<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p><font face="Times New Roman">WIEN2k 18.2 usersguide (pg. 237)
has:</font></p>
<p><font face="Times New Roman">USE_REMOTE [0|1] determines whether
parallel jobs are run in background (on shared memory machines)
or using ssh.<br>
</font></p>
<p>Since you are utilizing ssh-copy-id for using ssh, you most
likely need USE_REMOTE=1 [
<a class="moz-txt-link-freetext" href="https://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/msg17572.html">https://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/msg17572.html</a>
].</p>
<p>"permission_denied, please try again" might come from failed
password entry as seen at:<br>
</p>
<p><a class="moz-txt-link-freetext" href="https://askubuntu.com/questions/315377/ssh-error-permission-denied-please-try-again">https://askubuntu.com/questions/315377/ssh-error-permission-denied-please-try-again</a></p>
<p>In your .machines, you have hostname for each of your nodes. You
don't mention what they are called, but say they are called node1,
node2, ..., etc.</p>
<p>Try to ssh into each of the nodes listed in your .machines file
from your head node:</p>
ssh node1<br>
exit<br>
ssh node2<br>
exit<br>
...<br>
<p>That might help you find which nodes the "permission_denied,
please try again" is occurring with.</p>
<p>Maybe less likely the issue, but it might also be that you need
compute node to compute node keys setup [
<a class="moz-txt-link-freetext" href="https://users.open-mpi.narkive.com/mtYcZsVm/ompi-users-problem-with-connecting-to-3-or-more-nodes">https://users.open-mpi.narkive.com/mtYcZsVm/ompi-users-problem-with-connecting-to-3-or-more-nodes</a>
], for example, you may need to check ssh from node 1 to node 2
(and so on):<br>
</p>
ssh node1<br>
ssh node2<br>
...<br>
exit<br>
exit<br>
...<br>
<p>If you have issues with passwordless login using SSH keys, the
following webpages might help:<br>
</p>
<a class="moz-txt-link-freetext" href="https://www.tecmint.com/ssh-passwordless-login-using-ssh-keygen-in-5-easy-steps/">https://www.tecmint.com/ssh-passwordless-login-using-ssh-keygen-in-5-easy-steps/</a><br>
<a class="moz-txt-link-freetext" href="https://www.ssh.com/ssh/copy-id">https://www.ssh.com/ssh/copy-id</a>
<p>The "1: hostname hostname" I'm not sure how that behaves. I
suggest using the format:</p>
<p>1:hostname:1</p>
<p>like for example at links:</p>
<a class="moz-txt-link-freetext" href="https://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/msg17110.html">https://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/msg17110.html</a><br>
<a class="moz-txt-link-freetext" href="http://www.wien2k.at/reg_user/faq/ecss_hliu_051012.pdf">http://www.wien2k.at/reg_user/faq/ecss_hliu_051012.pdf</a> (for example
on slide 7, 3:gamma:2)<br>
<p><br>
</p>
<div class="moz-cite-prefix">On 5/6/2019 6:23 AM, <a class="moz-txt-link-abbreviated" href="mailto:webfinder@ukr.net">webfinder@ukr.net</a>
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:1557143990.546524100.8qazfqwt@frv55.fwdcdn.com">
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<span style="display:block;" class="xfm_34425334">Dear wien2k
users,
<div><br>
</div>
<div>wien2k_18.2</div>
<div>I'm trying to run a test task on a cluster with slurm batch
system using mpi parallelization.</div>
<div><br>
</div>
<div>In "parallel_options" USE_REMOTE=0, MPI_REMOTE=0.</div>
<div>(during the siteconfig_lapw the slurm option was chosen)</div>
<div><br>
</div>
<div>the k-point parallelization works well. But if I change the
"slurm.job" script to produce .machines file for mpi run</div>
<div>(e.g. from </div>
<div>1: hostname</div>
<div>1: hostname</div>
<div>....</div>
<div>to</div>
<div>1: hostname hostname ....)</div>
<div><br>
</div>
<div>there is always a error message: </div>
<div>permission_denied, please try again.</div>
<div>permission_denied, please try again</div>
<div>permission_denied, please try again (....)<br>
</div>
<div><br>
</div>
<div>How can I solve this?</div>
<div>How could it be that k-point parallelization works but mpi
not?</div>
<div><br>
</div>
<div>P.S. I have also tried after getting "nodelist" from batch
system to include ssh-copy-id command to slurm.job script to
copy the keys but the result is the same.</div>
<div><br>
</div>
<div>Thank you for the answers!</div>
</span></blockquote>
<br>
<blockquote type="cite"
cite="mid:1557143990.546524100.8qazfqwt@frv55.fwdcdn.com">
</blockquote>
</body>
</html>