<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><span class="Apple-style-span" style="font-size: 15px; ">Hello,</span><div style="font-size: 15px; "><br><div><div>Le 27 déc. 2011 à 06:48, Pavan Balaji a écrit :</div><br class="Apple-interchange-newline"><blockquote type="cite"><span class="Apple-style-span" style="border-collapse: separate; font-family: Courier; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; 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; "><br>This is not an MPD vs. Hydra issue, but something that went wrong in the new release of MPICH2. Can you tell us which versions you can reproduce the performance degradation with and file a ticket for it?<br></span></blockquote><br></div><div><div>No I can't reproduce the performance degradation.</div><div>I think that it was a wrong interpretation from myself</div><div><br></div><div>I apologize for this wrong information</div></div><div><br></div><div><br></div>I have rerun the same code, compiled with gcc (4.1.x), and I can't get higher numbers with gcc than icc.</div><div style="font-size: 15px; "><br></div><div style="font-size: 15px; ">and with gcc, I'm not so far from the eth2 limit (~1GB/s)</div><div style="font-size: 15px; "><br></div><div style="font-size: 13px; ">> dstat -n -N eth0,eth2</div><div style="font-size: 13px; ">--net/eth0- --net/eth2-</div><div style="font-size: 13px; "> recv send: recv send</div><div style="font-size: 13px; "> 0 0 : 0 0 </div><div style="font-size: 13px; "> 796B 848B:1710k 859M</div><div style="font-size: 13px; "> 340B 134B:1842k 934M</div><div style="font-size: 13px; "> 70B 734B:1647k 827M</div><div style="font-size: 13px; "> 134B 134B:1800k 898M</div><div style="font-size: 13px; "> 326B 209B:1483k 728M</div><div style="font-size: 15px; "><br></div><div style="font-size: 15px; ">Best regards</div><div style="font-size: 15px; "><br></div><div><div style="font-size: 15px; ">
<div><div><div><div><div>---------------<br>Bernard CHAMBON<br>IN2P3 / CNRS<br>04 72 69 42 18<br></div></div></div></div></div>
</div>
<br style="font-size: 15px; "></div></body></html>