<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Sorry, I don't quite understand what you mean by first error was
earlier?<br>
<br>
Yes, symbols are on and I found the crash-related part in the log
file. See it attached. <br>
<br>
Regards,<br>
Alexander<br>
<br>
On 09.01.2012 12:51, Jed Brown wrote:
<blockquote
cite="mid:CAM9tzSkik2jPhcKuMO4S06Z8d14i-wWMWx8+3FtfLQhycGE2eg@mail.gmail.com"
type="cite">
<p>The first error was likely earlier.</p>
<p>Do you have debugging symbols turned on?</p>
<p>Valgrind has options to write exception files for false
positives. MPICH is usually valgrind-clean while Open MPI is
quite noisy.</p>
<p>I will look at the log when I have a computer.</p>
<div class="gmail_quote">On Jan 9, 2012 5:47 AM, "Alexander
Grayver" <<a moz-do-not-send="true"
href="mailto:agrayver@gfz-potsdam.de">agrayver@gfz-potsdam.de</a>>
wrote:<br type="attribution">
<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt
0.8ex; border-left: 1px solid rgb(204, 204, 204);
padding-left: 1ex;">
<div bgcolor="#ffffff" text="#000000"> Hi Jed,<br>
<br>
On 09.01.2012 12:34, Jed Brown wrote:
<blockquote type="cite">
<div class="gmail_quote">On Mon, Jan 9, 2012 at 05:23,
Alexander Grayver <span dir="ltr"><<a
moz-do-not-send="true"
href="mailto:agrayver@gfz-potsdam.de"
target="_blank">agrayver@gfz-potsdam.de</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin: 0pt 0pt
0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204);
padding-left: 1ex;">
<div>I run petsc-dev like that:<br>
mpirun -n 2 /home/solveTest -ksp_view -ksp_monitor
-ksp_converged_reason -ksp_monitor_true_residual
-log_summary -mat_type mpiaij -ksp_rtol 1.0e-12<br>
<br>
</div>
</blockquote>
<div>[...] </div>
<blockquote class="gmail_quote" style="margin: 0pt 0pt
0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204);
padding-left: 1ex;">
<div> But just switching to one process (-n 1) makes
it crashing:<br>
</div>
</blockquote>
<div><br>
</div>
<div>Try removing the "-mat_type mpiaij" part. Note that
you can still use "-mat_type aij". Also note that you
should usually use a prefix so that you are setting
the type of a specific matrix instead of setting the
type of all matrices (for which MatSetFromOptions() is
called).</div>
</div>
</blockquote>
<br>
There is only one matrix in application. It is very simple
one, the test just loads system matrix and rhs and solves
system. I want to use it to test different
solvers/preconditioners.<br>
<br>
<blockquote type="cite">
<div class="gmail_quote">
<div> </div>
<blockquote class="gmail_quote" style="margin: 0pt 0pt
0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204);
padding-left: 1ex;">
<div> <br>
[0]PETSC ERROR:
------------------------------------------------------------------------<br>
[0]PETSC ERROR: Caught signal number 11 SEGV:
Segmentation Violation, probably memory access out
of range</div>
</blockquote>
</div>
<br>
<div>Please run with valgrind --db-attach=yes (or at least
a debugger) to get a stack trace.</div>
</blockquote>
<br>
This is the stack trace:<br>
<br>
zdotc, FP=7fffa35afce0<br>
VecNorm_Seq, FP=7fffa35afe40<br>
VecNorm, FP=7fffa35aff80<br>
VecNormalize, FP=7fffa35b0080<br>
GMREScycle, FP=7fffa35b02e0<br>
KSPSolve_GMRES, FP=7fffa35b0390<br>
KSPSolve, FP=7fffa35b1ef0<br>
main, FP=7fffa35b31d0<br>
<br>
It crashes here:<br>
<br>
PetscFunctionBegin;<br>
if (type == NORM_2 || type == NORM_FROBENIUS) {<br>
ierr = VecGetArrayRead(xin,&xx);CHKERRQ(ierr);<br>
*z = BLASdot_(&bn,xx,&one,xx,&one); //
<<<< crash<br>
<br>
The log from valgrind is attached, but it is completely
filled with stupid MPI messages. How could one filter out
all that stuff? <br>
<br>
Regards,<br>
Alexander<br>
</div>
</blockquote>
</div>
</blockquote>
<br>
</body>
</html>