<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div apple-content-edited="true"><span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-size: medium; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; "><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">On Dec 12, 2009, at 10:41 AM, <a href="mailto:beowulf-request@beowulf.org">beowulf-request@beowulf.org</a> wrote:</div></span></div><div><br class="Apple-interchange-newline"><blockquote type="cite"><div><br>From: Gus Correa <<a href="mailto:gus@ldeo.columbia.edu">gus@ldeo.columbia.edu</a>><br><br>Hi Amjad<br><br>amjad ali wrote:<br><blockquote type="cite">Hi Gus,<br></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite"> I was told that some people used to run two processes only on<br></blockquote><blockquote type="cite"> dual-socket dual-core Xeon nodes , leaving the other two cores idle.<br></blockquote><blockquote type="cite"> Although it is an apparent waste, the argument was that it paid<br></blockquote><blockquote type="cite"> off in terms of overall efficiency.<br></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite">I guess I fully agree with this.<br></blockquote><blockquote type="cite"><br></blockquote></div></blockquote>The other reason I see folks choose this is licensing. In some cases the "cost" of the license tokens to use the extra cores is too expensive given the minimal benefit since they still compete for Memory Bandwidth, CPU Cache, or less commonly Network Bandwidth/Latency.</div><div>...</div><div><blockquote type="cite"><div><blockquote type="cite"><font class="Apple-style-span" color="#000000"><br></font></blockquote><blockquote type="cite">But still if it is a shared cluster (as in my case) then the cores you<br></blockquote><blockquote type="cite">left unbusy may be allocated to another process of another user by the <br></blockquote><blockquote type="cite">Batch scheduler. Right??<br></blockquote><br>Unless you request full nodes, as Chris Samuel suggested:<br>#PBS -l nodes=10:ppn=8<br><br>However, beware that this greedy and wasteful behavior<br>may drive your system administrator and<br>the other cluster users mad at you! :)<br>Well, you can always justify it in the name of science, of course. ;)<br><br></div></blockquote><div>They may thank you for not sharing a "maxed out" node. If someone is doing benchmarking or running a similarly sensitive code you're saving everyone a lot of head scratching. In my world users sharing nodes is almost always trouble looking for a way to ruin a weekend.</div><br>Cheers!</div><div>Greg</div></body></html>