<br><br><div class="gmail_quote">On Sun, May 26, 2013 at 9:09 AM, Andrei Mikhailovsky <span dir="ltr"><<a href="mailto:andrei@arhont.com" target="_blank">andrei@arhont.com</a>></span> wrote:<br><blockquote style="margin:0px 0px 0px 0.8ex;padding-left:1ex;border-left-color:rgb(204,204,204);border-left-width:1px;border-left-style:solid" class="gmail_quote">
<div><div style="font-family:arial,helvetica,sans-serif;font-size:10pt"><br><br><hr><div style="font-family:Helvetica,Arial,sans-serif;font-size:12pt;font-style:normal;font-weight:normal;text-decoration:none"><div class="im">
<b>From: </b>"John Valdes" <<a href="mailto:valdes@anl.gov" target="_blank">valdes@anl.gov</a>><br><b>To: </b>"Andrei Mikhailovsky" <<a href="mailto:andrei@arhont.com" target="_blank">andrei@arhont.com</a>><br>
<b>Cc: </b><a href="mailto:users@lists.openfabrics.org" target="_blank">users@lists.openfabrics.org</a><br></div><b>Sent: </b>Saturday, 25 May, 2013 2:19:40 AM<div class="im"><br><b>Subject: </b>Re: [Users] HP BLc QLogic 4X QDR IB Switch oddness<br>
<br></div><div class="im">Andrei Mikhailovsky wrote:<br>> John Valdes wrote:<br>> > What's the physical topology of the IB network between the blade <br>> > servers and the switch?<br>> <br>> AM: I am not really sure. The servers do have the IB mezzanine card and from what i've read it is a pci-e card. I am unsure how the blade servers are connected to the switch. I guess it's an internal HP/QLogic interconnect. <br>
<br>Found some docs on Intel's website at:<br><a href="http://www.intel.com/p/en_US/support/highlights/network/ts-fbs12100" target="_blank">http://www.intel.com/p/en_US/support/highlights/network/ts-fbs12100</a> <br>From that, it looks like the topology is very simple; the switch<br>
installs in a slot in the blade chassis, and it looks like it has 16<br>internal (through the backplane of the chassis) IB connections, one<br>to each blade server in the chassis, plus 16 external QSFP ports.<br><br><br></div>
AM: yeah, that pretty much sums up the switch<div class="im"><br><br><br><br>I was thinking maybe there was something odd in the topology that<br>was causing the subnet manager to fail to negotiate link properly w/<br>the blade servers. It doesn't sound like that's the case.<br>
<br><br></div>AM: I do not see any logs on the SM side when the port state changes. The only logs I see is when the port becomes Active, I see that in the logs and no errors before or prior to that</div><div style="font-family:Helvetica,Arial,sans-serif;font-size:12pt;font-style:normal;font-weight:normal;text-decoration:none">
</div></div></div></blockquote><div> </div><div>By port state, do you mean port state or port physical state ? Note that there's some relationship between the two but port physical state can change without port state changing. In the opensm log, you should see trap 128 when link (port) state changes. If the port/link is constantly (re)negotiating and doesn't get to LinkUp (port physical state)/Init (port state), you won't see this in the log. If port state is truly changing, you should see this trap in the opensm log.</div>
<div> </div><div>-- Hal<font size="1" face="ArialMT"><font size="1" face="ArialMT"></font></font></div><font size="1" face="ArialMT"><font size="1" face="ArialMT"></font></font><div> </div><blockquote style="margin:0px 0px 0px 0.8ex;padding-left:1ex;border-left-color:rgb(204,204,204);border-left-width:1px;border-left-style:solid" class="gmail_quote">
<div><div style="font-family:arial,helvetica,sans-serif;font-size:10pt"><div style="font-family:Helvetica,Arial,sans-serif;font-size:12pt;font-style:normal;font-weight:normal;text-decoration:none"> </div><br></div></div><br>
_______________________________________________<br>
Users mailing list<br>
<a href="mailto:Users@lists.openfabrics.org">Users@lists.openfabrics.org</a><br>
<a href="http://lists.openfabrics.org/cgi-bin/mailman/listinfo/users" target="_blank">http://lists.openfabrics.org/cgi-bin/mailman/listinfo/users</a><br>
<br></blockquote></div><br>