<div>Hello Amjad,</div>
<div> </div>
<div>You need exclusive access to (part of) the cluster. Generally a batch scheduler is available that will schedule the jobs of multiple users on generally a FIFO basis, guaranteeing exclusive access and thus optimal performance.</div>
<div> </div>
<div> </div>
<div class="gmail_quote">On Thu, Dec 10, 2009 at 2:46 AM, amjad ali <span dir="ltr"><<a href="mailto:amjad11@gmail.com">amjad11@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Hi all,<br><br>I am usually running my parallel jobs on the university cluster of several hundred nodes (accessible to all). So often I observe very different total MPI_Wtime value when I run my program (even of same problem size) on different occasion.<br>
<br>How should I make a reasonable performance measurement in such a case? Is it fine to get speedup/measurements on such a shared cluster?<br><br><br>Thanks.<br><br>_______________________________________________<br>Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank">http://www.beowulf.org/mailman/listinfo/beowulf</a><br><br></blockquote></div><br>