I made the change. It was PR #35. People were on board with it back when it was accepted, but if it's forking, then I agree we should just get rid of it. After that was put it, another issue crept up as it was found that the command that it calls doesn't even always return the same format on every system. I guess that's the risk you run when making system calls. I support killing it.<br>
<br>Britton<br><br><div class="gmail_quote">On Wed, May 9, 2012 at 8:37 PM, John Wise <span dir="ltr"><<a href="mailto:jwise@physics.gatech.edu" target="_blank">jwise@physics.gatech.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi Matt and Geoffrey,<br>
<br>
If you're talking to this John, I didn't make that change. I think Britton made that change in changeset ab0e7664f75d.<br>
<br>
But if popen() creates forks, I'd -1 on this being default, also because it causes problems in some MPI implementations, as Geoffrey has found out the hard way!<br>
<br>
John<div class="HOEnZb"><div class="h5"><br>
<br>
On 05/09/2012 08:23 PM, Matthew Turk wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi Geoffrey,<br>
<br>
Grepping through the yt codebase, I think the most likely culprit is<br>
that get_memory_usage (which I believe gets called often during<br>
parallel HOP) falls back on calling popen, which results in a fork. I<br>
think John might have added this. I am -1 on this being default<br>
behavior, and +1 on changing fallback (by default) to just return 0 if<br>
it can't get memory information from the resource module, and maybe<br>
governing this with a config parameter. John, what do you think?<br>
<br>
-MAtt<br>
<br>
On Wed, May 9, 2012 at 7:46 PM, Geoffrey So<<a href="mailto:gsiisg@gmail.com" target="_blank">gsiisg@gmail.com</a>> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
I got this warning message when running paralllel HOP, which I guess was<br>
there before but never noticed before because it's close to the top (usually<br>
looking at the bottom of the logs). I was wondering if there's anything I<br>
need to worry about?<br>
<br>
------------------------------<u></u>------------------------------<u></u>--------------<br>
An MPI process has executed an operation involving a call to the<br>
"fork()" system call to create a child process. Open MPI is currently<br>
operating in a condition that could result in memory corruption or<br>
other system errors; your MPI job may hang, crash, or produce silent<br>
data corruption. The use of fork() (or system() or other calls that<br>
create child processes) is strongly discouraged.<br>
<br>
The process that invoked fork was:<br>
<br>
Local host: lens51 (PID 6818)<br>
MPI_COMM_WORLD rank: 323<br>
<br>
If you are *absolutely sure* that your application will successfully<br>
and correctly survive a call to fork(), you may disable this warning<br>
by setting the mpi_warn_on_fork MCA parameter to 0.<br>
------------------------------<u></u>------------------------------<u></u>--------------<br>
[lens6:19012] 447 more processes have sent help message help-mpi-runtime.txt<br>
/ mpi_init:warn-fork<br>
[lens6:19012] Set MCA parameter "orte_base_help_aggregate" to 0 to see all<br>
help / error messages<br>
[lens6:19012] 32 more processes have sent help message help-mpi-runtime.txt<br>
/ mpi_init:warn-fork<br>
[lens6:19012] 32 more processes have sent help message help-mpi-runtime.txt<br>
/ mpi_init:warn-fork<br>
<br>
From<br>
G.S.<br>
<br>
______________________________<u></u>_________________<br>
yt-users mailing list<br>
<a href="mailto:yt-users@lists.spacepope.org" target="_blank">yt-users@lists.spacepope.org</a><br>
<a href="http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org" target="_blank">http://lists.spacepope.org/<u></u>listinfo.cgi/yt-users-<u></u>spacepope.org</a><br>
<br>
</blockquote>
______________________________<u></u>_________________<br>
yt-users mailing list<br>
<a href="mailto:yt-users@lists.spacepope.org" target="_blank">yt-users@lists.spacepope.org</a><br>
<a href="http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org" target="_blank">http://lists.spacepope.org/<u></u>listinfo.cgi/yt-users-<u></u>spacepope.org</a><br>
</blockquote>
<br></div></div><span class="HOEnZb"><font color="#888888">
-- <br>
John Wise<br>
Assistant Professor of Physics<br>
Center for Relativistic Astrophysics, Georgia Tech</font></span><div class="HOEnZb"><div class="h5"><br>
______________________________<u></u>_________________<br>
yt-users mailing list<br>
<a href="mailto:yt-users@lists.spacepope.org" target="_blank">yt-users@lists.spacepope.org</a><br>
<a href="http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org" target="_blank">http://lists.spacepope.org/<u></u>listinfo.cgi/yt-users-<u></u>spacepope.org</a><br>
</div></div></blockquote></div><br>