Thanks for the pointer Justin!<br><br><div class="gmail_quote">On Thu, Sep 13, 2012 at 10:29 AM, Justin Riley <span dir="ltr"><<a href="mailto:jtriley@mit.edu" target="_blank">jtriley@mit.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
-----BEGIN PGP SIGNED MESSAGE-----<br>
Hash: SHA1<br>
<br>
Hi Jesse,<br>
<br>
Sorry for the delay in responding but glad you figured out to use<br>
all-Ubuntu AMIs for both HVM and non-HVM nodes. With that said keep in<br>
mind that only HVM nodes are on the high speed network IIRC which means<br>
all traffic between master and nodes (e.g. NFS) will be suboptimal<br>
compared to the performance of an all HVM cluster.<br>
<br>
~Justin<br>
<div class="im"><br>
<br>
On 08/27/2012 05:59 PM, Jesse Lu wrote:<br>
> Okay, figured out that using ami-999d49f0 for non-HVM master and<br>
> ami-4583572c for HVM nodes makes SGE work well. It's my fault for<br>
> not looking at the available public starcluster images carefully<br>
> enough.<br>
><br>
><br>
><br>
> On Mon, Aug 27, 2012 at 2:26 PM, Jesse Lu <<a href="mailto:jesselu@stanford.edu">jesselu@stanford.edu</a><br>
</div><div class="im">> <mailto:<a href="mailto:jesselu@stanford.edu">jesselu@stanford.edu</a>>> wrote:<br>
><br>
> Sorry for the spam, but here's another follow-up.<br>
><br>
> I found that this only happens when I use a non HVM-EBS AMI for<br>
> the master, but an HWM-EBS for the master.<br>
><br>
> This is probably because StarCluster copies the sge install from<br>
> the master to the nodes, and this doesn't play nice when the nodes<br>
> are CentOS based but the master is Ubuntu based.<br>
><br>
> Any ideas for a work-around?<br>
><br>
><br>
> On Mon, Aug 27, 2012 at 2:07 PM, Jesse Lu <<a href="mailto:jesselu@stanford.edu">jesselu@stanford.edu</a><br>
</div><div class="im">> <mailto:<a href="mailto:jesselu@stanford.edu">jesselu@stanford.edu</a>>> wrote:<br>
><br>
> Follow-up,<br>
><br>
> Here are the contents of the installation log file (for grid<br>
> engine)<br>
><br>
> cat<br>
> /opt/sge6/default/common/install_logs/execd_install_node001_2012-08-27_14:04:29.log<br>
><br>
><br>
><br>
> Your $SGE_ROOT directory: /opt/sge6<br>
><br>
><br>
> Using cell: >default<<br>
><br>
><br>
><br>
><br>
><br>
> Using local execd spool directory<br>
> [/opt/sge6/default/spool/exec_spool_local]<br>
><br>
> Creating local configuration for host >node001< sgeadmin@node001<br>
> modified "node001" in configuration list Local configuration for<br>
> host >node001< created.<br>
><br>
> Host >master< already in submit host list! Host >node001< already<br>
> in submit host list!<br>
><br>
><br>
> starting sge_execd<br>
><br>
><br>
> No modification because "node001" already exists in "hostlist" of<br>
> "hostgroup" root@node001 modified "@allhosts" in host group list<br>
> root@node001 modified "all.q" in cluster queue list<br>
><br>
> got select error: Connection refused got select error: closing<br>
> "node001/execd/1" Execd on host node001 is not started!<br>
><br>
><br>
> On Mon, Aug 27, 2012 at 1:37 PM, Jesse Lu <<a href="mailto:jesselu@stanford.edu">jesselu@stanford.edu</a><br>
</div><div class="im">> <mailto:<a href="mailto:jesselu@stanford.edu">jesselu@stanford.edu</a>>> wrote:<br>
><br>
> ami-12b6477b produces the folowing error on cluster startup<br>
><br>
> !!! ERROR - command 'cd /opt/sge6 && TERM=rxvt ./inst_sge -x<br>
> -noremote -auto ./ec2_sge.conf' failed with status 1<br>
><br>
> I'm guessing the sge6 installation is faulty? Can anyone help?<br>
> Thanks!<br>
><br>
> Jesse<br>
><br>
><br>
><br>
><br>
><br>
><br>
</div>> _______________________________________________ StarCluster mailing<br>
> list <a href="mailto:StarCluster@mit.edu">StarCluster@mit.edu</a><br>
> <a href="http://mailman.mit.edu/mailman/listinfo/starcluster" target="_blank">http://mailman.mit.edu/mailman/listinfo/starcluster</a><br>
><br>
<br>
-----BEGIN PGP SIGNATURE-----<br>
Version: GnuPG v2.0.19 (GNU/Linux)<br>
Comment: Using GnuPG with Mozilla - <a href="http://enigmail.mozdev.org/" target="_blank">http://enigmail.mozdev.org/</a><br>
<br>
iEYEARECAAYFAlBSF/4ACgkQ4llAkMfDcrlSwwCbB5lJLmj4GY9rriY9jfxNdqO3<br>
s2UAn13+cEYu9bCqx6jiAP/wuPdetm+D<br>
=Dyis<br>
-----END PGP SIGNATURE-----<br>
</blockquote></div><br>