that the process is killed.<br></div><div><br></div><div>Changed the oom options to allow over-commiting. I think it<br>
should work now.<br><br></div><div>Thanks.<br>-<br></div><div>Garnet<br></div><div><br></div><div><br></div><br><br></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Tue, Jul 9, 2013 at 3:57 PM, Jed Brown <span dir="ltr"><<a href="mailto:jedbrown@mcs.anl.gov" target="_blank">jedbrown@mcs.anl.gov</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im">Garnet Vaz <<a href="mailto:garnet.vaz@gmail.com">garnet.vaz@gmail.com</a>> writes:<br>
<br>
> Hi Jed,<br>
><br>
> Thanks. The output of quota reads "unlimited".<br>
> The system memory is 16GB.<br>
><br>
> Doing "ulimit -m" gives 13938212<br>
> in kilobytes which corresponds to 13GB. I think this means<br>
> that I should be able to use most of it. I am the only person<br>
> running jobs on this machine right now.<br>
><br>
> I can run with -memory_info for the smaller problem and try<br>
> to extrapolate. Is this a good idea?<br>
<br>
</div>You can. Does it run correctly for smaller problem sizes? Look at<br>
-log_summary for memory usage information. The OOM killer seems the<br>
most likely culprit.<br>
</blockquote></div><br><br clear="all"><br>-- <br>Regards,<div>Garnet</div>
</div>