<div class="gmail_quote">On Fri, Jun 8, 2012 at 3:11 PM, Dave Goodell <span dir="ltr"><<a href="mailto:goodell@mcs.anl.gov" target="_blank">goodell@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">> ==29174== 15 bytes in 1 blocks are still reachable in loss record 1 of 1<br>
> ==29174== at 0x4C274A8: malloc (vg_replace_malloc.c:236)<br>
> ==29174== by 0x410927: ??? (in /usr/bin/mpiexec.hydra)<br>
> ==29174== by 0x40205A: ??? (in /usr/bin/mpiexec.hydra)<br>
> ==29174== by 0x548AC4C: (below main) (libc-start.c:226)<br>
<br>
</div>This stack trace indicates that there is a small leak (possibly harmless) in libc, not in any of the actual hydra (mpiexec) code.</blockquote><div><br></div><div>Isn't this pointing to a static constructor?</div>
<div><br></div><div>FWIW, I get the following, though it's almost certainly harmless.</div><div><br></div><div><div>==17609== 131,120 bytes in 2 blocks are still reachable in loss record 1 of 1</div><div>==17609== at 0x4C2B8A4: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)</div>
<div>==17609== by 0x41FC41: HYDU_sock_forward_stdio (in /home/jed/usr/mpich-gcc/bin/mpiexec.hydra)</div><div>==17609== by 0x42D62B: HYDT_bscu_stdio_cb (in /home/jed/usr/mpich-gcc/bin/mpiexec.hydra)</div><div>==17609== by 0x42ADE7: HYDT_dmxu_poll_wait_for_event (in /home/jed/usr/mpich-gcc/bin/mpiexec.hydra)</div>
<div>==17609== by 0x40AE98: HYD_pmci_wait_for_completion (in /home/jed/usr/mpich-gcc/bin/mpiexec.hydra)</div><div>==17609== by 0x40431E: main (in /home/jed/usr/mpich-gcc/bin/mpiexec.hydra)</div><div>==17609== </div>
<div>==17609== LEAK SUMMARY:</div><div>==17609== definitely lost: 0 bytes in 0 blocks</div><div>==17609== indirectly lost: 0 bytes in 0 blocks</div><div>==17609== possibly lost: 0 bytes in 0 blocks</div><div>==17609== still reachable: 131,120 bytes in 2 blocks</div>
<div>==17609== suppressed: 0 bytes in 0 blocks</div></div><div><br></div></div>