<div dir="ltr">Attached! :)<br><div class="gmail_extra"><div><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div><div><br></div></div></div><div>Federico</div></div></div></div></div></div>
<br><div class="gmail_quote">2016-04-06 14:45 GMT+02:00 Cyrill Gorcunov <span dir="ltr"><<a href="mailto:gorcunov@gmail.com" target="_blank">gorcunov@gmail.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">On Wed, Apr 06, 2016 at 02:17:22PM +0200, Federico Reghenzani wrote:<br>
> Hi Cyrill, <br>
> it was a MPI process (1074 was the Open MPI daemon, 1075 and 1076 the MPI<br>
> processes).<br>
> Now it's: 1721 daemon, 1722 first process, 1723 second process. I attached<br>
> the log and maps<br>
<br>
</span>Weird. Federico, could you please attach into the process and show its registers?<br>
<br>
gdb -p 1722<br>
info registers<br>
<br>
and show output. (-p $PID, where $PID is failing task's pid)<br>
</blockquote></div><br></div></div>