<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">Hi,<div><br></div><div><div><div>Le 19 janv. 2012 à 21:54, Darius Buntinas 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; font-size: medium; "><br>You were right about the bogus characters after "description#". Try applying this patch to the MPICH2 source, then do a "make clean" followed by "make" and "make install", then recompile your app and see if it helps.</span></blockquote></div><div><br></div><div>Goods news, it works ! thank you very very much</div><div>Now I can run a test between 2 machines with high number of tasks like this request :</div><div><br></div><div><div style="font-size: 14px; ">>mpiexec -iface eth2 -f /tmp/machines -n 255 bin/advance_test</div><div style="font-size: 14px; ">bchambon@ccwpge0062's password: </div><div style="font-size: 14px; ">I am there </div><div style="font-size: 14px; ">Running MPI version 2, subversion 2 </div><div style="font-size: 14px; ">ref_message is ready </div><div style="font-size: 14px; ">I am the master task 0 sur ccwpge0061, for 254 slaves tasks, we will exchange a buffer of 10 MB</div><div style="font-size: 14px; "><br></div><div style="font-size: 14px; ">slave number 1, iteration = 1</div><div style="font-size: 14px; ">slave number 2, iteration = 1</div><div style="font-size: 14px; ">slave number 3, iteration = 1</div><div style="font-size: 14px; ">slave number 4, iteration = 1</div><div style="font-size: 14px; ">slave number 5, iteration = 1</div><div style="font-size: 14px; ">slave number 6, iteration = 1</div><div style="font-size: 14px; ">slave number 7, iteration = 1</div><div style="font-size: 14px; ">…</div></div><div><br></div><div>dstat on the second machine (eth2 : 10Gb/s ~= 1GB/s)</div><div style="font-size: 14px; "><br></div><div style="font-size: 14px; ">> dstat -n -N eth0,eth2</div><div style="font-size: 14px; ">--net/eth0- --net/eth2-</div><div style="font-size: 14px; "> recv send: recv send</div><div style="font-size: 14px; "> 262B 134B:1049M 2427k</div><div style="font-size: 14px; "> 402B 402B:1049M 2427k</div><div style="font-size: 14px; "> 198B 884B:1046M 2422k</div><div style="font-size: 14px; "> 436B 134B:1047M 2420k</div><div style="font-size: 14px; "> 134B 134B:1041M 2406k</div><div style="font-size: 14px; "><br></div><div style="font-size: 14px; "><br></div><div style="font-size: 17px; "><br></div><div style="font-size: 17px; ">Next step, test jobs thru GridEngine + hydra.</div><div style="font-size: 17px; "> It seems to work but sometimes I got timeout (*) like </div><div style="font-size: 15px; "><i>error: got no connection within 60 seconds. "Timeout occured while waiting for connection"</i></div><div style="font-size: 17px; "><br></div><div style="font-size: 17px; ">Is there such a timeout related to hydra I could increase ?</div><div style="font-size: 17px; ">(I mean SMPD_SHORT_TIMEOUT (=60) in src/pm/smpd/smpd.h) or not ?</div><div style="font-size: 17px; "><br></div><div style="font-size: 17px; ">Thank you again for taking times for my troubles</div><div style="font-size: 17px; ">Regards</div><div style="font-size: 17px; "><br></div><div style="font-size: 17px; ">(*) probably due to test on worker nodes running other jobs (production farm)</div><div style="font-size: 17px; ">
<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: 17px; "></div></body></html>