On Sat, Aug 6, 2011 at 1:34 AM, Debao Shao <span dir="ltr"><<a href="mailto:Debao.Shao@brion.com">Debao.Shao@brion.com</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<u></u>
<div lang="ZH-CN" link="blue" vlink="blue">
<div>
<p class="MsoNormal"><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy">Thanks a lot, Jed and Aron.
<u></u><u></u></span></font></p>
<p class="MsoNormal"><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy"><u></u> <u></u></span></font></p>
<p class="MsoNormal"><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy">Do you have ideas for this problem?<u></u><u></u></span></font></p>
<p class="MsoNormal"><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy"><u></u> <u></u></span></font></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">But I encounter a new problem, the situation is:<u></u><u></u></span></font></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">1, the matrix is big, and can be partitioned to several blocks;<u></u><u></u></span></font></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">2, started several threads to handle each block of matrix;<u></u><u></u></span></font></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">3, integrated all block matrices together.<u></u><u></u></span></font></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:7.5pt"><u></u> <u></u></span></font></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">Again, the program crashed with reporting:
<u></u><u></u></span></font></p>
<p style="layout-grid-mode:char"><u></u><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">"</span></font><u></u><span lang="EN-US">[0]PETSC ERROR: Caught
<font color="red"><span style="color:red">signal number 11 SEGV</span></font>: Segmentation Violation, probably memory access out of range<u></u>"</span></p></div></div></blockquote><div><br></div><div>Yes, PETSc allows threads, but one of your threads is illegally accessing memory. I suggest using valgrind to track this down.</div>
<div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div lang="ZH-CN" link="blue" vlink="blue"><div><p style="layout-grid-mode:char">
<span class="Apple-style-span" style="font-family: 宋体; font-size: 12px; ">My libpetsc.a is built with option
<u></u>"<u></u><font color="red"><span style="color:red">--with-mpi=0</span></font> --with-debugging=0 -with-log=0 -with-info=0<u></u>"<u></u>.</span></p>
<p style="layout-grid-mode:char"><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">Will it support this type of multiple threads?<u></u><u></u></span></font></p>
<p class="MsoNormal"><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy"><u></u> <u></u></span></font></p>
<p class="MsoNormal"><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy">Thanks,<u></u><u></u></span></font></p>
<p class="MsoNormal"><u></u><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy">De</span></font><u></u><font size="1" color="navy" face="Arial"><span lang="EN-US" style="font-size:9.0pt;font-family:Arial;color:navy">bao<u></u><u></u></span></font></p>
<div>
<div class="MsoNormal" align="center" style="text-align:center"><font size="3" face="宋体"><span lang="EN-US" style="font-size:12.0pt">
<hr size="2" width="100%" align="center">
</span></font></div>
<p class="MsoNormal"><b><font size="2" face="Tahoma"><span lang="EN-US" style="font-size:10.0pt;font-family:Tahoma;font-weight:bold">From:</span></font></b><font size="2" face="Tahoma"><span lang="EN-US" style="font-size:10.0pt;font-family:Tahoma"> <a href="mailto:petsc-users-bounces@mcs.anl.gov" target="_blank">petsc-users-bounces@mcs.anl.gov</a>
[mailto:<a href="mailto:petsc-users-bounces@mcs.anl.gov" target="_blank">petsc-users-bounces@mcs.anl.gov</a>] <b><span style="font-weight:bold">On Behalf Of
</span></b>Jed Brown<br>
<b><span style="font-weight:bold">Sent:</span></b> Friday, August 05, 2011 9:26 PM<br>
<b><span style="font-weight:bold">To:</span></b> <u></u>PETSc users list<u></u><br>
<b><span style="font-weight:bold">Subject:</span></b> Re: [petsc-users] PETSC ERROR: Caught signal number 15 Terminate</span></font><span lang="EN-US"><u></u><u></u></span></p>
</div>
<p class="MsoNormal"><font size="3" face="宋体"><span lang="EN-US" style="font-size:12.0pt"><u></u> <u></u></span></font></p>
<div>
<p class="MsoNormal"><font size="3" face="宋体"><span lang="EN-US" style="font-size:12.0pt">On Fri, Aug 5, 2011 at 04:00,
<u></u>De<u></u>bao Shao <<a href="mailto:Debao.Shao@brion.com" target="_blank">Debao.Shao@brion.com</a>> wrote:<u></u><u></u></span></font></p>
<p><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">1, I put <u></u>
"<u></u>PetscInitialize<u></u>"<u></u> at the beginning of main, and
<u></u>"<u></u>PetscInitialize<u></u>"<u></u> registers a signal handler to capture
<u></u>"<u></u>SIGTERM<u></u>"<u></u>;</span></font><span lang="EN-US"><u></u><u></u></span></p>
<p><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">2, the problem ran in server side will send SIGTERM to kill all of clients after one stage is done.</span></font><span lang="EN-US"><u></u><u></u></span></p>
<p><font size="1" face="宋体"><span lang="EN-US" style="font-size:9.0pt">3, then, unfortunately, the signal
<u></u>"<u></u>SIGTERM<u></u>"<u></u> is caught by the signal handler installed by
<u></u>"<u></u>PetscInitialize<u></u>"<u></u>, and caused to abort.</span></font><span lang="EN-US"><u></u><u></u></span></p>
</div>
<div>
<p class="MsoNormal"><font size="3" face="宋体"><span lang="EN-US" style="font-size:12.0pt">You can remove the order dependence by running with -no_signal_handler or setting your own signal handler with:<u></u><u></u></span></font></p>
</div>
<div>
<p class="MsoNormal"><font size="3" face="宋体"><span lang="EN-US" style="font-size:12.0pt"><u></u> <u></u></span></font></p>
</div>
<p class="MsoNormal"><font size="3" face="宋体"><span lang="EN-US" style="font-size:12.0pt"><a href="http://www.mcs.anl.gov/petsc/petsc-as/snapshots/petsc-dev/docs/manualpages/Sys/PetscPushSignalHandler.html" target="_blank">http://www.mcs.anl.gov/petsc/petsc-as/snapshots/petsc-dev/docs/manualpages/Sys/PetscPushSignalHandler.html</a>
<u></u><u></u></span></font></p>
</div>
<br>
<hr>
<font face="Arial" color="Gray" size="1">-- The information contained in this communication and any attachments is confidential and may be privileged, and is for the sole use of the intended recipient(s). Any unauthorized review, use, disclosure or distribution
is prohibited. Unless explicitly stated otherwise in the body of this communication or the attachment thereto (if any), the information is provided on an AS-IS basis without any express or implied warranties or liabilities. To the extent you are relying on
this information, you are doing so at your own risk. If you are not the intended recipient, please notify the sender immediately by replying to this message and destroy all copies of this message and any attachments. ASML is neither liable for the proper and
complete transmission of the information contained in this communication, nor for any delay in its receipt.<br>
</font>
</div>
</blockquote></div><br><br clear="all"><br>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener<br>