<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:x="urn:schemas-microsoft-com:office:excel" xmlns:p="urn:schemas-microsoft-com:office:powerpoint" xmlns:a="urn:schemas-microsoft-com:office:access" xmlns:dt="uuid:C2F41010-65B3-11d1-A29F-00AA00C14882" xmlns:s="uuid:BDC6E3F0-6DA3-11d1-A2A3-00AA00C14882" xmlns:rs="urn:schemas-microsoft-com:rowset" xmlns:z="#RowsetSchema" xmlns:b="urn:schemas-microsoft-com:office:publisher" xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet" xmlns:c="urn:schemas-microsoft-com:office:component:spreadsheet" xmlns:odc="urn:schemas-microsoft-com:office:odc" xmlns:oa="urn:schemas-microsoft-com:office:activation" xmlns:html="http://www.w3.org/TR/REC-html40" xmlns:q="http://schemas.xmlsoap.org/soap/envelope/" xmlns:rtc="http://microsoft.com/officenet/conferencing" xmlns:D="DAV:" xmlns:Repl="http://schemas.microsoft.com/repl/" xmlns:mt="http://schemas.microsoft.com/sharepoint/soap/meetings/" xmlns:x2="http://schemas.microsoft.com/office/excel/2003/xml" xmlns:ppda="http://www.passport.com/NameSpace.xsd" xmlns:ois="http://schemas.microsoft.com/sharepoint/soap/ois/" xmlns:dir="http://schemas.microsoft.com/sharepoint/soap/directory/" xmlns:ds="http://www.w3.org/2000/09/xmldsig#" xmlns:dsp="http://schemas.microsoft.com/sharepoint/dsp" xmlns:udc="http://schemas.microsoft.com/data/udc" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:sub="http://schemas.microsoft.com/sharepoint/soap/2002/1/alerts/" xmlns:ec="http://www.w3.org/2001/04/xmlenc#" xmlns:sp="http://schemas.microsoft.com/sharepoint/" xmlns:sps="http://schemas.microsoft.com/sharepoint/soap/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:udcs="http://schemas.microsoft.com/data/udc/soap" xmlns:udcxf="http://schemas.microsoft.com/data/udc/xmlfile" xmlns:udcp2p="http://schemas.microsoft.com/data/udc/parttopart" xmlns:wf="http://schemas.microsoft.com/sharepoint/soap/workflow/" xmlns:dsss="http://schemas.microsoft.com/office/2006/digsig-setup" xmlns:dssi="http://schemas.microsoft.com/office/2006/digsig" xmlns:mdssi="http://schemas.openxmlformats.org/package/2006/digital-signature" xmlns:mver="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns:mrels="http://schemas.openxmlformats.org/package/2006/relationships" xmlns:spwp="http://microsoft.com/sharepoint/webpartpages" xmlns:ex12t="http://schemas.microsoft.com/exchange/services/2006/types" xmlns:ex12m="http://schemas.microsoft.com/exchange/services/2006/messages" xmlns:pptsl="http://schemas.microsoft.com/sharepoint/soap/SlideLibrary/" xmlns:spsl="http://microsoft.com/webservices/SharePointPortalServer/PublishedLinksService" xmlns:Z="urn:schemas-microsoft-com:" xmlns:st="&#1;" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 12 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
        {font-family:"Cambria Math";
        panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0cm;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri","sans-serif";}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:blue;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:purple;
        text-decoration:underline;}
span.EmailStyle17
        {mso-style-type:personal-compose;
        font-family:"Calibri","sans-serif";
        color:windowtext;}
.MsoChpDefault
        {mso-style-type:export-only;}
@page WordSection1
        {size:612.0pt 792.0pt;
        margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
        {page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-AU link=blue vlink=purple><div class=WordSection1><p class=MsoNormal><span lang=EN-US>Hi All,<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span lang=EN-US>I added a basic gpus count information to one of our compute nodes with:<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>qmgr &#8211;c &#8216;s n n121 gpus = 2&#8217;<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>and it seems fine:<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&gt; pbsnodes -a n121<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>n121<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp; &nbsp;&nbsp;state = free<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp;&nbsp;&nbsp; np = 12<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp;&nbsp;&nbsp; ntype = cluster<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp;&nbsp;&nbsp; status = rectime=1328238593,varattr=,jobs=,state=free,size=133709780kb:144492840kb,netload=156768229618,gres=,loadave=2.00,ncpus=24,physmem=99195396kb,availmem=95103784kb,totmem=101299868kb,idletime=173222,nusers=0,nsessions=0,uname=Linux n121 2.6.32.49-0.3-default #1 SMP 2011-12-02 11:28:04 +0100 x86_64,opsys=sles11,arch=x86_64<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp;&nbsp;&nbsp; mom_service_port = 15002<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp;&nbsp;&nbsp; mom_manager_port = 15003<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>&nbsp;&nbsp;&nbsp;&nbsp; gpus = 2<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span lang=EN-US>However when I run a job with the recommended syntax:<o:p></o:p></span></p><p class=MsoNormal><a href="http://www.adaptivecomputing.com/resources/docs/torque/3-0-3/3.7schedulinggpus.php">http://www.adaptivecomputing.com/resources/docs/torque/3-0-3/3.7schedulinggpus.php</a><o:p></o:p></p><p class=MsoNormal>I get:<o:p></o:p></p><p class=MsoNormal><span lang=EN-US>&gt; qsub -I -q viz -l nodes=1:ppn=1:gpus=1<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>qsub: Job exceeds queue resource limits MSG=cannot locate feasible nodes<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span lang=EN-US>The torque version is 3.0.3-snap.201108261653<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span lang=EN-US>Note that this is _<i>not</i>_ the </span><span style='font-size:11.5pt;color:black'>--enable-nvidia-gpus functionality.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'>Also note that the server has not been restarted.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'>The scheduler is moab but I&#8217;m pretty sure the job gets rejected well before moab comes into the picture.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'>Does anyone have such a setup working or can anyone see what is wrong (or have an idea of where to look)?<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'>Regards,<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'><o:p>&nbsp;</o:p></span></p><p class=MsoNormal><span style='font-size:11.5pt;color:black'>Gareth</span><span lang=EN-US><o:p></o:p></span></p></div></body></html>